metadata: run_metadata: 960 rows where devstage_curation_coarse = "Undetermined" and tissue_curation

960 rows where devstage_curation_coarse = "Undetermined" and tissue_curation_coarse = "Cancer or Tumor"

descending

Link	rowid ▼	run.accession	experiment.accession	sample.accession	study.accession	bioproject	study.title	study.alias	study.type	study.abstract	study.attributes	study.PMIDs	sample.title	sample.alias	sample.attributes	GEOsample.title	GEOsample.dataprocessing	GEOsample.source	GEOsample.treatmentprotocol	GEOsample.extractprotocol	GEOsample.growthprotocol	GEOsample.characteristics	GEOsample.accession	experiment.title	experiment.alias	experiment.library_name	experiment.design_description	experiment.library_construction_protocol	experiment.attributes	experiment.library_strategy	experiment.library_source	experiment.library_selection	experiment.library_layout	experiment.platform	experiment.instrument_model	experiment.study_ref	run.filename	run.semantic_name	run.total_bases	run.total_spots	run.alias	run.read_lengths	run.base_counts	run.r1_length	run.r2_length	run.Acount	run.Ccount	run.Gcount	run.Tcount	run.Ncount	run.experiment	run.pool_member	submission.accession	submission.srasource	submission.bioprojectsource	seqdetective.n_mates	seqdetective.mapping_rate.mate1	seqdetective.mapping_rate.mate2	seqdetective.nofeature_rate.mate1	seqdetective.nofeature_rate.mate2	seqdetective.sparsity.mate1	seqdetective.sparsity.mate2	seqdetective.pos_strand_rate.mate1	seqdetective.pos_strand_rate.mate2	seqdetective.readlen.mate1	seqdetective.readlen.mate2	seqdetective.judgement.mate1	seqdetective.judgement.mate2	seqdetective.judgement.reason	platform_family	instrument_generation	read_bias	selection_class	prep_kit	sc_or_bulk	tech_class	technology	submission.bioprojectsource.country	earliest_date	devstage_curation	devstage_curation_coarse	tissue_curation	tissue_curation_coarse
32850	32850	SRR29482329	SRX24993379	SRS21694843	SRP515141	PRJNA1126244	Specific oncogene activation of the cell of origin in mucosal melanoma [RNA Seq]	GSE270354	Transcriptome Analysis	Mucosal melanoma MM is a deadly cancer derived from mucosal melanocytes. To test the consequences of MM genetics we develop a zebrafish model in which all melanocytes experience CCND1 expression and loss of PTEN and TP53. Surprisingly melanoma only develops from melanocytes lining internal organs analogous to the location of patient MM. We find that zebrafish MMs have a unique chromatin landscape from cutaneous melanoma. Internal melanocytes are labeled using a MM specific transcriptional enhancer. Normal zebrafish internal melanocytes share a gene expression signature with MMs. Patient and zebrafish MMs show increased migratory neural crest gene and decreased antigen presentation gene expression consistent with the increased metastatic behavior and decreased immunotherapy sensitivity of MM. Our work suggests the cell state of the originating melanocyte influences the behavior of derived melanomas. Our animal model phenotypically and transcriptionally mimics patient tumors allowing this model to be used for MM therapeutic discovery. As this is a non MAPK driven genetically engineered model of melanoma our work also has implications for the 15% of cutaneous melanoma patients who lack MAPK driving mutations. Overall design: Bulk RNA sequencing data from mucosal melanoma and cutaneous melanoma zebrafish models			MM rep5 [RNA Seq]	GSM8340235	source name:mucosal melanoma\|tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1\|geo loc name:missing\|collection date:missing	MM rep5 [RNA Seq]	Cutadpt was used to remove adaptor sequences and low quality regions. The high quality reads were aligned to UCSC build danRer11 of zebrafish genome using Tophat 2.0.11 without xxx splicing form calls. Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. Assembly: danRer11 Supplementary files format and content: .txt file contains differential gene expression of mucosal melanoma samples vs. cutaneous melanoma	mucosal melanoma		Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530	Melanomas generated from mitfa / ; tp53 / ; BRAFV600E zebrafish injected with MCR:EGFP or roy / ; mitfa / zebrafish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1were isolated for RNA seq.	tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1	GSM8340235	GSM8340235: MM rep5 [RNA Seq]; Danio rerio; RNA Seq	GSM8340235 r1	GSM8340235	1	Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq 6000	SRP515141	MI-Dr-F381.R2.fastq.gz MI-Dr-F381.R1.fastq.gz	fastq fastq	12158543700.0	40528479.0	GSM8340235 r1	0:150 1:150	A:3249684583;C:2829283376;G:2878779006;T:3198464780;N:2331955	150	150	3249684583	2829283376	2878779006	3198464780	2331955	SRX24993379	SRS21694843	SRA1904140	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	2	0.91528	0.91522	0.06081	0.06071	0.71662	0.72606	0.50019	0.49902	150	150	B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	nebnext	bulk	bulk	bulk	United States	2024-06-20	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
32851	32851	SRR29482330	SRX24993378	SRS21694842	SRP515141	PRJNA1126244	Specific oncogene activation of the cell of origin in mucosal melanoma [RNA Seq]	GSE270354	Transcriptome Analysis	Mucosal melanoma MM is a deadly cancer derived from mucosal melanocytes. To test the consequences of MM genetics we develop a zebrafish model in which all melanocytes experience CCND1 expression and loss of PTEN and TP53. Surprisingly melanoma only develops from melanocytes lining internal organs analogous to the location of patient MM. We find that zebrafish MMs have a unique chromatin landscape from cutaneous melanoma. Internal melanocytes are labeled using a MM specific transcriptional enhancer. Normal zebrafish internal melanocytes share a gene expression signature with MMs. Patient and zebrafish MMs show increased migratory neural crest gene and decreased antigen presentation gene expression consistent with the increased metastatic behavior and decreased immunotherapy sensitivity of MM. Our work suggests the cell state of the originating melanocyte influences the behavior of derived melanomas. Our animal model phenotypically and transcriptionally mimics patient tumors allowing this model to be used for MM therapeutic discovery. As this is a non MAPK driven genetically engineered model of melanoma our work also has implications for the 15% of cutaneous melanoma patients who lack MAPK driving mutations. Overall design: Bulk RNA sequencing data from mucosal melanoma and cutaneous melanoma zebrafish models			MM rep4 [RNA Seq]	GSM8340234	source name:mucosal melanoma\|tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1\|geo loc name:missing\|collection date:missing	MM rep4 [RNA Seq]	Cutadpt was used to remove adaptor sequences and low quality regions. The high quality reads were aligned to UCSC build danRer11 of zebrafish genome using Tophat 2.0.11 without xxx splicing form calls. Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. Assembly: danRer11 Supplementary files format and content: .txt file contains differential gene expression of mucosal melanoma samples vs. cutaneous melanoma	mucosal melanoma		Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530	Melanomas generated from mitfa / ; tp53 / ; BRAFV600E zebrafish injected with MCR:EGFP or roy / ; mitfa / zebrafish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1were isolated for RNA seq.	tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1	GSM8340234	GSM8340234: MM rep4 [RNA Seq]; Danio rerio; RNA Seq	GSM8340234 r1	GSM8340234	1	Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq 6000	SRP515141	MI-Dr-F380.R2.fastq.gz MI-Dr-F380.R1.fastq.gz	fastq fastq	15136959300.0	50456531.0	GSM8340234 r1	0:150 1:150	A:3999982463;C:3565423997;G:3623206178;T:3945454250;N:2892412	150	150	3999982463	3565423997	3623206178	3945454250	2892412	SRX24993378	SRS21694842	SRA1904140	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	2	0.91544	0.91681	0.05707	0.05629	0.71873	0.7278	0.50536	0.50794	150	150	B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	nebnext	bulk	bulk	bulk	United States	2024-06-20	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
32852	32852	SRR29482331	SRX24993377	SRS21694841	SRP515141	PRJNA1126244	Specific oncogene activation of the cell of origin in mucosal melanoma [RNA Seq]	GSE270354	Transcriptome Analysis	Mucosal melanoma MM is a deadly cancer derived from mucosal melanocytes. To test the consequences of MM genetics we develop a zebrafish model in which all melanocytes experience CCND1 expression and loss of PTEN and TP53. Surprisingly melanoma only develops from melanocytes lining internal organs analogous to the location of patient MM. We find that zebrafish MMs have a unique chromatin landscape from cutaneous melanoma. Internal melanocytes are labeled using a MM specific transcriptional enhancer. Normal zebrafish internal melanocytes share a gene expression signature with MMs. Patient and zebrafish MMs show increased migratory neural crest gene and decreased antigen presentation gene expression consistent with the increased metastatic behavior and decreased immunotherapy sensitivity of MM. Our work suggests the cell state of the originating melanocyte influences the behavior of derived melanomas. Our animal model phenotypically and transcriptionally mimics patient tumors allowing this model to be used for MM therapeutic discovery. As this is a non MAPK driven genetically engineered model of melanoma our work also has implications for the 15% of cutaneous melanoma patients who lack MAPK driving mutations. Overall design: Bulk RNA sequencing data from mucosal melanoma and cutaneous melanoma zebrafish models			MM rep3 [RNA Seq]	GSM8340233	source name:mucosal melanoma\|tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1\|geo loc name:missing\|collection date:missing	MM rep3 [RNA Seq]	Cutadpt was used to remove adaptor sequences and low quality regions. The high quality reads were aligned to UCSC build danRer11 of zebrafish genome using Tophat 2.0.11 without xxx splicing form calls. Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. Assembly: danRer11 Supplementary files format and content: .txt file contains differential gene expression of mucosal melanoma samples vs. cutaneous melanoma	mucosal melanoma		Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530	Melanomas generated from mitfa / ; tp53 / ; BRAFV600E zebrafish injected with MCR:EGFP or roy / ; mitfa / zebrafish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1were isolated for RNA seq.	tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1	GSM8340233	GSM8340233: MM rep3 [RNA Seq]; Danio rerio; RNA Seq	GSM8340233 r1	GSM8340233	1	Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq 6000	SRP515141	MI-Dr-F379.R1.fastq.gz MI-Dr-F379.R2.fastq.gz	fastq fastq	19584405300.0	65281351.0	GSM8340233 r1	0:150 1:150	A:5193657176;C:4586793253;G:4681119346;T:5119062192;N:3773333	150	150	5193657176	4586793253	4681119346	5119062192	3773333	SRX24993377	SRS21694841	SRA1904140	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	2	0.91009	0.91075	0.05605	0.05603	0.70709	0.71553	0.48633	0.5046	150	150	B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	nebnext	bulk	bulk	bulk	United States	2024-06-20	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
32853	32853	SRR29482332	SRX24993376	SRS21694840	SRP515141	PRJNA1126244	Specific oncogene activation of the cell of origin in mucosal melanoma [RNA Seq]	GSE270354	Transcriptome Analysis	Mucosal melanoma MM is a deadly cancer derived from mucosal melanocytes. To test the consequences of MM genetics we develop a zebrafish model in which all melanocytes experience CCND1 expression and loss of PTEN and TP53. Surprisingly melanoma only develops from melanocytes lining internal organs analogous to the location of patient MM. We find that zebrafish MMs have a unique chromatin landscape from cutaneous melanoma. Internal melanocytes are labeled using a MM specific transcriptional enhancer. Normal zebrafish internal melanocytes share a gene expression signature with MMs. Patient and zebrafish MMs show increased migratory neural crest gene and decreased antigen presentation gene expression consistent with the increased metastatic behavior and decreased immunotherapy sensitivity of MM. Our work suggests the cell state of the originating melanocyte influences the behavior of derived melanomas. Our animal model phenotypically and transcriptionally mimics patient tumors allowing this model to be used for MM therapeutic discovery. As this is a non MAPK driven genetically engineered model of melanoma our work also has implications for the 15% of cutaneous melanoma patients who lack MAPK driving mutations. Overall design: Bulk RNA sequencing data from mucosal melanoma and cutaneous melanoma zebrafish models			MM rep2 [RNA Seq]	GSM8340232	source name:mucosal melanoma\|tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1\|geo loc name:missing\|collection date:missing	MM rep2 [RNA Seq]	Cutadpt was used to remove adaptor sequences and low quality regions. The high quality reads were aligned to UCSC build danRer11 of zebrafish genome using Tophat 2.0.11 without xxx splicing form calls. Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. Assembly: danRer11 Supplementary files format and content: .txt file contains differential gene expression of mucosal melanoma samples vs. cutaneous melanoma	mucosal melanoma		Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530	Melanomas generated from mitfa / ; tp53 / ; BRAFV600E zebrafish injected with MCR:EGFP or roy / ; mitfa / zebrafish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1were isolated for RNA seq.	tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1	GSM8340232	GSM8340232: MM rep2 [RNA Seq]; Danio rerio; RNA Seq	GSM8340232 r1	GSM8340232	1	Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq 6000	SRP515141	MI-Dr-F378.R2.fastq.gz MI-Dr-F378.R1.fastq.gz	fastq fastq	12509804100.0	41699347.0	GSM8340232 r1	0:150 1:150	A:3348127771;C:2902757443;G:2952121486;T:3304405412;N:2391988	150	150	3348127771	2902757443	2952121486	3304405412	2391988	SRX24993376	SRS21694840	SRA1904140	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	2	0.90209	0.903	0.07387	0.07393	0.7232	0.73083	0.51976	0.52071	150	150	B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	nebnext	bulk	bulk	bulk	United States	2024-06-20	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
32854	32854	SRR29482333	SRX24993375	SRS21694839	SRP515141	PRJNA1126244	Specific oncogene activation of the cell of origin in mucosal melanoma [RNA Seq]	GSE270354	Transcriptome Analysis	Mucosal melanoma MM is a deadly cancer derived from mucosal melanocytes. To test the consequences of MM genetics we develop a zebrafish model in which all melanocytes experience CCND1 expression and loss of PTEN and TP53. Surprisingly melanoma only develops from melanocytes lining internal organs analogous to the location of patient MM. We find that zebrafish MMs have a unique chromatin landscape from cutaneous melanoma. Internal melanocytes are labeled using a MM specific transcriptional enhancer. Normal zebrafish internal melanocytes share a gene expression signature with MMs. Patient and zebrafish MMs show increased migratory neural crest gene and decreased antigen presentation gene expression consistent with the increased metastatic behavior and decreased immunotherapy sensitivity of MM. Our work suggests the cell state of the originating melanocyte influences the behavior of derived melanomas. Our animal model phenotypically and transcriptionally mimics patient tumors allowing this model to be used for MM therapeutic discovery. As this is a non MAPK driven genetically engineered model of melanoma our work also has implications for the 15% of cutaneous melanoma patients who lack MAPK driving mutations. Overall design: Bulk RNA sequencing data from mucosal melanoma and cutaneous melanoma zebrafish models			MM rep1 [RNA Seq]	GSM8340231	source name:mucosal melanoma\|tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1\|geo loc name:missing\|collection date:missing	MM rep1 [RNA Seq]	Cutadpt was used to remove adaptor sequences and low quality regions. The high quality reads were aligned to UCSC build danRer11 of zebrafish genome using Tophat 2.0.11 without xxx splicing form calls. Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. Assembly: danRer11 Supplementary files format and content: .txt file contains differential gene expression of mucosal melanoma samples vs. cutaneous melanoma	mucosal melanoma		Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530	Melanomas generated from mitfa / ; tp53 / ; BRAFV600E zebrafish injected with MCR:EGFP or roy / ; mitfa / zebrafish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1were isolated for RNA seq.	tissue:mucosal melanoma\|cell type:melanoma\|genotype:roy / ; mitfa / fish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1	GSM8340231	GSM8340231: MM rep1 [RNA Seq]; Danio rerio; RNA Seq	GSM8340231 r1	GSM8340231	1	Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq 6000	SRP515141	MI-Dr-F377.R2.fastq.gz MI-Dr-F377.R1.fastq.gz	fastq fastq	10304309400.0	34347698.0	GSM8340231 r1	0:150 1:150	A:2725877839;C:2430296510;G:2469399791;T:2676748684;N:1986576	150	150	2725877839	2430296510	2469399791	2676748684	1986576	SRX24993375	SRS21694839	SRA1904140	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	2	0.9288	0.9297	0.05311	0.05279	0.7708	0.77918	0.53907	0.53683	150	150	B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	nebnext	bulk	bulk	bulk	United States	2024-06-20	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
32855	32855	SRR29482334	SRX24993374	SRS21694838	SRP515141	PRJNA1126244	Specific oncogene activation of the cell of origin in mucosal melanoma [RNA Seq]	GSE270354	Transcriptome Analysis	Mucosal melanoma MM is a deadly cancer derived from mucosal melanocytes. To test the consequences of MM genetics we develop a zebrafish model in which all melanocytes experience CCND1 expression and loss of PTEN and TP53. Surprisingly melanoma only develops from melanocytes lining internal organs analogous to the location of patient MM. We find that zebrafish MMs have a unique chromatin landscape from cutaneous melanoma. Internal melanocytes are labeled using a MM specific transcriptional enhancer. Normal zebrafish internal melanocytes share a gene expression signature with MMs. Patient and zebrafish MMs show increased migratory neural crest gene and decreased antigen presentation gene expression consistent with the increased metastatic behavior and decreased immunotherapy sensitivity of MM. Our work suggests the cell state of the originating melanocyte influences the behavior of derived melanomas. Our animal model phenotypically and transcriptionally mimics patient tumors allowing this model to be used for MM therapeutic discovery. As this is a non MAPK driven genetically engineered model of melanoma our work also has implications for the 15% of cutaneous melanoma patients who lack MAPK driving mutations. Overall design: Bulk RNA sequencing data from mucosal melanoma and cutaneous melanoma zebrafish models			CM rep3 [RNA Seq]	GSM8340230	source name:cutaneous melanoma\|tissue:cutaneous melanoma\|cell type:melanoma\|genotype:mitfa / ; tp53 / ; BRAFV600E fish injected with MCR:EGFP\|geo loc name:missing\|collection date:missing	CM rep3 [RNA Seq]	Cutadpt was used to remove adaptor sequences and low quality regions. The high quality reads were aligned to UCSC build danRer11 of zebrafish genome using Tophat 2.0.11 without xxx splicing form calls. Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. Assembly: danRer11 Supplementary files format and content: .txt file contains differential gene expression of mucosal melanoma samples vs. cutaneous melanoma	cutaneous melanoma		Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530	Melanomas generated from mitfa / ; tp53 / ; BRAFV600E zebrafish injected with MCR:EGFP or roy / ; mitfa / zebrafish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1were isolated for RNA seq.	tissue:cutaneous melanoma\|cell type:melanoma\|genotype:mitfa / ; tp53 / ; BRAFV600E fish injected with MCR:EGFP	GSM8340230	GSM8340230: CM rep3 [RNA Seq]; Danio rerio; RNA Seq	GSM8340230 r1	GSM8340230	1	Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq 6000	SRP515141	MI_12_USPD16098384-12_H2553BBXX_L8_2.fq.gz MI_12_USPD16098384-12_H2553BBXX_L8_1.fq.gz	fastq fastq	10930590300.0	36435301.0	GSM8340230 r1	0:150 1:150	A:2979658653;C:2484668914;G:2536584911;T:2928246610;N:1431212	150	150	2979658653	2484668914	2536584911	2928246610	1431212	SRX24993374	SRS21694838	SRA1904140	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	2	0.92203	0.92273	0.08582	0.08561	0.73815	0.73868	0.54966	0.54645	150	150	B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	nebnext	bulk	bulk	bulk	United States	2024-06-20	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
32856	32856	SRR29482335	SRX24993373	SRS21694837	SRP515141	PRJNA1126244	Specific oncogene activation of the cell of origin in mucosal melanoma [RNA Seq]	GSE270354	Transcriptome Analysis	Mucosal melanoma MM is a deadly cancer derived from mucosal melanocytes. To test the consequences of MM genetics we develop a zebrafish model in which all melanocytes experience CCND1 expression and loss of PTEN and TP53. Surprisingly melanoma only develops from melanocytes lining internal organs analogous to the location of patient MM. We find that zebrafish MMs have a unique chromatin landscape from cutaneous melanoma. Internal melanocytes are labeled using a MM specific transcriptional enhancer. Normal zebrafish internal melanocytes share a gene expression signature with MMs. Patient and zebrafish MMs show increased migratory neural crest gene and decreased antigen presentation gene expression consistent with the increased metastatic behavior and decreased immunotherapy sensitivity of MM. Our work suggests the cell state of the originating melanocyte influences the behavior of derived melanomas. Our animal model phenotypically and transcriptionally mimics patient tumors allowing this model to be used for MM therapeutic discovery. As this is a non MAPK driven genetically engineered model of melanoma our work also has implications for the 15% of cutaneous melanoma patients who lack MAPK driving mutations. Overall design: Bulk RNA sequencing data from mucosal melanoma and cutaneous melanoma zebrafish models			CM rep2 [RNA Seq]	GSM8340229	source name:cutaneous melanoma\|tissue:cutaneous melanoma\|cell type:melanoma\|genotype:mitfa / ; tp53 / ; BRAFV600E fish injected with MCR:EGFP\|geo loc name:missing\|collection date:missing	CM rep2 [RNA Seq]	Cutadpt was used to remove adaptor sequences and low quality regions. The high quality reads were aligned to UCSC build danRer11 of zebrafish genome using Tophat 2.0.11 without xxx splicing form calls. Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. Assembly: danRer11 Supplementary files format and content: .txt file contains differential gene expression of mucosal melanoma samples vs. cutaneous melanoma	cutaneous melanoma		Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530	Melanomas generated from mitfa / ; tp53 / ; BRAFV600E zebrafish injected with MCR:EGFP or roy / ; mitfa / zebrafish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1were isolated for RNA seq.	tissue:cutaneous melanoma\|cell type:melanoma\|genotype:mitfa / ; tp53 / ; BRAFV600E fish injected with MCR:EGFP	GSM8340229	GSM8340229: CM rep2 [RNA Seq]; Danio rerio; RNA Seq	GSM8340229 r1	GSM8340229	1	Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq 6000	SRP515141	MI_11_USPD16098384-11_H2553BBXX_L8_2.fq.gz MI_11_USPD16098384-11_H2553BBXX_L8_1.fq.gz	fastq fastq	10972223700.0	36574079.0	GSM8340229 r1	0:150 1:150	A:2948309811;C:2536000818;G:2588828858;T:2897662110;N:1422103	150	150	2948309811	2536000818	2588828858	2897662110	1422103	SRX24993373	SRS21694837	SRA1904140	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	2	0.92722	0.92814	0.06917	0.06867	0.71382	0.71575	0.5158	0.51662	150	150	B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	nebnext	bulk	bulk	bulk	United States	2024-06-20	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
32857	32857	SRR29482336	SRX24993372	SRS21694836	SRP515141	PRJNA1126244	Specific oncogene activation of the cell of origin in mucosal melanoma [RNA Seq]	GSE270354	Transcriptome Analysis	Mucosal melanoma MM is a deadly cancer derived from mucosal melanocytes. To test the consequences of MM genetics we develop a zebrafish model in which all melanocytes experience CCND1 expression and loss of PTEN and TP53. Surprisingly melanoma only develops from melanocytes lining internal organs analogous to the location of patient MM. We find that zebrafish MMs have a unique chromatin landscape from cutaneous melanoma. Internal melanocytes are labeled using a MM specific transcriptional enhancer. Normal zebrafish internal melanocytes share a gene expression signature with MMs. Patient and zebrafish MMs show increased migratory neural crest gene and decreased antigen presentation gene expression consistent with the increased metastatic behavior and decreased immunotherapy sensitivity of MM. Our work suggests the cell state of the originating melanocyte influences the behavior of derived melanomas. Our animal model phenotypically and transcriptionally mimics patient tumors allowing this model to be used for MM therapeutic discovery. As this is a non MAPK driven genetically engineered model of melanoma our work also has implications for the 15% of cutaneous melanoma patients who lack MAPK driving mutations. Overall design: Bulk RNA sequencing data from mucosal melanoma and cutaneous melanoma zebrafish models			CM rep1 [RNA Seq]	GSM8340228	source name:cutaneous melanoma\|tissue:cutaneous melanoma\|cell type:melanoma\|genotype:mitfa / ; tp53 / ; BRAFV600E fish injected with MCR:EGFP\|geo loc name:missing\|collection date:missing	CM rep1 [RNA Seq]	Cutadpt was used to remove adaptor sequences and low quality regions. The high quality reads were aligned to UCSC build danRer11 of zebrafish genome using Tophat 2.0.11 without xxx splicing form calls. Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. Assembly: danRer11 Supplementary files format and content: .txt file contains differential gene expression of mucosal melanoma samples vs. cutaneous melanoma	cutaneous melanoma		Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530	Melanomas generated from mitfa / ; tp53 / ; BRAFV600E zebrafish injected with MCR:EGFP or roy / ; mitfa / zebrafish injected with CRISPR MCR:tp53 sgRNA; CRISPR MCR:ptena/b sgRNA; MCR:CCND1were isolated for RNA seq.	tissue:cutaneous melanoma\|cell type:melanoma\|genotype:mitfa / ; tp53 / ; BRAFV600E fish injected with MCR:EGFP	GSM8340228	GSM8340228: CM rep1 [RNA Seq]; Danio rerio; RNA Seq	GSM8340228 r1	GSM8340228	1	Tissue was disrupted using QIAshredder columns Qiagen 79656. DNA was removed and RNA was purified using columns Qiagen 74134. RNA was polyA selected NEB E7490. NEBNext Ultra RNA Library Prep Kit for Illumina NEB E7530		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq 6000	SRP515141	MI_10_USPD16098384-10_H2553BBXX_L8_1.fq.gz MI_10_USPD16098384-10_H2553BBXX_L8_2.fq.gz	fastq fastq	11662049100.0	38873497.0	GSM8340228 r1	0:150 1:150	A:3125745391;C:2697305234;G:2752722644;T:3084760577;N:1515254	150	150	3125745391	2697305234	2752722644	3084760577	1515254	SRX24993372	SRS21694836	SRA1904140	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	Insco Lab, Medical Oncology, Dana Farber Cancer Institute	2	0.92667	0.92674	0.0665	0.06609	0.7207	0.72107	0.52399	0.5179	150	150	B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	nebnext	bulk	bulk	bulk	United States	2024-06-20	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34353	34353	SRR31668404	SRX27031101	SRS23495066	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven tp53 / primary neuroblastoma biological sample 3	GSM8675202	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven tp53 / primary neuroblastoma biological sample 3	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;tp53 /	GSM8675202	GSM8675202: MYCN driven tp53 / primary neuroblastoma biological sample 3; Danio rerio; RNA Seq	GSM8675202 r1	GSM8675202	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	tp53_3_R1.fastq.gz tp53_3_R2.fastq.gz	fastq fastq	23336192320.0	77272160.0	GSM8675202 r1	0:151 1:151	A:6254847499;C:5434444966;G:5467895678;T:6178911394;N:92783	151	151	6254847499	5434444966	5467895678	6178911394	92783	SRX27031101	SRS23495066	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34354	34354	SRR31668405	SRX27031100	SRS23495065	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven tp53 / primary neuroblastoma biological sample 2	GSM8675201	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven tp53 / primary neuroblastoma biological sample 2	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;tp53 /	GSM8675201	GSM8675201: MYCN driven tp53 / primary neuroblastoma biological sample 2; Danio rerio; RNA Seq	GSM8675201 r1	GSM8675201	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	tp53_2_R1.fastq.gz tp53_2_R2.fastq.gz	fastq fastq	20339315252.0	67348726.0	GSM8675201 r1	0:151 1:151	A:5418776023;C:4755013552;G:4799958409;T:5365490819;N:76449	151	151	5418776023	4755013552	4799958409	5365490819	76449	SRX27031100	SRS23495065	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34355	34355	SRR31668406	SRX27031099	SRS23495064	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven tp53 / primary neuroblastoma biological sample 1	GSM8675200	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven tp53 / primary neuroblastoma biological sample 1	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;tp53 /	GSM8675200	GSM8675200: MYCN driven tp53 / primary neuroblastoma biological sample 1; Danio rerio; RNA Seq	GSM8675200 r1	GSM8675200	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	tp53_1_R1.fastq.gz tp53_1_R2.fastq.gz	fastq fastq	23005026972.0	76175586.0	GSM8675200 r1	0:151 1:151	A:6117051407;C:5407786944;G:5434080472;T:6046021055;N:87094	151	151	6117051407	5407786944	5434080472	6046021055	87094	SRX27031099	SRS23495064	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34356	34356	SRR31668407	SRX27031098	SRS23495063	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven atm+/ ;tp53+/ primary neuroblastoma	GSM8675199	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;atm+/ ;tp53+/ \|geo loc name:missing\|collection date:missing	MYCN driven atm+/ ;tp53+/ primary neuroblastoma	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;atm+/ ;tp53+/	GSM8675199	GSM8675199: MYCN driven atm+/ ;tp53+/ primary neuroblastoma; Danio rerio; RNA Seq	GSM8675199 r1	GSM8675199	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	atm_2_R1.fastq.gz atm_2_R2.fastq.gz	fastq fastq	23261284240.0	77024120.0	GSM8675199 r1	0:151 1:151	A:6145376247;C:5458254950;G:5636744711;T:6020701748;N:206584	151	151	6145376247	5458254950	5636744711	6020701748	206584	SRX27031098	SRS23495063	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34357	34357	SRR31668408	SRX27031097	SRS23495062	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven atm+/ ;tp53 / primary neuroblastoma	GSM8675198	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;atm+/ ;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven atm+/ ;tp53 / primary neuroblastoma	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;atm+/ ;tp53 /	GSM8675198	GSM8675198: MYCN driven atm+/ ;tp53 / primary neuroblastoma; Danio rerio; RNA Seq	GSM8675198 r1	GSM8675198	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	atm_1_R1.fastq.gz atm_1_R2.fastq.gz	fastq fastq	28077605910.0	92972205.0	GSM8675198 r1	0:151 1:151	A:7498074413;C:6502104689;G:6709307820;T:7367870925;N:248063	151	151	7498074413	6502104689	6709307820	7367870925	248063	SRX27031097	SRS23495062	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34358	34358	SRR31668409	SRX27031096	SRS23495061	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 3	GSM8675197	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 3	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 /	GSM8675197	GSM8675197: MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 3; Danio rerio; RNA Seq	GSM8675197 r1	GSM8675197	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	brca2_4T_3_R1.fastq.gz brca2_4T_3_R2.fastq.gz	fastq fastq	25734256842.0	85212771.0	GSM8675197 r1	0:151 1:151	A:6992891847;C:5899631235;G:5926941082;T:6914693910;N:98768	151	151	6992891847	5899631235	5926941082	6914693910	98768	SRX27031096	SRS23495061	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34359	34359	SRR31668410	SRX27031095	SRS23495060	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 2	GSM8675196	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 2	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 /	GSM8675196	GSM8675196: MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 2; Danio rerio; RNA Seq	GSM8675196 r1	GSM8675196	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	brca2_4T_2_R1.fastq.gz brca2_4T_2_R2.fastq.gz	fastq fastq	25491325626.0	84408363.0	GSM8675196 r1	0:151 1:151	A:6895400993;C:5873291336;G:5902861384;T:6819673005;N:98908	151	151	6895400993	5873291336	5902861384	6819673005	98908	SRX27031095	SRS23495060	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34360	34360	SRR31668411	SRX27031094	SRS23495059	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 1	GSM8675195	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 1	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 /	GSM8675195	GSM8675195: MYCN driven brca2+/ ;tp53 / primary neuroblastoma 4x serially passaged by transplant biological sample 1; Danio rerio; RNA Seq	GSM8675195 r1	GSM8675195	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	brca2_4T_1_R1.fastq.gz brca2_4T_1_R2.fastq.gz	fastq fastq	31806877070.0	105320785.0	GSM8675195 r1	0:151 1:151	A:8688753401;C:7248230638;G:7264489119;T:8605282978;N:120934	151	151	8688753401	7248230638	7264489119	8605282978	120934	SRX27031094	SRS23495059	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34361	34361	SRR31668412	SRX27031093	SRS23495058	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 3	GSM8675194	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 3	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 /	GSM8675194	GSM8675194: MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 3; Danio rerio; RNA Seq	GSM8675194 r1	GSM8675194	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	brca2_3_R1.fastq.gz brca2_3_R2.fastq.gz	fastq fastq	24462829594.0	81002747.0	GSM8675194 r1	0:151 1:151	A:6540455142;C:5666171087;G:5856369054;T:6399621980;N:212331	151	151	6540455142	5666171087	5856369054	6399621980	212331	SRX27031093	SRS23495058	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34362	34362	SRR31668413	SRX27031092	SRS23495057	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 2	GSM8675193	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 2	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 /	GSM8675193	GSM8675193: MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 2; Danio rerio; RNA Seq	GSM8675193 r1	GSM8675193	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	brca2_2_R1.fastq.gz brca2_2_R2.fastq.gz	fastq fastq	28830972694.0	95466797.0	GSM8675193 r1	0:151 1:151	A:7699874582;C:6741660506;G:6766796779;T:7622528008;N:112819	151	151	7699874582	6741660506	6766796779	7622528008	112819	SRX27031092	SRS23495057	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
34363	34363	SRR31668414	SRX27031091	SRS23495056	SRP550584	PRJNA1196438	DNA Damage Response Deficiency Enhances Neuroblastoma Progression and Sensitivity to Combination PARP and ATR Inhibition	GSE283976	Transcriptome Analysis	Next generation sequencing of neuroblastoma NB tumors have revealed frequent somatic and germline genetic alterations in genes encoding proteins involved in DNA damage response DDR pathways. Despite being well studied in many adult cancers roles for DDR disruption in pediatric solid tumors have not been fully elucidated. To address this patient relevant loss of function mutations in DDR pathway components including Brca2 Atm and Palb2 were incorporated into an established zebrafish MYCN transgenic model Tgdbh:EGFP MYCN. These mutations were found to enhance NB formation and metastasis in vivo and result in upregulation of proliferation cell cycle checkpoint and DNA damage repair transcriptional signatures revealing novel molecular vulnerabilities in DDR deficient NB. Zebrafish DDR deficient NB and human NB cells with DDR protein knock down were sensitive to the polyADP ribose polymerase PARP inhibitor olaparib and this effect was further enhanced by inhibition of the ataxia telangiectasia and rad3 related ATR kinase. Altogether our data supports a functional role for DDR deficiency in NB in vivo and therapeutic potential for combination PARP + ATR inhibition in NB patients with alterations in DDR genes. Overall design: To capture broad transcriptomic differences associated with HDR/DDR deficiency in primary and transplanted neuroblastoma we performed RNA sequencing of GFP+ sorted tumor cells from zebrafish MYCN driven neuroblastoma from various engineered genetic backgrounds			MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 1	GSM8675192	source name:GFP+ sorted neuroblastoma\|tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 / \|geo loc name:missing\|collection date:missing	MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 1	Raw .fastq data was processed using Salmon quantification of transcripts. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23. Samples were quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Assembly: GRCz11 Supplementary files format and content: Comma separated values .csv file including raw non normalized counts for all conditions generated by Salmon	GFP+ sorted neuroblastoma	All animal monitoring and sample collection were performed in accordance with animal use protocols approved by the Hospital for Sick Children Animal Care Committee #1000054111 #1000064586.	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.	Zebrafish were reared and maintained according to standard husbandry procedure at the Zebrafish Genetics and Disease Modeling Core Facility at the Hospital for Sick Children.	tissue:GFP+ sorted neuroblastoma\|cell type:neuroblastoma\|genotype:MYCN;brca2+/ ;tp53 /	GSM8675192	GSM8675192: MYCN driven brca2+/ ;tp53 / primary neuroblastoma biological sample 1; Danio rerio; RNA Seq	GSM8675192 r1	GSM8675192	1	Dissected neuroblastoma tumors were manually dissociated and processed to single cell suspensions. GFP+ tumor cells were sorted from bulk tissue at the SickKids UHN Flow Cytometry Core Facility on a Sony MA900 VBYR cell sorter before pelleting and lysis using Qiagen RNeasy Mini Kit as per manufacturer instructions. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760. Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina NEB E7760.		RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina NovaSeq X	SRP550584	brca2_1_R1.fastq.gz brca2_1_R2.fastq.gz	fastq fastq	24936530788.0	82571294.0	GSM8675192 r1	0:151 1:151	A:6625695379;C:5867258006;G:5887073244;T:6556406745;N:97414	151	151	6625695379	5867258006	5887073244	6556406745	97414	SRX27031091	SRS23495056	SRA2031529	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research												B	B	biological fallback assumption	illumina	novaseq_era	unknown	poly_a	unknown	bulk	unknown	unknown	Canada	2024-12-10	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42480	42480	SRR5639268	SRX2877668	SRS2249441	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYC 8	GSM2646589	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYC 8	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646589	GSM2646589: MYC 8; Danio rerio; RNA Seq	GSM2646589		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646589	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161116_MYC-8_MWZ3676_S8_R1_001.fastq.gz 20161116_MYC-8_MWZ3676_S8_R2_001.fastq.gz	fastq fastq	10081869900.0	67212466.0	GSM2646589 r1	0:75 1:75	A:2790689900;C:2299822096;G:2324357632;T:2662657984;N:4342288	75	75	2790689900	2299822096	2324357632	2662657984	4342288	SRX2877668	SRS2249441	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.90216	0.90346	0.05109	0.05044	0.75073	0.75552	0.53113	0.44417	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42481	42481	SRR5639267	SRX2877667	SRS2249444	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYC 7	GSM2646588	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYC 7	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646588	GSM2646588: MYC 7; Danio rerio; RNA Seq	GSM2646588		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646588	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161116_MYC-7_MWZ3676_S7_R1_001.fastq.gz 20161116_MYC-7_MWZ3676_S7_R2_001.fastq.gz	fastq fastq	9707643300.0	64717622.0	GSM2646588 r1	0:75 1:75	A:2656490466;C:2245711917;G:2271269818;T:2529962783;N:4208316	75	75	2656490466	2245711917	2271269818	2529962783	4208316	SRX2877667	SRS2249444	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.89705	0.89957	0.06207	0.06203	0.75722	0.7624	0.5384	0.53863	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42482	42482	SRR5639266	SRX2877666	SRS2249443	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYC 6	GSM2646587	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYC 6	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646587	GSM2646587: MYC 6; Danio rerio; RNA Seq	GSM2646587		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646587	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161116_MYC-6_MWZ3676_S6_R2_001.fastq.gz 20161116_MYC-6_MWZ3676_S6_R1_001.fastq.gz	fastq fastq	9715852500.0	64772350.0	GSM2646587 r1	0:75 1:75	A:2676443912;C:2226149175;G:2271136868;T:2537875397;N:4247148	75	75	2676443912	2226149175	2271136868	2537875397	4247148	SRX2877666	SRS2249443	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.90528	0.90734	0.07913	0.07931	0.76694	0.77258	0.58608	0.58389	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42483	42483	SRR5639265	SRX2877665	SRS2249440	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYC 5	GSM2646586	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYC 5	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646586	GSM2646586: MYC 5; Danio rerio; RNA Seq	GSM2646586		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646586	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161116_MYC-5_MWZ3676_S5_R1_001.fastq.gz 20161116_MYC-5_MWZ3676_S5_R2_001.fastq.gz	fastq fastq	9009014700.0	60060098.0	GSM2646586 r1	0:75 1:75	A:2448288707;C:2095898874;G:2134585761;T:2326368656;N:3872702	75	75	2448288707	2095898874	2134585761	2326368656	3872702	SRX2877665	SRS2249440	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.90528	0.90592	0.08568	0.08499	0.76589	0.77232	0.56872	0.57864	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42484	42484	SRR5639264	SRX2877664	SRS2249442	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYC 4	GSM2646585	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYC 4	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646585	GSM2646585: MYC 4; Danio rerio; RNA Seq	GSM2646585		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646585	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161116_MYC-4_MWZ3676_S4_R1_001.fastq.gz 20161116_MYC-4_MWZ3676_S4_R2_001.fastq.gz	fastq fastq	8514092237.0	60342948.0	GSM2646585 r1	0:75 1:75.00	A:2362847360;C:1933488006;G:1961930272;T:2252168244;N:3658355	75	75	2362847360	1933488006	1961930272	2252168244	3658355	SRX2877664	SRS2249442	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.91098	0.91363	0.06049	0.06082	0.75237	0.75785	0.52723	0.44724	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42485	42485	SRR5639263	SRX2877663	SRS2249439	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYC 3	GSM2646584	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYC 3	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646584	GSM2646584: MYC 3; Danio rerio; RNA Seq	GSM2646584		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646584	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161116_MYC-3_MWZ3676_S3_R1_001.fastq.gz 20161116_MYC-3_MWZ3676_S3_R2_001.fastq.gz	fastq fastq	9499251600.0	63328344.0	GSM2646584 r1	0:75 1:75	A:2600983566;C:2193461949;G:2224307535;T:2476379293;N:4119257	75	75	2600983566	2193461949	2224307535	2476379293	4119257	SRX2877663	SRS2249439	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.9202	0.92206	0.07816	0.07901	0.74612	0.75268	0.55199	0.54541	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42486	42486	SRR5639262	SRX2877662	SRS2249438	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYC 2	GSM2646583	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYC 2	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646583	GSM2646583: MYC 2; Danio rerio; RNA Seq	GSM2646583		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646583	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161116_MYC-2_MWZ3676_S2_R1_001.fastq.gz 20161116_MYC-2_MWZ3676_S2_R2_001.fastq.gz	fastq fastq	9916108050.0	66107387.0	GSM2646583 r1	0:75 1:75	A:2707842597;C:2295701488;G:2339804244;T:2568467441;N:4292280	75	75	2707842597	2295701488	2339804244	2568467441	4292280	SRX2877662	SRS2249438	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.91755	0.91847	0.06435	0.06371	0.76721	0.77277	0.57525	0.58163	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42487	42487	SRR5639261	SRX2877661	SRS2249437	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYC 1	GSM2646582	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYC 1	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYC transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646582	GSM2646582: MYC 1; Danio rerio; RNA Seq	GSM2646582		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646582	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161116_MYC-1_MWZ3676_S1_R1_001.fastq.gz 20161116_MYC-1_MWZ3676_S1_R2_001.fastq.gz	fastq fastq	9133899450.0	60892663.0	GSM2646582 r1	0:75 1:75	A:2485889577;C:2124525486;G:2159911091;T:2359614852;N:3958444	75	75	2485889577	2124525486	2159911091	2359614852	3958444	SRX2877661	SRS2249437	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.92038	0.92088	0.07532	0.07511	0.74811	0.75576	0.58853	0.58804	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42488	42488	SRR5639260	SRX2877660	SRS2249436	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYCN 4	GSM2646581	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYCN 4	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646581	GSM2646581: MYCN 4; Danio rerio; RNA Seq	GSM2646581		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646581	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161021_WT-4_MWZ3582_S4_R1_001.fastq.gz 20161021_WT-4_MWZ3582_S4_R2_001.fastq.gz	fastq fastq	9350290500.0	62335270.0	GSM2646581 r1	0:75 1:75	A:2584645248;C:2113813813;G:2141529817;T:2509027204;N:1274418	75	75	2584645248	2113813813	2141529817	2509027204	1274418	SRX2877660	SRS2249436	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.94127	0.94311	0.07924	0.07907	0.73673	0.74026	0.48176	0.46073	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42489	42489	SRR5639259	SRX2877659	SRS2249434	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYCN 3	GSM2646580	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYCN 3	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646580	GSM2646580: MYCN 3; Danio rerio; RNA Seq	GSM2646580		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646580	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161021_WT-3_MWZ3582_S3_R1_001.fastq.gz 20161021_WT-3_MWZ3582_S3_R2_001.fastq.gz	fastq fastq	8155574400.0	54370496.0	GSM2646580 r1	0:75 1:75	A:2218692747;C:1881082606;G:1915867614;T:2138862711;N:1068722	75	75	2218692747	1881082606	1915867614	2138862711	1068722	SRX2877659	SRS2249434	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.94262	0.94367	0.05391	0.05378	0.74631	0.75099	0.48101	0.4861	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42490	42490	SRR5639258	SRX2877658	SRS2249435	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYCN 2	GSM2646579	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYCN 2	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646579	GSM2646579: MYCN 2; Danio rerio; RNA Seq	GSM2646579		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646579	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161021_WT-2_MWZ3582_S2_R1_001.fastq.gz 20161021_WT-2_MWZ3582_S2_R2_001.fastq.gz	fastq fastq	11327208000.0	75514720.0	GSM2646579 r1	0:75 1:75	A:3089154339;C:2598817018;G:2660297425;T:2977379789;N:1559429	75	75	3089154339	2598817018	2660297425	2977379789	1559429	SRX2877658	SRS2249435	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.94797	0.95019	0.06855	0.06894	0.75028	0.75386	0.51196	0.50362	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
42491	42491	SRR5639257	SRX2877657	SRS2249433	SRP108529	PRJNA388953	c MYC drives neuroblastoma tumorigenesis and retinoic acid resistance in zebrafish [RNA Seq]	GSE99567	Transcriptome Analysis	Neuroblastoma is an often intractable tumor that accounts for 15% of childhood cancer deaths. In addition to MYCN amplification in 20% of tumors 11% express high levels of c MYC MYC protein. To study this newly defined subgroup we have created a novel transgenic zebrafish model in which overexpression of MYC in the peripheral sympathetic nervous system drives early onset neuroblastoma. Overall design: RNA seq was performed on MYC and MYCN driven neuroblastoma tumors to determine chromatin accesibility in these cells	parent bioproject:PRJNA388873		MYCN 1	GSM2646578	tissue:EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN transgenic zebrafish.\|cell type:EGFP+ neuroblasts	MYCN 1	Sequenced reads were trimmed for adaptor sequence and masked for low complexity or low quality sequence using cutadapt then mapped to dr7 whole genome using Tophat 2.0.11 without xxx splicing form calls Transcript abundance and differential expression were calculated with Cufflinks 2.2.1. FPKM values were used to normalize and quantify each transcripts Genome build: dr7 Supplementary files format and content: excel files include RPKM values for each Sample ...	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN transgenic zebrafish.		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ neuroblasts	GSM2646578	GSM2646578: MYCN 1; Danio rerio; RNA Seq	GSM2646578		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2646578	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP108529	20161021_WT-1_MWZ3582_S1_R1_001.fastq.gz 20161021_WT-1_MWZ3582_S1_R2_001.fastq.gz	fastq fastq	11581106850.0	77207379.0	GSM2646578 r1	0:75 1:75	A:3217356977;C:2602411576;G:2673363734;T:3086367856;N:1606707	75	75	3217356977	2602411576	2673363734	3086367856	1606707	SRX2877657	SRS2249433	SRA569347	GEO	Oncology/Hematology, Boston Children's Hospital	2	0.94008	0.94168	0.08272	0.08234	0.72784	0.73283	0.50397	0.49362	75	75	B	B	biological fallback assumption	illumina	hiseq_era	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-06-01	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44955	44955	SRR6334491	SRX3433619	SRS2724937	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	MYCNoe r4	GSM2870458	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:n Myc	MYCNoe r4	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:n Myc	GSM2870458	GSM2870458: MYCNoe r4; Danio rerio; RNA Seq	GSM2870458		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870458	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	MYCNoe_r4.20161021_WT-4_MWZ3582_S4_R1_001.fastq.gz MYCNoe_r4.20161021_WT-4_MWZ3582_S4_R2_001.fastq.gz	fastq fastq	9350290500.0	62335270.0	GSM2870458 r1	0:75 1:75	A:2584645248;C:2113813813;G:2141529817;T:2509027204;N:1274418	75	75	2584645248	2113813813	2141529817	2509027204	1274418	SRX3433619	SRS2724937	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.94125	0.94312	0.07937	0.07925	0.73667	0.7405	0.48297	0.46234	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44956	44956	SRR6334490	SRX3433618	SRS2724936	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	MYCNoe r3	GSM2870457	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:n Myc	MYCNoe r3	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:n Myc	GSM2870457	GSM2870457: MYCNoe r3; Danio rerio; RNA Seq	GSM2870457		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870457	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	MYCNoe_r3.20161021_WT-3_MWZ3582_S3_R2_001.fastq.gz MYCNoe_r3.20161021_WT-3_MWZ3582_S3_R1_001.fastq.gz	fastq fastq	8155574400.0	54370496.0	GSM2870457 r1	0:75 1:75	A:2218692747;C:1881082606;G:1915867614;T:2138862711;N:1068722	75	75	2218692747	1881082606	1915867614	2138862711	1068722	SRX3433618	SRS2724936	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.94262	0.94367	0.05384	0.05359	0.74629	0.75097	0.48167	0.48775	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44957	44957	SRR6334489	SRX3433617	SRS2724935	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	MYCNoe r2	GSM2870456	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:n Myc	MYCNoe r2	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:n Myc	GSM2870456	GSM2870456: MYCNoe r2; Danio rerio; RNA Seq	GSM2870456		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870456	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	MYCNoe_r2.20161021_WT-2_MWZ3582_S2_R2_001.fastq.gz MYCNoe_r2.20161021_WT-2_MWZ3582_S2_R1_001.fastq.gz	fastq fastq	11327208000.0	75514720.0	GSM2870456 r1	0:75 1:75	A:3089154339;C:2598817018;G:2660297425;T:2977379789;N:1559429	75	75	3089154339	2598817018	2660297425	2977379789	1559429	SRX3433617	SRS2724935	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.94799	0.95014	0.06824	0.06879	0.75012	0.75396	0.5118	0.50287	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44958	44958	SRR6334488	SRX3433616	SRS2724934	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	MYCNoe r1	GSM2870455	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:n Myc	MYCNoe r1	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:n Myc	GSM2870455	GSM2870455: MYCNoe r1; Danio rerio; RNA Seq	GSM2870455		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870455	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	MYCNoe_r1.20161021_WT-1_MWZ3582_S1_R2_001.fastq.gz MYCNoe_r1.20161021_WT-1_MWZ3582_S1_R1_001.fastq.gz	fastq fastq	11581106850.0	77207379.0	GSM2870455 r1	0:75 1:75	A:3217356977;C:2602411576;G:2673363734;T:3086367856;N:1606707	75	75	3217356977	2602411576	2673363734	3086367856	1606707	SRX3433616	SRS2724934	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.94008	0.94163	0.08278	0.08227	0.7276	0.73255	0.50145	0.49414	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44959	44959	SRR6334487	SRX3433615	SRS2724933	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	cMYCoe line2 r4	GSM2870454	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	cMYCoe line2 r4	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	GSM2870454	GSM2870454: cMYCoe line2 r4; Danio rerio; RNA Seq	GSM2870454		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870454	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	cMYCoe_line2_r4.20161116_MYC-8_MWZ3676_S8_R2_001.fastq.gz cMYCoe_line2_r4.20161116_MYC-8_MWZ3676_S8_R1_001.fastq.gz	fastq fastq	10081869900.0	67212466.0	GSM2870454 r1	0:75 1:75	A:2790689900;C:2299822096;G:2324357632;T:2662657984;N:4342288	75	75	2790689900	2299822096	2324357632	2662657984	4342288	SRX3433615	SRS2724933	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.90219	0.90342	0.05116	0.05047	0.75091	0.75554	0.53057	0.44417	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44960	44960	SRR6334486	SRX3433614	SRS2724932	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	cMYCoe line2 r3	GSM2870453	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	cMYCoe line2 r3	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	GSM2870453	GSM2870453: cMYCoe line2 r3; Danio rerio; RNA Seq	GSM2870453		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870453	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	cMYCoe_line2_r3.20161116_MYC-7_MWZ3676_S7_R1_001.fastq.gz cMYCoe_line2_r3.20161116_MYC-7_MWZ3676_S7_R2_001.fastq.gz	fastq fastq	9707643300.0	64717622.0	GSM2870453 r1	0:75 1:75	A:2656490466;C:2245711917;G:2271269818;T:2529962783;N:4208316	75	75	2656490466	2245711917	2271269818	2529962783	4208316	SRX3433614	SRS2724932	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.89705	0.89958	0.06199	0.06253	0.75706	0.76232	0.54548	0.53954	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44961	44961	SRR6334485	SRX3433613	SRS2724931	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	cMYCoe line2 r2	GSM2870452	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	cMYCoe line2 r2	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	GSM2870452	GSM2870452: cMYCoe line2 r2; Danio rerio; RNA Seq	GSM2870452		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870452	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	cMYCoe_line2_r2.20161116_MYC-6_MWZ3676_S6_R1_001.fastq.gz cMYCoe_line2_r2.20161116_MYC-6_MWZ3676_S6_R2_001.fastq.gz	fastq fastq	9715852500.0	64772350.0	GSM2870452 r1	0:75 1:75	A:2676443912;C:2226149175;G:2271136868;T:2537875397;N:4247148	75	75	2676443912	2226149175	2271136868	2537875397	4247148	SRX3433613	SRS2724931	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.90529	0.90731	0.07869	0.0794	0.7669	0.77242	0.59274	0.5848	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44962	44962	SRR6334484	SRX3433612	SRS2724930	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	cMYCoe line2 r1	GSM2870451	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	cMYCoe line2 r1	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	GSM2870451	GSM2870451: cMYCoe line2 r1; Danio rerio; RNA Seq	GSM2870451		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870451	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	cMYCoe_line2_r1.20161116_MYC-5_MWZ3676_S5_R2_001.fastq.gz cMYCoe_line2_r1.20161116_MYC-5_MWZ3676_S5_R1_001.fastq.gz	fastq fastq	9009014700.0	60060098.0	GSM2870451 r1	0:75 1:75	A:2448288707;C:2095898874;G:2134585761;T:2326368656;N:3872702	75	75	2448288707	2095898874	2134585761	2326368656	3872702	SRX3433612	SRS2724930	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.90529	0.9059	0.08558	0.08533	0.76654	0.77252	0.56588	0.57792	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44963	44963	SRR6334483	SRX3433611	SRS2724929	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	cMYCoe line1 r4	GSM2870450	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	cMYCoe line1 r4	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	GSM2870450	GSM2870450: cMYCoe line1 r4; Danio rerio; RNA Seq	GSM2870450		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870450	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	cMYCoe_line1_r4.20161116_MYC-4_MWZ3676_S4_R2_001.fastq.gz cMYCoe_line1_r4.20161116_MYC-4_MWZ3676_S4_R1_001.fastq.gz	fastq fastq	9051442200.0	60342948.0	GSM2870450 r1	0:75 1:75	A:2512441086;C:2054230579;G:2086517596;T:2394346120;N:3906819	75	75	2512441086	2054230579	2086517596	2394346120	3906819	SRX3433611	SRS2724929	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.91137	0.91373	0.06085	0.06087	0.74424	0.75035	0.43441	0.53176	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44964	44964	SRR6334482	SRX3433610	SRS2724928	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	cMYCoe line1 r3	GSM2870449	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	cMYCoe line1 r3	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	GSM2870449	GSM2870449: cMYCoe line1 r3; Danio rerio; RNA Seq	GSM2870449		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870449	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	cMYCoe_line1_r3.20161116_MYC-3_MWZ3676_S3_R1_001.fastq.gz cMYCoe_line1_r3.20161116_MYC-3_MWZ3676_S3_R2_001.fastq.gz	fastq fastq	9499251600.0	63328344.0	GSM2870449 r1	0:75 1:75	A:2600983566;C:2193461949;G:2224307535;T:2476379293;N:4119257	75	75	2600983566	2193461949	2224307535	2476379293	4119257	SRX3433610	SRS2724928	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.92026	0.92207	0.0781	0.07917	0.74663	0.75284	0.55184	0.54485	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44965	44965	SRR6334481	SRX3433609	SRS2724927	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	cMYCoe line1 r2	GSM2870448	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	cMYCoe line1 r2	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	GSM2870448	GSM2870448: cMYCoe line1 r2; Danio rerio; RNA Seq	GSM2870448		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870448	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	cMYCoe_line1_r2.20161116_MYC-2_MWZ3676_S2_R1_001.fastq.gz cMYCoe_line1_r2.20161116_MYC-2_MWZ3676_S2_R2_001.fastq.gz	fastq fastq	9916108050.0	66107387.0	GSM2870448 r1	0:75 1:75	A:2707842597;C:2295701488;G:2339804244;T:2568467441;N:4292280	75	75	2707842597	2295701488	2339804244	2568467441	4292280	SRX3433609	SRS2724927	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.91753	0.91846	0.06388	0.06359	0.76702	0.77258	0.57242	0.58362	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
44966	44966	SRR6334480	SRX3433608	SRS2724926	SRP125946	PRJNA420576	c MYC drives a subset of high risk pediatric neuroblastomas and is activated through mechanisms including enhancer hijacking and focal enhancer amplification [RNA seq]	GSE107518	Transcriptome Analysis	Childhood neuroblastoma is known for MYCN gene amplification and here we show that in a separate subset of cases MYC itself is activated due to enhancer hijacking from chromosomal translocations or duplications thus defining a unique subset of high risk disease. Overall design: RNA seq in zebrafish overexpressing human c Myc or n Myc	parent bioproject:PRJNA398387	pubmed:29284669	cMYCoe line1 r1	GSM2870447	tissue:Neuroblastoma tumor cells\|cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	cMYCoe line1 r1	Reads were aligned to a custom version of the zebrafish reference genome containing danRer10 references for all zebrafish chromosomes and "pseudochromosomes" created from the coding sequence of human c Myc and n Myc used in the experimental system Reads were aligned using tophat with parameters no novel juncs and in single end mode Read counts per RefSeq gene and human c Myc and n Myc were quantified using htseq count using parameters stranded=no i gene name f bam Reads per kilobase of exon per million mapped reads were created from these readcounts by dividing by the number of kilobases in all isoforms with the same gene name and then by the millions of mapped reads Supplementary files format and content: WIG filess represent counts of aligned reads within 50 bp bins with each read being extended 200 in the direction of alignment. Counts are in reads per million and floored at 0.1	Neuroblastoma tumor cells		Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer’s protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	EGFP+ neuroblastoma cells were harvested from tumor bearing MYCN and MYC transgenic zebrafish. Tumors were mechanically homogenized and EGFP+ cells were sorted directly into Trizol LS	cell type:EGFP+ transformed neuroblasts\|overexpression:c Myc	GSM2870447	GSM2870447: cMYCoe line1 r1; Danio rerio; RNA Seq	GSM2870447		1	Sorted EGFP+ cells were sorted then total RNA was extracted with Trizol LS. Total RNA was depleted of ribosomal RNA with the SMARTer Universal Low Input RNA Kit Clontech. Enriched mRNA was then applied to library preparation according to manufacturer's protocol NEBNext Ultra. post repeated quality control for average DNA input size of 300 bp the samples were sequenced on a HiSeq Illumina sequencer with 2x100bp paired end reads.	GEO Accession:GSM2870447	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP125946	cMYCoe_line1_r1.20161116_MYC-1_MWZ3676_S1_R2_001.fastq.gz cMYCoe_line1_r1.20161116_MYC-1_MWZ3676_S1_R1_001.fastq.gz	fastq fastq	9133899450.0	60892663.0	GSM2870447 r1	0:75 1:75	A:2485889577;C:2124525486;G:2159911091;T:2359614852;N:3958444	75	75	2485889577	2124525486	2159911091	2359614852	3958444	SRX3433608	SRS2724926	SRA634977	GEO	Young Lab, Whitehead Institute for Biomedical Research	2	0.92038	0.92085	0.07527	0.07547	0.74848	0.75562	0.58873	0.58813	75	75	B	B	biological fallback assumption	illumina	nextseq	full_length	rrna_depletion	nebnext	bulk	unknown	unknown	United States	2017-11-29	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45035	45035	SRR6494615	SRX3583941	SRS2852966	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	12.2B	GSM2915057	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:low\|background strain:CG1\|cell type:blood	12.2B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:low\|background strain:CG1\|cell type:blood	GSM2915057	GSM2915057: 12.2B; Danio rerio; RNA Seq	GSM2915057		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915057	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	12.2B_R1.fastq.gz 12.2B_R2.fastq.gz	fastq fastq	4198177098.0	41158599.0	GSM2915057 r1	0:51 1:51	A:933297427;C:1160638498;G:1167269516;T:931714756;N:5256901	51	51	933297427	1160638498	1167269516	931714756	5256901	SRX3583941	SRS2852966	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.94442	0.95328	0.19284	0.1878	0.83668	0.83792	0.64423	0.61017	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45036	45036	SRR6494614	SRX3583940	SRS2852967	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	12.2A	GSM2915056	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:low\|background strain:CG1\|cell type:blood	12.2A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:low\|background strain:CG1\|cell type:blood	GSM2915056	GSM2915056: 12.2A; Danio rerio; RNA Seq	GSM2915056		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915056	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	12.2A_R1.fastq.gz 12.2A_R2.fastq.gz	fastq fastq	4664784100.0	46647841.0	GSM2915056 r1	0:50 1:50	A:1104404665;C:1222868717;G:1231852847;T:1104961679;N:696192	50	50	1104404665	1222868717	1231852847	1104961679	696192	SRX3583940	SRS2852967	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.92243	0.93608	0.22772	0.22103	0.80411	0.80626	0.61604	0.59999	50	50	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45037	45037	SRR6494613	SRX3583939	SRS2852965	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	10.2B	GSM2915055	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:low\|background strain:CG1\|cell type:blood	10.2B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:low\|background strain:CG1\|cell type:blood	GSM2915055	GSM2915055: 10.2B; Danio rerio; RNA Seq	GSM2915055		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915055	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	10.2B_R1.fastq.gz 10.2B_R2.fastq.gz	fastq fastq	4065465714.0	39857507.0	GSM2915055 r1	0:51 1:51	A:1004499069;C:1015058139;G:1027707268;T:1013076822;N:5124416	51	51	1004499069	1015058139	1027707268	1013076822	5124416	SRX3583939	SRS2852965	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.92877	0.93609	0.2145	0.21044	0.78879	0.79034	0.57017	0.5699	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45038	45038	SRR6494612	SRX3583938	SRS2852964	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	10.2A	GSM2915054	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:low\|background strain:CG1\|cell type:blood	10.2A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:low\|background strain:CG1\|cell type:blood	GSM2915054	GSM2915054: 10.2A; Danio rerio; RNA Seq	GSM2915054		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915054	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	10.2A_R1.fastq.gz 10.2A_R2.fastq.gz	fastq fastq	5825997800.0	58259978.0	GSM2915054 r1	0:50 1:50	A:1452695020;C:1453278793;G:1458683037;T:1460466496;N:874454	50	50	1452695020	1453278793	1458683037	1460466496	874454	SRX3583938	SRS2852964	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.92886	0.9381	0.21573	0.21305	0.78632	0.78813	0.55808	0.56378	50	50	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45039	45039	SRR6494611	SRX3583937	SRS2852963	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	9.2B	GSM2915053	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:low\|background strain:CG1\|cell type:blood	9.2B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:low\|background strain:CG1\|cell type:blood	GSM2915053	GSM2915053: 9.2B; Danio rerio; RNA Seq	GSM2915053		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915053	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	9.2B_R1.fastq.gz 9.2B_R2.fastq.gz	fastq fastq	4506740256.0	44183728.0	GSM2915053 r1	0:51 1:51	A:1112271704;C:1123458923;G:1145952359;T:1119515017;N:5542253	51	51	1112271704	1123458923	1145952359	1119515017	5542253	SRX3583937	SRS2852963	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.92746	0.93269	0.23417	0.23028	0.79904	0.8032	0.54807	0.56848	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45040	45040	SRR6494610	SRX3583936	SRS2852962	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	9.2A	GSM2915052	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:low\|background strain:CG1\|cell type:blood	9.2A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:low\|background strain:CG1\|cell type:blood	GSM2915052	GSM2915052: 9.2A; Danio rerio; RNA Seq	GSM2915052		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915052	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	9.2A_R1.fastq.gz 9.2A_R2.fastq.gz	fastq fastq	4360921770.0	42754135.0	GSM2915052 r1	0:51 1:51	A:1079666608;C:1084041944;G:1104190687;T:1087055139;N:5967392	51	51	1079666608	1084041944	1104190687	1087055139	5967392	SRX3583936	SRS2852962	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.93401	0.93834	0.24172	0.23839	0.79543	0.79853	0.54668	0.56646	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45041	45041	SRR6494609	SRX3583935	SRS2852961	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	7.2.1B	GSM2915051	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	7.2.1B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915051	GSM2915051: 7.2.1B; Danio rerio; RNA Seq	GSM2915051		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915051	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	7.2.1B_R1.fastq.gz 7.2.1B_R2.fastq.gz	fastq fastq	4269804864.0	41860832.0	GSM2915051 r1	0:51 1:51	A:1061177239;C:1059094144;G:1073327634;T:1070820946;N:5384901	51	51	1061177239	1059094144	1073327634	1070820946	5384901	SRX3583935	SRS2852961	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.93904	0.94983	0.27598	0.27453	0.80353	0.80732	0.56729	0.5674	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45042	45042	SRR6494608	SRX3583934	SRS2852960	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	7.2.1A	GSM2915050	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	7.2.1A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915050	GSM2915050: 7.2.1A; Danio rerio; RNA Seq	GSM2915050		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915050	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	7.2.1A_R1.fastq.gz 7.2.1A_R2.fastq.gz	fastq fastq	4365552700.0	43655527.0	GSM2915050 r1	0:50 1:50	A:1081366107;C:1100458538;G:1102308246;T:1080751188;N:668621	50	50	1081366107	1100458538	1102308246	1080751188	668621	SRX3583934	SRS2852960	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.95152	0.95745	0.25194	0.2485	0.80436	0.80377	0.48817	0.50698	50	50	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45043	45043	SRR6494607	SRX3583933	SRS2852959	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	13.1.1B	GSM2915049	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	13.1.1B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915049	GSM2915049: 13.1.1B; Danio rerio; RNA Seq	GSM2915049		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915049	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	13.1.1B_R1.fastq.gz 13.1.1B_R2.fastq.gz	fastq fastq	4354271166.0	42688933.0	GSM2915049 r1	0:51 1:51	A:1064019486;C:1100195568;G:1114361396;T:1070229465;N:5465251	51	51	1064019486	1100195568	1114361396	1070229465	5465251	SRX3583933	SRS2852959	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.93925	0.94875	0.25209	0.24836	0.80837	0.80996	0.47839	0.58777	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45044	45044	SRR6494606	SRX3583932	SRS2853049	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	13.1.1A	GSM2915048	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	13.1.1A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915048	GSM2915048: 13.1.1A; Danio rerio; RNA Seq	GSM2915048		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915048	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	13.1.1A_R1.fastq.gz 13.1.1A_R2.fastq.gz	fastq fastq	4640640100.0	46406401.0	GSM2915048 r1	0:50 1:50	A:1200822095;C:1111931040;G:1117066830;T:1210105773;N:714362	50	50	1200822095	1111931040	1117066830	1210105773	714362	SRX3583932	SRS2853049	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.91613	0.92428	0.32822	0.32518	0.79101	0.79243	0.56679	0.56385	50	50	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45045	45045	SRR6494605	SRX3583931	SRS2852958	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	15.2B	GSM2915047	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	15.2B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915047	GSM2915047: 15.2B; Danio rerio; RNA Seq	GSM2915047		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915047	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	15.2B_R1.fastq.gz 15.2B_R2.fastq.gz	fastq fastq	4734832758.0	46419929.0	GSM2915047 r1	0:51 1:51	A:1173476233;C:1180848673;G:1186821491;T:1187703528;N:5982833	51	51	1173476233	1180848673	1186821491	1187703528	5982833	SRX3583931	SRS2852958	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.93596	0.94402	0.29428	0.29343	0.81174	0.81292	0.59979	0.57701	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45046	45046	SRR6494604	SRX3583930	SRS2852957	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	15.2A	GSM2915046	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	15.2A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915046	GSM2915046: 15.2A; Danio rerio; RNA Seq	GSM2915046		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915046	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	15.2A_R1.fastq.gz 15.2A_R2.fastq.gz	fastq fastq	4146122700.0	41461227.0	GSM2915046 r1	0:50 1:50	A:1018153184;C:1052958176;G:1054611038;T:1019770342;N:629960	50	50	1018153184	1052958176	1054611038	1019770342	629960	SRX3583930	SRS2852957	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.95101	0.95735	0.2546	0.25126	0.81497	0.81497	0.51581	0.58721	50	50	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45047	45047	SRR6494603	SRX3583929	SRS2852956	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	2.1B	GSM2915045	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	2.1B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915045	GSM2915045: 2.1B; Danio rerio; RNA Seq	GSM2915045		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915045	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	2.1B_R1.fastq.gz 2.1B_R2.fastq.gz	fastq fastq	4485073008.0	43971304.0	GSM2915045 r1	0:51 1:51	A:1077166487;C:1155027635;G:1165169697;T:1082191047;N:5518142	51	51	1077166487	1155027635	1165169697	1082191047	5518142	SRX3583929	SRS2852956	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.94959	0.95559	0.25458	0.25289	0.8238	0.82475	0.55503	0.59704	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45048	45048	SRR6494602	SRX3583928	SRS2852955	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	2.1A	GSM2915044	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	2.1A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915044	GSM2915044: 2.1A; Danio rerio; RNA Seq	GSM2915044		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915044	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	2.1A_R1.fastq.gz 2.1A_R2.fastq.gz	fastq fastq	4648689474.0	45575387.0	GSM2915044 r1	0:51 1:51	A:1150739906;C:1156762106;G:1174418869;T:1160455829;N:6312764	51	51	1150739906	1156762106	1174418869	1160455829	6312764	SRX3583928	SRS2852955	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.93443	0.9425	0.3037	0.30192	0.81675	0.82035	0.5641	0.55492	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45049	45049	SRR6494601	SRX3583927	SRS2852953	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	8.3B	GSM2915043	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	8.3B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915043	GSM2915043: 8.3B; Danio rerio; RNA Seq	GSM2915043		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915043	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	8.3B_R1.fastq.gz 8.3B_R2.fastq.gz	fastq fastq	4463531424.0	43760112.0	GSM2915043 r1	0:51 1:51	A:1113035544;C:1103847188;G:1123396000;T:1117789326;N:5463366	51	51	1113035544	1103847188	1123396000	1117789326	5463366	SRX3583927	SRS2852953	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.94125	0.95133	0.17024	0.16786	0.78924	0.79255	0.54779	0.54529	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45050	45050	SRR6494600	SRX3583926	SRS2852954	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	8.3A	GSM2915042	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	8.3A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915042	GSM2915042: 8.3A; Danio rerio; RNA Seq	GSM2915042		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915042	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	8.3A_R1.fastq.gz 8.3A_R2.fastq.gz	fastq fastq	4393347876.0	43072038.0	GSM2915042 r1	0:51 1:51	A:1076247371;C:1106828053;G:1120376486;T:1083936462;N:5959504	51	51	1076247371	1106828053	1120376486	1083936462	5959504	SRX3583926	SRS2852954	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.94915	0.95442	0.17122	0.16696	0.79732	0.79744	0.56274	0.56769	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45051	45051	SRR6494599	SRX3583925	SRS2852951	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	4.3.1B	GSM2915041	tissue:Leukemia cells\|replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	4.3.1B	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:2\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915041	GSM2915041: 4.3.1B; Danio rerio; RNA Seq	GSM2915041		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915041	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	4.3.1B_R1.fastq.gz 4.3.1B_R2.fastq.gz	fastq fastq	4233856698.0	41508399.0	GSM2915041 r1	0:51 1:51	A:970446998;C:1135557372;G:1151321697;T:971335057;N:5195574	51	51	970446998	1135557372	1151321697	971335057	5195574	SRX3583925	SRS2852951	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.95681	0.961	0.26557	0.26012	0.83114	0.83201	0.65416	0.67322	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45052	45052	SRR6494598	SRX3583924	SRS2852952	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	4.3.1A	GSM2915040	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	4.3.1A	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915040	GSM2915040: 4.3.1A; Danio rerio; RNA Seq	GSM2915040		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915040	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	4.3.1A_R1.fastq.gz 4.3.1A_R2.fastq.gz	fastq fastq	4108362222.0	40278061.0	GSM2915040 r1	0:51 1:51	A:1008174247;C:1035055287;G:1046840431;T:1012717124;N:5575133	51	51	1008174247	1035055287	1046840431	1012717124	5575133	SRX3583924	SRS2852952	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.9417	0.94731	0.22098	0.21709	0.7949	0.79395	0.54887	0.56412	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45053	45053	SRR6494597	SRX3583923	SRS2852950	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	14.1.1.1	GSM2915039	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	14.1.1.1	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915039	GSM2915039: 14.1.1.1; Danio rerio; RNA Seq	GSM2915039		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915039	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	14.1.1.1_R1.fastq.gz 14.1.1.1_R2.fastq.gz	fastq fastq	4028614440.0	39496220.0	GSM2915039 r1	0:51 1:51	A:992630443;C:1013600907;G:1022333543;T:994338823;N:5710724	51	51	992630443	1013600907	1022333543	994338823	5710724	SRX3583923	SRS2852950	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.93918	0.94567	0.25463	0.2502	0.8045	0.80764	0.56238	0.57046	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
45054	45054	SRR6494596	SRX3583922	SRS2853033	SRP130950	PRJNA428951	Cell of origin dictates aggression and stem cell activity in acute lymphoblastic leukemia	GSE108855	Transcriptome Analysis	Subclassification of lymphoid neoplasms is often based on the presumed cell of origin based on T and B progenitor gene expression and the effect of cell lineage on influencing functional characteristics such as aggression and self renewal capacity is largely unknown accounted for in part by lack of experimental models to address these questions. Here we have used transgenic zebrafish to create the first models of Myc induced B ALL and mixed phenotypic B/T ALL opening new avenues for studying the these leukemias in the zebrafish. Our work has utilized syngeneic strain zebrafish limiting dilution cell transplantation and the widely reported rag2 Myc transgenic model to provide new understanding of how strain differences can underlie leukemia onset in the zebrafish model. Even more importantly our work now for the first time has allowed assessment of cell lineage on dictating aggression and leukemia stem cell frequency independent of the underlying oncogenic driver. In total our work uncoveres that T ALLs are more aggressive and have higher numbers of leukemia stem cells when compared with B ALL and mixed phenotypic ALL. Furthermore analysis of our biphenotypic B/T ALL suggests that B cell pathways lock cells in less aggressive and lower stem cell fates and are dominant in regulating these processes when T cell pathways are co regulated within ALL cells. Overall design: The goal of our study is to determine the transcriptional profiles of high and low self renewing capacity tumors. 20 samples total: 11 unique samples 9 samples with biological replicates 6 high self renewing tumors >1% cells could initiate leukemia and 5 low self renewing tumors <1% of cells could initiate leukemia.		pubmed:29749398	8.4.1.1.1	GSM2915038	tissue:Leukemia cells\|replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	8.4.1.1.1	Demultiplexed reads were aligned using STARDobin et al. 2013 to GRCz10. We used picard to filter out PCR duplicates and also removed reads aligning to rRNA intervals. We then assigned counts to each gene using featureCountsLiao Y Smyth GK and Shi W 2014. Genome build: GRCz10 Supplementary files format and content: count matrix provided as supplementary file	Leukemia cells		Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.		replicate number:1\|self renewal capacity:high\|background strain:CG1\|cell type:blood	GSM2915038	GSM2915038: 8.4.1.1.1; Danio rerio; RNA Seq	GSM2915038		1	Leukemia cell pellets were mixed 350ul of QIAGEN RLT buffer containing 1% 2 mercaptoethanol followed by RNA isolation using the RNAeasy Mini kit QIAGEN. RNA samples were prepped and sequenced on the Illumina HiSeq 2000 platform as previously described in Tang et al. PMID 28878000. RNA from bulk tumors were reverse transcribed and sequenced on the Illumina HiSeq 2000 platform.	GEO Accession:GSM2915038	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2000	SRP130950	8.4.1.1.1_R1.fastq.gz 8.4.1.1.1_R2.fastq.gz	fastq fastq	4383721014.0	42977657.0	GSM2915038 r1	0:51 1:51	A:1049228460;C:1129994718;G:1142953291;T:1055736129;N:5808416	51	51	1049228460	1129994718	1142953291	1055736129	5808416	SRX3583922	SRS2853033	SRA649887	GEO	Pathology, Massachusetts General Hospital	2	0.95266	0.95783	0.21527	0.20965	0.81357	0.81481	0.5049	0.56239	51	51	B	B	biological fallback assumption	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2018-01-08	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48402	48402	SRR7240617	SRX4146448	SRS3360068	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			cell line B fish	GSM3167490	tissue:melanoma cell line cells in a fish\|time:NA\|type:CEL Seq	cell line B fish	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	melanoma cell line cells in a fish		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:NA\|type:CEL Seq	GSM3167490	GSM3167490: cell line B fish; Danio rerio; RNA Seq	GSM3167490		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167490	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	Efish_R2_001.fastq.gz Efish_R1_001.fastq.gz	fastq fastq	7254277529.0	93829840.0	GSM3167490 r1	0:21.77 1:55.55	A:2013320976;C:1304302014;G:1275408938;T:2658668719;N:2576882	21	55	2013320976	1304302014	1275408938	2658668719	2576882	SRX4146448	SRS3360068	SRA713129	GEO	Yanai, NYU	2	0.35315	0.81249	0.33399	0.25257	0.99222	0.89526	0.4613	0.58245	26	58	T	B	sc-like readlen	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48403	48403	SRR7240616	SRX4146447	SRS3360067	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			cell line B cultured	GSM3167489	tissue:melanoma cell line cells\|time:NA\|type:CEL Seq	cell line B cultured	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	melanoma cell line cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:NA\|type:CEL Seq	GSM3167489	GSM3167489: cell line B cultured; Danio rerio; RNA Seq	GSM3167489		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167489	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	Edish_R1_001.fastq.gz Edish_R2_001.fastq.gz	fastq fastq	3315328468.0	40362508.0	GSM3167489 r1	0:24.95 1:57.19	A:870288472;C:583199815;G:546968405;T:1313319011;N:1552765	24	57	870288472	583199815	546968405	1313319011	1552765	SRX4146447	SRS3360067	SRA713129	GEO	Yanai, NYU	2	0.4358	0.77687	0.41224	0.1804	0.98673	0.92372	0.39048	0.55564	26	58	T	B	sc-like readlen	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48404	48404	SRR7240615	SRX4146446	SRS3360066	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			cell line A fish	GSM3167488	tissue:melanoma cell line cells in a fish\|time:NA\|type:CEL Seq	cell line A fish	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	melanoma cell line cells in a fish		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:NA\|type:CEL Seq	GSM3167488	GSM3167488: cell line A fish; Danio rerio; RNA Seq	GSM3167488		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167488	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	Afish_R1_001.fastq.gz Afish_R2_001.fastq.gz	fastq fastq	1760981184.0	27515331.0	GSM3167488 r1	0:13 1:51	A:527501645;C:354257934;G:378832308;T:500290272;N:99025	13	51	527501645	354257934	378832308	500290272	99025	SRX4146446	SRS3360066	SRA713129	GEO	Yanai, NYU	2	0.0	0.86857	0.0	0.2721	1.0	0.84869		0.53458	13	51	T	B	sc-like readlen	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48405	48405	SRR7240614	SRX4146445	SRS3360065	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			cell line A cultured	GSM3167487	tissue:melanoma cell line cells\|time:NA\|type:CEL Seq	cell line A cultured	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	melanoma cell line cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:NA\|type:CEL Seq	GSM3167487	GSM3167487: cell line A cultured; Danio rerio; RNA Seq	GSM3167487		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167487	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	Adish_R1_001.fastq.gz Adish_R2_001.fastq.gz	fastq fastq	2758577088.0	43102767.0	GSM3167487 r1	0:13 1:51	A:901840607;C:537128308;G:580843998;T:738597709;N:166466	13	51	901840607	537128308	580843998	738597709	166466	SRX4146445	SRS3360065	SRA713129	GEO	Yanai, NYU	2	0.0	0.73258	0.0	0.1063	1.0	0.85865		0.58942	13	51	T	B	sc-like readlen	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48406	48406	SRR7240613	SRX4146444	SRS3360064	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF3 ST	GSM3167486	tissue:tumor tissue section\|time:NA\|type:ST	ZF3 ST	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor tissue section		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:NA\|type:ST	GSM3167486	GSM3167486: ZF3 ST; Danio rerio; RNA Seq	GSM3167486		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167486	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	BS00715A_S4_R1_001.fastq.gz BS00715A_S4_R2_001.fastq.gz	fastq fastq	8346596335.0	108397355.0	GSM3167486 r1	0:31 1:46	A:2031003864;C:1619238171;G:2052969755;T:2622927017;N:20457528	31	46	2031003864	1619238171	2052969755	2622927017	20457528	SRX4146444	SRS3360064	SRA713129	GEO	Yanai, NYU	2	0.0219	0.7716	0.01972	0.18796	0.99429	0.83086	0.55276	0.5937	31	46	T	B	mate1 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48407	48407	SRR7240612	SRX4146443	SRS3360063	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF2 time point 2	GSM3167485	tissue:tumor cells\|time:2017 06 08\|type:inDrop	ZF2 time point 2	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 06 08\|type:inDrop	GSM3167485	GSM3167485: ZF2 time point 2; Danio rerio; RNA Seq	GSM3167485		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167485	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	BS00418A_S2_R1_001.fastq.gz BS00418A_S2_R2_001.fastq.gz	fastq fastq	18879921248.0	219533968.0	GSM3167485 r1	0:35 1:51	A:4915572934;C:4065059620;G:5109553396;T:4789479927;N:255371	35	51	4915572934	4065059620	5109553396	4789479927	255371	SRX4146443	SRS3360063	SRA713129	GEO	Yanai, NYU	2	0.22339	0.01677	0.04998	0.01242	0.904	0.99795	0.64786	0.76205	35	51	B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48408	48408	SRR7240611	SRX4146442	SRS3360062	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF2 time point 1	GSM3167484	tissue:tumor cells\|time:2017 05 25\|type:inDrop	ZF2 time point 1	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 05 25\|type:inDrop	GSM3167484	GSM3167484: ZF2 time point 1; Danio rerio; RNA Seq	GSM3167484		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167484	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	BS00417A_S1_R1_001.fastq.gz BS00417A_S1_R2_001.fastq.gz	fastq fastq	15195762260.0	176694910.0	GSM3167484 r1	0:35 1:51	A:3730288221;C:3100069649;G:3917397047;T:4447806244;N:201099	35	51	3730288221	3100069649	3917397047	4447806244	201099	SRX4146442	SRS3360062	SRA713129	GEO	Yanai, NYU	2	0.45584	0.02194	0.10866	0.01434	0.8508	0.99594	0.56562	0.74387	35	51	B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48409	48409	SRR7240610	SRX4146441	SRS3360061	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF1 tumor 2 time point 3	GSM3167483	tissue:tumor cells\|time:2017 06 22\|type:inDrop	ZF1 tumor 2 time point 3	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 06 22\|type:inDrop	GSM3167483	GSM3167483: ZF1 tumor 2 time point 3; Danio rerio; RNA Seq	GSM3167483		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167483	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	BS00516A_S3_R1_001.fastq.gz BS00516A_S3_R2_001.fastq.gz	fastq fastq	9387695500.0	109159250.0	GSM3167483 r1	0:35 1:51	A:1996385781;C:1819073805;G:2713262409;T:2858501572;N:471933	35	51	1996385781	1819073805	2713262409	2858501572	471933	SRX4146441	SRS3360061	SRA713129	GEO	Yanai, NYU	2	0.78336	0.12929	0.17042	0.07562	0.83116	0.98196	0.62361	0.7167	35	51	B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48410	48410	SRR7240609	SRX4146440	SRS3360060	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF1 tumor 2 time point 2	GSM3167482	tissue:tumor cells\|time:2017 06 15\|type:inDrop	ZF1 tumor 2 time point 2	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 06 15\|type:inDrop	GSM3167482	GSM3167482: ZF1 tumor 2 time point 2; Danio rerio; RNA Seq	GSM3167482		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167482	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	BS00515A_S2_R1_001.fastq.gz BS00515A_S2_R2_001.fastq.gz	fastq fastq	7645768166.0	88904281.0	GSM3167482 r1	0:35 1:51	A:1659830380;C:1483879485;G:1955626018;T:2546036303;N:395980	35	51	1659830380	1483879485	1955626018	2546036303	395980	SRX4146440	SRS3360060	SRA713129	GEO	Yanai, NYU	2	0.78059	0.04637	0.15414	0.03167	0.81156	0.99125	0.5786	0.82113	35	51	B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48411	48411	SRR7240608	SRX4146439	SRS3360059	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF1 tumor 2 time point 1	GSM3167481	tissue:tumor cells\|time:2017 06 02\|type:inDrop	ZF1 tumor 2 time point 1	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 06 02\|type:inDrop	GSM3167481	GSM3167481: ZF1 tumor 2 time point 1; Danio rerio; RNA Seq	GSM3167481		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167481	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	BS00514A_S1_R1_001.fastq.gz BS00514A_S1_R2_001.fastq.gz	fastq fastq	9759139906.0	113478371.0	GSM3167481 r1	0:35 1:51	A:2243979852;C:1912724883;G:2573948349;T:3027979990;N:506832	35	51	2243979852	1912724883	2573948349	3027979990	506832	SRX4146439	SRS3360059	SRA713129	GEO	Yanai, NYU												B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48412	48412	SRR7240607	SRX4146438	SRS3360058	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF1 tumor 1 time point 4	GSM3167480	tissue:tumor cells\|time:2017 06 22\|type:inDrop	ZF1 tumor 1 time point 4	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 06 22\|type:inDrop	GSM3167480	GSM3167480: ZF1 tumor 1 time point 4; Danio rerio; RNA Seq	GSM3167480		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167480	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	t4_R1.fastq.gz t4_R2.fastq.gz	fastq fastq	13285828250.0	154486375.0	GSM3167480 r1	0:35 1:51	A:3106404784;C:2642499289;G:3548717541;T:3987624595;N:582041	35	51	3106404784	2642499289	3548717541	3987624595	582041	SRX4146438	SRS3360058	SRA713129	GEO	Yanai, NYU	2	0.588	0.04697	0.13733	0.02918	0.8308	0.99119	0.59025	0.75017	35	51	B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48413	48413	SRR7240606	SRX4146437	SRS3360057	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF1 tumor 1 time point 3	GSM3167479	tissue:tumor cells\|time:2017 06 15\|type:inDrop	ZF1 tumor 1 time point 3	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 06 15\|type:inDrop	GSM3167479	GSM3167479: ZF1 tumor 1 time point 3; Danio rerio; RNA Seq	GSM3167479		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167479	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	t3_R1.fastq.gz t3_R2.fastq.gz	fastq fastq	12949174972.0	150571802.0	GSM3167479 r1	0:35 1:51	A:3045479995;C:2532873724;G:3340677661;T:4029571801;N:571791	35	51	3045479995	2532873724	3340677661	4029571801	571791	SRX4146437	SRS3360057	SRA713129	GEO	Yanai, NYU	2	0.56814	0.02383	0.11626	0.01895	0.82599	0.99569	0.55364	0.73492	35	51	B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48414	48414	SRR7240605	SRX4146436	SRS3360056	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF1 tumor 1 time point 2	GSM3167478	tissue:tumor cells\|time:2017 06 09\|type:inDrop	ZF1 tumor 1 time point 2	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 06 09\|type:inDrop	GSM3167478	GSM3167478: ZF1 tumor 1 time point 2; Danio rerio; RNA Seq	GSM3167478		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167478	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	t2_R1.fastq.gz t2_R2.fastq.gz	fastq fastq	24232410834.0	281772219.0	GSM3167478 r1	0:35 1:51	A:5863941889;C:4979860831;G:6744452007;T:6643024623;N:1131484	35	51	5863941889	4979860831	6744452007	6643024623	1131484	SRX4146436	SRS3360056	SRA713129	GEO	Yanai, NYU	2	0.36566	0.03272	0.07206	0.03013	0.85719	0.99673	0.55683	0.65034	35	51	B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
48415	48415	SRR7240604	SRX4146435	SRS3360055	SRP149420	PRJNA473915	Single cell analysis of tumor progression reveals the function structure and evolution of cancer archetypes	GSE115140	Transcriptome Analysis	The classic cancer evolution model posits that driver mutations sweep the population sequentially as the complete set of hallmarks are assembled by the neoplastic clone. However recent work has challenged this model revealing that most tumors contain highly complex dynamics with genetic diversity reflecting distinct clonal architectures. The functional and phenotypic heterogeneity also has been shown to have a crucial influence on the fate of the tumor5–10. However it is not well understood how distinct tumor clonal populations coexist and function. Here we study tumor architecture at the level of individual cells by sampling a zebrafish melanoma tumor over time and space. We found that cancer transcriptional programs can be classified to three archetypes each exploiting the existing neural crest mature melanocytes and stress modules and distinct intra tumor locations. Strikingly these archetypes are conserved in human melanoma. Further we found that the cancer cells are comprised of two distinct clones where one expresses a unique archetype. Over time we found that the cells of this clone adapt by exhibiting a more similar profile to the corresponding archetype. Overall design: Single cell RNA sequencing of zebrafish tumor cells from 2 zebrafish at multiple time points.			ZF1 tumor 1 time point 1	GSM3167477	tissue:tumor cells\|time:2017 06 02\|type:inDrop	ZF1 tumor 1 time point 1	Illumina RTA v2 software was used for basecalling and quality determination. Raw sequencing data obtained from the inDrop method was processed using a custom built pipeline available at https://github.com/flo compbio/singlecell. Briefly the location of the known “W1” adapter sequence of the inDrop RT primer was located in the barcode read read 2. Reads for which the W1 sequence could not be detected were discarded. The start position of the W1 sequence was then used to infer the length of the first part of the inDrop cell barcode in each read which can range from 8 11 bp as well as the start position of the second part of the inDrop cell barcode which is 8 bp long. Cell barcode sequences were mapped to the known list of 384 barcode sequences for each read. The resulting barcode combination was used to identify the cell from which the fragment originated. Finally UMI sequence was extracted and reads with low confidence base calls for the six bases comprising the UMI sequence minimum PHRED score less than 20 were discarded. The reads containing the mRNA sequence read 1 were mapped using STAR with parameter “—outSAMmultNmax 1” and default settings otherwise27. Expression was quantified by counting the number of reads mapped to each gene and correcting for UMI as described previously Grün et al. 2014 The genome and gff file used included the zebrafish genome and the BRAF human vector. Single cell transcriptomes with UMIs>750 mitochondrial transcripts < 20% and ribosomal transcripts < 30% were retained for analysis. Raw sequencing data obtained from the Spatial Transcriptomics ST method were processed using a publicly available pipeline https://github.com/jfnavarro/st pipeline. Briefly quality trimming is performed to remove low quality bases and reads with long nucleotide stretches > 15. Read 2 transcript sequence is mapped with STAR 2.5.1 and Read 1 spatial barcode is demultiplexed with Taggd. Reads that contain both a valid spatial barcode and are correctly map are kept. UMIs are then counted with htseq …	tumor cells		For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…		time:2017 06 02\|type:inDrop	GSM3167477	GSM3167477: ZF1 tumor 1 time point 1; Danio rerio; RNA Seq	GSM3167477		1	For inDrop and CEL Seq samples were obtained using a dissecting forceps and placing the desired tissue sample in 1.5 mL Eppendorf tube followed by addition of 500 uL 0.25% Trypsin EDTA for digestion. The digestion was carried out at 37ºC in thermomixer for 15 30 min to soften tissue every 5 minutes mashing the tissue using a disposable pestle to break up softened tissue. Upon completion of incubation at 37ºC 500 uL of DMEM10 were added to deactivate the trypsin. Cells were washed three times by spinning down the sample at 500 rcf for 5 minutes and resuspended in PBS. Then sample was filtered twice using 5 mL polystyrene round bottom tube with 35um cell strainer. Viability and single cell consistency were checked prior to encapsulation of the cells using the inDrop system for each biopsy taken. For the ST sample sections from zebrafish melanoma tumors were obtained by sectioning the entire tumor with its surrounding. Tissue was gently washed with cold 1X PBS and 4 5 mm3 cubes were removed with a scalpel for OCT embedding. Tissue was transferred from 1X PBS to a dry sterile 10 cm dish and gently dried prior to equilibration in cold OCT for 2 minutes. The tissue was then transferred to a tissue mold with OCT and snap frozen in liquid nitrogen chilled isopentane. Tissue blocks were stored at 80°C until further use. Prior to cryosectioning the cryostat was cleaned with 100% ethanol and equilibrated to an internal temperature of 18°C for 30 minutes. Once equilibrated OCT embedded tissue blocks were mounted onto the chuck and equilibrated to the cryostat temperature for 15 20 minutes prior to trimming. ST slide was also placed inside cryostat to keep the slide cold and minimize RNase activity. Sections were cut at 10 µm sections and mounted onto the ST arrays and stored at 80°C until use maximum of two weeks. Prior to fixation and staining the ST array was removed from the 80C and into a RNase free biosafety hood for 5 minutes to bring to room temperature followed by warming on a 37°C heat block for 1 mi…	GEO Accession:GSM3167477	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	NextSeq 500	SRP149420	t1_R1.fastq.gz t1_R2.fastq.gz	fastq fastq	9252930920.0	107592220.0	GSM3167477 r1	0:35 1:51	A:2335222288;C:1982182390;G:2612836318;T:2322125944;N:563980	35	51	2335222288	1982182390	2612836318	2322125944	563980	SRX4146435	SRS3360055	SRA713129	GEO	Yanai, NYU	2	0.23022	0.0283	0.05144	0.02308	0.90254	0.99608	0.58852	0.70642	35	51	B	T	mate2 technical by mapping diff	illumina	nextseq	unknown	random_priming	unknown	sc	single_cell_droplet	indrops	United States	2018-05-31	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50848	50848	SRR8312803	SRX5126180	SRS4139302	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	nonSP 1314	GSM3509262	source name:ALL tumor\|strain:CG2\|tissue:ALL	nonSP 1314	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509262	GSM3509262: nonSP 1314; Danio rerio; RNA Seq	GSM3509262		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509262	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			1102240750.0	22044815.0	GSM3509262 r1	0:50 1:0	A:238366338;C:290902481;G:270336209;T:302466123;N:169599	50	0	238366338	290902481	270336209	302466123	169599	SRX5126180	SRS4139302	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.95733		0.05326		0.82195		0.45391		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50849	50849	SRR8312804	SRX5126180	SRS4139302	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	nonSP 1314	GSM3509262	source name:ALL tumor\|strain:CG2\|tissue:ALL	nonSP 1314	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509262	GSM3509262: nonSP 1314; Danio rerio; RNA Seq	GSM3509262		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509262	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			2100323600.0	42006472.0	GSM3509262 r2	0:50 1:0	A:454665602;C:553824333;G:514968464;T:576182722;N:682479	50	0	454665602	553824333	514968464	576182722	682479	SRX5126180	SRS4139302	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.95581		0.05304		0.82246		0.44598		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50850	50850	SRR8312801	SRX5126179	SRS4139301	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	SP 1314	GSM3509261	source name:ALL tumor\|strain:CG2\|tissue:ALL	SP 1314	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509261	GSM3509261: SP 1314; Danio rerio; RNA Seq	GSM3509261		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509261	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			1795016300.0	35900326.0	GSM3509261 r1	0:50 1:0	A:414364764;C:453952517;G:425127792;T:501295946;N:275281	50	0	414364764	453952517	425127792	501295946	275281	SRX5126179	SRS4139301	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.94054		0.1034		0.77199		0.50665		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50851	50851	SRR8312802	SRX5126179	SRS4139301	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	SP 1314	GSM3509261	source name:ALL tumor\|strain:CG2\|tissue:ALL	SP 1314	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509261	GSM3509261: SP 1314; Danio rerio; RNA Seq	GSM3509261		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509261	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			1643807200.0	32876144.0	GSM3509261 r2	0:50 1:0	A:379875320;C:415331594;G:389155351;T:458912143;N:532792	50	0	379875320	415331594	389155351	458912143	532792	SRX5126179	SRS4139301	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.93812		0.1016		0.77281		0.50853		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50852	50852	SRR8312799	SRX5126178	SRS4139300	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	nonSP 1279	GSM3509260	source name:ALL tumor\|strain:CG2\|tissue:ALL	nonSP 1279	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509260	GSM3509260: nonSP 1279; Danio rerio; RNA Seq	GSM3509260		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509260	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			971515350.0	19430307.0	GSM3509260 r1	0:50 1:0	A:209882045;C:255304153;G:238689373;T:267489989;N:149790	50	0	209882045	255304153	238689373	267489989	149790	SRX5126178	SRS4139300	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.96223		0.08865		0.85437		0.45664		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50853	50853	SRR8312800	SRX5126178	SRS4139300	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	nonSP 1279	GSM3509260	source name:ALL tumor\|strain:CG2\|tissue:ALL	nonSP 1279	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509260	GSM3509260: nonSP 1279; Danio rerio; RNA Seq	GSM3509260		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509260	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			859048800.0	17180976.0	GSM3509260 r2	0:50 1:0	A:185797914;C:225529235;G:211061558;T:236378727;N:281366	50	0	185797914	225529235	211061558	236378727	281366	SRX5126178	SRS4139300	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.96055		0.08804		0.85283		0.48896		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50854	50854	SRR8312797	SRX5126177	SRS4139299	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	SP 1279	GSM3509259	source name:ALL tumor\|strain:CG2\|tissue:ALL	SP 1279	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509259	GSM3509259: SP 1279; Danio rerio; RNA Seq	GSM3509259		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509259	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			843819050.0	16876381.0	GSM3509259 r1	0:50 1:0	A:199287616;C:210295815;G:195583208;T:238522867;N:129544	50	0	199287616	210295815	195583208	238522867	129544	SRX5126177	SRS4139299	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.9391		0.1451		0.79683		0.50281		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50855	50855	SRR8312798	SRX5126177	SRS4139299	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	SP 1279	GSM3509259	source name:ALL tumor\|strain:CG2\|tissue:ALL	SP 1279	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509259	GSM3509259: SP 1279; Danio rerio; RNA Seq	GSM3509259		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509259	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			2285635100.0	45712702.0	GSM3509259 r2	0:50 1:0	A:540527368;C:568996224;G:529423615;T:645948448;N:739445	50	0	540527368	568996224	529423615	645948448	739445	SRX5126177	SRS4139299	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.93725		0.14453		0.79746		0.4961		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50856	50856	SRR8312795	SRX5126176	SRS4139298	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	nonSP 1404	GSM3509258	source name:ALL tumor\|strain:CG2\|tissue:ALL	nonSP 1404	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509258	GSM3509258: nonSP 1404; Danio rerio; RNA Seq	GSM3509258		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509258	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			2069543600.0	41390872.0	GSM3509258 r1	0:50 1:0	A:459382162;C:532071054;G:508544948;T:569228380;N:317056	50	0	459382162	532071054	508544948	569228380	317056	SRX5126176	SRS4139298	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.96095		0.06905		0.83412		0.4818		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50857	50857	SRR8312796	SRX5126176	SRS4139298	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	nonSP 1404	GSM3509258	source name:ALL tumor\|strain:CG2\|tissue:ALL	nonSP 1404	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509258	GSM3509258: nonSP 1404; Danio rerio; RNA Seq	GSM3509258		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509258	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			1547447200.0	30948944.0	GSM3509258 r2	0:50 1:0	A:343821341;C:397523901;G:380174292;T:425426296;N:501370	50	0	343821341	397523901	380174292	425426296	501370	SRX5126176	SRS4139298	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.95838		0.06884		0.83414		0.48727		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50858	50858	SRR8312793	SRX5126175	SRS4139297	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	SP 1404	GSM3509257	source name:ALL tumor\|strain:CG2\|tissue:ALL	SP 1404	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509257	GSM3509257: SP 1404; Danio rerio; RNA Seq	GSM3509257		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509257	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			2020346850.0	40406937.0	GSM3509257 r1	0:50 1:0	A:476259938;C:502400578;G:476364320;T:565010528;N:311486	50	0	476259938	502400578	476364320	565010528	311486	SRX5126175	SRS4139297	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.94163		0.11567		0.79287		0.52008		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
50859	50859	SRR8312794	SRX5126175	SRS4139297	SRP173302	PRJNA509471	The side population enriches for leukemia propagating cell activity and Wnt pathway expression in zebrafish acute lymphoblastic leukemia.	GSE123665	Transcriptome Analysis	Cancer stem cells have been strongly linked to resistance and relapse in many malignancies. However purifying them from within the bulk tumor has been challenging so their precise genetic and functional characteristics are not well defined. The side population assay exploits the ability of some cells to efflux Hoechst dye via ABC transporters. Stem cells have increased expression of these transporters and this assay has been shown to enrich for stem cells in various tissues and cancers. This study identifies the side population within a zebrafish model of acute lymphoblastic leukemia and correlates the frequency of side population cells with the frequency of leukemia stem cells more precisely referred to as leukemia propagating cells within our transplantation model. In addition the side population within the leukemia evolves with serial transplantation increasing in tandem with leukemia propagating cell frequency over subsequent generations. Sorted side population cells from these tumors are enriched for leukemia propagating cells and have enhanced engraftment compared to sorted non side population cells when transplanted into syngeneic recipients. RNA sequencing analysis of sorted side population cells compared to non side population cells identified a shared expression profile within the side population and pathway analysis yielded Wnt signaling as the most overrepresented. Gene set enrichment analysis showed that stem cell differentiation and canonical Wnt signaling were significantly upregulated in the side population. Overall these results demonstrate that the side population in zebrafish acute lymphoblastic leukemia significantly enriches for leukemia propagating cells and identifies the Wnt pathway as a likely genetic driver of leukemia stem cell fate. Overall design: mRNA expression comparison between sorted side population and non side population in 3 zebrafish ALL tumors		pubmed:30630989	SP 1404	GSM3509257	source name:ALL tumor\|strain:CG2\|tissue:ALL	SP 1404	Illumina Casava1.7 software used for basecalling. All RNA seq reads were used to align to the genome assembly GRCz10 using STAR v2.5.1b with default configurations. Transcripts were assembled from the aligned reads using Cufflinks v2.2.1 with the default configurations to generate FPKM Fragments Per Kilobase Million tables. Using 4 as the fold change cutoff DEGs Differentially expressed genes were detected using both Tuxedo suite FPKM based method and featureCounts DESeq v1.30.0 edgeR v3.20.7 read count based method with default configurations. Genes detected by at least more than one method were collected to create a high confidence DEG lists. Genome build: GRCz10 Supplementary files format and content: Count tables were generated using featureCount v1.28.1 based on Ensembl annotation GRCz10.	ALL tumor	None	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	None	strain:CG2\|tissue:ALL	GSM3509257	GSM3509257: SP 1404; Danio rerio; RNA Seq	GSM3509257		1	Tumors were removed sorted by FACS and RNA was harvested using Trizol reagent. RNA libraries were prepared for sequencing using standard Illumina protocols	GEO Accession:GSM3509257	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 4000	SRP173302			1560387300.0	31207746.0	GSM3509257 r2	0:50 1:0	A:368229806;C:387650010;G:367757630;T:436243680;N:506174	50	0	368229806	387650010	367757630	436243680	506174	SRX5126175	SRS4139297	SRA822847	GEO	Bioinformatics Core, Biological Sciences Division, The University of Chicago	1	0.93995		0.11774		0.79444		0.49697		50		B		usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	unknown	bulk	unknown	unknown	United States	2018-12-11	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51886	51886	SRR8928953	SRX5709910	SRS4649081	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TAGCGCTC TCGACTAG primary sc	GSM3730664	source name:mitfa:GFP cells from primary triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GC056829 TAGCGCTC TCGACTAG primary sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from primary triple melanoma		FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GSM3730664	GSM3730664: GC056829 TAGCGCTC TCGACTAG primary sc; Danio rerio; RNA Seq	GSM3730664		1	FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730664	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TAGCGCTC-TCGACTAG.R1.fastq.gz GC056829_TAGCGCTC-TCGACTAG.R2.fastq.gz	fastq fastq	291297384.0	1155942.0	GSM3730664 r1	0:126 1:126	A:75934677;C:69727236;G:68974546;T:76563463;N:97462	126	126	75934677	69727236	68974546	76563463	97462	SRX5709910	SRS4649081	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.91121	0.91015	0.08817	0.08834	0.89858	0.89858	0.51377	0.51817	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51887	51887	SRR8928952	SRX5709909	SRS4649080	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TAGCGCTC CTCTCTAT primary sc	GSM3730663	source name:mitfa:GFP cells from primary triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GC056829 TAGCGCTC CTCTCTAT primary sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from primary triple melanoma		FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GSM3730663	GSM3730663: GC056829 TAGCGCTC CTCTCTAT primary sc; Danio rerio; RNA Seq	GSM3730663		1	FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730663	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TAGCGCTC-CTCTCTAT.R1.fastq.gz GC056829_TAGCGCTC-CTCTCTAT.R2.fastq.gz	fastq fastq	113392440.0	449970.0	GSM3730663 r1	0:126 1:126	A:28731494;C:27721828;G:27545627;T:29349373;N:44118	126	126	28731494	27721828	27545627	29349373	44118	SRX5709909	SRS4649080	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.86439	0.8641	0.04586	0.04637	0.96848	0.96828	0.58025	0.58287	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51888	51888	SRR8928951	SRX5709908	SRS4649079	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TAGCGCTC CCTAGAGT primary sc	GSM3730662	source name:mitfa:GFP cells from primary triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GC056829 TAGCGCTC CCTAGAGT primary sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from primary triple melanoma		FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GSM3730662	GSM3730662: GC056829 TAGCGCTC CCTAGAGT primary sc; Danio rerio; RNA Seq	GSM3730662		1	FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730662	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TAGCGCTC-CCTAGAGT.R1.fastq.gz GC056829_TAGCGCTC-CCTAGAGT.R2.fastq.gz	fastq fastq	192644172.0	764461.0	GSM3730662 r1	0:126 1:126	A:51220771;C:45349495;G:44426842;T:51583802;N:63262	126	126	51220771	45349495	44426842	51583802	63262	SRX5709908	SRS4649079	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.91899	0.91846	0.08338	0.08378	0.9419	0.94205	0.57993	0.58363	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51889	51889	SRR8928950	SRX5709907	SRS4649078	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TAGCGCTC AAGGAGTA regressed sc	GSM3730661	source name:mitfa:GFP cells from regressed triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from regressed triple melanoma	GC056829 TAGCGCTC AAGGAGTA regressed sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from regressed triple melanoma		FACS sorting of a single GFP+ living cell from regression site SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from regressed triple melanoma	GSM3730661	GSM3730661: GC056829 TAGCGCTC AAGGAGTA regressed sc; Danio rerio; RNA Seq	GSM3730661		1	FACS sorting of a single GFP+ living cell from regression site SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730661	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TAGCGCTC-AAGGAGTA.R1.fastq.gz GC056829_TAGCGCTC-AAGGAGTA.R2.fastq.gz	fastq fastq	364945392.0	1448196.0	GSM3730661 r1	0:126 1:126	A:92235356;C:90530535;G:89271040;T:92862459;N:46002	126	126	92235356	90530535	89271040	92862459	46002	SRX5709907	SRS4649078	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.89628	0.89675	0.09274	0.09236	0.94817	0.9483	0.54004	0.54001	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51890	51890	SRR8928949	SRX5709906	SRS4649077	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TACGCTGC TCGACTAG primary sc	GSM3730660	source name:mitfa:GFP cells from primary triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GC056829 TACGCTGC TCGACTAG primary sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from primary triple melanoma		FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GSM3730660	GSM3730660: GC056829 TACGCTGC TCGACTAG primary sc; Danio rerio; RNA Seq	GSM3730660		1	FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730660	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TACGCTGC-TCGACTAG.R1.fastq.gz GC056829_TACGCTGC-TCGACTAG.R2.fastq.gz	fastq fastq	254888928.0	1011464.0	GSM3730660 r1	0:126 1:126	A:65738264;C:61378795;G:60939053;T:66745851;N:86965	126	126	65738264	61378795	60939053	66745851	86965	SRX5709906	SRS4649077	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.87128	0.87129	0.14421	0.1441	0.94194	0.94136	0.52886	0.52491	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51891	51891	SRR8928948	SRX5709905	SRS4649076	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TACGCTGC GTAAGGAG primary sc	GSM3730659	source name:mitfa:GFP cells from primary triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GC056829 TACGCTGC GTAAGGAG primary sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from primary triple melanoma		FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GSM3730659	GSM3730659: GC056829 TACGCTGC GTAAGGAG primary sc; Danio rerio; RNA Seq	GSM3730659		1	FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730659	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TACGCTGC-GTAAGGAG.R1.fastq.gz GC056829_TACGCTGC-GTAAGGAG.R2.fastq.gz	fastq fastq	178712352.0	709176.0	GSM3730659 r1	0:126 1:126	A:46055648;C:43301884;G:42970793;T:46345442;N:38585	126	126	46055648	43301884	42970793	46345442	38585	SRX5709905	SRS4649076	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.86694	0.86633	0.03958	0.03972	0.95808	0.95826	0.52389	0.52822	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51892	51892	SRR8928947	SRX5709904	SRS4649075	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TACGCTGC GAGCCTTA regressed sc	GSM3730658	source name:mitfa:GFP cells from regressed triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from regressed triple melanoma	GC056829 TACGCTGC GAGCCTTA regressed sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from regressed triple melanoma		FACS sorting of a single GFP+ living cell from regression site SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from regressed triple melanoma	GSM3730658	GSM3730658: GC056829 TACGCTGC GAGCCTTA regressed sc; Danio rerio; RNA Seq	GSM3730658		1	FACS sorting of a single GFP+ living cell from regression site SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730658	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TACGCTGC-GAGCCTTA.R2.fastq.gz GC056829_TACGCTGC-GAGCCTTA.R1.fastq.gz	fastq fastq	210371868.0	834809.0	GSM3730658 r1	0:126 1:126	A:53815943;C:51360144;G:50821809;T:54331673;N:42299	126	126	53815943	51360144	50821809	54331673	42299	SRX5709904	SRS4649075	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.83086	0.83081	0.16142	0.16216	0.95844	0.95893	0.53928	0.54334	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51893	51893	SRR8928946	SRX5709903	SRS4649074	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TACGCTGC CTCTCTAT primary sc	GSM3730657	source name:mitfa:GFP cells from primary triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GC056829 TACGCTGC CTCTCTAT primary sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from primary triple melanoma		FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GSM3730657	GSM3730657: GC056829 TACGCTGC CTCTCTAT primary sc; Danio rerio; RNA Seq	GSM3730657		1	FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730657	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TACGCTGC-CTCTCTAT.R1.fastq.gz GC056829_TACGCTGC-CTCTCTAT.R2.fastq.gz	fastq fastq	267534036.0	1061643.0	GSM3730657 r1	0:126 1:126	A:69417023;C:64596599;G:63565263;T:69859489;N:95662	126	126	69417023	64596599	63565263	69859489	95662	SRX5709903	SRS4649074	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.88641	0.88499	0.13392	0.13421	0.92644	0.92598	0.59348	0.58471	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51894	51894	SRR8928945	SRX5709902	SRS4649073	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TACGCTGC CGTCTAAT regressed sc	GSM3730656	source name:mitfa:GFP cells from regressed triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from regressed triple melanoma	GC056829 TACGCTGC CGTCTAAT regressed sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from regressed triple melanoma		FACS sorting of a single GFP+ living cell from regression site SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from regressed triple melanoma	GSM3730656	GSM3730656: GC056829 TACGCTGC CGTCTAAT regressed sc; Danio rerio; RNA Seq	GSM3730656		1	FACS sorting of a single GFP+ living cell from regression site SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730656	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TACGCTGC-CGTCTAAT.R1.fastq.gz GC056829_TACGCTGC-CGTCTAAT.R2.fastq.gz	fastq fastq	206996328.0	821414.0	GSM3730656 r1	0:126 1:126	A:55682407;C:47711331;G:47331267;T:56217785;N:53538	126	126	55682407	47711331	47331267	56217785	53538	SRX5709902	SRS4649073	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.83219	0.83189	0.27024	0.27104	0.94645	0.94617	0.51275	0.51998	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51895	51895	SRR8928944	SRX5709901	SRS4649072	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TACGCTGC CCTAGAGT primary sc	GSM3730655	source name:mitfa:GFP cells from primary triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GC056829 TACGCTGC CCTAGAGT primary sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from primary triple melanoma		FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GSM3730655	GSM3730655: GC056829 TACGCTGC CCTAGAGT primary sc; Danio rerio; RNA Seq	GSM3730655		1	FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730655	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TACGCTGC-CCTAGAGT.R2.fastq.gz GC056829_TACGCTGC-CCTAGAGT.R1.fastq.gz	fastq fastq	256972212.0	1019731.0	GSM3730655 r1	0:126 1:126	A:66668858;C:61688556;G:60949104;T:67584232;N:81462	126	126	66668858	61688556	60949104	67584232	81462	SRX5709901	SRS4649072	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.88856	0.8877	0.12238	0.12328	0.93324	0.93302	0.48855	0.48825	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor
51896	51896	SRR8928943	SRX5709900	SRS4649071	SRP193005	PRJNA533623	MITF low zebrafish melanomas reveal cells with no MITF activity at the site of residual disease	GSE130037	Transcriptome Analysis	The MITF low melanoma transcriptional signature is predictive of poor outcome for patients but little is known about its biological signature. We used genetic models of zebrafish with low expression of mitfa MITF low to study this biological subtype. We performed whole bulk RNA seq to classify zebrafish MITF low melanoma that cluster mainly by their directionality of growth and assess their resemblance to patients' MITF low subgroups. Furthermore using genetic inhibition of MITF activity we discover minimal residual disease at the site of regression and using single cell and low input RNA seq we characterise these MITF independent cells and show that they pre exist in the primary tumour. Overall design: We performed bulk RNAseq experiment of zebrafish primary melanomas to compare different phenotypes based on directionality of growth or original mutations. Further we performed single cell RNAseq of primary and regressed melanoma.		pubmed:31582381	GC056829 TAAGGCGA GTAAGGAG primary sc	GSM3730654	source name:mitfa:GFP cells from primary triple melanoma\|genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GC056829 TAAGGCGA GTAAGGAG primary sc	Sequence quality was checked using FastQC version 0.11.4. Raw reads were trimmed using Cutadapt to remove Smart Seq2 adaptor sequences. The trimmed reads were mapped using STAR to the reference genome version GRCz11 Ensembl V92 20178 including coding sequences for EGFP and hsBRAFV600E and point mutations in p53 and mitfa. Aligned reads were quantified using Salmon in the alignment based mode. Illumina software used for basecalling. Sequence quality was checked using FastQC version 0.11.3 Reads were aligned to the zebrafish genome GRCz11 using STAR STAR 2.5.1b with the default parameters or using Salmon in the alignment based mode The quality of the resulting alignment to the transcriptome Ensembl annotation version GRCz11 has been checked using RNASeqQC v1.1.8.1 Raw counts of reads covering the transcriptome Ensembl annotation version GRCz11 was obtained using htseq count 0.6.1 with the “ s reverse” option. Genome build: Zebrafish GRCz11 Supplementary files format and content: tab delimited filed of raw counts at gene level for each sample	mitfa:GFP cells from primary triple melanoma		FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads		genotype:mitfa:BRAFV600E;mitfavc7;p53M214K\|tissue:GFP+ cell from primary triple melanoma	GSM3730654	GSM3730654: GC056829 TAAGGCGA GTAAGGAG primary sc; Danio rerio; RNA Seq	GSM3730654		1	FACS sorting of a single GFP+ living cell from primary tumour SMARTseq2 Picelli et al 2014 polyA selection cDNA TruSeq or Nextera XT RNA Seq Paired end reads	GEO Accession:GSM3730654	RNA-Seq	TRANSCRIPTOMIC	cDNA	PAIRED	ILLUMINA	Illumina HiSeq 2500	SRP193005	GC056829_TAAGGCGA-GTAAGGAG.R1.fastq.gz GC056829_TAAGGCGA-GTAAGGAG.R2.fastq.gz	fastq fastq	260808408.0	1034954.0	GSM3730654 r1	0:126 1:126	A:66411357;C:64521343;G:62517949;T:67296408;N:61351	126	126	66411357	64521343	62517949	67296408	61351	SRX5709900	SRS4649071	SRA876955	GEO	Prof. Patton lab, MRC Institute of Genetics and Molecular Medicine, MRC Human Genetics Unit & Cancer Research UK EC	2	0.86131	0.86176	0.04877	0.04898	0.91277	0.91269	0.51465	0.52571	126	126	B	B	biological fallback assumption	illumina	hiseq_era	unknown	poly_a	nextera	sc	single_cell_plate	smartseq	United Kingdom	2019-04-18	Undetermined	Undetermined	Cancer or Tumor	Cancer or Tumor

Advanced export

JSON shape: default, array, newline-delimited

CREATE TABLE run_metadata("run.accession" VARCHAR, "experiment.accession" VARCHAR, "sample.accession" VARCHAR, "study.accession" VARCHAR, bioproject VARCHAR, "study.title" VARCHAR, "study.alias" VARCHAR, "study.type" VARCHAR, "study.abstract" VARCHAR, "study.attributes" VARCHAR, "study.PMIDs" VARCHAR, "sample.description" VARCHAR, "sample.title" VARCHAR, "sample.alias" VARCHAR, "sample.centername" VARCHAR, "sample.attributes" VARCHAR, "GEOsample.title" VARCHAR, "GEOsample.dataprocessing" VARCHAR, "GEOsample.source" VARCHAR, "GEOsample.treatmentprotocol" VARCHAR, "GEOsample.extractprotocol" VARCHAR, "GEOsample.growthprotocol" VARCHAR, "GEOsample.characteristics" VARCHAR, "GEOsample.accession" VARCHAR, "experiment.title" VARCHAR, "experiment.alias" VARCHAR, "experiment.library_name" VARCHAR, "experiment.design_description" VARCHAR, "experiment.library_construction_protocol" VARCHAR, "experiment.attributes" VARCHAR, "experiment.library_strategy" VARCHAR, "experiment.library_source" VARCHAR, "experiment.library_selection" VARCHAR, "experiment.library_layout" VARCHAR, "experiment.platform" VARCHAR, "experiment.instrument_model" VARCHAR, "experiment.spot_descriptor" VARCHAR, "experiment.study_ref" VARCHAR, "run.title" VARCHAR, "run.attributes" VARCHAR, "run.filename" VARCHAR, "run.semantic_name" VARCHAR, "run.total_bases" DOUBLE, "run.total_spots" DOUBLE, "run.alias" VARCHAR, "run.read_lengths" VARCHAR, "run.base_counts" VARCHAR, "run.r1_length" BIGINT, "run.r2_length" BIGINT, "run.r3_length" BIGINT, "run.r4_length" BIGINT, "run.Acount" BIGINT, "run.Ccount" BIGINT, "run.Gcount" BIGINT, "run.Tcount" BIGINT, "run.Ncount" BIGINT, "run.experiment" VARCHAR, "run.pool_member" VARCHAR, "submission.accession" VARCHAR, "submission.srasource" VARCHAR, "submission.bioprojectsource" VARCHAR, "seqdetective.n_mates" BIGINT, "seqdetective.mapping_rate.mate1" DOUBLE, "seqdetective.mapping_rate.mate2" DOUBLE, "seqdetective.nofeature_rate.mate1" DOUBLE, "seqdetective.nofeature_rate.mate2" DOUBLE, "seqdetective.sparsity.mate1" DOUBLE, "seqdetective.sparsity.mate2" DOUBLE, "seqdetective.pos_strand_rate.mate1" DOUBLE, "seqdetective.pos_strand_rate.mate2" DOUBLE, "seqdetective.readlen.mate1" BIGINT, "seqdetective.readlen.mate2" BIGINT, "seqdetective.judgement.mate1" VARCHAR, "seqdetective.judgement.mate2" VARCHAR, "seqdetective.judgement.reason" VARCHAR, platform_family VARCHAR, instrument_generation VARCHAR, read_bias VARCHAR, selection_class VARCHAR, prep_kit VARCHAR, sc_or_bulk VARCHAR, tech_class VARCHAR, technology VARCHAR, tech_variant VARCHAR, "submission.bioprojectsource.country" VARCHAR, earliest_date DATE, devstage_curation VARCHAR, devstage_curation_coarse VARCHAR, tissue_curation VARCHAR, tissue_curation_coarse VARCHAR);;
CREATE INDEX idx_run_bioproject ON run_metadata(bioproject);;
CREATE INDEX idx_run_run_accession ON run_metadata("run.accession");;