metadata: run_metadata: 56 rows where experiment.library_layout = "SINGLE", technology = "bulk" and tissue

56 rows where experiment.library_layout = "SINGLE", technology = "bulk" and tissue_curation = "Embryo Imprecise"

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.attributes	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.nofeature_rate.mate1	seqdetective.sparsity.mate1	seqdetective.pos_strand_rate.mate1	seqdetective.readlen.mate1	seqdetective.judgement.mate1	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
28690	28690	SRR26535341	SRX22238472	SRS19292733	SRP468564	PRJNA1032461	A syngeneic spontaneous zebrafish model oftp53 deficient EGFRviii and PI3KCAH1047R driven glioblastoma reveals inhibitory roles for inflammation during tumor initiation and relapsein vivo	GSE246295	Transcriptome Analysis	To build a patient relevantin vivomodel of human glioblastoma we expressed common oncogenic variants including activated human EGFRviii or KRAS and PI3KCAH1047Runder the control of the radial glial specific promoterher4.1in syngeneictp53loss of function mutant zebrafish.Robust tumor formation was observed prior to 45 days of life with a gene expression signature similar to human glioblastoma of the mesenchymal subtype along with a strong inflammatory component. Within early stage tumor lesions and in an intact and endogenous tumor microenvironment we visualized infiltration of phagocytic cells as well as internalization of tumor cells bympeg1.1:GFP+ microglia/macrophages suggesting negative regulatory pressure by pro inflammatory cell types on tumor growth at early stages of glioblastoma initiationin vivo. Furthermore CRISPR/Cas9 mediated gene targeting of master inflammatory transcription factorsirf7andirf8led to increased tumor formation in the primary context while suppression of microglial/macrophage activity led to enhanced tumor cell engraftment following transplantation into otherwise immune competent zebrafish hosts. Altogether we developed a genetically relevant model of aggressive human glioblastoma and harnessed the unique advantages of zebrafish including live imaging high throughput genetic and chemical manipulations to highlight important tumor suppressive roles for the innate immune system on glioblastoma initiation with important future significance for therapeutic discovery and optimizations. Overall design: To capture broad transcriptomic differences in tumor burdened brains versus normal brains we performed bulk RNA sequencing and gene expression analysis of whole brains and sorted cells. EGFRviii derived tumors were induced by microinjection of EGFRviii PI3KCAH1047R and mScarlet constructs defined as EPS. KRAS derived tumors were induced by microinjection of KRAS PI3KCAH1047R GFP constructs defined as KPG. Three whole brains positive for fluorescent tumors EPS 1 3 KPG 1 3 a…		pubmed:39052000	Pooled EPS brains mScarlet ve Sorted Cells	GSM7866396	source name:Sorted Cells\|strain:CG1 p53null\|tissue:Sorted Cells\|geo loc name:missing\|collection date:missing	Pooled EPS brains mScarlet ve Sorted Cells	Raw .fastq data was processed using Salmon quantification of transcripts for each sample. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23 with entries manually added for GFP mScarlet EGFRviii KRAS and PI3KCAH1047R transcripts. Samples were then quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Differential gene expression was compared utilizing DESeq2 and GSEA. Assembly: GRCz11 Supplementary files format and content: Tab delimited .csv file including raw counts for all conditions.	Sorted Cells	Fertilized embryos injected with either EPS or KPG construct mix	Dissected brains or sorted cells were immediately put into Trizol. RNA was then extracted and purified utilizing Monarch RNA Cleanup Kit following manufacturer's recommendations Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina according to manufacturer’s recommendations	Zebrafish were housed and reared following approved animal use protocol	strain:CG1 p53null\|tissue:Sorted Cells	GSM7866396	GSM7866396: Pooled EPS brains mScarlet ve Sorted Cells; Danio rerio; RNA Seq	GSM7866396 r1	GSM7866396	1	Dissected brains or sorted cells were immediately put into Trizol. RNA was then extracted and purified utilizing Monarch RNA Cleanup Kit following manufacturer's recommendations Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina according to manufacturer's recommendations		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina NovaSeq 6000	SRP468564	loader:fastq load.py	CS_Neg.fastq.gz	fastq	6384313020.0	63211020.0	GSM7866396 r1	0:101	A:1646899028;C:1504048934;G:1428638008;T:1804712211;N:14839	101		1646899028	1504048934	1428638008	1804712211	14839	SRX22238472	SRS19292733	SRA1740017	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research	1	0.94094	0.14273	0.67416	0.48471	101	B	usable mapping rate	illumina	novaseq_era	unknown	poly_a	unknown	bulk	bulk	bulk	Canada	2023-10-26	Undetermined	Embryo	Embryo Imprecise	All anatomical structures
28691	28691	SRR26535342	SRX22238471	SRS19292732	SRP468564	PRJNA1032461	A syngeneic spontaneous zebrafish model oftp53 deficient EGFRviii and PI3KCAH1047R driven glioblastoma reveals inhibitory roles for inflammation during tumor initiation and relapsein vivo	GSE246295	Transcriptome Analysis	To build a patient relevantin vivomodel of human glioblastoma we expressed common oncogenic variants including activated human EGFRviii or KRAS and PI3KCAH1047Runder the control of the radial glial specific promoterher4.1in syngeneictp53loss of function mutant zebrafish.Robust tumor formation was observed prior to 45 days of life with a gene expression signature similar to human glioblastoma of the mesenchymal subtype along with a strong inflammatory component. Within early stage tumor lesions and in an intact and endogenous tumor microenvironment we visualized infiltration of phagocytic cells as well as internalization of tumor cells bympeg1.1:GFP+ microglia/macrophages suggesting negative regulatory pressure by pro inflammatory cell types on tumor growth at early stages of glioblastoma initiationin vivo. Furthermore CRISPR/Cas9 mediated gene targeting of master inflammatory transcription factorsirf7andirf8led to increased tumor formation in the primary context while suppression of microglial/macrophage activity led to enhanced tumor cell engraftment following transplantation into otherwise immune competent zebrafish hosts. Altogether we developed a genetically relevant model of aggressive human glioblastoma and harnessed the unique advantages of zebrafish including live imaging high throughput genetic and chemical manipulations to highlight important tumor suppressive roles for the innate immune system on glioblastoma initiation with important future significance for therapeutic discovery and optimizations. Overall design: To capture broad transcriptomic differences in tumor burdened brains versus normal brains we performed bulk RNA sequencing and gene expression analysis of whole brains and sorted cells. EGFRviii derived tumors were induced by microinjection of EGFRviii PI3KCAH1047R and mScarlet constructs defined as EPS. KRAS derived tumors were induced by microinjection of KRAS PI3KCAH1047R GFP constructs defined as KPG. Three whole brains positive for fluorescent tumors EPS 1 3 KPG 1 3 a…		pubmed:39052000	Pooled EPS brains mScarlet+ve Sorted Cells	GSM7866395	source name:Sorted Cells\|strain:CG1 p53null\|tissue:Sorted Cells\|geo loc name:missing\|collection date:missing	Pooled EPS brains mScarlet+ve Sorted Cells	Raw .fastq data was processed using Salmon quantification of transcripts for each sample. A “decoy aware” index was built with the Danio rerio transcriptome and genome using the GRCz11 assembly with a k mers length of 23 with entries manually added for GFP mScarlet EGFRviii KRAS and PI3KCAH1047R transcripts. Samples were then quantified with the following arguments: r seqBias mp 3 validateMappings rangeFactorizationBins 4. Differential gene expression was compared utilizing DESeq2 and GSEA. Assembly: GRCz11 Supplementary files format and content: Tab delimited .csv file including raw counts for all conditions.	Sorted Cells	Fertilized embryos injected with either EPS or KPG construct mix	Dissected brains or sorted cells were immediately put into Trizol. RNA was then extracted and purified utilizing Monarch RNA Cleanup Kit following manufacturer's recommendations Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina according to manufacturer’s recommendations	Zebrafish were housed and reared following approved animal use protocol	strain:CG1 p53null\|tissue:Sorted Cells	GSM7866395	GSM7866395: Pooled EPS brains mScarlet+ve Sorted Cells; Danio rerio; RNA Seq	GSM7866395 r1	GSM7866395	1	Dissected brains or sorted cells were immediately put into Trizol. RNA was then extracted and purified utilizing Monarch RNA Cleanup Kit following manufacturer's recommendations Sequence ready polyA enriched libraries were prepared using the NEB Ultra II Directional mRNA prep kit for Illumina according to manufacturer's recommendations		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina NovaSeq 6000	SRP468564	loader:fastq load.py	CS_Pos.fastq.gz	fastq	6221936027.0	61603327.0	GSM7866395 r1	0:101	A:1586867899;C:1467436044;G:1398048259;T:1769569401;N:14424	101		1586867899	1467436044	1398048259	1769569401	14424	SRX22238471	SRS19292732	SRA1740017	Hayes Lab, DSCB, Sickkids Research	Hayes Lab, DSCB, Sickkids Research	1	0.88463	0.14567	0.69126	0.48428	101	B	usable mapping rate	illumina	novaseq_era	unknown	poly_a	unknown	bulk	bulk	bulk	Canada	2023-10-26	Undetermined	Embryo	Embryo Imprecise	All anatomical structures
38348	38348	SRR1785168	SRX864139	SRS834998	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			sphere cells rep1	GSM1600044	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:sphere cells	sphere cells rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:sphere cells	GSM1600044	GSM1600044: sphere cells rep1; Danio rerio; RNA Seq	GSM1600044		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600044	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W10T_1.fastq.gz	fastq	9786365912.0	96894712.0	GSM1600044 r1	0:101	A:2573654910;C:2329556867;G:2311713480;T:2571211477;N:229178	101		2573654910	2329556867	2311713480	2571211477	229178	SRX864139	SRS834998	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.95572	0.05587	0.73657	0.48128	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Blastula	Embryo	Embryo Imprecise	All anatomical structures
38349	38349	SRR1785167	SRX864138	SRS834995	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			1000 cell rep1	GSM1600043	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:1000 cells	1000 cell rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:1000 cells	GSM1600043	GSM1600043: 1000 cell rep1; Danio rerio; RNA Seq	GSM1600043		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600043	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W9T_1.fastq.gz	fastq	8394219282.0	83111082.0	GSM1600043 r1	0:101	A:2195214424;C:2012486651;G:1991514912;T:2194810285;N:193010	101		2195214424	2012486651	1991514912	2194810285	193010	SRX864138	SRS834995	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.95627	0.02474	0.75761	0.47804	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Blastula	Embryo	Embryo Imprecise	All anatomical structures
38350	38350	SRR1785166	SRX864137	SRS834994	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			256 cell rep1	GSM1600042	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:256 cell	256 cell rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:256 cell	GSM1600042	GSM1600042: 256 cell rep1; Danio rerio; RNA Seq	GSM1600042		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600042	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W8T_1.fastq.gz	fastq	7155728901.0	70848801.0	GSM1600042 r1	0:101	A:1868886025;C:1718971317;G:1698634177;T:1869072256;N:165126	101		1868886025	1718971317	1698634177	1869072256	165126	SRX864137	SRS834994	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.95828	0.02188	0.76307	0.47861	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Blastula	Embryo	Embryo Imprecise	All anatomical structures
38351	38351	SRR1785165	SRX864136	SRS835002	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			128 cell rep1	GSM1600041	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:128 cell	128 cell rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:128 cell	GSM1600041	GSM1600041: 128 cell rep1; Danio rerio; RNA Seq	GSM1600041		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600041	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W7T_1.fastq.gz	fastq	11606209465.0	114912965.0	GSM1600041 r1	0:101	A:2959737203;C:2867533898;G:2855568487;T:2922947397;N:422480	101		2959737203	2867533898	2855568487	2922947397	422480	SRX864136	SRS835002	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.95887	0.01798	0.76824	0.47695	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Blastula	Embryo	Embryo Imprecise	All anatomical structures
38352	38352	SRR1785164	SRX864135	SRS834996	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			64 cell rep1	GSM1600040	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:64 cell	64 cell rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:64 cell	GSM1600040	GSM1600040: 64 cell rep1; Danio rerio; RNA Seq	GSM1600040		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600040	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W6T_1.fastq.gz	fastq	8895665799.0	88075899.0	GSM1600040 r1	0:101	A:2214065560;C:2252759233;G:2253964784;T:2174045976;N:830246	101		2214065560	2252759233	2253964784	2174045976	830246	SRX864135	SRS834996	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.96228	0.0252	0.77481	0.4855	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Cleavage	Embryo	Embryo Imprecise	All anatomical structures
38353	38353	SRR1785163	SRX864134	SRS834991	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			16 cell rep1	GSM1600039	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:16 cell	16 cell rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:16 cell	GSM1600039	GSM1600039: 16 cell rep1; Danio rerio; RNA Seq	GSM1600039		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600039	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W5T_1.fastq.gz	fastq	8981816880.0	88928880.0	GSM1600039 r1	0:101	A:2337146004;C:2178908640;G:2150713936;T:2314829776;N:218524	101		2337146004	2178908640	2150713936	2314829776	218524	SRX864134	SRS834991	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.94918	0.02746	0.76264	0.50197	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Cleavage	Embryo	Embryo Imprecise	All anatomical structures
38354	38354	SRR1785162	SRX864133	SRS834990	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			4 cell rep1	GSM1600038	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:4 cell	4 cell rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:4 cell	GSM1600038	GSM1600038: 4 cell rep1; Danio rerio; RNA Seq	GSM1600038		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600038	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W4T_1.fastq.gz	fastq	13975600381.0	138372281.0	GSM1600038 r1	0:101	A:3535785422;C:3493456274;G:3501455121;T:3443583783;N:1319781	101		3535785422	3493456274	3501455121	3443583783	1319781	SRX864133	SRS834990	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.96034	0.01453	0.80397	0.48159	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Cleavage	Embryo	Embryo Imprecise	All anatomical structures
38355	38355	SRR1785161	SRX864132	SRS834993	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			1 cell rep1	GSM1600037	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:1 cell	1 cell rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:1 cell	GSM1600037	GSM1600037: 1 cell rep1; Danio rerio; RNA Seq	GSM1600037		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600037	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W3T_1.fastq.gz	fastq	4678817425.0	46324925.0	GSM1600037 r1	0:101	A:1226268061;C:1122155105;G:1116587571;T:1213657606;N:149082	101		1226268061	1122155105	1116587571	1213657606	149082	SRX864132	SRS834993	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.95665	0.0188	0.83631	0.49048	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Undetermined	Embryo	Embryo Imprecise	All anatomical structures
38356	38356	SRR1785160	SRX864131	SRS834992	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			oocyte cells rep1	GSM1600036	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:oocyte cells	oocyte cells rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:oocyte cells	GSM1600036	GSM1600036: oocyte cells rep1; Danio rerio; RNA Seq	GSM1600036		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600036	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W2T_1.fastq.gz	fastq	6479637628.0	64154828.0	GSM1600036 r1	0:101	A:1673078599;C:1583189342;G:1563072444;T:1660074744;N:222499	101		1673078599	1583189342	1563072444	1660074744	222499	SRX864131	SRS834992	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.96179	0.02299	0.80052	0.48738	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Zygote	Embryo	Embryo Imprecise	All anatomical structures
38357	38357	SRR1785159	SRX864130	SRS834997	SRP053099	PRJNA274362	Transcriptomics analysis of gene expression in 10 embryo development stages of Danio rerio	GSE65556	Transcriptome Analysis	RNA was isolated from Danio embryo cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100. All samples showed a RIN RNA integrity number of higher than 9. Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer's protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 101 bp. Sequencing chemistry v2 Illumina was used and samples were multiplexed in two samples per lane. Overall design: Examination of gene expressive levels in embryo development of Danio			sperm cells rep1	GSM1600035	tissue:Danio embryo cells\|developmental stage:embryo\|cell type:sperm cells	sperm cells rep1	Reads were aligned to theZv9 genome assembly using TopHat v2.0.9 For each sample RPKM was computed as the number of reads which map per kilobase of exon model per million mapped reads for each gene. Genome build: Zv9 Supplementary files format and content: RPKM for each gene in each development stage	Danio embryo cells		RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.		developmental stage:embryo\|cell type:sperm cells	GSM1600035	GSM1600035: sperm cells rep1; Danio rerio; RNA Seq	GSM1600035		1	RNA was isolated from Danio cells using the TRIzol Invitrogen reagent by following the company manual. For all samples the RNA integrity was checked using an Agilent Bioanalyzer 2100 Approximately 2.5 µg of total RNA was then used for library preparation using a TruSeq™ RNA Sample Prep Kit v2 Illumina San Diego CA USA according to the manufacturer’s protocol.The libraries were sequenced using HiSeq2000 Illumina in single read mode creating reads with a length of 50 bp.	GEO Accession:GSM1600035	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	Illumina HiSeq 2000	SRP053099		W1T_1.fastq.gz	fastq	5332672841.0	52798741.0	GSM1600035 r1	0:101	A:1401445230;C:1274787038;G:1282323111;T:1373844821;N:272641	101		1401445230	1274787038	1282323111	1373844821	272641	SRX864130	SRS834997	SRA236187	GEO	Beijing Institute of Genomics (BIG) of Chinese Academy of Sciences (CAS)	1	0.92774	0.08051	0.66204	0.5063	101	B	usable mapping rate	illumina	hiseq_era	unknown	cdna_unspecified	trueseq	bulk	bulk	bulk	China	2015-02-03	Zygote	Embryo	Embryo Imprecise	All anatomical structures
52139	52139	SRR8945527	SRX5725657	SRS4663725	SRP193485	PRJNA534270	Genome wide strategies reveal downstream target genes of Npas4l associated with cardiovascular development in zebrafish [RNA Seq 2]	GSE130200	Transcriptome Analysis	The development of a vascular network is essential to nourish tissues and sustain organ function throughout life. Endothelial cells ECs are the building blocks of blood vessels yet our understanding of EC specification in vertebrates remains incomplete. cloche/npas4l mutants have broadly been used as an avascular model in zebrafish but little is known about the molecular mechanism of action of Npas4l. Here to identify the direct and indirect target genes of this transcription factor we combined complementary genome wide approaches including transcriptome analyses and chromatin immunoprecipitation ChIP. The cross analysis of these datasets indicate that Npas4l functions as a master regulator by directly inducing a wave of transcription factor genes crucial for hematoendothelial specification in vertebrates including etv2 tal1 and lmo2. We identified additional target genes acting downstream of npas4l and investigated the function of a subset of them using CRISPR/Cas9 technology. Phenotypic characterization of tspan18b mutants reveals a novel role for tspan18b in developmental angiogenesis confirming the reliability of the datasets generated. Collectively these data represent a useful resource for future studies aimed to investigate novel genes with a potential role in vascular development and EC fate determination in vertebrates. Overall design: RNA seq examination of Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 zebrafish embryos at 6 somite stage in duplicates.	parent bioproject:PRJNA534269	pubmed:31097478	Cre Injected 2	GSM3733699	tissue:Embryo\|genotype:Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 injected with Cre to induce recombinase	Cre Injected 2	The resulting raw reads were assessed for quality adapter content and duplication rates with FastQC 0.11.8 Andrews S. 2010 FastQC: a quality control tool for high throughput sequence data. Available online at: http://www.bioinformatics.babraham.ac.uk/projects/fastqc. Trimmomatic version 0.36 was employed to trim reads post a quality drop below a mean of Q15 in a window of 5 nucleotides Bolger et al. Trimmomatic: a flexible trimmer for Illumina sequence data. Only reads longer than 15 nucleotides were cleared for further analyses. Trimmed and filtered reads were aligned versus the Ensembl Zebrafish genome version DanRer11 GRCz11 using STAR 2.6.0c with the parameter “ outFilterMismatchNoverLmax 0.1” to increase the maximum ratio of mismatches to mapped length to 10% Dobin et al. STAR: ultrafast universal RNA seq aligner. The number of reads aligning to genes was counted with featureCounts 1.6.0 from the Subread package Liao et al. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Only reads mapping at least partially inside exons were admitted and aggregated per gene. Reads overlapping multiple genes or aligning to multiple regions were excluded. Differentially expressed genes were identified using DESeq2 version 1.14.1 Love et al. Moderated estimation of fold change and dispersion for RNA Seq data with DESeq2. The Ensemble annotation was enriched with UniProt data release 12.04.2018 based on Ensembl gene identifiers Activities at the Universal Protein Resource UniProt. Genome build: danrer11 / GRCz11 Supplementary files format and content: The tab delimited matrix with DESeq normalized counts.	Embryo	Fish embryos raised at 28 ̊C were subject to a 37 ̊C heat shock for 1 hr by replacing the egg water with pre warmed 37 ̊C egg water starting at different time points and then keeping them in a 37 ̊C incubator.	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 injected with cre at the one cell stage and uninjected were grown in E3 medium at xxx°C until tailbud stage.	genotype:Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 injected with Cre to induce recombinase	GSM3733699	GSM3733699: Cre Injected 2; Danio rerio; RNA Seq	GSM3733699		1	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	GEO Accession:GSM3733699	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP193485		Marass_RNA_lib_inj_2.fastq.gz	fastq	1318624367.0	17749685.0	GSM3733699 r1	0:74.29 1:0	A:320435609;C:333825364;G:380093353;T:284207932;N:62109	74	0	320435609	333825364	380093353	284207932	62109	SRX5725657	SRS4663725	SRA878585	GEO	Bioinformatics, Max Planck Institute for Heart and Lung Research	1	0.93022	0.12203	0.75935	0.65366	75	B	usable mapping rate	illumina	nextseq	full_length	cdna_unspecified	smarter	bulk	bulk	bulk	Germany	2019-04-23	Multi-stage	Embryo	Embryo Imprecise	All anatomical structures
52140	52140	SRR8945526	SRX5725656	SRS4663727	SRP193485	PRJNA534270	Genome wide strategies reveal downstream target genes of Npas4l associated with cardiovascular development in zebrafish [RNA Seq 2]	GSE130200	Transcriptome Analysis	The development of a vascular network is essential to nourish tissues and sustain organ function throughout life. Endothelial cells ECs are the building blocks of blood vessels yet our understanding of EC specification in vertebrates remains incomplete. cloche/npas4l mutants have broadly been used as an avascular model in zebrafish but little is known about the molecular mechanism of action of Npas4l. Here to identify the direct and indirect target genes of this transcription factor we combined complementary genome wide approaches including transcriptome analyses and chromatin immunoprecipitation ChIP. The cross analysis of these datasets indicate that Npas4l functions as a master regulator by directly inducing a wave of transcription factor genes crucial for hematoendothelial specification in vertebrates including etv2 tal1 and lmo2. We identified additional target genes acting downstream of npas4l and investigated the function of a subset of them using CRISPR/Cas9 technology. Phenotypic characterization of tspan18b mutants reveals a novel role for tspan18b in developmental angiogenesis confirming the reliability of the datasets generated. Collectively these data represent a useful resource for future studies aimed to investigate novel genes with a potential role in vascular development and EC fate determination in vertebrates. Overall design: RNA seq examination of Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 zebrafish embryos at 6 somite stage in duplicates.	parent bioproject:PRJNA534269	pubmed:31097478	Cre Injected 1	GSM3733698	tissue:Embryo\|genotype:Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 injected with Cre to induce recombinase	Cre Injected 1	The resulting raw reads were assessed for quality adapter content and duplication rates with FastQC 0.11.8 Andrews S. 2010 FastQC: a quality control tool for high throughput sequence data. Available online at: http://www.bioinformatics.babraham.ac.uk/projects/fastqc. Trimmomatic version 0.36 was employed to trim reads post a quality drop below a mean of Q15 in a window of 5 nucleotides Bolger et al. Trimmomatic: a flexible trimmer for Illumina sequence data. Only reads longer than 15 nucleotides were cleared for further analyses. Trimmed and filtered reads were aligned versus the Ensembl Zebrafish genome version DanRer11 GRCz11 using STAR 2.6.0c with the parameter “ outFilterMismatchNoverLmax 0.1” to increase the maximum ratio of mismatches to mapped length to 10% Dobin et al. STAR: ultrafast universal RNA seq aligner. The number of reads aligning to genes was counted with featureCounts 1.6.0 from the Subread package Liao et al. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Only reads mapping at least partially inside exons were admitted and aggregated per gene. Reads overlapping multiple genes or aligning to multiple regions were excluded. Differentially expressed genes were identified using DESeq2 version 1.14.1 Love et al. Moderated estimation of fold change and dispersion for RNA Seq data with DESeq2. The Ensemble annotation was enriched with UniProt data release 12.04.2018 based on Ensembl gene identifiers Activities at the Universal Protein Resource UniProt. Genome build: danrer11 / GRCz11 Supplementary files format and content: The tab delimited matrix with DESeq normalized counts.	Embryo	Fish embryos raised at 28 ̊C were subject to a 37 ̊C heat shock for 1 hr by replacing the egg water with pre warmed 37 ̊C egg water starting at different time points and then keeping them in a 37 ̊C incubator.	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 injected with cre at the one cell stage and uninjected were grown in E3 medium at xxx°C until tailbud stage.	genotype:Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 injected with Cre to induce recombinase	GSM3733698	GSM3733698: Cre Injected 1; Danio rerio; RNA Seq	GSM3733698		1	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	GEO Accession:GSM3733698	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP193485		Marass_RNA_lib_inj_1.fastq.gz	fastq	1238690565.0	16655617.0	GSM3733698 r1	0:74.37 1:0	A:308225901;C:304528449;G:340420680;T:285472238;N:43297	74	0	308225901	304528449	340420680	285472238	43297	SRX5725656	SRS4663727	SRA878585	GEO	Bioinformatics, Max Planck Institute for Heart and Lung Research	1	0.91996	0.17266	0.75308	0.62697	75	B	usable mapping rate	illumina	nextseq	full_length	cdna_unspecified	smarter	bulk	bulk	bulk	Germany	2019-04-23	Multi-stage	Embryo	Embryo Imprecise	All anatomical structures
52141	52141	SRR8945525	SRX5725655	SRS4663726	SRP193485	PRJNA534270	Genome wide strategies reveal downstream target genes of Npas4l associated with cardiovascular development in zebrafish [RNA Seq 2]	GSE130200	Transcriptome Analysis	The development of a vascular network is essential to nourish tissues and sustain organ function throughout life. Endothelial cells ECs are the building blocks of blood vessels yet our understanding of EC specification in vertebrates remains incomplete. cloche/npas4l mutants have broadly been used as an avascular model in zebrafish but little is known about the molecular mechanism of action of Npas4l. Here to identify the direct and indirect target genes of this transcription factor we combined complementary genome wide approaches including transcriptome analyses and chromatin immunoprecipitation ChIP. The cross analysis of these datasets indicate that Npas4l functions as a master regulator by directly inducing a wave of transcription factor genes crucial for hematoendothelial specification in vertebrates including etv2 tal1 and lmo2. We identified additional target genes acting downstream of npas4l and investigated the function of a subset of them using CRISPR/Cas9 technology. Phenotypic characterization of tspan18b mutants reveals a novel role for tspan18b in developmental angiogenesis confirming the reliability of the datasets generated. Collectively these data represent a useful resource for future studies aimed to investigate novel genes with a potential role in vascular development and EC fate determination in vertebrates. Overall design: RNA seq examination of Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 zebrafish embryos at 6 somite stage in duplicates.	parent bioproject:PRJNA534269	pubmed:31097478	Uninjected 2	GSM3733697	tissue:Embryo\|genotype:Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298	Uninjected 2	The resulting raw reads were assessed for quality adapter content and duplication rates with FastQC 0.11.8 Andrews S. 2010 FastQC: a quality control tool for high throughput sequence data. Available online at: http://www.bioinformatics.babraham.ac.uk/projects/fastqc. Trimmomatic version 0.36 was employed to trim reads post a quality drop below a mean of Q15 in a window of 5 nucleotides Bolger et al. Trimmomatic: a flexible trimmer for Illumina sequence data. Only reads longer than 15 nucleotides were cleared for further analyses. Trimmed and filtered reads were aligned versus the Ensembl Zebrafish genome version DanRer11 GRCz11 using STAR 2.6.0c with the parameter “ outFilterMismatchNoverLmax 0.1” to increase the maximum ratio of mismatches to mapped length to 10% Dobin et al. STAR: ultrafast universal RNA seq aligner. The number of reads aligning to genes was counted with featureCounts 1.6.0 from the Subread package Liao et al. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Only reads mapping at least partially inside exons were admitted and aggregated per gene. Reads overlapping multiple genes or aligning to multiple regions were excluded. Differentially expressed genes were identified using DESeq2 version 1.14.1 Love et al. Moderated estimation of fold change and dispersion for RNA Seq data with DESeq2. The Ensemble annotation was enriched with UniProt data release 12.04.2018 based on Ensembl gene identifiers Activities at the Universal Protein Resource UniProt. Genome build: danrer11 / GRCz11 Supplementary files format and content: The tab delimited matrix with DESeq normalized counts.	Embryo	Fish embryos raised at 28 ̊C were subject to a 37 ̊C heat shock for 1 hr by replacing the egg water with pre warmed 37 ̊C egg water starting at different time points and then keeping them in a 37 ̊C incubator.	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 injected with cre at the one cell stage and uninjected were grown in E3 medium at xxx°C until tailbud stage.	genotype:Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298	GSM3733697	GSM3733697: Uninjected 2; Danio rerio; RNA Seq	GSM3733697		1	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	GEO Accession:GSM3733697	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP193485		Marass_RNA_lib_Ab_2.fastq.gz	fastq	1403915686.0	18892344.0	GSM3733697 r1	0:74.31 1:0	A:317311926;C:374434129;G:413852871;T:298232684;N:84076	74	0	317311926	374434129	413852871	298232684	84076	SRX5725655	SRS4663726	SRA878585	GEO	Bioinformatics, Max Planck Institute for Heart and Lung Research	1	0.92665	0.1128	0.75929	0.67981	74	B	usable mapping rate	illumina	nextseq	full_length	cdna_unspecified	smarter	bulk	bulk	bulk	Germany	2019-04-23	Multi-stage	Embryo	Embryo Imprecise	All anatomical structures
52142	52142	SRR8945524	SRX5725654	SRS4663724	SRP193485	PRJNA534270	Genome wide strategies reveal downstream target genes of Npas4l associated with cardiovascular development in zebrafish [RNA Seq 2]	GSE130200	Transcriptome Analysis	The development of a vascular network is essential to nourish tissues and sustain organ function throughout life. Endothelial cells ECs are the building blocks of blood vessels yet our understanding of EC specification in vertebrates remains incomplete. cloche/npas4l mutants have broadly been used as an avascular model in zebrafish but little is known about the molecular mechanism of action of Npas4l. Here to identify the direct and indirect target genes of this transcription factor we combined complementary genome wide approaches including transcriptome analyses and chromatin immunoprecipitation ChIP. The cross analysis of these datasets indicate that Npas4l functions as a master regulator by directly inducing a wave of transcription factor genes crucial for hematoendothelial specification in vertebrates including etv2 tal1 and lmo2. We identified additional target genes acting downstream of npas4l and investigated the function of a subset of them using CRISPR/Cas9 technology. Phenotypic characterization of tspan18b mutants reveals a novel role for tspan18b in developmental angiogenesis confirming the reliability of the datasets generated. Collectively these data represent a useful resource for future studies aimed to investigate novel genes with a potential role in vascular development and EC fate determination in vertebrates. Overall design: RNA seq examination of Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 zebrafish embryos at 6 somite stage in duplicates.	parent bioproject:PRJNA534269	pubmed:31097478	Uninjected 1	GSM3733696	tissue:Embryo\|genotype:Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298	Uninjected 1	The resulting raw reads were assessed for quality adapter content and duplication rates with FastQC 0.11.8 Andrews S. 2010 FastQC: a quality control tool for high throughput sequence data. Available online at: http://www.bioinformatics.babraham.ac.uk/projects/fastqc. Trimmomatic version 0.36 was employed to trim reads post a quality drop below a mean of Q15 in a window of 5 nucleotides Bolger et al. Trimmomatic: a flexible trimmer for Illumina sequence data. Only reads longer than 15 nucleotides were cleared for further analyses. Trimmed and filtered reads were aligned versus the Ensembl Zebrafish genome version DanRer11 GRCz11 using STAR 2.6.0c with the parameter “ outFilterMismatchNoverLmax 0.1” to increase the maximum ratio of mismatches to mapped length to 10% Dobin et al. STAR: ultrafast universal RNA seq aligner. The number of reads aligning to genes was counted with featureCounts 1.6.0 from the Subread package Liao et al. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Only reads mapping at least partially inside exons were admitted and aggregated per gene. Reads overlapping multiple genes or aligning to multiple regions were excluded. Differentially expressed genes were identified using DESeq2 version 1.14.1 Love et al. Moderated estimation of fold change and dispersion for RNA Seq data with DESeq2. The Ensemble annotation was enriched with UniProt data release 12.04.2018 based on Ensembl gene identifiers Activities at the Universal Protein Resource UniProt. Genome build: danrer11 / GRCz11 Supplementary files format and content: The tab delimited matrix with DESeq normalized counts.	Embryo	Fish embryos raised at 28 ̊C were subject to a 37 ̊C heat shock for 1 hr by replacing the egg water with pre warmed 37 ̊C egg water starting at different time points and then keeping them in a 37 ̊C incubator.	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298 injected with cre at the one cell stage and uninjected were grown in E3 medium at xxx°C until tailbud stage.	genotype:Tghsp70l:loxP STOP loxP npas4l GGGGGLSRS P2A mCherrybns298	GSM3733696	GSM3733696: Uninjected 1; Danio rerio; RNA Seq	GSM3733696		1	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	GEO Accession:GSM3733696	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP193485		Marass_RNA_lib_Ab_1.fastq.gz	fastq	1439519955.0	19389235.0	GSM3733696 r1	0:74.24 1:0	A:306530355;C:398952556;G:440224503;T:293709258;N:103283	74	0	306530355	398952556	440224503	293709258	103283	SRX5725654	SRS4663724	SRA878585	GEO	Bioinformatics, Max Planck Institute for Heart and Lung Research	1	0.93162	0.10646	0.76627	0.68572	75	B	usable mapping rate	illumina	nextseq	full_length	cdna_unspecified	smarter	bulk	bulk	bulk	Germany	2019-04-23	Multi-stage	Embryo	Embryo Imprecise	All anatomical structures
52143	52143	SRR8945523	SRX5725653	SRS4663723	SRP193484	PRJNA534271	Genome wide strategies reveal downstream target genes of Npas4l associated with cardiovascular development in zebrafish [RNA Seq 1]	GSE130199	Transcriptome Analysis	The development of a vascular network is essential to nourish tissues and sustain organ function throughout life. Endothelial cells ECs are the building blocks of blood vessels yet our understanding of EC specification in vertebrates remains incomplete. cloche/npas4l mutants have broadly been used as an avascular model in zebrafish but little is known about the molecular mechanism of action of Npas4l. Here to identify the direct and indirect target genes of this transcription factor we combined complementary genome wide approaches including transcriptome analyses and chromatin immunoprecipitation ChIP. The cross analysis of these datasets indicate that Npas4l functions as a master regulator by directly inducing a wave of transcription factor genes crucial for hematoendothelial specification in vertebrates including etv2 tal1 and lmo2. We identified additional target genes acting downstream of npas4l and investigated the function of a subset of them using CRISPR/Cas9 technology. Phenotypic characterization of tspan18b mutants reveals a novel role for tspan18b in developmental angiogenesis confirming the reliability of the datasets generated. Collectively these data represent a useful resource for future studies aimed to investigate novel genes with a potential role in vascular development and EC fate determination in vertebrates. Overall design: RNA seq examination of wild type and npas4l bns297/bns297 zebrafish embryos at 6 somite stage in duplicates.	parent bioproject:PRJNA534269	pubmed:31097478	Npas4l KO 2	GSM3733690	tissue:Embryo\|genotype:npas4l bns297/bns297	Npas4l KO 2	The resulting raw reads were assessed for quality adapter content and duplication rates with FastQC Andrews S. 2010 FastQC: a quality control tool for high throughput sequence data. Available online at: http://www.bioinformatics.babraham.ac.uk/projects/fastqc. Reaper version 13 100 was employed to trim reads post a quality drop below a mean of Q20 in a window of 10 nucleotides Davis et al. Kraken: A set of tools for quality control and analysis of high throughput sequence data. Only reads between 30 and 150 nucleotides were cleared for further analyses. Trimmed and filtered reads were aligned versus the Ensembl Zebrafish genome version DanRer10 GRCz10.90 using STAR 2.4.0a with the parameter “ outFilterMismatchNoverLmax 0.1” to increase the maximum ratio of mismatches to mapped length to 10% Dobin et al. STAR: ultrafast universal RNA seq aligner. The number of reads aligning to genes was counted with featureCounts 1.4.5 p1 tool from the Subread package Liao et al. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Only reads mapping at least partially inside exons were admitted and aggregated per gene. Reads overlapping multiple genes or aligning to multiple regions were excluded. Differentially expressed genes were identified using DESeq2 version 1.62 Love et al. Moderated estimation of fold change and dispersion for RNA Seq data with DESeq2. The Ensemble annotation was enriched with UniProt data release 06.06.2014 based on Ensembl gene identifiers Activities at the Universal Protein Resource UniProt. Genome build: danRer10 Supplementary files format and content: The tab delimited matrix shows DESeq normalized counts.	Embryo		For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	Wild type AB embryos and npas4lbns297/bns297 were grown in E3 medium at 28°C until 6 somite stage.	genotype:npas4l bns297/bns297	GSM3733690	GSM3733690: Npas4l KO 2; Danio rerio; RNA Seq	GSM3733690		1	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	GEO Accession:GSM3733690	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP193484		NPAS4L-KO_2.fastq.gz	fastq	2188145091.0	30480884.0	GSM3733690 r1	0:71.79 1:0	A:565091244;C:556088129;G:587566739;T:479372691;N:26288	71	0	565091244	556088129	587566739	479372691	26288	SRX5725653	SRS4663723	SRA878584	GEO	Bioinformatics, Max Planck Institute for Heart and Lung Research	1	0.93251	0.36429	0.79344	0.7597	70	B	usable mapping rate	illumina	nextseq	full_length	cdna_unspecified	smarter	bulk	bulk	bulk	Germany	2019-04-23	Segmentation	Embryo	Embryo Imprecise	All anatomical structures
52144	52144	SRR8945522	SRX5725652	SRS4663722	SRP193484	PRJNA534271	Genome wide strategies reveal downstream target genes of Npas4l associated with cardiovascular development in zebrafish [RNA Seq 1]	GSE130199	Transcriptome Analysis	The development of a vascular network is essential to nourish tissues and sustain organ function throughout life. Endothelial cells ECs are the building blocks of blood vessels yet our understanding of EC specification in vertebrates remains incomplete. cloche/npas4l mutants have broadly been used as an avascular model in zebrafish but little is known about the molecular mechanism of action of Npas4l. Here to identify the direct and indirect target genes of this transcription factor we combined complementary genome wide approaches including transcriptome analyses and chromatin immunoprecipitation ChIP. The cross analysis of these datasets indicate that Npas4l functions as a master regulator by directly inducing a wave of transcription factor genes crucial for hematoendothelial specification in vertebrates including etv2 tal1 and lmo2. We identified additional target genes acting downstream of npas4l and investigated the function of a subset of them using CRISPR/Cas9 technology. Phenotypic characterization of tspan18b mutants reveals a novel role for tspan18b in developmental angiogenesis confirming the reliability of the datasets generated. Collectively these data represent a useful resource for future studies aimed to investigate novel genes with a potential role in vascular development and EC fate determination in vertebrates. Overall design: RNA seq examination of wild type and npas4l bns297/bns297 zebrafish embryos at 6 somite stage in duplicates.	parent bioproject:PRJNA534269	pubmed:31097478	Npas4l KO 1	GSM3733689	tissue:Embryo\|genotype:npas4l bns297/bns297	Npas4l KO 1	The resulting raw reads were assessed for quality adapter content and duplication rates with FastQC Andrews S. 2010 FastQC: a quality control tool for high throughput sequence data. Available online at: http://www.bioinformatics.babraham.ac.uk/projects/fastqc. Reaper version 13 100 was employed to trim reads post a quality drop below a mean of Q20 in a window of 10 nucleotides Davis et al. Kraken: A set of tools for quality control and analysis of high throughput sequence data. Only reads between 30 and 150 nucleotides were cleared for further analyses. Trimmed and filtered reads were aligned versus the Ensembl Zebrafish genome version DanRer10 GRCz10.90 using STAR 2.4.0a with the parameter “ outFilterMismatchNoverLmax 0.1” to increase the maximum ratio of mismatches to mapped length to 10% Dobin et al. STAR: ultrafast universal RNA seq aligner. The number of reads aligning to genes was counted with featureCounts 1.4.5 p1 tool from the Subread package Liao et al. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Only reads mapping at least partially inside exons were admitted and aggregated per gene. Reads overlapping multiple genes or aligning to multiple regions were excluded. Differentially expressed genes were identified using DESeq2 version 1.62 Love et al. Moderated estimation of fold change and dispersion for RNA Seq data with DESeq2. The Ensemble annotation was enriched with UniProt data release 06.06.2014 based on Ensembl gene identifiers Activities at the Universal Protein Resource UniProt. Genome build: danRer10 Supplementary files format and content: The tab delimited matrix shows DESeq normalized counts.	Embryo		For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	Wild type AB embryos and npas4lbns297/bns297 were grown in E3 medium at 28°C until 6 somite stage.	genotype:npas4l bns297/bns297	GSM3733689	GSM3733689: Npas4l KO 1; Danio rerio; RNA Seq	GSM3733689		1	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	GEO Accession:GSM3733689	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP193484		NPAS4L-KO_1.fastq.gz	fastq	2433253496.0	33687089.0	GSM3733689 r1	0:72.23 1:0	A:593060668;C:644801659;G:698633749;T:496734812;N:22608	72	0	593060668	644801659	698633749	496734812	22608	SRX5725652	SRS4663722	SRA878584	GEO	Bioinformatics, Max Planck Institute for Heart and Lung Research	1	0.95463	0.30956	0.82254	0.78357	74	B	usable mapping rate	illumina	nextseq	full_length	cdna_unspecified	smarter	bulk	bulk	bulk	Germany	2019-04-23	Segmentation	Embryo	Embryo Imprecise	All anatomical structures
52145	52145	SRR8945521	SRX5725651	SRS4663720	SRP193484	PRJNA534271	Genome wide strategies reveal downstream target genes of Npas4l associated with cardiovascular development in zebrafish [RNA Seq 1]	GSE130199	Transcriptome Analysis	The development of a vascular network is essential to nourish tissues and sustain organ function throughout life. Endothelial cells ECs are the building blocks of blood vessels yet our understanding of EC specification in vertebrates remains incomplete. cloche/npas4l mutants have broadly been used as an avascular model in zebrafish but little is known about the molecular mechanism of action of Npas4l. Here to identify the direct and indirect target genes of this transcription factor we combined complementary genome wide approaches including transcriptome analyses and chromatin immunoprecipitation ChIP. The cross analysis of these datasets indicate that Npas4l functions as a master regulator by directly inducing a wave of transcription factor genes crucial for hematoendothelial specification in vertebrates including etv2 tal1 and lmo2. We identified additional target genes acting downstream of npas4l and investigated the function of a subset of them using CRISPR/Cas9 technology. Phenotypic characterization of tspan18b mutants reveals a novel role for tspan18b in developmental angiogenesis confirming the reliability of the datasets generated. Collectively these data represent a useful resource for future studies aimed to investigate novel genes with a potential role in vascular development and EC fate determination in vertebrates. Overall design: RNA seq examination of wild type and npas4l bns297/bns297 zebrafish embryos at 6 somite stage in duplicates.	parent bioproject:PRJNA534269	pubmed:31097478	WT 2	GSM3733688	tissue:Embryo\|genotype:wild type	WT 2	The resulting raw reads were assessed for quality adapter content and duplication rates with FastQC Andrews S. 2010 FastQC: a quality control tool for high throughput sequence data. Available online at: http://www.bioinformatics.babraham.ac.uk/projects/fastqc. Reaper version 13 100 was employed to trim reads post a quality drop below a mean of Q20 in a window of 10 nucleotides Davis et al. Kraken: A set of tools for quality control and analysis of high throughput sequence data. Only reads between 30 and 150 nucleotides were cleared for further analyses. Trimmed and filtered reads were aligned versus the Ensembl Zebrafish genome version DanRer10 GRCz10.90 using STAR 2.4.0a with the parameter “ outFilterMismatchNoverLmax 0.1” to increase the maximum ratio of mismatches to mapped length to 10% Dobin et al. STAR: ultrafast universal RNA seq aligner. The number of reads aligning to genes was counted with featureCounts 1.4.5 p1 tool from the Subread package Liao et al. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Only reads mapping at least partially inside exons were admitted and aggregated per gene. Reads overlapping multiple genes or aligning to multiple regions were excluded. Differentially expressed genes were identified using DESeq2 version 1.62 Love et al. Moderated estimation of fold change and dispersion for RNA Seq data with DESeq2. The Ensemble annotation was enriched with UniProt data release 06.06.2014 based on Ensembl gene identifiers Activities at the Universal Protein Resource UniProt. Genome build: danRer10 Supplementary files format and content: The tab delimited matrix shows DESeq normalized counts.	Embryo		For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	Wild type AB embryos and npas4lbns297/bns297 were grown in E3 medium at 28°C until 6 somite stage.	genotype:wild type	GSM3733688	GSM3733688: WT 2; Danio rerio; RNA Seq	GSM3733688		1	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	GEO Accession:GSM3733688	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP193484		WT_2.fastq.gz	fastq	2431837029.0	33941204.0	GSM3733688 r1	0:71.65 1:0	A:605500316;C:637722247;G:683241300;T:505342978;N:30188	71	0	605500316	637722247	683241300	505342978	30188	SRX5725651	SRS4663720	SRA878584	GEO	Bioinformatics, Max Planck Institute for Heart and Lung Research	1	0.94056	0.3147	0.80892	0.75935	37	B	usable mapping rate	illumina	nextseq	full_length	cdna_unspecified	smarter	bulk	bulk	bulk	Germany	2019-04-23	Segmentation	Embryo	Embryo Imprecise	All anatomical structures
52146	52146	SRR8945520	SRX5725650	SRS4663721	SRP193484	PRJNA534271	Genome wide strategies reveal downstream target genes of Npas4l associated with cardiovascular development in zebrafish [RNA Seq 1]	GSE130199	Transcriptome Analysis	The development of a vascular network is essential to nourish tissues and sustain organ function throughout life. Endothelial cells ECs are the building blocks of blood vessels yet our understanding of EC specification in vertebrates remains incomplete. cloche/npas4l mutants have broadly been used as an avascular model in zebrafish but little is known about the molecular mechanism of action of Npas4l. Here to identify the direct and indirect target genes of this transcription factor we combined complementary genome wide approaches including transcriptome analyses and chromatin immunoprecipitation ChIP. The cross analysis of these datasets indicate that Npas4l functions as a master regulator by directly inducing a wave of transcription factor genes crucial for hematoendothelial specification in vertebrates including etv2 tal1 and lmo2. We identified additional target genes acting downstream of npas4l and investigated the function of a subset of them using CRISPR/Cas9 technology. Phenotypic characterization of tspan18b mutants reveals a novel role for tspan18b in developmental angiogenesis confirming the reliability of the datasets generated. Collectively these data represent a useful resource for future studies aimed to investigate novel genes with a potential role in vascular development and EC fate determination in vertebrates. Overall design: RNA seq examination of wild type and npas4l bns297/bns297 zebrafish embryos at 6 somite stage in duplicates.	parent bioproject:PRJNA534269	pubmed:31097478	WT 1	GSM3733687	tissue:Embryo\|genotype:wild type	WT 1	The resulting raw reads were assessed for quality adapter content and duplication rates with FastQC Andrews S. 2010 FastQC: a quality control tool for high throughput sequence data. Available online at: http://www.bioinformatics.babraham.ac.uk/projects/fastqc. Reaper version 13 100 was employed to trim reads post a quality drop below a mean of Q20 in a window of 10 nucleotides Davis et al. Kraken: A set of tools for quality control and analysis of high throughput sequence data. Only reads between 30 and 150 nucleotides were cleared for further analyses. Trimmed and filtered reads were aligned versus the Ensembl Zebrafish genome version DanRer10 GRCz10.90 using STAR 2.4.0a with the parameter “ outFilterMismatchNoverLmax 0.1” to increase the maximum ratio of mismatches to mapped length to 10% Dobin et al. STAR: ultrafast universal RNA seq aligner. The number of reads aligning to genes was counted with featureCounts 1.4.5 p1 tool from the Subread package Liao et al. featureCounts: an efficient general purpose program for assigning sequence reads to genomic features. Only reads mapping at least partially inside exons were admitted and aggregated per gene. Reads overlapping multiple genes or aligning to multiple regions were excluded. Differentially expressed genes were identified using DESeq2 version 1.62 Love et al. Moderated estimation of fold change and dispersion for RNA Seq data with DESeq2. The Ensemble annotation was enriched with UniProt data release 06.06.2014 based on Ensembl gene identifiers Activities at the Universal Protein Resource UniProt. Genome build: danRer10 Supplementary files format and content: The tab delimited matrix shows DESeq normalized counts.	Embryo		For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	Wild type AB embryos and npas4lbns297/bns297 were grown in E3 medium at 28°C until 6 somite stage.	genotype:wild type	GSM3733687	GSM3733687: WT 1; Danio rerio; RNA Seq	GSM3733687		1	For RNAseq total RNA was isolated from zebrafish embryos at 6 somite stage using the miRNeasy micro Kit Qiagen. For exclusion of genomic DNA contamination the samples were treated by on column DNase digestion DNase Free DNase Set Qiagen. Total RNA and library integrity were verified with LabChip Gx Touch 24 Perkin Elmer. 10ng of total RNA was used as input for SMARTer Stranded Total RNA Sample Prep Kit Pico Input Mammalian Takara Clontech following manufacturers protcol. Sequencing was performed on the NextSeq500 instrument Illumina using v2 chemistry resulting in average of 30M reads per library with 1x75bp single end setup.	GEO Accession:GSM3733687	RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP193484		WT_1.fastq.gz	fastq	2100118003.0	29339428.0	GSM3733687 r1	0:71.58 1:0	A:512913868;C:558713165;G:598879366;T:429576279;N:35325	71	0	512913868	558713165	598879366	429576279	35325	SRX5725650	SRS4663721	SRA878584	GEO	Bioinformatics, Max Planck Institute for Heart and Lung Research	1	0.94426	0.30979	0.80417	0.76724	75	B	usable mapping rate	illumina	nextseq	full_length	cdna_unspecified	smarter	bulk	bulk	bulk	Germany	2019-04-23	Segmentation	Embryo	Embryo Imprecise	All anatomical structures
68502	68502	SRR18074848	SRX14226378	SRS12047703	SRP358067	PRJNA803151	mRNA aging shapes the Cap2 methylome in mammalian mRNA	GSE196043	Other	The mRNA cap structure is a major site of dynamic mRNA methylation. mRNA caps exist in either the Cap1 or Cap2 form depending on the presence of 2' O methylation on the first or both the first and second transcribed nucleotide respectively. However the identity of Cap2 containing mRNAs and the function of Cap2 are unclear. Here we describe CLAM Cap Seq a method for transcriptome wide mapping and quantification of Cap2. We find that unlike other epitranscriptomic modifications Cap2 can occur on all mRNAs. Cap2 is formed through a slow continuous conversion of mRNAs from Cap1 to Cap2 as mRNAs age in the cytosol. As a result Cap2 is enriched on long lived mRNAs. We find that large increases in the abundance of Cap1 leads to activation of RIG I especially in conditions where RIG I expression is increased. The methylation of Cap1 to Cap2 markedly reduces the ability of RNAs to bind and activate RIG I. We find that the slow Cap2 methylation rate allows Cap2 to accumulate on host mRNAs yet ensures that low Cap2 levels occur on newly expressed viral RNAs. Overall these results reveal an immunostimulatory role for Cap1 and that Cap2 functions to reduce activation of the innate immune response. Overall design: We developed next generation sequencing methods for quantification of Cap2 methylation in bulk mRNA CapTag seq as well as in individual mRNAs in a transcriptome wide manner CLAM Cap seq. Furthermore we developed tools for measuring translation and stability of transcript start nucleotide TSN mRNA isoforms by combining polysome profiling and actinomycin D treatment with TSS seq transcription start site sequencing.		pubmed:36725932	Zebrafish CapQuant seq 2	GSM5907184	source name:48 hpf embryo\|cell line/tissue:whole\|genotype:wild type A/B\|purification:oligodT25 beads	Zebrafish CapQuant seq 2	Removal of low quality reads and three prime end adapter trimming was performed with flexbar v2.5. Removal of duplicated reads was accomplished with pyFastqDuplicateRemover.py within the pyCRAC package v1.3.2. Read trimming was performed using seqtk package v1.3. Read alignement to fly mouse or human genome was conducted using Bowtie v1.2.3. five prime end read coverage was calculated per each genomic position using BEDTools v2.28.0. Genome build: Drosohila melanogaster; dm6 Mus musculus; mm10 Homo sapiens; hg38.	48 hpf embryo		CapTag seq Total RNA was extracted using TRIzol reagent according to the manufacturers instructions followed by isopropanol precipitation. PolyA+ RNA was isolated from total RNA using magnetic oligodT25 beads NEB.	Zebrafish AB line embryos were maintained in E3 medium at 28 degrees and staged as previously described Kimmel et al. Developmental Dynamics 1995.	cell line/tissue:whole\|genotype:wild type A/B\|purification:oligodT25 beads	GSM5907184	GSM5907184: Zebrafish CapQuant seq 2; Danio rerio; OTHER	GSM5907184 r1	GSM5907184	1	CapTag seq Total RNA was extracted using TRIzol reagent according to the manufacturers instructions followed by isopropanol precipitation. PolyA+ RNA was isolated from total RNA using magnetic oligodT25 beads NEB.		OTHER	TRANSCRIPTOMIC	other	SINGLE	ILLUMINA	Illumina HiSeq 2500	SRP358067		Zebrafish_CQS2_R1.fastq.gz	fastq	658260009.0	12907059.0	GSM5907184 r1	0:51 1:0	A:158463141;C:142984303;G:213148834;T:143656235;N:7496	51	0	158463141	142984303	213148834	143656235	7496	SRX14226378	SRS12047703	SRA1545466	Pharmacology, Weill Cornell Medicine	Pharmacology, Weill Cornell Medicine	1	0.0	0.0	1.0		51	T	under 1.2% mapping rate	illumina	hiseq_era	5prime	poly_a	unknown	bulk	bulk	bulk	United States	2022-02-18	Hatching	Embryo	Embryo Imprecise	All anatomical structures
68503	68503	SRR18074849	SRX14226377	SRS12047702	SRP358067	PRJNA803151	mRNA aging shapes the Cap2 methylome in mammalian mRNA	GSE196043	Other	The mRNA cap structure is a major site of dynamic mRNA methylation. mRNA caps exist in either the Cap1 or Cap2 form depending on the presence of 2' O methylation on the first or both the first and second transcribed nucleotide respectively. However the identity of Cap2 containing mRNAs and the function of Cap2 are unclear. Here we describe CLAM Cap Seq a method for transcriptome wide mapping and quantification of Cap2. We find that unlike other epitranscriptomic modifications Cap2 can occur on all mRNAs. Cap2 is formed through a slow continuous conversion of mRNAs from Cap1 to Cap2 as mRNAs age in the cytosol. As a result Cap2 is enriched on long lived mRNAs. We find that large increases in the abundance of Cap1 leads to activation of RIG I especially in conditions where RIG I expression is increased. The methylation of Cap1 to Cap2 markedly reduces the ability of RNAs to bind and activate RIG I. We find that the slow Cap2 methylation rate allows Cap2 to accumulate on host mRNAs yet ensures that low Cap2 levels occur on newly expressed viral RNAs. Overall these results reveal an immunostimulatory role for Cap1 and that Cap2 functions to reduce activation of the innate immune response. Overall design: We developed next generation sequencing methods for quantification of Cap2 methylation in bulk mRNA CapTag seq as well as in individual mRNAs in a transcriptome wide manner CLAM Cap seq. Furthermore we developed tools for measuring translation and stability of transcript start nucleotide TSN mRNA isoforms by combining polysome profiling and actinomycin D treatment with TSS seq transcription start site sequencing.		pubmed:36725932	Zebrafish CapQuant seq 1	GSM5907183	source name:48 hpf embryo\|cell line/tissue:whole\|genotype:wild type A/B\|purification:oligodT25 beads	Zebrafish CapQuant seq 1	Removal of low quality reads and three prime end adapter trimming was performed with flexbar v2.5. Removal of duplicated reads was accomplished with pyFastqDuplicateRemover.py within the pyCRAC package v1.3.2. Read trimming was performed using seqtk package v1.3. Read alignement to fly mouse or human genome was conducted using Bowtie v1.2.3. five prime end read coverage was calculated per each genomic position using BEDTools v2.28.0. Genome build: Drosohila melanogaster; dm6 Mus musculus; mm10 Homo sapiens; hg38.	48 hpf embryo		CapTag seq Total RNA was extracted using TRIzol reagent according to the manufacturers instructions followed by isopropanol precipitation. PolyA+ RNA was isolated from total RNA using magnetic oligodT25 beads NEB.	Zebrafish AB line embryos were maintained and staged as previously described Kimmel et al. Developmental Dynamics 1995.	cell line/tissue:whole\|genotype:wild type A/B\|purification:oligodT25 beads	GSM5907183	GSM5907183: Zebrafish CapQuant seq 1; Danio rerio; OTHER	GSM5907183 r1	GSM5907183	1	CapTag seq Total RNA was extracted using TRIzol reagent according to the manufacturers instructions followed by isopropanol precipitation. PolyA+ RNA was isolated from total RNA using magnetic oligodT25 beads NEB.		OTHER	TRANSCRIPTOMIC	other	SINGLE	ILLUMINA	Illumina HiSeq 2500	SRP358067		Zebrafish_CQS1_R1.fastq.gz	fastq	1636691694.0	32091994.0	GSM5907183 r1	0:51 1:0	A:394187895;C:355520591;G:529426272;T:357424863;N:132073	51	0	394187895	355520591	529426272	357424863	132073	SRX14226377	SRS12047702	SRA1545466	Pharmacology, Weill Cornell Medicine	Pharmacology, Weill Cornell Medicine	1	0.0	0.0	1.0		51	T	under 1.2% mapping rate	illumina	hiseq_era	5prime	poly_a	unknown	bulk	bulk	bulk	United States	2022-02-18	Hatching	Embryo	Embryo Imprecise	All anatomical structures
72263	72263	SRR22398713	SRX18368432	SRS15854864	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt cp25 4	GSM6754861	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:WT +2.5 4\|conc ng ul:138.222\|a 260s280:2.11\|a 260s230:1.69\|sequence count:53490826	wt cp25 4	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:WT +2.5 4\|conc ng ul:138.222\|a 260s280:2.11\|a 260s230:1.69\|sequence count:53490826	GSM6754861	GSM6754861: wt cp25 4; Danio rerio; RNA Seq	GSM6754861 r1	GSM6754861	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_cp25_4_R1.fastq.gz	fastq	3971633541.0	53490826.0	GSM6754861 r1	0:74.25 1:0	A:1007182228;C:929484142;G:892507427;T:1142079615;N:380129	74	0	1007182228	929484142	892507427	1142079615	380129	SRX18368432	SRS15854864	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94921	0.1103	0.66513	0.48762	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72264	72264	SRR22398716	SRX18368431	SRS15854863	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt cp25 3	GSM6754860	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:WT +2.5 3\|conc ng ul:107.595\|a 260s280:2.14\|a 260s230:1.34\|sequence count:55925525	wt cp25 3	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:WT +2.5 3\|conc ng ul:107.595\|a 260s280:2.14\|a 260s230:1.34\|sequence count:55925525	GSM6754860	GSM6754860: wt cp25 3; Danio rerio; RNA Seq	GSM6754860 r1	GSM6754860	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_cp25_3_R1.fastq.gz	fastq	4151847256.0	55925525.0	GSM6754860 r1	0:74.24 1:0	A:1050577660;C:974197737;G:936600779;T:1190080560;N:390520	74	0	1050577660	974197737	936600779	1190080560	390520	SRX18368431	SRS15854863	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94795	0.10889	0.66732	0.48527	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72265	72265	SRR22398714	SRX18368430	SRS15854862	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt cp25 2	GSM6754859	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:WT +2.5 2\|conc ng ul:117.806\|a 260s280:2.13\|a 260s230:0.82\|sequence count:58067253	wt cp25 2	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:WT +2.5 2\|conc ng ul:117.806\|a 260s280:2.13\|a 260s230:0.82\|sequence count:58067253	GSM6754859	GSM6754859: wt cp25 2; Danio rerio; RNA Seq	GSM6754859 r1	GSM6754859	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_cp25_2_R1.fastq.gz	fastq	4309818874.0	58067253.0	GSM6754859 r1	0:74.22 1:0	A:1114944612;C:990370711;G:956027483;T:1248075089;N:400979	74	0	1114944612	990370711	956027483	1248075089	400979	SRX18368430	SRS15854862	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94404	0.12016	0.66732	0.47887	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72266	72266	SRR22398715	SRX18368429	SRS15854861	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt cp25 1	GSM6754858	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:WT +2.5 1\|conc ng ul:127.291\|a 260s280:2.15\|a 260s230:0.94\|sequence count:59428413	wt cp25 1	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:WT +2.5 1\|conc ng ul:127.291\|a 260s280:2.15\|a 260s230:0.94\|sequence count:59428413	GSM6754858	GSM6754858: wt cp25 1; Danio rerio; RNA Seq	GSM6754858 r1	GSM6754858	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_cp25_1_R1.fastq.gz	fastq	4407739857.0	59428413.0	GSM6754858 r1	0:74.17 1:0	A:1137830012;C:1015732103;G:975339556;T:1278384440;N:453746	74	0	1137830012	1015732103	975339556	1278384440	453746	SRX18368429	SRS15854861	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94356	0.12239	0.67543	0.48843	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72267	72267	SRR22398717	SRX18368428	SRS15854860	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko cp25 4	GSM6754857	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:KO +2.5 4\|conc ng ul:163.39\|a 260s280:2.11\|a 260s230:2.03\|sequence count:46388653	ko cp25 4	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:KO +2.5 4\|conc ng ul:163.39\|a 260s280:2.11\|a 260s230:2.03\|sequence count:46388653	GSM6754857	GSM6754857: ko cp25 4; Danio rerio; RNA Seq	GSM6754857 r1	GSM6754857	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_cp25_4_R1.fastq.gz	fastq	3446442454.0	46388653.0	GSM6754857 r1	0:74.29 1:0	A:885382304;C:794319275;G:763794659;T:1002667835;N:278381	74	0	885382304	794319275	763794659	1002667835	278381	SRX18368428	SRS15854860	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94513	0.1161	0.66598	0.4967	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72268	72268	SRR22398718	SRX18368427	SRS15854859	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko cp25 3	GSM6754856	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:KO +2.5 3\|conc ng ul:119.387\|a 260s280:2.09\|a 260s230:2.25\|sequence count:58009227	ko cp25 3	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:KO +2.5 3\|conc ng ul:119.387\|a 260s280:2.09\|a 260s230:2.25\|sequence count:58009227	GSM6754856	GSM6754856: ko cp25 3; Danio rerio; RNA Seq	GSM6754856 r1	GSM6754856	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_cp25_3_R1.fastq.gz	fastq	4311994952.0	58009227.0	GSM6754856 r1	0:74.33 1:0	A:1098005222;C:1005030862;G:965223116;T:1243452005;N:283747	74	0	1098005222	1005030862	965223116	1243452005	283747	SRX18368427	SRS15854859	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94673	0.11276	0.66847	0.49233	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72269	72269	SRR22398726	SRX18368426	SRS15854858	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko cp25 2	GSM6754855	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:KO +2.5 2\|conc ng ul:105.565\|a 260s280:2.12\|a 260s230:0.98\|sequence count:49990819	ko cp25 2	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:KO +2.5 2\|conc ng ul:105.565\|a 260s280:2.12\|a 260s230:0.98\|sequence count:49990819	GSM6754855	GSM6754855: ko cp25 2; Danio rerio; RNA Seq	GSM6754855 r1	GSM6754855	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_cp25_2_R1.fastq.gz	fastq	3706388155.0	49990819.0	GSM6754855 r1	0:74.14 1:0	A:948025653;C:857558445;G:827401541;T:1072813059;N:589457	74	0	948025653	857558445	827401541	1072813059	589457	SRX18368426	SRS15854858	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.9446	0.12345	0.66902	0.49658	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72270	72270	SRR22398719	SRX18368425	SRS15854857	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko cp25 1	GSM6754854	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:KO +2.5 1\|conc ng ul:109.491\|a 260s280:2.11\|a 260s230:1.42\|sequence count:47621085	ko cp25 1	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time:2.5\|mdibl id:KO +2.5 1\|conc ng ul:109.491\|a 260s280:2.11\|a 260s230:1.42\|sequence count:47621085	GSM6754854	GSM6754854: ko cp25 1; Danio rerio; RNA Seq	GSM6754854 r1	GSM6754854	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_cp25_1_R1.fastq.gz	fastq	3535345923.0	47621085.0	GSM6754854 r1	0:74.24 1:0	A:912664803;C:814365640;G:784261393;T:1023651094;N:402993	74	0	912664803	814365640	784261393	1023651094	402993	SRX18368425	SRS15854857	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94483	0.12372	0.67058	0.49227	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72271	72271	SRR22398725	SRX18368424	SRS15854856	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt bz00 4	GSM6754853	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:0\|mdibl id:WT 0 4\|conc ng ul:143.511\|a 260s280:2.13\|a 260s230:1.57\|sequence count:61583000	wt bz00 4	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time:0\|mdibl id:WT 0 4\|conc ng ul:143.511\|a 260s280:2.13\|a 260s230:1.57\|sequence count:61583000	GSM6754853	GSM6754853: wt bz00 4; Danio rerio; RNA Seq	GSM6754853 r1	GSM6754853	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_bz00_4_R1.fastq.gz	fastq	4558041252.0	61583000.0	GSM6754853 r1	0:74.01 1:0	A:1174813850;C:1053099181;G:1012107824;T:1316617074;N:1403323	74	0	1174813850	1053099181	1012107824	1316617074	1403323	SRX18368424	SRS15854856	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94572	0.12348	0.67448	0.4873	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72272	72272	SRR22398720	SRX18368423	SRS15854855	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt bz00 3	GSM6754852	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:0\|mdibl id:WT 0 3\|conc ng ul:138.681\|a 260s280:2.13\|a 260s230:1.54\|sequence count:58341062	wt bz00 3	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time:0\|mdibl id:WT 0 3\|conc ng ul:138.681\|a 260s280:2.13\|a 260s230:1.54\|sequence count:58341062	GSM6754852	GSM6754852: wt bz00 3; Danio rerio; RNA Seq	GSM6754852 r1	GSM6754852	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_bz00_3_R1.fastq.gz	fastq	4324729722.0	58341062.0	GSM6754852 r1	0:74.13 1:0	A:1096278358;C:1014112739;G:973246126;T:1240721487;N:371012	74	0	1096278358	1014112739	973246126	1240721487	371012	SRX18368423	SRS15854855	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94897	0.11731	0.66835	0.48302	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72273	72273	SRR22398724	SRX18368422	SRS15854854	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt bz00 2	GSM6754851	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:0\|mdibl id:WT 0 2\|conc ng ul:135.007\|a 260s280:2.13\|a 260s230:0.98\|sequence count:49196377	wt bz00 2	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time:0\|mdibl id:WT 0 2\|conc ng ul:135.007\|a 260s280:2.13\|a 260s230:0.98\|sequence count:49196377	GSM6754851	GSM6754851: wt bz00 2; Danio rerio; RNA Seq	GSM6754851 r1	GSM6754851	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_bz00_2_R1.fastq.gz	fastq	3643049767.0	49196377.0	GSM6754851 r1	0:74.05 1:0	A:925447169;C:847530454;G:817481959;T:1051509088;N:1081097	74	0	925447169	847530454	817481959	1051509088	1081097	SRX18368422	SRS15854854	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94762	0.1071	0.66149	0.48635	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72274	72274	SRR22398721	SRX18368421	SRS15854853	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt bz00 1	GSM6754850	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:0\|mdibl id:WT 0 1\|conc ng ul:149.394\|a 260s280:2.12\|a 260s230:1.12\|sequence count:55724803	wt bz00 1	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time:0\|mdibl id:WT 0 1\|conc ng ul:149.394\|a 260s280:2.12\|a 260s230:1.12\|sequence count:55724803	GSM6754850	GSM6754850: wt bz00 1; Danio rerio; RNA Seq	GSM6754850 r1	GSM6754850	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_bz00_1_R1.fastq.gz	fastq	4132217260.0	55724803.0	GSM6754850 r1	0:74.15 1:0	A:1065785685;C:951791352;G:916868354;T:1197414078;N:357791	74	0	1065785685	951791352	916868354	1197414078	357791	SRX18368421	SRS15854853	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94384	0.11036	0.66253	0.48713	73	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72275	72275	SRR22398722	SRX18368420	SRS15854852	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko bz00 3	GSM6754848	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:0\|mdibl id:KO 0 3\|conc ng ul:125.073\|a 260s280:2.13\|a 260s230:0.54\|sequence count:43888003	ko bz00 3	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time:0\|mdibl id:KO 0 3\|conc ng ul:125.073\|a 260s280:2.13\|a 260s230:0.54\|sequence count:43888003	GSM6754848	GSM6754848: ko bz00 3; Danio rerio; RNA Seq	GSM6754848 r1	GSM6754848	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_bz00_3_R1.fastq.gz	fastq	3261925759.0	43888003.0	GSM6754848 r1	0:74.32 1:0	A:829455673;C:763869126;G:729279622;T:939176246;N:145092	74	0	829455673	763869126	729279622	939176246	145092	SRX18368420	SRS15854852	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94701	0.12716	0.67004	0.50296	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72276	72276	SRR22398723	SRX18368419	SRS15854851	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko bz00 4	GSM6754849	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:0\|mdibl id:KO 0 4\|conc ng ul:126.704\|a 260s280:2.12\|a 260s230:1.91\|sequence count:46608771	ko bz00 4	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time:0\|mdibl id:KO 0 4\|conc ng ul:126.704\|a 260s280:2.12\|a 260s230:1.91\|sequence count:46608771	GSM6754849	GSM6754849: ko bz00 4; Danio rerio; RNA Seq	GSM6754849 r1	GSM6754849	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_bz00_4_R1.fastq.gz	fastq	3465408347.0	46608771.0	GSM6754849 r1	0:74.35 1:0	A:882442105;C:807154063;G:770576357;T:1004932656;N:303166	74	0	882442105	807154063	770576357	1004932656	303166	SRX18368419	SRS15854851	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94561	0.12587	0.6672	0.48039	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72277	72277	SRR22398727	SRX18368418	SRS15854850	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko bz00 2	GSM6754847	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:0\|mdibl id:KO 0 2\|conc ng ul:123.215\|a 260s280:2.12\|a 260s230:1.67\|sequence count:43789649	ko bz00 2	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time:0\|mdibl id:KO 0 2\|conc ng ul:123.215\|a 260s280:2.12\|a 260s230:1.67\|sequence count:43789649	GSM6754847	GSM6754847: ko bz00 2; Danio rerio; RNA Seq	GSM6754847 r1	GSM6754847	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_bz00_2_R1.fastq.gz	fastq	3253450441.0	43789649.0	GSM6754847 r1	0:74.30 1:0	A:839107458;C:748950160;G:719943086;T:945309012;N:140725	74	0	839107458	748950160	719943086	945309012	140725	SRX18368418	SRS15854850	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94525	0.12477	0.67028	0.49471	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72278	72278	SRR22398734	SRX18368417	SRS15854849	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko bz00 1	GSM6754846	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time:0\|mdibl id:KO 0 1\|conc ng ul:138.474\|a 260s280:2.15\|a 260s230:1.58\|sequence count:63322040	ko bz00 1	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time:0\|mdibl id:KO 0 1\|conc ng ul:138.474\|a 260s280:2.15\|a 260s230:1.58\|sequence count:63322040	GSM6754846	GSM6754846: ko bz00 1; Danio rerio; RNA Seq	GSM6754846 r1	GSM6754846	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_bz00_1_R1.fastq.gz	fastq	4702919348.0	63322040.0	GSM6754846 r1	0:74.27 1:0	A:1208884586;C:1089826557;G:1044501432;T:1359302369;N:404404	74	0	1208884586	1089826557	1044501432	1359302369	404404	SRX18368417	SRS15854849	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94777	0.12221	0.67708	0.49392	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72279	72279	SRR22398728	SRX18368416	SRS15854848	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt am30 4	GSM6754845	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:WT 3 4\|conc ng ul:134.487\|a 260s280:2.15\|a 260s230:1.39\|sequence count:63356407	wt am30 4	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:WT 3 4\|conc ng ul:134.487\|a 260s280:2.15\|a 260s230:1.39\|sequence count:63356407	GSM6754845	GSM6754845: wt am30 4; Danio rerio; RNA Seq	GSM6754845 r1	GSM6754845	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_am30_4_R1.fastq.gz	fastq	4707868699.0	63356407.0	GSM6754845 r1	0:74.31 1:0	A:1203701452;C:1089432799;G:1048996672;T:1364846807;N:890969	74	0	1203701452	1089432799	1048996672	1364846807	890969	SRX18368416	SRS15854848	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94701	0.11284	0.66714	0.48591	73	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72280	72280	SRR22398733	SRX18368415	SRS15854847	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt am30 3	GSM6754844	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:WT 3 3\|conc ng ul:133.341\|a 260s280:2.07\|a 260s230:1.29\|sequence count:67175079	wt am30 3	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:WT 3 3\|conc ng ul:133.341\|a 260s280:2.07\|a 260s230:1.29\|sequence count:67175079	GSM6754844	GSM6754844: wt am30 3; Danio rerio; RNA Seq	GSM6754844 r1	GSM6754844	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_am30_3_R1.fastq.gz	fastq	4993030085.0	67175079.0	GSM6754844 r1	0:74.33 1:0	A:1275030845;C:1160279340;G:1117068336;T:1440349025;N:302539	74	0	1275030845	1160279340	1117068336	1440349025	302539	SRX18368415	SRS15854847	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94645	0.11554	0.66724	0.46708	72	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72281	72281	SRR22398729	SRX18368414	SRS15854846	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt am30 2	GSM6754843	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:WT 3 2\|conc ng ul:144.163\|a 260s280:2.11\|a 260s230:1.41\|sequence count:64202767	wt am30 2	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:WT 3 2\|conc ng ul:144.163\|a 260s280:2.11\|a 260s230:1.41\|sequence count:64202767	GSM6754843	GSM6754843: wt am30 2; Danio rerio; RNA Seq	GSM6754843 r1	GSM6754843	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_am30_2_R1.fastq.gz	fastq	4774624628.0	64202767.0	GSM6754843 r1	0:74.37 1:0	A:1226843673;C:1106688102;G:1065434365;T:1375454118;N:204370	74	0	1226843673	1106688102	1065434365	1375454118	204370	SRX18368414	SRS15854846	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94652	0.12306	0.66951	0.49383	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72282	72282	SRR22398732	SRX18368413	SRS15854845	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			wt am30 1	GSM6754842	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:WT 3 1\|conc ng ul:123.886\|a 260s280:2.1\|a 260s230:1.65\|sequence count:57588838	wt am30 1	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype WT\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:WT 3 1\|conc ng ul:123.886\|a 260s280:2.1\|a 260s230:1.65\|sequence count:57588838	GSM6754842	GSM6754842: wt am30 1; Danio rerio; RNA Seq	GSM6754842 r1	GSM6754842	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		wt_am30_1_R1.fastq.gz	fastq	4279904253.0	57588838.0	GSM6754842 r1	0:74.32 1:0	A:1108696635;C:979371472;G:944355461;T:1247033388;N:447297	74	0	1108696635	979371472	944355461	1247033388	447297	SRX18368413	SRS15854845	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94514	0.11835	0.66981	0.4881	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72283	72283	SRR22398730	SRX18368412	SRS15854844	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko am30 4	GSM6754841	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:KO 3 4\|conc ng ul:146.811\|a 260s280:2.13\|a 260s230:1.64\|sequence count:45580367	ko am30 4	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time: 3\|mdibl id:KO 3 4\|conc ng ul:146.811\|a 260s280:2.13\|a 260s230:1.64\|sequence count:45580367	GSM6754841	GSM6754841: ko am30 4; Danio rerio; RNA Seq	GSM6754841 r1	GSM6754841	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_am30_4_R1.fastq.gz	fastq	3387836215.0	45580367.0	GSM6754841 r1	0:74.33 1:0	A:878994756;C:771715446;G:742146109;T:994764227;N:215677	74	0	878994756	771715446	742146109	994764227	215677	SRX18368412	SRS15854844	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94286	0.12355	0.6731	0.48888	75	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72284	72284	SRR22398731	SRX18368411	SRS15854843	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko am30 3	GSM6754840	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:KO 3 3\|conc ng ul:130.202\|a 260s280:2.11\|a 260s230:1.82\|sequence count:45716196	ko am30 3	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time: 3\|mdibl id:KO 3 3\|conc ng ul:130.202\|a 260s280:2.11\|a 260s230:1.82\|sequence count:45716196	GSM6754840	GSM6754840: ko am30 3; Danio rerio; RNA Seq	GSM6754840 r1	GSM6754840	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_am30_3_R1.fastq.gz	fastq	3397790979.0	45716196.0	GSM6754840 r1	0:74.32 1:0	A:874671145;C:781147028;G:750987590;T:990652325;N:332891	74	0	874671145	781147028	750987590	990652325	332891	SRX18368411	SRS15854843	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94685	0.12013	0.67247	0.49487	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72285	72285	SRR22398735	SRX18368410	SRS15854842	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko am30 2	GSM6754839	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:KO 3 2\|conc ng ul:153.06\|a 260s280:2.13\|a 260s230:1.88\|sequence count:61815409	ko am30 2	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time: 3\|mdibl id:KO 3 2\|conc ng ul:153.06\|a 260s280:2.13\|a 260s230:1.88\|sequence count:61815409	GSM6754839	GSM6754839: ko am30 2; Danio rerio; RNA Seq	GSM6754839 r1	GSM6754839	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_am30_2_R1.fastq.gz	fastq	4591792497.0	61815409.0	GSM6754839 r1	0:74.28 1:0	A:1166498576;C:1070326771;G:1027221078;T:1327476945;N:269127	74	0	1166498576	1070326771	1027221078	1327476945	269127	SRX18368410	SRS15854842	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94781	0.11355	0.66864	0.49723	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
72286	72286	SRR22398736	SRX18368409	SRS15854841	SRP409542	PRJNA904806	Bulk RNA seq of zebrafish 5dpf embryos comparing Klf9 knockout with matched controls at 3 timepoints flanking zeitgeber lights on	GSE218687	Transcriptome Analysis	Krüppel like factor 9 Klf9 is a ubiquitously expressed transcription factor that is a feedforward regulator of multiple stress responsive and endocrine signaling pathways. We previously described how loss of Klf9 function affects the transcriptome of zebrafish larvae sampled at a single time point 5 dpf dpf. However klf9 expression oscillates diurnally and the time point that was sampled corresponded to its expression nadir. To determine if klf9 / function varies with time of day we performed bulk RNA seq on 5 dpf zebrafish embryos sampled at three timepoints encompassing the predawn peak and midmorning nadir of klf9 expression. We found that while the major effects of the klf9 / mutation that we reported previously are robust to time of day the mutation has additional effects that manifest only at the predawn time point. We used a published single cell atlas of zebrafish development to map the effects of the klf9 / mutation onto different cell types and found that the mutation increased representation of genes associated with digestive organs liver pancreas and intestine and decreased representation of genes associated with differentiating neurons blood and somites. Measurements from confocally imaged larvae suggest that overrepresentation of liver genes in klf9 / mutants is due to development of enlarged livers. Overall design: Comparative gene expression profiling analysis of RNA seq data for zebrafish klf9 / mutant larvae vs wild type at three times of day. Klf9 / knockouts were generated through CRISPR creating a 2 bp deletion in the first exon that causes a frameshift and premature stop codon as previously described in Gans et al Scientific Reports 10 11415 2020. https://doi.org/10.1038/s41598 020 68040 z			ko am30 1	GSM6754838	source name:larvae\|tissue:larvae\|developmental stage:5 dpf embryo\|time: 3\|mdibl id:KO 3 1\|conc ng ul:166.574\|a 260s280:1.94\|a 260s230:1.16\|sequence count:50914883	ko am30 1	Quality and adapter trimming was applied to fastq formatted read files with Trim Galore Version 0.6.5 with options: " fastqc args ' noextract'" " illumina" " length 1 35" " length 2 35" " stringency 1" " length 20" and " quality 20". Gene and isoform expression was estimated with RSEM Version 1.3.3 using Ensembl release 101 of the Danio rerio genome for alignment and using command “rsem calculate expression” with options: " keep intermediate files" " star gzipped read file" " p 64" " estimate rspd" " append names" " output genome bam" and " star". This run used 64 threads with the option to estimate the read start position distribution RSPD from the data instead of the default uniform RPSD and the option to output a BAM formatted file of read alignments in genomic coordinates. Counts were formatted into a count matrix with tximport using default options. Due to concerns regarding potential confounding experimental variables this experiment was repeated with improved collection protocols yielding two runs of RNAseq data. PCA of these two runs revealed high similarity between the two so the two were "merged" into one by taking the sum of transcript counts from corresponding samples with respect to time replicate number and genetics from the two runs. The transcripts from this experiment were aligned to Ensembl gene IDs Danio rerio 101. For downstream analysis it is more valuable to refer to genes by their name to estimate expression. There were 581 genes that were associated with more than one ensembl ID so the count matrix collapsed these distinct transcript counts by taking the sum of all transcript counts that correspond to the same gene name effectively removing gene duplicates from the count matrix. Principal Components Analysis PCA was run on the count matrix to identify dominant sources of variance in transcript counts between samples in this experiment. This analysis was conducted with the pipeline developed by Bianca M. Massacci for the MDIBL Bioinformatics Core Massacci …	larvae		At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.	Zebrafish were klf9 / mutants derived from the AB strain and wildtype controls derived from the same grandparents. Husbandry and procedures were as described previously. All animal procedures were approved by the Institutional Animal Care and Use Committee of the MDI Biological Laboratory and all methods were performed in accordance with the relevant guidelines and regulations. Embryo culture and cortisol treatments were performed as previously described. Briefly fertilized eggs were collected in the morning disinfected and at 4 hpf placed in dishes with embryo media. Embryos developed in a 28.5o C incubator with a 14/10 light/dark cycle synchronized with the core fish room. Media was changed daily.	tissue:larvae\|genotype Klf9 / \|developmental stage:5 dpf embryo\|time: 3\|mdibl id:KO 3 1\|conc ng ul:166.574\|a 260s280:1.94\|a 260s230:1.16\|sequence count:50914883	GSM6754838	GSM6754838: ko am30 1; Danio rerio; RNA Seq	GSM6754838 r1	GSM6754838	1	At 3 0 and 2.5 hours zeitgeber time onset of the light phase in the incubator on day 5 post fertilization four biological replicates of klf9 / mutant and wildtype larvae were collected as follows. Each biological replicate from each genotype and timepoint consisted of six larvae in a 30mm dish in 4ml of media. Larvae were collected from the dish into Eppendorf tubes media was removed and larvae immediately snap frozen in liquid nitrogen. Collection of the 8 samples at each time point occurred over 10 minutes. Frozen samples were stored at 80 deg C. RNA was prepared using the Qiagen RNeasy Plus mini kit Qiagen 74134. For each set of four biological replicate samples RLT Plus lysis buffer plus beta mercaptoethanol per kit instructions was added to each sample immediately upon its retrieval from the freezer and the sample was then immediately homogenized with a motorized pestle and placed on ice before the next sample was retrieved from the freezer and subjected to the same procedure. Following pestle homogenization replicate samples received simultaneous processing—i.e. passed though Qiashredder columns Qiagen 79654 bound washed and eluted per kit instructions. RNA was quantified and sent to the Oklahoma State Genomics Facility for Illumina library preparation and single end sequencing.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ILLUMINA	NextSeq 500	SRP409542		ko_am30_1_R1.fastq.gz	fastq	3786315387.0	50914883.0	GSM6754838 r1	0:74.37 1:0	A:965927215;C:875465462;G:846443972;T:1098110795;N:367943	74	0	965927215	875465462	846443972	1098110795	367943	SRX18368409	SRS15854841	SRA1546501	Bioinformatics Core, MDI Biological Laboratory	Bioinformatics Core, MDI Biological Laboratory	1	0.94574	0.11829	0.66574	0.4914	74	B	usable mapping rate	illumina	nextseq	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	United States	2022-11-23	Larval	Larval	Embryo Imprecise	All anatomical structures
74329	74329	SRR23635030	SRX19518333	SRS16905710	SRP425040	PRJNA939370	The TET BMP regulatory axis in pathogenesis of CFM [RNA Seq]	GSE226182	Transcriptome Analysis	Craniofacial microsomia CFM is a congenital defect that usually results from aberrant development of embryonic pharyngeal arches. However the molecular basis of CFM pathogenesis is largely unknown. Here we employ zebrafish model to investigate the mechanism of CFM pathogenesis. In early embryos tet2 and tet3 are highly expressed and are essential for pharyngeal cartilage development. Single cell RNA sequencing and genetic analyses reveal that loss of Tet2/3 impaired chondrocyte differentiation largely due to insufficient BMP signaling. Mechanistically Tet2/3 mediated 5 hydroxymethylcytosine modification allows the 5 hydroxymethylcytosine “reader” Sall4 to specifically bind the bmp4 promoter thereby promoting bmp4 expression and enabling efficient BMP signaling. These findings indicate the TET BMP regulatory axis via 5 hydroxymethylcytosine to be critical for pharyngeal cartilage development. Whole exome sequencing of CFM patient samples show that single nucleotide polymorphisms in TET and BMP pathway genes increase the risk of CFM. Collectively our study provides novel insights into understanding craniofacial development and CFM pathogenesis. Overall design: Total RNAs were purified using TRIzol reagent Life Technologies 343702. Libraries were constructed using a VAHTS Universal V8 RNA seq Library Prep Kit for MGI Vazyme according to the manufacturer's instructions and then sequenced on the MGISEQ 2000 platform.	parent bioproject:PRJNA939357	pubmed:38427557	KO replicate 2 bulk RNAseq	GSM7067524	source name:embryo\|tissue:embryo\|age:48 hpf\|genotype:tet2/3 double knock out\|geo loc name:missing\|collection date:missing	KO replicate 2 bulk RNAseq	Sequence reads were mapped to GRCz11/danrer11 using STAR v2.7.10a Read count extraction were performed using RSEM v1.3.1 Reads normalization and differentially expressed gene calling were performed using DESeq2 v1.32.0 Assembly: danrer11 Supplementary files format and content: tab delimited text files include gene expression for each Sample	embryo		RNA was extracted by TRNzol method and 500ng of total RNA was used to construct sequencing library. RNA libraries for RNA Seq were prepared using the Vazyme RNA Seq library kit according to the manufacturer's protocol.		tissue:embryo\|age:48 hpf\|genotype:tet2/3 double knock out	GSM7067524	GSM7067524: KO replicate 2 bulk RNAseq; Danio rerio; RNA Seq	GSM7067524 r1	GSM7067524	1	RNA was extracted by TRNzol method and 500ng of total RNA was used to construct sequencing library. RNA libraries for RNA Seq were prepared using the Vazyme RNA Seq library kit according to the manufacturer's protocol.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	DNBSEQ	DNBSEQ-G400	SRP425040		KO2.fastq.gz	fastq	4188284200.0	41882842.0	GSM7067524 r1	0:100	A:1066992737;C:1011357361;G:1055554148;T:1041284278;N:13095676	100		1066992737	1011357361	1055554148	1041284278	13095676	SRX19518333	SRS16905710	SRA1597336	Yunnan University	Yunnan University	1	0.88647	0.07541	0.7237	0.47069	100	B	usable mapping rate	bgi	bgi	unknown	cdna_unspecified	unknown	sc_generic	bulk	bulk	China	2023-02-27	Hatching	Embryo	Embryo Imprecise	All anatomical structures
74330	74330	SRR23635031	SRX19518332	SRS16905709	SRP425040	PRJNA939370	The TET BMP regulatory axis in pathogenesis of CFM [RNA Seq]	GSE226182	Transcriptome Analysis	Craniofacial microsomia CFM is a congenital defect that usually results from aberrant development of embryonic pharyngeal arches. However the molecular basis of CFM pathogenesis is largely unknown. Here we employ zebrafish model to investigate the mechanism of CFM pathogenesis. In early embryos tet2 and tet3 are highly expressed and are essential for pharyngeal cartilage development. Single cell RNA sequencing and genetic analyses reveal that loss of Tet2/3 impaired chondrocyte differentiation largely due to insufficient BMP signaling. Mechanistically Tet2/3 mediated 5 hydroxymethylcytosine modification allows the 5 hydroxymethylcytosine “reader” Sall4 to specifically bind the bmp4 promoter thereby promoting bmp4 expression and enabling efficient BMP signaling. These findings indicate the TET BMP regulatory axis via 5 hydroxymethylcytosine to be critical for pharyngeal cartilage development. Whole exome sequencing of CFM patient samples show that single nucleotide polymorphisms in TET and BMP pathway genes increase the risk of CFM. Collectively our study provides novel insights into understanding craniofacial development and CFM pathogenesis. Overall design: Total RNAs were purified using TRIzol reagent Life Technologies 343702. Libraries were constructed using a VAHTS Universal V8 RNA seq Library Prep Kit for MGI Vazyme according to the manufacturer's instructions and then sequenced on the MGISEQ 2000 platform.	parent bioproject:PRJNA939357	pubmed:38427557	KO replicate 1 bulk RNAseq	GSM7067523	source name:embryo\|tissue:embryo\|age:48 hpf\|genotype:tet2/3 double knock out\|geo loc name:missing\|collection date:missing	KO replicate 1 bulk RNAseq	Sequence reads were mapped to GRCz11/danrer11 using STAR v2.7.10a Read count extraction were performed using RSEM v1.3.1 Reads normalization and differentially expressed gene calling were performed using DESeq2 v1.32.0 Assembly: danrer11 Supplementary files format and content: tab delimited text files include gene expression for each Sample	embryo		RNA was extracted by TRNzol method and 500ng of total RNA was used to construct sequencing library. RNA libraries for RNA Seq were prepared using the Vazyme RNA Seq library kit according to the manufacturer's protocol.		tissue:embryo\|age:48 hpf\|genotype:tet2/3 double knock out	GSM7067523	GSM7067523: KO replicate 1 bulk RNAseq; Danio rerio; RNA Seq	GSM7067523 r1	GSM7067523	1	RNA was extracted by TRNzol method and 500ng of total RNA was used to construct sequencing library. RNA libraries for RNA Seq were prepared using the Vazyme RNA Seq library kit according to the manufacturer's protocol.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	DNBSEQ	DNBSEQ-G400	SRP425040		KO1.fastq.gz	fastq	4181083400.0	41810834.0	GSM7067523 r1	0:100	A:1077414361;C:996554293;G:1053357384;T:1040649776;N:13107586	100		1077414361	996554293	1053357384	1040649776	13107586	SRX19518332	SRS16905709	SRA1597336	Yunnan University	Yunnan University	1	0.87685	0.07522	0.72699	0.48859	100	B	usable mapping rate	bgi	bgi	unknown	cdna_unspecified	unknown	sc_generic	bulk	bulk	China	2023-02-27	Hatching	Embryo	Embryo Imprecise	All anatomical structures
74331	74331	SRR23635032	SRX19518331	SRS16905708	SRP425040	PRJNA939370	The TET BMP regulatory axis in pathogenesis of CFM [RNA Seq]	GSE226182	Transcriptome Analysis	Craniofacial microsomia CFM is a congenital defect that usually results from aberrant development of embryonic pharyngeal arches. However the molecular basis of CFM pathogenesis is largely unknown. Here we employ zebrafish model to investigate the mechanism of CFM pathogenesis. In early embryos tet2 and tet3 are highly expressed and are essential for pharyngeal cartilage development. Single cell RNA sequencing and genetic analyses reveal that loss of Tet2/3 impaired chondrocyte differentiation largely due to insufficient BMP signaling. Mechanistically Tet2/3 mediated 5 hydroxymethylcytosine modification allows the 5 hydroxymethylcytosine “reader” Sall4 to specifically bind the bmp4 promoter thereby promoting bmp4 expression and enabling efficient BMP signaling. These findings indicate the TET BMP regulatory axis via 5 hydroxymethylcytosine to be critical for pharyngeal cartilage development. Whole exome sequencing of CFM patient samples show that single nucleotide polymorphisms in TET and BMP pathway genes increase the risk of CFM. Collectively our study provides novel insights into understanding craniofacial development and CFM pathogenesis. Overall design: Total RNAs were purified using TRIzol reagent Life Technologies 343702. Libraries were constructed using a VAHTS Universal V8 RNA seq Library Prep Kit for MGI Vazyme according to the manufacturer's instructions and then sequenced on the MGISEQ 2000 platform.	parent bioproject:PRJNA939357	pubmed:38427557	WT replicate 2 bulk RNAseq	GSM7067522	source name:embryo\|tissue:embryo\|age:48 hpf\|genotype:wild type\|geo loc name:missing\|collection date:missing	WT replicate 2 bulk RNAseq	Sequence reads were mapped to GRCz11/danrer11 using STAR v2.7.10a Read count extraction were performed using RSEM v1.3.1 Reads normalization and differentially expressed gene calling were performed using DESeq2 v1.32.0 Assembly: danrer11 Supplementary files format and content: tab delimited text files include gene expression for each Sample	embryo		RNA was extracted by TRNzol method and 500ng of total RNA was used to construct sequencing library. RNA libraries for RNA Seq were prepared using the Vazyme RNA Seq library kit according to the manufacturer's protocol.		tissue:embryo\|age:48 hpf\|genotype:wild type	GSM7067522	GSM7067522: WT replicate 2 bulk RNAseq; Danio rerio; RNA Seq	GSM7067522 r1	GSM7067522	1	RNA was extracted by TRNzol method and 500ng of total RNA was used to construct sequencing library. RNA libraries for RNA Seq were prepared using the Vazyme RNA Seq library kit according to the manufacturer's protocol.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	DNBSEQ	DNBSEQ-G400	SRP425040		WT2.fastq.gz	fastq	1435167700.0	14351677.0	GSM7067522 r1	0:100	A:371412640;C:334204906;G:351277070;T:371684263;N:6588821	100		371412640	334204906	351277070	371684263	6588821	SRX19518331	SRS16905708	SRA1597336	Yunnan University	Yunnan University	1	0.83841	0.15087	0.71417	0.50982	100	B	usable mapping rate	bgi	bgi	unknown	cdna_unspecified	unknown	sc_generic	bulk	bulk	China	2023-02-27	Hatching	Embryo	Embryo Imprecise	All anatomical structures
74332	74332	SRR23635033	SRX19518330	SRS16905707	SRP425040	PRJNA939370	The TET BMP regulatory axis in pathogenesis of CFM [RNA Seq]	GSE226182	Transcriptome Analysis	Craniofacial microsomia CFM is a congenital defect that usually results from aberrant development of embryonic pharyngeal arches. However the molecular basis of CFM pathogenesis is largely unknown. Here we employ zebrafish model to investigate the mechanism of CFM pathogenesis. In early embryos tet2 and tet3 are highly expressed and are essential for pharyngeal cartilage development. Single cell RNA sequencing and genetic analyses reveal that loss of Tet2/3 impaired chondrocyte differentiation largely due to insufficient BMP signaling. Mechanistically Tet2/3 mediated 5 hydroxymethylcytosine modification allows the 5 hydroxymethylcytosine “reader” Sall4 to specifically bind the bmp4 promoter thereby promoting bmp4 expression and enabling efficient BMP signaling. These findings indicate the TET BMP regulatory axis via 5 hydroxymethylcytosine to be critical for pharyngeal cartilage development. Whole exome sequencing of CFM patient samples show that single nucleotide polymorphisms in TET and BMP pathway genes increase the risk of CFM. Collectively our study provides novel insights into understanding craniofacial development and CFM pathogenesis. Overall design: Total RNAs were purified using TRIzol reagent Life Technologies 343702. Libraries were constructed using a VAHTS Universal V8 RNA seq Library Prep Kit for MGI Vazyme according to the manufacturer's instructions and then sequenced on the MGISEQ 2000 platform.	parent bioproject:PRJNA939357	pubmed:38427557	WT replicate 1 bulk RNAseq	GSM7067521	source name:embryo\|tissue:embryo\|age:48 hpf\|genotype:wild type\|geo loc name:missing\|collection date:missing	WT replicate 1 bulk RNAseq	Sequence reads were mapped to GRCz11/danrer11 using STAR v2.7.10a Read count extraction were performed using RSEM v1.3.1 Reads normalization and differentially expressed gene calling were performed using DESeq2 v1.32.0 Assembly: danrer11 Supplementary files format and content: tab delimited text files include gene expression for each Sample	embryo		RNA was extracted by TRNzol method and 500ng of total RNA was used to construct sequencing library. RNA libraries for RNA Seq were prepared using the Vazyme RNA Seq library kit according to the manufacturer's protocol.		tissue:embryo\|age:48 hpf\|genotype:wild type	GSM7067521	GSM7067521: WT replicate 1 bulk RNAseq; Danio rerio; RNA Seq	GSM7067521 r1	GSM7067521	1	RNA was extracted by TRNzol method and 500ng of total RNA was used to construct sequencing library. RNA libraries for RNA Seq were prepared using the Vazyme RNA Seq library kit according to the manufacturer's protocol.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	DNBSEQ	DNBSEQ-G400	SRP425040		WT1.fastq.gz	fastq	1961618800.0	19616188.0	GSM7067521 r1	0:100	A:518460045;C:447438337;G:477081234;T:509513188;N:9125996	100		518460045	447438337	477081234	509513188	9125996	SRX19518330	SRS16905707	SRA1597336	Yunnan University	Yunnan University	1	0.81315	0.14097	0.72342	0.50905	100	B	usable mapping rate	bgi	bgi	unknown	cdna_unspecified	unknown	sc_generic	bulk	bulk	China	2023-02-27	Hatching	Embryo	Embryo Imprecise	All anatomical structures
75396	75396	SRR24497420	SRX20282374	SRS17609397	SRP436940	PRJNA971233	MCPIP1 functions as a safeguard of early embryonic development	GSE232220	Transcriptome Analysis	Expression of zc3h12a encoding Mcpip1 is tightly controlled within first cell divisions of zebrafish. Overexpression of Mcpip1 leads to the profound transcriptomic changes in the developing embryos and impairs early embryonic development of zebrafish. Overall design: RNA seq was performed to analyse transcriptome of zebrafish embryos overexpressing Mcpip1 wild type and catalytically inactive mutant.		pubmed:37805647	Mcpip1 DN replicate3	GSM7321058	source name:embryo 6 hpf\|tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1 D112N\|geo loc name:missing\|collection date:missing	Mcpip1 DN replicate3	Signal processing and basecalling was performed with Torrent Suite version 5.14.0. Raw reads were mapped to Danio rerio Ensembl genome version GRCz11 using STAR version 2.7.10a PMID: 23104886 and bowtie2 version 2.4.4 PMID: 22388286 for unmapped reads. Gene counts were created with htseq count PMID: 25260700 using Ensembl gene model. Differential expression was tested with DESeq2 version version 1.40.1 PMID: 2551628 Assembly: Danio rerio Ensembl genome version GRCz11 Supplementary files format and content: DESeq2 normalized count	embryo 6 hpf	Zebrafish eggs at 1 cell stage were microinjected with mRNA using WPI Picopump PV820 microinjector.	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.	AB/TL zebrafish were maintained in a continuous recirculating closed system aquarium with a light/dark cycle of 14/10 hours at 280C. Larvae were incubated in E3 medium at 28°C according to standard protocols.	tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1 D112N	GSM7321058	GSM7321058: Mcpip1 DN replicate3; Danio rerio; RNA Seq	GSM7321058 r1	GSM7321058	1	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ION_TORRENT	Ion Torrent Proton	SRP436940		DN_C24.fastq.gz	fastq	4215951250.0	27509986.0	GSM7321058 r1	0:153.25	A:1174686445;C:999279135;G:1076390086;T:965595584;N:0	153		1174686445	999279135	1076390086	965595584	0	SRX20282374	SRS17609397	SRA1636184	Genetics, Maria Sklodowska-Curie National Research Institute of Oncology	Genetics, Maria Skłodowska-Curie National Research Institute of Oncology	1	0.7271	0.04079	0.77583	0.48331	128	B	usable mapping rate	ion_torrent	ion_torrent	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	Poland	2023-05-10	Multi-stage	Multi-stage	Embryo Imprecise	All anatomical structures
75397	75397	SRR24497423	SRX20282373	SRS17609396	SRP436940	PRJNA971233	MCPIP1 functions as a safeguard of early embryonic development	GSE232220	Transcriptome Analysis	Expression of zc3h12a encoding Mcpip1 is tightly controlled within first cell divisions of zebrafish. Overexpression of Mcpip1 leads to the profound transcriptomic changes in the developing embryos and impairs early embryonic development of zebrafish. Overall design: RNA seq was performed to analyse transcriptome of zebrafish embryos overexpressing Mcpip1 wild type and catalytically inactive mutant.		pubmed:37805647	Mcpip1 DN replicate2	GSM7321057	source name:embryo 6 hpf\|tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1 D112N\|geo loc name:missing\|collection date:missing	Mcpip1 DN replicate2	Signal processing and basecalling was performed with Torrent Suite version 5.14.0. Raw reads were mapped to Danio rerio Ensembl genome version GRCz11 using STAR version 2.7.10a PMID: 23104886 and bowtie2 version 2.4.4 PMID: 22388286 for unmapped reads. Gene counts were created with htseq count PMID: 25260700 using Ensembl gene model. Differential expression was tested with DESeq2 version version 1.40.1 PMID: 2551628 Assembly: Danio rerio Ensembl genome version GRCz11 Supplementary files format and content: DESeq2 normalized count	embryo 6 hpf	Zebrafish eggs at 1 cell stage were microinjected with mRNA using WPI Picopump PV820 microinjector.	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.	AB/TL zebrafish were maintained in a continuous recirculating closed system aquarium with a light/dark cycle of 14/10 hours at 280C. Larvae were incubated in E3 medium at 28°C according to standard protocols.	tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1 D112N	GSM7321057	GSM7321057: Mcpip1 DN replicate2; Danio rerio; RNA Seq	GSM7321057 r1	GSM7321057	1	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ION_TORRENT	Ion Torrent Proton	SRP436940		DN_B16.fastq.gz	fastq	4150646040.0	29771678.0	GSM7321057 r1	0:139.42	A:1158168842;C:981804106;G:1077873702;T:932799390;N:0	139		1158168842	981804106	1077873702	932799390	0	SRX20282373	SRS17609396	SRA1636184	Genetics, Maria Sklodowska-Curie National Research Institute of Oncology	Genetics, Maria Skłodowska-Curie National Research Institute of Oncology	1	0.83432	0.03292	0.77068	0.48489	149	B	usable mapping rate	ion_torrent	ion_torrent	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	Poland	2023-05-10	Multi-stage	Multi-stage	Embryo Imprecise	All anatomical structures
75398	75398	SRR24497421	SRX20282372	SRS17609394	SRP436940	PRJNA971233	MCPIP1 functions as a safeguard of early embryonic development	GSE232220	Transcriptome Analysis	Expression of zc3h12a encoding Mcpip1 is tightly controlled within first cell divisions of zebrafish. Overexpression of Mcpip1 leads to the profound transcriptomic changes in the developing embryos and impairs early embryonic development of zebrafish. Overall design: RNA seq was performed to analyse transcriptome of zebrafish embryos overexpressing Mcpip1 wild type and catalytically inactive mutant.		pubmed:37805647	Mcpip1 DN replicate1	GSM7321056	source name:embryo 6 hpf\|tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1 D112N\|geo loc name:missing\|collection date:missing	Mcpip1 DN replicate1	Signal processing and basecalling was performed with Torrent Suite version 5.14.0. Raw reads were mapped to Danio rerio Ensembl genome version GRCz11 using STAR version 2.7.10a PMID: 23104886 and bowtie2 version 2.4.4 PMID: 22388286 for unmapped reads. Gene counts were created with htseq count PMID: 25260700 using Ensembl gene model. Differential expression was tested with DESeq2 version version 1.40.1 PMID: 2551628 Assembly: Danio rerio Ensembl genome version GRCz11 Supplementary files format and content: DESeq2 normalized count	embryo 6 hpf	Zebrafish eggs at 1 cell stage were microinjected with mRNA using WPI Picopump PV820 microinjector.	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.	AB/TL zebrafish were maintained in a continuous recirculating closed system aquarium with a light/dark cycle of 14/10 hours at 280C. Larvae were incubated in E3 medium at 28°C according to standard protocols.	tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1 D112N	GSM7321056	GSM7321056: Mcpip1 DN replicate1; Danio rerio; RNA Seq	GSM7321056 r1	GSM7321056	1	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ION_TORRENT	Ion Torrent Proton	SRP436940		DN_A8.fastq.gz	fastq	3405374389.0	22617333.0	GSM7321056 r1	0:150.56	A:943415180;C:825787941;G:885910600;T:750260668;N:0	150		943415180	825787941	885910600	750260668	0	SRX20282372	SRS17609394	SRA1636184	Genetics, Maria Sklodowska-Curie National Research Institute of Oncology	Genetics, Maria Skłodowska-Curie National Research Institute of Oncology	1	0.85916	0.04442	0.78344	0.48648	177	B	usable mapping rate	ion_torrent	ion_torrent	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	Poland	2023-05-10	Multi-stage	Multi-stage	Embryo Imprecise	All anatomical structures
75399	75399	SRR24497422	SRX20282371	SRS17609395	SRP436940	PRJNA971233	MCPIP1 functions as a safeguard of early embryonic development	GSE232220	Transcriptome Analysis	Expression of zc3h12a encoding Mcpip1 is tightly controlled within first cell divisions of zebrafish. Overexpression of Mcpip1 leads to the profound transcriptomic changes in the developing embryos and impairs early embryonic development of zebrafish. Overall design: RNA seq was performed to analyse transcriptome of zebrafish embryos overexpressing Mcpip1 wild type and catalytically inactive mutant.		pubmed:37805647	Mcpip1 WT replicate3	GSM7321055	source name:embryo 6 hpf\|tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1\|geo loc name:missing\|collection date:missing	Mcpip1 WT replicate3	Signal processing and basecalling was performed with Torrent Suite version 5.14.0. Raw reads were mapped to Danio rerio Ensembl genome version GRCz11 using STAR version 2.7.10a PMID: 23104886 and bowtie2 version 2.4.4 PMID: 22388286 for unmapped reads. Gene counts were created with htseq count PMID: 25260700 using Ensembl gene model. Differential expression was tested with DESeq2 version version 1.40.1 PMID: 2551628 Assembly: Danio rerio Ensembl genome version GRCz11 Supplementary files format and content: DESeq2 normalized count	embryo 6 hpf	Zebrafish eggs at 1 cell stage were microinjected with mRNA using WPI Picopump PV820 microinjector.	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.	AB/TL zebrafish were maintained in a continuous recirculating closed system aquarium with a light/dark cycle of 14/10 hours at 280C. Larvae were incubated in E3 medium at 28°C according to standard protocols.	tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1	GSM7321055	GSM7321055: Mcpip1 WT replicate3; Danio rerio; RNA Seq	GSM7321055 r1	GSM7321055	1	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ION_TORRENT	Ion Torrent Proton	SRP436940		WT_C23.fastq.gz	fastq	3644157793.0	27473010.0	GSM7321055 r1	0:132.65	A:1014320322;C:878841963;G:948316248;T:802679260;N:0	132		1014320322	878841963	948316248	802679260	0	SRX20282371	SRS17609395	SRA1636184	Genetics, Maria Sklodowska-Curie National Research Institute of Oncology	Genetics, Maria Skłodowska-Curie National Research Institute of Oncology	1	0.88531	0.03151	0.75101	0.49337	123	B	usable mapping rate	ion_torrent	ion_torrent	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	Poland	2023-05-10	Multi-stage	Multi-stage	Embryo Imprecise	All anatomical structures
75400	75400	SRR24497424	SRX20282370	SRS17609393	SRP436940	PRJNA971233	MCPIP1 functions as a safeguard of early embryonic development	GSE232220	Transcriptome Analysis	Expression of zc3h12a encoding Mcpip1 is tightly controlled within first cell divisions of zebrafish. Overexpression of Mcpip1 leads to the profound transcriptomic changes in the developing embryos and impairs early embryonic development of zebrafish. Overall design: RNA seq was performed to analyse transcriptome of zebrafish embryos overexpressing Mcpip1 wild type and catalytically inactive mutant.		pubmed:37805647	Mcpip1 WT replicate2	GSM7321054	source name:embryo 6 hpf\|tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1\|geo loc name:missing\|collection date:missing	Mcpip1 WT replicate2	Signal processing and basecalling was performed with Torrent Suite version 5.14.0. Raw reads were mapped to Danio rerio Ensembl genome version GRCz11 using STAR version 2.7.10a PMID: 23104886 and bowtie2 version 2.4.4 PMID: 22388286 for unmapped reads. Gene counts were created with htseq count PMID: 25260700 using Ensembl gene model. Differential expression was tested with DESeq2 version version 1.40.1 PMID: 2551628 Assembly: Danio rerio Ensembl genome version GRCz11 Supplementary files format and content: DESeq2 normalized count	embryo 6 hpf	Zebrafish eggs at 1 cell stage were microinjected with mRNA using WPI Picopump PV820 microinjector.	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.	AB/TL zebrafish were maintained in a continuous recirculating closed system aquarium with a light/dark cycle of 14/10 hours at 280C. Larvae were incubated in E3 medium at 28°C according to standard protocols.	tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1	GSM7321054	GSM7321054: Mcpip1 WT replicate2; Danio rerio; RNA Seq	GSM7321054 r1	GSM7321054	1	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ION_TORRENT	Ion Torrent Proton	SRP436940		WT_B15.fastq.gz	fastq	4930632556.0	30493682.0	GSM7321054 r1	0:161.69	A:1385638764;C:1206486517;G:1269832302;T:1068674973;N:0	161		1385638764	1206486517	1269832302	1068674973	0	SRX20282370	SRS17609393	SRA1636184	Genetics, Maria Sklodowska-Curie National Research Institute of Oncology	Genetics, Maria Skłodowska-Curie National Research Institute of Oncology	1	0.86405	0.03935	0.78324	0.49971	107	B	usable mapping rate	ion_torrent	ion_torrent	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	Poland	2023-05-10	Multi-stage	Multi-stage	Embryo Imprecise	All anatomical structures
75401	75401	SRR24497425	SRX20282369	SRS17609392	SRP436940	PRJNA971233	MCPIP1 functions as a safeguard of early embryonic development	GSE232220	Transcriptome Analysis	Expression of zc3h12a encoding Mcpip1 is tightly controlled within first cell divisions of zebrafish. Overexpression of Mcpip1 leads to the profound transcriptomic changes in the developing embryos and impairs early embryonic development of zebrafish. Overall design: RNA seq was performed to analyse transcriptome of zebrafish embryos overexpressing Mcpip1 wild type and catalytically inactive mutant.		pubmed:37805647	Mcpip1 WT replicate1	GSM7321053	source name:embryo 6 hpf\|tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1\|geo loc name:missing\|collection date:missing	Mcpip1 WT replicate1	Signal processing and basecalling was performed with Torrent Suite version 5.14.0. Raw reads were mapped to Danio rerio Ensembl genome version GRCz11 using STAR version 2.7.10a PMID: 23104886 and bowtie2 version 2.4.4 PMID: 22388286 for unmapped reads. Gene counts were created with htseq count PMID: 25260700 using Ensembl gene model. Differential expression was tested with DESeq2 version version 1.40.1 PMID: 2551628 Assembly: Danio rerio Ensembl genome version GRCz11 Supplementary files format and content: DESeq2 normalized count	embryo 6 hpf	Zebrafish eggs at 1 cell stage were microinjected with mRNA using WPI Picopump PV820 microinjector.	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.	AB/TL zebrafish were maintained in a continuous recirculating closed system aquarium with a light/dark cycle of 14/10 hours at 280C. Larvae were incubated in E3 medium at 28°C according to standard protocols.	tissue:embryo 6 hpf\|genotype:AB/TL\|treatment:microinjection with mRNA encoding zebrafish Mcpip1	GSM7321053	GSM7321053: Mcpip1 WT replicate1; Danio rerio; RNA Seq	GSM7321053 r1	GSM7321053	1	Zebrafish embryos were collected in Fenozol A&A Biotechnology Gdansk Polska and stored at 80°C prior to analysis. For RNA isolation the samples were homogenized in Fenozol using a tissue homogenizer OMNI International Kennesaw GA USA. The poly A mRNA fraction from total RNA was isolated with Dynabeads® mRNA DIRECT™ Micro Kit Thermo. The sequencing library for each RNA sample was prepared according to the protocol provided by the manufacturer using the Ion Total RNA Seq Kit v2 Thermo. The libraries were generated from 1 15 ng of mRNA by fragmenting the mRNA with RNaseIII purifying the fragmented RNA and hybridizing and ligating it with Ion adaptors. Subsequently the RNA products were reverse transcribed and amplified to double stranded cDNA and then purified using a magnetic bead based method. The molar concentration and size of each cDNA library was determined using the DNA HS Kit on Bioanalyzer 2100 Agilent. Each library was diluted to 53 pM concentration before template preparation. Up to three barcoded libraries were mixed in equal volume and used for automatic template preparation on the Ion Chef instrument Thermo using reagents from the Ion PI Hi Q 200 Kit Thermo and Ion PI v3 Proton Chip.		RNA-Seq	TRANSCRIPTOMIC	cDNA	SINGLE	ION_TORRENT	Ion Torrent Proton	SRP436940		WT_A7.fastq.gz	fastq	4888312783.0	29414563.0	GSM7321053 r1	0:166.19	A:1356799075;C:1172146709;G:1273947582;T:1085419417;N:0	166		1356799075	1172146709	1273947582	1085419417	0	SRX20282369	SRS17609392	SRA1636184	Genetics, Maria Sklodowska-Curie National Research Institute of Oncology	Genetics, Maria Skłodowska-Curie National Research Institute of Oncology	1	0.82661	0.05547	0.7751	0.49668	188	B	usable mapping rate	ion_torrent	ion_torrent	unknown	cdna_unspecified	unknown	bulk	bulk	bulk	Poland	2023-05-10	Multi-stage	Multi-stage	Embryo Imprecise	All anatomical structures

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");;