metadata: run_metadata: 1 row where experiment.library_selection = "other", experiment.library_source = "TRANSCRIPTOMIC" and tissue_curation

1 row where experiment.library_selection = "other", experiment.library_source = "TRANSCRIPTOMIC" and tissue_curation_coarse = "Endocrine System"

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.description	sample.title	sample.alias	sample.centername	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.spot_descriptor	experiment.study_ref	run.title	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.r3_length	run.r4_length	run.Acount	run.Ccount	run.Gcount	run.Tcount	run.Ncount	run.experiment	run.pool_member	submission.accession	submission.srasource	submission.bioprojectsource	seqdetective.n_mates	seqdetective.mapping_rate.mate1	seqdetective.mapping_rate.mate2	seqdetective.nofeature_rate.mate1	seqdetective.nofeature_rate.mate2	seqdetective.sparsity.mate1	seqdetective.sparsity.mate2	seqdetective.pos_strand_rate.mate1	seqdetective.pos_strand_rate.mate2	seqdetective.readlen.mate1	seqdetective.readlen.mate2	seqdetective.judgement.mate1	seqdetective.judgement.mate2	seqdetective.judgement.reason	platform_family	instrument_generation	read_bias	selection_class	prep_kit	sc_or_bulk	tech_class	technology	tech_variant	submission.bioprojectsource.country	earliest_date	devstage_curation	devstage_curation_coarse	tissue_curation	tissue_curation_coarse
43988	43988	SRR6811827	SRX3768867	SRS3023384	SRP121343	PRJNA415636	Simultaneous lineage tracing and cell type identification using CRISPR/Cas9 induced genetic scars	GSE106121	Other	A key goal of developmental biology is to understand how a single cell transforms into a full grown organism consisting of many different cell types. Single cell RNA sequencing scRNA seq has become a widely used method due to its ability to identify all cell types in a tissue or organ in a systematic manner. However a major challenge is to organize the resulting taxonomy of cell types into lineage trees revealing the developmental origin of cells. Here we present a strategy for simultaneous lineage tracing and transcriptome profiling in thousands of single cells. By combining scRNA seq with computational analysis of lineage barcodes generated by genome editing of transgenic reporter genes we reconstruct developmental lineage trees in zebrafish larvae and adult fish. In future analyses LINNAEUS LINeage tracing by Nuclease Activated Editing of Ubiquitous Sequences can be used as a systematic approach for identifying the lineage origin of novel cell types or of known cell types under different conditions. Overall design: Combining scRNA seq with computational analysis of lineage barcodes generated by genome editing of transgenic reporter genes.		pubmed:29644996		Pancreas 3 endo scar	GSM3032170		source name:Primary pancreatic islet\|strain/background:Zebrabow M\|tissue:Primary pancreatic islet\|developmental stage:Adult	Pancreas 3 endo scar	Library strategy: Targeted amplification Scar reads have the same structure as transcript reads: they consist of a barcode a UMI and a scar. The scar sequences were aligned using bwa mem6 to a reference of RFP. We defined a cell as a barcode with at least 500 reads. We removed reads that were unmapped had an incorrect barcode or did not start with the exact PCR primer we used. We truncated all scar sequences to 75 nucleotides and filtered out shorter sequences. To correct for sequencing errors we implemented several rounds of scar filtering Supplementary Fig. 2 in publication. We started by counting the number of times each molecule was sequenced. Sequencing errors will typically have fewer reads than the actual scars they originate from. As a first filtering step we therefore removed all molecules only seen once to reduce the complexity in the dataset for consecutive filtering steps. In the second filtering step we aimed to remove easily recognizable sequencing errors. To this end we consecutively considered scar sequences that have the same cellular barcode and UMI UMIs that have the same cellular barcode and scar sequence and cellular barcodes that have the same UMI and scar sequence. In each step we kept only the molecule with the highest number of reads. The rationale behind this is that it is very improbable to have two valid scar sequences in the same cell with the same UMI or to have a scar sequence with the same UMI appear in two different cells. The observation of two different UMIs for the same scar in the same cell is much more likely and corresponds to detection of multiple transcripts from the same locus but information about scar expression levels was not required in our downstream analysis. In the third filtering step we specifically targeted sequencing errors within each cell. We compared the scar sequences found within a cell to each other. We filtered out sequences that had a Hamming distance of 2 or less to another scar sequence in the same cell that occurred in at least eight tim…	Primary pancreatic islet		Single cell dissociation. 10X Genomics Chromium		strain/background:Zebrabow M\|tissue:Primary pancreatic islet\|developmental stage:Adult	GSM3032170	GSM3032170: Pancreas 3 endo scar; Danio rerio; OTHER	GSM3032170		1	Single cell dissociation. 10X Genomics Chromium	GEO Accession:GSM3032170	OTHER	TRANSCRIPTOMIC	other	PAIRED	ILLUMINA	NextSeq 500		SRP121343			P7endo_scar_R1.fastq.gz P7endo_scar_R2.fastq.gz	fastq fastq	2537781396.0	20465979.0	GSM3032170 r1	0:26 1:98	A:741745261;C:801599713;G:561531527;T:431666561;N:1238334	26	98			741745261	801599713	561531527	431666561	1238334	SRX3768867	SRS3023384	SRA623333	GEO	Max Delbrück Center	2	0.00014	0.00289	0.00012	0.00028	0.99995	0.99602	1.0	0.68478	26	98	T	T	mates < 9% mapping rate	illumina	nextseq	unknown	other	unknown	sc	single_cell_droplet	10x		Germany	2018-03-06	Adult	Adult	Pancreas	Endocrine System

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");;