{"database": "metadata", "table": "run_metadata", "rows": [[10005, "ERR6806872", "ERX6430465", "ERS5060035", "ERP123913", "PRJEB40292", "Multidimensional chromatin profiling of zebrafish and human pancreas to uncover and validate disease related enhancers", "ena-STUDY-I3S-10-09-2020-08:12:35:299-4", "Other", "The pancreas is a central organ for human diseases. Most disease associated alleles overlap with non coding cis regulatory elements of DNA  suggesting that alterations in regulatory sequences contribute to pancreatic diseases. However  the interspecies identification of equivalent cis regulatory elements required for in vivo testing face fundamental challenges  including lack of sequence conservation. In this work  we performed a combined analysis of ATAC seq  ChIP seq  4C seq and HiChIP seq data from zebrafish and human pancreatic cells to identify interspecies functionally equivalent cis regulatory elements  regardless of sequence conservation. To link cis regulation with the expression of target genes in the pancreas  we additionally integrated in our analysis own and public RNA seq data from zebrafish pancreatic cell types. Among several disease associated sequences  we identified a zebrafish ptf1a distal enhancer whose deletion generates pancreatic agenesis  demonstrating the causality of this condition in humans. Our results further demonstrate that this phenotype is a consequence of loss of pancreas progenitor cells. Overall  we show that chromatin profiling can uncover interspecies functional equivalency of cis regulatory elements  contributing to the prediction of new disease causative enhancers and their role in human disease.", "ChIP seq  ATAC seq  HiChIP seq  4C seq  RNA seq|chromatin accessibility|cis regulatory mutations|pancreas and pancreatic diseases|transcriptional enhancers|ENA FIRST PUBLIC:2020 09 11|ENA LAST UPDATE:2021 09 22", null, "Adult zebrafish endocrine pancreas RNA seq replicate3 raw reads", "Zebrafish Endocrine Pancreas RNA seq replicate3", "SAMEA7301476", "I3S", "ENA first public:2021 09 23|ENA last update:2021 09 23|External Id:SAMEA7301476|INSDC center alias:I3S|INSDC center name:I3S|INSDC first public:2021 09 23T20:37:00Z|INSDC last update:2021 09 23T20:37:00Z|INSDC status:public|Submitter Id:Zebrafish Endocrine Pancreas RNA seq replicate3|common name:zebrafish|sample name:Zebrafish Endocrine Pancreas RNA seq replicate3|tissue type:endocrine pancreas principal islet", null, null, null, null, null, null, null, null, "Illumina HiSeq 2000 sequencing", "ena EXPERIMENT I3S 23 09 2021 16:43:09:330 3", "Endocrine3", "1", "Total RNA extracted with TRIZOL from zebrafish primary pancreatic islet and preprared for sequencing with the TruSeq kit", null, "RNA-Seq", "TRANSCRIPTOMIC", "cDNA", "SINGLE", "ILLUMINA", "Illumina HiSeq 2000", null, "ERP123913", "Illumina HiSeq 2000 sequencing", "ENA FIRST PUBLIC:2021 09 23|ENA LAST UPDATE:2021 09 23", "Endocrine_Old_1.fastq.gz", "fastq", 1979582750.0, 39591655.0, "ena RUN I3S 23 09 2021 16:43:09:330 3", "0:50 1:0", "A:483713055;C:499972514;G:479484600;T:516281513;N:131068", 50, 0, null, null, 483713055, 499972514, 479484600, 516281513, 131068, "ERX6430465", "ERS5060035", "ERA6385885", "I3S|European Nucleotide Archive", "I3S", 1, 0.93722, null, 0.04096, null, 0.7559, null, 0.52069, null, 50, null, "B", null, "usable mapping rate", "illumina", "hiseq_era", "unknown", "cdna_unspecified", "trueseq", "bulk", "unknown", "unknown", null, "Portugal", "2020-09-11", "Adult", "Adult", "Pancreas", "Endocrine System"]], "columns": ["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"], "primary_keys": ["rowid"], "primary_key_values": ["10005"], "units": {}, "query_ms": 14.072383999518934}