pysradb: A Python package to query next-generation sequencing metadata and data from NCBI Sequence Read Archive.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:31114675", "kind": "science-record", "revision": 4, "content_hash": "sha256:efd609a923a2afd96504e5b8b2dc0e4235bbfc42dad422ef82ddd001f48287a5", "created_at": "2026-11-01T15:40:45Z", "updated_at": "2026-11-01T18:50:50Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "pysradb: A Python package to query next-generation sequencing metadata and data from NCBI Sequence Read Archive.", "doi": "10.12688/f1000research.18676.1", "pmid": "31114675", "authors": ["Saket Choudhary"], "journal": "F1000Research", "year": 2019, "abstract": "The NCBI Sequence Read Archive (SRA) is the primary archive of next-generation sequencing datasets. SRA makes metadata and raw sequencing data available to the research community to encourage reproducibility and to provide avenues for testing novel hypotheses on publicly available data. However, methods to programmatically access this data are limited. We introduce the Python package, pysradb, which provides a collection of command line methods to query and download metadata and data from SRA, utilizing the curated metadata database available through the SRAdb project. We demonstrate the utility of pysradb on multiple use cases for searching and downloading SRA datasets. It is available freely at https://github.com/saketkc/pysradb.", "claims": [{"id": "claim-data-access", "statement": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:31114675", "locator": "sections[14] \"Underlying data\" paragraph 2", "quote": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075"}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:31114675"], "outputs": ["the published estimate and its evidence"], "instruments": [], "reagents": []}, {"id": "obtain_source_data", "order": 2, "name": "Obtain the source data from the named repository", "kind": "data-preparation", "state": "complete", "blocked_on": null, "description": "The GEO series accession resolves and its sample accessions are listed. This lane did not download the dataset or read its licence.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE100007"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "complete", "blocked_on": null, "description": "Apply the paper's statistical method to the resolved series and compare the result with the published target.", "duration_hours": null, "parameters": {}, "inputs": ["data:geo:GSE100007"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:31114675", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.12688/f1000research.18676.1", "sha256": "sha256:16b2fd09cbd9fee8e7e9818886f1a62c0e8bac2b2da892157d31974e4a4d378a", "bytes": 17796, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.12688/f1000research.18676.1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6505635", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE100007", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE100007", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE100007", "version": null, "note": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2667747", "GSM2667748", "GSM2667749", "GSM2667750", "GSM2667751", "GSM2667752", "GSM2667753", "GSM2667754", "GSM2667755", "GSM2667756", "GSM2667757", "GSM2667758", "GSM2667759", "GSM2667760", "GSM2667761", "GSM2667762", "GSM2667763", "GSM2667764", "GSM2667765", "GSM2667766", "GSM2667767", "GSM2667768", "GSM2667769", "GSM2667770", "GSM2667771", "GSM2667772", "GSM2667773", "GSM2667774", "GSM2667775", "GSM2667776", "GSM2667777", "GSM2667778", "GSM2667779", "GSM2667780", "GSM2667781", "GSM2667782", "GSM2667783", "GSM2667784", "GSM2667785", "GSM2667786", "GSM2667787", "GSM2667788", "GSM2667789", "GSM2667790", "GSM2667791", "GSM2667792", "GSM2667793", "GSM2667794", "GSM2667795", "GSM2667796", "GSM2667797", "GSM2667798"], "sample_count": 52, "group_sizes": null, "group_sizes_basis": null, "platform": "20301", "taxon": "Homo sapiens", "title": "Widespread translational remodeling during human neuronal differentiation", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE24355", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE24355", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE24355", "version": null, "note": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM600348", "GSM600349", "GSM600350", "GSM600351", "GSM600352"], "sample_count": 5, "group_sizes": null, "group_sizes_basis": null, "platform": "9138", "taxon": "Homo sapiens", "title": "Deep-transcriptome and ribonome sequencing redefines the molecular networks of pluripotency and the extracellular space in human Embryonic Stem cells", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE25842", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE25842", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE25842", "version": null, "note": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM634750", "GSM634751", "GSM634752", "GSM634753", "GSM634754", "GSM634755", "GSM634756", "GSM634757", "GSM634758", "GSM634759", "GSM634760", "GSM634761", "GSM634762", "GSM634763", "GSM634764", "GSM634765", "GSM634766"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "9138", "taxon": "Homo sapiens", "title": "Deep-transcriptome and ribonome sequencing redefines the molecular networks of pluripotency and the extracellular space in human Embryonic Stem cells (part 2)", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE41637", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE41637", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE41637", "version": null, "note": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1020640", "GSM1020641", "GSM1020642", "GSM1020643", "GSM1020644", "GSM1020645", "GSM1020646", "GSM1020647", "GSM1020648", "GSM1020649", "GSM1020650", "GSM1020651", "GSM1020652", "GSM1020653", "GSM1020654", "GSM1020655", "GSM1020656", "GSM1020657", "GSM1020658", "GSM1020659", "GSM1020660", "GSM1020661", "GSM1020662", "GSM1020663", "GSM1020664", "GSM1020665", "GSM1020666", "GSM1020667", "GSM1020668", "GSM1020669", "GSM1020670", "GSM1020671", "GSM1020672", "GSM1020673", "GSM1020674", "GSM1020675", "GSM1020676", "GSM1020677", "GSM1020678", "GSM1020679", "GSM1020680", "GSM1020681", "GSM1020682", "GSM1020683", "GSM1020684", "GSM1020685", "GSM1020686", "GSM1020687", "GSM1020688", "GSM1020689", "GSM1020690", "GSM1020691", "GSM1020692", "GSM1020693", "GSM1020694", "GSM1020695", "GSM1020696", "GSM1020697", "GSM1020698", "GSM1020699", "GSM1020700", "GSM1020701", "GSM1020702", "GSM1020703", "GSM1020704", "GSM1020705", "GSM1020706", "GSM1020707", "GSM1020708", "GSM1020709", "GSM1020710", "GSM1020711", "GSM1020712", "GSM1020713", "GSM1020714", "GSM1020715", "GSM1020716", "GSM1020717", "GSM1020718", "GSM1020719", "GSM1020720", "GSM1020721", "GSM1020722", "GSM1020723", "GSM1020724", "GSM1020725", "GSM1020726", "GSM1020727", "GSM1020728", "GSM1020729", "GSM1020730", "GSM1020731", "GSM1020732", "GSM1020733", "GSM1020734", "GSM1020735", "GSM1020736", "GSM1020737", "GSM1020738", "GSM1020739", "GSM1020740", "GSM1020741", "GSM1020742", "GSM1020743", "GSM1020744", "GSM1020745", "GSM1020746", "GSM1020747", "GSM1020748", "GSM1020749", "GSM1020750", "GSM1020751", "GSM1020752", "GSM1020753", "GSM1020754", "GSM1020755", "GSM1020756", "GSM1020757", "GSM1020758", "GSM1020759", "GSM1020760", "GSM1020761", "GSM1020762", "GSM1020763", "GSM1020764", "GSM1020765", "GSM1020766", "GSM1020767", "GSM1020768", "GSM1020769", "GSM1020770", "GSM1020771", "GSM1020772", "GSM1020773"], "sample_count": 134, "group_sizes": null, "group_sizes_basis": null, "platform": "14844;15749;16133;10669;14954;11002;13112", "taxon": "Bos taurus; Mus musculus; Rattus norvegicus; Gallus gallus; Macaca mulatta", "title": "Evolutionary dynamics of gene and isoform regulation in mammalian tissues", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRP000941", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=SRP000941", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRP000941", "version": null, "note": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "access_statement_kind": "repository_route_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:SRP010679", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=SRP010679", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "SRP010679", "version": null, "note": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075", "access_statement_kind": "repository_route_statement", "sample_accessions": [], "sample_count": null, "group_sizes": null, "group_sizes_basis": null, "platform": null, "taxon": null, "title": null, "resolution_checked_at": "2026-10-31T18:35:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:31114675:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c1e1028004a627054a49e273d71231b65d89ae7b0f3f7c0271321dd2ba73a930", "bytes": 625, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#T1", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 6, "section_title": "Search", "row_count": 9, "column_count": 4}, "table": {"label": null, "caption": null, "rows": [["study_accession", "experiment_accession", "sample_accession", "run_accession"], ["DRP003075", "DRX019536", "DRS026974", "DRR021383"], ["DRP003075", "DRX019537", "DRS026982", "DRR021384"], ["DRP003075", "DRX019538", "DRS026979", "DRR021385"], ["DRP003075", "DRX019540", "DRS026984", "DRR021387"], ["DRP003075", "DRX019541", "DRS026978", "DRR021388"], ["DRP003075", "DRX019543", "DRS026980", "DRR021390"], ["DRP003075", "DRX019544", "DRS026981", "DRR021391"], ["ERP013565", "ERX1264364", "ERS1016056", "ERR1190989"]], "row_count": 9, "column_count": 4, "numeric_cells": 32, "header_rows": 0, "locator": "section[6]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:31114675:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d858fbfabb03d662fc35231e5bd8112932530dd234226b4c266e79264a832eb6", "bytes": 823, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#T2", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 7, "section_title": "Getting metadata for a SRA project", "row_count": 13, "column_count": 4}, "table": {"label": null, "caption": null, "rows": [["study_accession", "experiment_accession", "sample_accession", "run_accession"], ["SRP010679", "SRX118285", "SRS290854", "SRR403882"], ["SRP010679", "SRX118286", "SRS290855", "SRR403883"], ["SRP010679", "SRX118287", "SRS290856", "SRR403884"], ["SRP010679", "SRX118288", "SRS290857", "SRR403885"], ["SRP010679", "SRX118289", "SRS290858", "SRR403886"], ["SRP010679", "SRX118290", "SRS290859", "SRR403887"], ["SRP010679", "SRX118291", "SRS290860", "SRR403888"], ["SRP010679", "SRX118292", "SRS290861", "SRR403889"], ["SRP010679", "SRX118293", "SRS290862", "SRR403890"], ["SRP010679", "SRX118294", "SRS290863", "SRR403891"], ["SRP010679", "SRX118295", "SRS290864", "SRR403892"], ["SRP010679", "SRX118296", "SRS290865", "SRR403893"]], "row_count": 13, "column_count": 4, "numeric_cells": 48, "header_rows": 0, "locator": "section[7]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:31114675:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a735e99196e90d8d54f351fb26a1a893885512bce0c30dc62c9df58d89eee90f", "bytes": 923, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[2]#T3", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 7, "section_title": "Getting metadata for a SRA project", "row_count": 5, "column_count": 5}, "table": {"label": null, "caption": null, "rows": [["study_accession", "experiment_accession", "sample_accession", "run_accession", "sample_attribute"], ["SRP010679", "SRX118285", "SRS290854", "SRR403882", "source_name: PC3 human prostate cancer cells || cell line: PC3 || sample type: polyA RNA || treatment: vehicle"], ["SRP010679", "SRX118286", "SRS290855", "SRR403883", "source_name: PC3 human prostate cancer cells || cell line: PC3 || sample type: ribosome protected RNA || treatment: vehicle"], ["SRP010679", "SRX118287", "SRS290856", "SRR403884", "source_name: PC3 human prostate cancer cells || cell line: PC3 || sample type: polyA RNA || treatment: rapamycin"], ["SRP010679", "SRX118288", "SRS290857", "SRR403885", "source_name: PC3 human prostate cancer cells || cell line: PC3 || sample type: ribosome protected RNA || treatment: rapamycin"]], "row_count": 5, "column_count": 5, "numeric_cells": 16, "header_rows": 0, "locator": "section[7]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:31114675:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:068c166813e1323b53718020c7cf7eb1a8781754493bf7bcd504b91c3e27bc01", "bytes": 1225, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[3]#T4", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 7, "section_title": "Getting metadata for a SRA project", "row_count": 14, "column_count": 5}, "table": {"label": null, "caption": null, "rows": [["... [truncated]"], ["run_accession", "cell_line", "sample_type", "source_name", "treatment"], ["SRR403882", "pc3", "polya rna", "pc3 human prostate cancer cells", "vehicle"], ["SRR403883", "pc3", "ribosome protected rna", "pc3 human prostate cancer cells", "vehicle"], ["SRR403884", "pc3", "polya rna", "pc3 human prostate cancer cells", "rapamycin"], ["SRR403885", "pc3", "ribosome protected rna", "pc3 human prostate cancer cells", "rapamycin"], ["SRR403886", "pc3", "polya rna", "pc3 human prostate cancer cells", "pp242"], ["SRR403887", "pc3", "ribosome protected rna", "pc3 human prostate cancer cells", "pp242"], ["SRR403888", "pc3", "polya rna", "pc3 human prostate cancer cells", "vehicle"], ["SRR403889", "pc3", "ribosome protected rna", "pc3 human prostate cancer cells", "vehicle"], ["SRR403890", "pc3", "polya rna", "pc3 human prostate cancer cells", "rapamycin"], ["SRR403891", "pc3", "ribosome protected rna", "pc3 human prostate cancer cells", "rapamycin"], ["SRR403892", "pc3", "polya rna", "pc3 human prostate cancer cells", "pp242"], ["SRR403893", "pc3", "ribosome protected rna", "pc3 human prostate cancer cells", "pp242"]], "row_count": 14, "column_count": 5, "numeric_cells": 16, "header_rows": 0, "locator": "section[7]/table-wrap[3]#T4"}}, {"id": "asset:table:pmid:31114675:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0465cfdf71d913dff07de151282a2b5474b745d3429f070ee5ed58a491e37cef", "bytes": 233, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[4]#T5", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 7, "section_title": "Getting metadata for a SRA project", "row_count": 5, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["999", "Bisulfite-Seq"], ["768", "ChIP-Seq"], ["121", "OTHER"], ["353", "RNA-Seq"], ["28", "WGS"]], "row_count": 5, "column_count": 2, "numeric_cells": 5, "header_rows": 0, "locator": "section[7]/table-wrap[4]#T5"}}, {"id": "asset:table:pmid:31114675:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:27948e036be34abd5e28610b62e70242f87740c569ce12701819a98eef28ddc0", "bytes": 227, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#T6", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 8, "section_title": "Getting SRPs from GSE", "row_count": 3, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["study_alias", "study_accession"], ["GSE24355", "SRP003870"], ["GSE25842", "SRP005378"]], "row_count": 3, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[8]/table-wrap[1]#T6"}}, {"id": "asset:table:pmid:31114675:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:76d15db0151d2dc7b6fc446d70b71bda0de8725b4df507d10f505780e3afebbc", "bytes": 957, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[2]#T7", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 8, "section_title": "Getting SRPs from GSE", "row_count": 10, "column_count": 6}, "table": {"label": null, "caption": null, "rows": [["study_alias", "study_accession", "experiment_accession", "sample_accession", "experiment_alias", "sample_alias"], ["GSE100007", "SRP109126", "SRX2916198", "SRS2282390", "GSM2667747", "GSM2667747"], ["GSE100007", "SRP109126", "SRX2916199", "SRS2282391", "GSM2667748", "GSM2667748"], ["GSE100007", "SRP109126", "SRX2916200", "SRS2282392", "GSM2667749", "GSM2667749"], ["GSE100007", "SRP109126", "SRX2916201", "SRS2282393", "GSM2667750", "GSM2667750"], ["GSE100007", "SRP109126", "SRX2916202", "SRS2282394", "GSM2667751", "GSM2667751"], ["GSE100007", "SRP109126", "SRX2916203", "SRS2282395", "GSM2667752", "GSM2667752"], ["GSE100007", "SRP109126", "SRX2916204", "SRS2282396", "GSM2667753", "GSM2667753"], ["GSE100007", "SRP109126", "SRX2916205", "SRS2282397", "GSM2667754", "GSM2667754"], ["GSE100007", "SRP109126", "SRX2916206", "SRS2282400", "GSM2667755", "GSM2667755"]], "row_count": 10, "column_count": 6, "numeric_cells": 54, "header_rows": 0, "locator": "section[8]/table-wrap[2]#T7"}}, {"id": "asset:table:pmid:31114675:8", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:931a8963c24dcdfaeaec42e7d5e5ddc1c2967e4c20b48f8e0492ab77e0901b6b", "bytes": 432, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T8", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 9, "section_title": "Getting a list of GEO experiments for a GEO study", "row_count": 10, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["study_alias", "experiment_alias"], ["GSE41637", "GSM1020640_1"], ["GSE41637", "GSM1020641_1"], ["GSE41637", "GSM1020642_1"], ["GSE41637", "GSM1020643_1"], ["GSE41637", "GSM1020644_1"], ["GSE41637", "GSM1020645_1"], ["GSE41637", "GSM1020646_1"], ["GSE41637", "GSM1020647_1"], ["GSE41637", "GSM1020648_1"]], "row_count": 10, "column_count": 2, "numeric_cells": 18, "header_rows": 0, "locator": "section[9]/table-wrap[1]#T8"}}, {"id": "asset:table:pmid:31114675:9", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e42c2869c6893e0d16de178df738f7009db11e485e1c20e13364f5bfca3bc393", "bytes": 1021, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#T9", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 9, "section_title": "Getting a list of GEO experiments for a GEO study", "row_count": 10, "column_count": 3}, "table": {"label": null, "caption": null, "rows": [["study_alias", "experiment_alias", "sample_attribute"], ["GSE41637", "GSM1020640_1", "source_name: mouse_brain || strain: DBA/2J || tissue: brain"], ["GSE41637", "GSM1020641_1", "source_name: mouse_colon || strain: DBA/2J || tissue: colon"], ["GSE41637", "GSM1020642_1", "source_name: mouse_heart || strain: DBA/2J || tissue: heart"], ["GSE41637", "GSM1020643_1", "source_name: mouse_kidney || strain: DBA/2J || tissue: kidney"], ["GSE41637", "GSM1020644_1", "source_name: mouse_liver || strain: DBA/2J || tissue: liver"], ["GSE41637", "GSM1020645_1", "source_name: mouse_lung || strain: DBA/2J || tissue: lung"], ["GSE41637", "GSM1020646_1", "source_name: mouse_skm || strain: DBA/2J || tissue: skeletal muscle"], ["GSE41637", "GSM1020647_1", "source_name: mouse_spleen || strain: DBA/2J || tissue: spleen"], ["GSE41637", "GSM1020648_1", "source_name: mouse_testes || strain: DBA/2J || tissue: testes"]], "row_count": 10, "column_count": 3, "numeric_cells": 27, "header_rows": 0, "locator": "section[9]/table-wrap[2]#T9"}}, {"id": "asset:table:pmid:31114675:10", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:cec1fea3364d0ddb78e64b7c298adf6efc8b6c585cf5fee685915862b1b4094f", "bytes": 633, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[3]#T10", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 9, "section_title": "Getting a list of GEO experiments for a GEO study", "row_count": 8, "column_count": 5}, "table": {"label": null, "caption": null, "rows": [["study_alias", "experiment_alias", "source_name", "strain", "tissue"], ["GSE41637", "GSM1020640_1", "mouse_brain", "dba/2j", "brain"], ["GSE41637", "GSM1020641_1", "mouse_colon", "dba/2j", "colon"], ["GSE41637", "GSM1020642_1", "mouse_heart", "dba/2j", "heart"], ["GSE41637", "GSM1020643_1", "mouse_kidney", "dba/2j", "kidney"], ["GSE41637", "GSM1020644_1", "mouse_liver", "dba/2j", "liver"], ["GSE41637", "GSM1020645_1", "mouse_lung", "dba/2j", "lung"], ["GSE41637", "GSM1020646_1", "mouse_skm", "dba/2j", "skeletal muscle"]], "row_count": 8, "column_count": 5, "numeric_cells": 21, "header_rows": 0, "locator": "section[9]/table-wrap[3]#T10"}}, {"id": "asset:table:pmid:31114675:11", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:3d5d5a4fcf793dd2c1ccb53fe39805f8d135e4230be2aff28bb627edfc9b1d2d", "bytes": 240, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#T11", "version": null, "note": null, "structure": {"pmcid": "PMC6505635", "section_index": 10, "section_title": "Getting SRR from GSM", "row_count": 3, "column_count": 2}, "table": {"label": null, "caption": null, "rows": [["experiment_alias", "run_accession"], ["GSM1020640_1", "SRR594393"], ["GSM1020646_1", "SRR594399"]], "row_count": 3, "column_count": 2, "numeric_cells": 4, "header_rows": 0, "locator": "section[10]/table-wrap[1]#T11"}}], "gaps": ["asset:data:geo:GSE100007 not downloaded", "asset:data:geo:GSE100007 licence not read", "asset:data:geo:GSE24355 not downloaded", "asset:data:geo:GSE24355 licence not read", "asset:data:geo:GSE25842 not downloaded", "asset:data:geo:GSE25842 licence not read", "asset:data:geo:GSE41637 not downloaded", "asset:data:geo:GSE41637 licence not read", "asset:data:geo:SRP000941 not downloaded", "asset:data:geo:SRP000941 licence not read", "asset:data:geo:SRP010679 not downloaded", "asset:data:geo:SRP010679 licence not read"]}, "analysis": {"state": "absent", "methods": [], "targets": [], "gaps": ["method", "operations"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (not named), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE24355", "GSE25842", "GSE100007", "GSE41637", "SRP010679", "SRP000941"], "resolved_accessions": ["GSE24355", "GSE25842", "GSE100007", "GSE41637"], "statements": ["Dataset from DDBJ Sequence Read Archive, Accession number DRP003075: https://identifiers.org/ insdc.sra/DRP003075"], "basis": "The paper names GSE24355, GSE25842, GSE100007, GSE41637 in Gene Expression Omnibus and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:31114675", "data:geo:GSE100007", "asset:table:pmid:31114675:1", "asset:table:pmid:31114675:2", "asset:table:pmid:31114675:3", "asset:table:pmid:31114675:4", "asset:table:pmid:31114675:5", "asset:table:pmid:31114675:6", "asset:table:pmid:31114675:7", "asset:table:pmid:31114675:8", "asset:table:pmid:31114675:9", "asset:table:pmid:31114675:10", "asset:table:pmid:31114675:11"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE100007"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:14:48Z", "independence": "single_reader"}, "evidence_check": {"method": null, "availability": null}, "calls": 3, "usage": {"prompt_tokens": 15611, "completion_tokens": 2323, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:31114675", "type": "paper", "label": "pmid:31114675"}, {"id": "source:pmid:31114675", "type": "manuscript", "label": "PMID 31114675 full text"}, {"id": "data:geo:GSE100007", "type": "dataset", "label": "GEO GSE100007"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:31114675", "type": "paper", "label": "pmid:31114675"}, {"id": "source:pmid:31114675", "type": "manuscript", "label": "PMID 31114675 full text"}, {"id": "data:geo:GSE100007", "type": "dataset", "label": "GEO GSE100007"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-31114675", "type": "extraction", "used": ["source:pmid:31114675"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE100007", "type": "accession_resolution", "used": ["data:geo:GSE100007"], "agent": "agent:corpus-assay-engine"}], "agents": [{"id": "agent:corpus-assay-engine", "type": "software", "label": "Corpus assay engine"}, {"id": "agent:minimax-reader", "type": "software", "label": "MiniMax literature reader"}], "source_run_id": "reading-sci-2026-11-01", "dsl_catalogue_fingerprint": "343fb30756ba6ec3", "capability_table_fingerprint": "2cb3e42f047d2ecf", "snapshot_id": "ba34b49490d9bfaf"}, "lineage": {"parent_id": "pmid:31114675", "parent_hash": "sha256:7768fecc36ede888076dbd970603ce57f84087e17173db1d5d4923093ad88c35", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE100007 licence not read", "asset:data:geo:GSE100007 not downloaded", "asset:data:geo:GSE24355 licence not read", "asset:data:geo:GSE24355 not downloaded", "asset:data:geo:GSE25842 licence not read", "asset:data:geo:GSE25842 not downloaded", "asset:data:geo:GSE41637 licence not read", "asset:data:geo:GSE41637 not downloaded", "asset:data:geo:SRP000941 licence not read", "asset:data:geo:SRP000941 not downloaded", "asset:data:geo:SRP010679 licence not read", "asset:data:geo:SRP010679 not downloaded", "execution.not_run", "method", "operations", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "amplicon_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["pysradb: A Python package to query next-generation sequencing metadata and data from NCBI Sequence Read Ar", "Read Archive (SRA) is the primary archive of next-generation sequencing datasets. SRA makes metadata and raw sequenc"], "order_basis": "paper_text_order:0", "id": "assay:1"}]}