{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:20459635", "kind": "science-record", "revision": 8, "content_hash": "sha256:3474e28ccfedf028195524c445b24b0633381bd269800a3c39c0dcb5c1e3063d", "created_at": "2026-11-01T15:14:34Z", "updated_at": "2026-11-01T21:19:36Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Predicting environmental chemical factors associated with disease-related gene expression data.", "doi": "10.1186/1755-8794-3-17", "pmid": "20459635", "authors": ["Chirag J Patel", "Atul J Butte"], "journal": "BMC medical genomics", "year": 2010, "abstract": "BACKGROUND: Many common diseases arise from an interaction between environmental and genetic factors. Our knowledge regarding environment and gene interactions is growing, but frameworks to build an association between gene-environment interactions and disease using preexisting, publicly available data has been lacking. Integrating freely-available environment-gene interaction and disease phenotype data would allow hypothesis generation for potential environmental associations to disease.\nMETHODS: We integrated publicly available disease-specific gene expression microarray data and curated chemical-gene interaction data to systematically predict environmental chemicals associated with disease. We derived chemical-gene signatures for 1,338 chemical/environmental chemicals from the Comparative Toxicogenomics Database (CTD). We associated these chemical-gene signatures with differentially expressed genes from datasets found in the Gene Expression Omnibus (GEO) through an enrichment test.\nRESULTS: We were able to verify our analytic method by accurately identifying chemicals applied to samples and cell lines. Furthermore, we were able to predict known and novel environmental associations with prostate, lung, and breast cancers, such as estradiol and bisphenol A.\nCONCLUSIONS: We have developed a scalable and statistical method to identify possible environmental associations with disease using publicly available data and have validated some of the associations in the literature.", "claims": [{"id": "claim-method", "statement": "We checked for enrichment of differentially expressed genes among our 1,338 chemical-gene sets with the hypergeometric test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:20459635", "locator": "sections[3] \"Method to Predict Environmental Associations to Gene Expression Data\" paragraph 10", "quote": "We checked for enrichment of differentially expressed genes among our 1,338 chemical-gene sets with the hypergeometric test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:20459635", "locator": "sections[3] \"Method to Predict Environmental Associations to Gene Expression Data\" paragraph 2", "quote": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The study developed a scalable statistical method that uses CTD-derived chemical–gene signatures and GEO disease gene-expression data, testing enrichment of differentially expressed genes in each chemical signature.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:20459635", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We integrated publicly available disease-specific gene expression microarray data and curated chemical-gene interaction data to systematically predict environmental chemicals associated with disease."}, {"asset": "source:pmid:20459635", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We derived chemical-gene signatures for 1,338 chemical/environmental chemicals from the Comparative Toxicogenomics Database (CTD)."}, {"asset": "source:pmid:20459635", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "We associated these chemical-gene signatures with differentially expressed genes from datasets found in the Gene Expression Omnibus (GEO) through an enrichment test."}, {"asset": "source:pmid:20459635", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "We have developed a scalable and statistical method to identify possible environmental associations with disease using publicly available data and have validated some of the associations in the literature."}, {"asset": "source:pmid:20459635", "locator": "sections[7] \"Results\" paragraph 2", "quote": "The method is centered on chemical-gene sets that are derived from single curated chemical-gene relationships in the CTD."}, {"asset": "source:pmid:20459635", "locator": "sections[7] \"Results\" paragraph 2", "quote": "We determine whether the differentially expressed genes are associated to a chemical by assessing if the expressed genes are enriched for a chemical-gene set, or contain more genes from the chemical-gene set than expected at random using the hypergeometric test."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The study developed a scalable statistical method that uses CTD-derived chemical–gene signatures and GEO disease gene-expression data, testing enrichment of differentially expressed genes in each chemical signature.", "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:20459635"], "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:GSE10072"], "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:GSE10072"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:20459635", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/1755-8794-3-17", "sha256": "sha256:7d41780f9c319c539db30e377abcae676cf990433c32dd44a80902080e9f099d", "bytes": 45161, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/1755-8794-3-17", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC2880288", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10072", "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=GSE10072", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10072", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM254625", "GSM254626", "GSM254627", "GSM254628", "GSM254629", "GSM254630", "GSM254631", "GSM254632", "GSM254633", "GSM254634", "GSM254635", "GSM254636", "GSM254637", "GSM254638", "GSM254639", "GSM254640", "GSM254641", "GSM254642", "GSM254643", "GSM254644", "GSM254645", "GSM254646", "GSM254647", "GSM254648", "GSM254649", "GSM254650", "GSM254651", "GSM254652", "GSM254653", "GSM254654", "GSM254655", "GSM254656", "GSM254657", "GSM254658", "GSM254659", "GSM254660", "GSM254661", "GSM254662", "GSM254663", "GSM254664", "GSM254665", "GSM254666", "GSM254667", "GSM254668", "GSM254669", "GSM254670", "GSM254671", "GSM254672", "GSM254673", "GSM254674", "GSM254675", "GSM254676", "GSM254677", "GSM254678", "GSM254679", "GSM254680", "GSM254681", "GSM254682", "GSM254683", "GSM254684", "GSM254685", "GSM254686", "GSM254687", "GSM254688", "GSM254689", "GSM254690", "GSM254691", "GSM254692", "GSM254693", "GSM254694", "GSM254695", "GSM254696", "GSM254697", "GSM254698", "GSM254699", "GSM254700", "GSM254701", "GSM254702", "GSM254703", "GSM254704", "GSM254705", "GSM254706", "GSM254707", "GSM254708", "GSM254709", "GSM254710", "GSM254711", "GSM254712", "GSM254713", "GSM254714", "GSM254715", "GSM254716", "GSM254717", "GSM254718", "GSM254719", "GSM254720", "GSM254721", "GSM254722", "GSM254723", "GSM254724", "GSM254725", "GSM254726", "GSM254727", "GSM254728", "GSM254729", "GSM254730", "GSM254731"], "sample_count": 107, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene expression signature of cigarette smoking and its role in lung adenocarcinoma development and survival", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE10082", "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=GSE10082", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10082", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM254869", "GSM254870", "GSM254871", "GSM254872", "GSM254873", "GSM254874", "GSM254875", "GSM254876", "GSM254877", "GSM254878", "GSM254879", "GSM254880", "GSM254881", "GSM254882", "GSM254883", "GSM254884", "GSM254885"], "sample_count": 17, "group_sizes": null, "group_sizes_basis": null, "platform": "1261", "taxon": "Mus musculus", "title": "Aryl Hydrocarbon Receptor Regulates Distinct Dioxin-Dependent and Dioxin-Independent Gene Batteries", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE11352", "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=GSE11352", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE11352", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM286756", "GSM286757", "GSM286758", "GSM286759", "GSM286760", "GSM286761", "GSM286762", "GSM286763", "GSM286764", "GSM286765", "GSM286766", "GSM286767", "GSM286768", "GSM286769", "GSM286770", "GSM286771", "GSM286772", "GSM286773"], "sample_count": 18, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Timecourse of estradiol (10nM) exposure in MCF7 breast cancer cells.", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE17624", "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=GSE17624", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17624", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM439987", "GSM439988", "GSM439989", "GSM439990", "GSM439991", "GSM439992", "GSM439993", "GSM439994", "GSM439995", "GSM439996", "GSM439997", "GSM439998", "GSM439999", "GSM440000", "GSM440001", "GSM440002", "GSM440003", "GSM440004", "GSM440005", "GSM440006", "GSM440007", "GSM440008", "GSM440009", "GSM440010", "GSM440011", "GSM440012", "GSM440013", "GSM440014", "GSM440015", "GSM440016", "GSM440017", "GSM440018", "GSM440019", "GSM440020", "GSM440021", "GSM440022", "GSM440023", "GSM440024", "GSM440025", "GSM440026", "GSM440027", "GSM440028", "GSM440029", "GSM440030", "GSM440031", "GSM440032", "GSM440033", "GSM440034", "GSM440035", "GSM440036", "GSM440037", "GSM440038", "GSM440039", "GSM440040", "GSM440041", "GSM440042", "GSM440043", "GSM440044", "GSM440045", "GSM440046"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from human Ishikawa cells treated with Bisphenol A", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE2111", "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=GSE2111", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE2111", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM38117", "GSM38118", "GSM38119", "GSM38120", "GSM38121", "GSM38122", "GSM38123", "GSM38124", "GSM38125", "GSM38126", "GSM38127", "GSM38128"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Metal and Gene Expression", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE2889", "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=GSE2889", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE2889", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM63205", "GSM63206", "GSM63207", "GSM63208", "GSM63210", "GSM63211", "GSM63212", "GSM63213", "GSM63214", "GSM63215", "GSM63216", "GSM63217", "GSM63218", "GSM63220"], "sample_count": 14, "group_sizes": null, "group_sizes_basis": null, "platform": "339", "taxon": "Mus musculus", "title": "Gene Expression Profiling of 17 beta-Estradiol and Genistein Effects on Mouse Thymus", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE5145", "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=GSE5145", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE5145", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM116101", "GSM116102", "GSM116103", "GSM116104", "GSM116105", "GSM116106"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Genes regulated by vitamin D in bronchial smooth muscle cells", "resolution_checked_at": "2026-11-01T15:14:33Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6883", "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=GSE6883", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6883", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM158635", "GSM158636", "GSM158637", "GSM158638", "GSM158639", "GSM158640", "GSM158641", "GSM158642", "GSM158643", "GSM158644", "GSM158645", "GSM158646", "GSM158647", "GSM158648", "GSM158649", "GSM158650", "GSM158651", "GSM158652", "GSM158653", "GSM158654", "GSM158655", "GSM158656", "GSM158657", "GSM158658"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "96;97", "taxon": "Homo sapiens", "title": "The prognostic role of a gene signature from tumorigenic breast-cancer cells.", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE6919", "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=GSE6919", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6919", "version": null, "note": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM152804", "GSM152805", "GSM152806", "GSM152807", "GSM152808", "GSM152809", "GSM152810", "GSM152811", "GSM152812", "GSM152813", "GSM152814", "GSM152815", "GSM152816", "GSM152817", "GSM152818", "GSM152819", "GSM152820", "GSM152821", "GSM152822", "GSM152823", "GSM152824", "GSM152825", "GSM152826", "GSM152827", "GSM152828", "GSM152829", "GSM152830", "GSM152831", "GSM152832", "GSM152833", "GSM152834", "GSM152835", "GSM152836", "GSM152837", "GSM152838", "GSM152839", "GSM152840", "GSM152841", "GSM152842", "GSM152843", "GSM152844", "GSM152845", "GSM152846", "GSM152847", "GSM152848", "GSM152849", "GSM152850", "GSM152851", "GSM152852", "GSM152853", "GSM152854", "GSM152855", "GSM152856", "GSM152857", "GSM152858", "GSM152859", "GSM152860", "GSM152861", "GSM152862", "GSM152863", "GSM152864", "GSM152865", "GSM152866", "GSM152867", "GSM152868", "GSM152869", "GSM152870", "GSM152871", "GSM152872", "GSM152873", "GSM152874", "GSM152875", "GSM152876", "GSM152877", "GSM152878", "GSM152879", "GSM152880", "GSM152881", "GSM152882", "GSM152883", "GSM152884", "GSM152885", "GSM152886", "GSM152887", "GSM152888", "GSM152889", "GSM152890", "GSM152891", "GSM152892", "GSM152893", "GSM152894", "GSM152895", "GSM152896", "GSM152897", "GSM152898", "GSM152899", "GSM152900", "GSM152901", "GSM152902", "GSM152903", "GSM152904", "GSM152905", "GSM152906", "GSM152907", "GSM152908", "GSM152909", "GSM152910", "GSM152911", "GSM152912", "GSM152913", "GSM152914", "GSM152915", "GSM152916", "GSM152917", "GSM152918", "GSM152919", "GSM152920", "GSM152921", "GSM152922", "GSM152923", "GSM152924", "GSM152925", "GSM152926", "GSM152927", "GSM152928", "GSM152929", "GSM152930", "GSM152931", "GSM152932", "GSM152933", "GSM152934", "GSM152935", "GSM152936", "GSM152937", "GSM152938", "GSM152939", "GSM152940", "GSM152941", "GSM152942", "GSM152943", "GSM152944", "GSM152945", "GSM152946", "GSM152947", "GSM152948", "GSM152949", "GSM152950", "GSM152951", "GSM152952", "GSM152953", "GSM152954", "GSM152955", "GSM152956", "GSM152957", "GSM152958", "GSM152959", "GSM152960", "GSM152961", "GSM152962", "GSM152963", "GSM152964", "GSM152965", "GSM152966", "GSM152967", "GSM152968", "GSM152969", "GSM152970", "GSM152971", "GSM152972", "GSM152973", "GSM152974", "GSM152975", "GSM152976", "GSM152977", "GSM152978", "GSM152979", "GSM152980", "GSM152981", "GSM152982", "GSM152983", "GSM152984", "GSM152985", "GSM152986", "GSM152987", "GSM152988", "GSM152989", "GSM152990", "GSM152991", "GSM152992", "GSM152993", "GSM152994", "GSM152995", "GSM152996", "GSM152997", "GSM152998", "GSM152999", "GSM153000", "GSM153001", "GSM153002", "GSM153003", "GSM153004", "GSM153005", "GSM153006", "GSM153007", "GSM153008", "GSM153009", "GSM153010", "GSM153011", "GSM153012", "GSM153013", "GSM153014", "GSM153015", "GSM153016", "GSM153017", "GSM153018", "GSM153019", "GSM153020", "GSM153021", "GSM153022", "GSM153023", "GSM153024", "GSM153025", "GSM153026", "GSM153027", "GSM153028", "GSM153029", "GSM153030", "GSM153031", "GSM153032", "GSM153033", "GSM153034", "GSM153035", "GSM153036", "GSM153037", "GSM153038", "GSM153039", "GSM153040", "GSM153041", "GSM153042", "GSM153043", "GSM153044", "GSM153045", "GSM153046", "GSM153047", "GSM153048", "GSM153049", "GSM153050", "GSM153051", "GSM153052", "GSM153053", "GSM153054", "GSM153055", "GSM153056", "GSM153057", "GSM153058", "GSM153059", "GSM153060", "GSM153061", "GSM153062", "GSM153063", "GSM153064", "GSM153065", "GSM153066", "GSM153067", "GSM153068", "GSM153069", "GSM153070", "GSM153071", "GSM153072", "GSM153073", "GSM153074", "GSM153075", "GSM153076", "GSM153077", "GSM153078", "GSM153079", "GSM153080", "GSM153081", "GSM153082", "GSM153083", "GSM153084", "GSM153085", "GSM153086", "GSM153087", "GSM153088", "GSM153089", "GSM153090", "GSM153091", "GSM153092", "GSM153093", "GSM153094", "GSM153095", "GSM153096", "GSM153097", "GSM153098", "GSM153099", "GSM153100", "GSM153101", "GSM153102", "GSM153103", "GSM153104", "GSM153105", "GSM153106", "GSM153107", "GSM153108", "GSM153109", "GSM153110", "GSM153111", "GSM153112", "GSM153113", "GSM153114", "GSM153115", "GSM153116", "GSM153117", "GSM153118", "GSM153119", "GSM153120", "GSM153121", "GSM153122", "GSM153123", "GSM153124", "GSM153125", "GSM153126", "GSM153127", "GSM153128", "GSM153129", "GSM153130", "GSM153131", "GSM153132", "GSM153133", "GSM153134", "GSM153135", "GSM153136", "GSM153137", "GSM153138", "GSM153139", "GSM153140", "GSM153141", "GSM153142", "GSM153143", "GSM153144", "GSM153145", "GSM153146", "GSM153147", "GSM153148", "GSM153149", "GSM153150", "GSM153151", "GSM153152", "GSM153153", "GSM153154", "GSM153155", "GSM153156", "GSM153157", "GSM153158", "GSM153159", "GSM153160", "GSM153161", "GSM153162", "GSM153163", "GSM153164", "GSM153165", "GSM153166", "GSM153167", "GSM153168", "GSM153169", "GSM153170", "GSM153171", "GSM153172", "GSM153173", "GSM153174", "GSM153175", "GSM153176", "GSM153177", "GSM153178", "GSM153179", "GSM153180", "GSM153181", "GSM153182", "GSM153183", "GSM153184", "GSM153185", "GSM153186", "GSM153187", "GSM153188", "GSM153189", "GSM153190", "GSM153191", "GSM153192", "GSM153193", "GSM153194", "GSM153195", "GSM153196", "GSM153197", "GSM153198", "GSM153199", "GSM153200", "GSM153201", "GSM153202", "GSM153203", "GSM153204", "GSM153205", "GSM153206", "GSM153207", "GSM153208", "GSM153209", "GSM153210", "GSM153211", "GSM153212", "GSM153213", "GSM153214", "GSM153215", "GSM153216", "GSM153217", "GSM153218", "GSM153219", "GSM153220", "GSM153221", "GSM153222", "GSM153223", "GSM153224", "GSM153225", "GSM153226", "GSM153227", "GSM153228", "GSM153229", "GSM153230", "GSM153231", "GSM153232", "GSM153233", "GSM153234", "GSM153235", "GSM153236", "GSM153237", "GSM153238", "GSM153239", "GSM153240", "GSM153241", "GSM153242", "GSM153243", "GSM153244", "GSM153245", "GSM153246", "GSM153247", "GSM153248", "GSM153249", "GSM153250", "GSM153251", "GSM153252", "GSM153253", "GSM153254", "GSM153255", "GSM153256", "GSM153257", "GSM153258", "GSM153259", "GSM153260", "GSM153261", "GSM153262", "GSM153263", "GSM153264", "GSM153265", "GSM153266", "GSM153267", "GSM153268", "GSM153269", "GSM153270", "GSM153271", "GSM153272", "GSM153273", "GSM153274", "GSM153275", "GSM153276", "GSM153277", "GSM153278", "GSM153279", "GSM153280", "GSM153281", "GSM153282", "GSM153283", "GSM153284", "GSM153285", "GSM153286", "GSM153287", "GSM153288", "GSM153289", "GSM153290", "GSM153291", "GSM153292", "GSM153293", "GSM153294", "GSM153295", "GSM187524", "GSM187525", "GSM187526", "GSM187527", "GSM187528", "GSM187529", "GSM187530", "GSM187531", "GSM187532", "GSM187533", "GSM187534", "GSM187535"], "sample_count": 504, "group_sizes": null, "group_sizes_basis": null, "platform": "93;8300;92", "taxon": "Homo sapiens", "title": "Expression Data from Normal and Prostate Tumor Tissues", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:20459635:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0cef92c1984f87a9139213d0e37217ec44b5bb211b7350e0c428bd48af984a96", "bytes": 1117, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[8]/table-wrap[1]#T1", "version": null, "note": "Chemical Prediction Results from the Verification Phase.", "structure": {"pmcid": "PMC2880288", "section_index": 8, "section_title": "Verification Phase", "row_count": 12, "column_count": 6}, "table": {"label": "Table 1", "caption": "Chemical Prediction Results from the Verification Phase.", "rows": [["Actual Chemical Exposure (GEO accession)", "Chemicals Predicted", "Hypergeometric P-value", "Rank (Percentile)", "q-value", "Relevant Genes Expressed"], ["Vitamin D3 on H. sapiens muscle cells (GSE5145)", "Calcitriol", "1 × 10-23", "1 (100)", "0", "VDR (25), CYP24A1 (14)"], [""], ["TCDD on M. musculus (GSE10082)", "TCDD", "2 × 10-15", "3 (99)", "0", "CYP1A1 (59), CYP1B1 (15), AHRR(6), CYP1A2 (14)"], [""], ["Bisphenol A on H. sapiens Ishikawa cells (GSE17624)", "Bisphenol A", "1 × 10-6", "15 (99)", "0", "ESR1(31), ESR2(7), S100G (6)"], [""], ["Zinc sulfate on H. sapiens bronchial tissue (GSE2111)", "Zinc sulfate", "3 × 10-3", "15 (99)", "0.04", "SLC30A1 (3), MT1F(2), MT1G(2)"], [""], ["Estradiol on M. musculus thymus (GSE2889)", "Estradiol", "5 × 10-3", "17 (99)", "0.08", "C3(6), LPL (4), CTSB (2)"], [""], ["Estradiol on H. sapiens MCF7 cell line (GSE11352)", "Estradiol", "5 × 10-3", "19 (99)", "0.08", "ISG20 (2), MGP (2), SERPINA1 (2)"]], "row_count": 12, "column_count": 6, "numeric_cells": 30, "header_rows": 1, "locator": "section[8]/table-wrap[1]#T1"}}, {"id": "asset:table:pmid:20459635:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:eb2fcd632393149a514deec8e5d61ccbbcb59a26f23b18149412b6e5695a7b59", "bytes": 1248, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[1]#T2", "version": null, "note": "Prediction of environmental chemicals associated with prostate cancer samples (GSE6919).", "structure": {"pmcid": "PMC2880288", "section_index": 9, "section_title": "Predicting Environmental Chemicals Associated with Cancer Data Sets", "row_count": 20, "column_count": 6}, "table": {"label": "Table 2", "caption": "Prediction of environmental chemicals associated with prostate cancer samples (GSE6919).", "rows": [["Chemical Predicted", "Hypergeometric P-value", "Rank (percentile)", "q-value", "Relevant genes in set (number of references)", "Citations"], ["Estradiol", "4 × 10-10", "5 (99)", "0", "ESR2(37), PGR(34), MAPK1(14)", "[37]"], [""], ["Raloxifene", "1 × 10-9", "6 (99)", "0", "ESR2(6), IGF1(5), BCL2(4)", "[38]"], [""], ["Sodium arsenite", "1 × 10-8", "8 (99)", "0", "JUN(13), MAPK1(9), CCND1(8), FOS(6)", "[30]"], [""], ["Doxorubicin", "7 × 10-7", "11 (99)", "0", "BCL2(23), MAPK1(14), TNF(10)", "[39-42]"], [""], ["Cadmium", "6 × 10-6", "13 (99)", "0", "MT2A(14), MT1A(12), MT3(11), MT1(6)", "[43]"], [""], ["Genistein", "3 × 10-5", "19 (99)", "6 × 10-4", "ESR2(22), PGR (10), MAPK1 (5)", "[44-46]"], [""], ["Diethylstilbestrol", "3 × 10-5", "22 (98)", "0.001", "ESR2(8), FOS(8), HOXA10(4)", "[47,48]"], [""], ["Fenretinide", "3 × 10-4", "40 (97)", "0.004", "BCL2(3), ELF3(2), LDHA(2)", "[49]"], [""], ["Bisphenol A", "6 × 10-4", "47 (96)", "0.01", "PGR(8), ESR2(7), IL4RA(2)", "[37]"], [""], ["Zinc", "9 × 10-4", "53 (96)", "0.01", "MT3(18), MT2A(13), MT1A(11)", "[50-53]"]], "row_count": 20, "column_count": 6, "numeric_cells": 50, "header_rows": 1, "locator": "section[9]/table-wrap[1]#T2"}}, {"id": "asset:table:pmid:20459635:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7f1c0719a4d0a54da4d0c09b279b415662342580dbed261499312419bba89123", "bytes": 1078, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[2]#T3", "version": null, "note": "Prediction of environmental chemicals associated with lung cancer samples (GSE10072).", "structure": {"pmcid": "PMC2880288", "section_index": 9, "section_title": "Predicting Environmental Chemicals Associated with Cancer Data Sets", "row_count": 14, "column_count": 6}, "table": {"label": "Table 3", "caption": "Prediction of environmental chemicals associated with lung cancer samples (GSE10072).", "rows": [["Chemical Predicted", "Hypergeometric P-value", "Rank (percentile)", "q-value", "Relevant genes in set (number of references)", "Citations"], ["Doxorubicin", "1 × 10-6", "16 (99)", "4 × 10-4", "CASP3(60), ABCB1(28), BAX(26), BCL2 (23)", "[54]"], [""], ["Sodium arsenite", "8 × 10-6", "20 (98)", "4 × 10-4", "JUN(13), NQ01(6), EGR1(6)", "[55-57]"], [""], ["Vanadium pentoxide", "1 × 10-5", "24 (98)", "6 × 10-4", "HBEGF(3), CDK7(1), CDKN1B (1), CDKN1C(1)", "[58]"], [""], ["Dimethylnitrosamine", "6 × 10-5", "27 (98)", "7 × 10-4", "TGFB1(23), TIMP1(15), PCNA(6)", "[31]"], [""], ["Indomethacin", "2 × 10-4", "34 (97)", "0.002", "BIRC5(3), CDKN1B(2), MMP9(2)", "[59-61]"], [""], ["2-Acetylaminofluorene", "3 × 10-4", "36 (97)", "0.003", "ABCB1(4), ABCG2(4), KRT19(2)", "[62]"], [""], ["Asbestos, Serpentine", "4 × 10-4", "39 (97)", "0.004", "IL6(2), MMP9(2), MMP12(2), PDGFB(2)", "[63]"]], "row_count": 14, "column_count": 6, "numeric_cells": 36, "header_rows": 1, "locator": "section[9]/table-wrap[2]#T3"}}, {"id": "asset:table:pmid:20459635:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:829f06ee6e42929d00e384bd59ac54ddc7dfb929494328ab428afba0a8f768e2", "bytes": 1002, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[9]/table-wrap[3]#T4", "version": null, "note": "Prediction of environmental chemicals associated with breast cancer samples (GSE6883).", "structure": {"pmcid": "PMC2880288", "section_index": 9, "section_title": "Predicting Environmental Chemicals Associated with Cancer Data Sets", "row_count": 14, "column_count": 6}, "table": {"label": "Table 4", "caption": "Prediction of environmental chemicals associated with breast cancer samples (GSE6883).", "rows": [["Chemical Predicted", "Hypergeometric P-value", "Rank (percentile)", "q-value", "Relevant genes in set (number of references)", "Citations"], ["Progesterone", "2 × 10-4", "6 (99)", "0.01", "IL6(3), STC1(3), CEBPD(2)", "[64,65]"], [""], ["Genistein", "6 × 10-4", "10 (99)", "0.03", "CEBPD(1), APLP2(1), MLF1(1)", "[66-68]"], [""], ["Estradiol", "7 × 10-4", "11 (99)", "0.03", "LPL(4), IL6(3), CEBPD(2)", "[69-73]"], [""], ["Indomethacin", "3 × 10-3", "17 (99)", "0.05", "CCDC50(1), BIRC3(1), DNAJB(1)", "[74]"], [""], ["Diethylstilbestrol", "3 × 10-3", "18 (99)", "0.05", "IL6(1), MARCKS(1), MXD1(1), MMP7(1)", "[75,76]"], [""], ["Cyclophosphamide", "4 × 10-4", "19 (99)", "0.06", "IL6(3), MARCKS(1), PSMA5(1)", "[77-79]"], [""], ["Bisphenol A", "6 × 10-3", "21 (99)", "0.08", "CEBPD(1), MLF1(1), DTL(1)", "[80]"]], "row_count": 14, "column_count": 6, "numeric_cells": 35, "header_rows": 1, "locator": "section[9]/table-wrap[3]#T4"}}], "gaps": ["asset:data:geo:GSE10072 not downloaded", "asset:data:geo:GSE10072 licence not read", "asset:data:geo:GSE10082 not downloaded", "asset:data:geo:GSE10082 licence not read", "asset:data:geo:GSE11352 not downloaded", "asset:data:geo:GSE11352 licence not read", "asset:data:geo:GSE17624 not downloaded", "asset:data:geo:GSE17624 licence not read", "asset:data:geo:GSE2111 not downloaded", "asset:data:geo:GSE2111 licence not read", "asset:data:geo:GSE2889 not downloaded", "asset:data:geo:GSE2889 licence not read", "asset:data:geo:GSE5145 not downloaded", "asset:data:geo:GSE5145 licence not read", "asset:data:geo:GSE6883 not downloaded", "asset:data:geo:GSE6883 licence not read", "asset:data:geo:GSE6919 not downloaded", "asset:data:geo:GSE6919 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "hypergeometric test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We checked for enrichment of differentially expressed genes among our 1,338 chemical-gene sets with the hypergeometric test."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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 (hypergeometric test), 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": ["GSE5145", "GSE10082", "GSE17624", "GSE2111", "GSE2889", "GSE11352", "GSE6919", "GSE10072", "GSE6883"], "resolved_accessions": ["GSE5145", "GSE10082", "GSE17624", "GSE2111", "GSE2889", "GSE11352", "GSE6919", "GSE10072", "GSE6883"], "statements": ["The Comparative Toxicogenomics Database (CTD) includes manually-curated, cross-species relations between chemicals and genes, proteins, and mRNA transcripts [13]. We downloaded the knowledge-base spanning 4,078 chemicals and 15 461 genes and 85 937 relationships between them in January 2009."], "basis": "The paper names GSE5145, GSE10082, GSE17624, GSE2111, GSE2889, GSE11352, GSE6919, GSE10072, GSE6883 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:20459635", "data:geo:GSE10072", "asset:table:pmid:20459635:1", "asset:table:pmid:20459635:2", "asset:table:pmid:20459635:3", "asset:table:pmid:20459635:4"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10072"]}, "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": "2026-10-31T18:20:50Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 76362, "completion_tokens": 8117, "cached_tokens": 57460}}, "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:20459635", "type": "paper", "label": "pmid:20459635"}, {"id": "source:pmid:20459635", "type": "manuscript", "label": "PMID 20459635 full text"}, {"id": "data:geo:GSE10072", "type": "dataset", "label": "GEO GSE10072"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:20459635", "type": "paper", "label": "pmid:20459635"}, {"id": "source:pmid:20459635", "type": "manuscript", "label": "PMID 20459635 full text"}, {"id": "data:geo:GSE10072", "type": "dataset", "label": "GEO GSE10072"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-20459635", "type": "extraction", "used": ["source:pmid:20459635"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10072", "type": "accession_resolution", "used": ["data:geo:GSE10072"], "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:20459635", "parent_hash": "sha256:3e777b714b9630fed757408abf156081ebfb7a0829a34dd3c874f59debb30a7a", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE10072 licence not read", "asset:data:geo:GSE10072 not downloaded", "asset:data:geo:GSE10082 licence not read", "asset:data:geo:GSE10082 not downloaded", "asset:data:geo:GSE11352 licence not read", "asset:data:geo:GSE11352 not downloaded", "asset:data:geo:GSE17624 licence not read", "asset:data:geo:GSE17624 not downloaded", "asset:data:geo:GSE2111 licence not read", "asset:data:geo:GSE2111 not downloaded", "asset:data:geo:GSE2889 licence not read", "asset:data:geo:GSE2889 not downloaded", "asset:data:geo:GSE5145 licence not read", "asset:data:geo:GSE5145 not downloaded", "asset:data:geo:GSE6883 licence not read", "asset:data:geo:GSE6883 not downloaded", "asset:data:geo:GSE6919 licence not read", "asset:data:geo:GSE6919 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["y available disease-specific gene expression microarray data and curated chemical-gene interaction d", "select differentially expressed genes from a microarray experiment [14]. The FDR for SAM for all of", "rder to reduce false associations. We mapped microarray annotations to other corresponding represent", "ing 100 random resamplings of genes from the microarray experiment and testing each of these random"], "order_basis": "paper_text_order:620", "id": "assay:1"}, {"role": "data_generation", "definition_id": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["ally, set 6 was GSE11352 in which H. sapiens MCF-7 cell line was exposed to estradiol at 3 diff"], "order_basis": "paper_text_order:8793", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:15:59+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}