{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33731794", "kind": "science-record", "revision": 8, "content_hash": "sha256:9cdd50384c999bc7028171b6419d9dc69a8a763a56392f20ab3d7aab089258da", "created_at": "2026-11-01T15:41:29Z", "updated_at": "2026-11-01T22:03:20Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A 14-gene gemcitabine resistance gene signature is significantly associated with the prognosis of pancreatic cancer patients.", "doi": "10.1038/s41598-021-85680-x", "pmid": "33731794", "authors": ["Xing Wei", "Xiaochong Zhou", "Yun Zhao", "Yang He", "Zhen Weng", "Chunfang Xu"], "journal": "Scientific reports", "year": 2021, "abstract": "To identify a gemcitabine resistance-associated gene signature for risk stratification and prognosis prediction in pancreatic cancer. Pearson correlation analysis was performed with gemcitabine half maximal inhibitory concentration (IC50) data of 17 primary pancreatic cancer lines from Genomics of Drug Sensitivity in Cancer (GDSC) and the transcriptomic data from GDSC and Broad Institute Cancer Cell Line Encyclopedia, followed by risk stratification, expression evaluation, overall survival (OS) prediction, clinical data validation and nomogram establishment. Our biomarker discovery effort identified a 14-gene signature, most of which featured differential expression. The 14-gene signature was associated with poor OS in E-MTAB-6134 (HR 2.37; 95% CI 1.75-3.2; p < 0.0001), pancreatic cancer-Canada (PACA-CA) (HR 1.76; 95% CI 1.31-2.37; p = 0.00015), and 4 other independent validation cohorts: pancreatic cancer-Australia (PACA-AU) (HR 1.9; 95% CI 1.38-2.61; p < 0.0001), The Cancer Genome Atlas (TCGA) (HR 1.73; 95% CI 1.11-2.69; p = 0.014), GSE85916 (HR 1.97; 95% CI 1.14-3.42; p = 0.014) and GSE62452 (HR 1.82; 95% CI 1.02-3.24; p = 0.039). Multivariate analysis revealed that the 14-gene risk score was an independent pancreatic cancer outcome predictor in E-MTAB-6134 (p < 0.001) and TCGA (p = 0.006). A nomogram including the 14-gene was established for eventual clinical translation. We identified a novel gemcitabine resistance gene signature for risk stratification and robust categorization of pancreatic cancer patients with poor prognosis.", "claims": [{"id": "claim-method", "statement": "Genes related to gemcitabine resistance were identified with gemcitabine IC50 data of pancreatic cancer cell lines from GDSC and the gene expression data from both the E-MTAB-3610 and CCLE datasets using Pearson correlation with the criterion of p < 0.05 as determined cor.test () function in the R base package.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33731794", "locator": "sections[11] \"Identification of survival-related genes from gemcitabine resistance-related genes and establishment of the prognostic gene signature\" paragraph 2", "quote": "Genes related to gemcitabine resistance were identified with gemcitabine IC50 data of pancreatic cancer cell lines from GDSC and the gene expression data from both the E-MTAB-3610 and CCLE datasets using Pearson correlation with the criterion of p < 0.05 as determined cor.test () function in the R base package."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33731794", "locator": "sections[10] \"Acquisition of gene expression, half maximal inhibitory concentration (IC50) of gemcitabine and clinical data\" paragraph 2", "quote": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/)."}], "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:33731794"], "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:E-MTAB-3610"], "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:E-MTAB-3610"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33731794", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-021-85680-x", "sha256": "sha256:ad3ef3790a2b60ba4609c6e00b4798d466b6d786424494a6dea6cbd25aafb2b1", "bytes": 38505, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-021-85680-x", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7969955", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:E-MTAB-3610", "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=E-MTAB-3610", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-3610", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "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": "2026-10-31T18:28:59Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:E-MTAB-6134", "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=E-MTAB-6134", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "E-MTAB-6134", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "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": "2026-10-31T18:29:02Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE140077", "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=GSE140077", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE140077", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM4153736", "GSM4153737", "GSM4153738", "GSM4153739", "GSM4153740", "GSM4153741", "GSM4153742", "GSM4153743", "GSM4153744", "GSM4153745", "GSM4153746", "GSM4153747"], "sample_count": 12, "group_sizes": null, "group_sizes_basis": null, "platform": "20795", "taxon": "Homo sapiens", "title": "Transcriptome analysis of human pancreatic cancer cell lines and gemcitabine-resistant pancreatic cancer cell lines", "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:GSE19650", "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=GSE19650", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19650", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM490138", "GSM490139", "GSM490140", "GSM490141", "GSM490142", "GSM490143", "GSM490144", "GSM490145", "GSM490146", "GSM490147", "GSM490148", "GSM490149", "GSM490150", "GSM490151", "GSM490152", "GSM490153", "GSM490154", "GSM490155", "GSM490156", "GSM490157", "GSM490158", "GSM490159"], "sample_count": 22, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from epithelial cells during the process of multistep pancreatic carcinogenesis", "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:GSE62165", "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=GSE62165", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62165", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1520738", "GSM1520739", "GSM1520740", "GSM1520741", "GSM1520742", "GSM1520743", "GSM1520744", "GSM1520745", "GSM1520746", "GSM1520747", "GSM1520748", "GSM1520749", "GSM1520750", "GSM1520751", "GSM1520752", "GSM1520753", "GSM1520754", "GSM1520755", "GSM1520756", "GSM1520757", "GSM1520758", "GSM1520759", "GSM1520760", "GSM1520761", "GSM1520762", "GSM1520763", "GSM1520764", "GSM1520765", "GSM1520766", "GSM1520767", "GSM1520768", "GSM1520769", "GSM1520770", "GSM1520771", "GSM1520772", "GSM1520773", "GSM1520774", "GSM1520775", "GSM1520776", "GSM1520777", "GSM1520778", "GSM1520779", "GSM1520780", "GSM1520781", "GSM1520782", "GSM1520783", "GSM1520784", "GSM1520785", "GSM1520786", "GSM1520787", "GSM1520788", "GSM1520789", "GSM1520790", "GSM1520791", "GSM1520792", "GSM1520793", "GSM1520794", "GSM1520795", "GSM1520796", "GSM1520797", "GSM1520798", "GSM1520799", "GSM1520800", "GSM1520801", "GSM1520802", "GSM1520803", "GSM1520804", "GSM1520805", "GSM1520806", "GSM1520807", "GSM1520808", "GSM1520809", "GSM1520810", "GSM1520811", "GSM1520812", "GSM1520813", "GSM1520814", "GSM1520815", "GSM1520816", "GSM1520817", "GSM1520818", "GSM1520819", "GSM1520820", "GSM1520821", "GSM1520822", "GSM1520823", "GSM1520824", "GSM1520825", "GSM1520826", "GSM1520827", "GSM1520828", "GSM1520829", "GSM1520830", "GSM1520831", "GSM1520832", "GSM1520833", "GSM1520834", "GSM1520835", "GSM1520836", "GSM1520837", "GSM1520838", "GSM1520839", "GSM1520840", "GSM1520841", "GSM1520842", "GSM1520843", "GSM1520844", "GSM1520845", "GSM1520846", "GSM1520847", "GSM1520848", "GSM1520849", "GSM1520850", "GSM1520851", "GSM1520852", "GSM1520853", "GSM1520854", "GSM1520855", "GSM1520856", "GSM1520857", "GSM1520858", "GSM1520859", "GSM1520860", "GSM1520861", "GSM1520862", "GSM1520863", "GSM1520864", "GSM1520865", "GSM1520866", "GSM1520867", "GSM1520868"], "sample_count": 131, "group_sizes": null, "group_sizes_basis": null, "platform": "13667", "taxon": "Homo sapiens", "title": "Prognostic relevance of molecular subtypes and master regulators in pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE62452", "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=GSE62452", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62452", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1527105", "GSM1527106", "GSM1527107", "GSM1527108", "GSM1527109", "GSM1527110", "GSM1527111", "GSM1527112", "GSM1527113", "GSM1527114", "GSM1527115", "GSM1527116", "GSM1527117", "GSM1527118", "GSM1527119", "GSM1527120", "GSM1527121", "GSM1527122", "GSM1527123", "GSM1527124", "GSM1527125", "GSM1527126", "GSM1527127", "GSM1527128", "GSM1527129", "GSM1527130", "GSM1527131", "GSM1527132", "GSM1527133", "GSM1527134", "GSM1527135", "GSM1527136", "GSM1527137", "GSM1527138", "GSM1527139", "GSM1527140", "GSM1527141", "GSM1527142", "GSM1527143", "GSM1527144", "GSM1527145", "GSM1527146", "GSM1527147", "GSM1527148", "GSM1527149", "GSM1527150", "GSM1527151", "GSM1527152", "GSM1527153", "GSM1527154", "GSM1527155", "GSM1527156", "GSM1527157", "GSM1527158", "GSM1527159", "GSM1527160", "GSM1527161", "GSM1527162", "GSM1527163", "GSM1527164", "GSM1527165", "GSM1527166", "GSM1527167", "GSM1527168", "GSM1527169", "GSM1527170", "GSM1527171", "GSM1527172", "GSM1527173", "GSM1527174", "GSM1527175", "GSM1527176", "GSM1527177", "GSM1527178", "GSM1527179", "GSM1527180", "GSM1527181", "GSM1527182", "GSM1527183", "GSM1527184", "GSM1527185", "GSM1527186", "GSM1527187", "GSM1527188", "GSM1527189", "GSM1527190", "GSM1527191", "GSM1527192", "GSM1527193", "GSM1527194", "GSM1527195", "GSM1527196", "GSM1527197", "GSM1527198", "GSM1527199", "GSM1527200", "GSM1527201", "GSM1527202", "GSM1527203", "GSM1527204", "GSM1527205", "GSM1527206", "GSM1527207", "GSM1527208", "GSM1527209", "GSM1527210", "GSM1527211", "GSM1527212", "GSM1527213", "GSM1527214", "GSM1527215", "GSM1527216", "GSM1527217", "GSM1527218", "GSM1527219", "GSM1527220", "GSM1527221", "GSM1527222", "GSM1527223", "GSM1527224", "GSM1527225", "GSM1527226", "GSM1527227", "GSM1527228", "GSM1527229", "GSM1527230", "GSM1527231", "GSM1527232", "GSM1527233", "GSM1527234"], "sample_count": 130, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Microarray gene-expression profiles of 69 pancreatic tumors and 61 adjacent non-tumor tissue from patients with pancreatic ductal adenocarcinoma", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE71729", "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=GSE71729", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE71729", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1843893", "GSM1843894", "GSM1843895", "GSM1843896", "GSM1843897", "GSM1843898", "GSM1843899", "GSM1843900", "GSM1843901", "GSM1843902", "GSM1843903", "GSM1843904", "GSM1843905", "GSM1843906", "GSM1843907", "GSM1843908", "GSM1843909", "GSM1843910", "GSM1843911", "GSM1843912", "GSM1843913", "GSM1843914", "GSM1843915", "GSM1843916", "GSM1843917", "GSM1843918", "GSM1843919", "GSM1843920", "GSM1843921", "GSM1843922", "GSM1843923", "GSM1843924", "GSM1843925", "GSM1843926", "GSM1843927", "GSM1843928", "GSM1843929", "GSM1843930", "GSM1843931", "GSM1843932", "GSM1843933", "GSM1843934", "GSM1843935", "GSM1843936", "GSM1843937", "GSM1843938", "GSM1843939", "GSM1843940", "GSM1843941", "GSM1843942", "GSM1843943", "GSM1843944", "GSM1843945", "GSM1843946", "GSM1843947", "GSM1843948", "GSM1843949", "GSM1843950", "GSM1843951", "GSM1843952", "GSM1843953", "GSM1843954", "GSM1843955", "GSM1843956", "GSM1843957", "GSM1843958", "GSM1843959", "GSM1843960", "GSM1843961", "GSM1843962", "GSM1843963", "GSM1843964", "GSM1843965", "GSM1843966", "GSM1843967", "GSM1843968", "GSM1843969", "GSM1843970", "GSM1843971", "GSM1843972", "GSM1843973", "GSM1843974", "GSM1843975", "GSM1843976", "GSM1843977", "GSM1843978", "GSM1843979", "GSM1843980", "GSM1843981", "GSM1843982", "GSM1843983", "GSM1843984", "GSM1843985", "GSM1843986", "GSM1843987", "GSM1843988", "GSM1843989", "GSM1843990", "GSM1843991", "GSM1843992", "GSM1843993", "GSM1843994", "GSM1843995", "GSM1843996", "GSM1843997", "GSM1843998", "GSM1843999", "GSM1844000", "GSM1844001", "GSM1844002", "GSM1844003", "GSM1844004", "GSM1844005", "GSM1844006", "GSM1844007", "GSM1844008", "GSM1844009", "GSM1844010", "GSM1844011", "GSM1844012", "GSM1844013", "GSM1844014", "GSM1844015", "GSM1844016", "GSM1844017", "GSM1844018", "GSM1844019", "GSM1844020", "GSM1844021", "GSM1844022", "GSM1844023", "GSM1844024", "GSM1844025", "GSM1844026", "GSM1844027", "GSM1844028", "GSM1844029", "GSM1844030", "GSM1844031", "GSM1844032", "GSM1844033", "GSM1844034", "GSM1844035", "GSM1844036", "GSM1844037", "GSM1844038", "GSM1844039", "GSM1844040", "GSM1844041", "GSM1844042", "GSM1844043", "GSM1844044", "GSM1844045", "GSM1844046", "GSM1844047", "GSM1844049", "GSM1844050", "GSM1844051", "GSM1844052", "GSM1844053", "GSM1844054", "GSM1844055", "GSM1844056", "GSM1844057", "GSM1844058", "GSM1844059", "GSM1844060", "GSM1844061", "GSM1844062", "GSM1844063", "GSM1844064", "GSM1844065", "GSM1844066", "GSM1844067", "GSM1844068", "GSM1844069", "GSM1844070", "GSM1844071", "GSM1844072", "GSM1844073", "GSM1844074", "GSM1844075", "GSM1844076", "GSM1844077", "GSM1844078", "GSM1844079", "GSM1844080", "GSM1844081", "GSM1844082", "GSM1844083", "GSM1844084", "GSM1844085", "GSM1844086", "GSM1844088", "GSM1844089", "GSM1844090", "GSM1844091", "GSM1844092", "GSM1844093", "GSM1844094", "GSM1844095", "GSM1844096", "GSM1844097", "GSM1844098", "GSM1844099", "GSM1844100", "GSM1844101", "GSM1844102", "GSM1844103", "GSM1844104", "GSM1844105", "GSM1844106", "GSM1844107", "GSM1844108", "GSM1844109", "GSM1844110", "GSM1844111", "GSM1844112", "GSM1844113", "GSM1844114", "GSM1844115", "GSM1844116", "GSM1844117", "GSM1844118", "GSM1844119", "GSM1844120", "GSM1844121", "GSM1844122", "GSM1844123", "GSM1844124", "GSM1844125", "GSM1844126", "GSM1844127", "GSM1844128", "GSM1844129", "GSM1844130", "GSM1844131", "GSM1844132", "GSM1844133", "GSM1844134", "GSM1844135", "GSM1844136", "GSM1844137", "GSM1844138", "GSM1844139", "GSM1844140", "GSM1844141", "GSM1844142", "GSM1844143", "GSM1844144", "GSM1844145", "GSM1844146", "GSM1844147", "GSM1844148", "GSM1844149", "GSM1844150", "GSM1844151", "GSM1844152", "GSM1844153", "GSM1844154", "GSM1844155", "GSM1844156", "GSM1844157", "GSM1844158", "GSM1844159", "GSM1844160", "GSM1844161", "GSM1844162", "GSM1844163", "GSM1844164", "GSM1844165", "GSM1844166", "GSM1844167", "GSM1844168", "GSM1844169", "GSM1844170", "GSM1844171", "GSM1844172", "GSM1844173", "GSM1844174", "GSM1844175", "GSM1844176", "GSM1844177", "GSM1844178", "GSM1844179", "GSM1844180", "GSM1844181", "GSM1844182", "GSM1844183", "GSM1844184", "GSM1844185", "GSM1844186", "GSM1844187", "GSM1844188", "GSM1844189", "GSM1844190", "GSM1844191", "GSM1844192", "GSM1844193", "GSM1844194", "GSM1844195", "GSM1844196", "GSM1844197", "GSM1844198", "GSM1844199", "GSM1844200", "GSM1844201", "GSM1844202", "GSM1844203", "GSM1844204", "GSM1844205", "GSM1844206", "GSM1844207", "GSM1844208", "GSM1844209", "GSM1844210", "GSM1844211", "GSM1844212", "GSM1844213", "GSM1844214", "GSM1844215", "GSM1844216", "GSM1844217", "GSM1844218", "GSM1844219", "GSM1844220", "GSM1844221", "GSM1844222", "GSM1844223", "GSM1844224", "GSM1844225", "GSM1844226", "GSM1844227", "GSM1844228", "GSM1844229", "GSM1844230", "GSM1844231", "GSM1844232", "GSM1844233", "GSM1844234", "GSM1844235", "GSM1844236", "GSM1844237", "GSM1844238", "GSM1844239", "GSM1844240", "GSM1844241", "GSM1844242", "GSM1844243", "GSM1844244", "GSM1844245", "GSM1844246", "GSM1844247", "GSM1844248", "GSM1844249", "GSM1844250", "GSM1844251"], "sample_count": 357, "group_sizes": null, "group_sizes_basis": null, "platform": "20769", "taxon": "Homo sapiens", "title": "Virtual Microdissection of Pancreatic Ductal Adenocarcinoma Reveals Tumor and Stroma Subtypes.", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE85916", "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=GSE85916", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE85916", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2287304", "GSM2287305", "GSM2287306", "GSM2287307", "GSM2287308", "GSM2287309", "GSM2287310", "GSM2287311", "GSM2287312", "GSM2287313", "GSM2287314", "GSM2287315", "GSM2287316", "GSM2287317", "GSM2287318", "GSM2287319", "GSM2287320", "GSM2287321", "GSM2287322", "GSM2287323", "GSM2287324", "GSM2287325", "GSM2287326", "GSM2287327", "GSM2287328", "GSM2287329", "GSM2287330", "GSM2287331", "GSM2287332", "GSM2287333", "GSM2287334", "GSM2287335", "GSM2287336", "GSM2287337", "GSM2287338", "GSM2287339", "GSM2287340", "GSM2287341", "GSM2287342", "GSM2287343", "GSM2287344", "GSM2287345", "GSM2287346", "GSM2287347", "GSM2287348", "GSM2287349", "GSM2287350", "GSM2287351", "GSM2287352", "GSM2287353", "GSM2287354", "GSM2287355", "GSM2287356", "GSM2287357", "GSM2287358", "GSM2287359", "GSM2287360", "GSM2287361", "GSM2287362", "GSM2287363", "GSM2287364", "GSM2287365", "GSM2287366", "GSM2287367", "GSM2287368", "GSM2287369", "GSM2287370", "GSM2287371", "GSM2287372", "GSM2287373", "GSM2287374", "GSM2287375", "GSM2287376", "GSM2287377", "GSM2287378", "GSM2287379", "GSM2287380", "GSM2287381", "GSM2287382", "GSM2287383"], "sample_count": 80, "group_sizes": null, "group_sizes_basis": null, "platform": "13667", "taxon": "Homo sapiens", "title": "Patients with human resected pancreatic cancer", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE91035", "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=GSE91035", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE91035", "version": null, "note": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM2419974", "GSM2419975", "GSM2419976", "GSM2419977", "GSM2419978", "GSM2419979", "GSM2419980", "GSM2419981", "GSM2419982", "GSM2419983", "GSM2419984", "GSM2419985", "GSM2419986", "GSM2419987", "GSM2419988", "GSM2419989", "GSM2419990", "GSM2419991", "GSM2419992", "GSM2419993", "GSM2419994", "GSM2419995", "GSM2419996", "GSM2419997", "GSM2419998", "GSM2419999", "GSM2420000", "GSM2420001", "GSM2420002", "GSM2420003", "GSM2420004", "GSM2420005", "GSM2420006", "GSM2420007", "GSM2420008", "GSM2420009", "GSM2420010", "GSM2420011", "GSM2420012", "GSM2420013", "GSM2420014", "GSM2420015", "GSM2420016", "GSM2420017", "GSM2420018", "GSM2420019", "GSM2420020", "GSM2420021", "GSM2420022", "GSM2420023"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "22763", "taxon": "Homo sapiens", "title": "The gene expression signatures of human normal, benign and PDAC pancreatic tisssues.", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33731794:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4e2a0e5a07e8c004c36de19e96a9945e64bbfc8c7f6f563a81e7df1c8c0ea2e1", "bytes": 1611, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[1]#Tab1", "version": null, "note": "Detailed information of the correlated genes.", "structure": {"pmcid": "PMC7969955", "section_index": 3, "section_title": "Identification of the gemcitabine resistance- and survival-related gene signature, establishment of the prognostic signature and evaluation of the expression of the identified genes", "row_count": 15, "column_count": 3}, "table": {"label": "Table 1", "caption": "Detailed information of the correlated genes.", "rows": [["Gene symbol", "Coefficient number", "Gene function"], ["CCDC148", "− 0.275", "Diseases associated include Tyrosinemia, Type Ii"], ["SH3RF2", "− 0.1514", "Gene Ontology (GO) annotations include ligase activity and protein phosphatase inhibitor activity"], ["CACNA1D", "− 0.1332", "GO annotations include ion channel activity and ankyrin binding"], ["POLD3", "− 0.125", "GO annotations include DNA-directed DNA polymerase activity"], ["PARP1", "− 0.0932", "GO annotations include protein kinase binding"], ["AP1M2", "− 0.0244", "Among its related pathways are Clathrin derived vesicle budding and Nef-mediates down modulation of cell surface receptors by recruiting them to clathrin adapters"], ["C4orf19", "− 0.0105", "NA"], ["ANO1", "0.0238", "GO annotations include protein homodimerization activity and intracellular calcium activated chloride channel activity"], ["VGLL1", "0.0387", "GO annotations include transcription coactivator activity"], ["SCEL", "0.11", "Diseases associated with SCEL include Extrahepatic Bile Duct Adenocarcinoma"], ["INPP4B", "0.1158", "GO annotations include lipid binding and phosphatidylinositol trisphosphate phosphatase activity"], ["NET1", "0.1943", "GO annotations include guanyl-nucleotide exchange factor activity and GTP-Rho binding"], ["INSIG2", "0.2316", "GO annotations include transcription factor binding"], ["BVES", "0.3211", "GO annotations include structural molecule activity and cAMP binding"]], "row_count": 15, "column_count": 3, "numeric_cells": 16, "header_rows": 1, "locator": "section[3]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:33731794:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a3653f126649fc298fe9a332117ab0a92a59189b680a169c338a37c7d0c51f4f", "bytes": 648, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[3]/table-wrap[2]#Tab2", "version": null, "note": "Detailed information of the expression pattern of the correlated genes.", "structure": {"pmcid": "PMC7969955", "section_index": 3, "section_title": "Identification of the gemcitabine resistance- and survival-related gene signature, establishment of the prognostic signature and evaluation of the expression of the identified genes", "row_count": 5, "column_count": 4}, "table": {"label": "Table 2", "caption": "Detailed information of the expression pattern of the correlated genes.", "rows": [["Genes", "Downregulated genes", "Upregulated genes", "Total numbers"], ["14-gene in GSE140077", "ANO1, NET1, PARP1, POLD3, SCEL,", "C4orf19, CACNA1D, CCDC148, INPP4B, SH3RF2", "10"], ["14-gene in GSE62165", "C4orf19", "ANO1, BVES, CACNA1D, INPP4B, NET1, SCEL", "7"], ["14-gene in GSE91035", "C4orf19, PARP1", "ANO1, CACNA1D, INPP4B, NET1, SCEL", "7"], ["14-gene in GSE19650", "VGLL1", "ANO1, C4orf19, CACNA1D, INPP4B, NET1, SCEL, SH3RF2", "10*"]], "row_count": 5, "column_count": 4, "numeric_cells": 12, "header_rows": 1, "locator": "section[3]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:33731794:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:98f2646f3dc03b2efb06050a305098a43557ca25aebfb94c4984806bd9ca90a8", "bytes": 1522, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab3", "version": null, "note": "Basic information of patient from the included datasets.", "structure": {"pmcid": "PMC7969955", "section_index": 10, "section_title": "Acquisition of gene expression, half maximal inhibitory concentration (IC50) of gemcitabine and clinical data", "row_count": 34, "column_count": 7}, "table": {"label": "Table 3", "caption": "Basic information of patient from the included datasets.", "rows": [["", "E-MTAB-6134 (n = 288)", "PACA-CA (n = 214)", "PACA-AU* (n = 266)", "TCGA (n = 148)", "GSE85916 (n = 79)", "GSE62452 (n = 65)"], ["Sex"], ["Male", "166", "128", "142", "79", "NA", "NA"], ["Female", "122", "86", "124", "69", "NA", "NA"], ["Age (mean ± SD, years)", "NA", "65.2 ± 11.0", "66.6 ± 10.6", "65.0 ± 10.8", "NA", "NA"], ["Status"], ["Alive", "107", "34", "106", "67", "22", "16"], ["Dead", "181", "180", "160", "81", "57", "49"], ["Follow-up (mean ± SD, Months)", "29.8 ± 26.9", "22.6 ± 20.8", "18.3 ± 13.7", "17.5 ± 13.9", "28.0 ± 30.5", "20.2 ± 16.7"], ["T-stage"], ["T1", "12", "NA", "NA", "5", "NA", "NA"], ["T2", "39", "NA", "3", "16", "NA", "NA"], ["T3", "237", "NA", "4", "123", "NA", "NA"], ["T4", "0", "NA", "NA", "3", "NA", "NA"], ["N-stage"], ["N0", "72", "NA", "5", "39", "NA", "NA"], ["N1", "216", "NA", "1", "108", "NA", "NA"], ["Nx", "0", "NA", "6", "1", "NA", "NA"], ["M-stage"], ["M0", "NA", "NA", "NA", "67", "NA", "NA"], ["M1", "NA", "NA", "NA", "4", "NA", "NA"], ["Mx", "NA", "NA", "NA", "77", "NA", "NA"], ["AJCC stage"], ["I", "NA", "55", "1", "12", "NA", "4"], ["II", "NA", "89", "2", "127", "NA", "44"], ["III", "NA", "8", "NA", "3", "NA", "10"], ["IV", "NA", "0", "NA", "4", "NA", "6"], ["Uncertain", "NA", "62", "NA", "2", "NA", "1"], ["Grade"], ["G1", "110", "NA", "NA", "20", "NA", "2"], ["G2", "130", "NA", "NA", "84", "NA", "32"], ["G3", "48", "NA", "NA", "43", "NA", "29"], ["G4", "0", "NA", "NA", "1", "NA", "1"], ["Gx", "0", "NA", "NA", "0", "NA", "1"]], "row_count": 34, "column_count": 7, "numeric_cells": 89, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab3"}}], "gaps": ["asset:data:geo:E-MTAB-3610 not downloaded", "asset:data:geo:E-MTAB-3610 licence not read", "asset:data:geo:E-MTAB-6134 not downloaded", "asset:data:geo:E-MTAB-6134 licence not read", "asset:data:geo:GSE140077 not downloaded", "asset:data:geo:GSE140077 licence not read", "asset:data:geo:GSE19650 not downloaded", "asset:data:geo:GSE19650 licence not read", "asset:data:geo:GSE62165 not downloaded", "asset:data:geo:GSE62165 licence not read", "asset:data:geo:GSE62452 not downloaded", "asset:data:geo:GSE62452 licence not read", "asset:data:geo:GSE71729 not downloaded", "asset:data:geo:GSE71729 licence not read", "asset:data:geo:GSE85916 not downloaded", "asset:data:geo:GSE85916 licence not read", "asset:data:geo:GSE91035 not downloaded", "asset:data:geo:GSE91035 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Genes related to gemcitabine resistance were identified with gemcitabine IC50 data of pancreatic cancer cell lines from GDSC and the gene expression data from both the E-MTAB-3610 and CCLE datasets using Pearson correlation with the criterion of p < 0.05 as determined cor.test () function in the R base package."}}, {"id": "method-2", "family": "group_comparison", "specific": "student_t_test", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["student_t"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Student's t-test"}}, {"id": "method-3", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "ANOVA"}}, {"id": "method-4", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "KM"}}, {"id": "method-5", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-6", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log rank"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["E-MTAB-3610", "E-MTAB-6134", "GSE140077", "GSE62165", "GSE91035", "GSE19650", "GSE85916", "GSE62452", "GSE71729"], "resolved_accessions": ["E-MTAB-3610", "E-MTAB-6134", "GSE140077", "GSE62165", "GSE91035", "GSE19650", "GSE85916", "GSE62452", "GSE71729"], "statements": ["Gene expression data and gemcitabine IC50 data of specific pancreatic cancer lines were obtained from GDSC (https://www.cancerrxgene.org/)."], "basis": "The paper names E-MTAB-3610, E-MTAB-6134, GSE140077, GSE62165, GSE91035, GSE19650, GSE85916, GSE62452, GSE71729 in ArrayExpress and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:33731794", "data:geo:E-MTAB-3610", "asset:table:pmid:33731794:1", "asset:table:pmid:33731794:2", "asset:table:pmid:33731794:3"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:E-MTAB-3610"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:28:18Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 30575, "completion_tokens": 3487, "cached_tokens": 10376}}, "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:33731794", "type": "paper", "label": "pmid:33731794"}, {"id": "source:pmid:33731794", "type": "manuscript", "label": "PMID 33731794 full text"}, {"id": "data:geo:E-MTAB-3610", "type": "dataset", "label": "GEO E-MTAB-3610"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33731794", "type": "paper", "label": "pmid:33731794"}, {"id": "source:pmid:33731794", "type": "manuscript", "label": "PMID 33731794 full text"}, {"id": "data:geo:E-MTAB-3610", "type": "dataset", "label": "GEO E-MTAB-3610"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33731794", "type": "extraction", "used": ["source:pmid:33731794"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-E-MTAB-3610", "type": "accession_resolution", "used": ["data:geo:E-MTAB-3610"], "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:33731794", "parent_hash": "sha256:3336e5d2d8c468e13222ac48f71267858cc0bf5f21c7cd7e18026a1a03f96d46", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:E-MTAB-3610 licence not read", "asset:data:geo:E-MTAB-3610 not downloaded", "asset:data:geo:E-MTAB-6134 licence not read", "asset:data:geo:E-MTAB-6134 not downloaded", "asset:data:geo:GSE140077 licence not read", "asset:data:geo:GSE140077 not downloaded", "asset:data:geo:GSE19650 licence not read", "asset:data:geo:GSE19650 not downloaded", "asset:data:geo:GSE62165 licence not read", "asset:data:geo:GSE62165 not downloaded", "asset:data:geo:GSE62452 licence not read", "asset:data:geo:GSE62452 not downloaded", "asset:data:geo:GSE71729 licence not read", "asset:data:geo:GSE71729 not downloaded", "asset:data:geo:GSE85916 licence not read", "asset:data:geo:GSE85916 not downloaded", "asset:data:geo:GSE91035 licence not read", "asset:data:geo:GSE91035 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Genes related to gemcitabine resistance were identified with gemcitabine IC50 data of pancreatic cancer cell lines from GDSC and the gene expression data from both the E-MTAB-3610 and CCLE datasets using Pearson correlation with the criterion of p < 0.05 as determined cor.test () function in the R base package."], "order_basis": "analysis_only", "id": "assay:1"}]},"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":"2026-11-04T00:41:11+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}}}