{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33091876", "kind": "science-record", "revision": 8, "content_hash": "sha256:877399f9b960c707f096c71b298ae72a819d5e126ce635b4b43bec977e946bf1", "created_at": "2026-11-01T15:41:13Z", "updated_at": "2026-11-01T22:02:22Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "TRIM28 is a distinct prognostic biomarker that worsens the tumor immune microenvironment in lung adenocarcinoma.", "doi": "10.18632/aging.103804", "pmid": "33091876", "authors": ["Jie Liu", "Xiao Han", "Lijuan Chen", "Dong Han", "Xiaoqian Mu", "Xiufeng Hu", "Hongbo Wu", "Huijuan Wu", "Wenjing Liu", "Yanqiu Zhao"], "journal": "Aging", "year": 2020, "abstract": "The tumor immune microenvironment (TIME) is an important determinant of cancer prognosis and treatment efficacy. To identify immune-related prognostic biomarkers of lung adenocarcinoma, we used the ESTIMATE algorithm to calculate the immune and stromal scores of 517 lung adenocarcinoma patients from The Cancer Genome Atlas (TCGA). We detected 985 differentially expressed genes (DEGs) between patients with high and low immune and stromal scores, and we analyzed their functions and protein-protein interactions. TRIM28 was upregulated in lung adenocarcinoma patients with low immune and stromal scores, and was associated with a poor prognosis. The TISIDB and TIMER databases indicated that TRIM28 expression correlated negatively with immune infiltration. We then explored genes that were co-expressed with TRIM28 in TCGA, and investigated DEGs based on TRIM28 expression in GSE43580 and GSE7670. The 429 common DEGs from these analyses were functionally analyzed. We also performed a Gene Set Enrichment Analysis using TCGA data, and predicted substrates of TRIM28 using UbiBrowser. The results indicated that TRIM28 may negatively regulate the TIME by increasing the SUMOylation of IRF5 and IRF8. Correlation analyses and validations in two lung adenocarcinoma cell lines (PC9 and H1299) confirmed these findings. Thus, TRIM28 may worsen the TIME and prognosis of lung adenocarcinoma.", "claims": [{"id": "claim-method", "statement": "Patients’ immune and stromal scores were determined using the ESTIMATE algorithm based on gene expression data [11].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33091876", "locator": "sections[3] \"The correlations among the immune and stromal scores, clinical features and prognoses of LUAD patients\" paragraph 2", "quote": "Patients’ immune and stromal scores were determined using the ESTIMATE algorithm based on gene expression data [11]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33091876", "locator": "sections[12] \"Gene expression profile data\" paragraph 2", "quote": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.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:33091876"], "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:GSE11121"], "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": {"hazard_ratio": "ults are displayed with HRs and p-values or Cox p-"}, "inputs": ["data:geo:GSE11121"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33091876", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.103804", "sha256": "sha256:36aca37a512645e2f57627e5048a0e0db06553f02eabe4b8a42dd3e46387e10e", "bytes": 44085, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.103804", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7655206", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE11121", "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=GSE11121", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE11121", "version": null, "note": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM282373", "GSM282374", "GSM282375", "GSM282376", "GSM282377", "GSM282378", "GSM282379", "GSM282380", "GSM282381", "GSM282382", "GSM282383", "GSM282384", "GSM282385", "GSM282386", "GSM282387", "GSM282388", "GSM282389", "GSM282390", "GSM282391", "GSM282392", "GSM282393", "GSM282394", "GSM282395", "GSM282396", "GSM282397", "GSM282398", "GSM282399", "GSM282400", "GSM282401", "GSM282402", "GSM282403", "GSM282404", "GSM282405", "GSM282406", "GSM282407", "GSM282408", "GSM282409", "GSM282410", "GSM282411", "GSM282412", "GSM282413", "GSM282414", "GSM282415", "GSM282416", "GSM282417", "GSM282418", "GSM282419", "GSM282420", "GSM282421", "GSM282422", "GSM282423", "GSM282424", "GSM282425", "GSM282426", "GSM282427", "GSM282428", "GSM282429", "GSM282430", "GSM282431", "GSM282432", "GSM282433", "GSM282434", "GSM282435", "GSM282436", "GSM282437", "GSM282438", "GSM282439", "GSM282440", "GSM282441", "GSM282442", "GSM282443", "GSM282444", "GSM282445", "GSM282446", "GSM282447", "GSM282448", "GSM282449", "GSM282450", "GSM282451", "GSM282452", "GSM282453", "GSM282454", "GSM282455", "GSM282456", "GSM282457", "GSM282458", "GSM282459", "GSM282460", "GSM282461", "GSM282462", "GSM282463", "GSM282464", "GSM282465", "GSM282466", "GSM282467", "GSM282468", "GSM282469", "GSM282470", "GSM282471", "GSM282472", "GSM282473", "GSM282474", "GSM282475", "GSM282476", "GSM282477", "GSM282478", "GSM282479", "GSM282480", "GSM282481", "GSM282482", "GSM282483", "GSM282484", "GSM282485", "GSM282486", "GSM282487", "GSM282488", "GSM282489", "GSM282490", "GSM282491", "GSM282492", "GSM282493", "GSM282494", "GSM282495", "GSM282496", "GSM282497", "GSM282498", "GSM282499", "GSM282500", "GSM282501", "GSM282502", "GSM282503", "GSM282504", "GSM282505", "GSM282506", "GSM282507", "GSM282508", "GSM282509", "GSM282510", "GSM282511", "GSM282512", "GSM282513", "GSM282514", "GSM282515", "GSM282516", "GSM282517", "GSM282518", "GSM282519", "GSM282520", "GSM282521", "GSM282522", "GSM282523", "GSM282524", "GSM282525", "GSM282526", "GSM282527", "GSM282528", "GSM282529", "GSM282530", "GSM282531", "GSM282532", "GSM282533", "GSM282534", "GSM282535", "GSM282536", "GSM282537", "GSM282538", "GSM282539", "GSM282540", "GSM282541", "GSM282542", "GSM282543", "GSM282544", "GSM282545", "GSM282546", "GSM282547", "GSM282548", "GSM282549", "GSM282550", "GSM282551", "GSM282552", "GSM282553", "GSM282554", "GSM282555", "GSM282556", "GSM282557", "GSM282558", "GSM282559", "GSM282560", "GSM282561", "GSM282562", "GSM282563", "GSM282564", "GSM282565", "GSM282566", "GSM282567", "GSM282568", "GSM282569", "GSM282570", "GSM282571", "GSM282572"], "sample_count": 200, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "The humoral immune system has a key prognostic impact in node-negative breast cancer", "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:GSE19188", "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=GSE19188", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19188", "version": null, "note": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM475656", "GSM475657", "GSM475658", "GSM475659", "GSM475660", "GSM475661", "GSM475662", "GSM475663", "GSM475664", "GSM475665", "GSM475666", "GSM475667", "GSM475668", "GSM475669", "GSM475670", "GSM475671", "GSM475672", "GSM475673", "GSM475674", "GSM475675", "GSM475676", "GSM475677", "GSM475678", "GSM475679", "GSM475680", "GSM475681", "GSM475682", "GSM475683", "GSM475684", "GSM475685", "GSM475686", "GSM475687", "GSM475688", "GSM475689", "GSM475690", "GSM475691", "GSM475692", "GSM475693", "GSM475694", "GSM475695", "GSM475696", "GSM475697", "GSM475698", "GSM475699", "GSM475700", "GSM475701", "GSM475702", "GSM475703", "GSM475704", "GSM475705", "GSM475706", "GSM475707", "GSM475708", "GSM475709", "GSM475710", "GSM475711", "GSM475712", "GSM475713", "GSM475714", "GSM475715", "GSM475716", "GSM475717", "GSM475718", "GSM475719", "GSM475720", "GSM475721", "GSM475722", "GSM475723", "GSM475724", "GSM475725", "GSM475726", "GSM475727", "GSM475728", "GSM475729", "GSM475730", "GSM475731", "GSM475732", "GSM475733", "GSM475734", "GSM475735", "GSM475736", "GSM475737", "GSM475738", "GSM475739", "GSM475740", "GSM475741", "GSM475742", "GSM475743", "GSM475744", "GSM475745", "GSM475746", "GSM475747", "GSM475748", "GSM475749", "GSM475750", "GSM475751", "GSM475752", "GSM475753", "GSM475754", "GSM475755", "GSM475756", "GSM475757", "GSM475758", "GSM475759", "GSM475760", "GSM475761", "GSM475762", "GSM475763", "GSM475764", "GSM475765", "GSM475766", "GSM475767", "GSM475768", "GSM475769", "GSM475770", "GSM475771", "GSM475772", "GSM475773", "GSM475774", "GSM475775", "GSM475776", "GSM475777", "GSM475778", "GSM475779", "GSM475780", "GSM475781", "GSM475782", "GSM475783", "GSM475784", "GSM475785", "GSM475786", "GSM475787", "GSM475788", "GSM475789", "GSM475790", "GSM475791", "GSM475792", "GSM475793", "GSM475794", "GSM475795", "GSM475796", "GSM475797", "GSM475798", "GSM475799", "GSM475800", "GSM475801", "GSM475802", "GSM475803", "GSM475804", "GSM475805", "GSM475806", "GSM475807", "GSM475808", "GSM475809", "GSM475810", "GSM475811"], "sample_count": 156, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data for early stage NSCLC", "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:GSE31210", "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=GSE31210", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31210", "version": null, "note": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM773540", "GSM773541", "GSM773542", "GSM773543", "GSM773544", "GSM773545", "GSM773546", "GSM773547", "GSM773548", "GSM773549", "GSM773550", "GSM773551", "GSM773552", "GSM773553", "GSM773554", "GSM773555", "GSM773556", "GSM773557", "GSM773558", "GSM773559", "GSM773560", "GSM773561", "GSM773562", "GSM773563", "GSM773564", "GSM773565", "GSM773566", "GSM773567", "GSM773568", "GSM773569", "GSM773570", "GSM773571", "GSM773572", "GSM773573", "GSM773574", "GSM773575", "GSM773576", "GSM773577", "GSM773578", "GSM773579", "GSM773580", "GSM773581", "GSM773582", "GSM773583", "GSM773584", "GSM773585", "GSM773586", "GSM773587", "GSM773588", "GSM773589", "GSM773590", "GSM773591", "GSM773592", "GSM773593", "GSM773594", "GSM773595", "GSM773596", "GSM773597", "GSM773598", "GSM773599", "GSM773600", "GSM773601", "GSM773602", "GSM773603", "GSM773604", "GSM773605", "GSM773606", "GSM773607", "GSM773608", "GSM773609", "GSM773610", "GSM773611", "GSM773612", "GSM773613", "GSM773614", "GSM773615", "GSM773616", "GSM773617", "GSM773618", "GSM773619", "GSM773620", "GSM773621", "GSM773622", "GSM773623", "GSM773624", "GSM773625", "GSM773626", "GSM773627", "GSM773628", "GSM773629", "GSM773630", "GSM773631", "GSM773632", "GSM773633", "GSM773634", "GSM773635", "GSM773636", "GSM773637", "GSM773638", "GSM773639", "GSM773640", "GSM773641", "GSM773642", "GSM773643", "GSM773644", "GSM773645", "GSM773646", "GSM773647", "GSM773648", "GSM773649", "GSM773650", "GSM773651", "GSM773652", "GSM773653", "GSM773654", "GSM773655", "GSM773656", "GSM773657", "GSM773658", "GSM773659", "GSM773660", "GSM773661", "GSM773662", "GSM773663", "GSM773664", "GSM773665", "GSM773666", "GSM773667", "GSM773668", "GSM773669", "GSM773670", "GSM773671", "GSM773672", "GSM773673", "GSM773674", "GSM773675", "GSM773676", "GSM773677", "GSM773678", "GSM773679", "GSM773680", "GSM773681", "GSM773682", "GSM773683", "GSM773684", "GSM773685", "GSM773686", "GSM773687", "GSM773688", "GSM773689", "GSM773690", "GSM773691", "GSM773692", "GSM773693", "GSM773694", "GSM773695", "GSM773696", "GSM773697", "GSM773698", "GSM773699", "GSM773700", "GSM773701", "GSM773702", "GSM773703", "GSM773704", "GSM773705", "GSM773706", "GSM773707", "GSM773708", "GSM773709", "GSM773710", "GSM773711", "GSM773712", "GSM773713", "GSM773714", "GSM773715", "GSM773716", "GSM773717", "GSM773718", "GSM773719", "GSM773720", "GSM773721", "GSM773722", "GSM773723", "GSM773724", "GSM773725", "GSM773726", "GSM773727", "GSM773728", "GSM773729", "GSM773730", "GSM773731", "GSM773732", "GSM773733", "GSM773734", "GSM773735", "GSM773736", "GSM773737", "GSM773738", "GSM773739", "GSM773740", "GSM773741", "GSM773742", "GSM773743", "GSM773744", "GSM773745", "GSM773746", "GSM773747", "GSM773748", "GSM773749", "GSM773750", "GSM773751", "GSM773752", "GSM773753", "GSM773754", "GSM773755", "GSM773756", "GSM773757", "GSM773758", "GSM773759", "GSM773760", "GSM773761", "GSM773762", "GSM773763", "GSM773764", "GSM773765", "GSM773766", "GSM773767", "GSM773768", "GSM773769", "GSM773770", "GSM773771", "GSM773772", "GSM773773", "GSM773774", "GSM773775", "GSM773776", "GSM773777", "GSM773778", "GSM773779", "GSM773780", "GSM773781", "GSM773782", "GSM773783", "GSM773784", "GSM773785"], "sample_count": 246, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression data for pathological stage I-II lung adenocarcinomas", "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:GSE32863", "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=GSE32863", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32863", "version": null, "note": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM813411", "GSM813412", "GSM813413", "GSM813414", "GSM813415", "GSM813416", "GSM813417", "GSM813418", "GSM813419", "GSM813420", "GSM813421", "GSM813422", "GSM813423", "GSM813424", "GSM813425", "GSM813426", "GSM813427", "GSM813428", "GSM813429", "GSM813430", "GSM813431", "GSM813432", "GSM813433", "GSM813434", "GSM813435", "GSM813436", "GSM813437", "GSM813438", "GSM813439", "GSM813440", "GSM813441", "GSM813442", "GSM813443", "GSM813444", "GSM813445", "GSM813446", "GSM813447", "GSM813448", "GSM813449", "GSM813450", "GSM813451", "GSM813452", "GSM813453", "GSM813454", "GSM813455", "GSM813456", "GSM813457", "GSM813458", "GSM813459", "GSM813460", "GSM813461", "GSM813462", "GSM813463", "GSM813464", "GSM813465", "GSM813466", "GSM813467", "GSM813468", "GSM813469", "GSM813470", "GSM813471", "GSM813472", "GSM813473", "GSM813474", "GSM813475", "GSM813476", "GSM813477", "GSM813478", "GSM813479", "GSM813480", "GSM813481", "GSM813482", "GSM813483", "GSM813484", "GSM813485", "GSM813486", "GSM813487", "GSM813488", "GSM813489", "GSM813490", "GSM813491", "GSM813492", "GSM813493", "GSM813494", "GSM813495", "GSM813496", "GSM813497", "GSM813498", "GSM813499", "GSM813500", "GSM813501", "GSM813502", "GSM813503", "GSM813504", "GSM813505", "GSM813506", "GSM813507", "GSM813508", "GSM813509", "GSM813510", "GSM813511", "GSM813512", "GSM813513", "GSM813514", "GSM813515", "GSM813516", "GSM813517", "GSM813518", "GSM813519", "GSM813520", "GSM813521", "GSM813522", "GSM813523", "GSM813524", "GSM813525", "GSM813526"], "sample_count": 116, "group_sizes": null, "group_sizes_basis": null, "platform": "6884", "taxon": "Homo sapiens", "title": "Gene expression analysis of lung adenocarcinoma and matched adjacent non-tumor lung tissue", "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:GSE43580", "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=GSE43580", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43580", "version": null, "note": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1065725", "GSM1065726", "GSM1065727", "GSM1065728", "GSM1065729", "GSM1065730", "GSM1065731", "GSM1065732", "GSM1065733", "GSM1065734", "GSM1065735", "GSM1065736", "GSM1065737", "GSM1065738", "GSM1065739", "GSM1065740", "GSM1065741", "GSM1065742", "GSM1065743", "GSM1065744", "GSM1065745", "GSM1065746", "GSM1065747", "GSM1065748", "GSM1065749", "GSM1065750", "GSM1065751", "GSM1065752", "GSM1065753", "GSM1065754", "GSM1065755", "GSM1065756", "GSM1065757", "GSM1065758", "GSM1065759", "GSM1065760", "GSM1065761", "GSM1065762", "GSM1065763", "GSM1065764", "GSM1065765", "GSM1065766", "GSM1065767", "GSM1065768", "GSM1065769", "GSM1065770", "GSM1065771", "GSM1065772", "GSM1065773", "GSM1065774", "GSM1065775", "GSM1065776", "GSM1065777", "GSM1065778", "GSM1065779", "GSM1065780", "GSM1065781", "GSM1065782", "GSM1065783", "GSM1065784", "GSM1065785", "GSM1065786", "GSM1065787", "GSM1065788", "GSM1065789", "GSM1065790", "GSM1065791", "GSM1065792", "GSM1065793", "GSM1065794", "GSM1065795", "GSM1065796", "GSM1065797", "GSM1065798", "GSM1065799", "GSM1065800", "GSM1065801", "GSM1065802", "GSM1065803", "GSM1065804", "GSM1065805", "GSM1065806", "GSM1065807", "GSM1065808", "GSM1065809", "GSM1065810", "GSM1065811", "GSM1065812", "GSM1065813", "GSM1065814", "GSM1065815", "GSM1065816", "GSM1065817", "GSM1065818", "GSM1065819", "GSM1065820", "GSM1065821", "GSM1065822", "GSM1065823", "GSM1065824", "GSM1065825", "GSM1065826", "GSM1065827", "GSM1065828", "GSM1065829", "GSM1065830", "GSM1065831", "GSM1065832", "GSM1065833", "GSM1065834", "GSM1065835", "GSM1065836", "GSM1065837", "GSM1065838", "GSM1065839", "GSM1065840", "GSM1065841", "GSM1065842", "GSM1065843", "GSM1065844", "GSM1065845", "GSM1065846", "GSM1065847", "GSM1065848", "GSM1065849", "GSM1065850", "GSM1065851", "GSM1065852", "GSM1065853", "GSM1065854", "GSM1065855", "GSM1065856", "GSM1065857", "GSM1065858", "GSM1065859", "GSM1065860", "GSM1065861", "GSM1065862", "GSM1065863", "GSM1065864", "GSM1065865", "GSM1065866", "GSM1065867", "GSM1065868", "GSM1065869", "GSM1065870", "GSM1065871", "GSM1065872", "GSM1065873", "GSM1065874"], "sample_count": 150, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "SBV - Gene Expression Profiles of Lung Cancer Tumors - Adenocarcinomas and Squamous Cell Carcinomas", "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:GSE7378", "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=GSE7378", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7378", "version": null, "note": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM177493", "GSM177494", "GSM177495", "GSM177496", "GSM177497", "GSM177498", "GSM177499", "GSM177500", "GSM177501", "GSM177502", "GSM177503", "GSM177504", "GSM177505", "GSM177506", "GSM177507", "GSM177508", "GSM177509", "GSM177510", "GSM177511", "GSM177512", "GSM177513", "GSM177514", "GSM177515", "GSM177516", "GSM177517", "GSM177518", "GSM177519", "GSM177520", "GSM177521", "GSM177522", "GSM177523", "GSM177524", "GSM177525", "GSM177526", "GSM177527", "GSM177528", "GSM177529", "GSM177530", "GSM177531", "GSM177532", "GSM177533", "GSM177534", "GSM177535", "GSM177536", "GSM177537", "GSM177538", "GSM177539", "GSM177540", "GSM177541", "GSM177542", "GSM177543", "GSM177544", "GSM177545", "GSM177546"], "sample_count": 54, "group_sizes": null, "group_sizes_basis": null, "platform": "4685", "taxon": "Homo sapiens", "title": "Expression data from age-dichotomized ER+, N0 breast tumors", "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:GSE7670", "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=GSE7670", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7670", "version": null, "note": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM185811", "GSM185812", "GSM185813", "GSM185814", "GSM185815", "GSM185816", "GSM185817", "GSM185818", "GSM185819", "GSM185820", "GSM185821", "GSM185822", "GSM185823", "GSM185824", "GSM185825", "GSM185826", "GSM185827", "GSM185828", "GSM185829", "GSM185830", "GSM185831", "GSM185832", "GSM185833", "GSM185834", "GSM185835", "GSM185836", "GSM185837", "GSM185838", "GSM185839", "GSM185840", "GSM185841", "GSM185842", "GSM185843", "GSM185844", "GSM185845", "GSM185846", "GSM185847", "GSM185848", "GSM185849", "GSM185850", "GSM185851", "GSM185852", "GSM185853", "GSM185854", "GSM185855", "GSM185856", "GSM185857", "GSM185858", "GSM185859", "GSM185860", "GSM185861", "GSM185862", "GSM185863", "GSM185864", "GSM185865", "GSM185866", "GSM185867", "GSM185868", "GSM185869", "GSM185870", "GSM185871", "GSM185872", "GSM185873", "GSM185874", "GSM185875", "GSM185876"], "sample_count": 66, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression data from Lung cancer", "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:GSE9893", "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=GSE9893", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE9893", "version": null, "note": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM249296", "GSM249524", "GSM249527", "GSM249529", "GSM249530", "GSM249531", "GSM249532", "GSM249533", "GSM249534", "GSM249535", "GSM249536", "GSM249537", "GSM249538", "GSM249539", "GSM249540", "GSM249541", "GSM249542", "GSM249543", "GSM249544", "GSM249545", "GSM249546", "GSM249547", "GSM249548", "GSM249549", "GSM249551", "GSM249552", "GSM249553", "GSM249555", "GSM249556", "GSM249557", "GSM249558", "GSM249559", "GSM249560", "GSM249561", "GSM249563", "GSM249564", "GSM249565", "GSM249566", "GSM249567", "GSM249595", "GSM249596", "GSM249597", "GSM249598", "GSM249599", "GSM249600", "GSM249601", "GSM249602", "GSM249603", "GSM249604", "GSM249605", "GSM249606", "GSM249607", "GSM249608", "GSM249609", "GSM249610", "GSM249611", "GSM249612", "GSM249613", "GSM249614", "GSM249615", "GSM249616", "GSM249617", "GSM249618", "GSM249619", "GSM249620", "GSM249622", "GSM249623", "GSM249624", "GSM249625", "GSM249627", "GSM249628", "GSM249629", "GSM249630", "GSM249631", "GSM249632", "GSM249633", "GSM249634", "GSM249635", "GSM249636", "GSM249637", "GSM249638", "GSM249639", "GSM249640", "GSM249641", "GSM249642", "GSM249643", "GSM249644", "GSM249646", "GSM249647", "GSM249648", "GSM249649", "GSM249650", "GSM249651", "GSM249652", "GSM249653", "GSM249654", "GSM249655", "GSM249657", "GSM249658", "GSM249659", "GSM249663", "GSM249664", "GSM249665", "GSM249666", "GSM249667", "GSM249668", "GSM249669", "GSM249670", "GSM249681", "GSM249682", "GSM249683", "GSM249684", "GSM249685", "GSM249686", "GSM249687", "GSM249688", "GSM249689", "GSM249690", "GSM249691", "GSM249692", "GSM249693", "GSM249694", "GSM249695", "GSM249696", "GSM249697", "GSM249698", "GSM249699", "GSM249700", "GSM249701", "GSM249702", "GSM249704", "GSM249705", "GSM249706", "GSM249707", "GSM249708", "GSM249709", "GSM249710", "GSM249711", "GSM249713", "GSM249772", "GSM249952", "GSM250002", "GSM250004", "GSM250006", "GSM250007", "GSM250009", "GSM250010", "GSM250011", "GSM250012", "GSM250013", "GSM250014", "GSM250015", "GSM250016", "GSM250017", "GSM250018"], "sample_count": 155, "group_sizes": null, "group_sizes_basis": null, "platform": "5049", "taxon": "Homo sapiens", "title": "A gene expression signature predicting the recurrence of tamoxifen-treated primary breast 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": "asset:table:pmid:33091876:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b9c8c328c9dcd3a7e1b890f41ec8b01275d59f0e9eadaed15fd1fdeeb843dd6c", "bytes": 2174, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[6]/table-wrap[1]#t1", "version": null, "note": "Correlation between TRIM28 mRNA expression and prognosis in lung cancer patients with different clinicopathological characteristics, determined via Kaplan-Meier plotter.", "structure": {"pmcid": "PMC7655206", "section_index": 6, "section_title": "Prognostic value of TRIM28 across cancer types", "row_count": 32, "column_count": 7}, "table": {"label": "Table 1", "caption": "Correlation between TRIM28 mRNA expression and prognosis in lung cancer patients with different clinicopathological characteristics, determined via Kaplan-Meier plotter.", "rows": [["Clinicopathological characteristics", "OS (n = 1928)", "FP (n = 646)"], ["N", "Hazard ratio", "P-value", "N", "Hazard ratio", "P-value"], ["Sex", "", "", "", "", "", ""], ["Female", "715", "2.11(1.54-2.9)", "<0.001", "468", "2.09(1.57-2.78)", "<0.001"], ["male", "1387", "1.48(1.25-1.75)", "<0.001", "514", "1.87(1.44-2.44)", "<0.001"], ["Histology", "", "", "", "", "", ""], ["Adenocarcinoma", "720", "2.65(1.96-3.59)", "<0.001", "461", "2.00(1.45-2.75)", "<0.001"], ["Squamous cell carcinoma", "524", "1.25(0.96-1.64)", "0.095", "141", "2.15(1.27-3.64)", "0.003"], ["Grade", "", "", "", "", "", ""], ["I", "201", "0.81(0.56-1.16)", "0.250", "140", "0.81(0.51-1.29)", "0.380"], ["II", "310", "1.34(0.96-1.87)", "0.079", "165", "1.68(1.08-2.62)", "0.020"], ["III", "77", "0.64(0.28-1.47)", "0.290", "51", "1.36(0.6-3.05)", "0.460"], ["Stage", "", "", "", "", "", ""], ["1", "577", "2.45(1.85-3.25)", "<0.001", "325", "1.47(0.94-2.31)", "0.091"], ["2", "244", "2.2(1.45-3.35)", "<0.001", "130", "0.79(0.46-1.35)", "0.380"], ["3", "70", "0.69(0.39-1.21)", "0.200", "19", "-", "-"], ["4", "4", "-", "-", "0", "-", "-"], ["Stage T", "", "", "", "", "", ""], ["1", "437", "1.37(0.97-1.92)", "0.070", "177", "2.31(1.38-3.89)", "0.001"], ["2", "589", "1.26(0.99-1.6)", "0.056", "351", "1.45(1.08-1.96)", "0.014"], ["3", "81", "0.8(0.47-1.34)", "0.390", "21", "0.58(0.21-1.62)", "0.290"], ["4", "46", "1.46(0.72-2.96)", "0.290", "7", "-", "-"], ["Stage N", "", "", "", "", "", ""], ["0", "781", "1.31(1.05-1.64)", "0.015", "374", "1,83(1.3-2.56)", "<0.001"], ["1", "252", "1.29(0.94-1.76)", "0.110", "130", "1.96(1.24-3.1)", "0.004"], ["2", "111", "1.18(0.78-1.78)", "0.430", "51", "1.82(0.91-3.65)", "0.087"], ["Stage M", "", "", "", "", "", ""], ["0", "681", "1.61(1.3-1.99)", "<0.001", "195", "1.56(0.94-2.59)", "0.080"], ["1", "10", "-", "-", "0", "-", "-"], ["Smoking history", "", "", "", "", "", ""], ["Never smoked", "205", "4.1(2.17-7.73)", "<0.001", "193", "2.72(1.66-4.45)", "<0.001"], ["Smoked", "820", "1.87(1.39-2.52)", "<0.001", "603", "1.71(1.34-2.18)", "<0.001"]], "row_count": 32, "column_count": 7, "numeric_cells": 135, "header_rows": 0, "locator": "section[6]/table-wrap[1]#t1"}}, {"id": "asset:table:pmid:33091876:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7e085d5bc8c209df52a3f425e627dce91b564211cae5f384b95e19b696fb6a77", "bytes": 1905, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[7]/table-wrap[1]#t2", "version": null, "note": "A multivariate Cox proportional hazards model was used to explore the effects of TRIM28 expression, clinicopathological characteristics and immune infiltration levels on survival.", "structure": {"pmcid": "PMC7655206", "section_index": 7, "section_title": "TRIM28 expression is associated with the immune infiltration level", "row_count": 28, "column_count": 7}, "table": {"label": "Table 2", "caption": "A multivariate Cox proportional hazards model was used to explore the effects of TRIM28 expression, clinicopathological characteristics and immune infiltration levels on survival.", "rows": [["LUAD (N=436)", "Variable", "Coef", "HR", "95%CI_l", "95%CI_u", "P-value"], ["", "Age", "0.019", "1.019", "1.002", "1.037", "0.028"], ["", "Gender", "-0.258", "0.772", "0.553", "1.079", "0.130"], ["", "Stage2", "0.857", "2.356", "1.550", "3.583", "<0.001"], ["", "Stage3", "1.065", "2.901", "1.900", "4.430", "<0.001"], ["", "Stage4", "1.256", "3.510", "1.918", "6.424", "<0.001"], ["", "Purity", "0.357", "1.430", "0.628", "3.257", "0.395"], ["", "B cell", "-3.507", "0.030", "0.002", "0.493", "0.014"], ["", "CD8+Tcell", "0.471", "1.601", "0.217", "11.801", "0.644"], ["", "CD4+Tcell", "2.090", "8.086", "0.537", "121.759", "0.131"], ["", "Macrophage", "0.782", "2.187", "0.138", "34.629", "0.579"], ["", "Neutrophil", "-1.888", "0.151", "0.003", "7.376", "0.341"], ["", "Dendritic", "0.219", "1.245", "0.297", "5.208", "0.765"], ["", "TRIM28", "0.595", "1.813", "1.317", "2.495", "<0.001"], ["LUSC (N=452)", "", "Coef", "HR", "95%CI_l", "95%CI_u", "P-value"], ["", "Age", "0.02", "1.02", "1.003", "1.038", "0.024"], ["", "Gender", "0.303", "1.353", "0.957", "1.913", "0.087"], ["", "Stage2", "0.107", "1.113", "0.792", "1.564", "0.539"], ["", "Stage3", "0.495", "1.641", "1.121", "2.402", "0.011"], ["", "Stage4", "0.982", "2.67", "0.949", "7.507", "0.063"], ["", "Purity", "-0.128", "0.88", "0.422", "1.834", "0.733"], ["", "B cell", "1.298", "3.663", "0.298", "45.061", "0.311"], ["", "CD8+Tcell", "-1.727", "0.178", "0.028", "1.124", "0.066"], ["", "CD4+Tcell", "0.705", "2.023", "0.153", "26.753", "0.593"], ["", "Macrophage", "-0.339", "0.713", "0.061", "8.326", "0.787"], ["", "Neutrophil", "0.980", "2.665", "0.099", "71.525", "0.559"], ["", "Dendritic", "0.722", "2.059", "0.489", "8.662", "0.325"], ["", "TRIM28", "0.000", "1.000", "0.774", "1.292", "1.000"]], "row_count": 28, "column_count": 7, "numeric_cells": 138, "header_rows": 0, "locator": "section[7]/table-wrap[1]#t2"}}], "gaps": ["asset:data:geo:GSE11121 not downloaded", "asset:data:geo:GSE11121 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE31210 not downloaded", "asset:data:geo:GSE31210 licence not read", "asset:data:geo:GSE32863 not downloaded", "asset:data:geo:GSE32863 licence not read", "asset:data:geo:GSE43580 not downloaded", "asset:data:geo:GSE43580 licence not read", "asset:data:geo:GSE7378 not downloaded", "asset:data:geo:GSE7378 licence not read", "asset:data:geo:GSE7670 not downloaded", "asset:data:geo:GSE7670 licence not read", "asset:data:geo:GSE9893 not downloaded", "asset:data:geo:GSE9893 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "ults are displayed with HRs and p-values or Cox p-"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "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 proportional hazards"}}, {"id": "method-3", "family": "clustering", "specific": "hierarchical", "label": "Clustering", "dsl_operations": ["hierarchical_cluster"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "hierarchical clustering"}}, {"id": "method-4", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "PPI"}}, {"id": "method-5", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "GO enrichment"}}, {"id": "method-6", "family": null, "specific": null, "label": "ESTIMATE algorithm", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Patients’ immune and stromal scores were determined using the ESTIMATE algorithm based on gene expression data [11]."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE43580", "GSE7670", "GSE32863", "GSE19188", "GSE4922-GPL96", "GSE3494-GPL96", "GSE7378", "GSE9893", "GSE11121", "GSE31210"], "resolved_accessions": ["GSE43580", "GSE7670", "GSE32863", "GSE19188", "GSE7378", "GSE9893", "GSE11121", "GSE31210"], "statements": ["TCGA data containing RNA sequencing results and clinical information (level 3 data) were downloaded from the cBioPortal database (http://www.cbioportal.org)."], "basis": "The paper names GSE43580, GSE7670, GSE32863, GSE19188, GSE7378, GSE9893, GSE11121, GSE31210 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": ["survival_km"], "assets": ["source:pmid:33091876", "data:geo:GSE11121", "asset:table:pmid:33091876:1", "asset:table:pmid:33091876:2"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE11121"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:24:05Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 33395, "completion_tokens": 4806, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:33091876", "type": "paper", "label": "pmid:33091876"}, {"id": "source:pmid:33091876", "type": "manuscript", "label": "PMID 33091876 full text"}, {"id": "data:geo:GSE11121", "type": "dataset", "label": "GEO GSE11121"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33091876", "type": "paper", "label": "pmid:33091876"}, {"id": "source:pmid:33091876", "type": "manuscript", "label": "PMID 33091876 full text"}, {"id": "data:geo:GSE11121", "type": "dataset", "label": "GEO GSE11121"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33091876", "type": "extraction", "used": ["source:pmid:33091876"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE11121", "type": "accession_resolution", "used": ["data:geo:GSE11121"], "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:33091876", "parent_hash": "sha256:ce4a4752d1aa66035162d7c168304f1b0392e8ac5e33e5b1c35c1d68967d95be", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE11121 licence not read", "asset:data:geo:GSE11121 not downloaded", "asset:data:geo:GSE19188 licence not read", "asset:data:geo:GSE19188 not downloaded", "asset:data:geo:GSE31210 licence not read", "asset:data:geo:GSE31210 not downloaded", "asset:data:geo:GSE32863 licence not read", "asset:data:geo:GSE32863 not downloaded", "asset:data:geo:GSE43580 licence not read", "asset:data:geo:GSE43580 not downloaded", "asset:data:geo:GSE7378 licence not read", "asset:data:geo:GSE7378 not downloaded", "asset:data:geo:GSE7670 licence not read", "asset:data:geo:GSE7670 not downloaded", "asset:data:geo:GSE9893 licence not read", "asset:data:geo:GSE9893 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["n Figure 1. In total, 517 LUAD patients with RNA sequencing data and clinical information in The Cancer", "and immune scores, clinical information and RNA sequencing data, we found that both the stromal and imm"], "order_basis": "paper_text_order:1653", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["the average linkage method. Cell culture and transfection We obtained the PC9 cell line from the RIKEN", "10 % fetal bovine serum and antibiotics. For transfection, the cells (1 × 105) were seeded in six-well", "re seeded in six-well plates. The cells were transfected using jetPRIME reagent (Polyplus transfectio", "transfected using jetPRIME reagent (Polyplus transfection) with 110 pmol of ON-TARGETplus SMARTpool-Hu"], "order_basis": "paper_text_order:7269", "id": "assay:2"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["Kaplan-Meier"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"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":"2026-11-04T02:44:40+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}}}