{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33676448", "kind": "science-record", "revision": 6, "content_hash": "sha256:fb3505d590d85f7269632b7104d1ad821cc52a44c514b5a39a4ebed9d969e741", "created_at": "2026-11-01T15:41:27Z", "updated_at": "2026-11-01T21:24:48Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "APE1 may influence CD4+ naïve T cells on recurrence free survival in early stage NSCLC.", "doi": "10.1186/s12885-021-07950-1", "pmid": "33676448", "authors": ["Yanping Li", "Xiaolong Zhao", "He Xiao", "Bo Yang", "Jie Liu", "Wen Rao", "Xiaoyan Dai", "Mengxia Li", "Nan Dai", "Yuxin Yang", "Dong Wang"], "journal": "BMC cancer", "year": 2021, "abstract": "BACKGROUND: It was demonstrated that multifunctional protein APE1 (Apurinic/apyrimidinic endonuclease 1) is closely related to tumor immune microenvironment in a number of investigations, Meanwhile, the abundance of tumor infiltrating lymphocytes (TILs) has been shown as a prognosis indicator in some researches. However, it remains unclear whether APE1 is involved in the process of TILs affecting the prognosis of patients. To this end, we investigated the associations between APE1 and TILs in non-small cell lung cancer (NSCLC) and explored whether APE1 would influence the associations of CD4+ T cells infiltration with the prognosis of patients.\nMETHODS: Genome-wide expression datasets were obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. MCPcounter and CIBERSORT analysis was conducted to evaluate the abundance of TILs in 1006 NSCLC patients of GEO database. Spearman correlation tests were used to evaluate correlations between abundance of various TILs and APE1 expression. RFS (recurrence free survival) was estimated using the Kaplan-Meier method and the Cox proportional-hazards model. The expression level of APE1 and tumor-infiltrating CD4+ T cells was evaluated by immunohistochemistry (IHC).\nRESULTS: The results showed that the abundance of CD4+ naïve T cells was negatively associated with the APE1 expression. CD4+ naïve T cells infiltration was a favorable prognostic factor for RFS, however, there was no effect of CD4+ T cells infiltration on RFS in patients with high APE1 expression. Subsequently, it was further confirmed that CD4+ T cells infiltration was negatively associated with the APE1 expression level in 108 NSCLC tissue samples; high CD4+ T cells infiltration was associated with longer RFS in low APE1 expression group but not in APE1 high expression group.\nCONCLUSION: These results suggested that APE1 may affect the relationship between CD4+ T cells infiltration and prognosis in NSCLC. This study provides new insights into predictors of outcome in patients with NSCLC, and suggests that combining immunotherapy and APE1-targeted therapy may be a promising treatment for NSCLC.", "claims": [{"id": "claim-method", "statement": "Spearman correlation tests were used to evaluate correlations between abundance of various TILs and APE1 expression.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33676448", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "Spearman correlation tests were used to evaluate correlations between abundance of various TILs and APE1 expression."}], "state": "complete"}, {"id": "claim-data-access", "statement": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33676448", "locator": "sections[23] \"Availability of data and materials\" paragraph 2", "quote": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file."}], "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:33676448"], "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:GSE30219"], "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:GSE30219"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33676448", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12885-021-07950-1", "sha256": "sha256:5785ae8a18ea53c252dab03a4d94169bf4b1ddca4f0cf53bb542a009477c91a9", "bytes": 41681, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12885-021-07950-1", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7937314", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE30219", "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=GSE30219", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE30219", "version": null, "note": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1465989", "GSM1465990", "GSM1465991", "GSM1465992", "GSM1465993", "GSM1465994", "GSM1465995", "GSM1465996", "GSM1465997", "GSM1465998", "GSM1465999", "GSM748053", "GSM748054", "GSM748055", "GSM748056", "GSM748057", "GSM748058", "GSM748059", "GSM748060", "GSM748061", "GSM748062", "GSM748063", "GSM748064", "GSM748065", "GSM748066", "GSM748067", "GSM748068", "GSM748069", "GSM748070", "GSM748071", "GSM748072", "GSM748073", "GSM748074", "GSM748075", "GSM748076", "GSM748077", "GSM748078", "GSM748079", "GSM748080", "GSM748081", "GSM748083", "GSM748084", "GSM748085", "GSM748086", "GSM748087", "GSM748088", "GSM748089", "GSM748090", "GSM748091", "GSM748092", "GSM748093", "GSM748094", "GSM748095", "GSM748096", "GSM748097", "GSM748098", "GSM748099", "GSM748100", "GSM748101", "GSM748102", "GSM748103", "GSM748104", "GSM748105", "GSM748106", "GSM748107", "GSM748108", "GSM748109", "GSM748110", "GSM748111", "GSM748112", "GSM748113", "GSM748115", "GSM748116", "GSM748117", "GSM748118", "GSM748119", "GSM748120", "GSM748121", "GSM748122", "GSM748123", "GSM748124", "GSM748125", "GSM748126", "GSM748127", "GSM748128", "GSM748129", "GSM748130", "GSM748131", "GSM748132", "GSM748133", "GSM748134", "GSM748135", "GSM748136", "GSM748137", "GSM748138", "GSM748139", "GSM748140", "GSM748141", "GSM748142", "GSM748143", "GSM748144", "GSM748145", "GSM748146", "GSM748147", "GSM748148", "GSM748149", "GSM748150", "GSM748151", "GSM748152", "GSM748153", "GSM748154", "GSM748155", "GSM748156", "GSM748157", "GSM748158", "GSM748159", "GSM748160", "GSM748161", "GSM748162", "GSM748163", "GSM748164", "GSM748165", "GSM748166", "GSM748167", "GSM748168", "GSM748169", "GSM748170", "GSM748171", "GSM748172", "GSM748173", "GSM748174", "GSM748175", "GSM748176", "GSM748177", "GSM748178", "GSM748179", "GSM748180", "GSM748181", "GSM748182", "GSM748183", "GSM748184", "GSM748185", "GSM748186", "GSM748187", "GSM748188", "GSM748189", "GSM748191", "GSM748192", "GSM748193", "GSM748195", "GSM748196", "GSM748197", "GSM748198", "GSM748199", "GSM748200", "GSM748201", "GSM748202", "GSM748203", "GSM748206", "GSM748207", "GSM748209", "GSM748210", "GSM748211", "GSM748212", "GSM748213", "GSM748214", "GSM748215", "GSM748216", "GSM748217", "GSM748218", "GSM748219", "GSM748220", "GSM748221", "GSM748222", "GSM748223", "GSM748224", "GSM748225", "GSM748226", "GSM748227", "GSM748228", "GSM748229", "GSM748232", "GSM748233", "GSM748234", "GSM748235", "GSM748239", "GSM748240", "GSM748242", "GSM748243", "GSM748244", "GSM748245", "GSM748246", "GSM748247", "GSM748248", "GSM748249", "GSM748250", "GSM748251", "GSM748252", "GSM748253", "GSM748254", "GSM748255", "GSM748256", "GSM748257", "GSM748258", "GSM748259", "GSM748260", "GSM748261", "GSM748262", "GSM748263", "GSM748264", "GSM748265", "GSM748266", "GSM748267", "GSM748268", "GSM748269", "GSM748270", "GSM748271", "GSM748272", "GSM748273", "GSM748274", "GSM748275", "GSM748276", "GSM748277", "GSM748278", "GSM748279", "GSM748280", "GSM748281", "GSM748282", "GSM748283", "GSM748284", "GSM748285", "GSM748286", "GSM748287", "GSM748288", "GSM748291", "GSM748292", "GSM748294", "GSM748295", "GSM748296", "GSM748297", "GSM748298", "GSM748299", "GSM748300", "GSM748301", "GSM748302", "GSM748303", "GSM748304", "GSM748305", "GSM748306", "GSM748307", "GSM748308", "GSM748309", "GSM748310", "GSM748311", "GSM748312", "GSM748313", "GSM748314", "GSM748315", "GSM748316", "GSM748317", "GSM748318", "GSM748319", "GSM748320", "GSM748321", "GSM748323", "GSM748324", "GSM748325", "GSM748326", "GSM748327", "GSM748328", "GSM748329", "GSM748330", "GSM748331", "GSM748332", "GSM748333", "GSM748334", "GSM748335", "GSM748336", "GSM748337", "GSM748338", "GSM748339", "GSM748341", "GSM748342", "GSM748343", "GSM748344", "GSM748345", "GSM748346", "GSM748347", "GSM748348", "GSM748349", "GSM748350", "GSM748351", "GSM748352", "GSM748353", "GSM748354", "GSM748355", "GSM748356", "GSM748357", "GSM748358", "GSM748359", "GSM748360", "GSM748361", "GSM748362", "GSM748363", "GSM748364", "GSM748365", "GSM748366"], "sample_count": 307, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "\"Off-context\" gene expression in lung cancer identifies a group of metastatic-prone tumors", "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": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "access_statement_kind": "data_availability_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:GSE50081", "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=GSE50081", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50081", "version": null, "note": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1213669", "GSM1213670", "GSM1213671", "GSM1213672", "GSM1213673", "GSM1213674", "GSM1213675", "GSM1213676", "GSM1213677", "GSM1213678", "GSM1213679", "GSM1213680", "GSM1213681", "GSM1213682", "GSM1213683", "GSM1213684", "GSM1213685", "GSM1213686", "GSM1213687", "GSM1213688", "GSM1213689", "GSM1213690", "GSM1213691", "GSM1213692", "GSM1213693", "GSM1213694", "GSM1213695", "GSM1213696", "GSM1213697", "GSM1213698", "GSM1213699", "GSM1213700", "GSM1213701", "GSM1213702", "GSM1213703", "GSM1213704", "GSM1213705", "GSM1213706", "GSM1213707", "GSM1213708", "GSM1213709", "GSM1213710", "GSM1213711", "GSM1213712", "GSM1213713", "GSM1213714", "GSM1213715", "GSM1213716", "GSM1213717", "GSM1213718", "GSM1213719", "GSM1213720", "GSM1213721", "GSM1213722", "GSM1213723", "GSM1213724", "GSM1213725", "GSM1213726", "GSM1213727", "GSM1213728", "GSM1213729", "GSM1213730", "GSM1213731", "GSM1213732", "GSM1213733", "GSM1213734", "GSM1213735", "GSM1213736", "GSM1213737", "GSM1213738", "GSM1213739", "GSM1213740", "GSM1213741", "GSM1213742", "GSM1213743", "GSM1213744", "GSM1213745", "GSM1213746", "GSM1213747", "GSM1213748", "GSM1213749", "GSM1213750", "GSM1213751", "GSM1213752", "GSM1213753", "GSM1213754", "GSM1213755", "GSM1213756", "GSM1213757", "GSM1213758", "GSM1213759", "GSM1213760", "GSM1213761", "GSM1213762", "GSM1213763", "GSM1213764", "GSM1213765", "GSM1213766", "GSM1213767", "GSM1213768", "GSM1213769", "GSM1213770", "GSM1213771", "GSM1213772", "GSM1213773", "GSM1213774", "GSM1213775", "GSM1213776", "GSM1213777", "GSM1213778", "GSM1213779", "GSM1213780", "GSM1213781", "GSM1213782", "GSM1213783", "GSM1213784", "GSM1213785", "GSM1213786", "GSM1213787", "GSM1213788", "GSM1213789", "GSM1213790", "GSM1213791", "GSM1213792", "GSM1213793", "GSM1213794", "GSM1213795", "GSM1213796", "GSM1213797", "GSM1213798", "GSM1213799", "GSM1213800", "GSM1213801", "GSM1213802", "GSM1213803", "GSM1213804", "GSM1213805", "GSM1213806", "GSM1213807", "GSM1213808", "GSM1213809", "GSM1213810", "GSM1213811", "GSM1213812", "GSM1213813", "GSM1213814", "GSM1213815", "GSM1213816", "GSM1213817", "GSM1213818", "GSM1213819", "GSM1213820", "GSM1213821", "GSM1213822", "GSM1213823", "GSM1213824", "GSM1213825", "GSM1213826", "GSM1213827", "GSM1213828", "GSM1213829", "GSM1213830", "GSM1213831", "GSM1213832", "GSM1213833", "GSM1213834", "GSM1213835", "GSM1213836", "GSM1213837", "GSM1213838", "GSM1213839", "GSM1213840", "GSM1213841", "GSM1213842", "GSM1213843", "GSM1213844", "GSM1213845", "GSM1213846", "GSM1213847", "GSM1213848", "GSM1213849"], "sample_count": 181, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Validation of a histology-independent prognostic gene signature for early stage, non-small cell lung cancer including stage IA patients", "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:GSE68465", "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=GSE68465", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE68465", "version": null, "note": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1672281", "GSM1672282", "GSM1672283", "GSM1672284", "GSM1672285", "GSM1672286", "GSM1672287", "GSM1672288", "GSM1672289", "GSM1672290", "GSM1672291", "GSM1672292", "GSM1672293", "GSM1672294", "GSM1672295", "GSM1672296", "GSM1672297", "GSM1672298", "GSM1672299", "GSM1672300", "GSM1672301", "GSM1672302", "GSM1672303", "GSM1672304", "GSM1672305", "GSM1672306", "GSM1672307", "GSM1672308", "GSM1672309", "GSM1672310", "GSM1672311", "GSM1672312", "GSM1672313", "GSM1672314", "GSM1672315", "GSM1672316", "GSM1672317", "GSM1672318", "GSM1672319", "GSM1672320", "GSM1672321", "GSM1672322", "GSM1672323", "GSM1672324", "GSM1672325", "GSM1672326", "GSM1672327", "GSM1672328", "GSM1672329", "GSM1672330", "GSM1672331", "GSM1672332", "GSM1672333", "GSM1672334", "GSM1672335", "GSM1672336", "GSM1672337", "GSM1672338", "GSM1672339", "GSM1672340", "GSM1672341", "GSM1672342", "GSM1672343", "GSM1672344", "GSM1672345", "GSM1672346", "GSM1672347", "GSM1672348", "GSM1672349", "GSM1672350", "GSM1672351", "GSM1672352", "GSM1672353", "GSM1672354", "GSM1672355", "GSM1672356", "GSM1672357", "GSM1672358", "GSM1672359", "GSM1672360", "GSM1672361", "GSM1672362", "GSM1672363", "GSM1672364", "GSM1672365", "GSM1672366", "GSM1672367", "GSM1672368", "GSM1672369", "GSM1672370", "GSM1672371", "GSM1672372", "GSM1672373", "GSM1672374", "GSM1672375", "GSM1672376", "GSM1672377", "GSM1672378", "GSM1672379", "GSM1672380", "GSM1672381", "GSM1672382", "GSM1672383", "GSM1672384", "GSM1672385", "GSM1672386", "GSM1672387", "GSM1672388", "GSM1672389", "GSM1672390", "GSM1672391", "GSM1672392", "GSM1672393", "GSM1672394", "GSM1672395", "GSM1672396", "GSM1672397", "GSM1672398", "GSM1672399", "GSM1672400", "GSM1672401", "GSM1672402", "GSM1672403", "GSM1672404", "GSM1672405", "GSM1672406", "GSM1672407", "GSM1672408", "GSM1672409", "GSM1672410", "GSM1672411", "GSM1672412", "GSM1672413", "GSM1672414", "GSM1672415", "GSM1672416", "GSM1672417", "GSM1672418", "GSM1672419", "GSM1672420", "GSM1672421", "GSM1672422", "GSM1672423", "GSM1672424", "GSM1672425", "GSM1672426", "GSM1672427", "GSM1672428", "GSM1672429", "GSM1672430", "GSM1672431", "GSM1672432", "GSM1672433", "GSM1672434", "GSM1672435", "GSM1672436", "GSM1672437", "GSM1672438", "GSM1672439", "GSM1672440", "GSM1672441", "GSM1672442", "GSM1672443", "GSM1672444", "GSM1672445", "GSM1672446", "GSM1672447", "GSM1672448", "GSM1672449", "GSM1672450", "GSM1672451", "GSM1672452", "GSM1672453", "GSM1672454", "GSM1672455", "GSM1672456", "GSM1672457", "GSM1672458", "GSM1672459", "GSM1672460", "GSM1672461", "GSM1672462", "GSM1672463", "GSM1672464", "GSM1672465", "GSM1672466", "GSM1672467", "GSM1672468", "GSM1672469", "GSM1672470", "GSM1672471", "GSM1672472", "GSM1672473", "GSM1672474", "GSM1672475", "GSM1672476", "GSM1672477", "GSM1672478", "GSM1672479", "GSM1672480", "GSM1672481", "GSM1672482", "GSM1672483", "GSM1672484", "GSM1672485", "GSM1672486", "GSM1672487", "GSM1672488", "GSM1672489", "GSM1672490", "GSM1672491", "GSM1672492", "GSM1672493", "GSM1672494", "GSM1672495", "GSM1672496", "GSM1672497", "GSM1672498", "GSM1672499", "GSM1672500", "GSM1672501", "GSM1672502", "GSM1672503", "GSM1672504", "GSM1672505", "GSM1672506", "GSM1672507", "GSM1672508", "GSM1672509", "GSM1672510", "GSM1672511", "GSM1672512", "GSM1672513", "GSM1672514", "GSM1672515", "GSM1672516", "GSM1672517", "GSM1672518", "GSM1672519", "GSM1672520", "GSM1672521", "GSM1672522", "GSM1672523", "GSM1672524", "GSM1672525", "GSM1672526", "GSM1672527", "GSM1672528", "GSM1672529", "GSM1672530", "GSM1672531", "GSM1672532", "GSM1672533", "GSM1672534", "GSM1672535", "GSM1672536", "GSM1672537", "GSM1672538", "GSM1672539", "GSM1672540", "GSM1672541", "GSM1672542", "GSM1672543", "GSM1672544", "GSM1672545", "GSM1672546", "GSM1672547", "GSM1672548", "GSM1672549", "GSM1672550", "GSM1672551", "GSM1672552", "GSM1672553", "GSM1672554", "GSM1672555", "GSM1672556", "GSM1672557", "GSM1672558", "GSM1672559", "GSM1672560", "GSM1672561", "GSM1672562", "GSM1672563", "GSM1672564", "GSM1672565", "GSM1672566", "GSM1672567", "GSM1672568", "GSM1672569", "GSM1672570", "GSM1672571", "GSM1672572", "GSM1672573", "GSM1672574", "GSM1672575", "GSM1672576", "GSM1672577", "GSM1672578", "GSM1672579", "GSM1672580", "GSM1672581", "GSM1672582", "GSM1672583", "GSM1672584", "GSM1672585", "GSM1672586", "GSM1672587", "GSM1672588", "GSM1672589", "GSM1672590", "GSM1672591", "GSM1672592", "GSM1672593", "GSM1672594", "GSM1672595", "GSM1672596", "GSM1672597", "GSM1672598", "GSM1672599", "GSM1672600", "GSM1672601", "GSM1672602", "GSM1672603", "GSM1672604", "GSM1672605", "GSM1672606", "GSM1672607", "GSM1672608", "GSM1672609", "GSM1672610", "GSM1672611", "GSM1672612", "GSM1672613", "GSM1672614", "GSM1672615", "GSM1672616", "GSM1672617", "GSM1672618", "GSM1672619", "GSM1672620", "GSM1672621", "GSM1672622", "GSM1672623", "GSM1672624", "GSM1672625", "GSM1672626", "GSM1672627", "GSM1672628", "GSM1672629", "GSM1672630", "GSM1672631", "GSM1672632", "GSM1672633", "GSM1672634", "GSM1672635", "GSM1672636", "GSM1672637", "GSM1672638", "GSM1672639", "GSM1672640", "GSM1672641", "GSM1672642", "GSM1672643", "GSM1672644", "GSM1672645", "GSM1672646", "GSM1672647", "GSM1672648", "GSM1672649", "GSM1672650", "GSM1672651", "GSM1672652", "GSM1672653", "GSM1672654", "GSM1672655", "GSM1672656", "GSM1672657", "GSM1672658", "GSM1672659", "GSM1672660", "GSM1672661", "GSM1672662", "GSM1672663", "GSM1672664", "GSM1672665", "GSM1672666", "GSM1672667", "GSM1672668", "GSM1672669", "GSM1672670", "GSM1672671", "GSM1672672", "GSM1672673", "GSM1672674", "GSM1672675", "GSM1672676", "GSM1672677", "GSM1672678", "GSM1672679", "GSM1672680", "GSM1672681", "GSM1672682", "GSM1672683", "GSM1672684", "GSM1672685", "GSM1672686", "GSM1672687", "GSM1672688", "GSM1672689", "GSM1672690", "GSM1672691", "GSM1672692", "GSM1672693", "GSM1672694", "GSM1672695", "GSM1672696", "GSM1672697", "GSM1672698", "GSM1672699", "GSM1672700", "GSM1672701", "GSM1672702", "GSM1672703", "GSM1672704", "GSM1672705", "GSM1672706", "GSM1672707", "GSM1672708", "GSM1672709", "GSM1672710", "GSM1672711", "GSM1672712", "GSM1672713", "GSM1672714", "GSM1672715", "GSM1672716", "GSM1672717", "GSM1672718", "GSM1672719", "GSM1672720", "GSM1672721", "GSM1672722", "GSM1672723", "GSM1672724", "GSM1672725", "GSM1672726", "GSM1672727", "GSM1672728", "GSM1672729", "GSM1672730", "GSM1672731", "GSM1672732", "GSM1672733", "GSM1672734", "GSM1672735", "GSM1672736", "GSM1672737", "GSM1672738", "GSM1672739", "GSM1672740", "GSM1672741", "GSM1672742"], "sample_count": 462, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "caArray_jacob-00182: Gene expression-based survival prediction in lung adenocarcinoma: a multi-site, blinded validation study", "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:33676448:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a8d44965c6b78eab780e7767eddbdafcce2a5bc7c2da33dcc29b79555b860d38", "bytes": 602, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#Tab1", "version": null, "note": "Baseline characteristic of four merged GEO datasets", "structure": {"pmcid": "PMC7937314", "section_index": 10, "section_title": "Patients’ characteristics", "row_count": 15, "column_count": 2}, "table": {"label": "Table 1", "caption": "Baseline characteristic of four merged GEO datasets", "rows": [["Characteristic", "The number of patients, n (%)"], ["Age", "63.15 ± 10.30"], ["Age range"], ["≥ 60 years", "675 (67.10)"], ["< 60 years", "331 (32.90)"], ["Sex"], ["Male", "480 (47.71)"], ["Female", "526 (52.29)"], ["Histological cell type"], ["Adenocarcinoma", "765 (76.04)"], ["Squamous cell carcinoma", "101 (10.04%)"], ["Others", "140 (13.92)"], ["Tumor stage"], ["I + II", "907 (90.16)"], ["III + IV", "98 (9.74)"]], "row_count": 15, "column_count": 2, "numeric_cells": 12, "header_rows": 1, "locator": "section[10]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:33676448:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7cf7d04babb2d5fcfe146294e5774783b1ec9a18d9fe9f0e458bd87d1ef655f2", "bytes": 1110, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#Tab2", "version": null, "note": "The correlation between APE1 and tummor infiltrating lymphocytes in NSCLC in merged GEO databases", "structure": {"pmcid": "PMC7937314", "section_index": 11, "section_title": "Correlation between APE1 expression and TILs infiltration", "row_count": 13, "column_count": 6}, "table": {"label": "Table 2", "caption": "The correlation between APE1 and tummor infiltrating lymphocytes in NSCLC in merged GEO databases", "rows": [["MCPcounter", "FARDEEP"], ["TILs", "rho", "P value", "TIICs", "rho", "P value"], ["NK cells", "−0.164", "< 0.001", "T cells CD4 memory activated", "0.154", "< 0.001"], ["T cells", "−0.139", "< 0.001", "B cells memory", "−0.134", "< 0.001"], ["B lineage", "−0.120", "< 0.001", "T cells follicular helper", "0.130", "< 0.001"], ["Cytotoxic lymphocytes", "−0.089", "0.005", "T cells CD4 naive", "−0.122", "< 0.001"], ["CD8 T cells", "−0.034", "0.282", "T cells CD8", "−0.108", "< 0.001"], ["scRNAseq signatures", "NK cells resting", "−0.055", "0.083"], ["", "rho", "P value", "T cells CD4 memory resting", "−0.039", "0.216"], ["CD8-C4-GZMK/CD8-C6-LAYN ratio", "−0.270", "< 0.001", "T cells gamma delta", "−0.023", "0.473"], ["TNFRSF9+ Treg", "0.386", "< 0.001", "B cells naive", "0.012", "0.710"], ["", "", "", "NK cells activated", "−0.012", "0.708"], ["", "", "", "T cells regulatory", "−0.006", "0.862"]], "row_count": 13, "column_count": 6, "numeric_cells": 36, "header_rows": 0, "locator": "section[11]/table-wrap[1]#Tab2"}}, {"id": "asset:table:pmid:33676448:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:82a80f5d149581077439f6db9c9804bb7276c8ea942df2c3ed0cd7b3bf299c14", "bytes": 689, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#Tab3", "version": null, "note": "The correlation between APE1 and tummor infiltrating lymphocytes in 20 patients", "structure": {"pmcid": "PMC7937314", "section_index": 11, "section_title": "Correlation between APE1 expression and TILs infiltration", "row_count": 13, "column_count": 3}, "table": {"label": "Table 3", "caption": "The correlation between APE1 and tummor infiltrating lymphocytes in 20 patients", "rows": [["TILs", "Estimate.rho", "P value"], ["CD4+ T cells", "−0.526", "0.019"], ["NK cells", "−0.379", "0.100"], ["other Cells", "0.349", "0.132"], ["B lineage", "−0.308", "0.186"], ["CD8+ T cells", "0.260", "0.267"], ["B cells", "−0.198", "0.400"], ["NK cells", "0.155", "0.513"], ["Cytotoxic lymphocytes", "−0.141", "0.551"], ["CD8+ T cells", "−0.137", "0.564"], ["T cells", "−0.056", "0.816"], ["CD8-C4-GZMK/CD8-C6-LAYN ratio", "−0.397", "0.084"], ["TNFRSF9+ Treg", "0.671", "0.002"]], "row_count": 13, "column_count": 3, "numeric_cells": 24, "header_rows": 1, "locator": "section[11]/table-wrap[2]#Tab3"}}, {"id": "asset:table:pmid:33676448:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b10850b46e47f88a4075d8a560117d386164c865778e6a3c9e81522e90f03fb1", "bytes": 1024, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab4", "version": null, "note": "The result of COX analysis of APE1 and the abundance of TILs with RFS in GEO databases", "structure": {"pmcid": "PMC7937314", "section_index": 12, "section_title": "Relationship of APE1 expression, CD4+ naïve T cells infiltration with NSCLC prognosis", "row_count": 13, "column_count": 5}, "table": {"label": "Table 4", "caption": "The result of COX analysis of APE1 and the abundance of TILs with RFS in GEO databases", "rows": [["", "HR(95% CI)", "P", "HR(95% CI)*", "P*"], ["APE1", "1.410 (1.130–1.760)", "0.002", "1.270 (1.007–1.603)", "0.044"], ["T cells CD4 naive", "0.101 (0.021–0.474)", "0.004", "0.243 (0.048–1.224)", "0.086"], ["T cells CD8", "0.217 (0.031–1.530)", "0.125", "", ""], ["B cells memory", "0.007 (0.000–5.560)", "0.146", "", ""], ["T cells", "0.871 (0.697–1.090)", "0.226", "", ""], ["NK cells", "1.280 (0.860–1.900)", "0.226", "", ""], ["T cells follicular helper", "2.890 (0.425–19.700)", "0.278", "", ""], ["B lineage", "0.942 (0.842–1.050)", "0.296", "", ""], ["Cytotoxic lymphocytes", "1.020 (0.866–1.210)", "0.779", "", ""], ["NK cells activated", "0.899 (0.048–16.900)", "0.943", "", ""], ["CD8-C4-GZMK/CD8-C6-LAYN ratio", "0.282 (0.138–0.577)", "0.001", "", ""], ["TNFRSF9+ Treg", "2.140 (1.244–3.683)", "0.006", "", ""]], "row_count": 13, "column_count": 5, "numeric_cells": 30, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:33676448:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:d0e01bfbc166a2e5d5d168a275feb15cccfb17e5c57b3318a8287dfe03ea7223", "bytes": 896, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab5", "version": null, "note": "The result of Cox analysis evaluating prognosis of CD4+ naive T cells for RFS in different APE1 level subgroups in GEO databases", "structure": {"pmcid": "PMC7937314", "section_index": 13, "section_title": "APE1 expression influence the relationship between CD4+ T cells infiltration and prognosis in NSCLC patients", "row_count": 10, "column_count": 5}, "table": {"label": "Table 5", "caption": "The result of Cox analysis evaluating prognosis of CD4+ naive T cells for RFS in different APE1 level subgroups in GEO databases", "rows": [["", "CD4+ naive T cells"], ["HR (95% CI)", "P", "HR (95% CI)*", "P*"], ["Low APE1", "0.003 (0.000–0.076)", "< 0.001", "0.009 (0.000–0.361)", "0.013"], ["High APE1", "0.455 (0.074–2.792)", "0.395", "0.604 (0.098–3.847)", "0.604"], ["Interaction", "117.46 (2.725–5062)", "0.013", "59.299 (1.246–2822)", "0.038"], ["", "CD8+T C4/C6 ratio", "P", "TNFRSF9+ Treg", "P"], ["HR (95% CI)", "HR (95% CI)"], ["Low APE1", "0.415 (0.078–2.221)", "0.304", "0.825 (0.246–2.764)", "0.756"], ["High APE1", "0.298 (0.136–0.656)", "0.003", "2.212 (1.103–4.080)", "0.024"], ["Interaction", "0.846 (0.134–5.349)", "0.859", "2.257 (0.576–8.850)", "0.243"]], "row_count": 10, "column_count": 5, "numeric_cells": 28, "header_rows": 0, "locator": "section[13]/table-wrap[1]#Tab5"}}, {"id": "asset:table:pmid:33676448:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:08698f5658e6b4ebed01f9600b11c2c420bf5dd619626e935c0bc940ca38303d", "bytes": 585, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab6", "version": null, "note": "Patients’ basic characteristic of 108 NSCLC patients", "structure": {"pmcid": "PMC7937314", "section_index": 14, "section_title": "APE1 expression and CD4+ T cells infiltration in tissue samples and the associations with prognosis", "row_count": 16, "column_count": 2}, "table": {"label": "Table 6", "caption": "Patients’ basic characteristic of 108 NSCLC patients", "rows": [["Characteristic", "The number of patients, n (%)"], ["Age", "57.97 ± 8.36"], ["Age range"], ["≥ 60 years", "52 (48.15)"], ["< 60 years", "56 (51.85)"], ["Sex"], ["Male", "54 (50.00)"], ["Female", "54 (50.00)"], ["Smoking status"], ["ever", "49 (45.37)"], ["never", "59 (54.63)"], ["Histological cell type"], ["Adenocarcinoma", "108 (100.00)"], ["Tumor stage"], ["I", "107 (99.07)"], ["II", "1 (0.93)"]], "row_count": 16, "column_count": 2, "numeric_cells": 12, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab6"}}], "gaps": ["asset:data:geo:GSE30219 not downloaded", "asset:data:geo:GSE30219 licence not read", "asset:data:geo:GSE31210 not downloaded", "asset:data:geo:GSE31210 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE68465 not downloaded", "asset:data:geo:GSE68465 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Spearman correlation tests were used to evaluate correlations between abundance of various TILs and APE1 expression."}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "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"}}, {"id": "method-4", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "Chi-square"}}], "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": ["spearman_rho"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: spearman."}, "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": ["GSE68465", "GSE30219", "GSE31210", "GSE50081"], "resolved_accessions": ["GSE68465", "GSE30219", "GSE31210", "GSE50081"], "statements": ["For GEO database, the data can be obtained from the Gene Expression Omnibus (GEO) public database under accession number GSE68465, GSE30219, GSE31210 and GSE50081. The data of APE1 expression and immune cell population in 20 NSCLCs can be obtained from supplementary file."], "basis": "The paper names GSE68465, GSE30219, GSE31210, GSE50081 in Gene Expression Omnibus (GEO) public database and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["spearman_rho"], "assets": ["source:pmid:33676448", "data:geo:GSE30219", "asset:table:pmid:33676448:1", "asset:table:pmid:33676448:2", "asset:table:pmid:33676448:3", "asset:table:pmid:33676448:4", "asset:table:pmid:33676448:5", "asset:table:pmid:33676448:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE30219"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:27:31Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 34157, "completion_tokens": 1736, "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:33676448", "type": "paper", "label": "pmid:33676448"}, {"id": "source:pmid:33676448", "type": "manuscript", "label": "PMID 33676448 full text"}, {"id": "data:geo:GSE30219", "type": "dataset", "label": "GEO GSE30219"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33676448", "type": "paper", "label": "pmid:33676448"}, {"id": "source:pmid:33676448", "type": "manuscript", "label": "PMID 33676448 full text"}, {"id": "data:geo:GSE30219", "type": "dataset", "label": "GEO GSE30219"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33676448", "type": "extraction", "used": ["source:pmid:33676448"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE30219", "type": "accession_resolution", "used": ["data:geo:GSE30219"], "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:33676448", "parent_hash": "sha256:89e23f9462e861f8f3e8c421dc7da3a446baae0ebddaad18e5a2c0ec766a02d2", "fork_of": null, "generation": 5}, "gaps": ["asset:data:geo:GSE30219 licence not read", "asset:data:geo:GSE30219 not downloaded", "asset:data:geo:GSE31210 licence not read", "asset:data:geo:GSE31210 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE68465 licence not read", "asset:data:geo:GSE68465 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["r-infiltrating CD4+ T cells was evaluated by immunohistochemistry (IHC). RESULTS: The results showed that the", "cells was evaluated by immunohistochemistry (IHC). RESULTS: The results showed that the abund", "low-score groups separately according to the IHC staining in the other cohort comprised of 10", "ents is shown in Table 6. The representative IHC images of APE1 and TILs density of CD4+ cell"], "order_basis": "paper_text_order:1308", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["e-wide gene expression was all profiled with Affymetrix HG-U133 chips (Affymetrix). Raw CEL files we", "all profiled with Affymetrix HG-U133 chips (Affymetrix). Raw CEL files were downloaded from GEO and"], "order_basis": "paper_text_order:2518", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["spearman_rho"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Spearman correlation tests were used to evaluate correlations between abundance of various TILs and APE1 expression."], "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":"2026-11-04T02:36:33+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}}}