{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33879165", "kind": "science-record", "revision": 7, "content_hash": "sha256:ef5d13d879825c09e645780f03f711d22766c59e885262fb107e3a21b0dee770", "created_at": "2026-11-01T15:41:33Z", "updated_at": "2026-11-01T22:03:35Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "NEIL3 may act as a potential prognostic biomarker for lung adenocarcinoma.", "doi": "10.1186/s12935-021-01938-4", "pmid": "33879165", "authors": ["Cui Zhao", "Jian Liu", "Haomiao Zhou", "Xin Qian", "Hui Sun", "Xuewen Chen", "Miaosen Zheng", "Tingting Bian", "Lei Liu", "Yifei Liu", "Jianguo Zhang"], "journal": "Cancer cell international", "year": 2021, "abstract": "BACKGROUND: Lung adenocarcinoma (LUAD) is the leading cause of cancer-related death. This study aimed to develop and validate reliable prognostic biomarkers and signature.\nMETHODS: Differentially expressed genes were identified based on three Gene Expression Omnibus (GEO) datasets. Based on 1052 samples' data from our cohort, GEO and The Cancer Genome Atlas, we explored the relationship of clinicopathological features and NEIL3 expression to determine clinical effect of NEIL3 in LUAD. Western blotting (22 pairs of tumor and normal tissues), Real-time quantitative PCR (19 pairs of tumor and normal tissues), and immunohistochemical analyses (406-tumor tissues subjected to microarray) were conducted. TIMER and ImmuCellAI analyzed relationship between NEIL3 expression and the abundance of tumor-infiltrating immune cells in LUAD. The co-expressed-gene prognostic signature was established based on the Cox regression analysis.\nRESULTS: This study identified 502 common differentially expressed genes and confirmed that NEIL3 was significantly overexpressed in LUAD samples (P < 0.001). Increased NEIL3 expression was related to advanced stage, larger tumor size and poor overall survival (p < 0.001) in three LUAD cohorts. The proportions of natural T regulatory cells and induced T regulatory cells increased in the high NEIL3 group, whereas those of B cells, Th17 cells and dendritic cells decreased. Gene set enrichment analysis indicated that NEIL3 may activate cell cycle progression and P53 signaling pathway, leading to poor outcomes. We identified nine prognosis-associated hub genes among 370 genes co-expressed with NEIL3. A 10-gene prognostic signature including NEIL3 and nine key co-expressed genes was constructed. Higher risk-score was correlated with more advanced stage, larger tumor size and worse outcome (p < 0.05). Finally, the signature was verified in test cohort (GSE50081) with superior diagnostic accuracy.\nCONCLUSIONS: This study suggested that NEIL3 has the potential to be an immune-related therapeutic target and an independent predictor of LUAD prognosis. We also developed a prognostic signature for LUAD with a precise diagnostic accuracy.", "claims": [{"id": "claim-method", "statement": "Multivariate Cox regression analysis was conducted to identify independent prognostic factors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33879165", "locator": "sections[11] \"Statistical analysis\" paragraph 2", "quote": "Multivariate Cox regression analysis was conducted to identify independent prognostic factors."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33879165", "locator": "sections[28] \"notes\" paragraph 1", "quote": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/)."}], "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:33879165"], "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:33879165", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12935-021-01938-4", "sha256": "sha256:bee89f14bae0b3ef808d24b8d9da5a23354822db1a82950f4fdb6a50c19e15bb", "bytes": 41522, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12935-021-01938-4", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8059184", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "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": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "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": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "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:GSE33532", "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=GSE33532", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33532", "version": null, "note": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM835268", "GSM835269", "GSM835270", "GSM835271", "GSM835272", "GSM835273", "GSM835274", "GSM835275", "GSM835276", "GSM835277", "GSM835278", "GSM835279", "GSM835280", "GSM835281", "GSM835282", "GSM835283", "GSM835284", "GSM835285", "GSM835286", "GSM835287", "GSM835288", "GSM835289", "GSM835290", "GSM835291", "GSM835292", "GSM835293", "GSM835294", "GSM835295", "GSM835296", "GSM835297", "GSM835298", "GSM835299", "GSM835300", "GSM835301", "GSM835302", "GSM835303", "GSM835304", "GSM835305", "GSM835306", "GSM835307", "GSM835308", "GSM835309", "GSM835310", "GSM835311", "GSM835312", "GSM835313", "GSM835314", "GSM835315", "GSM835316", "GSM835317", "GSM835318", "GSM835319", "GSM835320", "GSM835321", "GSM835322", "GSM835323", "GSM835324", "GSM835325", "GSM835326", "GSM835327", "GSM835328", "GSM835329", "GSM835330", "GSM835331", "GSM835332", "GSM835333", "GSM835334", "GSM835335", "GSM835336", "GSM835337", "GSM835338", "GSM835339", "GSM835340", "GSM835341", "GSM835342", "GSM835343", "GSM835344", "GSM835345", "GSM835346", "GSM835347", "GSM835348", "GSM835349", "GSM835350", "GSM835351", "GSM835352", "GSM835353", "GSM835354", "GSM835355", "GSM835356", "GSM835357", "GSM835358", "GSM835359", "GSM835360", "GSM835361", "GSM835362", "GSM835363", "GSM835364", "GSM835365", "GSM835366", "GSM835367"], "sample_count": 100, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Intratumor heterogeneity of gene expression profiles in early stage non-small cell lung cancer (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:GSE43458", "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=GSE43458", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43458", "version": null, "note": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1062765", "GSM1062766", "GSM1062767", "GSM1062768", "GSM1062769", "GSM1062770", "GSM1062771", "GSM1062772", "GSM1062773", "GSM1062774", "GSM1062775", "GSM1062776", "GSM1062777", "GSM1062778", "GSM1062779", "GSM1062780", "GSM1062781", "GSM1062782", "GSM1062783", "GSM1062784", "GSM1062785", "GSM1062786", "GSM1062787", "GSM1062788", "GSM1062789", "GSM1062790", "GSM1062791", "GSM1062792", "GSM1062793", "GSM1062794", "GSM1062795", "GSM1062796", "GSM1062797", "GSM1062798", "GSM1062799", "GSM1062800", "GSM1062801", "GSM1062802", "GSM1062803", "GSM1062804", "GSM1062805", "GSM1062806", "GSM1062807", "GSM1062808", "GSM1062809", "GSM1062810", "GSM1062811", "GSM1062812", "GSM1062813", "GSM1062814", "GSM1062815", "GSM1062816", "GSM1062817", "GSM1062818", "GSM1062819", "GSM1062820", "GSM1062821", "GSM1062822", "GSM1062823", "GSM1062824", "GSM1062825", "GSM1062826", "GSM1062827", "GSM1062828", "GSM1062829", "GSM1062830", "GSM1062831", "GSM1062832", "GSM1062833", "GSM1062834", "GSM1062835", "GSM1062836", "GSM1062837", "GSM1062838", "GSM1062839", "GSM1062840", "GSM1062841", "GSM1062842", "GSM1062843", "GSM1062844", "GSM1062845", "GSM1062846", "GSM1062847", "GSM1062848", "GSM1062849", "GSM1062850", "GSM1062851", "GSM1062852", "GSM1062853", "GSM1062854", "GSM1062855", "GSM1062856", "GSM1062857", "GSM1062858", "GSM1062859", "GSM1062860", "GSM1062861", "GSM1062862", "GSM1062863", "GSM1062864", "GSM1062865", "GSM1062866", "GSM1062867", "GSM1062868", "GSM1062869", "GSM1062870", "GSM1062871", "GSM1062872", "GSM1062873", "GSM1062874"], "sample_count": 110, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression profiling of lung adenocarcinomas and normal 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: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": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/).", "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": "asset:table:pmid:33879165:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:a2c73afb2050b84407f6f990a4717d227081645e6572612f919e925af9beff5d", "bytes": 1174, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab1", "version": null, "note": "Relationship between NEIL3 expression and clinicopathology in the TCGA LUAD cohort", "structure": {"pmcid": "PMC8059184", "section_index": 14, "section_title": "Correlation between NEIL3 expression and clinicopathological characteristics of LUAD patients", "row_count": 22, "column_count": 6}, "table": {"label": "Table 1", "caption": "Relationship between NEIL3 expression and clinicopathology in the TCGA LUAD cohort", "rows": [["Characteristics", "n", "NEIL3", "χ2", "P value"], ["Low expression", "High expression"], ["Total", "293", "147", "146", "", ""], ["Age", "0.206", "0.65"], ["≤ 60", "98", "51 (52.05)", "47 (47.95)", "", ""], ["> 60", "195", "96 (49.24)", "99 (50.76)", "", ""], ["Gender", "2.13", "0.144"], ["Male", "138", "63 (45.65)", "75 (54.35)", "", ""], ["Female", "155", "84 (54.19)", "71 (45.81)", "", ""], ["TNM stage", "7.689", "0.004*"], ["I and II", "223", "122 (54.70)", "101 (45.30)", "", ""], ["III and IV", "70", "25 (35.70)", "45 (64.30)", "", ""], ["Tumor stage", "7.201", "0.027*"], ["I", "88", "54 (61.40)", "34 (38.60)", "", ""], ["II", "169", "80 (47.30)", "89 (52.70)", "", ""], ["III and IV", "37", "14 (37.80)", "23 (62.20)", "", ""], ["Metastasis stage", "2.809", "0.094"], ["Negative", "274", "141 (51.50)", "133 (48.50)", "", ""], ["Positive", "19", "6 (31.60)", "13 (68.40)", "", ""], ["Node stage", "2.259", "0.133"], ["Negative", "187", "100 (53.50)", "87 (46.50)", "", ""], ["Positive", "106", "47 (44.30)", "59 (55.70)", "", ""]], "row_count": 22, "column_count": 6, "numeric_cells": 57, "header_rows": 2, "locator": "section[14]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:33879165:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:17d31937ed1bc614cafa76edb27b4050fc07ef6ad325835b3edd811b927de478", "bytes": 1212, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#Tab2", "version": null, "note": "Relationship between NEIL3 expression and clinicopathology in our LUAD cohort", "structure": {"pmcid": "PMC8059184", "section_index": 14, "section_title": "Correlation between NEIL3 expression and clinicopathological characteristics of LUAD patients", "row_count": 23, "column_count": 6}, "table": {"label": "Table 2", "caption": "Relationship between NEIL3 expression and clinicopathology in our LUAD cohort", "rows": [["Characteristics", "n", "NEIL3", "χ2", "P value"], ["Low expression", "High expression"], ["Total", "406", "228", "178", "", ""], ["Age", "1.082", "0.298"], ["≤ 60", "146", "77 (52.74)", "69 (47.26)", "", ""], ["> 60", "260", "151 (58.08)", "109 (41.92)", "", ""], ["Gender", "2.814", "0.093"], ["Male", "249", "148 (59.44)", "101 (40.56)", "", ""], ["Female", "157", "80 (50.96)", "77 (49.04)", "", ""], ["TNM stage", "1.81", "0.178"], ["I and II", "312", "169 (54.17)", "143 (45.83)", "", ""], ["III and IV", "94", "59 (62.77)", "35 (37.23)", "", ""], ["Tumor stage", "14.648", "0.002*"], ["I", "203", "124 (61.08)", "79 (38.92)", "", ""], ["II", "145", "81 (55.86)", "64 (44.14)", "", ""], ["III", "32", "8 (25.00)", "24 (75.00)", "", ""], ["IV", "26", "15 (57.69)", "11 (42.31)", "", ""], ["Metastasis stage", "0.001", "0.971"], ["Negative", "397", "223 (56.17)", "174 (43.83)", "", ""], ["Positive", "9", "5 (55.56)", "4 (44.44)", "", ""], ["Node stage", "0.88", "0.348"], ["Negative", "222", "120 (54.05)", "102 (45.94)", "", ""], ["Positive", "184", "108 (58.70)", "76 (41.30)", "", ""]], "row_count": 23, "column_count": 6, "numeric_cells": 60, "header_rows": 2, "locator": "section[14]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:33879165:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:48d9f67ea055ef8ed2fef3878cf0a8685acf1d346fe369bae5ce7066459352e5", "bytes": 901, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab3", "version": null, "note": "Univariate and multivariate analyses of factors associated with overall survival in LUADs using Cox regression", "structure": {"pmcid": "PMC8059184", "section_index": 15, "section_title": "NEIL3 overexpression predicts poor prognosis in LUAD patients", "row_count": 9, "column_count": 5}, "table": {"label": "Table 3", "caption": "Univariate and multivariate analyses of factors associated with overall survival in LUADs using Cox regression", "rows": [["Variable", "Univariate", "Multivariate"], ["HR (95% CI)", "P", "HR (95% CI)", "P"], ["Age", "1.004 (0.985 to 1.023)", "0.707", "1.016 (0.996 to 1.037)", "0.112"], ["Gender", "1.105 (0.753 to 1.621)", "0.611", "1.050 (0.712 to 1.549)", "0.806"], ["TNM stage", "1.322 (1.202 to 1.454)", "0.000*", "1.305 (1.021 to 1.669)", "0.034*"], ["Tumor stage", "1.696 (1.348 to 2.134)", "0.000*", "1.173 (0.875 to 1.573)", "0.286"], ["Metastasis stage", "1.594 (0.871 to 2.918)", "0.13", "0.528 (0.181 to 1.537)", "0.241"], ["Node stage", "1.820 (1.474 to 2.247)", "0.000*", "1.180 (0.836 to 1.666)", "0.345"], ["NEIL3", "1.760 (1.456 to 2.129)", "0.000*", "1.638 (1.338 to 2.005)", "0.000*"]], "row_count": 9, "column_count": 5, "numeric_cells": 30, "header_rows": 2, "locator": "section[15]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:33879165:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:6e4cecbd3b4d4b2cb7a6e08ddf0c9b7a77981723a805da2921a38aba5c6fd730", "bytes": 637, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[17]/table-wrap[1]#Tab4", "version": null, "note": "The hub genes co-expressed with NEIL3", "structure": {"pmcid": "PMC8059184", "section_index": 17, "section_title": "KEGG and GO enrichment analysis of NEIL3 and co-expressed genes in LUAD", "row_count": 11, "column_count": 4}, "table": {"label": "Table 4", "caption": "The hub genes co-expressed with NEIL3", "rows": [["Gene", "Cor", "P value", "Group"], ["TOP2A", "0.635", "1.52E−63", "Positive"], ["CCNA2", "0.726", "2.36E−91", "Positive"], ["BUB1B", "0.683", "4.49E−77", "Positive"], ["CDC45", "0.631", "2.04E−62", "Positive"], ["BUB1", "0.669", "7.54E−73", "Positive"], ["CDK1", "0.668", "1.34E−72", "Positive"], ["NCAPG", "0.7", "2.21E−82", "Positive"], ["KIF23", "0.672", "1.49E−73", "Positive"], ["UBE2C", "0.591", "3.82E−53", "Positive"], ["CCNB2", "0.674", "3.35E−74", "Positive"]], "row_count": 11, "column_count": 4, "numeric_cells": 22, "header_rows": 1, "locator": "section[17]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:33879165:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2bcb9d9cbe062eebe800aee5ccf7d0e3d33012295a621dc726115f02ccf0c772", "bytes": 802, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#Tab5", "version": null, "note": "Univariate and multivariate analyses of factors in the GSE50081 cohort using Cox regression", "structure": {"pmcid": "PMC8059184", "section_index": 18, "section_title": "Establishment and evaluation of prognostic signature for LUAD patients", "row_count": 8, "column_count": 5}, "table": {"label": "Table 5", "caption": "Univariate and multivariate analyses of factors in the GSE50081 cohort using Cox regression", "rows": [["Variable", "Univariate", "Multivariate"], ["HR (95% CI)", "P", "HR (95% CI)", "P"], ["Age", "1.020 (0.990 to 1.050)", "0.192", "1.009 (0.978 to 1.041)", "0.562"], ["Gender", "0.709 (0.406 to 1.240)", "0.228", "0.701 (0.395 to 1.244)", "0.225"], ["TNM stage", "1.603 (1.255 to 2.047)", "0.000*", "0.904 (0.126 to 6.476)", "0.92"], ["Tumor stage", "2.756 (1.438 to 5.283)", "0.002*", "2.229 (0.204 to 24.396)", "0.512"], ["Node stage", "2.142 (1.199 to 3.825)", "0.010*", "2.940 (0.056 to 155.468)", "0.594"], ["Risk score", "1.531 (1.241 to 1.888)", "0.000*", "1.577 (1.203 to 2.067)", "0.001*"]], "row_count": 8, "column_count": 5, "numeric_cells": 26, "header_rows": 2, "locator": "section[18]/table-wrap[1]#Tab5"}}], "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:GSE33532 not downloaded", "asset:data:geo:GSE33532 licence not read", "asset:data:geo:GSE43458 not downloaded", "asset:data:geo:GSE43458 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE50081 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "Multivariate Cox regression analysis was conducted to identify independent prognostic factors."}}, {"id": "method-2", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 0.8, "band": "high", "quote": "Wilcoxon"}}, {"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": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Pearson correlation"}}, {"id": "method-5", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-6", "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-7", "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-8", "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-9", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}, {"id": "method-10", "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE33532", "GSE30219", "GSE43458", "GSE31210", "GSE50081"], "resolved_accessions": ["GSE33532", "GSE30219", "GSE43458", "GSE31210", "GSE50081"], "statements": ["The datasets of this study can be found in the Gene Expression Omnibus (GEO) repository (https://www.ncbi.nlm.nih.gov/gds/) and The Cancer Genome Atlas (https://www.ncbi.nlm.nih.gov/gds/)."], "basis": "The paper names GSE33532, GSE30219, GSE43458, GSE31210, GSE50081 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": ["cox_ph"], "assets": ["source:pmid:33879165", "data:geo:GSE30219", "asset:table:pmid:33879165:1", "asset:table:pmid:33879165:2", "asset:table:pmid:33879165:3", "asset:table:pmid:33879165:4", "asset:table:pmid:33879165:5"], "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": "2026-10-31T18:29:58Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 32622, "completion_tokens": 2346, "cached_tokens": 11136}}, "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:33879165", "type": "paper", "label": "pmid:33879165"}, {"id": "source:pmid:33879165", "type": "manuscript", "label": "PMID 33879165 full text"}, {"id": "data:geo:GSE30219", "type": "dataset", "label": "GEO GSE30219"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33879165", "type": "paper", "label": "pmid:33879165"}, {"id": "source:pmid:33879165", "type": "manuscript", "label": "PMID 33879165 full text"}, {"id": "data:geo:GSE30219", "type": "dataset", "label": "GEO GSE30219"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33879165", "type": "extraction", "used": ["source:pmid:33879165"], "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:33879165", "parent_hash": "sha256:5cf2aa2af50d39026115fbacef5bb101e98a62a6b8ecd6668ce58b59939955ca", "fork_of": null, "generation": 6}, "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:GSE33532 licence not read", "asset:data:geo:GSE33532 not downloaded", "asset:data:geo:GSE43458 licence not read", "asset:data:geo:GSE43458 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE50081 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": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["determine clinical effect of NEIL3 in LUAD. Western blotting (22 pairs of tumor and normal tissues), Real", "tive polymerase chain reaction (RT-qPCR) and western blotting. Fresh tissues were frozen in liquid nitroge", "irs of tumor and normal tissues were used in Western blotting, which statistical power is 0.8291. 19 pairs"], "order_basis": "paper_text_order:521", "id": "assay:1"}, {"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["ting (22 pairs of tumor and normal tissues), Real-time quantitative PCR (19 pairs of tumor and normal tissues), and", "time quantitative polymerase chain reaction (RT-qPCR) and western blotting. Fresh tissues were fr", "e quantitative polymerase chain reaction (RT-qPCR) and western blotting. Fresh tissues were fr"], "order_basis": "paper_text_order:577", "id": "assay:2"}, {"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": ["(19 pairs of tumor and normal tissues), and immunohistochemical analyses (406-tumor tissues subjected to mic", "vided into low and high expression groups by IHC-score and median expression level. The resul"], "order_basis": "paper_text_order:649", "id": "assay:3"}, {"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": ["cal analyses (406-tumor tissues subjected to microarray) were conducted. TIMER and ImmuCellAI analyz", "at − 80 °C until the experiment. LUAD tissue microarray and clinical data for 406 tumor samples and"], "order_basis": "paper_text_order:709", "id": "assay:4"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Multivariate Cox regression analysis was conducted to identify independent prognostic factors."], "order_basis": "consumes_earlier_output", "id": "assay:5"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T00:34:29+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}}}