{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39488588", "kind": "science-record", "revision": 3, "content_hash": "sha256:a6c5684769f53b343965ba337753f35e5cc1fd22193a7df63529a757d8a8412b", "created_at": "2026-11-01T20:29:44Z", "updated_at": "2026-11-01T22:13:03Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Five-gene prognostic model based on autophagy-dependent cell death for predicting prognosis in lung adenocarcinoma.", "doi": "10.1038/s41598-024-76186-3", "pmid": "39488588", "authors": ["Zhanshuo Zhang", "Pengpeng Zhang", "Jiping Xie", "Yuechen Cui", "Shuo Wang", "Dongsheng Yue"], "journal": "Scientific reports", "year": 2024, "abstract": "Non-small cell lung adenocarcinoma (LUAD) is the predominant form of lung cancer originating from lung epithelial cells, making it the most prevalent pathological type. Currently, reliable indicators for predicting treatment efficacy and disease prognosis are lacking. Despite extensive validation of autophagy-dependent cell death (ADCD) in solid tumor studies and its correlation with immunotherapy effectiveness and cancer prognosis, systematic research on ADCD-related genes in LUAD is limited. We utilized AddModuleScore, ssGSEA, and WGCNA to identify genes associated with ADCD across single-cell and bulk transcriptome datasets. The TCGA dataset, comprising 598 cases, was randomly divided into training and validation sets to develop an ADCD-related LUAD prediction model. Internal validation was performed using the TCGA validation set. For external validation, datasets GSE13213 (119 LUAD samples), GSE26939 (115 LUAD samples), GSE29016 (39 LUAD samples), and GSE30219 (86 LUAD samples) were employed. We evaluated the model's accuracy and effectiveness in predicting prognostic risk. Additionally, CIBERSORT, ESTIMATE, and ssGSEA techniques were used to explore immunological characteristics, drug response, and gene expression in LUAD. Real-time RT-PCR was conducted to assess variations in mRNA expression levels of the gene XCR1 between cancerous and normal tissues in 10 lung cancer patients. We identified 249 genes associated with autophagy-dependent cell death (ADCD) at both single-cell and bulk transcriptome levels. Univariate COX regression analysis revealed that 18 genes were significantly associated with overall survival (OS). Using LASSO-Cox analysis, we developed an ADCD signature based on five genes (BIRC3, TAP1, SLAMF1, XCR1, and HLA-DMB) and created the ADCD-related risk scoring system (ADCDRS). Validation of this model demonstrated its ability to predict disease prognosis and its correlation with clinical characteristics, immune cell infiltration, and the tumor microenvironment. To enhance clinical applicability, we integrated an ADCDRS nomogram. Furthermore, we identified potential drugs targeting specific risk subgroups. We successfully identified a model based on five ADCD genes to predict disease prognosis and treatment efficacy in LUAD, as well as to assess the tumor immune microenvironment. An efficient and practical ADCDRS nomogram was designed.", "claims": [{"id": "claim-method", "statement": "Using LASSO-Cox analysis, we developed an ADCD signature based on five genes (BIRC3, TAP1, SLAMF1, XCR1, and HLA-DMB) and created the ADCD-related risk scoring system (ADCDRS).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39488588", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Using LASSO-Cox analysis, we developed an ADCD signature based on five genes (BIRC3, TAP1, SLAMF1, XCR1, and HLA-DMB) and created the ADCD-related risk scoring system (ADCDRS)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39488588", "locator": "sections[32] \"Data availability\" paragraph 2", "quote": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We successfully identified a model based on five ADCD genes to predict disease prognosis and treatment efficacy in LUAD, as well as to assess the tumor immune microenvironment.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39488588", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We successfully identified a model based on five ADCD genes to predict disease prognosis and treatment efficacy in LUAD, as well as to assess the tumor immune microenvironment."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We successfully identified a model based on five ADCD genes to predict disease prognosis and treatment efficacy in LUAD, as well as to assess the tumor immune microenvironment.", "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:39488588"], "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:GSE13213"], "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:GSE13213"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39488588", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-024-76186-3", "sha256": "sha256:aa433e096a49a8f8866438432f9d27afd88fd158f500a20254a9392fcf8c84b5", "bytes": 71108, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-024-76186-3", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11531468", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13213", "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=GSE13213", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13213", "version": null, "note": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM333673", "GSM333674", "GSM333675", "GSM333676", "GSM333677", "GSM333678", "GSM333679", "GSM333680", "GSM333681", "GSM333682", "GSM333683", "GSM333684", "GSM333685", "GSM333686", "GSM333687", "GSM333688", "GSM333689", "GSM333690", "GSM333691", "GSM333692", "GSM333693", "GSM333694", "GSM333695", "GSM333696", "GSM333697", "GSM333698", "GSM333699", "GSM333700", "GSM333701", "GSM333702", "GSM333703", "GSM333704", "GSM333705", "GSM333706", "GSM333707", "GSM333708", "GSM333709", "GSM333710", "GSM333711", "GSM333712", "GSM333713", "GSM333714", "GSM333715", "GSM333716", "GSM333717", "GSM333718", "GSM333719", "GSM333720", "GSM333721", "GSM333722", "GSM333723", "GSM333724", "GSM333725", "GSM333726", "GSM333727", "GSM333728", "GSM333729", "GSM333730", "GSM333731", "GSM333732", "GSM333733", "GSM333734", "GSM333735", "GSM333736", "GSM333737", "GSM333738", "GSM333739", "GSM333740", "GSM333741", "GSM333742", "GSM333743", "GSM333744", "GSM333745", "GSM333746", "GSM333747", "GSM333748", "GSM333749", "GSM333750", "GSM333751", "GSM333752", "GSM333753", "GSM333754", "GSM333755", "GSM333756", "GSM333757", "GSM333758", "GSM333759", "GSM333760", "GSM333761", "GSM333762", "GSM333763", "GSM333764", "GSM333765", "GSM333766", "GSM333767", "GSM333768", "GSM333769", "GSM333770", "GSM333771", "GSM333772", "GSM333773", "GSM333774", "GSM333775", "GSM333776", "GSM333777", "GSM333778", "GSM333779", "GSM333780", "GSM333781", "GSM333782", "GSM333783", "GSM333784", "GSM333785", "GSM333786", "GSM333787", "GSM333788", "GSM333789"], "sample_count": 117, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Relapse-related molecular signature in lung adenocarcinomas identifies patients with dismal prognosis", "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:GSE26939", "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=GSE26939", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE26939", "version": null, "note": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM663284", "GSM663285", "GSM663286", "GSM663287", "GSM663288", "GSM663289", "GSM663290", "GSM663291", "GSM663292", "GSM663293", "GSM663294", "GSM663295", "GSM663296", "GSM663297", "GSM663298", "GSM663299", "GSM663300", "GSM663301", "GSM663302", "GSM663303", "GSM663304", "GSM663305", "GSM663306", "GSM663307", "GSM663308", "GSM663309", "GSM663310", "GSM663311", "GSM663312", "GSM663313", "GSM663314", "GSM663315", "GSM663316", "GSM663317", "GSM663318", "GSM663319", "GSM663320", "GSM663321", "GSM663322", "GSM663323", "GSM663324", "GSM663325", "GSM663326", "GSM663327", "GSM663328", "GSM663329", "GSM663330", "GSM663331", "GSM663332", "GSM663333", "GSM663334", "GSM663335", "GSM663336", "GSM663337", "GSM663338", "GSM663339", "GSM663340", "GSM663341", "GSM663342", "GSM663343", "GSM663344", "GSM663345", "GSM663346", "GSM663347", "GSM663348", "GSM663349", "GSM663350", "GSM663351", "GSM663352", "GSM663353", "GSM663354", "GSM663355", "GSM663356", "GSM663357", "GSM663358", "GSM663359", "GSM663360", "GSM663361", "GSM663362", "GSM663363", "GSM663364", "GSM663365", "GSM663366", "GSM663367", "GSM663368", "GSM663369", "GSM663370", "GSM663371", "GSM663372", "GSM663373", "GSM663374", "GSM663375", "GSM663376", "GSM663377", "GSM663378", "GSM663379", "GSM663380", "GSM663381", "GSM663382", "GSM663383", "GSM663384", "GSM663385", "GSM663386", "GSM663387", "GSM663388", "GSM663389", "GSM663390", "GSM663391", "GSM663392", "GSM663393", "GSM663394", "GSM663395", "GSM663396", "GSM663397", "GSM663398", "GSM663399"], "sample_count": 116, "group_sizes": null, "group_sizes_basis": null, "platform": "9053", "taxon": "Homo sapiens", "title": "Human lung adenocarcinoma mRNA expression and gene mutations.", "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:GSE29016", "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=GSE29016", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29016", "version": null, "note": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM718902", "GSM718903", "GSM718904", "GSM718905", "GSM718906", "GSM718907", "GSM718908", "GSM718909", "GSM718910", "GSM718911", "GSM718912", "GSM718913", "GSM718914", "GSM718915", "GSM718916", "GSM718917", "GSM718918", "GSM718919", "GSM718920", "GSM718921", "GSM718922", "GSM718923", "GSM718924", "GSM718925", "GSM718926", "GSM718927", "GSM718928", "GSM718929", "GSM718930", "GSM718931", "GSM718932", "GSM718933", "GSM718934", "GSM718935", "GSM718936", "GSM718937", "GSM718938", "GSM718939", "GSM718940", "GSM718941", "GSM718942", "GSM718943", "GSM718944", "GSM718945", "GSM718946", "GSM718947", "GSM718948", "GSM718949", "GSM718950", "GSM718951", "GSM718952", "GSM718953", "GSM718954", "GSM718955", "GSM718956", "GSM718957", "GSM718958", "GSM718959", "GSM718960", "GSM718961", "GSM718962", "GSM718963", "GSM718964", "GSM718965", "GSM718966", "GSM718967", "GSM718968", "GSM718969", "GSM718970", "GSM718971", "GSM718972", "GSM718973"], "sample_count": 72, "group_sizes": null, "group_sizes_basis": null, "platform": "6947", "taxon": "Homo sapiens", "title": "Relation between smoking history and gene expression profiles in lung adenocarcinomas", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"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 GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes.", "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}}], "gaps": ["asset:data:geo:GSE13213 not downloaded", "asset:data:geo:GSE13213 licence not read", "asset:data:geo:GSE26939 not downloaded", "asset:data:geo:GSE26939 licence not read", "asset:data:geo:GSE29016 not downloaded", "asset:data:geo:GSE29016 licence not read", "asset:data:geo:GSE30219 not downloaded", "asset:data:geo:GSE30219 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": "Using LASSO-Cox analysis, we developed an ADCD signature based on five genes (BIRC3, TAP1, SLAMF1, XCR1, and HLA-DMB) and created the ADCD-related risk scoring system (ADCDRS)."}}, {"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": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-4", "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-5", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "PCA"}}, {"id": "method-6", "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-7", "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 curve"}}, {"id": "method-8", "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": ["GSE13213", "GSE26939", "GSE29016", "GSE30219"], "resolved_accessions": ["GSE13213", "GSE26939", "GSE29016", "GSE30219"], "statements": ["The GSE13213, GSE26939, GSE29016, and GSE30219 datasets from the Gene Expression Omnibus were acquired through the provided link [https://www.ncbi.nlm.nih.gov/geo/]. The datasets analyzed during the current study are available in The Cancer Genome Atlas repository, [https://portal.gdc.cancer.gov/projects/TCGA-LUAD]. The single-cell dataset HRA001130 from the Genome Sequence Archive (GSA) at the Beijing Institute of Genomics (BIG) Data Center was acquired through the provided link [http://bigd.big.ac.cn]. The datasets analyzed during the current study are available from the corresponding author upon reasonable request. Other data can be requested from the corresponding author for reasonable purposes."], "basis": "The paper names GSE13213, GSE26939, GSE29016, GSE30219 in Gene Expression Omnibus 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:39488588", "data:geo:GSE13213"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13213"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:37:26Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 17645, "completion_tokens": 3111, "cached_tokens": 264}}, "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:39488588", "type": "paper", "label": "pmid:39488588"}, {"id": "source:pmid:39488588", "type": "manuscript", "label": "PMID 39488588 full text"}, {"id": "data:geo:GSE13213", "type": "dataset", "label": "GEO GSE13213"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39488588", "type": "paper", "label": "pmid:39488588"}, {"id": "source:pmid:39488588", "type": "manuscript", "label": "PMID 39488588 full text"}, {"id": "data:geo:GSE13213", "type": "dataset", "label": "GEO GSE13213"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39488588", "type": "extraction", "used": ["source:pmid:39488588"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13213", "type": "accession_resolution", "used": ["data:geo:GSE13213"], "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:39488588", "parent_hash": "sha256:9d0ff221e323d693e6cf385a01c22847c4eec696c9845fc6031faa33ebf3a83e", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE13213 licence not read", "asset:data:geo:GSE13213 not downloaded", "asset:data:geo:GSE26939 licence not read", "asset:data:geo:GSE26939 not downloaded", "asset:data:geo:GSE29016 licence not read", "asset:data:geo:GSE29016 not downloaded", "asset:data:geo:GSE30219 licence not read", "asset:data:geo:GSE30219 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": "cell_culture", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["hinese Academy of Sciences. These cells were cultured in RPMI-1640 medium supplemented with 10% fetal", "nd two human lung adenocarcinoma cell lines (A549 and PC9), were sourced from the Cell Bank of", "e in normal cells (BEAS-2B) and tumor cells (A549, PC9). (b) Expression of XCR1 gene in 10 pai"], "order_basis": "paper_text_order:4279", "id": "assay:1"}, {"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": ["Using LASSO-Cox analysis, we developed an ADCD signature based on five genes (BIRC3, TAP1, SLAMF1, XCR1, and HLA-DMB) and created the ADCD-related risk scoring system (ADCDRS)."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:12:16+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}}}