Development and validation of machine learning models for diagnosis and prognosis of lung adenocarcinoma, and immune infiltration analysis.

{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39333719", "kind": "science-record", "revision": 3, "content_hash": "sha256:51a5670f426b0c254feb16f3391d6dcc0e28dfe909dd5f51c256cb27a8440151", "created_at": "2026-11-01T20:29:31Z", "updated_at": "2026-11-01T22:12:47Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development and validation of machine learning models for diagnosis and prognosis of lung adenocarcinoma, and immune infiltration analysis.", "doi": "10.1038/s41598-024-73498-2", "pmid": "39333719", "authors": ["Lin Lin", "Yongxia Bao"], "journal": "Scientific reports", "year": 2024, "abstract": "The aim of our study was to develop robust diagnostic and prognostic models for lung adenocarcinoma (LUAD) using machine learning (ML) techniques, focusing on early immune infiltration. Feature selection was performed on The Cancer Genome Atlas (TCGA) data using least absolute shrinkage and selection Operator (LASSO), random forest (RF), and support vector machine (SVM) algorithms. Six ML algorithms were employed to construct the diagnostic models, which were evaluated through receiver operating characteristic (ROC) curves, precision-recall curves (PRC), and classification error (CE), and validated on the GSE7670 dataset. Additionally, a lasso cox prognostic model was built on the TCGA-LUAD dataset and externally validated using independent Gene Expression Omnibus datasets (GSE30219, GSE31210, GSE50081, and GSE37745). Single-sample gene set enrichment analysis (ssGSEA) was performed to assess immune cell infiltration in stage I LUAD samples, revealing significant differences in immune cell types. These findings demonstrate a positive correlation between immune infiltration in stage I LUAD and Th2 cells, Tcm cells, and T helper cells, while a negative correlation was observed with Macrophages, Eosinophils, and Tem cells. These insights provide novel perspectives for clinical diagnosis and treatment of LUAD.", "claims": [{"id": "claim-method", "statement": "Six ML algorithms were employed to construct the diagnostic models, which were evaluated through receiver operating characteristic (ROC) curves, precision-recall curves (PRC), and classification error (CE), and validated on the GSE7670 dataset.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39333719", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Six ML algorithms were employed to construct the diagnostic models, which were evaluated through receiver operating characteristic (ROC) curves, precision-recall curves (PRC), and classification error (CE), and validated on the GSE7670 dataset."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39333719", "locator": "sections[27] \"notes\" paragraph 1", "quote": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation."}], "state": "complete"}, {"id": "claim-target-result", "statement": "KNN, RF, and SVM were the recommended diagnostic models, achieving AUC and PRAUC scores of 1.0000000 in both the training and testing sets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39333719", "locator": "sections[5] \"Comparison of six ML diagnostic models\" paragraph 2", "quote": "This study evaluated various mRNA ML models and found that KNN, RF and SVM performed exceptionally well, achieving AUC and PRAUC scores of 1.0000000 on both training and testing sets, emphasizing their advantages in data fitting and generalization."}, {"asset": "source:pmid:39333719", "locator": "sections[5] \"Comparison of six ML diagnostic models\" paragraph 2", "quote": "In summary, the study recommends prioritizing KNN, RF, and SVM, while recognizing NB as a viable alternative."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "KNN, RF, and SVM were the recommended diagnostic models, achieving AUC and PRAUC scores of 1.0000000 in both the training and testing sets.", "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:39333719"], "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": "blocked", "blocked_on": "method:machine_learning_random_forest", "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": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39333719", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1038/s41598-024-73498-2", "sha256": "sha256:13611133586893832c7cc7f8600df807593f82235e7858a1e73f0e7951fcae22", "bytes": 59423, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1038/s41598-024-73498-2", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11437281", "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 data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "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 data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "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:GSE37745", "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=GSE37745", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE37745", "version": null, "note": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1019138", "GSM1019139", "GSM1019140", "GSM1019141", "GSM1019142", "GSM1019143", "GSM1019144", "GSM1019145", "GSM1019146", "GSM1019147", "GSM1019148", "GSM1019149", "GSM1019150", "GSM1019151", "GSM1019152", "GSM1019153", "GSM1019154", "GSM1019155", "GSM1019156", "GSM1019157", "GSM1019158", "GSM1019159", "GSM1019160", "GSM1019161", "GSM1019162", "GSM1019163", "GSM1019164", "GSM1019165", "GSM1019166", "GSM1019167", "GSM1019168", "GSM1019169", "GSM1019170", "GSM1019171", "GSM1019172", "GSM1019173", "GSM1019174", "GSM1019175", "GSM1019176", "GSM1019177", "GSM1019178", "GSM1019179", "GSM1019180", "GSM1019181", "GSM1019182", "GSM1019183", "GSM1019184", "GSM1019185", "GSM1019186", "GSM1019187", "GSM1019188", "GSM1019189", "GSM1019190", "GSM1019191", "GSM1019192", "GSM1019193", "GSM1019194", "GSM1019195", "GSM1019196", "GSM1019197", "GSM1019198", "GSM1019199", "GSM1019200", "GSM1019201", "GSM1019202", "GSM1019203", "GSM1019204", "GSM1019205", "GSM1019206", "GSM1019207", "GSM1019208", "GSM1019209", "GSM1019210", "GSM1019211", "GSM1019212", "GSM1019213", "GSM1019214", "GSM1019215", "GSM1019216", "GSM1019217", "GSM1019218", "GSM1019219", "GSM1019220", "GSM1019221", "GSM1019222", "GSM1019223", "GSM1019224", "GSM1019225", "GSM1019226", "GSM1019227", "GSM1019228", "GSM1019229", "GSM1019230", "GSM1019231", "GSM1019232", "GSM1019233", "GSM1019234", "GSM1019235", "GSM1019236", "GSM1019237", "GSM1019238", "GSM1019239", "GSM1019240", "GSM1019241", "GSM1019242", "GSM1019243", "GSM1019244", "GSM1019245", "GSM1019246", "GSM1019247", "GSM1019248", "GSM1019249", "GSM1019250", "GSM1019251", "GSM1019252", "GSM1019253", "GSM1019254", "GSM1019255", "GSM1019256", "GSM1019257", "GSM1019258", "GSM1019259", "GSM1019260", "GSM1019261", "GSM1019262", "GSM1019263", "GSM1019264", "GSM1019265", "GSM1019266", "GSM1019267", "GSM1019268", "GSM1019269", "GSM1019270", "GSM1019271", "GSM1019272", "GSM1019273", "GSM1019274", "GSM1019275", "GSM1019276", "GSM1019277", "GSM1019278", "GSM1019279", "GSM1019280", "GSM1019281", "GSM1019282", "GSM1019283", "GSM1019284", "GSM1019285", "GSM1019286", "GSM1019287", "GSM1019288", "GSM1019289", "GSM1019290", "GSM1019291", "GSM1019292", "GSM1019293", "GSM1019294", "GSM1019295", "GSM1019296", "GSM1019297", "GSM1019298", "GSM1019299", "GSM1019300", "GSM1019301", "GSM1019302", "GSM1019303", "GSM1019304", "GSM1019305", "GSM1019306", "GSM1019307", "GSM1019308", "GSM1019309", "GSM1019310", "GSM1019311", "GSM1019312", "GSM1019313", "GSM1019314", "GSM1019315", "GSM1019316", "GSM1019317", "GSM1019318", "GSM1019319", "GSM1019320", "GSM1019321", "GSM1019322", "GSM1019323", "GSM1019324", "GSM1019325", "GSM1019326", "GSM1019327", "GSM1019328", "GSM1019329", "GSM1019330", "GSM1019331", "GSM1019332", "GSM1019333"], "sample_count": 196, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Biomarker discovery in non-small cell lung cancer: integrating gene expression profiling, meta-analysis and tissue microarray validation", "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 data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1213669", "GSM1213670", "GSM1213671", "GSM1213672", "GSM1213673", "GSM1213674", "GSM1213675", "GSM1213676", "GSM1213677", "GSM1213678", "GSM1213679", "GSM1213680", "GSM1213681", "GSM1213682", "GSM1213683", "GSM1213684", "GSM1213685", "GSM1213686", "GSM1213687", "GSM1213688", "GSM1213689", "GSM1213690", "GSM1213691", "GSM1213692", "GSM1213693", "GSM1213694", "GSM1213695", "GSM1213696", "GSM1213697", "GSM1213698", "GSM1213699", "GSM1213700", "GSM1213701", "GSM1213702", "GSM1213703", "GSM1213704", "GSM1213705", "GSM1213706", "GSM1213707", "GSM1213708", "GSM1213709", "GSM1213710", "GSM1213711", "GSM1213712", "GSM1213713", "GSM1213714", "GSM1213715", "GSM1213716", "GSM1213717", "GSM1213718", "GSM1213719", "GSM1213720", "GSM1213721", "GSM1213722", "GSM1213723", "GSM1213724", "GSM1213725", "GSM1213726", "GSM1213727", "GSM1213728", "GSM1213729", "GSM1213730", "GSM1213731", "GSM1213732", "GSM1213733", "GSM1213734", "GSM1213735", "GSM1213736", "GSM1213737", "GSM1213738", "GSM1213739", "GSM1213740", "GSM1213741", "GSM1213742", "GSM1213743", "GSM1213744", "GSM1213745", "GSM1213746", "GSM1213747", "GSM1213748", "GSM1213749", "GSM1213750", "GSM1213751", "GSM1213752", "GSM1213753", "GSM1213754", "GSM1213755", "GSM1213756", "GSM1213757", "GSM1213758", "GSM1213759", "GSM1213760", "GSM1213761", "GSM1213762", "GSM1213763", "GSM1213764", "GSM1213765", "GSM1213766", "GSM1213767", "GSM1213768", "GSM1213769", "GSM1213770", "GSM1213771", "GSM1213772", "GSM1213773", "GSM1213774", "GSM1213775", "GSM1213776", "GSM1213777", "GSM1213778", "GSM1213779", "GSM1213780", "GSM1213781", "GSM1213782", "GSM1213783", "GSM1213784", "GSM1213785", "GSM1213786", "GSM1213787", "GSM1213788", "GSM1213789", "GSM1213790", "GSM1213791", "GSM1213792", "GSM1213793", "GSM1213794", "GSM1213795", "GSM1213796", "GSM1213797", "GSM1213798", "GSM1213799", "GSM1213800", "GSM1213801", "GSM1213802", "GSM1213803", "GSM1213804", "GSM1213805", "GSM1213806", "GSM1213807", "GSM1213808", "GSM1213809", "GSM1213810", "GSM1213811", "GSM1213812", "GSM1213813", "GSM1213814", "GSM1213815", "GSM1213816", "GSM1213817", "GSM1213818", "GSM1213819", "GSM1213820", "GSM1213821", "GSM1213822", "GSM1213823", "GSM1213824", "GSM1213825", "GSM1213826", "GSM1213827", "GSM1213828", "GSM1213829", "GSM1213830", "GSM1213831", "GSM1213832", "GSM1213833", "GSM1213834", "GSM1213835", "GSM1213836", "GSM1213837", "GSM1213838", "GSM1213839", "GSM1213840", "GSM1213841", "GSM1213842", "GSM1213843", "GSM1213844", "GSM1213845", "GSM1213846", "GSM1213847", "GSM1213848", "GSM1213849"], "sample_count": 181, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Validation of a histology-independent prognostic gene signature for early stage, non-small cell lung cancer including stage IA patients", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE7670", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE7670", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE7670", "version": null, "note": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM185811", "GSM185812", "GSM185813", "GSM185814", "GSM185815", "GSM185816", "GSM185817", "GSM185818", "GSM185819", "GSM185820", "GSM185821", "GSM185822", "GSM185823", "GSM185824", "GSM185825", "GSM185826", "GSM185827", "GSM185828", "GSM185829", "GSM185830", "GSM185831", "GSM185832", "GSM185833", "GSM185834", "GSM185835", "GSM185836", "GSM185837", "GSM185838", "GSM185839", "GSM185840", "GSM185841", "GSM185842", "GSM185843", "GSM185844", "GSM185845", "GSM185846", "GSM185847", "GSM185848", "GSM185849", "GSM185850", "GSM185851", "GSM185852", "GSM185853", "GSM185854", "GSM185855", "GSM185856", "GSM185857", "GSM185858", "GSM185859", "GSM185860", "GSM185861", "GSM185862", "GSM185863", "GSM185864", "GSM185865", "GSM185866", "GSM185867", "GSM185868", "GSM185869", "GSM185870", "GSM185871", "GSM185872", "GSM185873", "GSM185874", "GSM185875", "GSM185876"], "sample_count": 66, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Expression data from Lung cancer", "resolution_checked_at": "2026-11-01T15:14:33Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "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:GSE37745 not downloaded", "asset:data:geo:GSE37745 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE7670 not downloaded", "asset:data:geo:GSE7670 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "support vector machine"}}, {"id": "method-3", "family": null, "specific": null, "label": "Six machine-learning algorithms evaluated through receiver operating characteristic curves, precision-recall curves, and classification error", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Six ML algorithms were employed to construct the diagnostic models, which were evaluated through receiver operating characteristic (ROC) curves, precision-recall curves (PRC), and classification error (CE), and validated on the GSE7670 dataset."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.machine_learning_random_forest"]}, "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": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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": ["GSE7670", "GSE30219", "GSE31210", "GSE50081", "GSE37745"], "resolved_accessions": ["GSE7670", "GSE30219", "GSE31210", "GSE50081", "GSE37745"], "statements": ["The data involved in this study are primarily sourced from two public databases: the TCGA Data Portal and the NCBI GEO Database. The following are the access methods for these data sources. For TCGA data, we utilized datasets provided by the Cancer Genome Atlas (TCGA) project. Readers can access the relevant data by visiting the official TCGA Data Portal at the following URL: https://portal.gdc.cancer.gov/ For gene expression data, we also utilized the NCBI Gene Expression Omnibus (GEO) Database. The complete URL strings for the GEO datasets used in this study are as follows: GSE7670: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE7670 GSE30219: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE30219 GSE31210: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE31210 GSE50081: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE50081 GSE37745: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc = GSE37745 These GEO datasets contain rich gene expression data, which are crucial for validating the conclusions of this study. Readers can directly copy the above URL strings into their browsers to access the corresponding pages on the GEO Database, view detailed descriptions of the datasets, download raw data, and obtain related analysis tools and documentation."], "basis": "The paper names GSE7670, GSE30219, GSE31210, GSE50081, GSE37745 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": [], "assets": ["source:pmid:39333719", "data:geo:GSE30219"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "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": "2026-11-01T19:33:20Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 16145, "completion_tokens": 2674, "cached_tokens": 256}}, "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:39333719", "type": "paper", "label": "pmid:39333719"}, {"id": "source:pmid:39333719", "type": "manuscript", "label": "PMID 39333719 full text"}, {"id": "data:geo:GSE30219", "type": "dataset", "label": "GEO GSE30219"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39333719", "type": "paper", "label": "pmid:39333719"}, {"id": "source:pmid:39333719", "type": "manuscript", "label": "PMID 39333719 full text"}, {"id": "data:geo:GSE30219", "type": "dataset", "label": "GEO GSE30219"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39333719", "type": "extraction", "used": ["source:pmid:39333719"], "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:39333719", "parent_hash": "sha256:5e06627b1ae6591be318df79f1842c14d0b958a0c26a65b53461e9257a70a7d1", "fork_of": null, "generation": 2}, "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:GSE37745 licence not read", "asset:data:geo:GSE37745 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE7670 licence not read", "asset:data:geo:GSE7670 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["random forest"], "order_basis": "analysis_only", "id": "assay:1"}]}