{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:35830566", "kind": "science-record", "revision": 4, "content_hash": "sha256:14b77c7e121138ef40e54dbc7912010e419b614d6f904af91fce0eae9f89f821", "created_at": "2026-11-01T18:14:53Z", "updated_at": "2026-11-01T22:07:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "A novel prognostic signature of metastasis-associated genes and personalized therapeutic strategy for lung adenocarcinoma patients.", "doi": "10.18632/aging.204169", "pmid": "35830566", "authors": ["Zhihao Wang", "Yusi Liu", "Xiaoqian Zhan", "Xi Wang", "Chao Zhang", "Lingzhi Qin", "Liwei Liu", "Shenghui Qin"], "journal": "Aging", "year": 2022, "abstract": "Lung adenocarcinoma (LUAD) is a highly invasive and metastatic malignant tumor with high morbidity and mortality. This study aimed to construct a prognostic signature for LUAD patients based on metastasis-associated genes (MAGs). RNA expression profiles were downloaded from the Cancer Genome Atlas (TCGA) database. RRA method was applied to identify differentially expressed MAGs. A total of 192 significantly robust MAGs were determined among seven GEO datasets. MAGs were initially selected through the Lasso Cox regression analysis and 6 MAGs were included to construct a prognostic signature model. Transcriptome profile, patient prognosis, correlation between the risk score and clinicopathological features, immune cell infiltration characteristics, immunotherapy sensitivity and chemotherapy sensitivity differed between low- and high-risk groups after grouping according to median risk score. The reliability and applicability of the signature were further validated in the GSE31210, GSE50081 and GSE68465 cohort. CMap predicted 62 small molecule drugs on the base of the prognostic MAGs. Targeted drug staurosporine had hydrogen bonding with Gln-172 of SLC2A1, which is one of MAGs. Staurosporine could inhibit cell migration in A549 and H1299. We further verified mRNA and protein expression of 6 MAGs in A549 and H1299. The signature can serve as a promising prognostic tool and may provide a novel personalized therapeutic strategy for LUAD patients.", "claims": [{"id": "claim-method", "statement": "RobustRankAggreg (RRA) method was used to obtain robust MAGs that were ranked consistently better than expected by chance with the R package RRA [42].", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35830566", "locator": "sections[15] \"Identification and enrichment analysis of differentially expressed MAGs\" paragraph 2", "quote": "RobustRankAggreg (RRA) method was used to obtain robust MAGs that were ranked consistently better than expected by chance with the R package RRA [42]."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:35830566", "locator": "sections[21] \"ACKNOWLEDGMENTS\" paragraph 2", "quote": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A total of 192 significantly robust metastasis-associated genes were determined among seven GEO datasets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:35830566", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A total of 192 significantly robust MAGs were determined among seven GEO datasets."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A total of 192 significantly robust metastasis-associated genes were determined among seven GEO datasets.", "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:35830566"], "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:GSE10072"], "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:GSE10072"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:35830566", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.18632/aging.204169", "sha256": "sha256:0e788a8ab856b65b78328e88b25a1e2d63004c365aa75ae4d868f001d25a89c8", "bytes": 45613, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.18632/aging.204169", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC9320549", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10072", "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=GSE10072", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10072", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM254625", "GSM254626", "GSM254627", "GSM254628", "GSM254629", "GSM254630", "GSM254631", "GSM254632", "GSM254633", "GSM254634", "GSM254635", "GSM254636", "GSM254637", "GSM254638", "GSM254639", "GSM254640", "GSM254641", "GSM254642", "GSM254643", "GSM254644", "GSM254645", "GSM254646", "GSM254647", "GSM254648", "GSM254649", "GSM254650", "GSM254651", "GSM254652", "GSM254653", "GSM254654", "GSM254655", "GSM254656", "GSM254657", "GSM254658", "GSM254659", "GSM254660", "GSM254661", "GSM254662", "GSM254663", "GSM254664", "GSM254665", "GSM254666", "GSM254667", "GSM254668", "GSM254669", "GSM254670", "GSM254671", "GSM254672", "GSM254673", "GSM254674", "GSM254675", "GSM254676", "GSM254677", "GSM254678", "GSM254679", "GSM254680", "GSM254681", "GSM254682", "GSM254683", "GSM254684", "GSM254685", "GSM254686", "GSM254687", "GSM254688", "GSM254689", "GSM254690", "GSM254691", "GSM254692", "GSM254693", "GSM254694", "GSM254695", "GSM254696", "GSM254697", "GSM254698", "GSM254699", "GSM254700", "GSM254701", "GSM254702", "GSM254703", "GSM254704", "GSM254705", "GSM254706", "GSM254707", "GSM254708", "GSM254709", "GSM254710", "GSM254711", "GSM254712", "GSM254713", "GSM254714", "GSM254715", "GSM254716", "GSM254717", "GSM254718", "GSM254719", "GSM254720", "GSM254721", "GSM254722", "GSM254723", "GSM254724", "GSM254725", "GSM254726", "GSM254727", "GSM254728", "GSM254729", "GSM254730", "GSM254731"], "sample_count": 107, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Gene expression signature of cigarette smoking and its role in lung adenocarcinoma development and survival", "resolution_checked_at": "2026-11-01T15:30:21Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE126044", "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=GSE126044", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE126044", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3589673", "GSM3589674", "GSM3589675", "GSM3589676", "GSM3589677", "GSM3589678", "GSM3589679", "GSM3589680", "GSM3589681", "GSM3589682", "GSM3589683", "GSM3589684", "GSM3589685", "GSM3589686", "GSM3589687", "GSM3589688"], "sample_count": 16, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Genome-wide identification of differentially methylated promoters and enhancers associated with response to anti-PD-1 therapy in non-small cell lung cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE135222", "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=GSE135222", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE135222", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3995402", "GSM3995403", "GSM3995404", "GSM3995405", "GSM3995406", "GSM3995407", "GSM3995408", "GSM3995409", "GSM3995410", "GSM3995411", "GSM3995412", "GSM3995413", "GSM3995414", "GSM3995415", "GSM3995416", "GSM3995417", "GSM3995418", "GSM3995419", "GSM3995420", "GSM3995421", "GSM3995422", "GSM3995423", "GSM3995424", "GSM3995425", "GSM3995426", "GSM3995427", "GSM3995428"], "sample_count": 27, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "DNA methylation loss coupled with mitotic cell division promotes immune evasion of tumours with high mutation load [RNA-seq]", "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:GSE18842", "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=GSE18842", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE18842", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM466947", "GSM466948", "GSM466949", "GSM466950", "GSM466951", "GSM466952", "GSM466953", "GSM466954", "GSM466955", "GSM466956", "GSM466957", "GSM466958", "GSM466959", "GSM466960", "GSM466961", "GSM466962", "GSM466963", "GSM466964", "GSM466965", "GSM466966", "GSM466967", "GSM466968", "GSM466969", "GSM466970", "GSM466971", "GSM466972", "GSM466973", "GSM466974", "GSM466975", "GSM466976", "GSM466977", "GSM466978", "GSM466979", "GSM466980", "GSM466981", "GSM466982", "GSM466983", "GSM466984", "GSM466985", "GSM466986", "GSM466987", "GSM466988", "GSM466989", "GSM466990", "GSM466991", "GSM466992", "GSM466993", "GSM466994", "GSM466995", "GSM466996", "GSM466997", "GSM466998", "GSM466999", "GSM467000", "GSM467001", "GSM467002", "GSM467003", "GSM467004", "GSM467005", "GSM467006", "GSM467007", "GSM467008", "GSM467009", "GSM467010", "GSM467011", "GSM467012", "GSM467013", "GSM467014", "GSM467015", "GSM467016", "GSM467017", "GSM467018", "GSM467019", "GSM467020", "GSM467021", "GSM467022", "GSM467023", "GSM467024", "GSM467025", "GSM467026", "GSM467027", "GSM467028", "GSM467029", "GSM467030", "GSM467031", "GSM467032", "GSM467033", "GSM467034", "GSM467035", "GSM467036", "GSM467037"], "sample_count": 91, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression analysis of human lung cancer and control samples", "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": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "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:GSE31320", "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=GSE31320", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31320", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM776555", "GSM776556", "GSM776557", "GSM776558", "GSM776559"], "sample_count": 5, "group_sizes": null, "group_sizes_basis": null, "platform": "9115", "taxon": "Homo sapiens", "title": "Genome-wide identification of functional elements regulated by T-bet and GATA3 in human T-cells", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE32863", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32863", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32863", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM813411", "GSM813412", "GSM813413", "GSM813414", "GSM813415", "GSM813416", "GSM813417", "GSM813418", "GSM813419", "GSM813420", "GSM813421", "GSM813422", "GSM813423", "GSM813424", "GSM813425", "GSM813426", "GSM813427", "GSM813428", "GSM813429", "GSM813430", "GSM813431", "GSM813432", "GSM813433", "GSM813434", "GSM813435", "GSM813436", "GSM813437", "GSM813438", "GSM813439", "GSM813440", "GSM813441", "GSM813442", "GSM813443", "GSM813444", "GSM813445", "GSM813446", "GSM813447", "GSM813448", "GSM813449", "GSM813450", "GSM813451", "GSM813452", "GSM813453", "GSM813454", "GSM813455", "GSM813456", "GSM813457", "GSM813458", "GSM813459", "GSM813460", "GSM813461", "GSM813462", "GSM813463", "GSM813464", "GSM813465", "GSM813466", "GSM813467", "GSM813468", "GSM813469", "GSM813470", "GSM813471", "GSM813472", "GSM813473", "GSM813474", "GSM813475", "GSM813476", "GSM813477", "GSM813478", "GSM813479", "GSM813480", "GSM813481", "GSM813482", "GSM813483", "GSM813484", "GSM813485", "GSM813486", "GSM813487", "GSM813488", "GSM813489", "GSM813490", "GSM813491", "GSM813492", "GSM813493", "GSM813494", "GSM813495", "GSM813496", "GSM813497", "GSM813498", "GSM813499", "GSM813500", "GSM813501", "GSM813502", "GSM813503", "GSM813504", "GSM813505", "GSM813506", "GSM813507", "GSM813508", "GSM813509", "GSM813510", "GSM813511", "GSM813512", "GSM813513", "GSM813514", "GSM813515", "GSM813516", "GSM813517", "GSM813518", "GSM813519", "GSM813520", "GSM813521", "GSM813522", "GSM813523", "GSM813524", "GSM813525", "GSM813526"], "sample_count": 116, "group_sizes": null, "group_sizes_basis": null, "platform": "6884", "taxon": "Homo sapiens", "title": "Gene expression analysis of lung adenocarcinoma and matched adjacent non-tumor lung tissue", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE40791", "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=GSE40791", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE40791", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1001510", "GSM1001511", "GSM1001512", "GSM1001513", "GSM1001514", "GSM1001515", "GSM1001516", "GSM1001517", "GSM1001518", "GSM1001519", "GSM1001520", "GSM1001521", "GSM1001522", "GSM1001523", "GSM1001524", "GSM1001525", "GSM1001526", "GSM1001527", "GSM1001528", "GSM1001529", "GSM1001530", "GSM1001531", "GSM1001532", "GSM1001533", "GSM1001534", "GSM1001535", "GSM1001536", "GSM1001537", "GSM1001538", "GSM1001539", "GSM1001540", "GSM1001541", "GSM1001542", "GSM1001543", "GSM1001544", "GSM1001545", "GSM1001546", "GSM1001547", "GSM1001548", "GSM1001549", "GSM1001550", "GSM1001551", "GSM1001552", "GSM1001553", "GSM1001554", "GSM1001555", "GSM1001556", "GSM1001557", "GSM1001558", "GSM1001559", "GSM1001560", "GSM1001561", "GSM1001562", "GSM1001563", "GSM1001564", "GSM1001565", "GSM1001566", "GSM1001567", "GSM1001568", "GSM1001569", "GSM1001570", "GSM1001571", "GSM1001572", "GSM1001573", "GSM1001574", "GSM1001575", "GSM1001576", "GSM1001577", "GSM1001578", "GSM1001579", "GSM1001580", "GSM1001581", "GSM1001582", "GSM1001583", "GSM1001584", "GSM1001585", "GSM1001586", "GSM1001587", "GSM1001588", "GSM1001589", "GSM1001590", "GSM1001591", "GSM1001592", "GSM1001593", "GSM1001594", "GSM1001595", "GSM1001596", "GSM1001597", "GSM1001598", "GSM1001599", "GSM1001600", "GSM1001601", "GSM1001602", "GSM1001603", "GSM1001604", "GSM1001605", "GSM1001606", "GSM1001607", "GSM1001608", "GSM1001609", "GSM1001610", "GSM1001611", "GSM1001612", "GSM1001613", "GSM1001614", "GSM1001615", "GSM1001616", "GSM1001617", "GSM1001618", "GSM1001619", "GSM1001620", "GSM1001621", "GSM1001622", "GSM1001623", "GSM1001624", "GSM1001625", "GSM1001626", "GSM1001627", "GSM1001628", "GSM1001629", "GSM1001630", "GSM1001631", "GSM1001632", "GSM1001633", "GSM1001634", "GSM1001635", "GSM1001636", "GSM1001637", "GSM1001638", "GSM1001639", "GSM1001640", "GSM1001641", "GSM1001642", "GSM1001643", "GSM1001644", "GSM1001645", "GSM1001646", "GSM1001647", "GSM1001648", "GSM1001649", "GSM1001650", "GSM1001651", "GSM1001652", "GSM1001653", "GSM1001654", "GSM1001655", "GSM1001656", "GSM1001657", "GSM1001658", "GSM1001659", "GSM1001660", "GSM1001661", "GSM1001662", "GSM1001663", "GSM1001664", "GSM1001665", "GSM1001666", "GSM1001667", "GSM1001668", "GSM1001669", "GSM1001670", "GSM1001671", "GSM1001672", "GSM1001673", "GSM1001674", "GSM1001675", "GSM1001676", "GSM1001677", "GSM1001678", "GSM1001679", "GSM1001680", "GSM1001681", "GSM1001682", "GSM1001683", "GSM1001684", "GSM1001685", "GSM1001686", "GSM1001687", "GSM1001688", "GSM1001689", "GSM1001690", "GSM1001691", "GSM1001692", "GSM1001693", "GSM1001694", "GSM1001695", "GSM1001696", "GSM1001697", "GSM1001698", "GSM1001699", "GSM1001700", "GSM1001701", "GSM1001702", "GSM1001703"], "sample_count": 194, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Usp44 binds centrin to regulate centrosome positioning and suppress tumorigenesis", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE43458", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE43458", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE43458", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1062765", "GSM1062766", "GSM1062767", "GSM1062768", "GSM1062769", "GSM1062770", "GSM1062771", "GSM1062772", "GSM1062773", "GSM1062774", "GSM1062775", "GSM1062776", "GSM1062777", "GSM1062778", "GSM1062779", "GSM1062780", "GSM1062781", "GSM1062782", "GSM1062783", "GSM1062784", "GSM1062785", "GSM1062786", "GSM1062787", "GSM1062788", "GSM1062789", "GSM1062790", "GSM1062791", "GSM1062792", "GSM1062793", "GSM1062794", "GSM1062795", "GSM1062796", "GSM1062797", "GSM1062798", "GSM1062799", "GSM1062800", "GSM1062801", "GSM1062802", "GSM1062803", "GSM1062804", "GSM1062805", "GSM1062806", "GSM1062807", "GSM1062808", "GSM1062809", "GSM1062810", "GSM1062811", "GSM1062812", "GSM1062813", "GSM1062814", "GSM1062815", "GSM1062816", "GSM1062817", "GSM1062818", "GSM1062819", "GSM1062820", "GSM1062821", "GSM1062822", "GSM1062823", "GSM1062824", "GSM1062825", "GSM1062826", "GSM1062827", "GSM1062828", "GSM1062829", "GSM1062830", "GSM1062831", "GSM1062832", "GSM1062833", "GSM1062834", "GSM1062835", "GSM1062836", "GSM1062837", "GSM1062838", "GSM1062839", "GSM1062840", "GSM1062841", "GSM1062842", "GSM1062843", "GSM1062844", "GSM1062845", "GSM1062846", "GSM1062847", "GSM1062848", "GSM1062849", "GSM1062850", "GSM1062851", "GSM1062852", "GSM1062853", "GSM1062854", "GSM1062855", "GSM1062856", "GSM1062857", "GSM1062858", "GSM1062859", "GSM1062860", "GSM1062861", "GSM1062862", "GSM1062863", "GSM1062864", "GSM1062865", "GSM1062866", "GSM1062867", "GSM1062868", "GSM1062869", "GSM1062870", "GSM1062871", "GSM1062872", "GSM1062873", "GSM1062874"], "sample_count": 110, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression profiling of lung adenocarcinomas and normal lung tissue", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE50081", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE50081", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE50081", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1213669", "GSM1213670", "GSM1213671", "GSM1213672", "GSM1213673", "GSM1213674", "GSM1213675", "GSM1213676", "GSM1213677", "GSM1213678", "GSM1213679", "GSM1213680", "GSM1213681", "GSM1213682", "GSM1213683", "GSM1213684", "GSM1213685", "GSM1213686", "GSM1213687", "GSM1213688", "GSM1213689", "GSM1213690", "GSM1213691", "GSM1213692", "GSM1213693", "GSM1213694", "GSM1213695", "GSM1213696", "GSM1213697", "GSM1213698", "GSM1213699", "GSM1213700", "GSM1213701", "GSM1213702", "GSM1213703", "GSM1213704", "GSM1213705", "GSM1213706", "GSM1213707", "GSM1213708", "GSM1213709", "GSM1213710", "GSM1213711", "GSM1213712", "GSM1213713", "GSM1213714", "GSM1213715", "GSM1213716", "GSM1213717", "GSM1213718", "GSM1213719", "GSM1213720", "GSM1213721", "GSM1213722", "GSM1213723", "GSM1213724", "GSM1213725", "GSM1213726", "GSM1213727", "GSM1213728", "GSM1213729", "GSM1213730", "GSM1213731", "GSM1213732", "GSM1213733", "GSM1213734", "GSM1213735", "GSM1213736", "GSM1213737", "GSM1213738", "GSM1213739", "GSM1213740", "GSM1213741", "GSM1213742", "GSM1213743", "GSM1213744", "GSM1213745", "GSM1213746", "GSM1213747", "GSM1213748", "GSM1213749", "GSM1213750", "GSM1213751", "GSM1213752", "GSM1213753", "GSM1213754", "GSM1213755", "GSM1213756", "GSM1213757", "GSM1213758", "GSM1213759", "GSM1213760", "GSM1213761", "GSM1213762", "GSM1213763", "GSM1213764", "GSM1213765", "GSM1213766", "GSM1213767", "GSM1213768", "GSM1213769", "GSM1213770", "GSM1213771", "GSM1213772", "GSM1213773", "GSM1213774", "GSM1213775", "GSM1213776", "GSM1213777", "GSM1213778", "GSM1213779", "GSM1213780", "GSM1213781", "GSM1213782", "GSM1213783", "GSM1213784", "GSM1213785", "GSM1213786", "GSM1213787", "GSM1213788", "GSM1213789", "GSM1213790", "GSM1213791", "GSM1213792", "GSM1213793", "GSM1213794", "GSM1213795", "GSM1213796", "GSM1213797", "GSM1213798", "GSM1213799", "GSM1213800", "GSM1213801", "GSM1213802", "GSM1213803", "GSM1213804", "GSM1213805", "GSM1213806", "GSM1213807", "GSM1213808", "GSM1213809", "GSM1213810", "GSM1213811", "GSM1213812", "GSM1213813", "GSM1213814", "GSM1213815", "GSM1213816", "GSM1213817", "GSM1213818", "GSM1213819", "GSM1213820", "GSM1213821", "GSM1213822", "GSM1213823", "GSM1213824", "GSM1213825", "GSM1213826", "GSM1213827", "GSM1213828", "GSM1213829", "GSM1213830", "GSM1213831", "GSM1213832", "GSM1213833", "GSM1213834", "GSM1213835", "GSM1213836", "GSM1213837", "GSM1213838", "GSM1213839", "GSM1213840", "GSM1213841", "GSM1213842", "GSM1213843", "GSM1213844", "GSM1213845", "GSM1213846", "GSM1213847", "GSM1213848", "GSM1213849"], "sample_count": 181, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Validation of a histology-independent prognostic gene signature for early stage, non-small cell lung cancer including stage IA patients", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE68465", "role": "raw", "format": "geo-series", "media_type": "application/vnd.ncbi.geo-series+json", "uri": "https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE68465", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE68465", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1672281", "GSM1672282", "GSM1672283", "GSM1672284", "GSM1672285", "GSM1672286", "GSM1672287", "GSM1672288", "GSM1672289", "GSM1672290", "GSM1672291", "GSM1672292", "GSM1672293", "GSM1672294", "GSM1672295", "GSM1672296", "GSM1672297", "GSM1672298", "GSM1672299", "GSM1672300", "GSM1672301", "GSM1672302", "GSM1672303", "GSM1672304", "GSM1672305", "GSM1672306", "GSM1672307", "GSM1672308", "GSM1672309", "GSM1672310", "GSM1672311", "GSM1672312", "GSM1672313", "GSM1672314", "GSM1672315", "GSM1672316", "GSM1672317", "GSM1672318", "GSM1672319", "GSM1672320", "GSM1672321", "GSM1672322", "GSM1672323", "GSM1672324", "GSM1672325", "GSM1672326", "GSM1672327", "GSM1672328", "GSM1672329", "GSM1672330", "GSM1672331", "GSM1672332", "GSM1672333", "GSM1672334", "GSM1672335", "GSM1672336", "GSM1672337", "GSM1672338", "GSM1672339", "GSM1672340", "GSM1672341", "GSM1672342", "GSM1672343", "GSM1672344", "GSM1672345", "GSM1672346", "GSM1672347", "GSM1672348", "GSM1672349", "GSM1672350", "GSM1672351", "GSM1672352", "GSM1672353", "GSM1672354", "GSM1672355", "GSM1672356", "GSM1672357", "GSM1672358", "GSM1672359", "GSM1672360", "GSM1672361", "GSM1672362", "GSM1672363", "GSM1672364", "GSM1672365", "GSM1672366", "GSM1672367", "GSM1672368", "GSM1672369", "GSM1672370", "GSM1672371", "GSM1672372", "GSM1672373", "GSM1672374", "GSM1672375", "GSM1672376", "GSM1672377", "GSM1672378", "GSM1672379", "GSM1672380", "GSM1672381", "GSM1672382", "GSM1672383", "GSM1672384", "GSM1672385", "GSM1672386", "GSM1672387", "GSM1672388", "GSM1672389", "GSM1672390", "GSM1672391", "GSM1672392", "GSM1672393", "GSM1672394", "GSM1672395", "GSM1672396", "GSM1672397", "GSM1672398", "GSM1672399", "GSM1672400", "GSM1672401", "GSM1672402", "GSM1672403", "GSM1672404", "GSM1672405", "GSM1672406", "GSM1672407", "GSM1672408", "GSM1672409", "GSM1672410", "GSM1672411", "GSM1672412", "GSM1672413", "GSM1672414", "GSM1672415", "GSM1672416", "GSM1672417", "GSM1672418", "GSM1672419", "GSM1672420", "GSM1672421", "GSM1672422", "GSM1672423", "GSM1672424", "GSM1672425", "GSM1672426", "GSM1672427", "GSM1672428", "GSM1672429", "GSM1672430", "GSM1672431", "GSM1672432", "GSM1672433", "GSM1672434", "GSM1672435", "GSM1672436", "GSM1672437", "GSM1672438", "GSM1672439", "GSM1672440", "GSM1672441", "GSM1672442", "GSM1672443", "GSM1672444", "GSM1672445", "GSM1672446", "GSM1672447", "GSM1672448", "GSM1672449", "GSM1672450", "GSM1672451", "GSM1672452", "GSM1672453", "GSM1672454", "GSM1672455", "GSM1672456", "GSM1672457", "GSM1672458", "GSM1672459", "GSM1672460", "GSM1672461", "GSM1672462", "GSM1672463", "GSM1672464", "GSM1672465", "GSM1672466", "GSM1672467", "GSM1672468", "GSM1672469", "GSM1672470", "GSM1672471", "GSM1672472", "GSM1672473", "GSM1672474", "GSM1672475", "GSM1672476", "GSM1672477", "GSM1672478", "GSM1672479", "GSM1672480", "GSM1672481", "GSM1672482", "GSM1672483", "GSM1672484", "GSM1672485", "GSM1672486", "GSM1672487", "GSM1672488", "GSM1672489", "GSM1672490", "GSM1672491", "GSM1672492", "GSM1672493", "GSM1672494", "GSM1672495", "GSM1672496", "GSM1672497", "GSM1672498", "GSM1672499", "GSM1672500", "GSM1672501", "GSM1672502", "GSM1672503", "GSM1672504", "GSM1672505", "GSM1672506", "GSM1672507", "GSM1672508", "GSM1672509", "GSM1672510", "GSM1672511", "GSM1672512", "GSM1672513", "GSM1672514", "GSM1672515", "GSM1672516", "GSM1672517", "GSM1672518", "GSM1672519", "GSM1672520", "GSM1672521", "GSM1672522", "GSM1672523", "GSM1672524", "GSM1672525", "GSM1672526", "GSM1672527", "GSM1672528", "GSM1672529", "GSM1672530", "GSM1672531", "GSM1672532", "GSM1672533", "GSM1672534", "GSM1672535", "GSM1672536", "GSM1672537", "GSM1672538", "GSM1672539", "GSM1672540", "GSM1672541", "GSM1672542", "GSM1672543", "GSM1672544", "GSM1672545", "GSM1672546", "GSM1672547", "GSM1672548", "GSM1672549", "GSM1672550", "GSM1672551", "GSM1672552", "GSM1672553", "GSM1672554", "GSM1672555", "GSM1672556", "GSM1672557", "GSM1672558", "GSM1672559", "GSM1672560", "GSM1672561", "GSM1672562", "GSM1672563", "GSM1672564", "GSM1672565", "GSM1672566", "GSM1672567", "GSM1672568", "GSM1672569", "GSM1672570", "GSM1672571", "GSM1672572", "GSM1672573", "GSM1672574", "GSM1672575", "GSM1672576", "GSM1672577", "GSM1672578", "GSM1672579", "GSM1672580", "GSM1672581", "GSM1672582", "GSM1672583", "GSM1672584", "GSM1672585", "GSM1672586", "GSM1672587", "GSM1672588", "GSM1672589", "GSM1672590", "GSM1672591", "GSM1672592", "GSM1672593", "GSM1672594", "GSM1672595", "GSM1672596", "GSM1672597", "GSM1672598", "GSM1672599", "GSM1672600", "GSM1672601", "GSM1672602", "GSM1672603", "GSM1672604", "GSM1672605", "GSM1672606", "GSM1672607", "GSM1672608", "GSM1672609", "GSM1672610", "GSM1672611", "GSM1672612", "GSM1672613", "GSM1672614", "GSM1672615", "GSM1672616", "GSM1672617", "GSM1672618", "GSM1672619", "GSM1672620", "GSM1672621", "GSM1672622", "GSM1672623", "GSM1672624", "GSM1672625", "GSM1672626", "GSM1672627", "GSM1672628", "GSM1672629", "GSM1672630", "GSM1672631", "GSM1672632", "GSM1672633", "GSM1672634", "GSM1672635", "GSM1672636", "GSM1672637", "GSM1672638", "GSM1672639", "GSM1672640", "GSM1672641", "GSM1672642", "GSM1672643", "GSM1672644", "GSM1672645", "GSM1672646", "GSM1672647", "GSM1672648", "GSM1672649", "GSM1672650", "GSM1672651", "GSM1672652", "GSM1672653", "GSM1672654", "GSM1672655", "GSM1672656", "GSM1672657", "GSM1672658", "GSM1672659", "GSM1672660", "GSM1672661", "GSM1672662", "GSM1672663", "GSM1672664", "GSM1672665", "GSM1672666", "GSM1672667", "GSM1672668", "GSM1672669", "GSM1672670", "GSM1672671", "GSM1672672", "GSM1672673", "GSM1672674", "GSM1672675", "GSM1672676", "GSM1672677", "GSM1672678", "GSM1672679", "GSM1672680", "GSM1672681", "GSM1672682", "GSM1672683", "GSM1672684", "GSM1672685", "GSM1672686", "GSM1672687", "GSM1672688", "GSM1672689", "GSM1672690", "GSM1672691", "GSM1672692", "GSM1672693", "GSM1672694", "GSM1672695", "GSM1672696", "GSM1672697", "GSM1672698", "GSM1672699", "GSM1672700", "GSM1672701", "GSM1672702", "GSM1672703", "GSM1672704", "GSM1672705", "GSM1672706", "GSM1672707", "GSM1672708", "GSM1672709", "GSM1672710", "GSM1672711", "GSM1672712", "GSM1672713", "GSM1672714", "GSM1672715", "GSM1672716", "GSM1672717", "GSM1672718", "GSM1672719", "GSM1672720", "GSM1672721", "GSM1672722", "GSM1672723", "GSM1672724", "GSM1672725", "GSM1672726", "GSM1672727", "GSM1672728", "GSM1672729", "GSM1672730", "GSM1672731", "GSM1672732", "GSM1672733", "GSM1672734", "GSM1672735", "GSM1672736", "GSM1672737", "GSM1672738", "GSM1672739", "GSM1672740", "GSM1672741", "GSM1672742"], "sample_count": 462, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "caArray_jacob-00182: Gene expression-based survival prediction in lung adenocarcinoma: a multi-site, blinded validation study", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE75037", "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=GSE75037", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE75037", "version": null, "note": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1941120", "GSM1941121", "GSM1941122", "GSM1941123", "GSM1941124", "GSM1941125", "GSM1941126", "GSM1941127", "GSM1941128", "GSM1941129", "GSM1941130", "GSM1941131", "GSM1941132", "GSM1941133", "GSM1941134", "GSM1941135", "GSM1941136", "GSM1941137", "GSM1941138", "GSM1941139", "GSM1941140", "GSM1941141", "GSM1941142", "GSM1941143", "GSM1941144", "GSM1941145", "GSM1941146", "GSM1941147", "GSM1941148", "GSM1941149", "GSM1941150", "GSM1941151", "GSM1941152", "GSM1941153", "GSM1941154", "GSM1941155", "GSM1941156", "GSM1941157", "GSM1941158", "GSM1941159", "GSM1941160", "GSM1941161", "GSM1941162", "GSM1941163", "GSM1941164", "GSM1941165", "GSM1941166", "GSM1941167", "GSM1941168", "GSM1941169", "GSM1941170", "GSM1941171", "GSM1941172", "GSM1941173", "GSM1941174", "GSM1941175", "GSM1941176", "GSM1941177", "GSM1941178", "GSM1941179", "GSM1941180", "GSM1941181", "GSM1941182", "GSM1941183", "GSM1941184", "GSM1941185", "GSM1941186", "GSM1941187", "GSM1941188", "GSM1941189", "GSM1941190", "GSM1941191", "GSM1941192", "GSM1941193", "GSM1941194", "GSM1941195", "GSM1941196", "GSM1941197", "GSM1941198", "GSM1941199", "GSM1941200", "GSM1941201", "GSM1941202", "GSM1941203", "GSM1941204", "GSM1941205", "GSM1941206", "GSM1941207", "GSM1941208", "GSM1941209", "GSM1941210", "GSM1941211", "GSM1941212", "GSM1941213", "GSM1941214", "GSM1941215", "GSM1941216", "GSM1941217", "GSM1941218", "GSM1941219", "GSM1941220", "GSM1941221", "GSM1941222", "GSM1941223", "GSM1941224", "GSM1941225", "GSM1941226", "GSM1941227", "GSM1941228", "GSM1941229", "GSM1941230", "GSM1941231", "GSM1941232", "GSM1941233", "GSM1941234", "GSM1941235", "GSM1941236", "GSM1941237", "GSM1941238", "GSM1941239", "GSM1941240", "GSM1941241", "GSM1941242", "GSM1941243", "GSM1941244", "GSM1941245", "GSM1941246", "GSM1941247", "GSM1941248", "GSM1941249", "GSM1941250", "GSM1941251", "GSM1941252", "GSM1941253", "GSM1941254", "GSM1941255", "GSM1941256", "GSM1941257", "GSM1941258", "GSM1941259", "GSM1941260", "GSM1941261", "GSM1941262", "GSM1941263", "GSM1941264", "GSM1941265", "GSM1941266", "GSM1941267", "GSM1941268", "GSM1941269", "GSM1941270", "GSM1941271", "GSM1941272", "GSM1941273", "GSM1941274", "GSM1941275", "GSM1941276", "GSM1941277", "GSM1941278", "GSM1941279", "GSM1941280", "GSM1941281", "GSM1941282", "GSM1941283", "GSM1941284", "GSM1941285"], "sample_count": 166, "group_sizes": null, "group_sizes_basis": null, "platform": "6884", "taxon": "Homo sapiens", "title": "Expression profiling of 83 matched pairs of lung adenocarcinomas and non-malignant adjacent tissue", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE10072 not downloaded", "asset:data:geo:GSE10072 licence not read", "asset:data:geo:GSE126044 not downloaded", "asset:data:geo:GSE126044 licence not read", "asset:data:geo:GSE135222 not downloaded", "asset:data:geo:GSE135222 licence not read", "asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE31210 not downloaded", "asset:data:geo:GSE31210 licence not read", "asset:data:geo:GSE31320 not downloaded", "asset:data:geo:GSE31320 licence not read", "asset:data:geo:GSE32863 not downloaded", "asset:data:geo:GSE32863 licence not read", "asset:data:geo:GSE40791 not downloaded", "asset:data:geo:GSE40791 licence not read", "asset:data:geo:GSE43458 not downloaded", "asset:data:geo:GSE43458 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE68465 not downloaded", "asset:data:geo:GSE68465 licence not read", "asset:data:geo:GSE75037 not downloaded", "asset:data:geo:GSE75037 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": 0.7, "band": "medium", "quote": "Cox regression"}}, {"id": "method-2", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "limma"}}, {"id": "method-3", "family": null, "specific": null, "label": "RobustRankAggreg (RRA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "RobustRankAggreg (RRA) method was used to obtain robust MAGs that were ranked consistently better than expected by chance with the R package RRA [42]."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["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": ["GSE10072", "GSE18842", "GSE31320", "GSE31210", "GSE32863", "GSE40791", "GSE43458", "GSE75037", "GSE50081", "GSE68465", "GSE135222", "GSE126044"], "resolved_accessions": ["GSE10072", "GSE18842", "GSE31320", "GSE31210", "GSE32863", "GSE40791", "GSE43458", "GSE75037", "GSE50081", "GSE68465", "GSE135222", "GSE126044"], "statements": ["All data generated or analyzed during the present study was downloaded from TCGA database, GEO database, GDSC database CMap database, HPA database, and AlphaFold Protein Structure Database."], "basis": "The paper names GSE10072, GSE18842, GSE31320, GSE31210, GSE32863, GSE40791, GSE43458, GSE75037, GSE50081, GSE68465, GSE135222, GSE126044 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:35830566", "data:geo:GSE10072"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10072"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:55:08Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13733, "completion_tokens": 3689, "cached_tokens": 128}}, "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:35830566", "type": "paper", "label": "pmid:35830566"}, {"id": "source:pmid:35830566", "type": "manuscript", "label": "PMID 35830566 full text"}, {"id": "data:geo:GSE10072", "type": "dataset", "label": "GEO GSE10072"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:35830566", "type": "paper", "label": "pmid:35830566"}, {"id": "source:pmid:35830566", "type": "manuscript", "label": "PMID 35830566 full text"}, {"id": "data:geo:GSE10072", "type": "dataset", "label": "GEO GSE10072"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-35830566", "type": "extraction", "used": ["source:pmid:35830566"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10072", "type": "accession_resolution", "used": ["data:geo:GSE10072"], "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:35830566", "parent_hash": "sha256:812ce063df2e862e69189fa7da407fe56e8877f25ea28dafd723f310349a02be", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE10072 licence not read", "asset:data:geo:GSE10072 not downloaded", "asset:data:geo:GSE126044 licence not read", "asset:data:geo:GSE126044 not downloaded", "asset:data:geo:GSE135222 licence not read", "asset:data:geo:GSE135222 not downloaded", "asset:data:geo:GSE18842 licence not read", "asset:data:geo:GSE18842 not downloaded", "asset:data:geo:GSE31210 licence not read", "asset:data:geo:GSE31210 not downloaded", "asset:data:geo:GSE31320 licence not read", "asset:data:geo:GSE31320 not downloaded", "asset:data:geo:GSE32863 licence not read", "asset:data:geo:GSE32863 not downloaded", "asset:data:geo:GSE40791 licence not read", "asset:data:geo:GSE40791 not downloaded", "asset:data:geo:GSE43458 licence not read", "asset:data:geo:GSE43458 not downloaded", "asset:data:geo:GSE50081 licence not read", "asset:data:geo:GSE50081 not downloaded", "asset:data:geo:GSE68465 licence not read", "asset:data:geo:GSE68465 not downloaded", "asset:data:geo:GSE75037 licence not read", "asset:data:geo:GSE75037 not downloaded", "execution.not_run", "method.reader_named_unmapped", "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": ["taurosporine could inhibit cell migration in A549 and H1299. We further verified mRNA and prot", "ied mRNA and protein expression of 6 MAGs in A549 and H1299. The signature can serve as a prom", "16HBE) and 2 lung adenocarcinoma cell lines (A549 and H1299) were carried out. As illustrated", "d KRT6A were also significantly increased in A549 and H1299 compare to 16HBE (Figure 14B). Fur"], "order_basis": "paper_text_order:1326", "id": "assay:1"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["otein expression in A549, H1299 and 16HBE by western blot. (C) Staurosporine could inhibit cell migrat"], "order_basis": "paper_text_order:2590", "id": "assay:2"}, {"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": 0.7, "evidence": ["Cox regression"], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T04:50:33+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}