{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:29921304", "kind": "science-record", "revision": 7, "content_hash": "sha256:edc791451a4c7655ba7ad76728cf467cd401988dade59c6a2c74d71ad8258005", "created_at": "2026-11-01T15:40:34Z", "updated_at": "2026-11-01T21:59:54Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of hub genes with prognostic values in gastric cancer by bioinformatics analysis.", "doi": "10.1186/s12957-018-1409-3", "pmid": "29921304", "authors": ["Ting Li", "Xujie Gao", "Lei Han", "Jinpu Yu", "Hui Li"], "journal": "World journal of surgical oncology", "year": 2018, "abstract": "BACKGROUND: Gastric cancer (GC) is a prevalent malignant cancer of digestive system. To identify key genes in GC, mRNA microarray GSE27342, GSE29272, and GSE33335 were downloaded from GEO database.\nMETHODS: Differentially expressed genes (DEGs) were obtained using GEO2R. DAVID database was used to analyze function and pathways enrichment of DEGs. Protein-protein interaction (PPI) network was established by STRING and visualized by Cytoscape software. Then, the influence of hub genes on overall survival (OS) was performed by the Kaplan-Meier plotter online tool. Module analysis of the PPI network was performed using MCODE. Additionally, potential stem loop miRNAs of hub genes were predicted by miRecords and screened by TCGA dataset. Transcription factors (TFs) of hub genes were detected by NetworkAnalyst.\nRESULTS: In total, 67 DEGs were identified; upregulated DEGs were mainly enriched in biological process (BP) related to angiogenesis and extracellular matrix organization and the downregulated DEGs were mainly enriched in BP related to ion transport and response to bacterium. KEGG pathways analysis showed that the upregulated DEGs were enriched in ECM-receptor interaction and the downregulated DEGs were enriched in gastric acid secretion. A PPI network of DEGs was constructed, consisting of 43 nodes and 87 edges. Twelve genes were considered as hub genes owing to high degrees in the network. Hsa-miR-29c, hsa-miR-30c, hsa-miR-335, hsa-miR-33b, and hsa-miR-101 might play a crucial role in hub genes regulation. In addition, the transcription factors-hub genes pairs were displayed with 182 edges and 102 nodes. The high expression of 7 out of 12 hub genes was associated with worse OS, including COL4A1, VCAN, THBS2, TIMP1, COL1A2, SERPINH1, and COL6A3.\nCONCLUSIONS: The miRNA and TFs regulation network of hub genes in GC may promote understanding of the molecular mechanisms underlying the development of gastric cancer and provide potential targets for GC diagnosis and treatment.", "claims": [{"id": "claim-method", "statement": "DEG was obtained from GEO database by a way of GEO2R analysis (http://www.ncbi.nlm.nih.gov/geo/geo2r/). The adj. P < 0.05 and |logFC| > 1.5 were set as DEGs cutoff criterion.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29921304", "locator": "sections[3] \"Identification of DEGs\" paragraph 2", "quote": "DEG was obtained from GEO database by a way of GEO2R analysis (http://www.ncbi.nlm.nih.gov/geo/geo2r/). The adj. P < 0.05 and |logFC| > 1.5 were set as DEGs cutoff criterion."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets supporting the conclusion of this article are included within the article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:29921304", "locator": "sections[23] \"ack\" paragraph 1", "quote": "The datasets supporting the conclusion of this article are included within the article."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": null, "steps": [{"id": "read_published_estimate", "order": 1, "name": "Read the published estimate from the source", "kind": "other", "state": "complete", "blocked_on": null, "description": "The claim, method and evidence span published with the source article.", "duration_hours": null, "parameters": {}, "inputs": ["source:pmid:29921304"], "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:GSE15459"], "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:GSE15459"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:29921304", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12957-018-1409-3", "sha256": "sha256:b21ba68204c9840ad8525c262ecdf87914e1cdf6501684f129fe38f7adba62e7", "bytes": 30084, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12957-018-1409-3", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6009060", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE15459", "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=GSE15459", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE15459", "version": null, "note": "The datasets supporting the conclusion of this article are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusion of this article are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM387788", "GSM387789", "GSM387790", "GSM387791", "GSM387792", "GSM387793", "GSM387794", "GSM387795", "GSM387796", "GSM387797", "GSM387798", "GSM387799", "GSM387800", "GSM387801", "GSM387802", "GSM387803", "GSM387804", "GSM387805", "GSM387806", "GSM387807", "GSM387808", "GSM387809", "GSM387810", "GSM387811", "GSM387812", "GSM387813", "GSM387814", "GSM387815", "GSM387816", "GSM387817", "GSM387818", "GSM387819", "GSM387820", "GSM387821", "GSM387822", "GSM387823", "GSM387824", "GSM387825", "GSM387826", "GSM387827", "GSM387828", "GSM387829", "GSM387830", "GSM387831", "GSM387832", "GSM387833", "GSM387834", "GSM387835", "GSM387836", "GSM387837", "GSM387838", "GSM387839", "GSM387840", "GSM387841", "GSM387842", "GSM387843", "GSM387844", "GSM387845", "GSM387846", "GSM387847", "GSM387848", "GSM387849", "GSM387850", "GSM387851", "GSM387852", "GSM387853", "GSM387854", "GSM387855", "GSM387856", "GSM387857", "GSM387858", "GSM387859", "GSM387860", "GSM387861", "GSM387862", "GSM387863", "GSM387864", "GSM387865", "GSM387866", "GSM387867", "GSM387868", "GSM387869", "GSM387870", "GSM387871", "GSM387872", "GSM387873", "GSM387874", "GSM387875", "GSM387876", "GSM387877", "GSM387878", "GSM387879", "GSM387880", "GSM387881", "GSM387882", "GSM387883", "GSM387884", "GSM387885", "GSM387886", "GSM387887", "GSM387888", "GSM387889", "GSM387890", "GSM387891", "GSM387892", "GSM387893", "GSM387894", "GSM387895", "GSM387896", "GSM387897", "GSM387898", "GSM387899", "GSM387900", "GSM387901", "GSM387902", "GSM387903", "GSM387904", "GSM387905", "GSM387906", "GSM387907", "GSM387908", "GSM387909", "GSM387910", "GSM387911", "GSM387912", "GSM387913", "GSM387914", "GSM387915", "GSM387916", "GSM387917", "GSM387918", "GSM387919", "GSM387920", "GSM387921", "GSM387922", "GSM387923", "GSM387924", "GSM387925", "GSM387926", "GSM387927", "GSM387928", "GSM387929", "GSM387930", "GSM387931", "GSM387932", "GSM387933", "GSM387934", "GSM387935", "GSM387936", "GSM387937", "GSM387938", "GSM387939", "GSM387940", "GSM387941", "GSM387942", "GSM387943", "GSM387944", "GSM387945", "GSM387946", "GSM387947", "GSM387948", "GSM387949", "GSM387950", "GSM387951", "GSM387952", "GSM387953", "GSM387954", "GSM387955", "GSM387956", "GSM387957", "GSM387958", "GSM387959", "GSM387960", "GSM387961", "GSM387962", "GSM387963", "GSM387964", "GSM387965", "GSM387966", "GSM387967", "GSM387968", "GSM387969", "GSM387970", "GSM387971", "GSM387972", "GSM387973", "GSM387974", "GSM387975", "GSM387976", "GSM387977", "GSM387978", "GSM387979", "GSM387980", "GSM387981", "GSM387982", "GSM387983", "GSM387984", "GSM387985", "GSM387986", "GSM387987"], "sample_count": 200, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gastric Cancer Project '08 (Singapore Patient Cohort)", "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:GSE27342", "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=GSE27342", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27342", "version": null, "note": "The datasets supporting the conclusion of this article are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusion of this article are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM675890", "GSM675891", "GSM675892", "GSM675893", "GSM675894", "GSM675895", "GSM675896", "GSM675897", "GSM675898", "GSM675899", "GSM675900", "GSM675901", "GSM675902", "GSM675903", "GSM675904", "GSM675905", "GSM675906", "GSM675907", "GSM675908", "GSM675909", "GSM675910", "GSM675911", "GSM675912", "GSM675913", "GSM675914", "GSM675915", "GSM675916", "GSM675917", "GSM675918", "GSM675919", "GSM675920", "GSM675921", "GSM675922", "GSM675923", "GSM675924", "GSM675925", "GSM675926", "GSM675927", "GSM675928", "GSM675929", "GSM675930", "GSM675931", "GSM675932", "GSM675933", "GSM675934", "GSM675935", "GSM675936", "GSM675937", "GSM675938", "GSM675939", "GSM675940", "GSM675941", "GSM675942", "GSM675943", "GSM675944", "GSM675945", "GSM675946", "GSM675947", "GSM675948", "GSM675949", "GSM675950", "GSM675951", "GSM675952", "GSM675953", "GSM675954", "GSM675955", "GSM675956", "GSM675957", "GSM675958", "GSM675959", "GSM675960", "GSM675961", "GSM675962", "GSM675963", "GSM675964", "GSM675965", "GSM675966", "GSM675967", "GSM675968", "GSM675969", "GSM675970", "GSM675971", "GSM675972", "GSM675973", "GSM675974", "GSM675975", "GSM675976", "GSM675977", "GSM675978", "GSM675979", "GSM675980", "GSM675981", "GSM675982", "GSM675983", "GSM675984", "GSM675985", "GSM675986", "GSM675987", "GSM675988", "GSM675989", "GSM675990", "GSM675991", "GSM675992", "GSM675993", "GSM675994", "GSM675995", "GSM675996", "GSM675997", "GSM675998", "GSM675999", "GSM676000", "GSM676001", "GSM676002", "GSM676003", "GSM676004", "GSM676005", "GSM676006", "GSM676007", "GSM676008", "GSM676009", "GSM676010", "GSM676011", "GSM676012", "GSM676013", "GSM676014", "GSM676015", "GSM676016", "GSM676017", "GSM676018", "GSM676019", "GSM676020", "GSM676021", "GSM676022", "GSM676023", "GSM676024", "GSM676025", "GSM676026", "GSM676027", "GSM676028", "GSM676029", "GSM676030", "GSM676031", "GSM676032", "GSM676033", "GSM676034", "GSM676035", "GSM676036", "GSM676037", "GSM676038", "GSM676039", "GSM676040", "GSM676041", "GSM676042", "GSM676043", "GSM676044", "GSM676045", "GSM676046", "GSM676047", "GSM676048", "GSM676049"], "sample_count": 160, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Transcriptome analysis on gastric 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:GSE29272", "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=GSE29272", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE29272", "version": null, "note": "The datasets supporting the conclusion of this article are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusion of this article are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM723464", "GSM723465", "GSM723466", "GSM723467", "GSM723468", "GSM723469", "GSM723470", "GSM723471", "GSM723472", "GSM723473", "GSM723474", "GSM723475", "GSM723476", "GSM723477", "GSM723478", "GSM723479", "GSM723480", "GSM723481", "GSM723482", "GSM723483", "GSM723484", "GSM723485", "GSM723486", "GSM723487", "GSM723488", "GSM723489", "GSM723490", "GSM723491", "GSM723492", "GSM723493", "GSM723494", "GSM723495", "GSM723496", "GSM723497", "GSM723498", "GSM723499", "GSM723500", "GSM723501", "GSM723502", "GSM723503", "GSM723504", "GSM723505", "GSM723506", "GSM723507", "GSM723508", "GSM723509", "GSM723510", "GSM723511", "GSM723512", "GSM723513", "GSM723514", "GSM723515", "GSM723516", "GSM723517", "GSM723518", "GSM723519", "GSM723520", "GSM723521", "GSM723522", "GSM723523", "GSM723524", "GSM723525", "GSM723526", "GSM723527", "GSM723528", "GSM723529", "GSM723530", "GSM723531", "GSM723532", "GSM723533", "GSM723534", "GSM723535", "GSM723536", "GSM723537", "GSM723538", "GSM723539", "GSM723540", "GSM723541", "GSM723542", "GSM723543", "GSM723544", "GSM723545", "GSM723546", "GSM723547", "GSM723548", "GSM723549", "GSM723550", "GSM723551", "GSM723552", "GSM723553", "GSM723554", "GSM723555", "GSM723556", "GSM723557", "GSM723558", "GSM723559", "GSM723560", "GSM723561", "GSM723562", "GSM723563", "GSM723564", "GSM723565", "GSM723566", "GSM723567", "GSM723568", "GSM723569", "GSM723570", "GSM723571", "GSM723572", "GSM723573", "GSM723574", "GSM723575", "GSM723576", "GSM723577", "GSM723578", "GSM723579", "GSM723580", "GSM723581", "GSM723582", "GSM723583", "GSM723584", "GSM723585", "GSM723586", "GSM723587", "GSM723588", "GSM723589", "GSM723590", "GSM723591", "GSM723592", "GSM723593", "GSM723594", "GSM723595", "GSM723596", "GSM723597", "GSM723598", "GSM723599", "GSM723600", "GSM723601", "GSM723602", "GSM723603", "GSM723604", "GSM723605", "GSM723606", "GSM723607", "GSM723608", "GSM723609", "GSM723610", "GSM723611", "GSM723612", "GSM723613", "GSM723614", "GSM723615", "GSM723616", "GSM723617", "GSM723618", "GSM723619", "GSM723620", "GSM723621", "GSM723622", "GSM723623", "GSM723624", "GSM723625", "GSM723626", "GSM723627", "GSM723628", "GSM723629", "GSM723630", "GSM723631", "GSM723632", "GSM723633", "GSM723634", "GSM723635", "GSM723636", "GSM723637", "GSM723638", "GSM723639", "GSM723640", "GSM723641", "GSM723642", "GSM723643", "GSM723644", "GSM723645", "GSM723646", "GSM723647", "GSM723648", "GSM723649", "GSM723650", "GSM723651", "GSM723652", "GSM723653", "GSM723654", "GSM723655", "GSM723656", "GSM723657", "GSM723658", "GSM723659", "GSM723660", "GSM723661", "GSM723662", "GSM723663", "GSM723664", "GSM723665", "GSM723666", "GSM723667", "GSM723668", "GSM723669", "GSM723670", "GSM723671", "GSM723672", "GSM723673", "GSM723674", "GSM723675", "GSM723676", "GSM723677", "GSM723678", "GSM723679", "GSM723680", "GSM723681", "GSM723682", "GSM723683", "GSM723684", "GSM723685", "GSM723686", "GSM723687", "GSM723688", "GSM723689", "GSM723690", "GSM723691", "GSM723692", "GSM723693", "GSM723694", "GSM723695", "GSM723696", "GSM723697", "GSM723698", "GSM723699", "GSM723700", "GSM723701", "GSM723702", "GSM723703", "GSM723704", "GSM723705", "GSM723706", "GSM723707", "GSM723708", "GSM723709", "GSM723710", "GSM723711", "GSM723712", "GSM723713", "GSM723714", "GSM723715", "GSM723716", "GSM723717", "GSM723718", "GSM723719", "GSM723720", "GSM723721", "GSM723722", "GSM723723", "GSM723724", "GSM723725", "GSM723726", "GSM723727", "GSM723728", "GSM723729", "GSM723730", "GSM723731"], "sample_count": 268, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Affymetrix gene expression array data for cardia and non-cardia gastric cancer  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:GSE33335", "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=GSE33335", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33335", "version": null, "note": "The datasets supporting the conclusion of this article are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusion of this article are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM824327", "GSM824328", "GSM824329", "GSM824330", "GSM824331", "GSM824332", "GSM824333", "GSM824334", "GSM824335", "GSM824336", "GSM824337", "GSM824338", "GSM824339", "GSM824340", "GSM824341", "GSM824342", "GSM824343", "GSM824344", "GSM824345", "GSM824346", "GSM824347", "GSM824348", "GSM824349", "GSM824350", "GSM824351", "GSM824352", "GSM824353", "GSM824354", "GSM824355", "GSM824356", "GSM824357", "GSM824358", "GSM824359", "GSM824360", "GSM824361", "GSM824362", "GSM824363", "GSM824364", "GSM824365", "GSM824366", "GSM824367", "GSM824368", "GSM824369", "GSM824370", "GSM824371", "GSM824372", "GSM824373", "GSM824374", "GSM824375", "GSM824376"], "sample_count": 50, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Expression data from gastric tissues: Cancer Samples vs. Matched Adjacent Noncancerous 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:GSE62254", "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=GSE62254", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE62254", "version": null, "note": "The datasets supporting the conclusion of this article are included within the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets supporting the conclusion of this article are included within the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1523727", "GSM1523728", "GSM1523729", "GSM1523744", "GSM1523745", "GSM1523746", "GSM1523747", "GSM1523748", "GSM1523765", "GSM1523768", "GSM1523769", "GSM1523770", "GSM1523771", "GSM1523772", "GSM1523773", "GSM1523774", "GSM1523775", "GSM1523776", "GSM1523777", "GSM1523778", "GSM1523779", "GSM1523780", "GSM1523781", "GSM1523782", "GSM1523783", "GSM1523784", "GSM1523785", "GSM1523786", "GSM1523787", "GSM1523788", "GSM1523789", "GSM1523790", "GSM1523791", "GSM1523792", "GSM1523793", "GSM1523794", "GSM1523795", "GSM1523796", "GSM1523797", "GSM1523798", "GSM1523799", "GSM1523800", "GSM1523801", "GSM1523802", "GSM1523803", "GSM1523804", "GSM1523805", "GSM1523806", "GSM1523807", "GSM1523808", "GSM1523809", "GSM1523810", "GSM1523811", "GSM1523812", "GSM1523813", "GSM1523814", "GSM1523815", "GSM1523816", "GSM1523817", "GSM1523818", "GSM1523819", "GSM1523820", "GSM1523821", "GSM1523822", "GSM1523823", "GSM1523824", "GSM1523825", "GSM1523826", "GSM1523827", "GSM1523828", "GSM1523829", "GSM1523830", "GSM1523831", "GSM1523832", "GSM1523833", "GSM1523834", "GSM1523835", "GSM1523836", "GSM1523837", "GSM1523838", "GSM1523839", "GSM1523840", "GSM1523841", "GSM1523842", "GSM1523843", "GSM1523844", "GSM1523845", "GSM1523846", "GSM1523847", "GSM1523848", "GSM1523849", "GSM1523850", "GSM1523851", "GSM1523852", "GSM1523853", "GSM1523854", "GSM1523855", "GSM1523856", "GSM1523857", "GSM1523858", "GSM1523859", "GSM1523860", "GSM1523861", "GSM1523862", "GSM1523863", "GSM1523864", "GSM1523865", "GSM1523866", "GSM1523867", "GSM1523868", "GSM1523869", "GSM1523870", "GSM1523871", "GSM1523872", "GSM1523873", "GSM1523874", "GSM1523875", "GSM1523876", "GSM1523877", "GSM1523878", "GSM1523879", "GSM1523880", "GSM1523881", "GSM1523882", "GSM1523883", "GSM1523884", "GSM1523885", "GSM1523886", "GSM1523887", "GSM1523888", "GSM1523889", "GSM1523890", "GSM1523891", "GSM1523892", "GSM1523893", "GSM1523894", "GSM1523895", "GSM1523896", "GSM1523897", "GSM1523898", "GSM1523899", "GSM1523901", "GSM1523903", "GSM1523904", "GSM1523905", "GSM1523906", "GSM1523908", "GSM1523909", "GSM1523910", "GSM1523911", "GSM1523918", "GSM1523919", "GSM1523920", "GSM1523921", "GSM1523922", "GSM1523923", "GSM1523924", "GSM1523925", "GSM1523926", "GSM1523927", "GSM1523928", "GSM1523929", "GSM1523930", "GSM1523931", "GSM1523932", "GSM1523933", "GSM1523934", "GSM1523935", "GSM1523936", "GSM1523937", "GSM1523938", "GSM1523939", "GSM1523940", "GSM1523941", "GSM1523942", "GSM1523943", "GSM1523944", "GSM1523945", "GSM1523946", "GSM1523947", "GSM1523948", "GSM1523949", "GSM1523950", "GSM1523951", "GSM1523952", "GSM1523953", "GSM1523954", "GSM1523955", "GSM1523956", "GSM1523957", "GSM1523958", "GSM1523959", "GSM1523960", "GSM1523961", "GSM1523962", "GSM1523963", "GSM1523964", "GSM1523965", "GSM1523966", "GSM1523967", "GSM1523968", "GSM1523969", "GSM1523970", "GSM1523971", "GSM1523972", "GSM1523973", "GSM1523974", "GSM1523975", "GSM1523976", "GSM1523977", "GSM1523978", "GSM1523979", "GSM1523980", "GSM1523981", "GSM1523982", "GSM1523983", "GSM1523984", "GSM1523985", "GSM1523986", "GSM1523987", "GSM1523988", "GSM1523989", "GSM1523990", "GSM1523991", "GSM1523992", "GSM1523993", "GSM1523994", "GSM1523995", "GSM1523996", "GSM1523997", "GSM1523998", "GSM1523999", "GSM1524000", "GSM1524001", "GSM1524002", "GSM1524003", "GSM1524004", "GSM1524005", "GSM1524006", "GSM1524007", "GSM1524008", "GSM1524009", "GSM1524010", "GSM1524011", "GSM1524012", "GSM1524013", "GSM1524014", "GSM1524015", "GSM1524016", "GSM1524017", "GSM1524018", "GSM1524019", "GSM1524020", "GSM1524021", "GSM1524022", "GSM1524023", "GSM1524024", "GSM1524025", "GSM1524026", "GSM1524027", "GSM1524028", "GSM1524029", "GSM1524030", "GSM1524031", "GSM1524032", "GSM1524033", "GSM1524034", "GSM1524035", "GSM1524036", "GSM1524037", "GSM1524038", "GSM1524039", "GSM1524040", "GSM1524041", "GSM1524042", "GSM1524043", "GSM1524044", "GSM1524045", "GSM1524046", "GSM1524047", "GSM1524048", "GSM1524049", "GSM1524050", "GSM1524051", "GSM1524052", "GSM1524053", "GSM1524054", "GSM1524055", "GSM1524056", "GSM1524057", "GSM1524058", "GSM1524059", "GSM1524060", "GSM1524061", "GSM1524062", "GSM1524068", "GSM1524069", "GSM1524070", "GSM1524071", "GSM1524072"], "sample_count": 300, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Molecular analysis of gastric cancer identifies discrete subtypes associated with distinct clinical characteristics and survival outcomes: the ACRG (Asian Cancer Research Group) study [gastric tumors]", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:29921304:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:49b1364c0314750949ae443a609ed8d51cf1ff08b70c7a1acd44ab475d9c0f4a", "bytes": 1584, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#Tab1", "version": null, "note": "GO analysis of DEGs associated with GC", "structure": {"pmcid": "PMC6009060", "section_index": 12, "section_title": "GO term and KEGG pathway enrichment analysis of DEGs", "row_count": 21, "column_count": 4}, "table": {"label": "Table 1", "caption": "GO analysis of DEGs associated with GC", "rows": [["Expression", "Term/gene function", "Gene count", "P value"], ["Upregulation", "GO:0001568~blood vessel development", "9", "3.68E-06"], ["GO:0001944~vasculature development", "9", "6.21E-06"], ["GO:0030198~extracellular matrix organization", "6", "2.43E-05"], ["GO:0043062~extracellular structure organization", "6", "2.51E-05"], ["GO:0030199~collagen fibril organization", "4", "3.97E-05"], ["GO:0010033~response to organic substance", "13", "6.13E-05"], ["GO:0051291~protein heterooligomerization", "4", "7.68E-05"], ["GO:0071230~cellular response to amino acid stimulus", "4", "8.34E-05"], ["GO:0072358~cardiovascular system development", "9", "1.17E-04"], ["GO:0072359~circulatory system development", "9", "1.17E-04"], ["Downregulation", "GO:0006813~potassium ion transport", "4", "5.11E-04"], ["GO:0010107~potassium ion import", "3", "7.71E-04"], ["GO:0019731~antibacterial humoral response", "3", "1.13E-03"], ["GO:0019730~antimicrobial humoral response", "3", "1.46E-03"], ["GO:0042742~defense response to bacterium", "4", "2.80E-03"], ["GO:0015672~monovalent inorganic cation transport", "4", "4.94E-03"], ["GO:0002803~positive regulation of antibacterial peptide production", "2", "5.18E-03"], ["GO:0002760~positive regulation of antimicrobial humoral response", "2", "5.18E-03"], ["GO:0002786~regulation of antibacterial peptide production", "2", "5.18E-03"], ["GO:0002225~positive regulation of antimicrobial peptide production", "2", "5.18E-03"]], "row_count": 21, "column_count": 4, "numeric_cells": 60, "header_rows": 1, "locator": "section[12]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:29921304:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7de046f63809803467e1562cb09f64a6ca9694c2a8f612db20b8192d54ab62ab", "bytes": 765, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#Tab2", "version": null, "note": "KEGG pathway analysis of DEGs associated with GC", "structure": {"pmcid": "PMC6009060", "section_index": 12, "section_title": "GO term and KEGG pathway enrichment analysis of DEGs", "row_count": 10, "column_count": 4}, "table": {"label": "Table 2", "caption": "KEGG pathway analysis of DEGs associated with GC", "rows": [["Expression", "Term", "Count", "P value"], ["Upregulation", "hsa04512: ECM-receptor interaction", "7", "8.90E-08"], ["hsa04510: Focal adhesion", "7", "1.46E-05"], ["hsa04974: Protein digestion and absorption", "5", "7.37E-05"], ["hsa04151: PI3K-Akt signaling pathway", "7", "2.25E-04"], ["hsa05146: Amoebiasis", "4", "3.00E-03"], ["hsa04670: Leukocyte transendothelial migration", "4", "4.16E-03"], ["hsa04514: Cell adhesion molecules (CAMs)", "4", "5.92E-03"], ["Downregulation", "hsa04971: Gastric acid secretion", "7", "1.64E-08"], ["hsa04966: Collecting duct acid secretion", "3", "2.12E-03"]], "row_count": 10, "column_count": 4, "numeric_cells": 27, "header_rows": 1, "locator": "section[12]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:29921304:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:dde436ba3b64724ead7f68101c63e86b65e7b29df188974f2f0d099e5aeeb3e4", "bytes": 538, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab3", "version": null, "note": "KEGG pathways enrichment analysis of the genes in module", "structure": {"pmcid": "PMC6009060", "section_index": 13, "section_title": "PPI network construction and modules selection", "row_count": 7, "column_count": 3}, "table": {"label": "Table 3", "caption": "KEGG pathways enrichment analysis of the genes in module", "rows": [["Term", "Count", "P value"], ["hsa04512: ECM-receptor interaction", "7", "3.05E-10"], ["hsa04510: Focal adhesion", "7", "5.86E-08"], ["hsa04151: PI3K-Akt signaling pathway", "7", "1.07E-06"], ["hsa04974: Protein digestion and absorption", "5", "2.63E-06"], ["hsa05146: Amoebiasis", "4", "2.91E-04"], ["hsa04611: Platelet activation", "3", "1.15E-02"]], "row_count": 7, "column_count": 3, "numeric_cells": 18, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab3"}}, {"id": "asset:table:pmid:29921304:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:50ceb3565d26461f2c818417fc67e6515c83b6c2aadcbb9effdcb4ebc7f13c3f", "bytes": 1151, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#Tab4", "version": null, "note": "Hub genes and its predicted miRNAs", "structure": {"pmcid": "PMC6009060", "section_index": 14, "section_title": "MiRNA-hub genes pairs", "row_count": 13, "column_count": 3}, "table": {"label": "Table 4", "caption": "Hub genes and its predicted miRNAs", "rows": [["Gene", "Predicted miRNA", "Total"], ["COL1A1", "hsa-let-7d hsa-miR-98 hsa-let-7a hsa-let-7 g hsa-let-7i", "149"], ["COL1A2", "hsa-miR-29c hsa-let-7c hsa-miR-25 hsa-miR-29a hsa-miR-29b", "91"], ["COL3A1", "hsa-miR-29b hsa-let-7 g hsa-let-7f hsa-let-7i hsa-let-7a", "85"], ["COL4A1", "hsa-miR-29a hsa-miR-29b hsa-miR-29c hsa-miR-148a hsa-let-7c", "118"], ["COL6A3", "hsa-miR-29c hsa-miR-29a hsa-miR-29b hsa-miR-206 hsa-miR-330-3p", "108"], ["MMP7", "hsa-miR-297 hsa-miR-641 hsa-miR-19b hsa-miR-122 hsa-miR-380", "32"], ["SERPINH1", "hsa-miR-200b hsa-miR-24 hsa-miR-346 hsa-miR-561 hsa-miR-637", "56"], ["SPARC", "hsa-miR-29a hsa-miR-299-3p hsa-miR-29c hsa-miR-203 hsa-miR-29b", "206"], ["SPP1", "hsa-miR-220b hsa-miR-127-5p hsa-miR-181c hsa-miR-181a hsa-miR-181b", "72"], ["THBS2", "hsa-miR-607 hsa-miR-891b hsa-miR-616 hsa-miR-519a hsa-miR-221", "184"], ["TIMP1", "hsa-miR-484 hsa-miR-892a hsa-miR-1293 hsa-miR-1292", "4"], ["VCAN", "hsa-miR-203 hsa-miR-144 hsa-miR-632 hsa-miR-135b hsa-miR-136", "57"]], "row_count": 13, "column_count": 3, "numeric_cells": 24, "header_rows": 1, "locator": "section[14]/table-wrap[1]#Tab4"}}, {"id": "asset:table:pmid:29921304:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e7290c43cb03e61cd6879cd9689427db0e0484db85e84af1a352aba14e178136", "bytes": 1068, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#Tab5", "version": null, "note": "Hub genes and its screening stem loop miRNAs", "structure": {"pmcid": "PMC6009060", "section_index": 14, "section_title": "MiRNA-hub genes pairs", "row_count": 12, "column_count": 3}, "table": {"label": "Table 5", "caption": "Hub genes and its screening stem loop miRNAs", "rows": [["Gene", "Screening stem loop miRNAs", "Total"], ["COL1A1", "hsa-miR-378 hsa-miR-144 hsa-miR-29c hsa-miR-7 hsa-miR-556", "21"], ["COL1A2", "hsa-let-378 hsa-miR-144 hsa-miR-7 hsa-miR-556 hsa-miR-200c", "32"], ["COL3A1", "hsa-miR-7 hsa-miR-556 hsa-miR-378 hsa-miR-200c hsa-miR-18a", "44"], ["COL4A1", "hsa-miR-222 hsa-miR-429 hsa-miR-96 hsa-miR-33b hsa-miR-556", "23"], ["COL6A3", "hsa-miR-200c hsa-miR-96 hsa-miR-7 hsa-miR-592 hsa-miR-200a", "38"], ["MMP7", "hsa-miR-378 hsa-miR-503 hsa-miR-19a hsa-miR-301b hsa-miR-509", "11"], ["SERPINH1", "hsa-miR-101 hsa-miR-29c hsa-miR-378 hsa-miR-195", "4"], ["SPARC", "hsa-miR-7 hsa-miR-378 hsa-miR-18a hsa-miR-19a hsa-miR-96", "38"], ["SPP1", "hsa-miR-29c hsa-miR-139 hsa-miR-195 hsa-miR-101 hsa-miR-129", "6"], ["THBS2", "hsa-miR-144 hsa-miR-378 hsa-miR-7 hsa-miR-200c hsa-miR-592", "39"], ["VCAN", "hsa-miR-378 hsa-miR-556 hsa-miR-200c hsa-miR-7 hsa-miR-96", "38"]], "row_count": 12, "column_count": 3, "numeric_cells": 22, "header_rows": 1, "locator": "section[14]/table-wrap[2]#Tab5"}}, {"id": "asset:table:pmid:29921304:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b4e69252a1605540ff89ca1f4e9129b8d9ef569d39375b8ce77b4da7d290ee12", "bytes": 2551, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[3]#Tab6", "version": null, "note": "Hub genes’ negatively correlated stem loop miRNAs in predicted miRNAs", "structure": {"pmcid": "PMC6009060", "section_index": 14, "section_title": "MiRNA-hub genes pairs", "row_count": 12, "column_count": 3}, "table": {"label": "Table 6", "caption": "Hub genes’ negatively correlated stem loop miRNAs in predicted miRNAs", "rows": [["Genes", "Negatively correlated stem loop miRNAs", "Total"], ["COL1A1", "hsa-miR-378 hsa-miR-29c hsa-miR-592 hsa-miR-30c hsa-miR-19a hsa-miR-18a hsa-miR-96 hsa-miR-802 hsa-miR-101 hsa-miR-182 hsa-miR-577 hsa-miR-335 hsa-miR-877 hsa-miR-130b hsa-miR-33b", "15"], ["COL1A2", "hsa-miR-7 hsa-miR-200c hsa-miR-19a hsa-miR-96 hsa-miR-200a hsa-miR-200b hsa-miR-429 hsa-miR-29c hsa-miR-130b hsa-miR-30c hsa-miR-182 hsa-miR-194 hsa-miR-301b hsa-miR-335 hsa-miR-577 hsa-miR-1304 hsa-miR-105 hsa-miR-196a hsa-miR-579 hsa-miR-9 hsa-miR-135b", "21"], ["COL3A1", "hsa-miR-200c hsa-miR-96 hsa-miR-144 hsa-miR-200a hsa-miR-200b hsa-miR-429 hsa-miR-130b hsa-miR-877 hsa-miR-192 hsa-miR-182 hsa-miR-33b hsa-miR-301b hsa-miR-577 hsa-miR-335 hsa-miR-30c-2* hsa-miR-1304 hsa-miR-29c hsa-miR-206", "22"], ["COL4A1", "hsa-miR-429 hsa-miR-96 hsa-miR-33b hsa-miR-556 hsa-miR-200b hsa-miR-200c hsa-miR-182 hsa-miR-18a hsa-miR-29c hsa-miR-19a hsa-miR-301b hsa-miR-192 hsa-miR-335 hsa-miR-378 hsa-miR-130b", "15"], ["COL6A3", "hsa-miR-509-3p hsa-miR-549 hsa-miR-509-3p hsa-miR-29c hsa-miR-605 hsa-miR-579 hsa-miR-206 hsa-miR-1304 hsa-miR-135b hsa-miR-33b hsa-miR-30c hsa-miR-335 hsa-miR-194 hsa-miR-301b hsa-miR-877 hsa-miR-378 hsa-miR-130b hsa-miR-19a hsa-miR-96", "19"], ["MMP7", "hsa-miR-19a", "1"], ["SERPINH1", "hsa-miR-30c hsa-miR-195 hsa-miR-378 hsa-miR-29c", "2"], ["SPARC", "hsa-miR-579 hsa-miR-605 hsa-miR-135b hsa-miR-215 hsa-miR-767-3p hsa-miR-105 hsa-miR-206 hsa-miR-196a hsa-miR-33b hsa-miR-335 hsa-miR-30c hsa-miR-592 hsa-miR-1304 hsa-miR-101 hsa-miR-182 hsa-miR-222 hsa-miR-188-3p hsa-miR-192 hsa-miR-877 hsa-miR-29c hsa-miR-144 hsa-miR-200a hsa-miR-200c hsa-miR-200b hsa-miR-96 hsa-miR-19a hsa-miR-18a hsa-miR-378", "28"], ["SPP1", "hsa-miR-195 hsa-miR-101", "2"], ["THBS2", "hsa-miR-509 hsa-miR-504 hsa-miR-767 hsa-miR-579 hsa-miR-509 hsa-miR-135b hsa-miR-335 hsa-miR-196a hsa-miR-101 hsa-miR-33bhsa-miR-577 hsa-miR-802 hsa-miR-29c hsa-miR-222 hsa-miR-301b hsa-miR-188 hsa-miR-182 hsa-miR-30c hsa-miR-194 hsa-miR-877hsa-miR-192 hsa-miR-130b hsa-miR-206 hsa-miR-429 hsa-miR-96 hsa-miR-19a hsa-miR-200b hsa-miR-18a hsa-miR-486 hsa-miR-556 hsa-miR-592 hsa-miR-200c hsa-miR-144", "33"], ["VCAN", "hsa-mir-605 hsa-mir-135b hsa-mir-579 hsa-mir-33b hsa-mir-206 hsa-mir-192 hsa-mir-222 hsa-mir-200b hsa-mir-429 hsa-mir-200a hsa-mir-19a hsa-mir-144 hsa-mir-18a hsa-mir-200c", "14"]], "row_count": 12, "column_count": 3, "numeric_cells": 22, "header_rows": 1, "locator": "section[14]/table-wrap[3]#Tab6"}}, {"id": "asset:table:pmid:29921304:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1445d22f13b16e4de41a05ad541b94ae6926633779203dee2d96c1f3cb9f312c", "bytes": 1150, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[15]/table-wrap[1]#Tab7", "version": null, "note": "The transcription factors of hub genes", "structure": {"pmcid": "PMC6009060", "section_index": 15, "section_title": "Transcription factors-hub genes pairs", "row_count": 26, "column_count": 3}, "table": {"label": "Table 7", "caption": "The transcription factors of hub genes", "rows": [["TFs", "Genes", "Total"], ["AR", "SPARC COL6A3 SERPINH1 COL4A1 VCAN", "5"], ["NANOG", "SPARC SPP1 SERPINH1 COL3A1 VCAN", "5"], ["SOX2", "SPARC SPP1 COL4A1 VCAN SERPINH1", "5"], ["EP300", "SPARC COL4A1 VCAN SERPINH1", "4"], ["PPARG", "SPARC SPP1 SERPINH1 COL3A1", "4"], ["SALL4", "SPP1 COL4A1 VCAN SERPINH1", "4"], ["TCF3", "SPARC SPP1 VCAN SERPINH1", "4"], ["EZH2", "COL4A1 VCAN COL6A3", "3"], ["FLI1", "SPARC SERPINH1 COL6A3", "3"], ["FOXP1", "SPP1 VCAN COL6A3", "3"], ["GATA2", "SPARC SPP1 SERPINH1", "3"], ["HSF1", "SPARC SERPINH1 COL6A3", "3"], ["NFE2L2", "SPARC COL4A1 VCAN", "3"], ["NR1H3", "SPP1 COL4A1 COL6A3", "3"], ["POU3F2", "SPP1 VCAN COL3A1", "3"], ["POU5F1", "SPARC SPP1 VCAN", "3"], ["PRDM14", "SPARC SPP1 VCAN", "3"], ["RUNX1", "SPARC SPP1 COL6A3", "3"], ["RUNX2", "SPARC VCAN COL6A3", "3"], ["SMAD4", "VCAN COL6A3 COL3A1", "3"], ["SPI1", "SPARC SPP1 SERPINH1", "3"], ["SUZ12", "COL4A1 VCAN SERPINH1", "3"], ["TCF4", "COL4A1 VCAN COL6A3", "3"], ["TP53", "COL4A1 VCAN COL6A3", "3"], ["TP63", "SPARC COL4A1 SERPINH1", "3"]], "row_count": 26, "column_count": 3, "numeric_cells": 30, "header_rows": 1, "locator": "section[15]/table-wrap[1]#Tab7"}}], "gaps": ["asset:data:geo:GSE15459 not downloaded", "asset:data:geo:GSE15459 licence not read", "asset:data:geo:GSE27342 not downloaded", "asset:data:geo:GSE27342 licence not read", "asset:data:geo:GSE29272 not downloaded", "asset:data:geo:GSE29272 licence not read", "asset:data:geo:GSE33335 not downloaded", "asset:data:geo:GSE33335 licence not read", "asset:data:geo:GSE62254 not downloaded", "asset:data:geo:GSE62254 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-2", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "The hazard ratio (HR) with 95% confidenc"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log rank"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "Protein-protein interaction"}}, {"id": "method-4", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}, {"id": "method-5", "family": null, "specific": null, "label": "GEO2R analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "DEG was obtained from GEO database by a way of GEO2R analysis (http://www.ncbi.nlm.nih.gov/geo/geo2r/). The adj. P < 0.05 and |logFC| > 1.5 were set as DEGs cutoff criterion."}}], "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": ["survival_km"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: kaplan_meier."}, "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": ["GSE27342", "GSE29272", "GSE33335", "GSE15459", "GSE62254"], "resolved_accessions": ["GSE27342", "GSE29272", "GSE33335", "GSE15459", "GSE62254"], "statements": ["The datasets supporting the conclusion of this article are included within the article."], "basis": "The paper names GSE27342, GSE29272, GSE33335, GSE15459, GSE62254 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["survival_km"], "assets": ["source:pmid:29921304", "data:geo:GSE15459", "asset:table:pmid:29921304:1", "asset:table:pmid:29921304:2", "asset:table:pmid:29921304:3", "asset:table:pmid:29921304:4", "asset:table:pmid:29921304:5", "asset:table:pmid:29921304:6", "asset:table:pmid:29921304:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE15459"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:11:51Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 28366, "completion_tokens": 1586, "cached_tokens": 784}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:29921304", "type": "paper", "label": "pmid:29921304"}, {"id": "source:pmid:29921304", "type": "manuscript", "label": "PMID 29921304 full text"}, {"id": "data:geo:GSE15459", "type": "dataset", "label": "GEO GSE15459"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:29921304", "type": "paper", "label": "pmid:29921304"}, {"id": "source:pmid:29921304", "type": "manuscript", "label": "PMID 29921304 full text"}, {"id": "data:geo:GSE15459", "type": "dataset", "label": "GEO GSE15459"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-29921304", "type": "extraction", "used": ["source:pmid:29921304"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE15459", "type": "accession_resolution", "used": ["data:geo:GSE15459"], "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:29921304", "parent_hash": "sha256:b19fbea05ccafb9e2b8868c368e89b0cf86e09f8ef47174104346fa1da7e465c", "fork_of": null, "generation": 6}, "gaps": ["asset:data:geo:GSE15459 licence not read", "asset:data:geo:GSE15459 not downloaded", "asset:data:geo:GSE27342 licence not read", "asset:data:geo:GSE27342 not downloaded", "asset:data:geo:GSE29272 licence not read", "asset:data:geo:GSE29272 not downloaded", "asset:data:geo:GSE33335 licence not read", "asset:data:geo:GSE33335 not downloaded", "asset:data:geo:GSE62254 licence not read", "asset:data:geo:GSE62254 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["ve system. To identify key genes in GC, mRNA microarray GSE27342, GSE29272, and GSE33335 were downlo"], "order_basis": "paper_text_order:171", "id": "assay:1"}, {"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["survival_km"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.7, "evidence": ["Kaplan-Meier"], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T03:38:13+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}}}