{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:33116619", "kind": "science-record", "revision": 8, "content_hash": "sha256:8f217a809a3f35b17e0e5e97d58786ca157ed22b7a1c8b79cbbc732ba3bb12e7", "created_at": "2026-11-01T15:41:14Z", "updated_at": "2026-11-01T22:02:24Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Gene Expression Along with Genomic Copy Number Variation and Mutational Analysis Were Used to Develop a 9-Gene Signature for Estimating Prognosis of COAD.", "doi": "10.2147/OTT.S255590", "pmid": "33116619", "authors": ["Yiping Lu", "Si Wu", "Changwan Cui", "Miao Yu", "Shuang Wang", "Yuanyi Yue", "Miao Liu", "Zhengrong Sun"], "journal": "OncoTargets and therapy", "year": 2020, "abstract": "PURPOSE: This study aims to systematically analyze multi-omics data to explore new prognosis biomarkers in colon adenocarcinoma (COAD).\nMATERIALS AND METHODS: Multi-omics data of COAD and clinical information were obtained from The Cancer Genome Atlas (TCGA). Univariate Cox analysis was used to select genes which significantly related to the overall survival. GISTIC 2.0 software was used to identify significant amplification or deletion. Mutsig 2.0 software was used to identify significant mutation genes. The 9-gene signature was screened by random forest algorithm and Cox regression analysis. GSE17538 dataset was used as an external dataset to verify the predictive ability of 9-gene signature. qPCR was used to detect the expression of 9 genes in clinical specimens.\nRESULTS: A total of 71 candidate genes are obtained by integrating genomic variation, mutation and prognostic data. Then, 9-gene signature was established, which includes HOXD12, RNF25, CBLN3, DOCK3, DNAJB13, PYGO2, CTNNA1, PTPRK, and NAT1. The 9-gene signature is an independent prognostic risk factor for COAD patients. In addition, the signature shows good predicting performance and clinical practicality in training set, testing set and external verification set. The results of qPCR based on clinical samples showed that the expression of HOXD12, RNF25, CBLN3, DOCK3, DNAJB13, and PYGO2 was increased in colon cancer tissues and the expression of CTNNA1, PTPRK, NAT1 was decreased in colon cancer tissues.\nCONCLUSION: In this study, 9-gene signature is constructed as a new prognostic marker to predict the survival of COAD patients.", "claims": [{"id": "claim-data-access", "statement": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:33116619", "locator": "sections[3] \"Data Acquisition and Processing\" paragraph 2", "quote": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/)."}], "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:33116619"], "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:GSE17538"], "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:GSE17538"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:33116619", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/OTT.S255590", "sha256": "sha256:73f57e38fdc6eb2cffd2f22cf2b6196810383dffc6a5e49436bb26f007010c71", "bytes": 36368, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/OTT.S255590", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7569059", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE17538", "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=GSE17538", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE17538", "version": null, "note": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM437093", "GSM437094", "GSM437095", "GSM437096", "GSM437097", "GSM437098", "GSM437099", "GSM437100", "GSM437101", "GSM437102", "GSM437103", "GSM437104", "GSM437105", "GSM437106", "GSM437107", "GSM437108", "GSM437109", "GSM437110", "GSM437111", "GSM437112", "GSM437113", "GSM437114", "GSM437115", "GSM437116", "GSM437117", "GSM437118", "GSM437119", "GSM437120", "GSM437121", "GSM437122", "GSM437123", "GSM437124", "GSM437125", "GSM437126", "GSM437127", "GSM437128", "GSM437129", "GSM437130", "GSM437131", "GSM437132", "GSM437133", "GSM437134", "GSM437135", "GSM437136", "GSM437137", "GSM437138", "GSM437139", "GSM437140", "GSM437141", "GSM437142", "GSM437143", "GSM437144", "GSM437145", "GSM437146", "GSM437147", "GSM437148", "GSM437149", "GSM437150", "GSM437151", "GSM437152", "GSM437153", "GSM437154", "GSM437155", "GSM437156", "GSM437157", "GSM437158", "GSM437159", "GSM437160", "GSM437161", "GSM437162", "GSM437163", "GSM437164", "GSM437165", "GSM437166", "GSM437167", "GSM437168", "GSM437169", "GSM437170", "GSM437171", "GSM437172", "GSM437173", "GSM437174", "GSM437175", "GSM437176", "GSM437177", "GSM437178", "GSM437179", "GSM437180", "GSM437181", "GSM437182", "GSM437183", "GSM437184", "GSM437185", "GSM437186", "GSM437187", "GSM437188", "GSM437189", "GSM437190", "GSM437191", "GSM437192", "GSM437193", "GSM437194", "GSM437195", "GSM437196", "GSM437197", "GSM437198", "GSM437199", "GSM437200", "GSM437201", "GSM437202", "GSM437203", "GSM437204", "GSM437205", "GSM437206", "GSM437207", "GSM437208", "GSM437209", "GSM437210", "GSM437211", "GSM437212", "GSM437213", "GSM437214", "GSM437215", "GSM437216", "GSM437217", "GSM437218", "GSM437219", "GSM437220", "GSM437221", "GSM437222", "GSM437223", "GSM437224", "GSM437225", "GSM437226", "GSM437227", "GSM437228", "GSM437229", "GSM437230", "GSM437231", "GSM437232", "GSM437233", "GSM437234", "GSM437235", "GSM437236", "GSM437237", "GSM437238", "GSM437239", "GSM437240", "GSM437241", "GSM437242", "GSM437243", "GSM437244", "GSM437245", "GSM437246", "GSM437247", "GSM437248", "GSM437249", "GSM437250", "GSM437251", "GSM437252", "GSM437253", "GSM437254", "GSM437255", "GSM437256", "GSM437257", "GSM437258", "GSM437259", "GSM437260", "GSM437261", "GSM437262", "GSM437263", "GSM437264", "GSM437265", "GSM437266", "GSM437267", "GSM437268", "GSM437269", "GSM437270", "GSM437271", "GSM437272", "GSM437273", "GSM437274", "GSM437275", "GSM437276", "GSM437277", "GSM437278", "GSM437279", "GSM437280", "GSM437281", "GSM437282", "GSM437283", "GSM437284", "GSM437285", "GSM437286", "GSM437287", "GSM437288", "GSM437289", "GSM437290", "GSM437291", "GSM437292", "GSM437293", "GSM437294", "GSM437295", "GSM437296", "GSM437297", "GSM437298", "GSM437299", "GSM437300", "GSM437301", "GSM437302", "GSM437303", "GSM437304", "GSM437305", "GSM437306", "GSM437307", "GSM437308", "GSM437309", "GSM437310", "GSM437311", "GSM437312", "GSM437313", "GSM437314", "GSM437315", "GSM437316", "GSM437317", "GSM437318", "GSM437319", "GSM437320", "GSM437321", "GSM437322", "GSM437323", "GSM437324", "GSM472192", "GSM472193", "GSM472194", "GSM472195", "GSM472196", "GSM472197", "GSM472198", "GSM472199", "GSM472200", "GSM472201", "GSM472202", "GSM472203"], "sample_count": 244, "group_sizes": null, "group_sizes_basis": null, "platform": "570;1261", "taxon": "Mus musculus; Homo sapiens", "title": "Experimentally Derived Metastasis Gene Expression Profile Predicts Recurrence and Death in Colon Cancer 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:GSE19234", "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=GSE19234", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE19234", "version": null, "note": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM476606", "GSM476607", "GSM476608", "GSM476609", "GSM476610", "GSM476611", "GSM476612", "GSM476613", "GSM476614", "GSM476615", "GSM476616", "GSM476617", "GSM476618", "GSM476619", "GSM476620", "GSM476621", "GSM476622", "GSM476623", "GSM476624", "GSM476625", "GSM476626", "GSM476627", "GSM476628", "GSM476629", "GSM476630", "GSM476631", "GSM476632", "GSM476633", "GSM476634", "GSM476635", "GSM476636", "GSM476637", "GSM476638", "GSM476639", "GSM476640", "GSM476641", "GSM476642", "GSM476643", "GSM476644", "GSM476645", "GSM476646", "GSM476647", "GSM476648", "GSM476649"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Immune profile and mitotic index of metastatic melanoma lesions enhance clinical staging in predicting patient survival.", "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:GSE24551", "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=GSE24551", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE24551", "version": null, "note": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM712082", "GSM712083", "GSM712084", "GSM712085", "GSM712086", "GSM712087", "GSM712088", "GSM712089", "GSM712090", "GSM712091", "GSM712092", "GSM712093", "GSM712094", "GSM712095", "GSM712096", "GSM712097", "GSM712098", "GSM712099", "GSM712100", "GSM712101", "GSM712102", "GSM712103", "GSM712104", "GSM712105", "GSM712106", "GSM712107", "GSM712108", "GSM712109", "GSM712110", "GSM712111", "GSM712112", "GSM712113", "GSM712114", "GSM712115", "GSM712116", "GSM712117", "GSM712118", "GSM712119", "GSM712120", "GSM712121", "GSM712122", "GSM712123", "GSM712124", "GSM712125", "GSM712126", "GSM712127", "GSM712128", "GSM712129", "GSM712130", "GSM712131", "GSM712132", "GSM712133", "GSM712134", "GSM712135", "GSM712136", "GSM712137", "GSM712138", "GSM712139", "GSM712140", "GSM712141", "GSM712142", "GSM712143", "GSM712144", "GSM712145", "GSM712146", "GSM712147", "GSM712148", "GSM712149", "GSM712150", "GSM712151", "GSM712152", "GSM712153", "GSM712154", "GSM712155", "GSM712156", "GSM712157", "GSM712158", "GSM712159", "GSM712160", "GSM712161", "GSM712162", "GSM712163", "GSM712164", "GSM712195", "GSM712196", "GSM712197", "GSM712198", "GSM712199", "GSM712200", "GSM712201", "GSM712202", "GSM712203", "GSM712204", "GSM712205", "GSM712206", "GSM712207", "GSM712208", "GSM712209", "GSM712210", "GSM712211", "GSM712212", "GSM712213", "GSM712214", "GSM712215", "GSM712216", "GSM712218", "GSM712221", "GSM712224", "GSM712226", "GSM712228", "GSM712231", "GSM712234", "GSM712237", "GSM712238", "GSM712241", "GSM712243", "GSM712245", "GSM712248", "GSM712251", "GSM712253", "GSM712255", "GSM712257", "GSM712258", "GSM712259", "GSM712260", "GSM712261", "GSM712262", "GSM712263", "GSM712264", "GSM712265", "GSM712266", "GSM712267", "GSM712268", "GSM712269", "GSM712270", "GSM712271", "GSM712272", "GSM712273", "GSM712274", "GSM712275", "GSM712276", "GSM712277", "GSM712278", "GSM712279", "GSM712280", "GSM712281", "GSM712282", "GSM712283", "GSM712284", "GSM712285", "GSM712286", "GSM712287", "GSM712288", "GSM712289", "GSM712290", "GSM712291", "GSM712292", "GSM712293", "GSM712294", "GSM712295", "GSM712296", "GSM712297", "GSM712298", "GSM712299", "GSM712300", "GSM712301", "GSM712398", "GSM712399", "GSM712400", "GSM712401", "GSM712402", "GSM712403", "GSM712404", "GSM712405", "GSM712406", "GSM712407", "GSM712408", "GSM712409", "GSM712410", "GSM712411", "GSM712412", "GSM712413", "GSM712414", "GSM712415", "GSM712416", "GSM712417", "GSM712418", "GSM712419", "GSM712420", "GSM712421", "GSM712422", "GSM712423", "GSM712424", "GSM712425", "GSM712426", "GSM712427", "GSM712428", "GSM712429", "GSM712430", "GSM712431", "GSM712432", "GSM712433", "GSM712434", "GSM712435", "GSM712436", "GSM712437", "GSM712438", "GSM712439", "GSM712440", "GSM712441", "GSM712442", "GSM712443", "GSM712444", "GSM712445", "GSM712446", "GSM712447", "GSM712448", "GSM712449", "GSM712450", "GSM712451", "GSM712452", "GSM712453", "GSM712454", "GSM712455", "GSM712456", "GSM712457", "GSM712458", "GSM712459", "GSM712460", "GSM712461", "GSM712462", "GSM712463", "GSM712464", "GSM712465", "GSM712466", "GSM712467", "GSM712468", "GSM712469", "GSM712470", "GSM712471", "GSM712472", "GSM712473", "GSM712474", "GSM712573", "GSM712574", "GSM712575", "GSM712576", "GSM712577", "GSM712578", "GSM712579", "GSM712580", "GSM712581", "GSM712582", "GSM712583", "GSM712584", "GSM712585", "GSM712586", "GSM712587", "GSM712588", "GSM712589", "GSM712590", "GSM712591", "GSM712592", "GSM712593", "GSM712594", "GSM712595", "GSM712596", "GSM712597", "GSM712598", "GSM712599", "GSM712600", "GSM712601", "GSM712602", "GSM712603", "GSM712604", "GSM712605", "GSM712606", "GSM712607", "GSM712608", "GSM712609", "GSM712610", "GSM712611", "GSM712612", "GSM712613", "GSM712614", "GSM712615", "GSM712616", "GSM712617", "GSM712618", "GSM712619", "GSM712620", "GSM712621", "GSM712622", "GSM712623", "GSM712624", "GSM712625", "GSM712626", "GSM712627", "GSM712628", "GSM712629", "GSM712630", "GSM712631", "GSM712632", "GSM712633", "GSM712634", "GSM712635", "GSM712636", "GSM712637", "GSM712638", "GSM712639", "GSM712640", "GSM712641", "GSM712642", "GSM712643", "GSM712644", "GSM712645", "GSM712646", "GSM712647", "GSM712648", "GSM712649", "GSM714419", "GSM714420", "GSM714421", "GSM714422", "GSM714423", "GSM714424", "GSM714425", "GSM714426", "GSM714427", "GSM714428", "GSM714429", "GSM714430", "GSM714431"], "sample_count": 333, "group_sizes": null, "group_sizes_basis": null, "platform": "5175;11028", "taxon": "Homo sapiens", "title": "Exon level expression profiling of colorectal cancer tissue 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:GSE39582", "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=GSE39582", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE39582", "version": null, "note": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM1681353", "GSM1681354", "GSM1681355", "GSM1681356", "GSM1681357", "GSM1681358", "GSM1681359", "GSM1681360", "GSM1681361", "GSM1681362", "GSM1681363", "GSM1681364", "GSM1681365", "GSM1681366", "GSM1681367", "GSM1681368", "GSM1681369", "GSM1681370", "GSM1681371", "GSM971957", "GSM971958", "GSM971959", "GSM971960", "GSM971961", "GSM971962", "GSM971963", "GSM971964", "GSM971965", "GSM971966", "GSM971967", "GSM971968", "GSM971969", "GSM971970", "GSM971971", "GSM971972", "GSM971973", "GSM971974", "GSM971975", "GSM971976", "GSM971977", "GSM971978", "GSM971979", "GSM971980", "GSM971981", "GSM971982", "GSM971983", "GSM971984", "GSM971985", "GSM971986", "GSM971987", "GSM971988", "GSM971989", "GSM971990", "GSM971991", "GSM971992", "GSM971993", "GSM971994", "GSM971995", "GSM971996", "GSM971997", "GSM971998", "GSM971999", "GSM972000", "GSM972001", "GSM972002", "GSM972003", "GSM972004", "GSM972005", "GSM972006", "GSM972007", "GSM972008", "GSM972009", "GSM972010", "GSM972011", "GSM972012", "GSM972013", "GSM972014", "GSM972015", "GSM972016", "GSM972017", "GSM972018", "GSM972019", "GSM972020", "GSM972021", "GSM972022", "GSM972023", "GSM972024", "GSM972025", "GSM972026", "GSM972027", "GSM972028", "GSM972029", "GSM972030", "GSM972031", "GSM972032", "GSM972033", "GSM972034", "GSM972035", "GSM972036", "GSM972037", "GSM972038", "GSM972039", "GSM972040", "GSM972041", "GSM972042", "GSM972043", "GSM972044", "GSM972045", "GSM972046", "GSM972047", "GSM972048", "GSM972049", "GSM972050", "GSM972051", "GSM972052", "GSM972053", "GSM972054", "GSM972055", "GSM972056", "GSM972057", "GSM972058", "GSM972059", "GSM972060", "GSM972061", "GSM972062", "GSM972063", "GSM972064", "GSM972065", "GSM972066", "GSM972067", "GSM972068", "GSM972069", "GSM972070", "GSM972071", "GSM972072", "GSM972073", "GSM972074", "GSM972075", "GSM972076", "GSM972077", "GSM972078", "GSM972079", "GSM972080", "GSM972081", "GSM972082", "GSM972083", "GSM972084", "GSM972085", "GSM972086", "GSM972087", "GSM972088", "GSM972089", "GSM972090", "GSM972091", "GSM972092", "GSM972093", "GSM972094", "GSM972095", "GSM972096", "GSM972097", "GSM972098", "GSM972099", "GSM972100", "GSM972101", "GSM972102", "GSM972103", "GSM972104", "GSM972105", "GSM972106", "GSM972107", "GSM972108", "GSM972109", "GSM972110", "GSM972111", "GSM972112", "GSM972113", "GSM972114", "GSM972115", "GSM972116", "GSM972117", "GSM972118", "GSM972119", "GSM972120", "GSM972121", "GSM972122", "GSM972123", "GSM972124", "GSM972125", "GSM972126", "GSM972127", "GSM972128", "GSM972129", "GSM972130", "GSM972131", "GSM972132", "GSM972133", "GSM972134", "GSM972135", "GSM972136", "GSM972137", "GSM972138", "GSM972139", "GSM972140", "GSM972141", "GSM972142", "GSM972143", "GSM972144", "GSM972145", "GSM972146", "GSM972147", "GSM972148", "GSM972149", "GSM972150", "GSM972151", "GSM972152", "GSM972153", "GSM972154", "GSM972155", "GSM972156", "GSM972157", "GSM972158", "GSM972159", "GSM972160", "GSM972161", "GSM972162", "GSM972163", "GSM972164", "GSM972165", "GSM972166", "GSM972167", "GSM972168", "GSM972169", "GSM972170", "GSM972171", "GSM972172", "GSM972173", "GSM972174", "GSM972175", "GSM972176", "GSM972177", "GSM972178", "GSM972179", "GSM972180", "GSM972181", "GSM972182", "GSM972183", "GSM972184", "GSM972185", "GSM972186", "GSM972187", "GSM972188", "GSM972189", "GSM972190", "GSM972191", "GSM972192", "GSM972193", "GSM972194", "GSM972195", "GSM972196", "GSM972197", "GSM972198", "GSM972199", "GSM972200", "GSM972201", "GSM972202", "GSM972203", "GSM972204", "GSM972205", "GSM972206", "GSM972207", "GSM972208", "GSM972209", "GSM972210", "GSM972211", "GSM972212", "GSM972213", "GSM972214", "GSM972215", "GSM972216", "GSM972217", "GSM972218", "GSM972219", "GSM972220", "GSM972221", "GSM972222", "GSM972223", "GSM972224", "GSM972225", "GSM972226", "GSM972227", "GSM972228", "GSM972229", "GSM972230", "GSM972231", "GSM972232", "GSM972233", "GSM972234", "GSM972235", "GSM972236", "GSM972237", "GSM972238", "GSM972239", "GSM972240", "GSM972241", "GSM972242", "GSM972243", "GSM972244", "GSM972245", "GSM972246", "GSM972247", "GSM972248", "GSM972249", "GSM972250", "GSM972251", "GSM972252", "GSM972253", "GSM972254", "GSM972255", "GSM972256", "GSM972257", "GSM972258", "GSM972259", "GSM972260", "GSM972261", "GSM972262", "GSM972263", "GSM972264", "GSM972265", "GSM972266", "GSM972267", "GSM972268", "GSM972269", "GSM972270", "GSM972271", "GSM972272", "GSM972273", "GSM972274", "GSM972275", "GSM972276", "GSM972277", "GSM972278", "GSM972279", "GSM972280", "GSM972281", "GSM972282", "GSM972283", "GSM972284", "GSM972285", "GSM972286", "GSM972287", "GSM972288", "GSM972289", "GSM972290", "GSM972291", "GSM972292", "GSM972293", "GSM972294", "GSM972295", "GSM972296", "GSM972297", "GSM972298", "GSM972299", "GSM972300", "GSM972301", "GSM972302", "GSM972303", "GSM972304", "GSM972305", "GSM972306", "GSM972307", "GSM972308", "GSM972309", "GSM972310", "GSM972311", "GSM972312", "GSM972313", "GSM972314", "GSM972315", "GSM972316", "GSM972317", "GSM972318", "GSM972319", "GSM972320", "GSM972321", "GSM972322", "GSM972323", "GSM972324", "GSM972325", "GSM972326", "GSM972327", "GSM972328", "GSM972329", "GSM972330", "GSM972331", "GSM972332", "GSM972333", "GSM972334", "GSM972335", "GSM972336", "GSM972337", "GSM972338", "GSM972339", "GSM972340", "GSM972341", "GSM972342", "GSM972343", "GSM972344", "GSM972345", "GSM972346", "GSM972347", "GSM972348", "GSM972349", "GSM972350", "GSM972351", "GSM972352", "GSM972353", "GSM972354", "GSM972355", "GSM972356", "GSM972357", "GSM972358", "GSM972359", "GSM972360", "GSM972361", "GSM972362", "GSM972363", "GSM972364", "GSM972365", "GSM972366", "GSM972367", "GSM972368", "GSM972369", "GSM972370", "GSM972371", "GSM972372", "GSM972373", "GSM972374", "GSM972375", "GSM972376", "GSM972377", "GSM972378", "GSM972379", "GSM972380", "GSM972381", "GSM972382", "GSM972383", "GSM972384", "GSM972385", "GSM972386", "GSM972387", "GSM972388", "GSM972389", "GSM972390", "GSM972391", "GSM972392", "GSM972393", "GSM972394", "GSM972395", "GSM972396", "GSM972397", "GSM972398", "GSM972399", "GSM972400", "GSM972401", "GSM972402", "GSM972403", "GSM972404", "GSM972405", "GSM972406", "GSM972407", "GSM972408", "GSM972409", "GSM972410", "GSM972411", "GSM972412", "GSM972413", "GSM972414", "GSM972415", "GSM972416", "GSM972417", "GSM972418", "GSM972419", "GSM972420", "GSM972421", "GSM972422", "GSM972423", "GSM972424", "GSM972425", "GSM972426", "GSM972427", "GSM972428", "GSM972429", "GSM972430", "GSM972431", "GSM972432", "GSM972433", "GSM972434", "GSM972435", "GSM972436", "GSM972437", "GSM972438", "GSM972439", "GSM972440", "GSM972441", "GSM972442", "GSM972443", "GSM972444", "GSM972445", "GSM972446", "GSM972447", "GSM972448", "GSM972449", "GSM972450", "GSM972451", "GSM972452", "GSM972453", "GSM972454", "GSM972455", "GSM972456", "GSM972457", "GSM972458", "GSM972459", "GSM972460", "GSM972461", "GSM972462", "GSM972463", "GSM972464", "GSM972465", "GSM972466", "GSM972467", "GSM972468", "GSM972469", "GSM972470", "GSM972471", "GSM972472", "GSM972473", "GSM972474", "GSM972475", "GSM972476", "GSM972477", "GSM972478", "GSM972479", "GSM972480", "GSM972481", "GSM972482", "GSM972483", "GSM972484", "GSM972485", "GSM972486", "GSM972487", "GSM972488", "GSM972489", "GSM972490", "GSM972491", "GSM972492", "GSM972493", "GSM972494", "GSM972495", "GSM972496", "GSM972497", "GSM972498", "GSM972499", "GSM972500", "GSM972501", "GSM972502", "GSM972503", "GSM972504", "GSM972505", "GSM972506", "GSM972507", "GSM972508", "GSM972509", "GSM972510", "GSM972511", "GSM972512", "GSM972513", "GSM972514", "GSM972515", "GSM972516", "GSM972517", "GSM972518", "GSM972519", "GSM972520", "GSM972521", "GSM972522"], "sample_count": 585, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression Classification of Colon Cancer defines six molecular subtypes with distinct clinical, molecular and survival characteristics [Expression]", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "asset:table:pmid:33116619:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:227d61ab934aebf930aaa9489a3b8f5cd1466a8f926bd65e00de0ae47bccab5b", "bytes": 1131, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[1]#t0001", "version": null, "note": "Clinical Information Statistics", "structure": {"pmcid": "PMC7569059", "section_index": 14, "section_title": "Preprocessing Data Statistics", "row_count": 25, "column_count": 6}, "table": {"label": "Table 1", "caption": "Clinical Information Statistics", "rows": [["Characteristics", "TCGA Training Datasets (n=226)", "TCGA Test Datasets (n=227)", "p value", "GSE17538 (n=238)"], ["Age (years)", "≤50", "31", "29", "0.875", "32"], [">50", "195", "198", "206"], ["Survival times (years)", "Median", "1.81", "1.97", "–", "2.38"], ["Mean", "2.25", "2.44", "3.12"], ["Survival status", "Living", "178", "176", "0.839", "145"], ["Dead", "48", "51", "55"], ["Gender", "Female", "104", "109", "0.739", "114"], ["Male", "122", "118", "124"], ["Lymphatic invasion", "NO", "125", "128", "0.695", "–"], ["YES", "81", "75", "–"], ["pathologic_T", "T1", "6", "5", "0.769", "–"], ["T2", "35", "43", "–"], ["T3", "157", "153", "–"], ["T4", "28", "25", "–"], ["pathologic_N", "N0", "127", "139", "0.454", "–"], ["N1", "54", "52", "–"], ["N2", "45", "36", "–"], ["N3", "0", "0", "–"], ["pathologic_M", "M0", "165", "168", "0.956", "–"], ["M1/MX", "57", "56", "–"], ["AJCC stage", "Stage Ⅰ", "34", "42", "0.332", "28"], ["Stage Ⅱ", "82", "92", "72"], ["Stage III", "73", "57", "76"], ["Stage Ⅳ", "30", "32", "56"]], "row_count": 25, "column_count": 6, "numeric_cells": 73, "header_rows": 1, "locator": "section[14]/table-wrap[1]#t0001"}}, {"id": "asset:table:pmid:33116619:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e2121ce1abf78a1b31ce39dc7176d7620c469da298df71946eaf77c63dad14e5", "bytes": 1526, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[14]/table-wrap[2]#t0002", "version": null, "note": "Information on Top20 Prognosis-Related Genes", "structure": {"pmcid": "PMC7569059", "section_index": 14, "section_title": "Preprocessing Data Statistics", "row_count": 21, "column_count": 6}, "table": {"label": "Table 2", "caption": "Information on Top20 Prognosis-Related Genes", "rows": [["ENGSID", "Genesymbol", "HR", "Coefficient", "z score", "p value"], ["ENSG00000241697", "TMEFF1", "1.552", "0.440", "4.737", "2.17E-06"], ["ENSG00000160117", "ANKLE1", "1.525", "0.422", "4.691", "2.72E-06"], ["ENSG00000214128", "TMEM213", "1.427", "0.355", "4.559", "5.13E-06"], ["ENSG00000090932", "DLL3", "1.622", "0.483", "4.528", "5.95E-06"], ["ENSG00000268940", "CT45A1", "1.361", "0.308", "4.522", "6.11E-06"], ["ENSG00000159556", "ISL2", "1.528", "0.424", "4.502", "6.72E-06"], ["ENSG00000205456", "TP53TG3D", "1.474", "0.388", "4.407", "1.05E-05"], ["ENSG00000100156", "SLC16A8", "1.473", "0.387", "4.381", "1.18E-05"], ["ENSG00000182759", "MAFA", "1.471", "0.386", "4.321", "1.56E-05"], ["ENSG00000106689", "LHX2", "1.472", "0.387", "4.284", "1.84E-05"], ["ENSG00000148331", "ASB6", "2.035", "0.711", "4.275", "1.91E-05"], ["ENSG00000269437", "NXF2B", "1.425", "0.354", "4.269", "1.96E-05"], ["ENSG00000124260", "MAGEA10", "1.366", "0.312", "4.262", "2.02E-05"], ["ENSG00000126890", "CTAG2", "1.346", "0.297", "4.210", "2.56E-05"], ["ENSG00000184029", "DSCR4", "1.414", "0.347", "4.172", "3.02E-05"], ["ENSG00000187730", "GABRD", "1.480", "0.392", "4.153", "3.29E-05"], ["ENSG00000149927", "DOC2A", "1.600", "0.470", "4.127", "3.68E-05"], ["ENSG00000075043", "KCNQ2", "1.428", "0.356", "4.126", "3.69E-05"], ["ENSG00000110148", "CCKBR", "1.404", "0.339", "4.113", "3.91E-05"], ["ENSG00000121905", "HPCA", "1.492", "0.400", "4.107", "4.01E-05"]], "row_count": 21, "column_count": 6, "numeric_cells": 105, "header_rows": 1, "locator": "section[14]/table-wrap[2]#t0002"}}, {"id": "asset:table:pmid:33116619:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ef8bfd1df3bf245a1d4a6b1b757b8b8219e7f9a3739c362a06ec36256a2ecfc0", "bytes": 1006, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[18]/table-wrap[1]#t0003", "version": null, "note": "9- Genes Significantly Associated with the Overall Survival in the Training Dataset", "structure": {"pmcid": "PMC7569059", "section_index": 18, "section_title": "Establishing 9-Gene Signature to Divide Samples in TCGA Training Cohort", "row_count": 10, "column_count": 7}, "table": {"label": "Table 3", "caption": "9- Genes Significantly Associated with the Overall Survival in the Training Dataset", "rows": [["Ensembl Gene ID", "Symbol", "HR", "Z-score", "P value", "Importance", "Relative Importance"], ["ENSG00000170178", "HOXD12", "1.30", "2.349091", "1.88E-02", "0.0096", "1"], ["ENSG00000163481", "RNF25", "1.52", "2.540626", "1.11E-02", "0.0094", "0.9848"], ["ENSG00000139899", "CBLN3", "1.39", "2.249482", "2.45E-02", "0.0088", "0.9242"], ["ENSG00000088538", "DOCK3", "1.52", "3.782743", "1.55E-04", "0.0078", "0.8182"], ["ENSG00000044115", "CTNNA1", "0.73", "−2.399278", "1.64E-02", "0.0064", "0.6667"], ["ENSG00000152894", "PTPRK", "0.71", "−2.371469", "1.77E-02", "0.0049", "0.5152"], ["ENSG00000187726", "DNAJB13", "1.28", "2.639895", "8.29E-03", "0.0046", "0.4848"], ["ENSG00000171428", "NAT1", "0.70", "−2.402113", "1.63E-02", "0.0045", "0.4697"], ["ENSG00000163348", "PYGO2", "1.47", "2.390166", "1.68E-02", "0.0032", "0.3333"]], "row_count": 10, "column_count": 7, "numeric_cells": 57, "header_rows": 1, "locator": "section[18]/table-wrap[1]#t0003"}}, {"id": "asset:table:pmid:33116619:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:b2775da1979b3501a0a73063906b2ee59aeaf4428d381a68155e466c97023a4e", "bytes": 1688, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[21]/table-wrap[1]#t0004", "version": null, "note": "Univariate and Multivariate Cox Regression Analyses", "structure": {"pmcid": "PMC7569059", "section_index": 21, "section_title": "Univariate and Multivariate Cox Regression Analysis", "row_count": 23, "column_count": 7}, "table": {"label": "Table 4", "caption": "Univariate and Multivariate Cox Regression Analyses", "rows": [["Variables", "Univariate Analysis", "Multivariable Analysis"], ["HR", "95% CI of HR", "P value", "HR", "95% CI of HR", "P value"], ["TCGA training datasets"], ["9-gene risk score"], ["Low-risk score", "1 (Ref)", "", "", "1 (Ref)", "", ""], ["High-risk score", "3.97", "2.04–7.73", "4.9E-05", "3.05", "1.36–6.84", "0.007"], ["Age(≤50/>50)", "1.02", "0.99–1.05", "6.0E-02", "1.04", "1.00–1.07", "0.016"], ["Gender female", "1 (Ref)", "", "", "1 (Ref)", "", ""], ["Gender male", "1.05", "0.59–1.86", "0.87", "0.66", "0.31–1.37", "0.265"], ["Lymphatic Invasion NO", "1 (Ref)", "", "", "1 (Ref)", "", ""], ["Lymphatic Invasion YES", "2.58", "1.35–4.91", "0.00", "1.94", "0.66–5.68", "0.227"], ["Pathologic T 1/ T 2", "1 (Ref)", "", "", "1 (Ref)", "", ""], ["Pathologic T 3", "1.55", "0.54–4.43", "0.412", "0.15", "0.01–1.34", "0.091"], ["Pathologic T 4", "5.15", "1.66–16", "0.005", "0.43", "0.04–4.13", "0.461"], ["Pathologic N 0", "1 (Ref)", "", "", "1 (Ref)", "", ""], ["Pathologic N 1", "1.38", "0.63–2.96", "0.413", "0.24", "0.04–1.56", "0.136"], ["Pathologic N 2", "3.00", "1.58–5.66", "0.001", "0.49", "0.07–3.21", "0.456"], ["Pathologic M 0", "1 (Ref)", "", "", "1 (Ref)", "", ""], ["Pathologic M 1", "4.52", "2.33–8.73", "7.42E-06", "2.28", "0.89–5.79", "0.080"], ["Pathologic M X", "1.82", "0.77–4.26", "0.168", "1.56", "0.50–4.84", "0.440"], ["AJCC Stage Ⅰ", "1 (Ref)", "", "", "1 (Ref)", "", ""], ["AJCC Stage Ⅱ", "1.94", "0.43–8.65", "0.3854", "13.42", "0.68–262.17", "0.087"], ["AJCC Stage III/Ⅳ", "4.28", "1.01–17.98", "0.047", "37.58", "1.42–990.93", "0.030"]], "row_count": 23, "column_count": 7, "numeric_cells": 98, "header_rows": 2, "locator": "section[21]/table-wrap[1]#t0004"}}, {"id": "asset:table:pmid:33116619:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:e70f1e000edfa96c6ca12d108db3d9f1dfd4d130ab162cc9e72a325f14e2f926", "bytes": 2458, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[22]/table-wrap[1]#t0005", "version": null, "note": "GSEA Analysis of 9-Gene Signature", "structure": {"pmcid": "PMC7569059", "section_index": 22, "section_title": "Analysis of Pathways Enriched in High-Risk and Low-Risk Groups Using GSEA", "row_count": 30, "column_count": 6}, "table": {"label": "Table 5", "caption": "GSEA Analysis of 9-Gene Signature", "rows": [["Name", "SIZE", "ES", "NES", "NOM p-val", "FDR q-val"], ["KEGG_O_GLYCAN_BIOSYNTHESIS", "26", "−0.650", "−1.907", "0.000", "0.355"], ["KEGG_UBIQUITIN_MEDIATED_PROTEOLYSIS", "133", "−0.502", "−1.882", "0.006", "0.245"], ["KEGG_ERBB_SIGNALING_PATHWAY", "87", "−0.455", "−1.772", "0.008", "0.494"], ["KEGG_ENDOMETRIAL_CANCER", "52", "−0.493", "−1.716", "0.008", "0.586"], ["KEGG_OOCYTE_MEIOSIS", "110", "−0.455", "−1.716", "0.008", "0.471"], ["KEGG_THYROID_CANCER", "29", "−0.511", "−1.709", "0.006", "0.415"], ["KEGG_COLORECTAL_CANCER", "62", "−0.470", "−1.701", "0.012", "0.377"], ["KEGG_VALINE_LEUCINE_AND_ISOLEUCINE_DEGRADATION", "44", "−0.584", "−1.690", "0.056", "0.356"], ["KEGG_PROSTATE_CANCER", "89", "−0.445", "−1.689", "0.019", "0.321"], ["KEGG_APOPTOSIS", "86", "−0.438", "−1.680", "0.021", "0.312"], ["KEGG_INSULIN_SIGNALING_PATHWAY", "136", "−0.393", "−1.675", "0.010", "0.292"], ["KEGG_BASAL_TRANSCRIPTION_FACTORS", "34", "−0.546", "−1.657", "0.025", "0.306"], ["KEGG_RENAL_CELL_CARCINOMA", "70", "−0.448", "−1.602", "0.037", "0.413"], ["KEGG_ADHERENS_JUNCTION", "73", "−0.455", "−1.596", "0.046", "0.400"], ["KEGG_DORSO_VENTRAL_AXIS_FORMATION", "24", "−0.511", "−1.585", "0.035", "0.398"], ["KEGG_NEUROTROPHIN_SIGNALING_PATHWAY", "125", "−0.399", "−1.585", "0.040", "0.374"], ["KEGG_RENIN_ANGIOTENSIN_SYSTEM", "17", "−0.527", "−1.583", "0.035", "0.356"], ["KEGG_ENDOCYTOSIS", "177", "−0.379", "−1.570", "0.042", "0.365"], ["KEGG_PEROXISOME", "78", "−0.470", "−1.568", "0.063", "0.351"], ["KEGG_AMINO_SUGAR_AND_NUCLEOTIDE_SUGAR_METABOLISM", "44", "−0.451", "−1.550", "0.054", "0.373"], ["KEGG_PROPANOATE_METABOLISM", "32", "−0.525", "−1.544", "0.064", "0.370"], ["KEGG_LONG_TERM_POTENTIATION", "68", "−0.402", "−1.534", "0.023", "0.375"], ["KEGG_FATTY_ACID_METABOLISM", "41", "−0.484", "−1.533", "0.100", "0.360"], ["KEGG_STARCH_AND_SUCROSE_METABOLISM", "50", "−0.441", "−1.517", "0.056", "0.380"], ["KEGG_CHRONIC_MYELOID_LEUKEMIA", "73", "−0.417", "−1.507", "0.086", "0.387"], ["KEGG_P53_SIGNALING_PATHWAY", "66", "−0.420", "−1.502", "0.056", "0.383"], ["KEGG_BIOSYNTHESIS_OF_UNSATURATED_FATTY_ACIDS", "20", "−0.506", "−1.496", "0.069", "0.383"], ["KEGG_TGF_BETA_SIGNALING_PATHWAY", "85", "−0.399", "−1.493", "0.059", "0.374"], ["KEGG_NICOTINATE_AND_NICOTINAMIDE_METABOLISM", "22", "−0.423", "−1.467", "0.0391", "0.4133"]], "row_count": 30, "column_count": 6, "numeric_cells": 146, "header_rows": 1, "locator": "section[22]/table-wrap[1]#t0005"}}], "gaps": ["asset:data:geo:GSE17538 not downloaded", "asset:data:geo:GSE17538 licence not read", "asset:data:geo:GSE19234 not downloaded", "asset:data:geo:GSE19234 licence not read", "asset:data:geo:GSE24551 not downloaded", "asset:data:geo:GSE24551 licence not read", "asset:data:geo:GSE39582 not downloaded", "asset:data:geo:GSE39582 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": 0.8, "band": "high", "quote": "Kaplan-Meier"}}, {"id": "method-2", "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-3", "family": "survival_analysis", "specific": "log_rank_test", "label": "Survival analysis", "dsl_operations": ["logrank_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "log-rank"}}, {"id": "method-4", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "random forest"}}, {"id": "method-5", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}, {"id": "method-6", "family": null, "specific": null, "label": "Random survival forest algorithm", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "reordered", "quote": "“The importance of prognostic genes is sequenced using R package random survival forest.”"}}], "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": ["GSE17538", "GSE39582", "GSE24551", "GSE19234"], "resolved_accessions": ["GSE17538", "GSE39582", "GSE24551", "GSE19234"], "statements": ["Level-3 RNA-sequencing data, the clinicopathological、 SNP 、 copy number segments and survival data of patients with COAD were downloaded from the UCSC Xena browser (https://xenabrowser.net/)."], "basis": "The paper names GSE17538, GSE39582, GSE24551, GSE19234 in GEO database 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:33116619", "data:geo:GSE17538", "asset:table:pmid:33116619:1", "asset:table:pmid:33116619:2", "asset:table:pmid:33116619:3", "asset:table:pmid:33116619:4", "asset:table:pmid:33116619:5"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE17538"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:38Z", "independence": "single_reader"}, "evidence_check": {"method": "reordered", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 29966, "completion_tokens": 1648, "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:33116619", "type": "paper", "label": "pmid:33116619"}, {"id": "source:pmid:33116619", "type": "manuscript", "label": "PMID 33116619 full text"}, {"id": "data:geo:GSE17538", "type": "dataset", "label": "GEO GSE17538"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:33116619", "type": "paper", "label": "pmid:33116619"}, {"id": "source:pmid:33116619", "type": "manuscript", "label": "PMID 33116619 full text"}, {"id": "data:geo:GSE17538", "type": "dataset", "label": "GEO GSE17538"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-33116619", "type": "extraction", "used": ["source:pmid:33116619"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE17538", "type": "accession_resolution", "used": ["data:geo:GSE17538"], "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:33116619", "parent_hash": "sha256:71c5c529ae821094dc1b93bf789f932f2a2b506607e80043247d49faeecac7a8", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE17538 licence not read", "asset:data:geo:GSE17538 not downloaded", "asset:data:geo:GSE19234 licence not read", "asset:data:geo:GSE19234 not downloaded", "asset:data:geo:GSE24551 licence not read", "asset:data:geo:GSE24551 not downloaded", "asset:data:geo:GSE39582 licence not read", "asset:data:geo:GSE39582 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["the predictive ability of 9-gene signature. qPCR was used to detect the expression of 9 genes", "nd external verification set. The results of qPCR based on clinical samples showed that the ex"], "order_basis": "paper_text_order:815", "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": 0.8, "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":"2026-11-04T01:50:14+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}}}