{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32953273", "kind": "science-record", "revision": 8, "content_hash": "sha256:3fec510a013d268fb7d86138d44789229a0a9e6881d7fecb62da0318c7bc0fa1", "created_at": "2026-11-01T15:41:10Z", "updated_at": "2026-11-01T22:45:21Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Prognostic implications of metabolism-associated gene signatures in colorectal cancer.", "doi": "10.7717/peerj.9847", "pmid": "32953273", "authors": ["Yandong Miao", "Qiutian Li", "Jiangtao Wang", "Wuxia Quan", "Chen Li", "Yuan Yang", "Denghai Mi"], "journal": "PeerJ", "year": 2020, "abstract": "Colorectal cancer (CRC) is one of the most common and deadly malignancies. Novel biomarkers for the diagnosis and prognosis of this disease must be identified. Besides, metabolism plays an essential role in the occurrence and development of CRC. This article aims to identify some critical prognosis-related metabolic genes (PRMGs) and construct a prognosis model of CRC patients for clinical use. We obtained the expression profiles of CRC from The Cancer Genome Atlas database (TCGA), then identified differentially expressed PRMGs by R and Perl software. Hub genes were filtered out by univariate Cox analysis and least absolute shrinkage and selection operator Cox analysis. We used functional enrichment analysis methods, such as Gene Ontology, Kyoto Encyclopedia of Genes and Genomes, and Gene Set Enrichment Analysis, to identify involved signaling pathways of PRMGs. The nomogram predicted overall survival (OS). Calibration traces were used to evaluate the consistency between the actual and the predicted survival rate. Finally, a prognostic model was constructed based on six metabolic genes (NAT2, XDH, GPX3, AKR1C4, SPHK1, and ADCY5), and the risk score was an independent prognostic prognosticator. Genetic expression and risk score were significantly correlated with clinicopathologic characteristics of CRC. A nomogram based on the clinicopathological feature of CRC and risk score accurately predicted the OS of individual CRC cancer patients. We also validated the results in the independent colorectal cancer cohorts GSE39582 and GSE87211. Our study demonstrates that the risk score is an independent prognostic biomarker and is closely correlated with the malignant clinicopathological characteristics of CRC patients. We also determined some metabolic genes associated with the survival and clinical stage of CRC as potential biomarkers for CRC diagnosis and treatment.", "claims": [{"id": "claim-method", "statement": "We screened differentially expressed metabolism-related genes using the Wilcox Test with R-package “edgeR” (Robinson, McCarthy & Smyth, 2010), and “limma”.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32953273", "locator": "sections[4] \"Identification of prognosis-associated metabolism-related genes\" paragraph 2", "quote": "We screened differentially expressed metabolism-related genes using the Wilcox Test with R-package “edgeR” (Robinson, McCarthy & Smyth, 2010), and “limma”."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The following information was supplied regarding data availability:The data are available at NCBI GEO (GSE39582, GSE87211) and at TCGA.The search instructions for TCGA:(1) Case keywords: “colon, rectosigmoid junction, and rectum [Primary Site]”, “TCGA[Program]”, “TCGA-COAD, TCGA-READ [Project]”, “Adenomas and Adenocarcinomas [Disease Type]”.(2) File keywords: “Transcriptome Profiling [Data Category]”, “Gene Expression Quantification [Data Category]”, “RNA-Seq [Experimental Strategy]”, “HTSeq—FPKM [Workflow Type]”, “Clinical [Data Category]”, “BCR XML [Data Format]”.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32953273", "locator": "sections[18] \"Additional Information and Declarations\" paragraph 4", "quote": "The following information was supplied regarding data availability:The data are available at NCBI GEO (GSE39582, GSE87211) and at TCGA.The search instructions for TCGA:(1) Case keywords: “colon, rectosigmoid junction, and rectum [Primary Site]”, “TCGA[Program]”, “TCGA-COAD, TCGA-READ [Project]”, “Adenomas and Adenocarcinomas [Disease Type]”.(2) File keywords: “Transcriptome Profiling [Data Category]”, “Gene Expression Quantification [Data Category]”, “RNA-Seq [Experimental Strategy]”, “HTSeq—FPKM [Workflow Type]”, “Clinical [Data Category]”, “BCR XML [Data Format]”."}], "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:32953273"], "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:GSE39582"], "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:GSE39582"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32953273", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.7717/peerj.9847", "sha256": "sha256:95f06c803b9fc7c8b4b10ad1997d231fab83d5686adf6bf968dc3c07c0e452e3", "bytes": 39035, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.7717/peerj.9847", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC7474523", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"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": "The following information was supplied regarding data availability:The data are available at NCBI GEO (GSE39582, GSE87211) and at TCGA.The search instructions for TCGA:(1) Case keywords: “colon, rectosigmoid junction, and rectum [Primary Site]”, “TCGA[Program]”, “TCGA-COAD, TCGA-READ [Project]”, “Adenomas and Adenocarcinomas [Disease Type]”.(2) File keywords: “Transcriptome Profiling [Data Category]”, “Gene Expression Quantification [Data Category]”, “RNA-Seq [Experimental Strategy]”, “HTSeq—FPKM [Workflow Type]”, “Clinical [Data Category]”, “BCR XML [Data Format]”.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The data are available at NCBI GEO (GSE39582, GSE87211) and at TCGA.The search instructions for TCGA:(1) Case keywords: “colon, rectosigmoid junction, and rectum [Primary Site]”, “TCGA[Program]”, “TCGA-COAD, TCGA-READ [Project]”, “Adenomas and Adenocarcinomas [Disease Type]”.(2) File keywords: “Transcriptome Profiling [Data Category]”, “Gene Expression Quantification [Data Category]”, “RNA-Seq [Experimental Strategy]”, “HTSeq—FPKM [Workflow Type]”, “Clinical [Data Category]”, “BCR XML [Data Format]”.", "access_statement_kind": "data_availability_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": "data:geo:GSE87211", "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=GSE87211", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE87211", "version": null, "note": "The following information was supplied regarding data availability:The data are available at NCBI GEO (GSE39582, GSE87211) and at TCGA.The search instructions for TCGA:(1) Case keywords: “colon, rectosigmoid junction, and rectum [Primary Site]”, “TCGA[Program]”, “TCGA-COAD, TCGA-READ [Project]”, “Adenomas and Adenocarcinomas [Disease Type]”.(2) File keywords: “Transcriptome Profiling [Data Category]”, “Gene Expression Quantification [Data Category]”, “RNA-Seq [Experimental Strategy]”, “HTSeq—FPKM [Workflow Type]”, “Clinical [Data Category]”, “BCR XML [Data Format]”.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The following information was supplied regarding data availability:The data are available at NCBI GEO (GSE39582, GSE87211) and at TCGA.The search instructions for TCGA:(1) Case keywords: “colon, rectosigmoid junction, and rectum [Primary Site]”, “TCGA[Program]”, “TCGA-COAD, TCGA-READ [Project]”, “Adenomas and Adenocarcinomas [Disease Type]”.(2) File keywords: “Transcriptome Profiling [Data Category]”, “Gene Expression Quantification [Data Category]”, “RNA-Seq [Experimental Strategy]”, “HTSeq—FPKM [Workflow Type]”, “Clinical [Data Category]”, “BCR XML [Data Format]”.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2325238", "GSM2325239", "GSM2325240", "GSM2325241", "GSM2325242", "GSM2325243", "GSM2325244", "GSM2325245", "GSM2325246", "GSM2325247", "GSM2325248", "GSM2325249", "GSM2325250", "GSM2325251", "GSM2325252", "GSM2325253", "GSM2325254", "GSM2325255", "GSM2325256", "GSM2325257", "GSM2325258", "GSM2325259", "GSM2325260", "GSM2325261", "GSM2325262", "GSM2325263", "GSM2325264", "GSM2325265", "GSM2325266", "GSM2325267", "GSM2325268", "GSM2325269", "GSM2325270", "GSM2325271", "GSM2325272", "GSM2325273", "GSM2325274", "GSM2325275", "GSM2325276", "GSM2325277", "GSM2325278", "GSM2325279", "GSM2325280", "GSM2325281", "GSM2325282", "GSM2325283", "GSM2325284", "GSM2325285", "GSM2325286", "GSM2325287", "GSM2325288", "GSM2325289", "GSM2325290", "GSM2325291", "GSM2325292", "GSM2325293", "GSM2325294", "GSM2325295", "GSM2325296", "GSM2325297", "GSM2325298", "GSM2325299", "GSM2325300", "GSM2325301", "GSM2325302", "GSM2325303", "GSM2325304", "GSM2325305", "GSM2325306", "GSM2325307", "GSM2325308", "GSM2325309", "GSM2325310", "GSM2325311", "GSM2325312", "GSM2325313", "GSM2325314", "GSM2325315", "GSM2325316", "GSM2325317", "GSM2325318", "GSM2325319", "GSM2325320", "GSM2325321", "GSM2325322", "GSM2325323", "GSM2325324", "GSM2325325", "GSM2325326", "GSM2325327", "GSM2325328", "GSM2325329", "GSM2325330", "GSM2325331", "GSM2325332", "GSM2325333", "GSM2325334", "GSM2325335", "GSM2325336", "GSM2325337", "GSM2325338", "GSM2325339", "GSM2325340", "GSM2325341", "GSM2325342", "GSM2325343", "GSM2325344", "GSM2325345", "GSM2325346", "GSM2325347", "GSM2325348", "GSM2325349", "GSM2325350", "GSM2325351", "GSM2325352", "GSM2325353", "GSM2325354", "GSM2325355", "GSM2325356", "GSM2325357", "GSM2325358", "GSM2325359", "GSM2325360", "GSM2325361", "GSM2325362", "GSM2325363", "GSM2325364", "GSM2325365", "GSM2325366", "GSM2325367", "GSM2325368", "GSM2325369", "GSM2325370", "GSM2325371", "GSM2325372", "GSM2325373", "GSM2325374", "GSM2325375", "GSM2325376", "GSM2325377", "GSM2325378", "GSM2325379", "GSM2325380", "GSM2325381", "GSM2325382", "GSM2325383", "GSM2325384", "GSM2325385", "GSM2325386", "GSM2325387", "GSM2325388", "GSM2325389", "GSM2325390", "GSM2325391", "GSM2325392", "GSM2325393", "GSM2325394", "GSM2325395", "GSM2325396", "GSM2325397", "GSM2325398", "GSM2325399", "GSM2325400", "GSM2325401", "GSM2325402", "GSM2325403", "GSM2325404", "GSM2325405", "GSM2325406", "GSM2325407", "GSM2325408", "GSM2325409", "GSM2325410", "GSM2325411", "GSM2325412", "GSM2325413", "GSM2325414", "GSM2325415", "GSM2325416", "GSM2325417", "GSM2325418", "GSM2325419", "GSM2325420", "GSM2325421", "GSM2325422", "GSM2325423", "GSM2325424", "GSM2325425", "GSM2325426", "GSM2325427", "GSM2325428", "GSM2325429", "GSM2325430", "GSM2325431", "GSM2325432", "GSM2325433", "GSM2325434", "GSM2325435", "GSM2325436", "GSM2325437", "GSM2325438", "GSM2325439", "GSM2325440", "GSM2325441", "GSM2325442", "GSM2325443", "GSM2325444", "GSM2325445", "GSM2325446", "GSM2325447", "GSM2325448", "GSM2325449", "GSM2325450", "GSM2325451", "GSM2325452", "GSM2325453", "GSM2325454", "GSM2325455", "GSM2325456", "GSM2325457", "GSM2325458", "GSM2325459", "GSM2325460", "GSM2325461", "GSM2325462", "GSM2325463", "GSM2325464", "GSM2325465", "GSM2325466", "GSM2325467", "GSM2325468", "GSM2325469", "GSM2325470", "GSM2325471", "GSM2325472", "GSM2325473", "GSM2325474", "GSM2325475", "GSM2325476", "GSM2325477", "GSM2325478", "GSM2325479", "GSM2325480", "GSM2325481", "GSM2325482", "GSM2325483", "GSM2325484", "GSM2325485", "GSM2325486", "GSM2325487", "GSM2325488", "GSM2325489", "GSM2325490", "GSM2325491", "GSM2325492", "GSM2325493", "GSM2325494", "GSM2325495", "GSM2325496", "GSM2325497", "GSM2325498", "GSM2325499", "GSM2325500", "GSM2325501", "GSM2325502", "GSM2325503", "GSM2325504", "GSM2325505", "GSM2325506", "GSM2325507", "GSM2325508", "GSM2325509", "GSM2325510", "GSM2325511", "GSM2325512", "GSM2325513", "GSM2325514", "GSM2325515", "GSM2325516", "GSM2325517", "GSM2325518", "GSM2325519", "GSM2325520", "GSM2325521", "GSM2325522", "GSM2325523", "GSM2325524", "GSM2325525", "GSM2325526", "GSM2325527", "GSM2325528", "GSM2325529", "GSM2325530", "GSM2325531", "GSM2325532", "GSM2325533", "GSM2325534", "GSM2325535", "GSM2325536", "GSM2325537", "GSM2325538", "GSM2325539", "GSM2325540", "GSM2325541", "GSM2325542", "GSM2325543", "GSM2325544", "GSM2325545", "GSM2325546", "GSM2325547", "GSM2325548", "GSM2325549", "GSM2325550", "GSM2325551", "GSM2325552", "GSM2325553", "GSM2325554", "GSM2325555", "GSM2325556", "GSM2325557", "GSM2325558", "GSM2325559", "GSM2325560", "GSM2325561", "GSM2325562", "GSM2325563", "GSM2325564", "GSM2325565", "GSM2325566", "GSM2325567", "GSM2325568", "GSM2325569", "GSM2325570", "GSM2325571", "GSM2325572", "GSM2325573", "GSM2325574", "GSM2325575", "GSM2325576", "GSM2325577", "GSM2325578", "GSM2325579", "GSM2325580", "GSM2325581", "GSM2325582", "GSM2325583", "GSM2325584", "GSM2325585", "GSM2325586", "GSM2325587", "GSM2325588", "GSM2325589", "GSM2325590", "GSM2325591", "GSM2325592", "GSM2325593", "GSM2325594", "GSM2325595", "GSM2325596", "GSM2325597", "GSM2325598", "GSM2325599", "GSM2325600"], "sample_count": 363, "group_sizes": null, "group_sizes_basis": null, "platform": "13497", "taxon": "Homo sapiens", "title": "Colorectal cancer susceptibility loci as predictive markers of rectal cancer prognosis after surgery", "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:32953273:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:734f3146a06520dbf43bd74b24c4db898ee0b370ed8abe7fc8d639ec78702142", "bytes": 206, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[10]/table-wrap[1]#table-1", "version": null, "note": "Functions of genes in the prognostic gene signatures.", "structure": {"pmcid": "PMC7474523", "section_index": 10, "section_title": "Construction prognosis model for TCGA colorectal cancer cohort", "row_count": 0, "column_count": 0}, "table": {"label": "Table 1", "caption": "Functions of genes in the prognostic gene signatures.", "rows": [], "row_count": 0, "column_count": 0, "numeric_cells": 0, "header_rows": 0, "locator": "section[10]/table-wrap[1]#table-1"}}], "gaps": ["asset:data:geo:GSE39582 not downloaded", "asset:data:geo:GSE39582 licence not read", "asset:data:geo:GSE87211 not downloaded", "asset:data:geo:GSE87211 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "edger", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We screened differentially expressed metabolism-related genes using the Wilcox Test with R-package “edgeR” (Robinson, McCarthy & Smyth, 2010), and “limma”."}}, {"id": "method-2", "family": "differential_expression", "specific": "limma_voom", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 0.8, "band": "high", "quote": "limma"}}, {"id": "method-3", "family": "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"}}], "targets": [], "gaps": []}, "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: edger."}, "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": ["GSE39582", "GSE87211"], "resolved_accessions": ["GSE39582", "GSE87211"], "statements": ["The following information was supplied regarding data availability:The data are available at NCBI GEO (GSE39582, GSE87211) and at TCGA.The search instructions for TCGA:(1) Case keywords: “colon, rectosigmoid junction, and rectum [Primary Site]”, “TCGA[Program]”, “TCGA-COAD, TCGA-READ [Project]”, “Adenomas and Adenocarcinomas [Disease Type]”.(2) File keywords: “Transcriptome Profiling [Data Category]”, “Gene Expression Quantification [Data Category]”, “RNA-Seq [Experimental Strategy]”, “HTSeq—FPKM [Workflow Type]”, “Clinical [Data Category]”, “BCR XML [Data Format]”."], "basis": "The paper names GSE39582, GSE87211 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:32953273", "data:geo:GSE39582", "asset:table:pmid:32953273:1"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE39582"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:22:39Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 3, "usage": {"prompt_tokens": 29582, "completion_tokens": 2623, "cached_tokens": 776}}, "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:32953273", "type": "paper", "label": "pmid:32953273"}, {"id": "source:pmid:32953273", "type": "manuscript", "label": "PMID 32953273 full text"}, {"id": "data:geo:GSE39582", "type": "dataset", "label": "GEO GSE39582"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32953273", "type": "paper", "label": "pmid:32953273"}, {"id": "source:pmid:32953273", "type": "manuscript", "label": "PMID 32953273 full text"}, {"id": "data:geo:GSE39582", "type": "dataset", "label": "GEO GSE39582"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32953273", "type": "extraction", "used": ["source:pmid:32953273"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE39582", "type": "accession_resolution", "used": ["data:geo:GSE39582"], "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:32953273", "parent_hash": "sha256:9bbeca1fba775df542dd2584e8d6c9ad489e9ec6ec0c3fea2df9bf1a4f12e081", "fork_of": null, "generation": 7}, "gaps": ["asset:data:geo:GSE39582 licence not read", "asset:data:geo:GSE39582 not downloaded", "asset:data:geo:GSE87211 licence not read", "asset:data:geo:GSE87211 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We screened differentially expressed metabolism-related genes using the Wilcox Test with R-package “edgeR” (Robinson, McCarthy & Smyth, 2010), and “limma”."], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:43:52+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}}}