{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:32021241", "kind": "science-record", "revision": 9, "content_hash": "sha256:e2acd78045bad6f621d6343f7994c2a4b3e8bde93989184aa45f778faa62de48", "created_at": "2026-11-01T15:40:55Z", "updated_at": "2026-11-01T22:44:33Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Potential Prognostic and Diagnostic Values of CDC6, CDC45, ORC6 and SNHG7 in Colorectal Cancer.", "doi": "10.2147/OTT.S231941", "pmid": "32021241", "authors": ["Yang Hu", "Liping Wang", "Zhixing Li", "Zirui Wan", "Mingjie Shao", "Shaobin Wu", "Guo Wang"], "journal": "OncoTargets and therapy", "year": 2019, "abstract": "BACKGROUND: Colorectal cancer (CRC) is a common human malignancy. The aims of this study are to investigate the gene expression profile of CRC and to explore potential strategy for CRC diagnosis, therapy and prognosis.\nMETHODS: We use affy and Limma package of Bioconductor R to do differential expression genes (DEGs) and differential expression lncRNAs (DELs) analysis from the gene datasets (GSE8671, GSE21510, GSE32323, GSE39582 and TCGA) respectively. Then, DEGs were analyzed by GO and KEGG pathway and Kaplan-Meier survival curve and Cox regression analyses were used to find aberrantly expressed genes associated with survival outcome of CRC patients. Real-time PCR assay was used to verify the aberrantly expressed genes expression in CRC samples.\nRESULTS: 306 up-regulation and 213 down-regulation common DEGs were found. A total of 485 DELs were identified, of which 241 up-regulated and 244 down-regulated. Then, GO and KEGG pathway analyses showed that DEGs were involved in cell cycle, mineral absorption, DNA replication, and Nitrogen metabolism. Among them, Kaplan-Meier survival curve and Cox regression analyses revealed that CDC6, CDC45, ORC6 and SNHG7 levels were significantly associated with survival outcome of CRC patients. Finally, real-time PCR assay was used to verify that the CDC6, CDC45, ORC6 and SNHG7 expression were up-regulated in 198 CRC samples compared with the expression levels in individual-matched adjacent mucosa samples.\nCONCLUSION: CDC6, CDC45, ORC6 and SNHG7 are implicated in CRC initiation and progression and could be explored as potential diagnosis, therapy and prognosis targets for CRC.", "claims": [{"id": "claim-method", "statement": "The DEG analysis between tumor and non-tumor samples of the GSE8671, GSE21510, GSE32323, and GSE39582 datasets and the DELs between tumor and non-tumor of TCGA dataset were performed with the Limma package of Bioconductor R (http://www.bioconductor.org/packages/release/bioc/html/limma.html).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32021241", "locator": "sections[4] \"Identification of DEGs\" paragraph 2", "quote": "The DEG analysis between tumor and non-tumor samples of the GSE8671, GSE21510, GSE32323, and GSE39582 datasets and the DELs between tumor and non-tumor of TCGA dataset were performed with the Limma package of Bioconductor R (http://www.bioconductor.org/packages/release/bioc/html/limma.html)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:32021241", "locator": "sections[3] \"Colorectal Cancer Datasets\" paragraph 2", "quote": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO."}], "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:32021241"], "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:GSE21510"], "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:GSE21510"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:32021241", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/OTT.S231941", "sha256": "sha256:d77f9f42173ac20c8cabf52d941f468148d85ab17eff5ac0b367fdbb484269e1", "bytes": 36937, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/OTT.S231941", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC6942537", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE21510", "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=GSE21510", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21510", "version": null, "note": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM537330", "GSM537331", "GSM537332", "GSM537333", "GSM537334", "GSM537335", "GSM537336", "GSM537337", "GSM537338", "GSM537339", "GSM537340", "GSM537341", "GSM537342", "GSM537343", "GSM537344", "GSM537345", "GSM537346", "GSM537347", "GSM537348", "GSM537349", "GSM537350", "GSM537351", "GSM537352", "GSM537353", "GSM537354", "GSM537355", "GSM537356", "GSM537357", "GSM537358", "GSM537359", "GSM537360", "GSM537361", "GSM537362", "GSM537363", "GSM537364", "GSM537365", "GSM537366", "GSM537367", "GSM537368", "GSM537369", "GSM537370", "GSM537371", "GSM537372", "GSM537373", "GSM537374", "GSM537375", "GSM537376", "GSM537377", "GSM537378", "GSM537379", "GSM537380", "GSM537381", "GSM537382", "GSM537383", "GSM537384", "GSM537385", "GSM537386", "GSM537387", "GSM537388", "GSM537389", "GSM537390", "GSM537391", "GSM537392", "GSM537393", "GSM537394", "GSM537395", "GSM537396", "GSM537397", "GSM537398", "GSM537399", "GSM537400", "GSM537401", "GSM537402", "GSM537403", "GSM537404", "GSM537405", "GSM537406", "GSM537407", "GSM537408", "GSM537409", "GSM537410", "GSM537411", "GSM537412", "GSM537413", "GSM537414", "GSM537415", "GSM537416", "GSM537417", "GSM537418", "GSM537419", "GSM537420", "GSM537421", "GSM537422", "GSM537423", "GSM537424", "GSM537425", "GSM537426", "GSM537427", "GSM537428", "GSM537429", "GSM537430", "GSM537431", "GSM537432", "GSM537433", "GSM549099", "GSM549100", "GSM549101", "GSM549102", "GSM549103", "GSM549104", "GSM549105", "GSM549106", "GSM549107", "GSM549108", "GSM549109", "GSM549110", "GSM549111", "GSM549112", "GSM549113", "GSM549114", "GSM549115", "GSM549116", "GSM549117", "GSM549118", "GSM549119", "GSM549120", "GSM549121", "GSM549122", "GSM549123", "GSM549124", "GSM549125", "GSM549126", "GSM549127", "GSM549128", "GSM549129", "GSM549130", "GSM549131", "GSM549132", "GSM549133", "GSM549134", "GSM549135", "GSM549136", "GSM549137", "GSM549138", "GSM549139", "GSM549140", "GSM549141", "GSM549142"], "sample_count": 148, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Clinical Significance of Osteoprotegerin Expression in Human Colorectal Cancer", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE32323", "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=GSE32323", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32323", "version": null, "note": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM800742", "GSM800743", "GSM800744", "GSM800745", "GSM800746", "GSM800747", "GSM800748", "GSM800749", "GSM800750", "GSM800751", "GSM800752", "GSM800753", "GSM800754", "GSM800755", "GSM800756", "GSM800757", "GSM800758", "GSM800759", "GSM800760", "GSM800761", "GSM800762", "GSM800763", "GSM800764", "GSM800765", "GSM800766", "GSM800767", "GSM800768", "GSM800769", "GSM800770", "GSM800771", "GSM800772", "GSM800773", "GSM800774", "GSM800775", "GSM800776", "GSM800777", "GSM800778", "GSM800779", "GSM800780", "GSM800781", "GSM800782", "GSM800783", "GSM800784", "GSM800785"], "sample_count": 44, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Screening for Epigenetically Masked Genes in Colorectal Cancer using 5-aza-2’-deoxycytidine treatment, Microarray and Gene Expression Profile", "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": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "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": "data:geo:GSE8671", "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=GSE8671", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE8671", "version": null, "note": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO.", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM215051", "GSM215052", "GSM215053", "GSM215054", "GSM215055", "GSM215056", "GSM215057", "GSM215058", "GSM215059", "GSM215060", "GSM215061", "GSM215062", "GSM215063", "GSM215064", "GSM215065", "GSM215066", "GSM215067", "GSM215068", "GSM215069", "GSM215070", "GSM215071", "GSM215072", "GSM215073", "GSM215074", "GSM215075", "GSM215076", "GSM215077", "GSM215078", "GSM215079", "GSM215080", "GSM215081", "GSM215082", "GSM215083", "GSM215084", "GSM215085", "GSM215086", "GSM215087", "GSM215088", "GSM215089", "GSM215090", "GSM215091", "GSM215092", "GSM215093", "GSM215094", "GSM215095", "GSM215096", "GSM215097", "GSM215098", "GSM215099", "GSM215100", "GSM215101", "GSM215102", "GSM215103", "GSM215104", "GSM215105", "GSM215106", "GSM215107", "GSM215108", "GSM215109", "GSM215110", "GSM215111", "GSM215112", "GSM215113", "GSM215114"], "sample_count": 64, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Transcriptome profile of human colorectal adenomas.", "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:32021241:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:7c7352de1e01e71d1585153b13dfda3741e0c8e9f8c80c43be44afb7fb889d81", "bytes": 2655, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[1]#T0001", "version": null, "note": "GO Analysis of DEGs Between Paired Tumor and Non-Tumor Sample", "structure": {"pmcid": "PMC6942537", "section_index": 11, "section_title": "Functional Enrichment Analysis of DEGs", "row_count": 31, "column_count": 5}, "table": {"label": "Table 1", "caption": "GO Analysis of DEGs Between Paired Tumor and Non-Tumor Sample", "rows": [["Category", "Term/Gene Function", "Count", "%", "P value"], ["GOTERM_BP_DIRECT", "GO:0051301~cell division", "42", "8.25", "4.11E-15"], ["GOTERM_BP_DIRECT", "GO:0007067~mitotic nuclear division", "35", "6.88", "9.67E-15"], ["GOTERM_BP_DIRECT", "GO:0000082~G1/S transition of mitotic cell cycle", "19", "3.73", "3.17E-10"], ["GOTERM_BP_DIRECT", "GO:0007052~mitotic spindle organization", "9", "1.77", "1.06E-06"], ["GOTERM_BP_DIRECT", "GO:0007059~chromosome segregation", "12", "2.36", "2.26E-06"], ["GOTERM_BP_DIRECT", "GO:0008283~cell proliferation", "28", "5.50", "3.56E-06"], ["GOTERM_BP_DIRECT", "GO:0006260~DNA replication", "17", "3.34", "5.94E-06"], ["GOTERM_BP_DIRECT", "GO:0006730~one-carbon metabolic process", "8", "1.57", "1.34E-05"], ["GOTERM_BP_DIRECT", "DNA replication initiation", "8", "1.57", "2.11E-05"], ["GOTERM_BP_DIRECT", "GO:0000086~G2/M transition of mitotic cell cycle", "15", "2.95", "2.53E-05"], ["GOTERM_CC_DIRECT", "GO:0000922~spindle pole", "14", "2.55", "6.25E-06"], ["GOTERM_CC_DIRECT", "GO:0000776~kinetochore", "12", "2.75", "9.20E-06"], ["GOTERM_CC_DIRECT", "GO:0000777~condensed chromosome kinetochore", "13", "2.36", "3.06E-06"], ["GOTERM_CC_DIRECT", "GO:0005819~spindle", "14", "2.75", "1.97E-05"], ["GOTERM_CC_DIRECT", "GO:0030496~midbody", "14", "2.75", "3.89E-05"], ["GOTERM_CC_DIRECT", "GO:0005654~nucleoplasm", "105", "20.62", "1.33E-04"], ["GOTERM_CC_DIRECT", "GO:0005615~extracellular space", "57", "11.20", "5.22E-04"], ["GOTERM_CC_DIRECT", "GO:0000775~chromosome, centromeric region", "8", "1.57", "7.40E-04"], ["GOTERM_CC_DIRECT", "GO:0000940~condensed chromosome outer kinetochore", "4", "0.79", "9.38E-04"], ["GOTERM_CC_DIRECT", "GO:0005876~spindle microtubule", "7", "1.38", "0.001009"], ["GOTERM_MF_DIRECT", "GO:0005515~protein binding", "282", "55.40", "5.39E-06"], ["GOTERM_MF_DIRECT", "GO:0008009~chemokine activity", "9", "1.77", "4.20E-05"], ["GOTERM_MF_DIRECT", "GO:0004089~carbonate dehydratase activity", "5", "0.98", "4.07E-04"], ["GOTERM_MF_DIRECT", "GO:0045236~CXCR chemokine receptor binding", "4", "0.79", "0.001411"], ["GOTERM_MF_DIRECT", "GO:0003688~DNA replication origin binding", "4", "0.79", "0.002664"], ["GOTERM_MF_DIRECT", "GO:0003678~DNA helicase activity", "5", "0.98", "0.003495"], ["GOTERM_MF_DIRECT", "GO:0005179~hormone activity", "9", "1.77", "0.003657"], ["GOTERM_MF_DIRECT", "GO:0016491~oxidoreductase activity", "13", "2.55", "0.007638"], ["GOTERM_MF_DIRECT", "GO:0008017~microtubule binding", "13", "2.55", "0.010269"], ["GOTERM_MF_DIRECT", "GO:0003697~single-stranded DNA binding", "8", "1.58", "0.012249"]], "row_count": 31, "column_count": 5, "numeric_cells": 119, "header_rows": 1, "locator": "section[11]/table-wrap[1]#T0001"}}, {"id": "asset:table:pmid:32021241:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:1abf316d5aaa5d7e9ba5de60ddd54f9b25472c99f0b497638cdee2849ef20392", "bytes": 1086, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[11]/table-wrap[2]#T0002", "version": null, "note": "Pathway Analysis of DEGs Between Paired Tumor and Non-Tumor Samples", "structure": {"pmcid": "PMC6942537", "section_index": 11, "section_title": "Functional Enrichment Analysis of DEGs", "row_count": 8, "column_count": 5}, "table": {"label": "Table 2", "caption": "Pathway Analysis of DEGs Between Paired Tumor and Non-Tumor Samples", "rows": [["Pathway", "Count", "Term/Gene Function", "%", "P value"], ["hsa04110: Cell cycle", "21", "CDC6, CDK1, DBF4, TTK, CHEK1, CDC20, PTTG1, MCM2, CDK4, MCM3, CDC25B, CCNB1, CDC45, MAD2L1, MCM7, CDKN2B, BUB1B, ORC6, MAD2L2, MYC, CCNA2", "4.13", "6.82E-10"], ["hsa04978: Mineral absorption", "9", "SLC26A3, TRPM6, MT1M, MT2A, CYBRD1, MT1E, MT1H, MT1X, MT1F", "1.77", "6.14E-05"], ["hsa03030: DNA replication", "7", "PRIM1, RFC4, MCM7, MCM2, MCM3, RNASEH2A, FEN1", "1.38", "6.66E-04"], ["hsa00910: Nitrogen metabolism", "5", "CA12, CA7, CA4, CA2, CA1", "0.98", "0.001445"], ["hsa04964: Proximal tubule bicarbonate reclamation", "4", "CA4, CA2, SLC4A4, PCK1", "0.79", "0.031313"], ["hsa04640: Hematopoietic cell lineage", "7", "IL1R2, CR2, CD44, MS4A1, ITGA2, IL6R, CD1D", "1.38", "0.044065"], ["hsa03008: Ribosome biogenesis in eukaryotes", "7", "WDR75, RAN, NOB1, RIOK1, WDR43, RBM28, RPP40", "1.38", "0.048443"]], "row_count": 8, "column_count": 5, "numeric_cells": 33, "header_rows": 1, "locator": "section[11]/table-wrap[2]#T0002"}}, {"id": "asset:table:pmid:32021241:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:200f1b1ec484d6ce3303d0a91a01e587b42f220b4d2c40d485240ab02388e206", "bytes": 1137, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[1]#T0003", "version": null, "note": "Relationship of the Expression Levels of CDC6, CDC45, ORC6 and CRC Clinicopathologic Characteristics in GSE39582 Dataset", "structure": {"pmcid": "PMC6942537", "section_index": 12, "section_title": "The Expression of CDC6, CDC45, ORC6 and lncRNA SNHG7 in Colorectal Cancer Datasets", "row_count": 13, "column_count": 8}, "table": {"label": "Table 3", "caption": "Relationship of the Expression Levels of CDC6, CDC45, ORC6 and CRC Clinicopathologic Characteristics in GSE39582 Dataset", "rows": [["Characteristics", "", "CDC6", "P-value", "CDC45", "P-value", "ORC6", "P-value"], ["Invasion depth", "", "", "0.280", "", "0.173", "", "0.003"], ["T1, T2", "60", "6.429±0.133", "", "6.770±0.077", "", "8.208±0.083", ""], ["T3, T4", "486", "6.275±0.047", "", "6.656±0.031", "", "7.938±0.028", ""], ["Lymph node metastasis", "", "", "< 0.001", "", "< 0.001", "", "0.902"], ["N0", "302", "6.457±0.059", "", "6.791±0.038", "", "7.967±0.035", ""], ["N1, N2", "238", "6.101±0.067", "", "6.531±0.045", "", "7.973±0.042", ""], ["Distant metastasis", "", "", "0.001", "", "< 0.001", "", "0.727"], ["M0", "482", "6.344±0.047", "", "6.709±0.031", "", "7.969±0.028", ""], ["M1", "61", "5.870±0.132", "", "6.337±0.082", "", "7.938±0.084", ""], ["TNM stage", "", "", "< 0.001", "", "< 0.001", "", "0.788"], ["I, II", "301", "6.456±0.059", "", "6.785±0.037", "", "7.965±0.035", ""], ["III, IV", "265", "6.052±0.064", "", "6.503±0.042", "", "7.950±0.040", ""]], "row_count": 13, "column_count": 8, "numeric_cells": 45, "header_rows": 1, "locator": "section[12]/table-wrap[1]#T0003"}}, {"id": "asset:table:pmid:32021241:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:954685cd19da08f13d0c12edd377bf8980a3744dfeb590470c2091e13588b3f9", "bytes": 706, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[12]/table-wrap[2]#T0004", "version": null, "note": "Relationship of the Expression Levels of CDC6, CDC45, ORC6 and CRC Clinicopathologic Characteristics in TCGA", "structure": {"pmcid": "PMC6942537", "section_index": 12, "section_title": "The Expression of CDC6, CDC45, ORC6 and lncRNA SNHG7 in Colorectal Cancer Datasets", "row_count": 13, "column_count": 4}, "table": {"label": "Table 4", "caption": "Relationship of the Expression Levels of CDC6, CDC45, ORC6 and CRC Clinicopathologic Characteristics in TCGA", "rows": [["Characteristics", "", "SNHG7", "P-value"], ["Invasion depth", "", "", "0.154"], ["T1, T2", "126", "9.865±0.534", ""], ["T3, T4", "492", "10.73±0.274", ""], ["Lymph node metastasis", "", "", "0.124"], ["N0", "351", "10.23±0.319", ""], ["N1, N2", "265", "11.00±0.380", ""], ["Distant metastasis", "", "", "0.804"], ["M0", "465", "10.70±0.285", ""], ["M1", "87", "10.87±0.604", ""], ["TNM stage", "", "", "0.141"], ["I, II", "346", "10.25±0.330", ""], ["III, IV", "268", "10.97±0.366", ""]], "row_count": 13, "column_count": 4, "numeric_cells": 20, "header_rows": 1, "locator": "section[12]/table-wrap[2]#T0004"}}, {"id": "asset:table:pmid:32021241:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:da63fd255d8d6d0de718dc1debde26c5c7de15c395bc6d38416fcc0ab420f120", "bytes": 1019, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#T0005", "version": null, "note": "Correlations Between Gene (CDC6, CDC45 and ORC6) Expression and Pathology Parameters of CRC Specimens in GSE39582 Dataset", "structure": {"pmcid": "PMC6942537", "section_index": 13, "section_title": "CDC6, CDC45, ORC6 and lncRNA SNHG7 Expression as Prognostic Indicators for Colorectal Cancer", "row_count": 9, "column_count": 7}, "table": {"label": "Table 5", "caption": "Correlations Between Gene (CDC6, CDC45 and ORC6) Expression and Pathology Parameters of CRC Specimens in GSE39582 Dataset", "rows": [["Risk Factors", "Univariate Analysis", "Multivariate Analysis"], ["HR", "P-value", "95% CI", "HR", "P-value", "95% CI"], ["CDC6 expression", "0.391", "< 0.001", "0.272–0.563", "0.581", "0.002", "0.414–0.815"], ["CDC45 expression", "0.522", "< 0.001", "0.376–0.724", "0.711", "0.041", "0.512–0.987"], ["ORC6 expression", "0.671", "0.0168", "0.484–0.931", "0.692", "0.0268", "0.500–0.959"], ["TNM stage (I/II, III/IV)", "2.325", "< 0.001", "1.666–3.245", "10.75", "<0.001", "4.695–24.39"], ["Lymph node metastasis (N0, N1/N2)", "2.444", "< 0.001", "1.697–3.520", "5.486", "<0.001", "2.613–11.516"], ["Invasion depth (T1/T2, T3/T4)", "2.259", "0.0040", "1.297–3.933", "4.065", "0.006", "1.499–10.99"], ["Distant metastasis (M0, M1)", "2.033", "0.1311", "0.809–5.105", "", "", ""]], "row_count": 9, "column_count": 7, "numeric_cells": 42, "header_rows": 2, "locator": "section[13]/table-wrap[1]#T0005"}}, {"id": "asset:table:pmid:32021241:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:4466de48f4519edf2d9e0e8746714b398a8bf5d848facb7de896866aa1497b6c", "bytes": 811, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#T0006", "version": null, "note": "Correlations Between lncRNA SNHG7 Expression and Pathology Parameters of CRC Specimens in TCGA", "structure": {"pmcid": "PMC6942537", "section_index": 13, "section_title": "CDC6, CDC45, ORC6 and lncRNA SNHG7 Expression as Prognostic Indicators for Colorectal Cancer", "row_count": 7, "column_count": 7}, "table": {"label": "Table 6", "caption": "Correlations Between lncRNA SNHG7 Expression and Pathology Parameters of CRC Specimens in TCGA", "rows": [["Risk Factors", "Univariate Analysis", "Multivariate Analysis"], ["HR", "P-value", "95% CI", "HR", "P-value", "95% CI"], ["SNHG7 expression", "1.632", "0.0066", "1.146–2.325", "1.493", "0.0030", "1.039–2.145"], ["Distant metastasis (M0, M1)", "9.232", "< 0.001", "5.196–16.40", "2.833", "<0.001", "1.815–4.405"], ["TNM stage (I/II, III/IV)", "2.861", "0.0198", "1.988–4.116", "2.042", "0.001", "1.336–3.121"], ["Lymph node metastasis (N0, N1/N2)", "2.806", "< 0.001", "1.953–4.032", "", "0.588", ""], ["Tumor invasion depth (T1/T2, T3/T4)", "2.014", "0.0027", "1.274–3.183", "", "0.180", ""]], "row_count": 7, "column_count": 7, "numeric_cells": 28, "header_rows": 2, "locator": "section[13]/table-wrap[2]#T0006"}}], "gaps": ["asset:data:geo:GSE21510 not downloaded", "asset:data:geo:GSE21510 licence not read", "asset:data:geo:GSE32323 not downloaded", "asset:data:geo:GSE32323 licence not read", "asset:data:geo:GSE39582 not downloaded", "asset:data:geo:GSE39582 licence not read", "asset:data:geo:GSE8671 not downloaded", "asset:data:geo:GSE8671 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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": 1.0, "band": "verbatim", "quote": "The DEG analysis between tumor and non-tumor samples of the GSE8671, GSE21510, GSE32323, and GSE39582 datasets and the DELs between tumor and non-tumor of TCGA dataset were performed with the Limma package of Bioconductor R (http://www.bioconductor.org/packages/release/bioc/html/limma.html)."}}, {"id": "method-2", "family": "survival_analysis", "specific": "kaplan_meier", "label": "Survival analysis", "dsl_operations": ["survival_km"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.7, "band": "medium", "quote": "Kaplan-Meier"}}, {"id": "method-3", "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-4", "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-5", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "Pathway Enrichment"}}, {"id": "method-6", "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 analysis"}}, {"id": "method-7", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "χ2"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "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: limma_voom."}, "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": ["GSE8671", "GSE21510", "GSE32323", "GSE39582"], "resolved_accessions": ["GSE8671", "GSE21510", "GSE32323", "GSE39582"], "statements": ["The discovery datasets GSE8671,9 GSE21510,10 GSE3232311 and GSE3958212 were downloaded from the GEO."], "basis": "The paper names GSE8671, GSE21510, GSE32323, GSE39582 in 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:32021241", "data:geo:GSE21510", "asset:table:pmid:32021241:1", "asset:table:pmid:32021241:2", "asset:table:pmid:32021241:3", "asset:table:pmid:32021241:4", "asset:table:pmid:32021241:5", "asset:table:pmid:32021241:6"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE21510"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:18:09Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 3, "usage": {"prompt_tokens": 31835, "completion_tokens": 1798, "cached_tokens": 10760}}, "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:32021241", "type": "paper", "label": "pmid:32021241"}, {"id": "source:pmid:32021241", "type": "manuscript", "label": "PMID 32021241 full text"}, {"id": "data:geo:GSE21510", "type": "dataset", "label": "GEO GSE21510"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:32021241", "type": "paper", "label": "pmid:32021241"}, {"id": "source:pmid:32021241", "type": "manuscript", "label": "PMID 32021241 full text"}, {"id": "data:geo:GSE21510", "type": "dataset", "label": "GEO GSE21510"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-32021241", "type": "extraction", "used": ["source:pmid:32021241"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE21510", "type": "accession_resolution", "used": ["data:geo:GSE21510"], "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:32021241", "parent_hash": "sha256:f5b406ef05a08a355baa36d284f5ce1fadeaf1bb9ebfe7ab0442ecc415404eda", "fork_of": null, "generation": 8}, "gaps": ["asset:data:geo:GSE21510 licence not read", "asset:data:geo:GSE21510 not downloaded", "asset:data:geo:GSE32323 licence not read", "asset:data:geo:GSE32323 not downloaded", "asset:data:geo:GSE39582 licence not read", "asset:data:geo:GSE39582 not downloaded", "asset:data:geo:GSE8671 licence not read", "asset:data:geo:GSE8671 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "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": ["iated with survival outcome of CRC patients. Real-time PCR assay was used to verify the aberrantly expr", "h survival outcome of CRC patients. Finally, real-time PCR assay was used to verify that the CDC6, CDC4"], "order_basis": "paper_text_order:711", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["d for more detailed and specific analysis of microarray data.18,19 DAVID (Database for Annotation, V"], "order_basis": "paper_text_order:2102", "id": "assay:2"}, {"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": ["The DEG analysis between tumor and non-tumor samples of the GSE8671, GSE21510, GSE32323, and GSE39582 datasets and the DELs between tumor and non-tumor of TCGA dataset were performed with the Limma package of Bioconductor R (http://www.bioconductor.org/packages/release/bioc/html/limma.html)."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:32:08+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}}}