{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:25551447", "kind": "science-record", "revision": 5, "content_hash": "sha256:fb6cc85d18be7aaa4d8a156f7ffe55ed419f500ea6b70f6de6562a9106405f2c", "created_at": "2026-11-01T15:40:07Z", "updated_at": "2026-11-01T21:19:56Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Meta-analysis of prostate cancer gene expression data identifies a novel discriminatory signature enriched for glycosylating enzymes.", "doi": "10.1186/s12920-014-0074-9", "pmid": "25551447", "authors": ["Stefan J Barfeld", "Philip East", "Verena Zuber", "Ian G Mills"], "journal": "BMC medical genomics", "year": 2014, "abstract": "BACKGROUND: Tumorigenesis is characterised by changes in transcriptional control. Extensive transcript expression data have been acquired over the last decade and used to classify prostate cancers. Prostate cancer is, however, a heterogeneous multifocal cancer and this poses challenges in identifying robust transcript biomarkers.\nMETHODS: In this study, we have undertaken a meta-analysis of publicly available transcriptomic data spanning datasets and technologies from the last decade and encompassing laser capture microdissected and macrodissected sample sets.\nRESULTS: We identified a 33 gene signature that can discriminate between benign tissue controls and localised prostate cancers irrespective of detection platform or dissection status. These genes were significantly overexpressed in localised prostate cancer versus benign tissue in at least three datasets within the Oncomine Compendium of Expression Array Data. In addition, they were also overexpressed in a recent exon-array dataset as well a prostate cancer RNA-seq dataset generated as part of the The Cancer Genomics Atlas (TCGA) initiative. Biologically, glycosylation was the single enriched process associated with this 33 gene signature, encompassing four glycosylating enzymes. We went on to evaluate the performance of this signature against three individual markers of prostate cancer, v-ets avian erythroblastosis virus E26 oncogene homolog (ERG) expression, prostate specific antigen (PSA) expression and androgen receptor (AR) expression in an additional independent dataset. Our signature had greater discriminatory power than these markers both for localised cancer and metastatic disease relative to benign tissue, or in the case of metastasis, also localised prostate cancer.\nCONCLUSION: In conclusion, robust transcript biomarkers are present within datasets assembled over many years and cohorts and our study provides both examples and a strategy for refining and comparing datasets to obtain additional markers as more data are generated.", "claims": [{"id": "claim-method", "statement": "To determine if any of the enriched modules were capable of segregating samples on phenotype we built contingency tables across clinical conditions from each of the data sets (Tomlins [5] and Ramaswamy [6]) for induced and repressed modules and tested for sample enrichment using a Fisher’s Exact test.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25551447", "locator": "sections[7] \"Phenotype segregation\" paragraph 2", "quote": "To determine if any of the enriched modules were capable of segregating samples on phenotype we built contingency tables across clinical conditions from each of the data sets (Tomlins [5] and Ramaswamy [6]) for induced and repressed modules and tested for sample enrichment using a Fisher’s Exact test."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:25551447", "locator": "sections[3] \"Description of datasets\" paragraph 2", "quote": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A meta-analysis using public transcriptomic data from multiple datasets, detection platforms, and dissection methods identified a 33-gene signature that discriminated benign tissue from localised prostate cancer.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:25551447", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "We identified a 33 gene signature that can discriminate between benign tissue controls and localised prostate cancers irrespective of detection platform or dissection status."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A meta-analysis using public transcriptomic data from multiple datasets, detection platforms, and dissection methods identified a 33-gene signature that discriminated benign tissue from localised prostate cancer.", "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:25551447"], "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:GSE21034"], "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:GSE21034"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:25551447", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s12920-014-0074-9", "sha256": "sha256:fc1fb30ee842d27c0500fc48276c7ccedcabe8fd50af74099e5bbfdd2b0e9081", "bytes": 79241, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s12920-014-0074-9", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC4351903", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE21034", "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=GSE21034", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21034", "version": null, "note": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM526134", "GSM526135", "GSM526136", "GSM526137", "GSM526138", "GSM526139", "GSM526140", "GSM526141", "GSM526142", "GSM526143", "GSM526144", "GSM526145", "GSM526146", "GSM526147", "GSM526148", "GSM526149", "GSM526150", "GSM526151", "GSM526152", "GSM526153", "GSM526154", "GSM526155", "GSM526156", "GSM526157", "GSM526158", "GSM526159", "GSM526160", "GSM526161", "GSM526162", "GSM526163", "GSM526164", "GSM526165", "GSM526166", "GSM526167", "GSM526168", "GSM526169", "GSM526170", "GSM526171", "GSM526172", "GSM526173", "GSM526174", "GSM526175", "GSM526176", "GSM526177", "GSM526178", "GSM526179", "GSM526180", "GSM526181", "GSM526182", "GSM526183", "GSM526184", "GSM526185", "GSM526186", "GSM526187", "GSM526188", "GSM526189", "GSM526190", "GSM526191", "GSM526192", "GSM526193", "GSM526194", "GSM526195", "GSM526196", "GSM526197", "GSM526198", "GSM526199", "GSM526200", "GSM526201", "GSM526202", "GSM526203", "GSM526204", "GSM526205", "GSM526206", "GSM526207", "GSM526208", "GSM526209", "GSM526210", "GSM526211", "GSM526212", "GSM526213", "GSM526214", "GSM526215", "GSM526216", "GSM526217", "GSM526218", "GSM526219", "GSM526220", "GSM526221", "GSM526222", "GSM526223", "GSM526224", "GSM526225", "GSM526226", "GSM526227", "GSM526228", "GSM526229", "GSM526230", "GSM526231", "GSM526232", "GSM526233", "GSM526234", "GSM526235", "GSM526236", "GSM526237", "GSM526238", "GSM526239", "GSM526240", "GSM526241", "GSM526242", "GSM526243", "GSM526244", "GSM526245", "GSM526246", "GSM526247", "GSM526248", "GSM526249", "GSM526250", "GSM526251", "GSM526252", "GSM526253", "GSM526254", "GSM526255", "GSM526256", "GSM526257", "GSM526258", "GSM526259", "GSM526260", "GSM526261", "GSM526262", "GSM526263", "GSM526264", "GSM526265", "GSM526266", "GSM526267", "GSM526268", "GSM526269", "GSM526270", "GSM526271", "GSM526272", "GSM526273", "GSM526274", "GSM526275", "GSM526276", "GSM526277", "GSM526278", "GSM526279", "GSM526280", "GSM526281", "GSM526282", "GSM526283", "GSM526284", "GSM526285", "GSM526286", "GSM526287", "GSM526288", "GSM526289", "GSM526290", "GSM526291", "GSM526292", "GSM526293", "GSM526294", "GSM526295", "GSM526296", "GSM526297", "GSM526298", "GSM526299", "GSM526300", "GSM526301", "GSM526302", "GSM526303", "GSM526304", "GSM526305", "GSM526306", "GSM526307", "GSM526308", "GSM526309", "GSM526310", "GSM526311", "GSM526312", "GSM526313", "GSM526314", "GSM526315", "GSM526316", "GSM526317", "GSM526318", "GSM527858", "GSM527859", "GSM527860", "GSM527861", "GSM527862", "GSM527863", "GSM527864", "GSM527865", "GSM527866", "GSM527867", "GSM527868", "GSM527869", "GSM527870", "GSM527871", "GSM527872", "GSM527873", "GSM527874", "GSM527875", "GSM527876", "GSM527877", "GSM527878", "GSM527879", "GSM527880", "GSM527881", "GSM527882", "GSM527883", "GSM527884", "GSM527885", "GSM527886", "GSM527887", "GSM527888", "GSM527889", "GSM527890", "GSM527891", "GSM527892", "GSM527893", "GSM527894", "GSM527895", "GSM527896", "GSM527897", "GSM527898", "GSM527899", "GSM527900", "GSM527901", "GSM527902", "GSM527903", "GSM527904", "GSM527905", "GSM527906", "GSM527907", "GSM527908", "GSM527909", "GSM527910", "GSM527911", "GSM527912", "GSM527913", "GSM527914", "GSM527915", "GSM527916", "GSM527917", "GSM527918", "GSM527919", "GSM527920", "GSM527921", "GSM527922", "GSM527923", "GSM527924", "GSM527925", "GSM527926", "GSM527927", "GSM527928", "GSM527929", "GSM527930", "GSM527931", "GSM527932", "GSM527933", "GSM527934", "GSM527935", "GSM527936", "GSM527937", "GSM527938", "GSM527939", "GSM527940", "GSM527941", "GSM527942", "GSM527943", "GSM527944", "GSM527945", "GSM527946", "GSM527947", "GSM527948", "GSM527949", "GSM527950", "GSM527951", "GSM527952", "GSM527953", "GSM527954", "GSM527955", "GSM527956", "GSM527957", "GSM527958", "GSM527959", "GSM527960", "GSM527961", "GSM527962", "GSM527963", "GSM527965", "GSM527966", "GSM527968", "GSM527970", "GSM527971", "GSM527972", "GSM527973", "GSM527974", "GSM527975", "GSM527977", "GSM527979", "GSM527980", "GSM527982", "GSM527984", "GSM527985", "GSM527986", "GSM527987", "GSM527988", "GSM527989", "GSM527990", "GSM527991", "GSM527992", "GSM527993", "GSM527994", "GSM527995", "GSM527996", "GSM527997", "GSM527998", "GSM527999", "GSM528000", "GSM528001", "GSM528002", "GSM528003", "GSM528004", "GSM528005", "GSM528006", "GSM528007", "GSM528008", "GSM528009", "GSM528010", "GSM528011", "GSM528012", "GSM528013", "GSM528014", "GSM528015", "GSM528016", "GSM528017", "GSM528018", "GSM528019", "GSM528020", "GSM528021", "GSM528022", "GSM528023", "GSM528024", "GSM528025", "GSM528026", "GSM528027", "GSM528028", "GSM528029", "GSM528030", "GSM528031", "GSM528032", "GSM528033", "GSM528034", "GSM528035", "GSM528036", "GSM528037", "GSM528038", "GSM528039", "GSM528040", "GSM528041", "GSM528042", "GSM528043", "GSM528044", "GSM528045", "GSM528046", "GSM528047", "GSM528048", "GSM528049"], "sample_count": 370, "group_sizes": null, "group_sizes_basis": null, "platform": "5188;10264", "taxon": "Homo sapiens", "title": "Whole-transcript and exon-level expression data for human primary and metastatic prostate cancer samples and control normal adjacent benign prostate", "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:GSE3325", "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=GSE3325", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3325", "version": null, "note": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM74875", "GSM74876", "GSM74877", "GSM74878", "GSM74879", "GSM74880", "GSM74881", "GSM74882", "GSM74883", "GSM74884", "GSM74885", "GSM74886", "GSM74887", "GSM74888", "GSM74889", "GSM74890", "GSM74891", "GSM74892", "GSM74893"], "sample_count": 19, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Integrative Genomic and Proteomic Analysis of Prostate Cancer Reveals Signatures of Metastatic Progression", "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:GSE35988", "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=GSE35988", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE35988", "version": null, "note": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM878750", "GSM878751", "GSM878752", "GSM878753", "GSM878754", "GSM878755", "GSM878756", "GSM878757", "GSM878758", "GSM878759", "GSM878760", "GSM878761", "GSM878762", "GSM878763", "GSM878764", "GSM878765", "GSM878766", "GSM878767", "GSM878768", "GSM878769", "GSM878770", "GSM878771", "GSM878772", "GSM878773", "GSM878774", "GSM878775", "GSM878776", "GSM878777", "GSM878778", "GSM878779", "GSM878780", "GSM878781", "GSM878782", "GSM878783", "GSM878784", "GSM878785", "GSM878786", "GSM878787", "GSM878788", "GSM878789", "GSM878790", "GSM878791", "GSM878792", "GSM878793", "GSM878794", "GSM878795", "GSM878796", "GSM878797", "GSM878798", "GSM878799", "GSM878800", "GSM878801", "GSM878802", "GSM878803", "GSM878804", "GSM878805", "GSM878806", "GSM878807", "GSM878808", "GSM878809", "GSM878810", "GSM878811", "GSM878812", "GSM878813", "GSM878814", "GSM878815", "GSM878816", "GSM878817", "GSM878818", "GSM878819", "GSM878820", "GSM878821", "GSM878822", "GSM878823", "GSM878824", "GSM878825", "GSM878826", "GSM878827", "GSM878828", "GSM878829", "GSM878830", "GSM878831", "GSM878832", "GSM878833", "GSM878834", "GSM878835", "GSM878836", "GSM878837", "GSM878838", "GSM878839", "GSM878840", "GSM878841", "GSM878842", "GSM878843", "GSM878844", "GSM878845", "GSM878846", "GSM878847", "GSM878848", "GSM878849", "GSM878850", "GSM878851", "GSM878852", "GSM878853", "GSM878854", "GSM878855", "GSM878856", "GSM878857", "GSM878858", "GSM878859", "GSM878860", "GSM878861", "GSM878862", "GSM878863", "GSM878864", "GSM878865", "GSM878866", "GSM878867", "GSM878868", "GSM878869", "GSM878870", "GSM878871", "GSM878882", "GSM878883", "GSM878884", "GSM878885", "GSM878886", "GSM878887", "GSM878888", "GSM878889", "GSM878890", "GSM878891", "GSM878892", "GSM878893", "GSM878894", "GSM878895", "GSM878896", "GSM878897", "GSM878898", "GSM878899", "GSM878900", "GSM878901", "GSM878902", "GSM878903", "GSM878904", "GSM878905", "GSM878906", "GSM878907", "GSM878908", "GSM878909", "GSM878910", "GSM878911", "GSM878912", "GSM878913", "GSM878914", "GSM878915", "GSM878916", "GSM878917", "GSM878918", "GSM878919", "GSM878920", "GSM878921", "GSM878922", "GSM878923", "GSM878924", "GSM878925", "GSM878926", "GSM878927", "GSM878928", "GSM878929", "GSM878930", "GSM878931", "GSM878932", "GSM878933", "GSM878934", "GSM878935", "GSM878936", "GSM878937", "GSM878938", "GSM878939", "GSM878940", "GSM878941", "GSM878942", "GSM878943", "GSM878944", "GSM878945", "GSM878946", "GSM878947", "GSM878948", "GSM878949", "GSM878950", "GSM878951", "GSM878953", "GSM878956", "GSM878957", "GSM878959", "GSM878962", "GSM878963", "GSM878964", "GSM878965", "GSM878966", "GSM878967", "GSM878968", "GSM878969", "GSM878970", "GSM878971", "GSM878972", "GSM878973", "GSM878974", "GSM878975", "GSM878976", "GSM878977", "GSM878978", "GSM878979", "GSM878980", "GSM878981", "GSM878982", "GSM878983", "GSM878984", "GSM878985", "GSM878986", "GSM878987", "GSM878988", "GSM878989", "GSM878990", "GSM878991", "GSM878992", "GSM878993", "GSM878994", "GSM878995", "GSM878996", "GSM878997", "GSM878998", "GSM878999", "GSM879000", "GSM879001", "GSM879002", "GSM879003", "GSM879004", "GSM879005", "GSM879006", "GSM879007", "GSM879008", "GSM879009"], "sample_count": 244, "group_sizes": null, "group_sizes_basis": null, "platform": "6480;9128;6848;9075", "taxon": "Homo sapiens", "title": "The Mutational Landscape of Lethal Castrate Resistant Prostate 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:GSE6099", "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=GSE6099", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE6099", "version": null, "note": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325).", "access_statement_kind": "repository_route_statement", "sample_accessions": ["GSM141184", "GSM141185", "GSM141186", "GSM141243", "GSM141244", "GSM141246", "GSM141247", "GSM141248", "GSM141249", "GSM141258", "GSM141259", "GSM141260", "GSM141261", "GSM141262", "GSM141263", "GSM141264", "GSM141265", "GSM141266", "GSM141267", "GSM141330", "GSM141334", "GSM141335", "GSM141336", "GSM141337", "GSM141338", "GSM141339", "GSM141340", "GSM141341", "GSM141342", "GSM141343", "GSM141356", "GSM141357", "GSM141358", "GSM141359", "GSM141360", "GSM141361", "GSM141362", "GSM141363", "GSM141364", "GSM141365", "GSM141366", "GSM141367", "GSM141368", "GSM141369", "GSM141370", "GSM141371", "GSM141372", "GSM141373", "GSM141374", "GSM141375", "GSM141376", "GSM141377", "GSM141378", "GSM141379", "GSM141380", "GSM141381", "GSM141382", "GSM141383", "GSM141384", "GSM141385", "GSM141386", "GSM141387", "GSM141388", "GSM141389", "GSM141390", "GSM141391", "GSM141392", "GSM141393", "GSM141394", "GSM141395", "GSM141396", "GSM141397", "GSM141398", "GSM141399", "GSM141400", "GSM141401", "GSM141402", "GSM141403", "GSM141404", "GSM141405", "GSM141406", "GSM141407", "GSM141408", "GSM141409", "GSM141410", "GSM141411", "GSM141412", "GSM141413", "GSM141414", "GSM141415", "GSM141416", "GSM141417", "GSM141418", "GSM141419", "GSM141420", "GSM141421", "GSM141422", "GSM141423", "GSM141424", "GSM141425", "GSM141426", "GSM141427", "GSM141428", "GSM141429"], "sample_count": 104, "group_sizes": null, "group_sizes_basis": null, "platform": "2013", "taxon": "Homo sapiens", "title": "Integrative Molecular Concepts Modeling of Prostate Cancer Progression", "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:25551447:1", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:2cb5ede2e698480a688ed010a1d88effce921fbb4820299e78b38d607f36e512", "bytes": 8143, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[1]#Tab1", "version": null, "note": "KEGG pathway enrichment analysis for the genes comprising signature 1 (101.6.1)", "structure": {"pmcid": "PMC4351903", "section_index": 13, "section_title": "Results and discussion", "row_count": 36, "column_count": 13}, "table": {"label": "Table 1", "caption": "KEGG pathway enrichment analysis for the genes comprising signature 1 (101.6.1)", "rows": [["Category", "Term", "Count", "%", "PValue", "Genes", "List Total", "Pop Hits", "Pop Total", "Fold Enrichment", "Bonferroni", "Benjamini", "FDR"], ["KEGG_PATHWAY", "hsa04510:Focal adhesion", "37", "2.86", "2.01E-06", "CAV2, CAV1, MYL5, MYL2, TNC, PTEN, MYL9, VCL, IGF1R, LAMB3, LAMB2, ITGB8, ILK, ITGB6, PDGFC, PAK1, THBS1, THBS4, COL4A4, PRKCA, ACTB, MET, ITGA1, ACTN1, IGF1, HGF, COL4A6, FLNA, LAMA4, ITGA6, CCND2, ITGA5, JUN, ITGA8, COL1A2, MYLK, PTENP1, PARVA", "404", "201", "5085", "2.32", "3.42E-04", "3.42E-04", "0"], ["KEGG_PATHWAY", "hsa05414:Dilated cardiomyopathy", "21", "1.62", "2.37E-05", "ACTB, SLC8A1, ACTC1, MYL2, LMNA, ITGA1, IGF1, CACNB2, TPM2, TPM1, TPM4, TGFB2, DES, ITGA6, ITGA5, ITGB8, PLN, ITGA8, ITGB6, PRKACB, SGCB", "404", "92", "5085", "2.87", "0", "0", "0.03"], ["KEGG_PATHWAY", "hsa05410:Hypertrophic cardiomyopathy (HCM)", "20", "1.55", "2.50E-05", "ACTB, SLC8A1, ACTC1, IL6, MYL2, LMNA, ITGA1, IGF1, CACNB2, TPM2, TPM1, TPM4, TGFB2, DES, ITGA6, ITGA5, ITGB8, ITGA8, ITGB6, SGCB", "404", "85", "5085", "2.96", "0", "0", "0.03"], ["KEGG_PATHWAY", "hsa00280:Valine, leucine and isoleucine degradation", "12", "0.93", "4.71E-04", "MCCC2, ALDH7A1, ALDH1B1, MCEE, AOX1, BCKDHB, DLD, ACAD8, ACAT1, HIBADH, ALDH3A2, AUH", "404", "44", "5085", "3.43", "0.08", "0.02", "0.57"], ["KEGG_PATHWAY", "hsa04512:ECM-receptor interaction", "17", "1.31", "7.54E-04", "COL4A4, TNC, ITGA1, COL4A6, CD47, LAMA4, LAMB3, LAMB2, CD44, ITGA6, ITGB8, ITGA5, ITGA8, ITGB6, COL1A2, THBS1, THBS4", "404", "84", "5085", "2.55", "0.12", "0.03", "0.92"], ["KEGG_PATHWAY", "hsa04270:Vascular smooth muscle contraction", "20", "1.55", "0", "PRKCA, ACTA2, PPP1R12B, CALD1, MRVI1, KCNMB1, ITPR1, MYL9, ITPR2, EDNRA, AGTR1, ACTG2, PLCB4, GNAQ, PLA2G12A, MYH11, PRKACB, PLCB1, PPP1R14A, MYLK", "404", "112", "5085", "2.25", "0.17", "0.03", "1.35"], ["KEGG_PATHWAY", "hsa05412:Arrhythmogenic right ventricular cardiomyopathy (ARVC)", "14", "1.08", "0.01", "ACTB, SLC8A1, LMNA, ITGA1, ACTN1, CACNB2, DES, ITGA6, ITGB8, ITGA5, PKP2, ITGA8, ITGB6, SGCB", "404", "76", "5085", "2.32", "0.65", "0.14", "7.2"], ["KEGG_PATHWAY", "hsa04610:Complement and coagulation cascades", "13", "1.01", "0.01", "C4A, MASP1, C4B, CFB, C1S, CD59, KLKB1, F3, SERPINE1, SERPINA1, CFI, C2, PROS1", "404", "69", "5085", "2.37", "0.71", "0.14", "8.49"], ["KEGG_PATHWAY", "hsa04310:Wnt signaling pathway", "22", "1.7", "0.01", "PRKCA, CSNK1A1, WNT5B, CAMK2G, MMP7, FZD1, DKK1, PLCB4, SFRP1, CCND2, SFRP2, JUN, SFRP4, PRICKLE2, PPP3CB, CAMK2D, WIF1, PRKACB, AXIN2, PLCB1, MYC, APC", "404", "151", "5085", "1.83", "0.72", "0.13", "8.79"], ["KEGG_PATHWAY", "hsa05332:Graft-versus-host disease", "9", "0.7", "0.01", "HLA-DQB1, IL6, HLA-DRB1, HLA-DRB4, HLA-C, HLA-DPA1, HLA-B, FAS, HLA-DMB, HLA-G, HLA-DQA1", "404", "39", "5085", "2.9", "0.82", "0.16", "11.58"], ["KEGG_PATHWAY", "hsa00590:Arachidonic acid metabolism", "11", "0.85", "0.01", "CYP2U1, GPX2, PTGIS, PTGS2, PTGDS, ALOX15B, PLA2G12A, PTGS1, GGTLC3, GGT1, ALOX5, CBR3", "404", "56", "5085", "2.47", "0.86", "0.16", "13.08"], ["KEGG_PATHWAY", "hsa00480:Glutathione metabolism", "10", "0.77", "0.02", "GSTM1, GPX2, GSTM2, GSTA4, GGTLC3, GSTZ1, GSTO2, ANPEP, GSTT2, GGT1, GSTO1", "404", "50", "5085", "2.52", "0.93", "0.2", "17.11"], ["KEGG_PATHWAY", "hsa04514:Cell adhesion molecules (CAMs)", "19", "1.47", "0.02", "HLA-DQB1, HLA-DRB1, CDH1, ITGB2, HLA-C, NEO1, HLA-B, HLA-DMB, CDH3, HLA-DQA1, HLA-G, ITGA6, ITGB8, ITGA8, PVRL3, CD2, HLA-DRB4, HLA-DPA1, JAM2, NEGR1, SELE", "404", "132", "5085", "1.81", "0.93", "0.19", "17.38"], ["KEGG_PATHWAY", "hsa04940:Type I diabetes mellitus", "9", "0.7", "0.02", "HLA-DQB1, HLA-DRB1, PTPRN2, HLA-DRB4, HLA-C, HLA-DPA1, HLA-B, FAS, HLA-DMB, HLA-G, HLA-DQA1", "404", "42", "5085", "2.7", "0.93", "0.17", "17.49"], ["KEGG_PATHWAY", "hsa04350:TGF-beta signaling pathway", "14", "1.08", "0.02", "SMAD6, FST, DCN, TGFB2, ACVR2A, ID1, ZFYVE16, ID4, ID3, THBS1, MYC, BMPR1A, ACVR1, THBS4", "404", "87", "5085", "2.03", "0.96", "0.19", "20.39"], ["KEGG_PATHWAY", "hsa04810:Regulation of actin cytoskeleton", "27", "2.09", "0.02", "FGFR2, FGF7, MYL5, MYL2, DIAPH2, FGF13, ITGB2, MYL9, VCL, GSN, ITGB8, ITGB6, RRAS, PDGFC, PAK1, FGF2, APC, ACTB, LIMK2, ITGA1, ACTN1, ITGA6, CHRM3, ITGA5, CFL2, ITGA8, MYLK", "404", "215", "5085", "1.58", "0.96", "0.18", "20.54"], ["KEGG_PATHWAY", "hsa05330:Allograft rejection", "8", "0.62", "0.02", "HLA-DQB1, HLA-DRB1, HLA-DRB4, HLA-C, HLA-DPA1, HLA-B, FAS, HLA-DMB, HLA-G, HLA-DQA1", "404", "36", "5085", "2.8", "0.97", "0.19", "22.63"], ["KEGG_PATHWAY", "hsa00330:Arginine and proline metabolism", "10", "0.77", "0.02", "ALDH7A1, ALDH18A1, ACY1, GATM, GLUD2, ALDH1B1, MAOB, OAT, ALDH3A2, CKB", "404", "53", "5085", "2.37", "0.98", "0.19", "23.67"], ["KEGG_PATHWAY", "hsa00982:Drug metabolism", "11", "0.85", "0.02", "GSTM1, GSTM2, CYP3A5, GSTA4, AOX1, MAOB, ADH5, GSTZ1, GSTO2, GSTT2, GSTO1", "404", "62", "5085", "2.23", "0.98", "0.18", "24.32"], ["KEGG_PATHWAY", "hsa05218:Melanoma", "12", "0.93", "0.02", "FGF7, MET, IGF1, CDH1, CDK6, FGF13, HGF, RB1, PTEN, IGF1R, PDGFC, FGF2, PTENP1", "404", "71", "5085", "2.13", "0.98", "0.18", "24.47"], ["KEGG_PATHWAY", "hsa05416:Viral myocarditis", "12", "0.93", "0.02", "ACTB, HLA-DQB1, CAV1, HLA-DRB1, ITGB2, HLA-C, HLA-B, HLA-DMB, HLA-DQA1, HLA-G, MYH11, HLA-DRB4, HLA-DPA1, SGCB", "404", "71", "5085", "2.13", "0.98", "0.18", "24.47"], ["KEGG_PATHWAY", "hsa05310:Asthma", "7", "0.54", "0.02", "FCER1A, HLA-DQB1, HLA-DRB1, HLA-DRB4, FCER1G, HLA-DPA1, HLA-DMB, HLA-DQA1", "404", "29", "5085", "3.04", "0.98", "0.18", "25.37"], ["KEGG_PATHWAY", "hsa00640:Propanoate metabolism", "7", "0.54", "0.04", "ALDH7A1, ALDH1B1, MCEE, SUCLA2, ACAT1, ACSS3, ALDH3A2", "404", "32", "5085", "2.75", "1", "0.25", "36.89"], ["KEGG_PATHWAY", "hsa04916:Melanogenesis", "14", "1.08", "0.05", "PRKCA, WNT5B, GNAI1, CAMK2G, CREB1, EDN1, FZD1, EDNRB, PLCB4, GNAQ, CAMK2D, CREB3L4, PRKACB, PLCB1", "404", "99", "5085", "1.78", "1", "0.3", "44.76"], ["KEGG_PATHWAY", "hsa04020:Calcium signaling pathway", "21", "1.62", "0.06", "PRKCA, SLC8A1, CAMK2G, PHKA1, PTGFR, ITPR1, ITPR2, EDNRA, AGTR1, EDNRB, GNAL, CD38, PLCB4, GNAQ, CHRM3, PLN, CAMK2D, PPP3CB, PRKACB, PLCB1, MYLK", "404", "176", "5085", "1.5", "1", "0.37", "54.64"], ["KEGG_PATHWAY", "hsa04530:Tight junction", "17", "1.31", "0.06", "PRKCA, ACTB, RAB3B, MYL5, MAGI2, ZAK, MYL2, MPDZ, GNAI1, ACTN1, AMOTL1, PTEN, MYL9, EPB41L2, MYH11, RRAS, JAM2, PTENP1", "404", "134", "5085", "1.6", "1", "0.36", "54.73"], ["KEGG_PATHWAY", "hsa05222:Small cell lung cancer", "12", "0.93", "0.07", "COL4A4, PTGS2, CDK6, RB1, PTEN, COL4A6, LAMB3, LAMA4, LAMB2, ITGA6, PIAS1, MYC, PTENP1", "404", "84", "5085", "1.8", "1", "0.36", "56.55"], ["KEGG_PATHWAY", "hsa04360:Axon guidance", "16", "1.24", "0.08", "LIMK2, GNAI1, MET, NTN4, SLIT2, EPHA3, SEMA5A, EPHA4, EPHB6, CFL2, PPP3CB, SEMA3C, EFNA5, UNC5D, PAK1, RASA1", "404", "129", "5085", "1.56", "1", "0.42", "65.75"], ["KEGG_PATHWAY", "hsa04115:p53 signaling pathway", "10", "0.77", "0.09", "SERPINB5, CCND2, SERPINE1, IGF1, CDK6, FAS, GADD45B, THBS1, CCNG2, PTEN, PTENP1", "404", "68", "5085", "1.85", "1", "0.42", "66.77"], ["KEGG_PATHWAY", "hsa04720:Long-term potentiation", "10", "0.77", "0.09", "PRKCA, PLCB4, GNAQ, CAMK2G, CAMK2D, PPP3CB, PRKACB, PLCB1, ITPR1, ITPR2", "404", "68", "5085", "1.85", "1", "0.42", "66.77"], ["KEGG_PATHWAY", "hsa04672:Intestinal immune network for IgA production", "8", "0.62", "0.09", "HLA-DQB1, IL6, TNFSF13B, HLA-DRB1, HLA-DRB4, HLA-DPA1, HLA-DMB, HLA-DQA1, TGFB2", "404", "49", "5085", "2.05", "1", "0.42", "68.02"], ["KEGG_PATHWAY", "hsa05322:Systemic lupus erythematosus", "13", "1.01", "0.09", "HLA-DQB1, HLA-DRB1, C4A, C4B, ACTN1, SSB, C1S, H2AFJ, HLA-DMB, HLA-DQA1, HLA-DRB4, HLA-DPA1, H3F3B, C2", "404", "99", "5085", "1.65", "1", "0.41", "68.42"], ["KEGG_PATHWAY", "hsa00620:Pyruvate metabolism", "7", "0.54", "0.09", "ALDH7A1, ALDH1B1, DLD, ACYP2, DLAT, ACAT1, ALDH3A2", "404", "40", "5085", "2.2", "1", "0.41", "69.45"], ["KEGG_PATHWAY", "hsa04730:Long-term depression", "10", "0.77", "0.09", "PRKCA, IGF1R, PLCB4, GNAQ, GNAI1, PLA2G12A, IGF1, PLCB1, ITPR1, ITPR2", "404", "69", "5085", "1.82", "1", "0.4", "69.5"], ["KEGG_PATHWAY", "hsa00980:Metabolism of xenobiotics by cytochrome P450", "9", "0.7", "0.1", "GSTM1, GSTM2, CYP3A5, GSTA4, ADH5, GSTZ1, GSTO2, GSTT2, GSTO1", "404", "60", "5085", "1.89", "1", "0.42", "71.98"]], "row_count": 36, "column_count": 13, "numeric_cells": 399, "header_rows": 1, "locator": "section[13]/table-wrap[1]#Tab1"}}, {"id": "asset:table:pmid:25551447:2", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:0dbcfc940c636802643cf3fb76169e54e516ad04ad2122595c16505c506170ea", "bytes": 1997, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[2]#Tab2", "version": null, "note": "KEGG pathway enrichment analysis for the genes comprising signature 2 (101.6.2)", "structure": {"pmcid": "PMC4351903", "section_index": 13, "section_title": "Results and discussion", "row_count": 10, "column_count": 13}, "table": {"label": "Table 2", "caption": "KEGG pathway enrichment analysis for the genes comprising signature 2 (101.6.2)", "rows": [["Category", "Term", "Count", "%", "PValue", "Genes", "List Total", "Pop Hits", "Pop Total", "Fold Enrichment", "Bonferroni", "Benjamini", "FDR"], ["KEGG_PATHWAY", "hsa04610:Complement and coagulation cascades", "10", "1.56", "0", "C1QA, FGG, A2M, C3, KLKB1, CD46, C1R, SERPING1, C1S, CFD", "219", "69", "5085", "3.37", "0.33", "0.33", "2.97"], ["KEGG_PATHWAY", "hsa04540:Gap junction", "10", "1.56", "0.01", "TJP1, ADCY2, GNAI1, PDGFA, TUBB6, GUCY1A3, GJA1, LPAR1, PRKACB, ITPR2", "219", "89", "5085", "2.61", "0.88", "0.65", "14.98"], ["KEGG_PATHWAY", "hsa04142:Lysosome", "11", "1.72", "0.03", "AGA, HGSNAT, LAMP2, CTSK, GM2A, PSAP, LGMN, CTSB, SCARB2, FUCA1, CLN5", "219", "117", "5085", "2.18", "0.99", "0.77", "28.69"], ["KEGG_PATHWAY", "hsa04270:Vascular smooth muscle contraction", "10", "1.56", "0.05", "PLA2G4A, ADCY2, CALD1, MRVI1, GUCY1A3, PRKCH, PRKACB, PPP1CB, MYLK, ITPR2", "219", "112", "5085", "2.07", "1", "0.87", "46.04"], ["KEGG_PATHWAY", "hsa04310:Wnt signaling pathway", "12", "1.88", "0.06", "CCND1, PRICKLE1, CCND2, BTRC, NFAT5, CAMK2D, TP53, MAPK10, PRKACB, FZD5, FZD4, FZD7", "219", "151", "5085", "1.85", "1", "0.85", "51.51"], ["KEGG_PATHWAY", "hsa05330:Allograft rejection", "5", "0.78", "0.07", "HLA-DRB5, HLA-DPB1, HLA-E, HLA-DOA, HLA-DRA", "219", "36", "5085", "3.22", "1", "0.84", "56.25"], ["KEGG_PATHWAY", "hsa05416:Viral myocarditis", "7", "1.1", "0.08", "CAV1, CCND1, HLA-DRB5, HLA-DPB1, HLA-E, HLA-DOA, HLA-DRA", "219", "71", "5085", "2.29", "1", "0.86", "64.57"], ["KEGG_PATHWAY", "hsa05332:Graft-versus-host disease", "5", "0.78", "0.08", "HLA-DRB5, HLA-DPB1, HLA-E, HLA-DOA, HLA-DRA", "219", "39", "5085", "2.98", "1", "0.82", "65.24"], ["KEGG_PATHWAY", "hsa04510:Focal adhesion", "14", "2.19", "0.09", "CAV1, PDGFA, MAPK10, FLNC, PPP1CB, VCL, CCND1, CCND2, ITGAV, COL6A2, RAP1A, THBS1, PIK3R1, MYLK", "219", "201", "5085", "1.62", "1", "0.81", "67.5"]], "row_count": 10, "column_count": 13, "numeric_cells": 102, "header_rows": 1, "locator": "section[13]/table-wrap[2]#Tab2"}}, {"id": "asset:table:pmid:25551447:3", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:994bf78a5b65f352c89f2aa42325987f18271937f4d4e91bf9ccaec7ad83b200", "bytes": 4366, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[3]#Tab3", "version": null, "note": "KEGG pathway enrichment analysis for the genes comprising signature 3 (101.6.3)", "structure": {"pmcid": "PMC4351903", "section_index": 13, "section_title": "Results and discussion", "row_count": 22, "column_count": 13}, "table": {"label": "Table 3", "caption": "KEGG pathway enrichment analysis for the genes comprising signature 3 (101.6.3)", "rows": [["Category", "Term", "Count", "%", "PValue", "Genes", "List Total", "Pop Hits", "Pop Total", "Fold Enrichment", "Bonferroni", "Benjamini", "FDR"], ["KEGG_PATHWAY", "hsa04110:Cell cycle", "36", "0.47", "9.03E-20", "E2F1, E2F2, E2F3, TTK, CHEK1, PTTG1, CCNE2, CCNE1, CDKN2A, MCM7, CDKN2C, CDKN2D, ORC6L, TFDP2, BUB1, CCNA2, STAG1, CDC7, CDC6, RBL1, SKP2, ESPL1, CDC20, MCM2, CDC25C, MCM4, CDC25A, CDC25B, CDKN1C, CCNB1, CCNB2, MAD2L1, PLK1, GSK3B, BUB1B, MAD2L2", "225", "125", "5085", "6.51", "1.29E-17", "1.29E-17", "1.07E-16"], ["KEGG_PATHWAY", "hsa03030:DNA replication", "12", "0.16", "2.15E-07", "RFC5, PRIM1, MCM7, RFC4, POLE2, LIG1, POLA1, POLA2, MCM2, RNASEH2A, MCM4, FEN1", "225", "36", "5085", "7.53", "3.08E-05", "1.54E-05", "2.55E-04"], ["KEGG_PATHWAY", "hsa04114:Oocyte meiosis", "18", "0.23", "4.82E-06", "SGOL1, AURKA, CDC20, ESPL1, PTTG1, CDC25C, CCNE2, CCNB1, CCNE1, CCNB2, MAD2L1, ADCY9, CALML3, PLK1, BUB1, FBXO5, CAMK2B, MAD2L2", "225", "110", "5085", "3.7", "6.89E-04", "2.30E-04", "0.01"], ["KEGG_PATHWAY", "hsa04914:Progesterone-mediated oocyte maturation", "14", "0.18", "8.26E-05", "HSP90AA1, CDC25C, CDC25A, CDC25B, CCNB1, CCNB2, MAD2L1, KRAS, ADCY9, PLK1, BUB1, MAD2L2, PIK3R3, CCNA2", "225", "86", "5085", "3.68", "0.01", "0", "0.1"], ["KEGG_PATHWAY", "hsa04115:p53 signaling pathway", "10", "0.13", "0", "CCNE2, CCNB1, CCNE1, CDKN2A, CCNB2, RRM2, TSC2, CHEK1, PMAIP1, GTSE1", "225", "68", "5085", "3.32", "0.32", "0.07", "3.16"], ["KEGG_PATHWAY", "hsa05222:Small cell lung cancer", "11", "0.14", "0", "E2F1, CCNE2, E2F2, CCNE1, CKS1B, E2F3, PTK2, SKP2, PIAS2, PIK3R3, ITGA2B", "225", "84", "5085", "2.96", "0.4", "0.08", "4.12"], ["KEGG_PATHWAY", "hsa04360:Axon guidance", "14", "0.18", "0", "PLXNA1, EFNB3, PLXNA2, DPYSL5, EPHB1, PTK2, KRAS, UNC5B, PAK2, UNC5A, FYN, GSK3B, SRGAP1, SRGAP2", "225", "129", "5085", "2.45", "0.45", "0.08", "4.83"], ["KEGG_PATHWAY", "hsa00240:Pyrimidine metabolism", "11", "0.14", "0.01", "PRIM1, TYMS, POLR3K, POLE2, RRM2, RRM1, DCK, POLA1, POLA2, NME7, TK1", "225", "95", "5085", "2.62", "0.71", "0.14", "9.63"], ["KEGG_PATHWAY", "hsa05219:Bladder cancer", "7", "0.09", "0.01", "E2F1, RPS6KA5, E2F2, E2F3, CDKN2A, KRAS, PGF", "225", "42", "5085", "3.77", "0.74", "0.14", "10.67"], ["KEGG_PATHWAY", "hsa05215:Prostate cancer", "10", "0.13", "0.02", "E2F1, CCNE2, E2F2, CCNE1, E2F3, HSP90AA1, KRAS, GSK3B, PIK3R3, CTNNB1", "225", "89", "5085", "2.54", "0.9", "0.2", "17.14"], ["KEGG_PATHWAY", "hsa00230:Purine metabolism", "14", "0.18", "0.02", "POLR3K, POLA1, DCK, POLA2, HPRT1, GMPS, NME7, GART, PRIM1, ADCY9, POLE2, RRM2, PKLR, RRM1", "225", "153", "5085", "2.07", "0.91", "0.2", "18.08"], ["KEGG_PATHWAY", "hsa03410:Base excision repair", "6", "0.08", "0.02", "POLE2, UNG, LIG1, MBD4, NTHL1, FEN1", "225", "35", "5085", "3.87", "0.92", "0.19", "18.86"], ["KEGG_PATHWAY", "hsa05214:Glioma", "8", "0.1", "0.02", "E2F1, E2F2, E2F3, CDKN2A, KRAS, CALML3, CAMK2B, PIK3R3", "225", "63", "5085", "2.87", "0.94", "0.2", "21.16"], ["KEGG_PATHWAY", "hsa05200:Pathways in cancer", "23", "0.3", "0.03", "E2F1, E2F2, FZD8, CKS1B, MSH6, E2F3, HSP90AA1, PGF, FGF9, SKP2, BIRC5, FZD2, CTNNB1, CTNNA2, CCNE2, CCNE1, PTK2, CDKN2A, KRAS, GSK3B, PIAS2, PIK3R3, ITGA2B", "225", "328", "5085", "1.58", "0.99", "0.27", "30.48"], ["KEGG_PATHWAY", "hsa00670:One carbon pool by folate", "4", "0.05", "0.03", "TYMS, MTHFD2, SHMT2, GART", "225", "16", "5085", "5.65", "0.99", "0.26", "31.03"], ["KEGG_PATHWAY", "hsa04916:Melanogenesis", "9", "0.12", "0.07", "FZD8, KRAS, ADCY9, CALML3, GSK3B, GNAS, CAMK2B, FZD2, CTNNB1", "225", "99", "5085", "2.05", "1", "0.47", "57.19"], ["KEGG_PATHWAY", "hsa05210:Colorectal cancer", "8", "0.1", "0.08", "FZD8, MSH6, KRAS, GSK3B, BIRC5, FZD2, PIK3R3, CTNNB1", "225", "84", "5085", "2.15", "1", "0.48", "60.57"], ["KEGG_PATHWAY", "hsa03430:Mismatch repair", "4", "0.05", "0.08", "RFC5, MSH6, RFC4, LIG1", "225", "23", "5085", "3.93", "1", "0.48", "61.82"], ["KEGG_PATHWAY", "hsa05223:Non-small cell lung cancer", "6", "0.08", "0.09", "E2F1, E2F2, E2F3, CDKN2A, KRAS, PIK3R3", "225", "54", "5085", "2.51", "1", "0.5", "66.23"], ["KEGG_PATHWAY", "hsa05218:Melanoma", "7", "0.09", "0.09", "E2F1, E2F2, E2F3, CDKN2A, KRAS, FGF9, PIK3R3", "225", "71", "5085", "2.23", "1", "0.5", "67.79"], ["KEGG_PATHWAY", "hsa05212:Pancreatic cancer", "7", "0.09", "0.1", "E2F1, E2F2, E2F3, CDKN2A, KRAS, PGF, PIK3R3", "225", "72", "5085", "2.2", "1", "0.5", "69.77"]], "row_count": 22, "column_count": 13, "numeric_cells": 236, "header_rows": 1, "locator": "section[13]/table-wrap[3]#Tab3"}}, {"id": "asset:table:pmid:25551447:4", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:8ff9b926c93d3e7792af534f6801cd0b880a88ca83956fb08581b9676e235134", "bytes": 1109, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[4]#Tab4", "version": null, "note": "KEGG pathway enrichment analysis for the genes comprising signature 3 (101.6.4)", "structure": {"pmcid": "PMC4351903", "section_index": 13, "section_title": "Results and discussion", "row_count": 6, "column_count": 13}, "table": {"label": "Table 4", "caption": "KEGG pathway enrichment analysis for the genes comprising signature 3 (101.6.4)", "rows": [["Category", "Term", "Count", "%", "PValue", "Genes", "List Total", "Pop Hits", "Pop Total", "Fold Enrichment", "Bonferroni", "Benjamini", "FDR"], ["KEGG_PATHWAY", "hsa00100:Steroid biosynthesis", "3", "0.1", "0.03", "SQLE, FDFT1, SC4MOL", "86", "17", "5085", "10.43", "0.97", "0.97", "30.81"], ["KEGG_PATHWAY", "hsa05200:Pathways in cancer", "11", "0.38", "0.05", "LAMA1, HRAS, PTK2, SOS1, CBL, VEGFA, PPARG, RALA, LEF1, MDM2, LAMB1", "86", "328", "5085", "1.98", "0.99", "0.93", "41.08"], ["KEGG_PATHWAY", "hsa04510:Focal adhesion", "8", "0.27", "0.05", "LAMA1, HRAS, PTK2, FLT1, DIAPH1, SOS1, VEGFA, LAMB1", "86", "201", "5085", "2.35", "1", "0.85", "44.04"], ["KEGG_PATHWAY", "hsa00330:Arginine and proline metabolism", "4", "0.14", "0.06", "ARG1, P4HA2, P4HA1, CPS1", "86", "53", "5085", "4.46", "1", "0.82", "49.31"], ["KEGG_PATHWAY", "hsa05216:Thyroid cancer", "3", "0.1", "0.08", "HRAS, PPARG, LEF1", "86", "29", "5085", "6.12", "1", "0.86", "63"]], "row_count": 6, "column_count": 13, "numeric_cells": 55, "header_rows": 1, "locator": "section[13]/table-wrap[4]#Tab4"}}, {"id": "asset:table:pmid:25551447:5", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:07bf757b23ab964e7fa5c0cb8a3c6a1286ebc9d0b6d252f4c1aff8698591edd8", "bytes": 1155, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[5]#Tab5", "version": null, "note": "KEGG pathway enrichment for the 71-gene signature capable of subclustering localised prostate cancer cases across multiple datasets", "structure": {"pmcid": "PMC4351903", "section_index": 13, "section_title": "Results and discussion", "row_count": 6, "column_count": 13}, "table": {"label": "Table 5", "caption": "KEGG pathway enrichment for the 71-gene signature capable of subclustering localised prostate cancer cases across multiple datasets", "rows": [["Category", "Term", "Count", "%", "PValue", "Genes", "List Total", "Pop Hits", "Pop Total", "Fold Enrichment", "Bonferroni", "Benjamini", "FDR"], ["KEGG_PATHWAY", "hsa04270:Vascular smooth muscle contraction", "5", "6.94", "0", "ACTG2, MYH11, KCNMB1, MYLK, MYL9", "26", "112", "5085", "8.73", "0.12", "0.12", "1.99"], ["KEGG_PATHWAY", "hsa05414:Dilated cardiomyopathy", "4", "5.56", "0.01", "DES, PLN, IGF1, TPM2", "26", "92", "5085", "8.5", "0.47", "0.27", "9.6"], ["KEGG_PATHWAY", "hsa04960:Aldosterone-regulated sodium reabsorption", "3", "4.17", "0.02", "IGF1, ATP1A2, IRS1", "26", "41", "5085", "14.31", "0.66", "0.31", "15.92"], ["KEGG_PATHWAY", "hsa04310:Wnt signaling pathway", "4", "5.56", "0.04", "SFRP1, CAMK2G, PRICKLE2, MYC", "26", "151", "5085", "5.18", "0.91", "0.45", "31.53"], ["KEGG_PATHWAY", "hsa05410:Hypertrophic cardiomyopathy (HCM)", "3", "4.17", "0.06", "DES, IGF1, TPM2", "26", "85", "5085", "6.9", "0.99", "0.57", "49.28"]], "row_count": 6, "column_count": 13, "numeric_cells": 56, "header_rows": 1, "locator": "section[13]/table-wrap[5]#Tab5"}}, {"id": "asset:table:pmid:25551447:6", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:c7f145b2c3b2d92c02475e704517063209e39ece2f18a6616af4fc697fdba183", "bytes": 874, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[6]#Tab6", "version": null, "note": "KEGG pathway enrichment analysis for the entire set of overexpressed genes in localised prostate cancer versus benign tissue in the Varambally dataset (GSE3325)", "structure": {"pmcid": "PMC4351903", "section_index": 13, "section_title": "Results and discussion", "row_count": 4, "column_count": 13}, "table": {"label": "Table 6", "caption": "KEGG pathway enrichment analysis for the entire set of overexpressed genes in localised prostate cancer versus benign tissue in the Varambally dataset (GSE3325)", "rows": [["Category", "Term", "Count", "%", "PValue", "Genes", "List Total", "Pop Hits", "Pop Total", "Fold Enrichment", "Bonferroni", "Benjamini", "FDR"], ["KEGG_PATHWAY", "hsa00512:O-Glycan biosynthesis", "3", "0.34", "0.01", "GALNTL4, GCNT1, ST6GALNAC1", "26", "30", "5085", "19.56", "0.43", "0.43", "8.95"], ["KEGG_PATHWAY", "hsa04610:Complement and coagulation cascades", "3", "0.34", "0.04", "C4A, C4B, SERPINA1", "26", "69", "5085", "8.5", "0.94", "0.75", "36.76"], ["KEGG_PATHWAY", "hsa05322:Systemic lupus erythematosus", "3", "0.34", "0.08", "C4A, C4B, HLA-DMB", "26", "99", "5085", "5.93", "1", "0.83", "58.75"]], "row_count": 4, "column_count": 13, "numeric_cells": 33, "header_rows": 1, "locator": "section[13]/table-wrap[6]#Tab6"}}, {"id": "asset:table:pmid:25551447:7", "role": "table", "format": "jats-table", "media_type": "application/vnd.jats.table+json", "uri": null, "sha256": "sha256:ea948976687da1ef22a5a9823824a52a895500426200766463f88c56fd0973be", "bytes": 632, "access": "open", "state": "verified", "reader": "read_table", "reader_status": "available", "identifier": "section[13]/table-wrap[7]#Tab7", "version": null, "note": "Comparison of the performance of a 31-gene signature with ERG, AR and KLK3 in discriminating between benign tissue, localised prostate cancer and metastatic disease", "structure": {"pmcid": "PMC4351903", "section_index": 13, "section_title": "Results and discussion", "row_count": 6, "column_count": 4}, "table": {"label": "Table 7", "caption": "Comparison of the performance of a 31-gene signature with ERG, AR and KLK3 in discriminating between benign tissue, localised prostate cancer and metastatic disease", "rows": [["Gene/signature", "AUC benign-local", "AUC benign-metastatic", "AUC localized-metastatic"], ["KLK3", "0.5204082", "0.9104938", "0.8707483"], ["ERG", "0.812616", "0.9326599", "0.6099773"], ["AR", "0.6581633", "0.8395062", "0.8435374"], ["31 Gene signature", "0.994898", "0.9938272", "0.957672"], ["Derived from the Grasso Data", "", "", ""]], "row_count": 6, "column_count": 4, "numeric_cells": 13, "header_rows": 1, "locator": "section[13]/table-wrap[7]#Tab7"}}], "gaps": ["asset:data:geo:GSE21034 not downloaded", "asset:data:geo:GSE21034 licence not read", "asset:data:geo:GSE3325 not downloaded", "asset:data:geo:GSE3325 licence not read", "asset:data:geo:GSE35988 not downloaded", "asset:data:geo:GSE35988 licence not read", "asset:data:geo:GSE6099 not downloaded", "asset:data:geo:GSE6099 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": null, "specific": null, "label": "Fisher’s Exact test", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To determine if any of the enriched modules were capable of segregating samples on phenotype we built contingency tables across clinical conditions from each of the data sets (Tomlins [5] and Ramaswamy [6]) for induced and repressed modules and tested for sample enrichment using a Fisher’s Exact test."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "blocked", "tier": "R4", "blocking_axis": "method", "blocked_on": "method:not_determinable", "axes": {"method": {"tier": "R4", "expressible": false, "required_operations": [], "missing_operations": [], "basis": "The reader quoted the method the paper names (Fisher’s Exact test), but the corpus's method extractor could not map it onto a DSL operation, so the method is published but not expressible."}, "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": ["GSE3325", "GSE6099", "GSE21034", "GSE35988"], "resolved_accessions": ["GSE3325", "GSE6099", "GSE21034", "GSE35988"], "statements": ["The expression array data were downloaded from GEO under accession number GSE3325 (http://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE3325)."], "basis": "The paper names GSE3325, GSE6099, GSE21034, GSE35988 in NCBI GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:25551447", "data:geo:GSE21034", "asset:table:pmid:25551447:1", "asset:table:pmid:25551447:2", "asset:table:pmid:25551447:3", "asset:table:pmid:25551447:4", "asset:table:pmid:25551447:5", "asset:table:pmid:25551447:6", "asset:table:pmid:25551447:7"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE21034"]}, "gaps": ["method:not_determinable"]}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-10-31T18:23:24Z", "independence": "same_provider"}, "evidence_check": {"method": "verbatim", "availability": null}, "calls": 8, "usage": {"prompt_tokens": 160629, "completion_tokens": 5263, "cached_tokens": 1952}}, "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:25551447", "type": "paper", "label": "pmid:25551447"}, {"id": "source:pmid:25551447", "type": "manuscript", "label": "PMID 25551447 full text"}, {"id": "data:geo:GSE21034", "type": "dataset", "label": "GEO GSE21034"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:25551447", "type": "paper", "label": "pmid:25551447"}, {"id": "source:pmid:25551447", "type": "manuscript", "label": "PMID 25551447 full text"}, {"id": "data:geo:GSE21034", "type": "dataset", "label": "GEO GSE21034"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-25551447", "type": "extraction", "used": ["source:pmid:25551447"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE21034", "type": "accession_resolution", "used": ["data:geo:GSE21034"], "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:25551447", "parent_hash": "sha256:64c4bc154bf9f8dacadf50f2adbaf6f4aeccc88b18169000600be1f2239b0307", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE21034 licence not read", "asset:data:geo:GSE21034 not downloaded", "asset:data:geo:GSE3325 licence not read", "asset:data:geo:GSE3325 not downloaded", "asset:data:geo:GSE35988 licence not read", "asset:data:geo:GSE35988 not downloaded", "asset:data:geo:GSE6099 licence not read", "asset:data:geo:GSE6099 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["exon-array dataset as well a prostate cancer RNA-seq dataset generated as part of the The Cancer", "rtaken a meta-analysis of publicly available transcriptomic data spanning datasets and technologies from"], "order_basis": "paper_text_order:502", "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":"2026-11-04T02:52:11+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}}}