{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:40428318", "kind": "science-record", "revision": 3, "content_hash": "sha256:cf17719e06c64e7a5a68f9e91ce0ac5d9ae8b3b513d82bbc55e8911990f7042e", "created_at": "2026-11-01T20:30:34Z", "updated_at": "2026-11-01T22:14:07Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Development and Experimental Validation of Machine Learning-Based Disulfidptosis-Related Ferroptosis Biomarkers in Inflammatory Bowel Disease.", "doi": "10.3390/genes16050496", "pmid": "40428318", "authors": ["Yongchao Liu", "Jing Shao", "Jie Zhang", "Mengmeng Sang", "Qiuyun Xu", "Liming Mao"], "journal": "Genes", "year": 2025, "abstract": "Background: Inflammatory bowel disease (IBD) is a chronic inflammatory condition of the gastrointestinal tract, defined by intestinal epithelial cell death. While ferroptosis and disulfidptosis have been linked to IBD pathogenesis, the functional significance of disulfidptosis-related ferroptosis genes (DRFGs) in this disease remains poorly characterized. This investigation sought to pinpoint DRFGs as diagnostic indicators and clarify their mechanistic contributions to IBD progression. Methods: Four IBD datasets (GSE65114, GSE87473, GSE102133, and GSE186582) from the GEO database were integrated to identify differentially expressed genes (DEGs) (|log2FC| > 0.585, adj. p < 0.05). A Pearson correlation analysis was used to link disulfidptosis and ferroptosis genes, followed by machine learning (LASSO and RF) to screen core DRFGs. The immune subtypes and single-cell sequencing (GSE217695) results were analyzed. A DSS-induced colitis Mus musculus (C57BL/6) model was used for validation. Results: Transcriptomic profiling identified 521 DEGs, with 16 defined as DRFGs. Nine hub genes showed diagnostic potential (AUC: 0.71-0.91). Functional annotation demonstrated that IBD-associated genes regulate diverse pathways, with a network analysis revealing their functional synergy. The PPI networks prioritized DUOX2, NCF2, ACSL4, GPX2, CBS, and LPCAT3 as central hubs. Two immune subtypes exhibited divergent DRFG expression. Single-cell mapping revealed epithelial/immune compartment specificity. The DSS-induced murine colitis model confirmed differential expression patterns of DRFGs, with concordant results between qRT-PCR and RNA-seq, emphasizing their pivotal regulatory roles in disease progression and potential for translational application. Conclusions: DRFGs mediate IBD progression via multi-signal pathway regulation across intestinal cell types, demonstrating diagnostic and prognostic potential.", "claims": [{"id": "claim-method", "statement": "A Pearson correlation analysis was used to link disulfidptosis and ferroptosis genes, followed by machine learning (LASSO and RF) to screen core DRFGs.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40428318", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A Pearson correlation analysis was used to link disulfidptosis and ferroptosis genes, followed by machine learning (LASSO and RF) to screen core DRFGs."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:40428318", "locator": "sections[37] \"Data Availability Statement\" paragraph 2", "quote": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors."}], "state": "complete"}, {"id": "claim-target-result", "statement": "Nine hub genes showed diagnostic potential (AUC: 0.71–0.91).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:40428318", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "Nine hub genes showed diagnostic potential (AUC: 0.71–0.91)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "Nine hub genes showed diagnostic potential (AUC: 0.71–0.91).", "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:40428318"], "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:GSE102133"], "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:GSE102133"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:40428318", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/genes16050496", "sha256": "sha256:66bc24d95ca0ef9d2efb609d80aff3e38bde56c7b72cf83d9139368fb83363e1", "bytes": 60087, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/genes16050496", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12110833", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE102133", "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=GSE102133", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE102133", "version": null, "note": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2728650", "GSM2728651", "GSM2728652", "GSM2728653", "GSM2728654", "GSM2728655", "GSM2728656", "GSM2728657", "GSM2728658", "GSM2728659", "GSM2728660", "GSM2728661", "GSM2728662", "GSM2728663", "GSM2728664", "GSM2728665", "GSM2728666", "GSM2728667", "GSM2728668", "GSM2728669", "GSM2728670", "GSM2728671", "GSM2728672", "GSM2728673", "GSM2728674", "GSM2728675", "GSM2728676", "GSM2728677", "GSM2728678", "GSM2728679", "GSM2728680", "GSM2728681", "GSM2728682", "GSM2728683", "GSM2728684", "GSM2728685", "GSM2728686", "GSM2728687", "GSM2728688", "GSM2728689", "GSM2728690", "GSM2728691", "GSM2728692", "GSM2728693", "GSM2728694", "GSM2728695", "GSM2728696", "GSM2728697", "GSM2728698", "GSM2728699", "GSM2728700", "GSM2728701", "GSM2728702", "GSM2728703", "GSM2728704", "GSM2728705", "GSM2728706", "GSM2728707", "GSM2728708", "GSM2728709", "GSM2728710", "GSM2728711", "GSM2728712", "GSM2728713", "GSM2728714", "GSM2728715", "GSM2728716", "GSM2728717", "GSM2728718", "GSM2728719", "GSM2728720", "GSM2728721", "GSM2728722", "GSM2728723", "GSM2728724", "GSM2728725", "GSM2728726"], "sample_count": 77, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Mucosal gene expression profiling in ileum of patients with Crohn's disease", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE186582", "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=GSE186582", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE186582", "version": null, "note": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5656170", "GSM5656171", "GSM5656172", "GSM5656173", "GSM5656174", "GSM5656175", "GSM5656176", "GSM5656177", "GSM5656178", "GSM5656179", "GSM5656180", "GSM5656181", "GSM5656182", "GSM5656183", "GSM5656184", "GSM5656185", "GSM5656186", "GSM5656187", "GSM5656188", "GSM5656189", "GSM5656190", "GSM5656191", "GSM5656192", "GSM5656193", "GSM5656194", "GSM5656195", "GSM5656196", "GSM5656197", "GSM5656198", "GSM5656199", "GSM5656200", "GSM5656201", "GSM5656202", "GSM5656203", "GSM5656204", "GSM5656205", "GSM5656206", "GSM5656207", "GSM5656208", "GSM5656209", "GSM5656210", "GSM5656211", "GSM5656212", "GSM5656213", "GSM5656214", "GSM5656215", "GSM5656216", "GSM5656217", "GSM5656218", "GSM5656219", "GSM5656220", "GSM5656221", "GSM5656222", "GSM5656223", "GSM5656224", "GSM5656225", "GSM5656226", "GSM5656227", "GSM5656228", "GSM5656229", "GSM5656230", "GSM5656231", "GSM5656232", "GSM5656233", "GSM5656234", "GSM5656235", "GSM5656236", "GSM5656237", "GSM5656238", "GSM5656239", "GSM5656240", "GSM5656241", "GSM5656242", "GSM5656243", "GSM5656244", "GSM5656245", "GSM5656246", "GSM5656247", "GSM5656248", "GSM5656249", "GSM5656250", "GSM5656251", "GSM5656252", "GSM5656253", "GSM5656254", "GSM5656255", "GSM5656256", "GSM5656257", "GSM5656258", "GSM5656259", "GSM5656260", "GSM5656261", "GSM5656262", "GSM5656263", "GSM5656264", "GSM5656265", "GSM5656266", "GSM5656267", "GSM5656268", "GSM5656269", "GSM5656270", "GSM5656271", "GSM5656272", "GSM5656273", "GSM5656274", "GSM5656275", "GSM5656276", "GSM5656277", "GSM5656278", "GSM5656279", "GSM5656280", "GSM5656281", "GSM5656282", "GSM5656283", "GSM5656284", "GSM5656285", "GSM5656286", "GSM5656287", "GSM5656288", "GSM5656289", "GSM5656290", "GSM5656291", "GSM5656292", "GSM5656293", "GSM5656294", "GSM5656295", "GSM5656296", "GSM5656297", "GSM5656298", "GSM5656299", "GSM5656300", "GSM5656301", "GSM5656302", "GSM5656303", "GSM5656304", "GSM5656305", "GSM5656306", "GSM5656307", "GSM5656308", "GSM5656309", "GSM5656310", "GSM5656311", "GSM5656312", "GSM5656313", "GSM5656314", "GSM5656315", "GSM5656316", "GSM5656317", "GSM5656318", "GSM5656319", "GSM5656320", "GSM5656321", "GSM5656322", "GSM5656323", "GSM5656324", "GSM5656325", "GSM5656326", "GSM5656327", "GSM5656328", "GSM5656329", "GSM5656330", "GSM5656331", "GSM5656332", "GSM5656333", "GSM5656334", "GSM5656335", "GSM5656336", "GSM5656337", "GSM5656338", "GSM5656339", "GSM5656340", "GSM5656341", "GSM5656342", "GSM5656343", "GSM5656344", "GSM5656345", "GSM5656346", "GSM5656347", "GSM5656348", "GSM5656349", "GSM5656350", "GSM5656351", "GSM5656352", "GSM5656353", "GSM5656354", "GSM5656355", "GSM5656356", "GSM5656357", "GSM5656358", "GSM5656359", "GSM5656360", "GSM5656361", "GSM5656362", "GSM5656363", "GSM5656364", "GSM5656365", "GSM5656366", "GSM5656367", "GSM5656368", "GSM5656369", "GSM5656370", "GSM5656371", "GSM5656372", "GSM5656373", "GSM5656374", "GSM5656375", "GSM5656376", "GSM5656377", "GSM5656378", "GSM5656379", "GSM5656380", "GSM5656381", "GSM5656382", "GSM5656383", "GSM5656384", "GSM5656385", "GSM5656386", "GSM5656387", "GSM5656388", "GSM5656389", "GSM5656390", "GSM5656391", "GSM5656392", "GSM5656393", "GSM5656394", "GSM5656395", "GSM5656396", "GSM5656397", "GSM5656398", "GSM5656399", "GSM5656400", "GSM5656401", "GSM5656402", "GSM5656403", "GSM5656404", "GSM5656405", "GSM5656406", "GSM5656407", "GSM5656408", "GSM5656409", "GSM5656410", "GSM5656411", "GSM5656412", "GSM5656413", "GSM5656414", "GSM5656415", "GSM5656416", "GSM5656417", "GSM5656418", "GSM5656419", "GSM5656420", "GSM5656421", "GSM5656422", "GSM5656423", "GSM5656424", "GSM5656425", "GSM5656426", "GSM5656427", "GSM5656428", "GSM5656429", "GSM5656430", "GSM5656431", "GSM5656432", "GSM5656433", "GSM5656434", "GSM5656435", "GSM5656436", "GSM5656437", "GSM5656438", "GSM5656439", "GSM5656440", "GSM5656441", "GSM5656442", "GSM5656443", "GSM5656444", "GSM5656445", "GSM5656446", "GSM5656447", "GSM5656448", "GSM5656449", "GSM5656450", "GSM5656451", "GSM5656452", "GSM5656453", "GSM5656454", "GSM5656455", "GSM5656456", "GSM5656457", "GSM5656458", "GSM5656459", "GSM5656460", "GSM5656461", "GSM5656462", "GSM5656463", "GSM5656464", "GSM5656465", "GSM5656466", "GSM5656467", "GSM5656468", "GSM5656469", "GSM5656470", "GSM5656471", "GSM5656472", "GSM5656473", "GSM5656474", "GSM5656475", "GSM5656476", "GSM5656477", "GSM5656478", "GSM5656479", "GSM5656480", "GSM5656481", "GSM5656482", "GSM5656483", "GSM5656484", "GSM5656485", "GSM5656486", "GSM5656487", "GSM5656488", "GSM5656489", "GSM5656490", "GSM5656491", "GSM5656492", "GSM5656493", "GSM5656494", "GSM5656495", "GSM5656496", "GSM5656497", "GSM5656498", "GSM5656499", "GSM5656500", "GSM5656501", "GSM5656502", "GSM5656503", "GSM5656504", "GSM5656505", "GSM5656506", "GSM5656507", "GSM5656508", "GSM5656509", "GSM5656510", "GSM5656511", "GSM5656512", "GSM5656513", "GSM5656514", "GSM5656515", "GSM5656516", "GSM5656517", "GSM5656518", "GSM5656519", "GSM5656520", "GSM5656521", "GSM5656522", "GSM5656523", "GSM5656524", "GSM5656525", "GSM5656526", "GSM5656527", "GSM5656528", "GSM5656529", "GSM5656530", "GSM5656531", "GSM5656532", "GSM5656533", "GSM5656534", "GSM5656535", "GSM5656536", "GSM5656537", "GSM5656538", "GSM5656539", "GSM5656540", "GSM5656541", "GSM5656542", "GSM5656543", "GSM5656544", "GSM5656545", "GSM5656546", "GSM5656547", "GSM5656548", "GSM5656549", "GSM5656550", "GSM5656551", "GSM5656552", "GSM5656553", "GSM5656554", "GSM5656555", "GSM5656556", "GSM5656557", "GSM5656558", "GSM5656559", "GSM5656560", "GSM5656561", "GSM5656562", "GSM5656563", "GSM5656564", "GSM5656565", "GSM5656566", "GSM5656567", "GSM5656568", "GSM5656569", "GSM5656570", "GSM5656571", "GSM5656572", "GSM5656573", "GSM5656574", "GSM5656575", "GSM5656576", "GSM5656577", "GSM5656578", "GSM5656579", "GSM5656580", "GSM5656581", "GSM5656582", "GSM5656583", "GSM5656584", "GSM5656585", "GSM5656586", "GSM5656587", "GSM5656588", "GSM5656589", "GSM5656590", "GSM5656591", "GSM5656592", "GSM5656593", "GSM5656594", "GSM5656595", "GSM5656596", "GSM5656597", "GSM5656598", "GSM5656599", "GSM5656600", "GSM5656601", "GSM5656602", "GSM5656603", "GSM5656604", "GSM5656605", "GSM5656606", "GSM5656607", "GSM5656608", "GSM5656609", "GSM5656610", "GSM5656611", "GSM5656612", "GSM5656613", "GSM5656614", "GSM5656615", "GSM5656616", "GSM5656617", "GSM5656618", "GSM5656619", "GSM5656620", "GSM5656621", "GSM5656622", "GSM5656623", "GSM5656624", "GSM5656625", "GSM5656626", "GSM5656627", "GSM5656628", "GSM5656629", "GSM5656630", "GSM5656631", "GSM5656632", "GSM5656633", "GSM5656634", "GSM5656635", "GSM5656636", "GSM5656637", "GSM5656638", "GSM5656639", "GSM5656640", "GSM5656641", "GSM5656642", "GSM5656643", "GSM5656644", "GSM5656645", "GSM5656646", "GSM5656647", "GSM5656648", "GSM5656649", "GSM5656650", "GSM5656651", "GSM5656652", "GSM5656653", "GSM5656654", "GSM5656655", "GSM5656656", "GSM5656657", "GSM5656658"], "sample_count": 489, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Expression data from intestinal mucosa of patients with Crohn disease", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE217695", "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=GSE217695", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE217695", "version": null, "note": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM6725129", "GSM6725130", "GSM6725131", "GSM6725132", "GSM6725133", "GSM6725134", "GSM6725135", "GSM6725136", "GSM6725137", "GSM6725138", "GSM6725139", "GSM6725140", "GSM6725141", "GSM6725142", "GSM6725143", "GSM6725144", "GSM6725145", "GSM6725146", "GSM6725147", "GSM6725148", "GSM6725149", "GSM6725150", "GSM6725151", "GSM6725152", "GSM6725153", "GSM6725154", "GSM6725155", "GSM6725156", "GSM6725157", "GSM6725158", "GSM6725159", "GSM6725160"], "sample_count": 32, "group_sizes": null, "group_sizes_basis": null, "platform": "24247", "taxon": "Mus musculus", "title": "Effect of LPS, sHVF18 and the combination therof on gene expression in murine lungs", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE65114", "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=GSE65114", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE65114", "version": null, "note": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1587517", "GSM1587518", "GSM1587519", "GSM1587520", "GSM1587521", "GSM1587522", "GSM1587523", "GSM1587524", "GSM1587525", "GSM1587526", "GSM1587527", "GSM1587528", "GSM1587529", "GSM1587530", "GSM1587531", "GSM1587532", "GSM1587533", "GSM1587534", "GSM1587535", "GSM1587536", "GSM1587537", "GSM1587538", "GSM1587539", "GSM1587540", "GSM1587541", "GSM1587542", "GSM1587543", "GSM1587544"], "sample_count": 28, "group_sizes": null, "group_sizes_basis": null, "platform": "16686", "taxon": "Homo sapiens", "title": "Expression data from colonic mucosal biopsies from healthy controls and patients with active ulcerative colitis", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE87473", "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=GSE87473", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE87473", "version": null, "note": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2332079", "GSM2332080", "GSM2332081", "GSM2332082", "GSM2332083", "GSM2332084", "GSM2332085", "GSM2332086", "GSM2332087", "GSM2332088", "GSM2332089", "GSM2332090", "GSM2332091", "GSM2332092", "GSM2332093", "GSM2332094", "GSM2332095", "GSM2332096", "GSM2332097", "GSM2332098", "GSM2332099", "GSM2332100", "GSM2332101", "GSM2332102", "GSM2332103", "GSM2332104", "GSM2332105", "GSM2332106", "GSM2332107", "GSM2332108", "GSM2332109", "GSM2332110", "GSM2332111", "GSM2332112", "GSM2332113", "GSM2332114", "GSM2332115", "GSM2332116", "GSM2332117", "GSM2332118", "GSM2332119", "GSM2332120", "GSM2332121", "GSM2332122", "GSM2332123", "GSM2332124", "GSM2332125", "GSM2332126", "GSM2332127", "GSM2332128", "GSM2332129", "GSM2332130", "GSM2332131", "GSM2332132", "GSM2332133", "GSM2332134", "GSM2332135", "GSM2332136", "GSM2332137", "GSM2332138", "GSM2332139", "GSM2332140", "GSM2332141", "GSM2332142", "GSM2332143", "GSM2332144", "GSM2332145", "GSM2332146", "GSM2332147", "GSM2332148", "GSM2332149", "GSM2332150", "GSM2332151", "GSM2332152", "GSM2332153", "GSM2332154", "GSM2332155", "GSM2332156", "GSM2332157", "GSM2332158", "GSM2332159", "GSM2332160", "GSM2332161", "GSM2332162", "GSM2332163", "GSM2332164", "GSM2332165", "GSM2332166", "GSM2332167", "GSM2332168", "GSM2332169", "GSM2332170", "GSM2332171", "GSM2332172", "GSM2332173", "GSM2332174", "GSM2332175", "GSM2332176", "GSM2332177", "GSM2332178", "GSM2332179", "GSM2332180", "GSM2332181", "GSM2332182", "GSM2332183", "GSM2332184", "GSM2332185", "GSM2332186", "GSM2332187", "GSM2332188", "GSM2332189", "GSM2332190", "GSM2332191", "GSM2332192", "GSM2332193", "GSM2332194", "GSM2332195", "GSM2332196", "GSM2332197", "GSM2332198", "GSM2332199", "GSM2332200", "GSM2332201", "GSM2332202", "GSM2332203", "GSM2332204", "GSM2332205"], "sample_count": 127, "group_sizes": null, "group_sizes_basis": null, "platform": "13158", "taxon": "Homo sapiens", "title": "Gene expression profiling of mucosal biopsies from pediatric or adult patients with moderately to severely active ulcerative colitis", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE102133 not downloaded", "asset:data:geo:GSE102133 licence not read", "asset:data:geo:GSE186582 not downloaded", "asset:data:geo:GSE186582 licence not read", "asset:data:geo:GSE217695 not downloaded", "asset:data:geo:GSE217695 licence not read", "asset:data:geo:GSE65114 not downloaded", "asset:data:geo:GSE65114 licence not read", "asset:data:geo:GSE87473 not downloaded", "asset:data:geo:GSE87473 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "A Pearson correlation analysis was used to link disulfidptosis and ferroptosis genes, followed by machine learning (LASSO and RF) to screen core DRFGs."}}, {"id": "method-2", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "PPI"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.8, "band": "high", "quote": "pathway enrichment"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["pearson_r"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pearson."}, "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": ["GSE65114", "GSE87473", "GSE102133", "GSE186582", "GSE217695"], "resolved_accessions": ["GSE65114", "GSE87473", "GSE102133", "GSE186582", "GSE217695"], "statements": ["The datasets and Supplementary Materials supporting this investigation are available within the published article and associated resources. Additional requests for data access may be submitted to the lead investigators. Transcriptomic profiles were sourced from the GEO repository (https://www.ncbi.nlm.nih.gov/geo/; accessed 1 October 2024), incorporating four datasets (GSE65114, GSE87473, GSE102133, and GSE186582) and single-cell RNA-seq data (GSE217695). Computational scripts generated during this research are available upon formal request to the corresponding authors."], "basis": "The paper names GSE65114, GSE87473, GSE102133, GSE186582, GSE217695 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pearson_r"], "assets": ["source:pmid:40428318", "data:geo:GSE102133"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE102133"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:53:25Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 17116, "completion_tokens": 2045, "cached_tokens": 256}}, "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:40428318", "type": "paper", "label": "pmid:40428318"}, {"id": "source:pmid:40428318", "type": "manuscript", "label": "PMID 40428318 full text"}, {"id": "data:geo:GSE102133", "type": "dataset", "label": "GEO GSE102133"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:40428318", "type": "paper", "label": "pmid:40428318"}, {"id": "source:pmid:40428318", "type": "manuscript", "label": "PMID 40428318 full text"}, {"id": "data:geo:GSE102133", "type": "dataset", "label": "GEO GSE102133"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-40428318", "type": "extraction", "used": ["source:pmid:40428318"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE102133", "type": "accession_resolution", "used": ["data:geo:GSE102133"], "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:40428318", "parent_hash": "sha256:675a3f0129165571a16d3c7141fb26dbc4b670965cc87c1c606561ece247d691", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE102133 licence not read", "asset:data:geo:GSE102133 not downloaded", "asset:data:geo:GSE186582 licence not read", "asset:data:geo:GSE186582 not downloaded", "asset:data:geo:GSE217695 licence not read", "asset:data:geo:GSE217695 not downloaded", "asset:data:geo:GSE65114 licence not read", "asset:data:geo:GSE65114 not downloaded", "asset:data:geo:GSE87473 licence not read", "asset:data:geo:GSE87473 not downloaded", "execution.not_run", "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": ["with concordant results between qRT-PCR and RNA-seq, emphasizing their pivotal regulatory roles", "L/6) model was used for validation. Results: Transcriptomic profiling identified 521 DEGs, with 16 defin", "constituent (Supplementary Figure S1B). The transcriptomic profiles of the control group exhibited sign"], "order_basis": "paper_text_order:1105", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["une compartment specificity. The DSS-induced murine colitis model confirmed differential express", "for all experimental subjects. Male C57BL/6 mice were randomly allocated to two cohorts s (n = 4 p", "owing an established protocol [19]. Finally, mice were euthanized in a carbon dioxide chamber. The"], "order_basis": "paper_text_order:1619", "id": "assay:2"}, {"role": "analysis", "definition_id": "correlation_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pearson_r"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["A Pearson correlation analysis was used to link disulfidptosis and ferroptosis genes, followed by machine learning (LASSO and RF) to screen core DRFGs."], "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":"2026-11-04T02:59:01+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}}}