{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39006497", "kind": "science-record", "revision": 3, "content_hash": "sha256:9b627575bda0d8aceab71fa5fcbcecc663e83ce2c5989327f54bfbef51711ea6", "created_at": "2026-11-01T20:29:04Z", "updated_at": "2026-11-01T22:12:14Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Discovery and Validation of Ferroptosis-Associated Genes of Ulcerative Colitis.", "doi": "10.2147/JIR.S463042", "pmid": "39006497", "authors": ["Jiejie Zhu", "Yumei Wu", "Xiaoyuan Ge", "Xinwen Chen", "Qiao Mei"], "journal": "Journal of inflammation research", "year": 2024, "abstract": "Background: Ulcerative colitis (UC) is a long-lasting idiopathic condition, but its precise mechanisms remain unclear. Meanwhile, evidence has demonstrated that ferroptosis seems to interlock with the progress of UC. This research sought to identify hub genes of UC related to ferroptosis.\nMethods: First, the relevant profiles for this article were obtained from GEO database. From the FerrDb, 479 genes linked to ferroptosis were retrieved. Using analysis of the difference and WGCNA on colonic samples from GSE73661, the remaining six hub genes linked to ferroptosis and UC were discovered. Through logistic regression analyses, the diagnostic model was constructed and was then evaluated by external validation using dataset GSE92415. Afterwards, the correlation between immune cell filtration in UC and hub genes was examined. Finally, a mice model of colitis was established, and the results were verified using qRT-PCR.\nResults: We acquired six hub genes linked to ferroptosis and UC. In order to create a diagnostic model for UC, we used logistic regression analysis to screen three of the six ferroptosis related genes (HIF1A, SLC7A11, and LPIN1). The ROC curve showed that the three hub genes had outstanding potential for disease diagnosis (AUC = 0.976), which was subsequently validated in samples from GSE92415 (AUC = 0.962) and blood samples from GSE3365 (AUC = 0.847) and GSE94648 (AUC = 0.769). These genes might be crucial for UC immunity based upon the results on the immune system. Furthermore, mouse samples examined using qRT-PCR also verified our findings.\nConclusion: In conclusion, the findings have important implications for ferroptosis and UC, and these hub genes may also offer fresh perspectives on the aetiology and therapeutic approaches of UC.", "claims": [{"id": "claim-method", "statement": "Through constructing logistic regression, HIF1A, SLC7A11, LPIN1 were selected, which could effectively differentiate UC patients from controls, boasting an AUC value of 0.976 (Figure 7A).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39006497", "locator": "sections[16] \"A Diagnostic Model Applicable to UC\" paragraph 2", "quote": "Through constructing logistic regression, HIF1A, SLC7A11, LPIN1 were selected, which could effectively differentiate UC patients from controls, boasting an AUC value of 0.976 (Figure 7A)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39006497", "locator": "sections[22] \"Data Sharing Statement\" paragraph 2", "quote": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request."}], "state": "complete"}, {"id": "claim-target-result", "statement": "The ROC curve showed that the three hub genes had outstanding potential for disease diagnosis (AUC = 0.976), which was subsequently validated in samples from GSE92415 (AUC = 0.962) and blood samples from GSE3365 (AUC = 0.847) and GSE94648 (AUC = 0.769).", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:39006497", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "The ROC curve showed that the three hub genes had outstanding potential for disease diagnosis (AUC = 0.976), which was subsequently validated in samples from GSE92415 (AUC = 0.962) and blood samples from GSE3365 (AUC = 0.847) and GSE94648 (AUC = 0.769)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "The ROC curve showed that the three hub genes had outstanding potential for disease diagnosis (AUC = 0.976), which was subsequently validated in samples from GSE92415 (AUC = 0.962) and blood samples from GSE3365 (AUC = 0.847) and GSE94648 (AUC = 0.769).", "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:39006497"], "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:GSE3365"], "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:GSE3365"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39006497", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/JIR.S463042", "sha256": "sha256:7d9ad768abe6198ee5f8dcac6f0b2059439af89a3aa559811e4d64fe26cb8e42", "bytes": 36562, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/JIR.S463042", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11246036", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE3365", "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=GSE3365", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE3365", "version": null, "note": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM76030", "GSM76031", "GSM76032", "GSM76033", "GSM76034", "GSM76035", "GSM76036", "GSM76037", "GSM76038", "GSM76039", "GSM76040", "GSM76041", "GSM76042", "GSM76043", "GSM76044", "GSM76045", "GSM76046", "GSM76047", "GSM76048", "GSM76049", "GSM76050", "GSM76051", "GSM76052", "GSM76053", "GSM76054", "GSM76055", "GSM76056", "GSM76057", "GSM76058", "GSM76059", "GSM76060", "GSM76061", "GSM76062", "GSM76063", "GSM76064", "GSM76065", "GSM76066", "GSM76067", "GSM76068", "GSM76069", "GSM76070", "GSM76071", "GSM76072", "GSM76073", "GSM76074", "GSM76075", "GSM76076", "GSM76077", "GSM76078", "GSM76079", "GSM76080", "GSM76081", "GSM76082", "GSM76083", "GSM76084", "GSM76085", "GSM76086", "GSM76087", "GSM76088", "GSM76089", "GSM76090", "GSM76091", "GSM76092", "GSM76093", "GSM76094", "GSM76095", "GSM76096", "GSM76097", "GSM76098", "GSM76099", "GSM76100", "GSM76101", "GSM76102", "GSM76103", "GSM76104", "GSM76105", "GSM76106", "GSM76107", "GSM76108", "GSM76109", "GSM76110", "GSM76111", "GSM76112", "GSM76113", "GSM76114", "GSM76115", "GSM76116", "GSM76117", "GSM76118", "GSM76119", "GSM76120", "GSM76121", "GSM76122", "GSM76123", "GSM76124", "GSM76125", "GSM76126", "GSM76127", "GSM76128", "GSM76129", "GSM76130", "GSM76131", "GSM76132", "GSM76133", "GSM76134", "GSM76135", "GSM76136", "GSM76137", "GSM76138", "GSM76139", "GSM76140", "GSM76141", "GSM76142", "GSM76143", "GSM76144", "GSM76145", "GSM76146", "GSM76147", "GSM76148", "GSM76149", "GSM76150", "GSM76151", "GSM76152", "GSM76153", "GSM76154", "GSM76155", "GSM76156"], "sample_count": 127, "group_sizes": null, "group_sizes_basis": null, "platform": "96", "taxon": "Homo sapiens", "title": "Comparison of PBMCs in Inflammatory Bowel 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:GSE73661", "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=GSE73661", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE73661", "version": null, "note": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1900148", "GSM1900149", "GSM1900150", "GSM1900151", "GSM1900152", "GSM1900153", "GSM1900154", "GSM1900155", "GSM1900156", "GSM1900157", "GSM1900158", "GSM1900159", "GSM1900160", "GSM1900161", "GSM1900162", "GSM1900163", "GSM1900164", "GSM1900165", "GSM1900166", "GSM1900167", "GSM1900168", "GSM1900169", "GSM1900170", "GSM1900171", "GSM1900172", "GSM1900173", "GSM1900174", "GSM1900175", "GSM1900176", "GSM1900177", "GSM1900178", "GSM1900179", "GSM1900180", "GSM1900181", "GSM1900182", "GSM1900183", "GSM1900184", "GSM1900185", "GSM1900186", "GSM1900187", "GSM1900188", "GSM1900189", "GSM1900190", "GSM1900191", "GSM1900192", "GSM1900193", "GSM1900194", "GSM1900195", "GSM1900196", "GSM1900197", "GSM1900198", "GSM1900199", "GSM1900200", "GSM1900201", "GSM1900202", "GSM1900203", "GSM1900204", "GSM1900205", "GSM1900206", "GSM1900207", "GSM1900208", "GSM1900209", "GSM1900210", "GSM1900211", "GSM1900212", "GSM1900213", "GSM1900214", "GSM1900215", "GSM1900216", "GSM1900217", "GSM1900218", "GSM1900219", "GSM1900220", "GSM1900221", "GSM1900222", "GSM1900223", "GSM1900224", "GSM1900225", "GSM1900226", "GSM1900227", "GSM1900228", "GSM1900229", "GSM1900230", "GSM1900231", "GSM1900232", "GSM1900233", "GSM1900234", "GSM1900235", "GSM1900236", "GSM1900237", "GSM1900238", "GSM1900239", "GSM1900240", "GSM1900241", "GSM1900242", "GSM1900243", "GSM1900244", "GSM1900245", "GSM1900246", "GSM1900247", "GSM1900248", "GSM1900249", "GSM1900250", "GSM1900251", "GSM1900252", "GSM1900253", "GSM1900254", "GSM1900255", "GSM1900256", "GSM1900257", "GSM1900258", "GSM1900259", "GSM1900260", "GSM1900261", "GSM1900262", "GSM1900263", "GSM1900264", "GSM1900265", "GSM1900266", "GSM1900267", "GSM1900268", "GSM1900269", "GSM1900270", "GSM1900271", "GSM1900272", "GSM1900273", "GSM1900274", "GSM1900275", "GSM1900276", "GSM1900277", "GSM1900278", "GSM1900279", "GSM1900280", "GSM1900281", "GSM1900282", "GSM1900283", "GSM1900284", "GSM1900285", "GSM1900286", "GSM1900287", "GSM1900288", "GSM1900289", "GSM1900290", "GSM1900291", "GSM1900292", "GSM1900293", "GSM1900294", "GSM1900295", "GSM1900296", "GSM1900297", "GSM1900298", "GSM1900299", "GSM1900300", "GSM1900301", "GSM1900302", "GSM1900303", "GSM1900304", "GSM1900305", "GSM1900306", "GSM1900307", "GSM1900308", "GSM1900309", "GSM1900310", "GSM1900311", "GSM1900312", "GSM1900313", "GSM1900314", "GSM1900315", "GSM1900316", "GSM1900317", "GSM1900318", "GSM1900319", "GSM1900320", "GSM1900321", "GSM1900322", "GSM1900323", "GSM1900324", "GSM1900325"], "sample_count": 178, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "The effect of vedolizumab (anti-α4β7-integrin) therapy on colonic mucosal gene expression in patients with ulcerative colitis (UC)", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE92415", "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=GSE92415", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE92415", "version": null, "note": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2429346", "GSM2429347", "GSM2429348", "GSM2429349", "GSM2429350", "GSM2429351", "GSM2429352", "GSM2429353", "GSM2429354", "GSM2429355", "GSM2429356", "GSM2429357", "GSM2429358", "GSM2429359", "GSM2429360", "GSM2429361", "GSM2429362", "GSM2429363", "GSM2429364", "GSM2429365", "GSM2429366", "GSM2429367", "GSM2429368", "GSM2429369", "GSM2429370", "GSM2429371", "GSM2429372", "GSM2429373", "GSM2429374", "GSM2429375", "GSM2429376", "GSM2429377", "GSM2429378", "GSM2429379", "GSM2429380", "GSM2429381", "GSM2429382", "GSM2429383", "GSM2429384", "GSM2429385", "GSM2429386", "GSM2429387", "GSM2429388", "GSM2429389", "GSM2429390", "GSM2429391", "GSM2429392", "GSM2429393", "GSM2429394", "GSM2429395", "GSM2429396", "GSM2429397", "GSM2429398", "GSM2429399", "GSM2429400", "GSM2429401", "GSM2429402", "GSM2429403", "GSM2429404", "GSM2429405", "GSM2429406", "GSM2429407", "GSM2429408", "GSM2429409", "GSM2429410", "GSM2429411", "GSM2429412", "GSM2429413", "GSM2429414", "GSM2429415", "GSM2429416", "GSM2429417", "GSM2429418", "GSM2429419", "GSM2429420", "GSM2429421", "GSM2429422", "GSM2429423", "GSM2429424", "GSM2429425", "GSM2429426", "GSM2429427", "GSM2429428", "GSM2429429", "GSM2429430", "GSM2429431", "GSM2429432", "GSM2429433", "GSM2429434", "GSM2429435", "GSM2429436", "GSM2429437", "GSM2429438", "GSM2429439", "GSM2429440", "GSM2429441", "GSM2429442", "GSM2429443", "GSM2429444", "GSM2429445", "GSM2429446", "GSM2429447", "GSM2429448", "GSM2429449", "GSM2429450", "GSM2429451", "GSM2429452", "GSM2429453", "GSM2429454", "GSM2429455", "GSM2429456", "GSM2429457", "GSM2429458", "GSM2429459", "GSM2429460", "GSM2429461", "GSM2429462", "GSM2429463", "GSM2429464", "GSM2429465", "GSM2429466", "GSM2429467", "GSM2429468", "GSM2429469", "GSM2429470", "GSM2429471", "GSM2429472", "GSM2429473", "GSM2429474", "GSM2429475", "GSM2429476", "GSM2429477", "GSM2429478", "GSM2429479", "GSM2429480", "GSM2429481", "GSM2429482", "GSM2429483", "GSM2429484", "GSM2429485", "GSM2429486", "GSM2429487", "GSM2429488", "GSM2429489", "GSM2429490", "GSM2429491", "GSM2429492", "GSM2429493", "GSM2429494", "GSM2429495", "GSM2429496", "GSM2429497", "GSM2429498", "GSM2429499", "GSM2429500", "GSM2429501", "GSM2429502", "GSM2429503", "GSM2429504", "GSM2429505", "GSM2429506", "GSM2429507", "GSM2429508", "GSM2429509", "GSM2429510", "GSM2429511", "GSM2429512", "GSM2429513", "GSM2429514", "GSM2429515", "GSM2429516", "GSM2429517", "GSM2429518", "GSM2429519", "GSM2429520", "GSM2429521", "GSM2429522", "GSM2429523", "GSM2429524", "GSM2429525", "GSM2429526", "GSM2429527", "GSM2429528"], "sample_count": 183, "group_sizes": null, "group_sizes_basis": null, "platform": "13158", "taxon": "Homo sapiens", "title": "Characterization of molecular response to Golimumab in Ulcerative Colitis by mucosal biopsy mRNA expression profiling: results from PURSUIT-SC induction study", "resolution_checked_at": "2026-11-01T15:39:55Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE94648", "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=GSE94648", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE94648", "version": null, "note": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2480251", "GSM2480252", "GSM2480253", "GSM2480254", "GSM2480255", "GSM2480256", "GSM2480257", "GSM2480258", "GSM2480259", "GSM2480260", "GSM2480261", "GSM2480262", "GSM2480263", "GSM2480264", "GSM2480265", "GSM2480266", "GSM2480267", "GSM2480268", "GSM2480269", "GSM2480270", "GSM2480271", "GSM2480272", "GSM2480273", "GSM2480274", "GSM2480275", "GSM2480276", "GSM2480277", "GSM2480278", "GSM2480279", "GSM2480280", "GSM2480281", "GSM2480282", "GSM2480283", "GSM2480284", "GSM2480285", "GSM2480286", "GSM2480287", "GSM2480288", "GSM2480289", "GSM2480290", "GSM2480291", "GSM2480292", "GSM2480293", "GSM2480294", "GSM2480295", "GSM2480296", "GSM2480297", "GSM2480298", "GSM2480299", "GSM2480300", "GSM2480301", "GSM2480302", "GSM2480303", "GSM2480304", "GSM2480305", "GSM2480306", "GSM2480307", "GSM2480308", "GSM2480309", "GSM2480310", "GSM2480311", "GSM2480312", "GSM2480313", "GSM2480314", "GSM2480315", "GSM2480316", "GSM2480317", "GSM2480318", "GSM2480319", "GSM2480320", "GSM2480321", "GSM2480322", "GSM2480323", "GSM2480324", "GSM2480325", "GSM2480326", "GSM2480327", "GSM2480328", "GSM2480329", "GSM2480330", "GSM2480331", "GSM2480332", "GSM2480333", "GSM2480334", "GSM2480335", "GSM2480336", "GSM2480337", "GSM2480338", "GSM2480339", "GSM2480340", "GSM2480341", "GSM2480342", "GSM2480343", "GSM2480344", "GSM2480345", "GSM2480346", "GSM2480347"], "sample_count": 97, "group_sizes": null, "group_sizes_basis": null, "platform": "19109", "taxon": "Homo sapiens", "title": "Expression data from peripheral whole blood of non-IBD controls, CD and UC patients", "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:GSE3365 not downloaded", "asset:data:geo:GSE3365 licence not read", "asset:data:geo:GSE73661 not downloaded", "asset:data:geo:GSE73661 licence not read", "asset:data:geo:GSE92415 not downloaded", "asset:data:geo:GSE92415 licence not read", "asset:data:geo:GSE94648 not downloaded", "asset:data:geo:GSE94648 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Through constructing logistic regression, HIF1A, SLC7A11, LPIN1 were selected, which could effectively differentiate UC patients from controls, boasting an AUC value of 0.976 (Figure 7A)."}}, {"id": "method-2", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.7, "band": "medium", "quote": "ROC curve"}}], "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": ["glm_logit_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: logistic."}, "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": ["GSE73661", "GSE92415", "GSE3365", "GSE94648"], "resolved_accessions": ["GSE73661", "GSE92415", "GSE3365", "GSE94648"], "statements": ["The data generated and thoroughly analyzed throughout this study are available for retrieval from the corresponding author upon receipt of a reasonable request."], "basis": "The paper names GSE73661, GSE92415, GSE3365, GSE94648 in NCBI Gene Expression Omnibus public database (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["glm_logit_fit"], "assets": ["source:pmid:39006497", "data:geo:GSE3365"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE3365"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:23:54Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 9703, "completion_tokens": 1439, "cached_tokens": 0}}, "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:39006497", "type": "paper", "label": "pmid:39006497"}, {"id": "source:pmid:39006497", "type": "manuscript", "label": "PMID 39006497 full text"}, {"id": "data:geo:GSE3365", "type": "dataset", "label": "GEO GSE3365"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39006497", "type": "paper", "label": "pmid:39006497"}, {"id": "source:pmid:39006497", "type": "manuscript", "label": "PMID 39006497 full text"}, {"id": "data:geo:GSE3365", "type": "dataset", "label": "GEO GSE3365"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39006497", "type": "extraction", "used": ["source:pmid:39006497"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE3365", "type": "accession_resolution", "used": ["data:geo:GSE3365"], "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:39006497", "parent_hash": "sha256:4787c849dc1436dd0f80a63e3414fc074b862e7bd9e5b6409eaf0e0b002662b7", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE3365 licence not read", "asset:data:geo:GSE3365 not downloaded", "asset:data:geo:GSE73661 licence not read", "asset:data:geo:GSE73661 not downloaded", "asset:data:geo:GSE92415 licence not read", "asset:data:geo:GSE92415 not downloaded", "asset:data:geo:GSE94648 licence not read", "asset:data:geo:GSE94648 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "clinical_cohort", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.77, "evidence": ["d in samples from GSE92415 (AUC = 0.962) and blood samples from GSE3365 (AUC = 0.847) and GSE94648 (AUC = 0."], "order_basis": "paper_text_order:1377", "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": 0.69, "evidence": ["e results on the immune system. Furthermore, mouse samples examined using qRT-PCR also verified"], "order_basis": "paper_text_order:1549", "id": "assay:2"}, {"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["glm_logit_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Through constructing logistic regression, HIF1A, SLC7A11, LPIN1 were selected, which could effectively differentiate UC patients from controls, boasting an AUC value of 0.976 (Figure 7A)."], "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":"2026-11-04T02:36:47+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}}}