{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37092131", "kind": "science-record", "revision": 3, "content_hash": "sha256:99651642a56ceffbf0d90bb0761d38a042b0d6d6c9e752933d036ed6022f69c1", "created_at": "2026-11-01T19:01:45Z", "updated_at": "2026-11-01T22:09:19Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Critical Modules and Biomarkers of Ulcerative Colitis by Using WGCNA.", "doi": "10.2147/JIR.S402715", "pmid": "37092131", "authors": ["Yifan Yuan", "Na Li", "Mingyue Fu", "Mei Ye"], "journal": "Journal of inflammation research", "year": 2023, "abstract": "Background: Ulcerative colitis (UC) is a chronic inflammatory disease of the colon and rectum that has no exact cause and is characterized by relapsing and remitting episodes. We aimed to find biomarkers of UC and its causes.\nMethods: We got GSE73661 from the GEO database and used WGCNA to find DEGs that were expressed in the same way in both normal and UC samples. To identify the co-expression modules, we used Weighted Gene Co-Expression Network Analysis. Next, we selected genes that were both DEGs and parts of main modules. Later, three datasets were used to find the hub genes, and qRT-PCR was utilized to confirm the in-silico findings. Additionally, we analyzed the connection between the hub genes and the filtration of immune cells in UC. Using the databases, we made predictions about the miRNAs and lncRNAs that regulate the hub genes and predicted possible therapeutic drugs.\nResults: We found 822 DEGs and three main modules related to immunity, endoplasmic reticulum, and metabolism. Using another three datasets and human samples to confirm the mRNA expression of these genes in UC patients, XBP1 and PLPP1 were selected as hub genes, and had excellent diagnostic potential. According to the findings of the immune infiltration, patients with UC exhibited a larger proportion of immune cells. And hub genes, particularly XBP1, were closely linked to a number of immune cell infiltrations. Based on the databases and hub genes, a lncRNA-miRNA-mRNA network, including two miRNAs (miR-214-3p and miR-93-5p), two hub genes, and 124 lncRNAs, and potential therapeutic medicine were identified.\nConclusion: We found two new genes, XBP1 and PLPP1, that are involved in UC and can help diagnose and measure the disease. XBP1 also relates to clinical scores and immune cells. We suggested a gene network and possible drugs based on them.", "claims": [{"id": "claim-method", "statement": "Each candidate hub gene was tested using a receiver operating characteristic (ROC) curve to guarantee its precision.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37092131", "locator": "sections[9] \"Analysis of ROC Curves for Hub Genes\" paragraph 2", "quote": "Each candidate hub gene was tested using a receiver operating characteristic (ROC) curve to guarantee its precision."}], "state": "complete"}, {"id": "claim-data-access", "statement": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37092131", "locator": "sections[24] \"Data Sharing Statement\" paragraph 2", "quote": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work."}], "state": "complete"}, {"id": "claim-target-result", "statement": "PLPP1 and XBP1 were identified as UC hub genes with strong diagnostic value, with area under the curve values of 0.986 and 0.991, respectively, and 0.994 for their combination.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37092131", "locator": "sections[17] \"Identification of Hub Genes and the Clinical Significance\" paragraph 2", "quote": "In GSE73661, the area under the curve for PLPP1, XBP1, and the combination were 0.986, 0.991, and 0.994 showing that the hub genes can function as UC biomarkers (Figure 5A)."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "PLPP1 and XBP1 were identified as UC hub genes with strong diagnostic value, with area under the curve values of 0.986 and 0.991, respectively, and 0.994 for their combination.", "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:37092131"], "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:GSE11223"], "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:GSE11223"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:37092131", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.2147/JIR.S402715", "sha256": "sha256:45db6f7e0bb37e21b27d27cea794164bb3e0b2a193324396a73d1865b1a1f397", "bytes": 34552, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.2147/JIR.S402715", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10120594", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE11223", "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=GSE11223", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE11223", "version": null, "note": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM282855", "GSM282856", "GSM282857", "GSM282858", "GSM282859", "GSM282860", "GSM282861", "GSM282862", "GSM282863", "GSM282864", "GSM282865", "GSM282866", "GSM282867", "GSM282868", "GSM282869", "GSM282870", "GSM282871", "GSM282872", "GSM282873", "GSM282874", "GSM282875", "GSM282876", "GSM282877", "GSM282878", "GSM282879", "GSM282880", "GSM282881", "GSM282882", "GSM282883", "GSM282884", "GSM282885", "GSM282886", "GSM282887", "GSM282888", "GSM282889", "GSM282890", "GSM282891", "GSM282892", "GSM282893", "GSM282894", "GSM282895", "GSM282896", "GSM282897", "GSM282898", "GSM282899", "GSM282900", "GSM282901", "GSM282902", "GSM282903", "GSM282904", "GSM282905", "GSM282906", "GSM282907", "GSM282908", "GSM282909", "GSM282910", "GSM282911", "GSM282912", "GSM282913", "GSM282914", "GSM282915", "GSM282916", "GSM282917", "GSM282918", "GSM282919", "GSM282920", "GSM282921", "GSM282922", "GSM282923", "GSM282924", "GSM282925", "GSM282926", "GSM282927", "GSM282928", "GSM282929", "GSM282930", "GSM282931", "GSM282932", "GSM282933", "GSM282934", "GSM282935", "GSM282936", "GSM282937", "GSM282938", "GSM282939", "GSM282940", "GSM282941", "GSM282942", "GSM282943", "GSM282944", "GSM282945", "GSM282946", "GSM282947", "GSM282948", "GSM282949", "GSM282950", "GSM282951", "GSM282952", "GSM282953", "GSM282954", "GSM282955", "GSM282956", "GSM282957", "GSM282958", "GSM282959", "GSM282960", "GSM282961", "GSM282962", "GSM282963", "GSM282964", "GSM282965", "GSM282966", "GSM282967", "GSM282968", "GSM282969", "GSM282970", "GSM282971", "GSM282972", "GSM282973", "GSM282974", "GSM282975", "GSM282976", "GSM282977", "GSM282978", "GSM282979", "GSM282980", "GSM282981", "GSM282982", "GSM282983", "GSM282984", "GSM282985", "GSM282986", "GSM282987", "GSM282988", "GSM282989", "GSM282990", "GSM282991", "GSM282992", "GSM282993", "GSM282994", "GSM282995", "GSM282996", "GSM282997", "GSM282998", "GSM282999", "GSM283000", "GSM283001", "GSM283002", "GSM283003", "GSM283004", "GSM283005", "GSM283006", "GSM283007", "GSM283008", "GSM283009", "GSM283010", "GSM283011", "GSM283012", "GSM283013", "GSM283014", "GSM283015", "GSM283016", "GSM283017", "GSM283018", "GSM283019", "GSM283020", "GSM283021", "GSM283022", "GSM283023", "GSM283024", "GSM283025", "GSM283026", "GSM283027", "GSM283028", "GSM283029", "GSM283030", "GSM283031", "GSM283032", "GSM283033", "GSM283034", "GSM283035", "GSM283036", "GSM283037", "GSM283038", "GSM283039", "GSM283040", "GSM283041", "GSM283042", "GSM283043", "GSM283044", "GSM283045", "GSM283046", "GSM283047", "GSM283048", "GSM283049", "GSM283050", "GSM283051", "GSM283052", "GSM283053", "GSM283054", "GSM283055", "GSM283056"], "sample_count": 202, "group_sizes": null, "group_sizes_basis": null, "platform": "1708", "taxon": "Homo sapiens", "title": "Colon biopsies from UC patients and healthy controls", "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:GSE16879", "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=GSE16879", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16879", "version": null, "note": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM364627", "GSM364628", "GSM364629", "GSM364630", "GSM364631", "GSM364632", "GSM364633", "GSM364634", "GSM364635", "GSM364636", "GSM364637", "GSM364638", "GSM364639", "GSM364640", "GSM364641", "GSM364642", "GSM364643", "GSM364644", "GSM364645", "GSM364646", "GSM364647", "GSM364648", "GSM364649", "GSM364650", "GSM364651", "GSM364652", "GSM364653", "GSM364654", "GSM364655", "GSM364656", "GSM422963", "GSM422965", "GSM422967", "GSM422969", "GSM422971", "GSM422973", "GSM422975", "GSM422977", "GSM422979", "GSM422981", "GSM422983", "GSM422985", "GSM422987", "GSM422989", "GSM422991", "GSM422993", "GSM422995", "GSM422997", "GSM422999", "GSM423001", "GSM423003", "GSM423005", "GSM423007", "GSM423009", "GSM423010", "GSM423011", "GSM423012", "GSM423013", "GSM423014", "GSM423015", "GSM423016", "GSM423017", "GSM423018", "GSM423019", "GSM423020", "GSM423021", "GSM423022", "GSM423023", "GSM423024", "GSM423025", "GSM423026", "GSM423027", "GSM423028", "GSM423029", "GSM423030", "GSM423031", "GSM423032", "GSM423033", "GSM423034", "GSM423035", "GSM423036", "GSM423037", "GSM423038", "GSM423039", "GSM423040", "GSM423041", "GSM423042", "GSM423043", "GSM423044", "GSM423045", "GSM423046", "GSM423047", "GSM423048", "GSM423049", "GSM423050", "GSM423051", "GSM423052", "GSM423053", "GSM423054", "GSM423055", "GSM423056", "GSM423057", "GSM423058", "GSM423059", "GSM423060", "GSM423061", "GSM423062", "GSM423063", "GSM423064", "GSM423065", "GSM423066", "GSM423067", "GSM423068", "GSM423069", "GSM423070", "GSM423071", "GSM423072", "GSM423073", "GSM423074", "GSM423075", "GSM423076", "GSM423077", "GSM423078", "GSM423079", "GSM423080", "GSM423081", "GSM423082", "GSM423083", "GSM423084", "GSM423085", "GSM423086", "GSM423087", "GSM423088"], "sample_count": 133, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Mucosal expression profiling in patients with inflammatory bowel disease before and after first infliximab treatment", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE48958", "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=GSE48958", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE48958", "version": null, "note": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1187602", "GSM1187603", "GSM1187604", "GSM1187605", "GSM1187606", "GSM1187607", "GSM1187608", "GSM1187609", "GSM1187610", "GSM1187611", "GSM1187612", "GSM1187613", "GSM1187614", "GSM1187615", "GSM1187616", "GSM1187617", "GSM1187618", "GSM1187619", "GSM1187620", "GSM1187621", "GSM1187622"], "sample_count": 21, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Mucosal gene expression profiling in (un)inflamed colon of patients with ulcerative colitis (UC)", "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: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": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "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:GSE75214", "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=GSE75214", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE75214", "version": null, "note": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1426071", "GSM1426072", "GSM1426073", "GSM1426074", "GSM1426075", "GSM1426076", "GSM1426077", "GSM1426078", "GSM1426079", "GSM1426080", "GSM1426081", "GSM1426082", "GSM1426083", "GSM1426084", "GSM1426085", "GSM1426086", "GSM1426087", "GSM1426088", "GSM1426089", "GSM1426090", "GSM1426091", "GSM1426092", "GSM1426093", "GSM1426094", "GSM1426095", "GSM1426096", "GSM1426097", "GSM1426098", "GSM1426099", "GSM1426100", "GSM1426101", "GSM1426102", "GSM1426103", "GSM1426104", "GSM1426105", "GSM1426106", "GSM1426107", "GSM1426108", "GSM1426109", "GSM1426110", "GSM1426111", "GSM1426112", "GSM1426113", "GSM1426114", "GSM1426115", "GSM1426116", "GSM1426117", "GSM1426118", "GSM1426119", "GSM1426120", "GSM1426121", "GSM1426122", "GSM1426123", "GSM1426124", "GSM1426125", "GSM1426126", "GSM1426127", "GSM1426128", "GSM1426129", "GSM1426130", "GSM1426131", "GSM1426132", "GSM1426133", "GSM1426134", "GSM1426135", "GSM1426136", "GSM1426137", "GSM1426138", "GSM1426139", "GSM1426140", "GSM1426141", "GSM1426142", "GSM1426143", "GSM1426144", "GSM1426145", "GSM1426146", "GSM1426147", "GSM1426148", "GSM1426149", "GSM1426150", "GSM1426151", "GSM1426152", "GSM1426153", "GSM1426154", "GSM1426155", "GSM1426156", "GSM1426157", "GSM1426158", "GSM1426159", "GSM1426160", "GSM1426161", "GSM1426162", "GSM1426163", "GSM1426164", "GSM1426165", "GSM1426166", "GSM1426167", "GSM1426168", "GSM1426169", "GSM1426170", "GSM1426171", "GSM1426172", "GSM1426173", "GSM1426174", "GSM1426175", "GSM1426176", "GSM1426177", "GSM1426178", "GSM1426179", "GSM1426180", "GSM1426181", "GSM1426182", "GSM1426183", "GSM1426184", "GSM1426185", "GSM1426186", "GSM1945759", "GSM1945760", "GSM1945761", "GSM1945762", "GSM1945763", "GSM1945764", "GSM1945765", "GSM1945766", "GSM1945767", "GSM1945768", "GSM1945769", "GSM1945770", "GSM1945771", "GSM1945772", "GSM1945773", "GSM1945774", "GSM1945775", "GSM1945776", "GSM1945777", "GSM1945778", "GSM1945779", "GSM1945780", "GSM1945781", "GSM1945782", "GSM1945783", "GSM1945784", "GSM1945785", "GSM1945786", "GSM1945787", "GSM1945788", "GSM1945789", "GSM1945790", "GSM1945791", "GSM1945792", "GSM1945793", "GSM1945794", "GSM1945795", "GSM1945796", "GSM1945797", "GSM1945798", "GSM1945799", "GSM1945800", "GSM1945801", "GSM1945802", "GSM1945803", "GSM1945804", "GSM1945805", "GSM1945806", "GSM1945807", "GSM1945808", "GSM1945809", "GSM1945810", "GSM1945811", "GSM1945812", "GSM1945813", "GSM1945814", "GSM1945815", "GSM1945816", "GSM1945817", "GSM1945818", "GSM1945819", "GSM1945820", "GSM1945821", "GSM1945822", "GSM1945823", "GSM1945824", "GSM1945825", "GSM1945826", "GSM1945827", "GSM1945828", "GSM1945829", "GSM1945830", "GSM1945831", "GSM1945832", "GSM1945833", "GSM1945834", "GSM1945835", "GSM1945836"], "sample_count": 194, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Mucosal gene expression profiling in patients with inflammatory bowel disease 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: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": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work.", "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}}], "gaps": ["asset:data:geo:GSE11223 not downloaded", "asset:data:geo:GSE11223 licence not read", "asset:data:geo:GSE16879 not downloaded", "asset:data:geo:GSE16879 licence not read", "asset:data:geo:GSE48958 not downloaded", "asset:data:geo:GSE48958 licence not read", "asset:data:geo:GSE73661 not downloaded", "asset:data:geo:GSE73661 licence not read", "asset:data:geo:GSE75214 not downloaded", "asset:data:geo:GSE75214 licence not read", "asset:data:geo:GSE92415 not downloaded", "asset:data:geo:GSE92415 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}, {"id": "method-2", "family": null, "specific": null, "label": "Receiver operating characteristic (ROC) curve analysis", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Each candidate hub gene was tested using a receiver operating characteristic (ROC) curve to guarantee its precision."}}], "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": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: roc."}, "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", "GSE48958", "GSE16879", "GSE75214", "GSE11223", "GSE92415"], "resolved_accessions": ["GSE73661", "GSE48958", "GSE16879", "GSE75214", "GSE11223", "GSE92415"], "statements": ["All of the information utilized in this investigation may be found in the public domain at the Gene Expression Omnibus (GEO, https://www.ncbi.nlm.nih.gov/geo/). With a reasonable request, the corresponding author will provide access to the R code used in this work."], "basis": "The paper names GSE73661, GSE48958, GSE16879, GSE75214, GSE11223, GSE92415 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "assets": ["source:pmid:37092131", "data:geo:GSE11223"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE11223"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T18:37:29Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 10021, "completion_tokens": 1899, "cached_tokens": 128}}, "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:37092131", "type": "paper", "label": "pmid:37092131"}, {"id": "source:pmid:37092131", "type": "manuscript", "label": "PMID 37092131 full text"}, {"id": "data:geo:GSE11223", "type": "dataset", "label": "GEO GSE11223"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37092131", "type": "paper", "label": "pmid:37092131"}, {"id": "source:pmid:37092131", "type": "manuscript", "label": "PMID 37092131 full text"}, {"id": "data:geo:GSE11223", "type": "dataset", "label": "GEO GSE11223"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37092131", "type": "extraction", "used": ["source:pmid:37092131"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE11223", "type": "accession_resolution", "used": ["data:geo:GSE11223"], "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:37092131", "parent_hash": "sha256:fc4c34fc9d9a155e2d8e1ea9ceddb48e6fe172bfb020b8078922302414da72da", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE11223 licence not read", "asset:data:geo:GSE11223 not downloaded", "asset:data:geo:GSE16879 licence not read", "asset:data:geo:GSE16879 not downloaded", "asset:data:geo:GSE48958 licence not read", "asset:data:geo:GSE48958 not downloaded", "asset:data:geo:GSE73661 licence not read", "asset:data:geo:GSE73661 not downloaded", "asset:data:geo:GSE75214 licence not read", "asset:data:geo:GSE75214 not downloaded", "asset:data:geo:GSE92415 licence not read", "asset:data:geo:GSE92415 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "diagnostic_evaluation", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["ROC curve"], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:33:24+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}}}