{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41312366", "kind": "science-record", "revision": 4, "content_hash": "sha256:eef347bcfae03615b1057f7584857aed1102e2ca34f38442bbb938f86111dcfc", "created_at": "2026-11-01T20:31:20Z", "updated_at": "2026-11-01T22:57:32Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of ferroptosis-genes associated with pediatric inflammatory bowel disease bioinformatics and machine learning approaches.", "doi": "10.3389/fimmu.2025.1619944", "pmid": "41312366", "authors": ["Zhen Xu", "Mei Yang", "Chenghao Ou", "Liming Mao", "Zhaoxiu Liu"], "journal": "Frontiers in immunology", "year": 2025, "abstract": "Background: Pediatric inflammatory bowel disease (PIBD) is increasingly common, and early diagnosis remains challenging due to unclear etiology. Ferroptosis, an iron-dependent form of cell death, may be involved in intestinal inflammation, but its expression and role in PIBD are poorly understood.\nObjective: To identify ferroptosis-related genes as candidate biomarkers for early diagnosis of PIBD and validate their role in ferroptosis.\nMethods: RNA-seq data of PIBD from GEO datasets were analyzed using DESeq2, WGCNA, and functional enrichment analysis. Ferroptosis-related diagnostic genes were screened through LASSO, Random Forest, and mSVM-RFE algorithms, and validated in GSE57945 and GSE117993 datasets. In vitro experiments using NCM460 cells were performed to validate the roles of PML and CHAC1 in LPS-induced ferroptosis, including siRNA-mediated gene knockdown, western blotting of ferroptosis-related proteins (ACSL4, SLC7A11, GPX4, FTH), and measurement of lipid peroxidation (MDA levels). CIBERSORT was used to assess immune cell infiltration, and DGIdb was used to predict potential targeted drugs. A ceRNA network was further constructed to explore miRNA-lncRNA interactions regulating these genes.\nResults: PML and CHAC1 were identified as potential biomarkers for early diagnosis of PIBD, showing high diagnostic performance (AUC > 0.7) in training, validation, and external datasets. In vitro experiments confirmed that knockdown of PML or CHAC1 significantly alleviated LPS-induced ferroptosis in NCM460 cells, as evidenced by restored ferroptosis-related protein expression and reduced MDA accumulation. Consistent with immune infiltration results, both genes were associated with immune-related pathways, and a ceRNA network revealed their potential involvement in complex regulatory mechanisms. DGIdb predicted several candidate drugs targeting these genes.\nConclusion: PML and CHAC1 are promising biomarkers for early PIBD diagnosis. These findings, supported by both bioinformatic analyses and experimental validation, may improve diagnostic accuracy and provide insights into the immune microenvironment and therapeutic strategies.", "claims": [{"id": "claim-method", "statement": "RNA-seq data of PIBD from GEO datasets were analyzed using DESeq2, WGCNA, and functional enrichment analysis. Ferroptosis-related diagnostic genes were screened through LASSO, Random Forest, and mSVM-RFE algorithms, and validated in GSE57945 and GSE117993 datasets.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41312366", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "RNA-seq data of PIBD from GEO datasets were analyzed using DESeq2, WGCNA, and functional enrichment analysis. Ferroptosis-related diagnostic genes were screened through LASSO, Random Forest, and mSVM-RFE algorithms, and validated in GSE57945 and GSE117993 datasets."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41312366", "locator": "sections[35] \"Data availability statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794."}], "state": "complete"}, {"id": "claim-target-result", "statement": "PML and CHAC1 were identified as potential biomarkers for early diagnosis of PIBD, showing high diagnostic performance (AUC > 0.7) in training, validation, and external datasets.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:41312366", "locator": "sections[0] \"Abstract\" paragraph 4", "quote": "PML and CHAC1 were identified as potential biomarkers for early diagnosis of PIBD, showing high diagnostic performance (AUC > 0.7) in training, validation, and external datasets."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "PML and CHAC1 were identified as potential biomarkers for early diagnosis of PIBD, showing high diagnostic performance (AUC > 0.7) in training, validation, and external datasets.", "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:41312366"], "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:GSE101794"], "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:GSE101794"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41312366", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2025.1619944", "sha256": "sha256:605d39858112ae824643d3d154a1fd11c9022d0d1180c115a71a3c7f6831cbd7", "bytes": 69260, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2025.1619944", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12647037", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE101794", "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=GSE101794", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE101794", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2715651", "GSM2715652", "GSM2715653", "GSM2715654", "GSM2715655", "GSM2715656", "GSM2715657", "GSM2715658", "GSM2715659", "GSM2715660", "GSM2715661", "GSM2715662", "GSM2715663", "GSM2715664", "GSM2715665", "GSM2715666", "GSM2715667", "GSM2715668", "GSM2715669", "GSM2715670", "GSM2715671", "GSM2715672", "GSM2715673", "GSM2715674", "GSM2715675", "GSM2715676", "GSM2715677", "GSM2715678", "GSM2715679", "GSM2715680", "GSM2715681", "GSM2715682", "GSM2715683", "GSM2715684", "GSM2715685", "GSM2715686", "GSM2715687", "GSM2715688", "GSM2715689", "GSM2715690", "GSM2715691", "GSM2715692", "GSM2715693", "GSM2715694", "GSM2715695", "GSM2715696", "GSM2715697", "GSM2715698", "GSM2715699", "GSM2715700", "GSM2715701", "GSM2715702", "GSM2715703", "GSM2715704", "GSM2715705", "GSM2715706", "GSM2715707", "GSM2715708", "GSM2715709", "GSM2715710", "GSM2715711", "GSM2715712", "GSM2715713", "GSM2715714", "GSM2715715", "GSM2715716", "GSM2715717", "GSM2715718", "GSM2715719", "GSM2715720", "GSM2715721", "GSM2715722", "GSM2715723", "GSM2715724", "GSM2715725", "GSM2715726", "GSM2715727", "GSM2715728", "GSM2715729", "GSM2715730", "GSM2715731", "GSM2715732", "GSM2715733", "GSM2715734", "GSM2715735", "GSM2715736", "GSM2715737", "GSM2715738", "GSM2715739", "GSM2715740", "GSM2715741", "GSM2715742", "GSM2715743", "GSM2715744", "GSM2715745", "GSM2715746", "GSM2715747", "GSM2715748", "GSM2715749", "GSM2715750", "GSM2715751", "GSM2715752", "GSM2715753", "GSM2715754", "GSM2715755", "GSM2715756", "GSM2715757", "GSM2715758", "GSM2715759", "GSM2715760", "GSM2715761", "GSM2715762", "GSM2715763", "GSM2715764", "GSM2715765", "GSM2715766", "GSM2715767", "GSM2715768", "GSM2715769", "GSM2715770", "GSM2715771", "GSM2715772", "GSM2715773", "GSM2715774", "GSM2715775", "GSM2715776", "GSM2715777", "GSM2715778", "GSM2715779", "GSM2715780", "GSM2715781", "GSM2715782", "GSM2715783", "GSM2715784", "GSM2715785", "GSM2715786", "GSM2715787", "GSM2715788", "GSM2715789", "GSM2715790", "GSM2715791", "GSM2715792", "GSM2715793", "GSM2715794", "GSM2715795", "GSM2715796", "GSM2715797", "GSM2715798", "GSM2715799", "GSM2715800", "GSM2715801", "GSM2715802", "GSM2715803", "GSM2715804", "GSM2715805", "GSM2715806", "GSM2715807", "GSM2715808", "GSM2715809", "GSM2715810", "GSM2715811", "GSM2715812", "GSM2715813", "GSM2715814", "GSM2715815", "GSM2715816", "GSM2715817", "GSM2715818", "GSM2715819", "GSM2715820", "GSM2715821", "GSM2715822", "GSM2715823", "GSM2715824", "GSM2715825", "GSM2715826", "GSM2715827", "GSM2715828", "GSM2715829", "GSM2715830", "GSM2715831", "GSM2715832", "GSM2715833", "GSM2715834", "GSM2715835", "GSM2715836", "GSM2715837", "GSM2715838", "GSM2715839", "GSM2715840", "GSM2715841", "GSM2715842", "GSM2715843", "GSM2715844", "GSM2715845", "GSM2715846", "GSM2715847", "GSM2715848", "GSM2715849", "GSM2715850", "GSM2715851", "GSM2715852", "GSM2715853", "GSM2715854", "GSM2715855", "GSM2715856", "GSM2715857", "GSM2715858", "GSM2715859", "GSM2715860", "GSM2715861", "GSM2715862", "GSM2715863", "GSM2715864", "GSM2715865", "GSM2715866", "GSM2715867", "GSM2715868", "GSM2715869", "GSM2715870", "GSM2715871", "GSM2715872", "GSM2715873", "GSM2715874", "GSM2715875", "GSM2715876", "GSM2715877", "GSM2715878", "GSM2715879", "GSM2715880", "GSM2715881", "GSM2715882", "GSM2715883", "GSM2715884", "GSM2715885", "GSM2715886", "GSM2715887", "GSM2715888", "GSM2715889", "GSM2715890", "GSM2715891", "GSM2715892", "GSM2715893", "GSM2715894", "GSM2715895", "GSM2715896", "GSM2715897", "GSM2715898", "GSM2715899", "GSM2715900", "GSM2715901", "GSM2715902", "GSM2715903", "GSM2715904", "GSM2715905", "GSM2715906", "GSM2715907", "GSM2715908", "GSM2715909", "GSM2715910", "GSM2715911", "GSM2715912", "GSM2715913", "GSM2715914", "GSM2715915", "GSM2715916", "GSM2715917", "GSM2715918", "GSM2715919", "GSM2715920", "GSM2715921", "GSM2715922", "GSM2715923", "GSM2715924", "GSM2715925", "GSM2715926", "GSM2715927", "GSM2715928", "GSM2715929", "GSM2715930", "GSM2715931", "GSM2715932", "GSM2715933", "GSM2715934", "GSM2715935", "GSM2715936", "GSM2715937", "GSM2715938", "GSM2715939", "GSM2715940", "GSM2715941", "GSM2715942", "GSM2715943", "GSM2715944", "GSM2715945", "GSM2715946", "GSM2715947", "GSM2715948", "GSM2715949", "GSM2715950", "GSM2715951", "GSM2715952", "GSM2715953", "GSM2715954"], "sample_count": 304, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Age-of-Onset Dependent Immune maturation in Pediatric Crohn Disease", "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:GSE109142", "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=GSE109142", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE109142", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2932807", "GSM2932808", "GSM2932809", "GSM2932810", "GSM2932811", "GSM2932812", "GSM2932813", "GSM2932814", "GSM2932815", "GSM2932816", "GSM2932817", "GSM2932818", "GSM2932819", "GSM2932820", "GSM2932821", "GSM2932822", "GSM2932823", "GSM2932824", "GSM2932825", "GSM2932826", "GSM2932827", "GSM2932828", "GSM2932829", "GSM2932830", "GSM2932831", "GSM2932832", "GSM2932833", "GSM2932834", "GSM2932835", "GSM2932836", "GSM2932837", "GSM2932838", "GSM2932839", "GSM2932840", "GSM2932841", "GSM2932842", "GSM2932843", "GSM2932844", "GSM2932845", "GSM2932846", "GSM2932847", "GSM2932848", "GSM2932849", "GSM2932850", "GSM2932851", "GSM2932852", "GSM2932853", "GSM2932854", "GSM2932855", "GSM2932856", "GSM2932857", "GSM2932858", "GSM2932859", "GSM2932860", "GSM2932861", "GSM2932862", "GSM2932863", "GSM2932864", "GSM2932865", "GSM2932866", "GSM2932867", "GSM2932868", "GSM2932869", "GSM2932870", "GSM2932871", "GSM2932872", "GSM2932873", "GSM2932874", "GSM2932875", "GSM2932876", "GSM2932877", "GSM2932878", "GSM2932879", "GSM2932880", "GSM2932881", "GSM2932882", "GSM2932883", "GSM2932884", "GSM2932885", "GSM2932886", "GSM2932887", "GSM2932888", "GSM2932889", "GSM2932890", "GSM2932891", "GSM2932892", "GSM2932893", "GSM2932894", "GSM2932895", "GSM2932896", "GSM2932897", "GSM2932898", "GSM2932899", "GSM2932900", "GSM2932901", "GSM2932902", "GSM2932903", "GSM2932904", "GSM2932905", "GSM2932906", "GSM2932907", "GSM2932908", "GSM2932909", "GSM2932910", "GSM2932911", "GSM2932912", "GSM2932913", "GSM2932914", "GSM2932915", "GSM2932916", "GSM2932917", "GSM2932918", "GSM2932919", "GSM2932920", "GSM2932921", "GSM2932922", "GSM2932923", "GSM2932924", "GSM2932925", "GSM2932926", "GSM2932927", "GSM2932928", "GSM2932929", "GSM2932930", "GSM2932931", "GSM2932932", "GSM2932933", "GSM2932934", "GSM2932935", "GSM2932936", "GSM2932937", "GSM2932938", "GSM2932939", "GSM2932940", "GSM2932941", "GSM2932942", "GSM2932943", "GSM2932944", "GSM2932945", "GSM2932946", "GSM2932947", "GSM2932948", "GSM2932949", "GSM2932950", "GSM2932951", "GSM2932952", "GSM2932953", "GSM2932954", "GSM2932955", "GSM2932956", "GSM2932957", "GSM2932958", "GSM2932959", "GSM2932960", "GSM2932961", "GSM2932962", "GSM2932963", "GSM2932964", "GSM2932965", "GSM2932966", "GSM2932967", "GSM2932968", "GSM2932969", "GSM2932970", "GSM2932971", "GSM2932972", "GSM2932973", "GSM2932974", "GSM2932975", "GSM2932976", "GSM2932977", "GSM2932978", "GSM2932979", "GSM2932980", "GSM2932981", "GSM2932982", "GSM2932983", "GSM2932984", "GSM2932985", "GSM2932986", "GSM2932987", "GSM2932988", "GSM2932989", "GSM2932990", "GSM2932991", "GSM2932992", "GSM2932993", "GSM2932994", "GSM2932995", "GSM2932996", "GSM2932997", "GSM2932998", "GSM2932999", "GSM2933000", "GSM2933001", "GSM2933002", "GSM2933003", "GSM2933004", "GSM2933005", "GSM2933006", "GSM2933007", "GSM2933008", "GSM2933009", "GSM2933010", "GSM2933011", "GSM2933012", "GSM2933013", "GSM2933014", "GSM2933015", "GSM2933016", "GSM2933017", "GSM2933018", "GSM2933019", "GSM2933020", "GSM2933021", "GSM2933022", "GSM2933023", "GSM2933024", "GSM2933025", "GSM2933026", "GSM2933027", "GSM2933028", "GSM2933029", "GSM2933030", "GSM2933031", "GSM2933032"], "sample_count": 226, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Mucosal transcriptome of rectal biopsies in treatment-naïve, pediatric ulcerative colitits patients", "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:GSE117993", "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=GSE117993", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE117993", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3316656", "GSM3316657", "GSM3316658", "GSM3316659", "GSM3316660", "GSM3316661", "GSM3316662", "GSM3316663", "GSM3316664", "GSM3316665", "GSM3316666", "GSM3316667", "GSM3316668", "GSM3316669", "GSM3316670", "GSM3316671", "GSM3316672", "GSM3316673", "GSM3316674", "GSM3316675", "GSM3316676", "GSM3316677", "GSM3316678", "GSM3316679", "GSM3316680", "GSM3316681", "GSM3316682", "GSM3316683", "GSM3316684", "GSM3316685", "GSM3316686", "GSM3316687", "GSM3316688", "GSM3316689", "GSM3316690", "GSM3316691", "GSM3316692", "GSM3316693", "GSM3316694", "GSM3316695", "GSM3316696", "GSM3316697", "GSM3316698", "GSM3316699", "GSM3316700", "GSM3316701", "GSM3316702", "GSM3316703", "GSM3316704", "GSM3316705", "GSM3316706", "GSM3316707", "GSM3316708", "GSM3316709", "GSM3316710", "GSM3316711", "GSM3316712", "GSM3316713", "GSM3316714", "GSM3316715", "GSM3316716", "GSM3316717", "GSM3316718", "GSM3316719", "GSM3316720", "GSM3316721", "GSM3316722", "GSM3316723", "GSM3316724", "GSM3316725", "GSM3316726", "GSM3316727", "GSM3316728", "GSM3316729", "GSM3316730", "GSM3316731", "GSM3316732", "GSM3316733", "GSM3316734", "GSM3316735", "GSM3316736", "GSM3316737", "GSM3316738", "GSM3316739", "GSM3316740", "GSM3316741", "GSM3316742", "GSM3316743", "GSM3316744", "GSM3316745", "GSM3316746", "GSM3316747", "GSM3316748", "GSM3316749", "GSM3316750", "GSM3316751", "GSM3316752", "GSM3316753", "GSM3316754", "GSM3316755", "GSM3316756", "GSM3316757", "GSM3316758", "GSM3316759", "GSM3316760", "GSM3316761", "GSM3316762", "GSM3316763", "GSM3316764", "GSM3316765", "GSM3316766", "GSM3316767", "GSM3316768", "GSM3316769", "GSM3316770", "GSM3316771", "GSM3316772", "GSM3316773", "GSM3316774", "GSM3316775", "GSM3316776", "GSM3316777", "GSM3316778", "GSM3316779", "GSM3316780", "GSM3316781", "GSM3316782", "GSM3316783", "GSM3316784", "GSM3316785", "GSM3316786", "GSM3316787", "GSM3316788", "GSM3316789", "GSM3316790", "GSM3316791", "GSM3316792", "GSM3316793", "GSM3316794", "GSM3316795", "GSM3316796", "GSM3316797", "GSM3316798", "GSM3316799", "GSM3316800", "GSM3316801", "GSM3316802", "GSM3316803", "GSM3316804", "GSM3316805", "GSM3316806", "GSM3316807", "GSM3316808", "GSM3316809", "GSM3316810", "GSM3316811", "GSM3316812", "GSM3316813", "GSM3316814", "GSM3316815", "GSM3316816", "GSM3316817", "GSM3316818", "GSM3316819", "GSM3316820", "GSM3316821", "GSM3316822", "GSM3316823", "GSM3316824", "GSM3316825", "GSM3316826", "GSM3316827", "GSM3316828", "GSM3316829", "GSM3316830", "GSM3316831", "GSM3316832", "GSM3316833", "GSM3316834", "GSM3316835", "GSM3316836", "GSM3316837", "GSM3316838", "GSM3316839", "GSM3316840", "GSM3316841", "GSM3316842", "GSM3316843", "GSM3316844", "GSM3316845"], "sample_count": 190, "group_sizes": null, "group_sizes_basis": null, "platform": "16791", "taxon": "Homo sapiens", "title": "Transcription profiles of rectal biopsies obtained during diagnostic colonoscopy for pediatric inflammatory bowel diseases.", "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:GSE57945", "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=GSE57945", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57945", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1598408", "GSM1598409", "GSM1598410", "GSM1598411", "GSM1598412", "GSM1598413", "GSM1598414", "GSM1598415", "GSM1598416", "GSM1598417", "GSM1598418", "GSM1598419", "GSM1598420", "GSM1598421", "GSM1598422", "GSM1598423", "GSM1598424", "GSM1598425", "GSM1598426", "GSM1598427", "GSM1598428", "GSM1598429", "GSM1598430", "GSM1598431", "GSM1598432", "GSM1598433", "GSM1598434", "GSM1598435", "GSM1598436", "GSM1598437", "GSM1598438", "GSM1598439", "GSM1598440", "GSM1598441", "GSM1598442", "GSM1598443", "GSM1598444", "GSM1598445", "GSM1598446", "GSM1598447", "GSM1598448", "GSM1598449", "GSM1598450", "GSM1598451", "GSM1598452", "GSM1598453", "GSM1598454", "GSM1598455", "GSM1598456", "GSM1598457", "GSM1598458", "GSM1598459", "GSM1598460", "GSM1598461", "GSM1598462", "GSM1598463", "GSM1598464", "GSM1598465", "GSM1598466", "GSM1598467", "GSM1598468", "GSM1598469", "GSM1598470", "GSM1598471", "GSM1598472", "GSM1598473", "GSM1598474", "GSM1598475", "GSM1598476", "GSM1598477", "GSM1598478", "GSM1598479", "GSM1598480", "GSM1598481", "GSM1598482", "GSM1598483", "GSM1598484", "GSM1598485", "GSM1598486", "GSM1598487", "GSM1598488", "GSM1598489", "GSM1598490", "GSM1598491", "GSM1598492", "GSM1598493", "GSM1598494", "GSM1598495", "GSM1598496", "GSM1598497", "GSM1598498", "GSM1598499", "GSM1598500", "GSM1598501", "GSM1598502", "GSM1598503", "GSM1598504", "GSM1598505", "GSM1598506", "GSM1598507", "GSM1598508", "GSM1598509", "GSM1598510", "GSM1598511", "GSM1598512", "GSM1598513", "GSM1598514", "GSM1598515", "GSM1598516", "GSM1598517", "GSM1598518", "GSM1598519", "GSM1598520", "GSM1598521", "GSM1598522", "GSM1598523", "GSM1598524", "GSM1598525", "GSM1598526", "GSM1598527", "GSM1598528", "GSM1598529", "GSM1598530", "GSM1598531", "GSM1598532", "GSM1598533", "GSM1598534", "GSM1598535", "GSM1598536", "GSM1598537", "GSM1598538", "GSM1598539", "GSM1598540", "GSM1598541", "GSM1598542", "GSM1598543", "GSM1598544", "GSM1598545", "GSM1598546", "GSM1598547", "GSM1598548", "GSM1598549", "GSM1598550", "GSM1598551", "GSM1598552", "GSM1598553", "GSM1598554", "GSM1598555", "GSM1598556", "GSM1598557", "GSM1598558", "GSM1598559", "GSM1598560", "GSM1598561", "GSM1598562", "GSM1598563", "GSM1598564", "GSM1598565", "GSM1598566", "GSM1598567", "GSM1598568", "GSM1598569", "GSM1598570", "GSM1598571", "GSM1598572", "GSM1598573", "GSM1598574", "GSM1598575", "GSM1598576", "GSM1598577", "GSM1598578", "GSM1598579", "GSM1598580", "GSM1598581", "GSM1598582", "GSM1598583", "GSM1598584", "GSM1598585", "GSM1598586", "GSM1598587", "GSM1598588", "GSM1598589", "GSM1598590", "GSM1598591", "GSM1598592", "GSM1598593", "GSM1598594", "GSM1598595", "GSM1598596", "GSM1598597", "GSM1598598", "GSM1598599", "GSM1598600", "GSM1598601", "GSM1598602", "GSM1598603", "GSM1598604", "GSM1598605", "GSM1598606", "GSM1598607", "GSM1598608", "GSM1598609", "GSM1598610", "GSM1598611", "GSM1598612", "GSM1598613", "GSM1598614", "GSM1598615", "GSM1598616", "GSM1598617", "GSM1598618", "GSM1598619", "GSM1598620", "GSM1598621", "GSM1598622", "GSM1598623", "GSM1598624", "GSM1598625", "GSM1598626", "GSM1598627", "GSM1598628", "GSM1598629", "GSM1598630", "GSM1598631", "GSM1598632", "GSM1598633", "GSM1598634", "GSM1598635", "GSM1598636", "GSM1598637", "GSM1598638", "GSM1598639", "GSM1598640", "GSM1598641", "GSM1598642", "GSM1598643", "GSM1598644", "GSM1598645", "GSM1598646", "GSM1598647", "GSM1598648", "GSM1598649", "GSM1598650", "GSM1598651", "GSM1598652", "GSM1598653", "GSM1598654", "GSM1598655", "GSM1598656", "GSM1598657", "GSM1598658", "GSM1598659", "GSM1598660", "GSM1598661", "GSM1598662", "GSM1598663", "GSM1598664", "GSM1598665", "GSM1598666", "GSM1598667", "GSM1598668", "GSM1598669", "GSM1598670", "GSM1598671", "GSM1598672", "GSM1598673", "GSM1598674", "GSM1598675", "GSM1598676", "GSM1598677", "GSM1598678", "GSM1598679", "GSM1598680", "GSM1598681", "GSM1598682", "GSM1598683", "GSM1598684", "GSM1598685", "GSM1598686", "GSM1598687", "GSM1598688", "GSM1598689", "GSM1598690", "GSM1598691", "GSM1598692", "GSM1598693", "GSM1598694", "GSM1598695", "GSM1598696", "GSM1598697", "GSM1598698", "GSM1598699", "GSM1598700", "GSM1598701", "GSM1598702", "GSM1598703", "GSM1598704", "GSM1598705", "GSM1598706", "GSM1598707", "GSM1598708", "GSM1598709", "GSM1598710", "GSM1598711", "GSM1598712", "GSM1598713", "GSM1598714", "GSM1598715", "GSM1598716", "GSM1598717", "GSM1598718", "GSM1598719", "GSM1598720", "GSM1598721", "GSM1598722", "GSM1598723", "GSM1598724", "GSM1598725", "GSM1598726", "GSM1598727", "GSM1598728", "GSM1598729"], "sample_count": 322, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Core Ileal Transcriptome in Pediatric Crohn Disease", "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:GSE93624", "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=GSE93624", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE93624", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2458832", "GSM2458833", "GSM2458834", "GSM2458835", "GSM2458836", "GSM2458837", "GSM2458838", "GSM2458839", "GSM2458840", "GSM2458841", "GSM2458842", "GSM2458843", "GSM2458844", "GSM2458845", "GSM2458846", "GSM2458847", "GSM2458848", "GSM2458849", "GSM2458850", "GSM2458851", "GSM2458852", "GSM2458853", "GSM2458854", "GSM2458855", "GSM2458856", "GSM2458857", "GSM2458858", "GSM2458859", "GSM2458860", "GSM2458861", "GSM2458862", "GSM2458863", "GSM2458864", "GSM2458865", "GSM2458866", "GSM2458867", "GSM2458868", "GSM2458869", "GSM2458870", "GSM2458871", "GSM2458872", "GSM2458873", "GSM2458874", "GSM2458875", "GSM2458876", "GSM2458877", "GSM2458878", "GSM2458879", "GSM2458880", "GSM2458881", "GSM2458882", "GSM2458883", "GSM2458884", "GSM2458885", "GSM2458886", "GSM2458887", "GSM2458888", "GSM2458889", "GSM2458890", "GSM2458891", "GSM2458892", "GSM2458893", "GSM2458894", "GSM2458895", "GSM2458896", "GSM2458897", "GSM2458898", "GSM2458899", "GSM2458900", "GSM2458901", "GSM2458902", "GSM2458903", "GSM2458904", "GSM2458905", "GSM2458906", "GSM2458907", "GSM2458908", "GSM2458909", "GSM2458910", "GSM2458911", "GSM2458912", "GSM2458913", "GSM2458914", "GSM2458915", "GSM2458916", "GSM2458917", "GSM2458918", "GSM2458919", "GSM2458920", "GSM2458921", "GSM2458922", "GSM2458923", "GSM2458924", "GSM2458925", "GSM2458926", "GSM2458927", "GSM2458928", "GSM2458929", "GSM2458930", "GSM2458931", "GSM2458932", "GSM2458933", "GSM2458934", "GSM2458935", "GSM2458936", "GSM2458937", "GSM2458938", "GSM2458939", "GSM2458940", "GSM2458941", "GSM2458942", "GSM2458943", "GSM2458944", "GSM2458945", "GSM2458946", "GSM2458947", "GSM2458948", "GSM2458949", "GSM2458950", "GSM2458951", "GSM2458952", "GSM2458953", "GSM2458954", "GSM2458955", "GSM2458956", "GSM2458957", "GSM2458958", "GSM2458959", "GSM2458960", "GSM2458961", "GSM2458962", "GSM2458963", "GSM2458964", "GSM2458965", "GSM2458966", "GSM2458967", "GSM2458968", "GSM2458969", "GSM2458970", "GSM2458971", "GSM2458972", "GSM2458973", "GSM2458974", "GSM2458975", "GSM2458976", "GSM2458977", "GSM2458978", "GSM2458979", "GSM2458980", "GSM2458981", "GSM2458982", "GSM2458983", "GSM2458984", "GSM2458985", "GSM2458986", "GSM2458987", "GSM2458988", "GSM2458989", "GSM2458990", "GSM2458991", "GSM2458992", "GSM2458993", "GSM2458994", "GSM2458995", "GSM2458996", "GSM2458997", "GSM2458998", "GSM2458999", "GSM2459000", "GSM2459001", "GSM2459002", "GSM2459003", "GSM2459004", "GSM2459005", "GSM2459006", "GSM2459007", "GSM2459008", "GSM2459009", "GSM2459010", "GSM2459011", "GSM2459012", "GSM2459013", "GSM2459014", "GSM2459015", "GSM2459016", "GSM2459017", "GSM2459018", "GSM2459019", "GSM2459020", "GSM2459021", "GSM2459022", "GSM2459023", "GSM2459024", "GSM2459025", "GSM2459026", "GSM2459027", "GSM2459028", "GSM2459029", "GSM2459030", "GSM2459031", "GSM2459032", "GSM2459033", "GSM2459034", "GSM2459035", "GSM2459036", "GSM2459037", "GSM2459038", "GSM2459039", "GSM2459040", "GSM2459041", "GSM2459042", "GSM2459043", "GSM2459044", "GSM2459045", "GSM2459046", "GSM2459047", "GSM2459048", "GSM2459049", "GSM2459050", "GSM2459051", "GSM2459052", "GSM2459053", "GSM2459054", "GSM2459055", "GSM2459056", "GSM2459057", "GSM2459058", "GSM2459059", "GSM2459060", "GSM2459061", "GSM2459062", "GSM2459063", "GSM2459064", "GSM2459065", "GSM2459066", "GSM2459067", "GSM2459068", "GSM2459069", "GSM2459070", "GSM2459071", "GSM2459072", "GSM2459073", "GSM2459074", "GSM2459075", "GSM2459076"], "sample_count": 245, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Profiling of Ileal Transcriptome in Pediatric Crohn Disease", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE101794 not downloaded", "asset:data:geo:GSE101794 licence not read", "asset:data:geo:GSE109142 not downloaded", "asset:data:geo:GSE109142 licence not read", "asset:data:geo:GSE117993 not downloaded", "asset:data:geo:GSE117993 licence not read", "asset:data:geo:GSE57945 not downloaded", "asset:data:geo:GSE57945 licence not read", "asset:data:geo:GSE93624 not downloaded", "asset:data:geo:GSE93624 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "differential_expression", "specific": "deseq2", "label": "Differential expression analysis", "dsl_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["count_matrix_with_condition"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "RNA-seq data of PIBD from GEO datasets were analyzed using DESeq2, WGCNA, and functional enrichment analysis. Ferroptosis-related diagnostic genes were screened through LASSO, Random Forest, and mSVM-RFE algorithms, and validated in GSE57945 and GSE117993 datasets."}}, {"id": "method-2", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.7, "band": "medium", "quote": "Random Forest"}}, {"id": "method-3", "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": 0.8, "band": "high", "quote": "logistic regression"}}, {"id": "method-4", "family": "correlation_analysis", "specific": "spearman", "label": "Correlation analysis", "dsl_operations": ["spearman_rho"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.8, "band": "high", "quote": "Spearman correlation"}}, {"id": "method-5", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC analysis"}}], "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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: deseq2."}, "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": ["GSE101794", "GSE93624", "GSE57945", "GSE117993", "GSE109142"], "resolved_accessions": ["GSE101794", "GSE93624", "GSE57945", "GSE117993", "GSE109142"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: https://www.ncbi.nlm.nih.gov/geo/GSE93624GSE101794."], "basis": "The paper names GSE101794, GSE93624, GSE57945, GSE117993, GSE109142 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": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "assets": ["source:pmid:41312366", "data:geo:GSE101794"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE101794"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:06:45Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 18734, "completion_tokens": 1817, "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:41312366", "type": "paper", "label": "pmid:41312366"}, {"id": "source:pmid:41312366", "type": "manuscript", "label": "PMID 41312366 full text"}, {"id": "data:geo:GSE101794", "type": "dataset", "label": "GEO GSE101794"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41312366", "type": "paper", "label": "pmid:41312366"}, {"id": "source:pmid:41312366", "type": "manuscript", "label": "PMID 41312366 full text"}, {"id": "data:geo:GSE101794", "type": "dataset", "label": "GEO GSE101794"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41312366", "type": "extraction", "used": ["source:pmid:41312366"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE101794", "type": "accession_resolution", "used": ["data:geo:GSE101794"], "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:41312366", "parent_hash": "sha256:27d902597cff05bbe3272006fa1e582e957e51ae3a446a829fc8f3a185c5b9c2", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE101794 licence not read", "asset:data:geo:GSE101794 not downloaded", "asset:data:geo:GSE109142 licence not read", "asset:data:geo:GSE109142 not downloaded", "asset:data:geo:GSE117993 licence not read", "asset:data:geo:GSE117993 not downloaded", "asset:data:geo:GSE57945 licence not read", "asset:data:geo:GSE57945 not downloaded", "asset:data:geo:GSE93624 licence not read", "asset:data:geo:GSE93624 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": 0.93, "evidence": ["validate their role in ferroptosis. Methods: RNA-seq data of PIBD from GEO datasets were analyzed"], "order_basis": "paper_text_order:541", "id": "assay:1"}, {"role": "data_generation", "definition_id": "transfection", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["d ferroptosis, including siRNA-mediated gene knockdown, western blotting of ferroptosis-related pro", "atasets. In vitro experiments confirmed that knockdown of PML or CHAC1 significantly alleviated LPS", "CHAC1 in LPS-induced ferroptosis, including siRNA-mediated gene knockdown, western blotting of"], "order_basis": "paper_text_order:940", "id": "assay:2"}, {"role": "data_generation", "definition_id": "western_blot", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["is, including siRNA-mediated gene knockdown, western blotting of ferroptosis-related proteins (ACSL4, SLC7"], "order_basis": "paper_text_order:970", "id": "assay:3"}, {"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": ["Figure 5A). In a 4-week DSS-induced colitis mouse model, DSS-treated mice displayed shortened colon", "Figure 5A). In a 4-week DSS-induced colitis mouse model, DSS-treated mice displayed shortened", "05). (G) mRNA expression of PML and CHAC1 in mouse colon tissues. (H, I) Immunohistochemical st"], "order_basis": "paper_text_order:4110", "id": "assay:4"}, {"role": "data_generation", "definition_id": "ihc", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["well as PML and CHAC1 (p < 0.01; Figure 5G). Immunohistochemistry confirmed elevated protein expression of PML", "PML and CHAC1 in mouse colon tissues. (H, I) Immunohistochemical staining and quantification (*p < 0.05; **p"], "order_basis": "paper_text_order:4512", "id": "assay:5"}, {"role": "analysis", "definition_id": "differential_expression", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["normalise_counts", "differential_expression_fit", "fdr_bh"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["RNA-seq data of PIBD from GEO datasets were analyzed using DESeq2, WGCNA, and functional enrichment analysis. Ferroptosis-related diagnostic genes were screened through LASSO, Random Forest, and mSVM-RFE algorithms, and validated in GSE57945 and GSE117993 datasets."], "order_basis": "consumes_earlier_output", "id": "assay:6"}]},"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":"2026-11-04T01:15:13+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}}}