{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38192798", "kind": "science-record", "revision": 2, "content_hash": "sha256:c6b7f23584039f4938936a767f0745f5e39835aba96139a8d91c6e26fef48e06", "created_at": "2026-11-01T19:20:06Z", "updated_at": "2026-11-01T21:32:15Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Pyroptosis-related signatures predict immune characteristics and prognosis in IPF.", "doi": "10.1016/j.heliyon.2023.e23683", "pmid": "38192798", "authors": ["Yijun He", "Tingting Yao", "Yan Zhang", "Lingzhi Long", "Guoliang Jiang", "Xiangyu Zhang", "Xin Lv", "Yuanyuan Han", "Xiaoyun Cheng", "Mengyu Li", "Mao Jiang", "Zhangzhe Peng", "Lijian Tao", "Jie Meng"], "journal": "Heliyon", "year": 2024, "abstract": "The purpose of this work was to use integrated bioinformatics analysis to screen for pyroptosis-related genes (PRGs) and possible immunological phenotypes linked to the development and course of IPF. Transcriptome sequencing datasets GSE70866, GSE47460 and GSE150910 were obtained from GEO database. From the GSE70866 database, 34 PRGs with differential expression were found in IPF as compared to healthy controls. In addition, a diagnostic model containing 4 genes PRGs (CAMP, MKI67, TCEA3 and USP24) was constructed based on LASSO logistic regression. The diagnostic model showed good predictive ability to differentiate between IPF and healthy, with ROC-AUC ranging from 0.910 to 0.997 in GSE70866 and GSE150910 datasets. Moreover, based on a combined cohort of the Freiburg and the Siena cohorts from GSE70866 dataset, we identified ten PRGs that might predict prognosis for IPF. We constructed a prognostic model that included eight PRGs (CLEC5A, TREM2, MMP1, IRF2, SEZ6L2, ADORA3, NOS2, USP24) by LASSO Cox regression and validated it in the Leuven cohort. The risk model divided IPF patients from the combined cohort into high-risk and low-risk subgroups. There were significant differences between the two subgroups in terms of IPF survival and GAP stage. There is a close correlation between leukocyte migration, plasma membrane junction, and poor prognosis in a high-risk subgroup. Furthermore, a high-risk score was associated with more plasma cells, activated NK cells, monocytes, and activated mast cells. Additionally, we identified HDAC inhibitors in the cMAP database that might be therapeutic for IPF. To summarize, pyroptosis and its underlying immunological features are to blame for the onset and progression of IPF. PRG-based predictive models and drugs may offer new treatment options for IPF.", "claims": [{"id": "claim-method", "statement": "Based on LASSO Cox regression analysis, an eight PRG prediction model was derived (Fig. 4D and E).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38192798", "locator": "sections[15] \"Construction of a PRGs-related prognostic model in IPF\" paragraph 2", "quote": "Based on LASSO Cox regression analysis, an eight PRG prediction model was derived (Fig. 4D and E)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38192798", "locator": "sections[21] \"Data availability statement\" paragraph 2", "quote": "The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "We constructed a prognostic model that included eight PRGs (CLEC5A, TREM2, MMP1, IRF2, SEZ6L2, ADORA3, NOS2, USP24) by LASSO Cox regression and validated it in the Leuven cohort.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:38192798", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "We constructed a prognostic model that included eight PRGs (CLEC5A, TREM2, MMP1, IRF2, SEZ6L2, ADORA3, NOS2, USP24) by LASSO Cox regression and validated it in the Leuven cohort."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "We constructed a prognostic model that included eight PRGs (CLEC5A, TREM2, MMP1, IRF2, SEZ6L2, ADORA3, NOS2, USP24) by LASSO Cox regression and validated it in the Leuven cohort.", "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:38192798"], "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:GSE150910"], "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:GSE150910"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38192798", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1016/j.heliyon.2023.e23683", "sha256": "sha256:1ba5ac9d7206114d2bfc69e886c7e1e9b5d0e2a0709832c94b161f58a0d29445", "bytes": 52670, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1016/j.heliyon.2023.e23683", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10772192", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE150910", "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=GSE150910", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE150910", "version": null, "note": "The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4560505", "GSM4560506", "GSM4560507", "GSM4560508", "GSM4560509", "GSM4560510", "GSM4560511", "GSM4560512", "GSM4560513", "GSM4560514", "GSM4560515", "GSM4560516", "GSM4560517", "GSM4560518", "GSM4560519", "GSM4560520", "GSM4560521", "GSM4560522", "GSM4560523", "GSM4560524", "GSM4560525", "GSM4560526", "GSM4560527", "GSM4560528", "GSM4560529", "GSM4560530", "GSM4560531", "GSM4560532", "GSM4560533", "GSM4560534", "GSM4560535", "GSM4560536", "GSM4560537", "GSM4560538", "GSM4560539", "GSM4560540", "GSM4560541", "GSM4560542", "GSM4560543", "GSM4560544", "GSM4560545", "GSM4560546", "GSM4560547", "GSM4560548", "GSM4560549", "GSM4560550", "GSM4560551", "GSM4560552", "GSM4560553", "GSM4560554", "GSM4560555", "GSM4560556", "GSM4560557", "GSM4560558", "GSM4560559", "GSM4560560", "GSM4560561", "GSM4560562", "GSM4560563", "GSM4560564", "GSM4560565", "GSM4560566", "GSM4560567", "GSM4560568", "GSM4560569", "GSM4560570", "GSM4560571", "GSM4560572", "GSM4560573", "GSM4560574", "GSM4560575", "GSM4560576", "GSM4560577", "GSM4560578", "GSM4560579", "GSM4560580", "GSM4560581", "GSM4560582", "GSM4560583", "GSM4560584", "GSM4560585", "GSM4560586", "GSM4560587", "GSM4560588", "GSM4560589", "GSM4560590", "GSM4560591", "GSM4560592", "GSM4560593", "GSM4560594", "GSM4560595", "GSM4560596", "GSM4560597", "GSM4560598", "GSM4560599", "GSM4560600", "GSM4560601", "GSM4560602", "GSM4560603", "GSM4560604", "GSM4560605", "GSM4560606", "GSM4560607", "GSM4560608", "GSM4560609", "GSM4560610", "GSM4560611", "GSM4560612", "GSM4560613", "GSM4560614", "GSM4560615", "GSM4560616", "GSM4560617", "GSM4560618", "GSM4560619", "GSM4560620", "GSM4560621", "GSM4560622", "GSM4560623", "GSM4560624", "GSM4560625", "GSM4560626", "GSM4560627", "GSM4560628", "GSM4560629", "GSM4560630", "GSM4560631", "GSM4560632", "GSM4560633", "GSM4560634", "GSM4560635", "GSM4560636", "GSM4560637", "GSM4560638", "GSM4560639", "GSM4560640", "GSM4560641", "GSM4560642", "GSM4560643", "GSM4560644", "GSM4560645", "GSM4560646", "GSM4560647", "GSM4560648", "GSM4560649", "GSM4560650", "GSM4560651", "GSM4560652", "GSM4560653", "GSM4560654", "GSM4560655", "GSM4560656", "GSM4560657", "GSM4560658", "GSM4560659", "GSM4560660", "GSM4560661", "GSM4560662", "GSM4560663", "GSM4560664", "GSM4560665", "GSM4560666", "GSM4560667", "GSM4560668", "GSM4560669", "GSM4560670", "GSM4560671", "GSM4560672", "GSM4560673", "GSM4560674", "GSM4560675", "GSM4560676", "GSM4560677", "GSM4560678", "GSM4560679", "GSM4560680", "GSM4560681", "GSM4560682", "GSM4560683", "GSM4560684", "GSM4560685", "GSM4560686", "GSM4560687", "GSM4560688", "GSM4560689", "GSM4560690", "GSM4560691", "GSM4560692", "GSM4560693", "GSM4560694", "GSM4560695", "GSM4560696", "GSM4560697", "GSM4560698", "GSM4560699", "GSM4560700", "GSM4560701", "GSM4560702", "GSM4560703", "GSM4560704", "GSM4560705", "GSM4560706", "GSM4560707", "GSM4560708", "GSM4560709", "GSM4560710", "GSM4560711", "GSM4560712", "GSM4560713", "GSM4560714", "GSM4560715", "GSM4560716", "GSM4560717", "GSM4560718", "GSM4560719", "GSM4560720", "GSM4560721", "GSM4560722", "GSM4560723", "GSM4560724", "GSM4560725", "GSM4560726", "GSM4560727", "GSM4560728", "GSM4560729", "GSM4560730", "GSM4560731", "GSM4560732", "GSM4560733", "GSM4560734", "GSM4560735", "GSM4560736", "GSM4560737", "GSM4560738", "GSM4560739", "GSM4560740", "GSM4560741", "GSM4560742", "GSM4560743", "GSM4560744", "GSM4560745", "GSM4560746", "GSM4560747", "GSM4560748", "GSM4560749", "GSM4560750", "GSM4560751", "GSM4560752", "GSM4560753", "GSM4560754", "GSM4560755", "GSM4560756", "GSM4560757", "GSM4560758", "GSM4560759", "GSM4560760", "GSM4560761", "GSM4560762", "GSM4560763", "GSM4560764", "GSM4560765", "GSM4560766", "GSM4560767", "GSM4560768", "GSM4560769", "GSM4560770", "GSM4560771", "GSM4560772", "GSM4560773", "GSM4560774", "GSM4560775", "GSM4560776", "GSM4560777", "GSM4560778", "GSM4560779", "GSM4560780", "GSM4560781", "GSM4560782", "GSM4560783", "GSM4560784", "GSM4560785", "GSM4560786", "GSM4560787", "GSM4560788", "GSM4560789", "GSM4560790", "GSM4560791", "GSM4560792"], "sample_count": 288, "group_sizes": null, "group_sizes_basis": null, "platform": "24676", "taxon": "Homo sapiens", "title": "RNA-Sequencing of Chronic hypersensitivity pneumonitis compared with Idiopathic Pulmonary Fibrosis and Control Lung", "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:GSE47460", "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=GSE47460", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE47460", "version": null, "note": "The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1149948", "GSM1149949", "GSM1149950", "GSM1149951", "GSM1149952", "GSM1149953", "GSM1149954", "GSM1149955", "GSM1149956", "GSM1149957", "GSM1149958", "GSM1149959", "GSM1149960", "GSM1149961", "GSM1149962", "GSM1149963", "GSM1149964", "GSM1149965", "GSM1149966", "GSM1149967", "GSM1149968", "GSM1149969", "GSM1149970", "GSM1149971", "GSM1149972", "GSM1149973", "GSM1149974", "GSM1149975", "GSM1149976", "GSM1149977", "GSM1149978", "GSM1149979", "GSM1149980", "GSM1149981", "GSM1149982", "GSM1149983", "GSM1149984", "GSM1149985", "GSM1149986", "GSM1149987", "GSM1149988", "GSM1149989", "GSM1149990", "GSM1149991", "GSM1149992", "GSM1149993", "GSM1149994", "GSM1149995", "GSM1149996", "GSM1149997", "GSM1149998", "GSM1149999", "GSM1150000", "GSM1150001", "GSM1150002", "GSM1150003", "GSM1150004", "GSM1150005", "GSM1150006", "GSM1150007", "GSM1150008", "GSM1150009", "GSM1150010", "GSM1150011", "GSM1150012", "GSM1150013", "GSM1150014", "GSM1150015", "GSM1150016", "GSM1150017", "GSM1150018", "GSM1150019", "GSM1150020", "GSM1150021", "GSM1150022", "GSM1150023", "GSM1150024", "GSM1150025", "GSM1150026", "GSM1150027", "GSM1150028", "GSM1150029", "GSM1150030", "GSM1150031", "GSM1150032", "GSM1150033", "GSM1150034", "GSM1150035", "GSM1150036", "GSM1150037", "GSM1150038", "GSM1150039", "GSM1150040", "GSM1150041", "GSM1150042", "GSM1150043", "GSM1150044", "GSM1150045", "GSM1150046", "GSM1150047", "GSM1150048", "GSM1150049", "GSM1150050", "GSM1150051", "GSM1150052", "GSM1150053", "GSM1150054", "GSM1150055", "GSM1150056", "GSM1150057", "GSM1150058", "GSM1150059", "GSM1150060", "GSM1150061", "GSM1150062", "GSM1150063", "GSM1150064", "GSM1150065", "GSM1150066", "GSM1150067", "GSM1150068", "GSM1150069", "GSM1150070", "GSM1150071", "GSM1150072", "GSM1150073", "GSM1150074", "GSM1150075", "GSM1150076", "GSM1150077", "GSM1150078", "GSM1150079", "GSM1150080", "GSM1150081", "GSM1150082", "GSM1150083", "GSM1150084", "GSM1150085", "GSM1150086", "GSM1150087", "GSM1150088", "GSM1150089", "GSM1150090", "GSM1150091", "GSM1150092", "GSM1150093", "GSM1150094", "GSM1150095", "GSM1150096", "GSM1150097", "GSM1150098", "GSM1150099", "GSM1150100", "GSM1150101", "GSM1150102", "GSM1150103", "GSM1150104", "GSM1150105", "GSM1150106", "GSM1150107", "GSM1150108", "GSM1150109", "GSM1150110", "GSM1150111", "GSM1150112", "GSM1150113", "GSM1150114", "GSM1150115", "GSM1150116", "GSM1150117", "GSM1150118", "GSM1150119", "GSM1150120", "GSM1150121", "GSM1150122", "GSM1150123", "GSM1150124", "GSM1150125", "GSM1150126", "GSM1150127", "GSM1150128", "GSM1150129", "GSM1150130", "GSM1150131", "GSM1150132", "GSM1150133", "GSM1150134", "GSM1150135", "GSM1150136", "GSM1150137", "GSM1150138", "GSM1150139", "GSM1150140", "GSM1150141", "GSM1150142", "GSM1150143", "GSM1150144", "GSM1150145", "GSM1150146", "GSM1150147", "GSM1150148", "GSM1150149", "GSM1150150", "GSM1150151", "GSM1150152", "GSM1150153", "GSM1150154", "GSM1150155", "GSM1150156", "GSM1150157", "GSM1150158", "GSM1150159", "GSM1150160", "GSM1150161", "GSM1150162", "GSM1150163", "GSM1150164", "GSM1150165", "GSM1150166", "GSM1150167", "GSM1150168", "GSM1150169", "GSM1150170", "GSM1150171", "GSM1150172", "GSM1150173", "GSM1150174", "GSM1150175", "GSM1150176", "GSM1150177", "GSM1150178", "GSM1150179", "GSM1150180", "GSM1150181", "GSM1150182", "GSM1150183", "GSM1150184", "GSM1150185", "GSM1150186", "GSM1150187", "GSM1150188", "GSM1150189", "GSM1150190", "GSM1150191", "GSM1150192", "GSM1150193", "GSM1150194", "GSM1150195", "GSM1150196", "GSM1150197", "GSM1150198", "GSM1150199", "GSM1150200", "GSM1150201", "GSM1150202", "GSM1150203", "GSM1150204", "GSM1150205", "GSM1150206", "GSM1150207", "GSM1150208", "GSM1150209", "GSM1150210", "GSM1150211", "GSM1150212", "GSM1150213", "GSM1150214", "GSM1150215", "GSM1150216", "GSM1150217", "GSM1150218", "GSM1150219", "GSM1150220", "GSM1150221", "GSM1150222", "GSM1150223", "GSM1150224", "GSM1150225", "GSM1150226", "GSM1150227", "GSM1150228", "GSM1150229", "GSM1150230", "GSM1150231", "GSM1150232", "GSM1150233", "GSM1150234", "GSM1150235", "GSM1150236", "GSM1150237", "GSM1150238", "GSM1150239", "GSM1150240", "GSM1150241", "GSM1150242", "GSM1150243", "GSM1150244", "GSM1150245", "GSM1150246", "GSM1150247", "GSM1150248", "GSM1150249", "GSM1150250", "GSM1150251", "GSM1150252", "GSM1150253", "GSM1150254", "GSM1150255", "GSM1150256", "GSM1150257", "GSM1150258", "GSM1150259", "GSM1150260", "GSM1150261", "GSM1150262", "GSM1150263", "GSM1150264", "GSM1150265", "GSM1150266", "GSM1150267", "GSM1150268", "GSM1150269", "GSM1150270", "GSM1150271", "GSM1150272", "GSM1150273", "GSM1150274", "GSM1150275", "GSM1150276", "GSM1150277", "GSM1150278", "GSM1150279", "GSM1150280", "GSM1150281", "GSM1150282", "GSM1150283", "GSM1150284", "GSM1150285", "GSM1150286", "GSM1150287", "GSM1150288", "GSM1150289", "GSM1150290", "GSM1150291", "GSM1150292", "GSM1150293", "GSM1150294", "GSM1150295", "GSM1150296", "GSM1150297", "GSM1150298", "GSM1150299", "GSM1150300", "GSM1150301", "GSM1150302", "GSM1150303", "GSM1150304", "GSM1150305", "GSM1150306", "GSM1150307", "GSM1150308", "GSM1150309", "GSM1150310", "GSM1150311", "GSM1150312", "GSM1150313", "GSM1150314", "GSM1150315", "GSM1150316", "GSM1150317", "GSM1150318", "GSM1150319", "GSM1150321", "GSM1150331", "GSM1150332", "GSM1150334", "GSM1150336", "GSM1150338", "GSM1150339", "GSM1150341", "GSM1150343", "GSM1150344", "GSM1150346", "GSM1150347", "GSM1150349", "GSM1150351", "GSM1150352", "GSM1150353", "GSM1150354", "GSM1150355", "GSM1150356", "GSM1150357", "GSM1150358", "GSM1150359", "GSM1150360", "GSM1150361", "GSM1150362", "GSM1150363", "GSM1150364", "GSM1150365", "GSM1150366", "GSM1150367", "GSM1150368", "GSM1150369", "GSM1150370", "GSM1150371", "GSM1150372", "GSM1150373", "GSM1150374", "GSM1150375", "GSM1150376", "GSM1150377", "GSM1150378", "GSM1150379", "GSM1150380", "GSM1150381", "GSM1150382", "GSM1150383", "GSM1150384", "GSM1150385", "GSM1150386", "GSM1150387", "GSM1150388", "GSM1150389", "GSM1150390", "GSM1150391", "GSM1150392", "GSM1150393", "GSM1150394", "GSM1150395", "GSM1150396", "GSM1150397", "GSM1150398", "GSM1150399", "GSM1150400", "GSM1150401", "GSM1150402", "GSM1150403", "GSM1150404", "GSM1150405", "GSM1150406", "GSM1150407", "GSM1150408", "GSM1150409", "GSM1150410", "GSM1150411", "GSM1150412", "GSM1150413", "GSM1150414", "GSM1150415", "GSM1150416", "GSM1150417", "GSM1150418", "GSM1150419", "GSM1150420", "GSM1150421", "GSM1150422", "GSM1150423", "GSM1150424", "GSM1150425", "GSM1150426", "GSM1150427", "GSM1150428", "GSM1150429", "GSM1150430", "GSM1150431", "GSM1150432", "GSM1150433", "GSM1150434", "GSM1150435", "GSM1150436", "GSM1150437", "GSM1150438", "GSM1150439", "GSM1150440", "GSM1150441", "GSM1150442", "GSM1150443", "GSM1150444", "GSM1150445", "GSM1150446", "GSM1150447", "GSM1150448", "GSM1150449", "GSM1150450", "GSM1150451", "GSM1150452", "GSM1150453", "GSM1150454", "GSM1150455", "GSM1150456", "GSM1150457", "GSM1150458", "GSM1150459", "GSM1150460", "GSM1150461", "GSM1150462", "GSM1150463", "GSM1150464", "GSM1150465", "GSM1150466", "GSM1150467", "GSM1150468", "GSM1150469", "GSM1150470", "GSM1150471", "GSM1150472", "GSM1150473", "GSM1150474", "GSM1150475", "GSM1150476", "GSM1150477", "GSM1150478", "GSM1150479", "GSM1150480", "GSM1150481", "GSM1150482", "GSM1150483", "GSM1150484", "GSM1150485", "GSM1150486", "GSM1150487", "GSM1150488", "GSM1150489", "GSM1150490", "GSM1150491", "GSM1150492", "GSM1150493", "GSM1150494", "GSM1150495", "GSM1150496", "GSM1150497", "GSM1150498", "GSM1150499", "GSM1150500", "GSM1150501", "GSM1150502", "GSM1150503", "GSM1150504", "GSM1150505", "GSM1150506", "GSM1150507", "GSM1150508", "GSM1150509", "GSM1150510", "GSM1150511", "GSM1150512", "GSM1150513", "GSM1150514", "GSM1150515", "GSM1150516", "GSM1150517", "GSM1150518", "GSM1150519", "GSM1150520", "GSM1150521", "GSM1150522", "GSM1150523", "GSM1150524", "GSM1150525", "GSM1150526", "GSM1150527", "GSM1150528", "GSM1150529", "GSM1150530", "GSM1150531", "GSM1150532", "GSM1150533", "GSM1150534", "GSM1150535", "GSM1150536", "GSM1150537", "GSM1150538", "GSM1150539", "GSM1150540", "GSM1150541", "GSM1150542", "GSM1150543", "GSM1150544", "GSM1150545", "GSM1150546", "GSM1150547"], "sample_count": 582, "group_sizes": null, "group_sizes_basis": null, "platform": "6480;14550", "taxon": "Homo sapiens", "title": "Gene expression profiling of chronic lung disease for the Lung Genomics Research Consortium", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE70866", "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=GSE70866", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE70866", "version": null, "note": "The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1820719", "GSM1820720", "GSM1820721", "GSM1820722", "GSM1820723", "GSM1820724", "GSM1820725", "GSM1820726", "GSM1820727", "GSM1820728", "GSM1820729", "GSM1820730", "GSM1820731", "GSM1820732", "GSM1820733", "GSM1820734", "GSM1820735", "GSM1820736", "GSM1820737", "GSM1820738", "GSM1820739", "GSM1820740", "GSM1820741", "GSM1820742", "GSM1820743", "GSM1820744", "GSM1820745", "GSM1820746", "GSM1820747", "GSM1820748", "GSM1820749", "GSM1820750", "GSM1820751", "GSM1820752", "GSM1820753", "GSM1820754", "GSM1820755", "GSM1820756", "GSM1820757", "GSM1820758", "GSM1820759", "GSM1820760", "GSM1820761", "GSM1820762", "GSM1820763", "GSM1820764", "GSM1820765", "GSM1820766", "GSM1820767", "GSM1820768", "GSM1820769", "GSM1820770", "GSM1820771", "GSM1820772", "GSM1820773", "GSM1820774", "GSM1820775", "GSM1820776", "GSM1820777", "GSM1820778", "GSM1820779", "GSM1820780", "GSM1820781", "GSM1820782", "GSM1820783", "GSM1820784", "GSM1820785", "GSM1820786", "GSM1820787", "GSM1820788", "GSM1820789", "GSM1820790", "GSM1820791", "GSM1820792", "GSM1820793", "GSM1820794", "GSM1820795", "GSM1820796", "GSM1820797", "GSM1820798", "GSM1820799", "GSM1820800", "GSM1820801", "GSM1820802", "GSM1820803", "GSM1820804", "GSM1820805", "GSM1820806", "GSM1820807", "GSM1820808", "GSM1820809", "GSM1820810", "GSM1820811", "GSM1820812", "GSM1820813", "GSM1820814", "GSM1820815", "GSM1820816", "GSM1820817", "GSM1820818", "GSM1820819", "GSM1820820", "GSM1820821", "GSM1820822", "GSM1820823", "GSM1820824", "GSM1820825", "GSM1820826", "GSM1820827", "GSM1820828", "GSM1820829", "GSM1820830", "GSM1820831", "GSM1820832", "GSM1820833", "GSM1820834", "GSM1820835", "GSM1820836", "GSM1820837", "GSM1820838", "GSM1820839", "GSM1820840", "GSM1820841", "GSM1820842", "GSM1820843", "GSM1820844", "GSM1820845", "GSM1820846", "GSM1820847", "GSM1820848", "GSM1820849", "GSM1820850", "GSM1820851", "GSM1820852", "GSM1820853", "GSM1820854", "GSM1820855", "GSM1820856", "GSM1820857", "GSM1820858", "GSM1820859", "GSM1820860", "GSM1820861", "GSM1820862", "GSM1820863", "GSM1820864", "GSM1820865", "GSM1820866", "GSM1820867", "GSM1820868", "GSM1820869", "GSM1820870", "GSM1820871", "GSM1820872", "GSM1820873", "GSM1820874", "GSM1820875", "GSM1820876", "GSM1820877", "GSM1820878", "GSM1820879", "GSM1820880", "GSM1820881", "GSM1820882", "GSM1820883", "GSM1820884", "GSM1820885", "GSM1820886", "GSM1820887", "GSM1820888", "GSM1820889", "GSM1820890", "GSM1820891", "GSM1820892", "GSM1820893", "GSM1820894", "GSM1820895", "GSM1820896", "GSM1820897", "GSM1820898", "GSM1820899", "GSM1820900", "GSM1820901", "GSM1820902", "GSM1820903", "GSM1820904", "GSM1820905", "GSM1820906", "GSM1820907", "GSM1820908", "GSM1820909", "GSM1820910", "GSM1820911", "GSM1820912", "GSM1820913", "GSM1820914"], "sample_count": 196, "group_sizes": null, "group_sizes_basis": null, "platform": "17077;14550", "taxon": "Homo sapiens", "title": "BAL cell gene expression is predictive of Mortality in Idiopathic Pulmonary Fibrosis and enriched for Genes of Airway Basal Cells (II)", "resolution_checked_at": "2026-11-01T17:30:42Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE150910 not downloaded", "asset:data:geo:GSE150910 licence not read", "asset:data:geo:GSE47460 not downloaded", "asset:data:geo:GSE47460 licence not read", "asset:data:geo:GSE70866 not downloaded", "asset:data:geo:GSE70866 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "Based on LASSO Cox regression analysis, an eight PRG prediction model was derived (Fig. 4D and E)."}}, {"id": "method-2", "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": 0.7, "band": "medium", "quote": "logistic regression"}}], "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": ["cox_ph"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: cox_proportional_hazards."}, "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": ["GSE70866", "GSE47460", "GSE150910"], "resolved_accessions": ["GSE70866", "GSE47460", "GSE150910"], "statements": ["The datasets presented in this study are available in online repositories. Please refer to the article/supplementary material for the name of the repository(ies) and accession number(s)."], "basis": "The paper names GSE70866, GSE47460, GSE150910 in GEO and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["cox_ph"], "assets": ["source:pmid:38192798", "data:geo:GSE150910"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE150910"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:04:22Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15941, "completion_tokens": 1168, "cached_tokens": 256}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:38192798", "type": "paper", "label": "pmid:38192798"}, {"id": "source:pmid:38192798", "type": "manuscript", "label": "PMID 38192798 full text"}, {"id": "data:geo:GSE150910", "type": "dataset", "label": "GEO GSE150910"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38192798", "type": "paper", "label": "pmid:38192798"}, {"id": "source:pmid:38192798", "type": "manuscript", "label": "PMID 38192798 full text"}, {"id": "data:geo:GSE150910", "type": "dataset", "label": "GEO GSE150910"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38192798", "type": "extraction", "used": ["source:pmid:38192798"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE150910", "type": "accession_resolution", "used": ["data:geo:GSE150910"], "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:38192798", "parent_hash": "sha256:a8fc8341df4c34295670b2237a0dda38c4cc0ac3c992144e32a8116f9bdf3522", "fork_of": null, "generation": 1}, "gaps": ["asset:data:geo:GSE150910 licence not read", "asset:data:geo:GSE150910 not downloaded", "asset:data:geo:GSE47460 licence not read", "asset:data:geo:GSE47460 not downloaded", "asset:data:geo:GSE70866 licence not read", "asset:data:geo:GSE70866 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "analysis", "definition_id": "survival_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["cox_ph"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["Based on LASSO Cox regression analysis, an eight PRG prediction model was derived (Fig. 4D and E)."], "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":"2026-11-04T00:45:03+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}}}