{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34804123", "kind": "science-record", "revision": 5, "content_hash": "sha256:c475ee650fb0320c19ee71436b4625964ba4ba7235013ee889a5a2cadb4c44aa", "created_at": "2026-11-01T17:36:30Z", "updated_at": "2026-11-01T22:47:55Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Potential Key Genes in the Pathogenesis of Chronic Obstructive Pulmonary Disease Through Bioinformatics Analysis.", "doi": "10.3389/fgene.2021.754569", "pmid": "34804123", "authors": ["Qingzhou Guan", "Yange Tian", "Zhenzhen Zhang", "Lanxi Zhang", "Peng Zhao", "Jiansheng Li"], "journal": "Frontiers in genetics", "year": 2021, "abstract": "Chronic obstructive pulmonary disease (COPD) is a common respiratory disease with high morbidity and mortality. The etiology of COPD is complex, and the pathogenesis mechanisms remain unclear. In this study, we used rat and human COPD gene expression data from our laboratory and the Gene Expression Omnibus (GEO) database to identify differentially expressed genes (DEGs) between individuals with COPD and healthy individuals. Then, protein-protein interaction (PPI) networks were constructed, and hub genes were identified. Cytoscape was used to construct the co-expressed network and competitive endogenous RNA (ceRNA) networks. A total of 198 DEGs were identified, and a PPI network with 144 nodes and 355 edges was constructed. Twelve hub genes were identified by the cytoHubba plugin in Cytoscape. Of these genes, CCR3, CCL2, COL4A2, VWF, IL1RN, IL2RA, and CCL13 were related to inflammation or immunity, or tissue-specific expression in lung tissue, and their messenger RNA (mRNA) levels were validated by qRT-PCR. COL4A2, VWF, and IL1RN were further verified by the GEO dataset GSE76925, and the ceRNA network was constructed with Cytoscape. These three genes were consistent with COPD rat model data compared with control data, and their dysregulation direction was reversed when the COPD rat model was treated with effective-component compatibility of Bufei Yishen formula III. This bioinformatics analysis strategy may be useful for elucidating novel mechanisms underlying COPD. We pinpointed three key genes that may play a role in COPD pathogenesis and therapy, which deserved to be further studied.", "claims": [{"id": "claim-method", "statement": "For the COPD rat data compared with normal controls, edgeR was applied to identify DEGs. For array- and seq-based data from public databases, significance analysis of microarray (SAM) and Wilcoxon rank-sum tests were used to identify DEGs, respectively.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34804123", "locator": "sections[3] \"Data Acquisition and Identification of Differentially Expressed Genes\" paragraph 5", "quote": "For the COPD rat data compared with normal controls, edgeR was applied to identify DEGs. For array- and seq-based data from public databases, significance analysis of microarray (SAM) and Wilcoxon rank-sum tests were used to identify DEGs, respectively."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34804123", "locator": "sections[15] \"Data Availability Statement\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A total of 198 DEGs were identified, and a PPI network with 144 nodes and 355 edges was constructed.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:34804123", "locator": "sections[0] \"Abstract\" paragraph 1", "quote": "A total of 198 DEGs were identified, and a PPI network with 144 nodes and 355 edges was constructed."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": "A total of 198 DEGs were identified, and a PPI network with 144 nodes and 355 edges was constructed.", "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:34804123"], "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:GSE13896"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:group_comparison_wilcoxon", "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:GSE13896"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:group_comparison_wilcoxon"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34804123", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2021.754569", "sha256": "sha256:703cb9ec13192c5ac3efd734b8a4d8129a10f7879e8f67bbf75e05b98d779f95", "bytes": 48063, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2021.754569", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8595135", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE13896", "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=GSE13896", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE13896", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM219241", "GSM219242", "GSM219243", "GSM219244", "GSM219245", "GSM219246", "GSM219247", "GSM219248", "GSM219249", "GSM219250", "GSM219251", "GSM219252", "GSM219253", "GSM219254", "GSM219256", "GSM219257", "GSM219258", "GSM219259", "GSM219260", "GSM219261", "GSM219262", "GSM219263", "GSM219264", "GSM349912", "GSM349913", "GSM349914", "GSM349915", "GSM349916", "GSM349917", "GSM349918", "GSM349919", "GSM349920", "GSM349921", "GSM349922", "GSM349923", "GSM349924", "GSM349925", "GSM349926", "GSM349927", "GSM349928", "GSM349929", "GSM349930", "GSM349931", "GSM349932", "GSM349933", "GSM349934", "GSM349935", "GSM349936", "GSM349937", "GSM349938", "GSM349939", "GSM349940", "GSM349941", "GSM349942", "GSM349943", "GSM349944", "GSM349945", "GSM349946", "GSM349947", "GSM349948", "GSM349949", "GSM349950", "GSM349951", "GSM349952", "GSM349953", "GSM349954", "GSM349955", "GSM349956", "GSM349957", "GSM349958"], "sample_count": 70, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Smoking-dependent Reprogramming of Alveolar Macrophage Polarization: Implication for Pathogenesis of COPD", "resolution_checked_at": "2026-11-01T15:39:54Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE38974", "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=GSE38974", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38974", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM953088", "GSM953089", "GSM953090", "GSM953091", "GSM953092", "GSM953093", "GSM953094", "GSM953095", "GSM953096", "GSM953097", "GSM953098", "GSM953099", "GSM953100", "GSM953101", "GSM953102", "GSM953103", "GSM953104", "GSM953105", "GSM953106", "GSM953107", "GSM953108", "GSM953109", "GSM953110", "GSM953111", "GSM953112", "GSM953113", "GSM953114", "GSM953115", "GSM953116", "GSM953117", "GSM953118", "GSM953119", "GSM953120", "GSM953121", "GSM953122", "GSM953123", "GSM953124", "GSM953125", "GSM953126", "GSM953127", "GSM953128", "GSM953129", "GSM953130", "GSM953131", "GSM953132", "GSM953133", "GSM953134", "GSM953135", "GSM953136", "GSM953137", "GSM953138", "GSM953139", "GSM953140", "GSM953141", "GSM953142", "GSM953143", "GSM953144", "GSM953145", "GSM953146"], "sample_count": 59, "group_sizes": null, "group_sizes_basis": null, "platform": "4133;7723", "taxon": "Mus musculus; Human gammaherpesvirus 8; Human alphaherpesvirus 1; human gammaherpesvirus 4; Betapolyomavirus macacae; Homo sapiens; Human betaherpesvirus 5; Murid betaherpesvirus 1; Human immunodeficiency virus 1; Rattus norvegicus; JC polyomavirus; Murid gammaherpesvirus 4; Betapolyomavirus hominis", "title": "Gene expression networks in COPD: microRNA and mRNA regulation", "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:GSE42057", "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=GSE42057", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42057", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1031549", "GSM1031550", "GSM1031551", "GSM1031552", "GSM1031553", "GSM1031554", "GSM1031555", "GSM1031556", "GSM1031557", "GSM1031558", "GSM1031559", "GSM1031560", "GSM1031561", "GSM1031562", "GSM1031563", "GSM1031564", "GSM1031565", "GSM1031566", "GSM1031567", "GSM1031568", "GSM1031569", "GSM1031570", "GSM1031571", "GSM1031572", "GSM1031573", "GSM1031574", "GSM1031575", "GSM1031576", "GSM1031577", "GSM1031578", "GSM1031579", "GSM1031580", "GSM1031581", "GSM1031582", "GSM1031583", "GSM1031584", "GSM1031585", "GSM1031586", "GSM1031587", "GSM1031588", "GSM1031589", "GSM1031590", "GSM1031591", "GSM1031592", "GSM1031593", "GSM1031594", "GSM1031595", "GSM1031596", "GSM1031597", "GSM1031598", "GSM1031599", "GSM1031600", "GSM1031601", "GSM1031602", "GSM1031603", "GSM1031604", "GSM1031605", "GSM1031606", "GSM1031607", "GSM1031608", "GSM1031609", "GSM1031610", "GSM1031611", "GSM1031612", "GSM1031613", "GSM1031614", "GSM1031615", "GSM1031616", "GSM1031617", "GSM1031618", "GSM1031619", "GSM1031620", "GSM1031621", "GSM1031622", "GSM1031623", "GSM1031624", "GSM1031625", "GSM1031626", "GSM1031627", "GSM1031628", "GSM1031629", "GSM1031630", "GSM1031631", "GSM1031632", "GSM1031633", "GSM1031634", "GSM1031635", "GSM1031636", "GSM1031637", "GSM1031638", "GSM1031639", "GSM1031640", "GSM1031641", "GSM1031642", "GSM1031643", "GSM1031644", "GSM1031645", "GSM1031646", "GSM1031647", "GSM1031648", "GSM1031649", "GSM1031650", "GSM1031651", "GSM1031652", "GSM1031653", "GSM1031654", "GSM1031655", "GSM1031656", "GSM1031657", "GSM1031658", "GSM1031659", "GSM1031660", "GSM1031661", "GSM1031662", "GSM1031663", "GSM1031664", "GSM1031665", "GSM1031666", "GSM1031667", "GSM1031668", "GSM1031669", "GSM1031670", "GSM1031671", "GSM1031672", "GSM1031673", "GSM1031674", "GSM1031675", "GSM1031676", "GSM1031677", "GSM1031678", "GSM1031679", "GSM1031680", "GSM1031681", "GSM1031682", "GSM1031683", "GSM1031684"], "sample_count": 136, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Peripheral blood mononuclear cell gene expression in chronic obstructive pulmonary disease", "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:GSE57148", "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=GSE57148", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE57148", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1375986", "GSM1375987", "GSM1375988", "GSM1375989", "GSM1375990", "GSM1375991", "GSM1375992", "GSM1375993", "GSM1375994", "GSM1375995", "GSM1375996", "GSM1375997", "GSM1375998", "GSM1375999", "GSM1376000", "GSM1376001", "GSM1376002", "GSM1376003", "GSM1376004", "GSM1376005", "GSM1376006", "GSM1376007", "GSM1376008", "GSM1376009", "GSM1376010", "GSM1376011", "GSM1376012", "GSM1376013", "GSM1376014", "GSM1376015", "GSM1376016", "GSM1376017", "GSM1376018", "GSM1376019", "GSM1376020", "GSM1376021", "GSM1376022", "GSM1376023", "GSM1376024", "GSM1376025", "GSM1376026", "GSM1376027", "GSM1376028", "GSM1376029", "GSM1376030", "GSM1376031", "GSM1376032", "GSM1376033", "GSM1376034", "GSM1376035", "GSM1376036", "GSM1376037", "GSM1376038", "GSM1376039", "GSM1376040", "GSM1376041", "GSM1376042", "GSM1376043", "GSM1376044", "GSM1376045", "GSM1376046", "GSM1376047", "GSM1376048", "GSM1376049", "GSM1376050", "GSM1376051", "GSM1376052", "GSM1376053", "GSM1376054", "GSM1376055", "GSM1376056", "GSM1376057", "GSM1376058", "GSM1376059", "GSM1376060", "GSM1376061", "GSM1376062", "GSM1376063", "GSM1376064", "GSM1376065", "GSM1376066", "GSM1376067", "GSM1376068", "GSM1376069", "GSM1376070", "GSM1376071", "GSM1376072", "GSM1376073", "GSM1376074", "GSM1376075", "GSM1376076", "GSM1376077", "GSM1376078", "GSM1376079", "GSM1376080", "GSM1376081", "GSM1376082", "GSM1376083", "GSM1376084", "GSM1376085", "GSM1376086", "GSM1376087", "GSM1376088", "GSM1376089", "GSM1376090", "GSM1376091", "GSM1376092", "GSM1376093", "GSM1376094", "GSM1376095", "GSM1376096", "GSM1376097", "GSM1376098", "GSM1376099", "GSM1376100", "GSM1376101", "GSM1376102", "GSM1376103", "GSM1376104", "GSM1376105", "GSM1376106", "GSM1376107", "GSM1376108", "GSM1376109", "GSM1376110", "GSM1376111", "GSM1376112", "GSM1376113", "GSM1376114", "GSM1376115", "GSM1376116", "GSM1376117", "GSM1376118", "GSM1376119", "GSM1376120", "GSM1376121", "GSM1376122", "GSM1376123", "GSM1376124", "GSM1376125", "GSM1376126", "GSM1376127", "GSM1376128", "GSM1376129", "GSM1376130", "GSM1376131", "GSM1376132", "GSM1376133", "GSM1376134", "GSM1376135", "GSM1376136", "GSM1376137", "GSM1376138", "GSM1376139", "GSM1376140", "GSM1376141", "GSM1376142", "GSM1376143", "GSM1376144", "GSM1376145", "GSM1376146", "GSM1376147", "GSM1376148", "GSM1376149", "GSM1376150", "GSM1376151", "GSM1376152", "GSM1376153", "GSM1376154", "GSM1376155", "GSM1376156", "GSM1376157", "GSM1376158", "GSM1376159", "GSM1376160", "GSM1376161", "GSM1376162", "GSM1376163", "GSM1376164", "GSM1376165", "GSM1376166", "GSM1376167", "GSM1376168", "GSM1376169", "GSM1376170", "GSM1376171", "GSM1376172", "GSM1376173", "GSM1376174"], "sample_count": 189, "group_sizes": null, "group_sizes_basis": null, "platform": "11154", "taxon": "Homo sapiens", "title": "Characterizing gene expression in lung tissue of COPD subjects using RNA-seq", "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:GSE76925", "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=GSE76925", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE76925", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2040792", "GSM2040793", "GSM2040794", "GSM2040795", "GSM2040796", "GSM2040797", "GSM2040798", "GSM2040799", "GSM2040800", "GSM2040801", "GSM2040802", "GSM2040803", "GSM2040804", "GSM2040805", "GSM2040806", "GSM2040807", "GSM2040808", "GSM2040809", "GSM2040810", "GSM2040811", "GSM2040812", "GSM2040813", "GSM2040814", "GSM2040815", "GSM2040816", "GSM2040817", "GSM2040818", "GSM2040819", "GSM2040820", "GSM2040821", "GSM2040822", "GSM2040823", "GSM2040824", "GSM2040825", "GSM2040826", "GSM2040827", "GSM2040828", "GSM2040829", "GSM2040830", "GSM2040831", "GSM2040832", "GSM2040833", "GSM2040834", "GSM2040835", "GSM2040836", "GSM2040837", "GSM2040838", "GSM2040839", "GSM2040840", "GSM2040841", "GSM2040842", "GSM2040843", "GSM2040844", "GSM2040845", "GSM2040846", "GSM2040847", "GSM2040848", "GSM2040849", "GSM2040850", "GSM2040851", "GSM2040852", "GSM2040853", "GSM2040854", "GSM2040855", "GSM2040856", "GSM2040857", "GSM2040858", "GSM2040859", "GSM2040860", "GSM2040861", "GSM2040862", "GSM2040863", "GSM2040864", "GSM2040865", "GSM2040866", "GSM2040867", "GSM2040868", "GSM2040869", "GSM2040870", "GSM2040871", "GSM2040872", "GSM2040873", "GSM2040874", "GSM2040875", "GSM2040876", "GSM2040877", "GSM2040878", "GSM2040879", "GSM2040880", "GSM2040881", "GSM2040882", "GSM2040883", "GSM2040884", "GSM2040885", "GSM2040886", "GSM2040887", "GSM2040888", "GSM2040889", "GSM2040890", "GSM2040891", "GSM2040892", "GSM2040893", "GSM2040894", "GSM2040895", "GSM2040896", "GSM2040897", "GSM2040898", "GSM2040899", "GSM2040900", "GSM2040901", "GSM2040902", "GSM2040903", "GSM2040904", "GSM2040905", "GSM2040906", "GSM2040907", "GSM2040908", "GSM2040909", "GSM2040910", "GSM2040911", "GSM2040912", "GSM2040913", "GSM2040914", "GSM2040915", "GSM2040916", "GSM2040917", "GSM2040918", "GSM2040919", "GSM2040920", "GSM2040921", "GSM2040922", "GSM2040923", "GSM2040924", "GSM2040925", "GSM2040926", "GSM2040927", "GSM2040928", "GSM2040929", "GSM2040930", "GSM2040931", "GSM2040932", "GSM2040933", "GSM2040934", "GSM2040935", "GSM2040936", "GSM2040937", "GSM2040938", "GSM2040939", "GSM2040940", "GSM2040941", "GSM2040942"], "sample_count": 151, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Functional interactors of genomewide association study genes are differentially expressed in severe chronic obstructive pulmonary disease lung tissue", "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:GSE8581", "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=GSE8581", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE8581", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM210004", "GSM210005", "GSM210006", "GSM210007", "GSM210008", "GSM210009", "GSM210010", "GSM210011", "GSM210012", "GSM210014", "GSM210015", "GSM210071", "GSM210087", "GSM210090", "GSM210188", "GSM210192", "GSM210193", "GSM210194", "GSM210196", "GSM210978", "GSM210979", "GSM210992", "GSM210993", "GSM210994", "GSM211007", "GSM211008", "GSM211009", "GSM211010", "GSM211865", "GSM211872", "GSM212067", "GSM212068", "GSM212069", "GSM212070", "GSM212074", "GSM212075", "GSM212787", "GSM212788", "GSM212789", "GSM212790", "GSM212809", "GSM212810", "GSM212811", "GSM212848", "GSM212849", "GSM212850", "GSM212852", "GSM212853", "GSM212854", "GSM212855", "GSM213017", "GSM213018", "GSM213019", "GSM213020", "GSM213034", "GSM213035", "GSM213036", "GSM213037"], "sample_count": 58, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Human Chronic Obstructive Pulmonary Disorder (COPD) Biomarker", "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:GSE13896 not downloaded", "asset:data:geo:GSE13896 licence not read", "asset:data:geo:GSE38974 not downloaded", "asset:data:geo:GSE38974 licence not read", "asset:data:geo:GSE42057 not downloaded", "asset:data:geo:GSE42057 licence not read", "asset:data:geo:GSE57148 not downloaded", "asset:data:geo:GSE57148 licence not read", "asset:data:geo:GSE76925 not downloaded", "asset:data:geo:GSE76925 licence not read", "asset:data:geo:GSE8581 not downloaded", "asset:data:geo:GSE8581 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "wilcoxon", "label": "Group comparison", "dsl_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "expressible": false, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "For the COPD rat data compared with normal controls, edgeR was applied to identify DEGs. For array- and seq-based data from public databases, significance analysis of microarray (SAM) and Wilcoxon rank-sum tests were used to identify DEGs, respectively."}}, {"id": "method-2", "family": "differential_expression", "specific": "edger", "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": 0.8, "band": "high", "quote": "edgeR"}}, {"id": "method-3", "family": "network_analysis", "specific": "ppi_network", "label": "Network / pathway analysis", "dsl_operations": ["build_graph", "centrality_scores", "pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "protein-protein interaction"}}], "targets": [], "gaps": ["method.group_comparison_wilcoxon"]}, "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": false, "required_operations": [], "missing_operations": ["group_comparison_wilcoxon"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: wilcoxon."}, "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": ["GSE38974", "GSE8581", "GSE57148", "GSE76925", "GSE13896", "GSE42057"], "resolved_accessions": ["GSE38974", "GSE8581", "GSE57148", "GSE76925", "GSE13896", "GSE42057"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article/Supplementary Material."], "basis": "The paper names GSE38974, GSE8581, GSE57148, GSE76925, GSE13896, GSE42057 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": [], "assets": ["source:pmid:34804123", "data:geo:GSE13896"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "group_comparison_wilcoxon", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE13896"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:08:36Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14605, "completion_tokens": 2237, "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:34804123", "type": "paper", "label": "pmid:34804123"}, {"id": "source:pmid:34804123", "type": "manuscript", "label": "PMID 34804123 full text"}, {"id": "data:geo:GSE13896", "type": "dataset", "label": "GEO GSE13896"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34804123", "type": "paper", "label": "pmid:34804123"}, {"id": "source:pmid:34804123", "type": "manuscript", "label": "PMID 34804123 full text"}, {"id": "data:geo:GSE13896", "type": "dataset", "label": "GEO GSE13896"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34804123", "type": "extraction", "used": ["source:pmid:34804123"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE13896", "type": "accession_resolution", "used": ["data:geo:GSE13896"], "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:34804123", "parent_hash": "sha256:4bb20d87273526ec79f45094a89b90c09e2dc3b0811d52114596929a990006d8", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE13896 licence not read", "asset:data:geo:GSE13896 not downloaded", "asset:data:geo:GSE38974 licence not read", "asset:data:geo:GSE38974 not downloaded", "asset:data:geo:GSE42057 licence not read", "asset:data:geo:GSE42057 not downloaded", "asset:data:geo:GSE57148 licence not read", "asset:data:geo:GSE57148 not downloaded", "asset:data:geo:GSE76925 licence not read", "asset:data:geo:GSE76925 not downloaded", "asset:data:geo:GSE8581 licence not read", "asset:data:geo:GSE8581 not downloaded", "execution.not_run", "method.group_comparison_wilcoxon", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:group_comparison_wilcoxon"], "assays": [{"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": ["nisms remain unclear. In this study, we used rat and human COPD gene expression data from our", "These three genes were consistent with COPD rat model data compared with control data, and t", "ulation direction was reversed when the COPD rat model was treated with effective-component c"], "order_basis": "paper_text_order:303", "id": "assay:1"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["For the COPD rat data compared with normal controls, edgeR was applied to identify DEGs. For array- and seq-based data from public databases, significance analysis of microarray (SAM) and Wilcoxon rank-sum tests were used to identify DEGs, respectively."], "order_basis": "consumes_earlier_output", "id": "assay:2"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T02:24:45+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}}}