{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:34880861", "kind": "science-record", "revision": 5, "content_hash": "sha256:aaf6a0608e47736b665b0568986f0f58a06c6947cafc085aa5de698b88fc57be", "created_at": "2026-11-01T17:36:35Z", "updated_at": "2026-11-01T22:48:01Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "CD247, a Potential T Cell-Derived Disease Severity and Prognostic Biomarker in Patients With Idiopathic Pulmonary Fibrosis.", "doi": "10.3389/fimmu.2021.762594", "pmid": "34880861", "authors": ["Yupeng Li", "Shibin Chen", "Xincheng Li", "Xue Wang", "Huiwen Li", "Shangwei Ning", "Hong Chen"], "journal": "Frontiers in immunology", "year": 2021, "abstract": "Background: Idiopathic pulmonary fibrosis (IPF) has high mortality worldwide. The CD247 molecule (CD247, as known as T-cell surface glycoprotein CD3 zeta chain) has been reported as a susceptibility locus in systemic sclerosis, but its correlation with IPF remains unclear.\nMethods: Datasets were acquired by researching the Gene Expression Omnibus (GEO). CD247 was identified as the hub gene associated with percent predicted diffusion capacity of the lung for carbon monoxide (Dlco% predicted) and prognosis according to Pearson correlation, logistic regression, and survival analysis.\nResults: CD247 is significantly downregulated in patients with IPF compared with controls in both blood and lung tissue samples. Moreover, CD247 is significantly positively associated with Dlco% predicted in blood and lung tissue samples. Patients with low-expression CD247 had shorter transplant-free survival (TFS) time and more composite end-point events (CEP, death, or decline in FVC >10% over a 6-month period) compared with patients with high-expression CD247 (blood). Moreover, in the follow-up 1st, 3rd, 6th, and 12th months, low expression of CD247 was still the risk factor of CEP in the GSE93606 dataset (blood). Thirteen genes were found to interact with CD247 according to the protein-protein interaction network, and the 14 genes including CD247 were associated with the functions of T cells and natural killer (NK) cells such as PD-L1 expression and PD-1 checkpoint pathway and NK cell-mediated cytotoxicity. Furthermore, we also found that a low expression of CD247 might be associated with a lower activity of TIL (tumor-infiltrating lymphocytes), checkpoint, and cytolytic activity and a higher activity of macrophages and neutrophils.\nConclusion: These results imply that CD247 may be a potential T cell-derived disease severity and prognostic biomarker for IPF.", "claims": [{"id": "claim-method", "statement": "CD247 was identified as the hub gene associated with percent predicted diffusion capacity of the lung for carbon monoxide (Dlco% predicted) and prognosis according to Pearson correlation, logistic regression, and survival analysis.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34880861", "locator": "sections[0] \"Abstract\" paragraph 2", "quote": "CD247 was identified as the hub gene associated with percent predicted diffusion capacity of the lung for carbon monoxide (Dlco% predicted) and prognosis according to Pearson correlation, logistic regression, and survival analysis."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:34880861", "locator": "sections[16] \"Data Availability Statement\" paragraph 2", "quote": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 ."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "", "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:34880861"], "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:GSE110147"], "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:GSE110147"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:34880861", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fimmu.2021.762594", "sha256": "sha256:61e9cce774049b29ef90cf05bd9db080c4fb43dc711b295843654cc8ff108e50", "bytes": 51492, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fimmu.2021.762594", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC8645971", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE110147", "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=GSE110147", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE110147", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2978752", "GSM2978753", "GSM2978754", "GSM2978755", "GSM2978756", "GSM2978757", "GSM2978758", "GSM2978759", "GSM2978760", "GSM2978761", "GSM2978762", "GSM2978763", "GSM2978764", "GSM2978765", "GSM2978766", "GSM2978767", "GSM2978768", "GSM2978769", "GSM2978770", "GSM2978771", "GSM2978772", "GSM2978773", "GSM2978774", "GSM2978775", "GSM2978776", "GSM2978777", "GSM2978778", "GSM2978779", "GSM2978780", "GSM2978781", "GSM2978782", "GSM2978783", "GSM2978784", "GSM2978785", "GSM2978786", "GSM2978787", "GSM2978788", "GSM2978789", "GSM2978790", "GSM2978791", "GSM2978792", "GSM2978793", "GSM2978794", "GSM2978795", "GSM2978796", "GSM2978797", "GSM2978798", "GSM2978799"], "sample_count": 48, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Gene expression profiling of idiopathic pulmonary fibrosis and non-specific interstitial pneumonia", "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:GSE132607", "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=GSE132607", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE132607", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM3879744", "GSM3879745", "GSM3879746", "GSM3879747", "GSM3879748", "GSM3879749", "GSM3879750", "GSM3879751", "GSM3879752", "GSM3879753", "GSM3879754", "GSM3879755", "GSM3879756", "GSM3879757", "GSM3879758", "GSM3879759", "GSM3879760", "GSM3879761", "GSM3879762", "GSM3879763", "GSM3879764", "GSM3879765", "GSM3879766", "GSM3879767", "GSM3879768", "GSM3879769", "GSM3879770", "GSM3879771", "GSM3879772", "GSM3879773", "GSM3879774", "GSM3879775", "GSM3879776", "GSM3879777", "GSM3879778", "GSM3879779", "GSM3879780", "GSM3879781", "GSM3879782", "GSM3879783", "GSM3879784", "GSM3879785", "GSM3879786", "GSM3879787", "GSM3879788", "GSM3879789", "GSM3879790", "GSM3879791", "GSM3879792", "GSM3879793", "GSM3879794", "GSM3879795", "GSM3879796", "GSM3879797", "GSM3879798", "GSM3879799", "GSM3879800", "GSM3879801", "GSM3879802", "GSM3879803", "GSM3879804", "GSM3879805", "GSM3879806", "GSM3879807", "GSM3879808", "GSM3879809", "GSM3879810", "GSM3879811", "GSM3879812", "GSM3879813", "GSM3879814", "GSM3879815", "GSM3879816", "GSM3879817", "GSM3879818", "GSM3879819", "GSM3879820", "GSM3879821", "GSM3879822", "GSM3879823", "GSM3879824", "GSM3879825", "GSM3879826", "GSM3879827", "GSM3879828", "GSM3879829", "GSM3879830", "GSM3879831", "GSM3879832", "GSM3879833", "GSM3879834", "GSM3879835", "GSM3879836", "GSM3879837", "GSM3879838", "GSM3879839", "GSM3879840", "GSM3879841", "GSM3879842", "GSM3879843", "GSM3879844", "GSM3879845", "GSM3879846", "GSM3879847", "GSM3879848", "GSM3879849", "GSM3879850", "GSM3879851", "GSM3879852", "GSM3879853", "GSM3879854", "GSM3879855", "GSM3879856", "GSM3879857", "GSM3879858", "GSM3879859", "GSM3879860", "GSM3879861", "GSM3879862", "GSM3879863", "GSM3879864", "GSM3879865", "GSM3879866", "GSM3879867", "GSM3879868", "GSM3879869", "GSM3879870", "GSM3879871", "GSM3879872", "GSM3879873", "GSM3879874", "GSM3879875", "GSM3879876", "GSM3879877", "GSM3879878", "GSM3879879", "GSM3879880", "GSM3879881", "GSM3879882", "GSM3879883", "GSM3879884", "GSM3879885", "GSM3879886", "GSM3879887", "GSM3879888", "GSM3879889", "GSM3879890", "GSM3879891", "GSM3879892", "GSM3879893", "GSM3879894", "GSM3879895", "GSM3879896", "GSM3879897", "GSM3879898", "GSM3879899", "GSM3879900", "GSM3879901", "GSM3879902", "GSM3879903", "GSM3879904", "GSM3879905", "GSM3879906", "GSM3879907", "GSM3879908", "GSM3879909", "GSM3879910", "GSM3879911", "GSM3879912", "GSM3879913", "GSM3879914", "GSM3879915", "GSM3879916", "GSM3879917", "GSM3879918", "GSM3879919", "GSM3879920", "GSM3879921", "GSM3879922", "GSM3879923", "GSM3879924", "GSM3879925", "GSM3879926", "GSM3879927", "GSM3879928", "GSM3879929", "GSM3879930", "GSM3879931", "GSM3879932", "GSM3879933", "GSM3879934", "GSM3879935", "GSM3879936", "GSM3879937", "GSM3879938", "GSM3879939", "GSM3879940", "GSM3879941", "GSM3879942", "GSM3879943", "GSM3879944", "GSM3879945", "GSM3879946", "GSM3879947", "GSM3879948", "GSM3879949", "GSM3879950", "GSM3879951", "GSM3879952", "GSM3879953", "GSM3879954", "GSM3879955", "GSM3879956", "GSM3879957", "GSM3879958", "GSM3879959", "GSM3879960", "GSM3879961", "GSM3879962", "GSM3879963", "GSM3879964", "GSM3879965", "GSM3879966", "GSM3879967", "GSM3879968", "GSM3879969", "GSM3879970", "GSM3879971", "GSM3879972", "GSM3879973", "GSM3879974", "GSM3879975", "GSM3879976", "GSM3879977", "GSM3879978", "GSM3879979", "GSM3879980", "GSM3879981", "GSM3879982", "GSM3879983", "GSM3879984", "GSM3879985", "GSM3879986", "GSM3879987", "GSM3879988", "GSM3879989", "GSM3879990", "GSM3879991", "GSM3879992", "GSM3879993", "GSM3879994", "GSM3879995", "GSM3879996", "GSM3879997", "GSM3879998", "GSM3879999", "GSM3880000", "GSM3880001", "GSM3880002", "GSM3880003", "GSM3880004", "GSM3880005", "GSM3880006", "GSM3880007", "GSM3880008", "GSM3880009", "GSM3880010", "GSM3880011", "GSM3880012", "GSM3880013", "GSM3880014", "GSM3880015", "GSM3880016", "GSM3880017", "GSM3880018", "GSM3880019"], "sample_count": 276, "group_sizes": null, "group_sizes_basis": null, "platform": "15207", "taxon": "Homo sapiens", "title": "Longitudinal Blood Transcriptomic Changes Predict Lung Function Decline in Idiopathic Pulmonary Fibrosis", "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:GSE141259", "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=GSE141259", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE141259", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM4200035", "GSM4200036", "GSM4200037", "GSM4200038", "GSM4200039", "GSM4200040", "GSM4200041", "GSM4200042", "GSM4200043", "GSM4200044", "GSM4200045", "GSM4200046", "GSM4200047", "GSM4200048", "GSM4200049", "GSM4200050", "GSM4200051", "GSM4200052", "GSM4200053", "GSM4200054", "GSM4200055", "GSM4200056", "GSM4200057", "GSM4200058", "GSM4200059", "GSM4200060", "GSM4200061", "GSM4200062", "GSM4200063", "GSM4200064", "GSM4200065", "GSM4200066", "GSM4200067", "GSM4200068", "GSM4200069", "GSM4200070", "GSM4200071", "GSM4200072", "GSM4200073", "GSM4200074", "GSM4200075", "GSM4200076", "GSM4200077", "GSM4200078", "GSM4200079", "GSM4200080", "GSM4200081", "GSM4200082", "GSM4200083", "GSM4200084", "GSM4200085", "GSM4200086", "GSM4200087", "GSM4200088", "GSM4200089", "GSM4200090", "GSM4200091", "GSM4200092", "GSM4200093", "GSM4200094"], "sample_count": 60, "group_sizes": null, "group_sizes_basis": null, "platform": "21103", "taxon": "Mus musculus", "title": "Longitudinal single-cell transcriptomics analysis of mouse lung upon bleomycin-induced injury", "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:GSE27957", "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=GSE27957", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE27957", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM691362", "GSM691363", "GSM691364", "GSM691365", "GSM691366", "GSM691367", "GSM691368", "GSM691369", "GSM691370", "GSM691371", "GSM691372", "GSM691373", "GSM691374", "GSM691375", "GSM691376", "GSM691377", "GSM691378", "GSM691379", "GSM691380", "GSM691381", "GSM691382", "GSM691383", "GSM691384", "GSM691385", "GSM691386", "GSM691387", "GSM691388", "GSM691389", "GSM691390", "GSM691391", "GSM691392", "GSM691393", "GSM691394", "GSM691395", "GSM691396", "GSM691397", "GSM691398", "GSM691399", "GSM691400", "GSM691401", "GSM691402", "GSM691403", "GSM691404", "GSM691405", "GSM691406"], "sample_count": 45, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Peripheral Blood Mononuclear Cell Gene Expression Profiles May Predict Poor Outcome in Idiopathic Pulmonary Fibrosis [Affymetrix]", "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:GSE28042", "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=GSE28042", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE28042", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM693750", "GSM693751", "GSM693752", "GSM693753", "GSM693754", "GSM693755", "GSM693756", "GSM693757", "GSM693758", "GSM693759", "GSM693760", "GSM693761", "GSM693762", "GSM693763", "GSM693764", "GSM693765", "GSM693766", "GSM693767", "GSM693768", "GSM693769", "GSM693770", "GSM693771", "GSM693772", "GSM693773", "GSM693774", "GSM693775", "GSM693776", "GSM693777", "GSM693778", "GSM693779", "GSM693780", "GSM693781", "GSM693782", "GSM693783", "GSM693784", "GSM693785", "GSM693786", "GSM693787", "GSM693788", "GSM693789", "GSM693790", "GSM693791", "GSM693792", "GSM693793", "GSM693794", "GSM693795", "GSM693796", "GSM693797", "GSM693798", "GSM693799", "GSM693800", "GSM693801", "GSM693802", "GSM693803", "GSM693804", "GSM693805", "GSM693806", "GSM693807", "GSM693808", "GSM693809", "GSM693810", "GSM693811", "GSM693812", "GSM693813", "GSM693814", "GSM693815", "GSM693816", "GSM693817", "GSM693818", "GSM693819", "GSM693820", "GSM693821", "GSM693822", "GSM693823", "GSM693824", "GSM698440", "GSM698441", "GSM698442", "GSM698443", "GSM698444", "GSM698445", "GSM698446", "GSM698447", "GSM698448", "GSM698449", "GSM698450", "GSM698451", "GSM698452", "GSM698453", "GSM698454", "GSM698455", "GSM698456", "GSM698457", "GSM698458"], "sample_count": 94, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "Peripheral Blood Mononuclear Cell Gene Expression Profiles May Predict Poor Outcome in Idiopathic Pulmonary Fibrosis [Agilent]", "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:GSE32537", "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=GSE32537", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32537", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM806204", "GSM806205", "GSM806206", "GSM806207", "GSM806208", "GSM806209", "GSM806210", "GSM806211", "GSM806212", "GSM806213", "GSM806214", "GSM806215", "GSM806216", "GSM806217", "GSM806218", "GSM806219", "GSM806220", "GSM806221", "GSM806222", "GSM806223", "GSM806224", "GSM806225", "GSM806226", "GSM806227", "GSM806228", "GSM806229", "GSM806230", "GSM806231", "GSM806232", "GSM806233", "GSM806234", "GSM806235", "GSM806236", "GSM806237", "GSM806238", "GSM806239", "GSM806240", "GSM806241", "GSM806242", "GSM806243", "GSM806244", "GSM806245", "GSM806246", "GSM806247", "GSM806248", "GSM806249", "GSM806250", "GSM806251", "GSM806252", "GSM806253", "GSM806254", "GSM806255", "GSM806256", "GSM806257", "GSM806258", "GSM806259", "GSM806260", "GSM806261", "GSM806262", "GSM806263", "GSM806264", "GSM806265", "GSM806266", "GSM806267", "GSM806268", "GSM806269", "GSM806270", "GSM806271", "GSM806272", "GSM806273", "GSM806274", "GSM806275", "GSM806276", "GSM806277", "GSM806278", "GSM806279", "GSM806280", "GSM806281", "GSM806282", "GSM806283", "GSM806284", "GSM806285", "GSM806286", "GSM806287", "GSM806288", "GSM806289", "GSM806290", "GSM806291", "GSM806292", "GSM806293", "GSM806294", "GSM806295", "GSM806296", "GSM806297", "GSM806298", "GSM806299", "GSM806300", "GSM806301", "GSM806302", "GSM806303", "GSM806304", "GSM806305", "GSM806306", "GSM806307", "GSM806308", "GSM806309", "GSM806310", "GSM806311", "GSM806312", "GSM806313", "GSM806314", "GSM806315", "GSM806316", "GSM806317", "GSM806318", "GSM806319", "GSM806320", "GSM806321", "GSM806322", "GSM806323", "GSM806324", "GSM806325", "GSM806326", "GSM806327", "GSM806328", "GSM806329", "GSM806330", "GSM806331", "GSM806332", "GSM806333", "GSM806334", "GSM806335", "GSM806336", "GSM806337", "GSM806338", "GSM806339", "GSM806340", "GSM806341", "GSM806342", "GSM806343", "GSM806344", "GSM806345", "GSM806346", "GSM806347", "GSM806348", "GSM806349", "GSM806350", "GSM806351", "GSM806352", "GSM806353", "GSM806354", "GSM806355", "GSM806356", "GSM806357", "GSM806358", "GSM806359", "GSM806360", "GSM806361", "GSM806362", "GSM806363", "GSM806364", "GSM806365", "GSM806366", "GSM806367", "GSM806368", "GSM806369", "GSM806370", "GSM806371", "GSM806372", "GSM806373", "GSM806374", "GSM806375", "GSM806376", "GSM806377", "GSM806378", "GSM806379", "GSM806380", "GSM806381", "GSM806382", "GSM806383", "GSM806384", "GSM806385", "GSM806386", "GSM806387", "GSM806388", "GSM806389", "GSM806390", "GSM806391", "GSM806392", "GSM806393", "GSM806394", "GSM806395", "GSM806396", "GSM806397", "GSM806398", "GSM806399", "GSM806400", "GSM806401", "GSM806402", "GSM806403", "GSM806404", "GSM806405", "GSM806406", "GSM806407", "GSM806408", "GSM806409", "GSM806410", "GSM806411", "GSM806412", "GSM806413", "GSM806414", "GSM806415", "GSM806416", "GSM806417", "GSM806418", "GSM806419", "GSM806420"], "sample_count": 217, "group_sizes": null, "group_sizes_basis": null, "platform": "6244", "taxon": "Homo sapiens", "title": "Molecular phenotyping of the idiopathic interstitial pneumonias [mRNA]", "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:GSE33566", "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=GSE33566", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE33566", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM829965", "GSM829966", "GSM829967", "GSM829968", "GSM829969", "GSM829970", "GSM829971", "GSM829972", "GSM829973", "GSM829974", "GSM829975", "GSM829976", "GSM829977", "GSM829978", "GSM829979", "GSM829980", "GSM829981", "GSM829982", "GSM829983", "GSM829984", "GSM829985", "GSM829986", "GSM829987", "GSM829988", "GSM829989", "GSM829990", "GSM829991", "GSM829992", "GSM829993", "GSM829994", "GSM829995", "GSM829996", "GSM829997", "GSM829998", "GSM829999", "GSM830000", "GSM830001", "GSM830002", "GSM830003", "GSM830004", "GSM830005", "GSM830006", "GSM830007", "GSM830008", "GSM830009", "GSM830010", "GSM830011", "GSM830012", "GSM830013", "GSM830014", "GSM830015", "GSM830016", "GSM830017", "GSM830018", "GSM830019", "GSM830020", "GSM830021", "GSM830022", "GSM830023", "GSM830024", "GSM830025", "GSM830026", "GSM830027", "GSM830028", "GSM830029", "GSM830030", "GSM830031", "GSM830032", "GSM830033", "GSM830034", "GSM830035", "GSM830036", "GSM830037", "GSM830038", "GSM830039", "GSM830040", "GSM830041", "GSM830042", "GSM830043", "GSM830044", "GSM830045", "GSM830046", "GSM830047", "GSM830048", "GSM830049", "GSM830050", "GSM830051", "GSM830052", "GSM830053", "GSM830054", "GSM830055", "GSM830056", "GSM830057", "GSM830058", "GSM830059", "GSM830060", "GSM830061", "GSM830062", "GSM830063", "GSM830064", "GSM830065", "GSM830066", "GSM830067", "GSM830068", "GSM830069", "GSM830070", "GSM830071", "GSM830072", "GSM830073", "GSM830074", "GSM830075", "GSM830076", "GSM830077", "GSM830078", "GSM830079", "GSM830080", "GSM830081", "GSM830082", "GSM830083", "GSM830084", "GSM830085", "GSM830086", "GSM830087"], "sample_count": 123, "group_sizes": null, "group_sizes_basis": null, "platform": "6480", "taxon": "Homo sapiens", "title": "The Peripheral Blood Transcriptome Predicts the Presence and Extent of Disease in Idiopathic Pulmonary Fibrosis", "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:GSE38958", "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=GSE38958", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE38958", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM952756", "GSM952757", "GSM952758", "GSM952759", "GSM952760", "GSM952761", "GSM952762", "GSM952763", "GSM952764", "GSM952765", "GSM952766", "GSM952767", "GSM952768", "GSM952769", "GSM952770", "GSM952771", "GSM952772", "GSM952773", "GSM952774", "GSM952775", "GSM952776", "GSM952777", "GSM952778", "GSM952779", "GSM952780", "GSM952781", "GSM952782", "GSM952783", "GSM952784", "GSM952785", "GSM952786", "GSM952787", "GSM952788", "GSM952789", "GSM952790", "GSM952791", "GSM952792", "GSM952793", "GSM952794", "GSM952795", "GSM952796", "GSM952797", "GSM952798", "GSM952799", "GSM952800", "GSM952801", "GSM952802", "GSM952803", "GSM952804", "GSM952805", "GSM952806", "GSM952807", "GSM952808", "GSM952809", "GSM952810", "GSM952811", "GSM952812", "GSM952813", "GSM952814", "GSM952815", "GSM952816", "GSM952817", "GSM952818", "GSM952819", "GSM952820", "GSM952821", "GSM952822", "GSM952823", "GSM952824", "GSM952825", "GSM952826", "GSM952827", "GSM952828", "GSM952829", "GSM952830", "GSM952831", "GSM952832", "GSM952833", "GSM952834", "GSM952835", "GSM952836", "GSM952837", "GSM952838", "GSM952839", "GSM952840", "GSM952841", "GSM952842", "GSM952843", "GSM952844", "GSM952845", "GSM952846", "GSM952847", "GSM952848", "GSM952849", "GSM952850", "GSM952851", "GSM952852", "GSM952853", "GSM952854", "GSM952855", "GSM952856", "GSM952857", "GSM952858", "GSM952859", "GSM952860", "GSM952861", "GSM952862", "GSM952863", "GSM952864", "GSM952865", "GSM952866", "GSM952867", "GSM952868", "GSM952869", "GSM952870"], "sample_count": 115, "group_sizes": null, "group_sizes_basis": null, "platform": "5175", "taxon": "Homo sapiens", "title": "Profiling of Gene Expression in Idiopathic Pulmonary Fibrosis", "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: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": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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}}, {"id": "data:geo:GSE93606", "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=GSE93606", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE93606", "version": null, "note": "Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "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: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 .", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2458563", "GSM2458564", "GSM2458565", "GSM2458566", "GSM2458567", "GSM2458568", "GSM2458569", "GSM2458570", "GSM2458571", "GSM2458572", "GSM2458573", "GSM2458574", "GSM2458575", "GSM2458576", "GSM2458577", "GSM2458578", "GSM2458579", "GSM2458580", "GSM2458581", "GSM2458582", "GSM2458583", "GSM2458584", "GSM2458585", "GSM2458586", "GSM2458587", "GSM2458588", "GSM2458589", "GSM2458590", "GSM2458591", "GSM2458592", "GSM2458593", "GSM2458594", "GSM2458595", "GSM2458596", "GSM2458597", "GSM2458598", "GSM2458599", "GSM2458600", "GSM2458601", "GSM2458602", "GSM2458603", "GSM2458604", "GSM2458605", "GSM2458606", "GSM2458607", "GSM2458608", "GSM2458609", "GSM2458610", "GSM2458611", "GSM2458612", "GSM2458613", "GSM2458614", "GSM2458615", "GSM2458616", "GSM2458617", "GSM2458618", "GSM2458619", "GSM2458620", "GSM2458621", "GSM2458622", "GSM2458623", "GSM2458624", "GSM2458625", "GSM2458626", "GSM2458627", "GSM2458628", "GSM2458629", "GSM2458630", "GSM2458631", "GSM2458632", "GSM2458633", "GSM2458634", "GSM2458635", "GSM2458636", "GSM2458637", "GSM2458638", "GSM2458639", "GSM2458640", "GSM2458641", "GSM2458642", "GSM2458643", "GSM2458644", "GSM2458645", "GSM2458646", "GSM2458647", "GSM2458648", "GSM2458649", "GSM2458650", "GSM2458651", "GSM2458652", "GSM2458653", "GSM2458654", "GSM2458655", "GSM2458656", "GSM2458657", "GSM2458658", "GSM2458659", "GSM2458660", "GSM2458661", "GSM2458662", "GSM2458663", "GSM2458664", "GSM2458665", "GSM2458666", "GSM2458667", "GSM2458668", "GSM2458669", "GSM2458670", "GSM2458671", "GSM2458672", "GSM2458673", "GSM2458674", "GSM2458675", "GSM2458676", "GSM2458677", "GSM2458678", "GSM2458679", "GSM2458680", "GSM2458681", "GSM2458682", "GSM2458683", "GSM2458684", "GSM2458685", "GSM2458686", "GSM2458687", "GSM2458688", "GSM2458689", "GSM2458690", "GSM2458691", "GSM2458692", "GSM2458693", "GSM2458694", "GSM2458695", "GSM2458696", "GSM2458697", "GSM2458698", "GSM2458699", "GSM2458700", "GSM2458701", "GSM2458702", "GSM2458703", "GSM2458704", "GSM2458705", "GSM2458706", "GSM2458707", "GSM2458708", "GSM2458709", "GSM2458710", "GSM2458711", "GSM2458712", "GSM2458713", "GSM2458714", "GSM2458715", "GSM2458716", "GSM2458717", "GSM2458718", "GSM2458719", "GSM2458720", "GSM2458721", "GSM2458722", "GSM2458723", "GSM2458724", "GSM2458725", "GSM2458726", "GSM2458727", "GSM2458728", "GSM2458729", "GSM2458730", "GSM2458731", "GSM2458732", "GSM2458733", "GSM2458734", "GSM2458735", "GSM2458736"], "sample_count": 174, "group_sizes": null, "group_sizes_basis": null, "platform": "11532", "taxon": "Homo sapiens", "title": "Host-Microbial interactions in Idiopathic Pulmonary Fibrosis", "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:GSE110147 not downloaded", "asset:data:geo:GSE110147 licence not read", "asset:data:geo:GSE132607 not downloaded", "asset:data:geo:GSE132607 licence not read", "asset:data:geo:GSE141259 not downloaded", "asset:data:geo:GSE141259 licence not read", "asset:data:geo:GSE27957 not downloaded", "asset:data:geo:GSE27957 licence not read", "asset:data:geo:GSE28042 not downloaded", "asset:data:geo:GSE28042 licence not read", "asset:data:geo:GSE32537 not downloaded", "asset:data:geo:GSE32537 licence not read", "asset:data:geo:GSE33566 not downloaded", "asset:data:geo:GSE33566 licence not read", "asset:data:geo:GSE38958 not downloaded", "asset:data:geo:GSE38958 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", "asset:data:geo:GSE93606 not downloaded", "asset:data:geo:GSE93606 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "regression_modelling", "specific": "logistic", "label": "Regression modelling", "dsl_operations": ["glm_logit_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "CD247 was identified as the hub gene associated with percent predicted diffusion capacity of the lung for carbon monoxide (Dlco% predicted) and prognosis according to Pearson correlation, logistic regression, and survival analysis."}}, {"id": "method-2", "family": "survival_analysis", "specific": "cox_proportional_hazards", "label": "Survival analysis", "dsl_operations": ["cox_ph"], "missing_operations": [], "expressible": true, "parameters": {"hazard_ratio": "The hazard ratio (HR) for the statistica"}, "data_shapes": ["time_to_event_with_censoring"], "evidence": {"score": 0.8, "band": "high", "quote": "Cox regression"}}, {"id": "method-3", "family": "principal_component_analysis", "specific": "pca", "label": "Principal component analysis", "dsl_operations": ["pca_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["wide_numeric_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "Principal component analysis"}}, {"id": "method-4", "family": "correlation_analysis", "specific": "pearson", "label": "Correlation analysis", "dsl_operations": ["pearson_r"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["paired_numeric_columns"], "evidence": {"score": 0.7, "band": "medium", "quote": "Pearson correlation"}}, {"id": "method-5", "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"}}, {"id": "method-6", "family": "diagnostic_evaluation", "specific": "roc", "label": "Diagnostic test evaluation", "dsl_operations": ["confusion_counts", "roc_curve", "sensitivity_specificity", "solve_confusion_matrix", "classification_metrics", "published_precision_envelope"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["reference_standard_and_test"], "evidence": {"score": 0.8, "band": "high", "quote": "ROC curve"}}, {"id": "method-7", "family": "contingency_analysis", "specific": "chi_square", "label": "Categorical (contingency table) analysis", "dsl_operations": ["chi_square_test"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["categorical_cross_tabulation"], "evidence": {"score": 0.8, "band": "high", "quote": "chi-square"}}], "targets": [], "gaps": ["method.reader_differs_from_extractor"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["glm_logit_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: logistic."}, "capability": {"tier": "R1", "capability_id": "capability:computational_analysis", "availability_state": "owned", "basis": "The computational analysis is owned. The physical bench the paper used is not, so a physical validation cannot be run here."}, "data": {"tier": "R1", "reachable": true, "accessions": ["GSE32537", "GSE47460", "GSE110147", "GSE141259", "GSE93606", "GSE27957", "GSE28042", "GSE38958", "GSE132607", "GSE33566", "GSE70866"], "resolved_accessions": ["GSE32537", "GSE47460", "GSE110147", "GSE141259", "GSE93606", "GSE27957", "GSE28042", "GSE38958", "GSE132607", "GSE33566", "GSE70866"], "statements": ["Publicly available datasets were analyzed in this study. This data can be found here: GSE32537 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE32537), GSE47460 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE47460), GSE110147 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110147), GSE141259 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE141259), GSE93606 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE93606, GSE27957 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE27957), GSE28042 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE28042), GSE38958 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE38958), GSE132607 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE132607), GSE33566 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE33566), GSE70866 (https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE70866). The annotated gene set file used in ssGSEA were available in Supplementary Material 2 ."], "basis": "The paper names GSE32537, GSE47460, GSE110147, GSE141259, GSE93606, GSE27957, GSE28042, GSE38958, GSE132607, GSE33566, GSE70866 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": ["glm_logit_fit"], "assets": ["source:pmid:34880861", "data:geo:GSE110147"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE110147"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T17:10:40Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 15620, "completion_tokens": 3968, "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:34880861", "type": "paper", "label": "pmid:34880861"}, {"id": "source:pmid:34880861", "type": "manuscript", "label": "PMID 34880861 full text"}, {"id": "data:geo:GSE110147", "type": "dataset", "label": "GEO GSE110147"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:34880861", "type": "paper", "label": "pmid:34880861"}, {"id": "source:pmid:34880861", "type": "manuscript", "label": "PMID 34880861 full text"}, {"id": "data:geo:GSE110147", "type": "dataset", "label": "GEO GSE110147"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-34880861", "type": "extraction", "used": ["source:pmid:34880861"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE110147", "type": "accession_resolution", "used": ["data:geo:GSE110147"], "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:34880861", "parent_hash": "sha256:3dbfd914fddd05a7943a8f2cf5912498bb2aa43d174eecce3b7379703daf246b", "fork_of": null, "generation": 4}, "gaps": ["asset:data:geo:GSE110147 licence not read", "asset:data:geo:GSE110147 not downloaded", "asset:data:geo:GSE132607 licence not read", "asset:data:geo:GSE132607 not downloaded", "asset:data:geo:GSE141259 licence not read", "asset:data:geo:GSE141259 not downloaded", "asset:data:geo:GSE27957 licence not read", "asset:data:geo:GSE27957 not downloaded", "asset:data:geo:GSE28042 licence not read", "asset:data:geo:GSE28042 not downloaded", "asset:data:geo:GSE32537 licence not read", "asset:data:geo:GSE32537 not downloaded", "asset:data:geo:GSE33566 licence not read", "asset:data:geo:GSE33566 not downloaded", "asset:data:geo:GSE38958 licence not read", "asset:data:geo:GSE38958 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", "asset:data:geo:GSE93606 licence not read", "asset:data:geo:GSE93606 not downloaded", "execution.not_run", "method.reader_differs_from_extractor", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "scrna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "unsupported", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["Materials and Methods Analysis of scRNA-seq Data The computational analysis of the GSE14", "nsform () function was used to normalize the scRNA-seq data. Principal component analysis (PCA) was", "ine in FVC >10% over six months period). The scRNA-seq Data Analysis of CD247 According to the Lung", "ells and NK cells in the human lung based on scRNA-seq data (37) ( Supplementary Figure 5A ). In th"], "order_basis": "paper_text_order:1995", "id": "assay:1"}, {"role": "data_generation", "definition_id": "animal_model", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["A-seq data (37) ( Supplementary Figure 5A ). In the mouse lung, Cd247 is also mainly expressed by the", "ata (37) ( Supplementary Figure 5A ). In the mouse lung, Cd247 is also mainly expressed by the", "tabase (https://www.lungmap.net/), (B–D) the mouse lung (GSE141259 dataset).Click here for addi"], "order_basis": "paper_text_order:6417", "id": "assay:2"}, {"role": "analysis", "definition_id": "regression_modelling", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["glm_logit_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["CD247 was identified as the hub gene associated with percent predicted diffusion capacity of the lung for carbon monoxide (Dlco% predicted) and prognosis according to Pearson correlation, logistic regression, and survival analysis."], "order_basis": "consumes_earlier_output", "id": "assay:3"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:24:24+00:00","total_papers":5529,"total_assays_tracked":29,"automatable_assay_families":6,"validated":true,"caveat_count":9,"blocking_caveats":5,"caveats":[{"code":"low_evidence_dominates","basis":["4,152 of 5,529 classifications (75.1%) matched no cue evidence and sit at the 0.05 floor.","34 of 230 data_only calls (14.8%) are in that group."],"claim":"Work type and confidence bands","gloss":"Most records were classified from their title and framing alone, with assay-cue coverage at zero.","detail":"Most classifications in this run rest on no matched evidence at all. At the evidence floor the work type comes from title framing and a fixed prior, not from anything in the paper, so the published work-type split should be read as a rough triage signal rather than a measured distribution. The impact is bounded but not removed: since 2026-10-23 the engine excludes floor-confidence records from the shortlist entirely and publishes them separately as held out, so the recommendation is unaffected even though the census is.","status":"unverified","severity":"high"},{"code":"runtime_is_modelled","basis":["Runtime is summed from published per-assay hour figures. Timing awaits the first executed replication.","4,407 of 5,529 records (79.7%) model to 0.00 hours because no assay was matched, which the ranking then reads as \"cheapest\".","0 of 10 shortlisted records carry a 0.00-hour estimate."],"claim":"Estimated replication runtime","gloss":"The hour figures are estimates built from assay mentions; timing awaits the first executed replication.","detail":"The hour figures are a cost model derived from the bench steps implied by each matched assay family. The first executed replication will supply measured timing. Records without an assay match currently receive a zero-hour model value.","status":"unverified","severity":"high"},{"code":"signal_score_without_citations","basis":["5,529 of 5,529 records (100.0%) have no citation count from the source metadata."],"claim":"Signal score","gloss":"The signal score uses publication-type weight because the mirror supplied zero citation counts.","detail":"The source supplied no citation counts for any record in this run, so the signal score is publication-type weight only. The citation term of the ranking is inert here, and the shortlist is ordered by publication type alone.","status":"unverified","severity":"high"},{"code":"abstract_absent","basis":["1,667 of 5,529 records (30.2%) carry no abstract at all."],"claim":"Evidence base for classification","gloss":"Some records contain a title and publication type only, defining the available classification evidence.","detail":"Where the mirror contains a title and publication types only, those fields define the classifier evidence. A methods section is required for fuller automated and human review.","status":"unverified","severity":"medium"},{"code":"classifier_agreement_measured","basis":["Published two-way decision agreement 77.7% (310 of 399 decidable records) from a stratified hand-check of 438 real records.","Three-way diagnostic agreement 73.9% (288 of 390 decidable records).","data_only agreement 75.2% (100 of 133 decidable).","48 record(s) could not be decided from title and abstract and were excluded from the denominator.","56 analysis-only records were published under another work type, so the data_only share is not an upper bound."],"claim":"Published automatable decision","gloss":"This figure has been checked against a human reading the same papers, so we know how often it is right.","detail":"The published automatable / not-automatable distribution comes from a rule-based classifier that was hand-checked against a fixed ground-truth definition. The agreement rates below are measured, not estimated. The three-way work type remains a diagnostic and is reported separately.","status":"measured","severity":"high"},{"code":"llm_comparison_not_measured","basis":["rule_based_v1+lex99e1195c7d6f produced 5,529 of 5,529 classifications.","Measured on 438 labelled records; these are RULE-BASED figures, not model results."],"claim":"Rule-based versus LLM agreement","gloss":"Every number here is the rule engine’s own. Model comparison begins when a working API credential is connected and measured.","detail":"The published two-way decision agreed with a human reading on 310 of 399 decidable records (77.7%). The diagnostic three-way label agreed on 288 of 390 decidable records (73.9%). Every percentage in this run belongs to the rule engine. Model comparison begins when a working API credential is connected and measured.","status":"not_measured","severity":"high"},{"code":"confidence_is_a_band","basis":["low band: 135 of 210 hand-judged records were correct, 64.3% [57.6, 70.5] (95% CI).","medium band: 80 of 104 hand-judged records were correct, 76.9% [68.0, 84.0] (95% CI).","high band: 73 of 76 hand-judged records were correct, 96.0% [89.0, 98.7] (95% CI).","A fitted calibrated probability was built, measured and withdrawn: it overstated held-out accuracy and reorders nothing."],"claim":"Confidence band and evidence score","gloss":"The confidence band carries a measured accuracy interval; 0.85 represents relative rank strength.","detail":"Confidence on this run is a BAND plus its measured accuracy interval. The number stored alongside each record is a monotone evidence score that orders records; 0.85 represents relative rank strength. A fitted probability was withdrawn after it overstated held-out accuracy. Threshold on the band.","status":"measured","severity":"medium"},{"code":"three_way_split_is_diagnostic","basis":["The corpus is published at the two-way decision: automatable or not-automatable. The three-way split (data_only / physical / mixed) is published as a diagnostic with its measured reliability attached, not as a claim, because the rule engine's `mixed` call cannot be defended.","The engine called 22 record(s) mixed; 10 matched the human judgement (45.5%, 95% CI 26.9-65.3).","The engine's `mixed` call is right on 10/22 hand-judged records (45.5%, 95% CI 26.9%-65.3%); a constant `physical` guess scores 36.4%.","The engine's `mixed` call does not reliably beat a constant `physical` guess on the hand-judged records it labels mixed.","The sign of that difference flips between two independent samples, so the three-way refinement is not demonstrably informative.","The mixed stratum contributes a disproportionate share of errors relative to its size.","At title-only depth the physical/mixed split collapses: a title says that work was done, not whether it was also analysed."],"claim":"The published decision is two-way","gloss":"The three-way split is shown for diagnosis only. The published split is two ways.","detail":"Count and filter the corpus on automatable versus not-automatable. The data_only / physical / mixed split remains an internal engine diagnostic because the mixed call has lower measured reliability.","status":"measured","severity":"medium"},{"code":"automatable_flag_unproven","basis":["6 of 29 assay families are marked automatable now: meta_analysis, machine_learning, survival_analysis, pca, molecular_docking, differential_expression.","The flag is a rule over assay family and work type; validation begins with the first executed replication.","It inherits the 75.2% data_only agreement rate, because the flag requires the record to be analysis-only."],"claim":"Automatable now","gloss":"This flag marks assay families the rules classify as data-only. The first executed replication will validate it.","detail":"This flag marks families the rules consider replicable from data alone. Its validity depends on the analysis-only classification and will be measured through an executed replication.","status":"unverified","severity":"medium"}],"confidence_policy":"band_with_measured_interval","confidence_contract":{"policy":"band_with_measured_interval","summary":"Confidence is reported as a BAND with a measured accuracy interval. The raw evidence score supplies monotone ordering. A fitted point estimate was withdrawn after it overstated held-out accuracy.","evidence_score":"A monotone evidence score in [0,1] built from cue mass, axis separation and text coverage. Use it to order records. Interpret 0.85 as relative rank strength.","confidence_band":"low | medium | high. Consumers threshold on this value.","band_accuracy":"Wilson 95% interval on the measured agreement of the hand-judged records in this band.","calibrated_confidence":"WITHDRAWN. Reintroduction requires held-out evidence demonstrating reliable estimates across every bin."},"band_accuracy":{"low":{"n":210,"low":0.576,"band":"low","high":0.7046,"agree":135,"accuracy":0.6429},"high":{"n":76,"low":0.8903,"band":"high","high":0.9865,"agree":73,"accuracy":0.9605},"medium":{"n":104,"low":0.6795,"band":"medium","high":0.8397,"agree":80,"accuracy":0.7692}},"provider":"rule_based_v1+lex99e1195c7d6f","lexicon_id":"99e1195c7d6f","contract_published_at":"2026-10-23T12:25:29.022232+00:00","confidence_is_band":true,"confidence_is_probability":false,"decision_taxonomy":"two_way","decidable_fraction_two_way":0.8854,"decidable_fraction_two_way_low":0.8565,"decidable_fraction_two_way_high":0.9143,"decidable_fraction_three_way":0.8586,"decidable_fraction_three_way_low":0.8287,"decidable_fraction_three_way_high":0.8884,"decidable_population":5529,"validation_sample_size":438,"three_way_cost_fraction":0.0268,"three_way_cost_records":148,"decision_counts":{"automatable":230,"not_automatable":5299},"decision_split":{"automatable":{"count":230,"share":0.04159884246699222},"not_automatable":{"count":5299,"share":0.9584011575330078}},"diagnostic_work_type_counts":{"mixed":24,"physical":5275,"data_only":230}}}