{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:37887075", "kind": "science-record", "revision": 4, "content_hash": "sha256:b57ad9b4b3b49e9236faf45ae8a486f9163621bf19a9caa39950c3c9f3d4d68d", "created_at": "2026-11-01T19:02:45Z", "updated_at": "2026-11-01T22:10:31Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of Hub Genes in Idiopathic Pulmonary Fibrosis and Their Association with Lung Cancer by Bioinformatics Analysis.", "doi": "10.3390/arm91050032", "pmid": "37887075", "authors": ["Juan Manuel Velázquez-Enríquez", "Itayetzi Reyes-Avendaño", "Jovito Cesar Santos-Álvarez", "Edilburga Reyes-Jiménez", "Verónica Rocío Vásquez-Garzón", "Rafael Baltiérrez-Hoyos"], "journal": "Advances in respiratory medicine", "year": 2023, "abstract": "BACKGROUND: Idiopathic pulmonary fibrosis (IPF) is a chronic, progressive, and irreversible disease with a high mortality rate worldwide. However, the etiology and pathogenesis of IPF have not yet been fully described. Moreover, lung cancer is a significant complication of IPF and is associated with increased mortality. Nevertheless, identifying common genes involved in developing IPF and its progression to lung cancer remains an unmet need. The present study aimed to identify hub genes related to the development of IPF by meta-analysis. In addition, we analyzed their expression and their relationship with patients' progression in lung cancer.\nMETHOD: Microarray datasets GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539 were downloaded from Gene Expression Omnibus (GEO). Next, we conducted a series of bioinformatics analysis to explore possible hub genes in IPF and evaluated the expression of hub genes in lung cancer and their relationship with the progression of different stages of cancer.\nRESULTS: A total of 1888 differentially expressed genes (DEGs) were identified, including 1105 upregulated and 783 downregulated genes. The 10 hub genes that exhibited a high degree of connectivity from the PPI network were identified. Analysis of the KEGG pathways showed that hub genes correlate with pathways such as the ECM-receptor interaction. Finally, we found that these hub genes are expressed in lung cancer and are associated with the progression of different stages of lung cancer.\nCONCLUSIONS: Based on the integration of GEO microarray datasets, the present study identified DEGs and hub genes that could play an essential role in the pathogenesis of IPF and its association with the development of lung cancer in these patients, which could be considered potential diagnostic biomarkers or therapeutic targets for the disease.", "claims": [{"id": "claim-method", "statement": "We used the effect size combination method, specifically the random effects model (REM) and default settings for the integration of differential gene expression.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37887075", "locator": "sections[5] \"2.3. Identification of DEGs\" paragraph 2", "quote": "We used the effect size combination method, specifically the random effects model (REM) and default settings for the integration of differential gene expression."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:37887075", "locator": "sections[27] \"notes\" paragraph 1", "quote": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files."}], "state": "complete"}, {"id": "claim-target-result", "statement": "A total of 1888 differentially expressed genes (DEGs) were identified, including 1105 upregulated and 783 downregulated genes.", "kind": "qualitative", "target": null, "evidence": [{"asset": "source:pmid:37887075", "locator": "sections[0] \"Abstract\" paragraph 7", "quote": "A total of 1888 differentially expressed genes (DEGs) were identified, including 1105 upregulated and 783 downregulated genes."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "A total of 1888 differentially expressed genes (DEGs) were identified, including 1105 upregulated and 783 downregulated genes.", "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:37887075"], "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:37887075", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3390/arm91050032", "sha256": "sha256:39f6aee891f65417295e9c4ee0588c28835aa35f13decef951f84e5944c1d351", "bytes": 58288, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3390/arm91050032", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC10604190", "source": "europe_pmc_fulltext", "coverage": "whole_body_without_references", "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 microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "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:GSE21369", "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=GSE21369", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE21369", "version": null, "note": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM533882", "GSM533883", "GSM533884", "GSM533885", "GSM533886", "GSM533887", "GSM533888", "GSM533889", "GSM533890", "GSM533891", "GSM533892", "GSM533893", "GSM533894", "GSM533895", "GSM533896", "GSM533897", "GSM533898", "GSM533899", "GSM533900", "GSM533901", "GSM533902", "GSM533903", "GSM533904", "GSM533905", "GSM533906", "GSM533907", "GSM533908", "GSM533909", "GSM533910"], "sample_count": 29, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Gene expression profiles of interstitial lung disease (ILD) patients", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE24206", "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=GSE24206", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE24206", "version": null, "note": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM595407", "GSM595411", "GSM595414", "GSM595416", "GSM595417", "GSM595419", "GSM595421", "GSM595422", "GSM595423", "GSM595424", "GSM595425", "GSM595426", "GSM595427", "GSM595428", "GSM595429", "GSM595432", "GSM595434", "GSM595435", "GSM595437", "GSM595439", "GSM595441", "GSM595443", "GSM595445"], "sample_count": 23, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Validated Gene Expression Signatures of Idiopathic Pulmonary Fibrosis", "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:GSE32539", "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=GSE32539", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE32539", "version": null, "note": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "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", "GSM806421", "GSM806422", "GSM806423", "GSM806424", "GSM806425", "GSM806426", "GSM806427", "GSM806428", "GSM806429", "GSM806430", "GSM806431", "GSM806432", "GSM806433", "GSM806434", "GSM806435", "GSM806436", "GSM806437", "GSM806438", "GSM806439", "GSM806440", "GSM806441", "GSM806442", "GSM806443", "GSM806444", "GSM806445", "GSM806446", "GSM806447", "GSM806448", "GSM806449", "GSM806450", "GSM806451", "GSM806452", "GSM806453", "GSM806454", "GSM806455", "GSM806456", "GSM806457", "GSM806458", "GSM806459", "GSM806460", "GSM806461", "GSM806462", "GSM806463", "GSM806464", "GSM806465", "GSM806466", "GSM806467", "GSM806468", "GSM806469", "GSM806470", "GSM806471", "GSM806472", "GSM806473", "GSM806474", "GSM806475", "GSM806476", "GSM806477", "GSM806478", "GSM806479", "GSM806480", "GSM806481", "GSM806482", "GSM806483", "GSM806484", "GSM806485", "GSM806486", "GSM806487", "GSM806488", "GSM806489", "GSM806490", "GSM806491", "GSM806492", "GSM806493", "GSM806494", "GSM806495", "GSM806496", "GSM806497", "GSM806498", "GSM806499", "GSM806500", "GSM806501", "GSM806502", "GSM806503", "GSM806504", "GSM806505", "GSM806506", "GSM806507", "GSM806508", "GSM806509", "GSM806510", "GSM806511", "GSM806512", "GSM806513", "GSM806514", "GSM806515", "GSM806516", "GSM806517", "GSM806518", "GSM806519", "GSM806520", "GSM806521", "GSM806522", "GSM806523", "GSM806524", "GSM806525", "GSM806526", "GSM806527", "GSM806528", "GSM806529", "GSM806530", "GSM806531", "GSM806532", "GSM806533", "GSM806534", "GSM806535", "GSM806536", "GSM806537", "GSM806538", "GSM806539", "GSM806540", "GSM806541", "GSM806542", "GSM806543", "GSM806544", "GSM806545", "GSM806546", "GSM806547", "GSM806548", "GSM806549", "GSM806550", "GSM806551", "GSM806552", "GSM806553", "GSM806554", "GSM806555", "GSM806556", "GSM806557", "GSM806558", "GSM806559", "GSM806560", "GSM806561", "GSM806562", "GSM806563", "GSM806564", "GSM806565", "GSM806566", "GSM806567", "GSM806568", "GSM806569", "GSM806570", "GSM806571", "GSM806572", "GSM806573", "GSM806574", "GSM806575", "GSM806576", "GSM806577", "GSM806578", "GSM806579", "GSM806580", "GSM806581", "GSM806582", "GSM806583", "GSM806584", "GSM806585", "GSM806586", "GSM806587", "GSM806588", "GSM806589", "GSM806590", "GSM806591", "GSM806592", "GSM806593", "GSM806594", "GSM806595", "GSM806596", "GSM806597", "GSM806598", "GSM806599", "GSM806600", "GSM806601", "GSM806602", "GSM806603", "GSM806604", "GSM806605", "GSM806606", "GSM806607", "GSM806608", "GSM806609", "GSM806610", "GSM806611", "GSM806612"], "sample_count": 409, "group_sizes": null, "group_sizes_basis": null, "platform": "6244;8786", "taxon": "Homo sapiens; synthetic construct", "title": "Molecular phenotyping of the idiopathic interstitial pneumonias identifies two Subtypes of idiopathic pulmonary fibrosis.", "resolution_checked_at": "2026-11-01T19:09:46Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE72073", "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=GSE72073", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE72073", "version": null, "note": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1854182", "GSM1854183", "GSM1854184", "GSM1854185", "GSM1854186", "GSM1854187", "GSM1854188", "GSM1854189"], "sample_count": 8, "group_sizes": null, "group_sizes_basis": null, "platform": "17586", "taxon": "Homo sapiens", "title": "Expression data from lung tissues of IPF patients and Normal Control", "resolution_checked_at": "2026-11-01T19:09:46Z", "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:GSE21369 not downloaded", "asset:data:geo:GSE21369 licence not read", "asset:data:geo:GSE24206 not downloaded", "asset:data:geo:GSE24206 licence not read", "asset:data:geo:GSE32539 not downloaded", "asset:data:geo:GSE32539 licence not read", "asset:data:geo:GSE72073 not downloaded", "asset:data:geo:GSE72073 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "meta_analysis", "specific": "random_effects", "label": "Meta-analysis / evidence synthesis", "dsl_operations": ["random_effects_pool"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["study_level_effect_estimates"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "We used the effect size combination method, specifically the random effects model (REM) and default settings for the integration of differential gene expression."}}, {"id": "method-2", "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": "PPI"}}], "targets": [], "gaps": []}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": true, "required_operations": ["random_effects_pool"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_effects."}, "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": ["GSE24206", "GSE21369", "GSE110147", "GSE72073", "GSE32539"], "resolved_accessions": ["GSE24206", "GSE21369", "GSE110147", "GSE72073", "GSE32539"], "statements": ["Publicly available microarray datasets were analyzed in this study. These microarray datasets can be found in the GEO database (https://www.ncbi.nlm.nih.gov/geo/, accessed on 2 September 2022) with accession numbers GSE24206, GSE21369, GSE110147, GSE72073, and GSE32539. All data generated or analyzed during this study are included in this published article and its supplementary information files."], "basis": "The paper names GSE24206, GSE21369, GSE110147, GSE72073, GSE32539 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": ["random_effects_pool"], "assets": ["source:pmid:37887075", "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": "2026-11-01T18:57:14Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14593, "completion_tokens": 1787, "cached_tokens": 264}}, "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:37887075", "type": "paper", "label": "pmid:37887075"}, {"id": "source:pmid:37887075", "type": "manuscript", "label": "PMID 37887075 full text"}, {"id": "data:geo:GSE110147", "type": "dataset", "label": "GEO GSE110147"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:37887075", "type": "paper", "label": "pmid:37887075"}, {"id": "source:pmid:37887075", "type": "manuscript", "label": "PMID 37887075 full text"}, {"id": "data:geo:GSE110147", "type": "dataset", "label": "GEO GSE110147"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-37887075", "type": "extraction", "used": ["source:pmid:37887075"], "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:37887075", "parent_hash": "sha256:ca2d7b6de1dd2bd8c93837d847bcd47b855be67991e521728a9478b830f29f7d", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE110147 licence not read", "asset:data:geo:GSE110147 not downloaded", "asset:data:geo:GSE21369 licence not read", "asset:data:geo:GSE21369 not downloaded", "asset:data:geo:GSE24206 licence not read", "asset:data:geo:GSE24206 not downloaded", "asset:data:geo:GSE32539 licence not read", "asset:data:geo:GSE32539 not downloaded", "asset:data:geo:GSE72073 licence not read", "asset:data:geo:GSE72073 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["atients' progression in lung cancer. METHOD: Microarray datasets GSE24206, GSE21369, GSE110147, GSE7", "CONCLUSIONS: Based on the integration of GEO microarray datasets, the present study identified DEGs"], "order_basis": "paper_text_order:743", "id": "assay:1"}, {"role": "analysis", "definition_id": "meta_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["random_effects_pool"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["We used the effect size combination method, specifically the random effects model (REM) and default settings for the integration of differential gene expression."], "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":"2026-11-04T02:50:07+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}}}