{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:39935835", "kind": "science-record", "revision": 3, "content_hash": "sha256:d47aa3481cfae41513333b1ccab6738c37cce90e2ed706b0997c23a72cec55ed", "created_at": "2026-11-01T20:30:12Z", "updated_at": "2026-11-01T22:13:39Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Vitamin A family suppresses periodontitis by restoring mitochondrial metabolic reprogramming in macrophages through JAK-STAT pathway.", "doi": "10.3389/fgene.2025.1505933", "pmid": "39935835", "authors": ["Zishuo Cheng", "Shun Huang", "Qiya Tang", "Danlan Zhang", "Lan Huang"], "journal": "Frontiers in genetics", "year": 2025, "abstract": "Objective: Mitochondrial metabolic reprogramming in macrophages is crucial in the development and progression of inflammation. Given vitamin A's antioxidant properties and its therapeutic effects on inflammation, this study aims to elucidate how vitamin A influences mitochondrial metabolic reprogramming in inflammatory states, specifically in periodontitis, through genetic bioinformatics and experimental methods.\nMethod: The study utilized the GSE16134 dataset from the Gene Expression Omnibus (GEO) database, focusing on human periodontitis. Vitamin A-targeted genes (ATGs) were identified and analyzed using CIBERSORT to explore their role in inflammation. Cluster analysis revealed two phenotypes associated with ATGs, showing differential expression of genes like COX1, IL-1β, and STAT3, and immune activation patterns. Weighted Gene Co-expression Network Analysis (WGCNA) identified 145 markers correlated with ATG-guided phenotypes and inflammation. Machine learning models, combined with Gene Set Variation Analysis (GSVA), identified five key genes (RGS1, ACAT2, KDR, TUBB2A, TDO2) linked to periodontitis. Cell Type-Specific Enrichment Analysis (CSEA) highlighted macrophages as critical in metabolic reprogramming, validated by external datasets with an AUC of 0.856 in GSE10334 and 0.750 in GSE1730678. Experimental validation showed vitamin A's role in suppressing endoplasmic reticulum stress and altering mitochondrial dynamics, as well as metabolic reprogramming influencing inflammation via the STAT3 pathway in RAW 264.7 cells.\nResults: The study identified 13 differentially expressed ATGs in periodontitis, showing strong correlations with inflammation, particularly in plasma cells, macrophages, dendritic cells, neutrophils, and mast cells. Two ATG-guided phenotypes were identified, differing in gene expression and immune activation. WGCNA and machine learning models identified 145 markers and five key genes associated with periodontitis. GSVA and CSEA analyses highlighted the JAK-STAT pathway and macrophage involvement in metabolic reprogramming. Experimental data confirmed vitamin A's effects on mitochondrial dynamics and metabolic reprogramming through the STAT3 pathway.\nConclusion: The study demonstrates that vitamin A's therapeutic effect on periodontitis is mediated through JAK-STAT pathway-guided mitochondrial metabolic reprogramming in macrophages. It identifies two genetic and immune-related phenotypes and five genetic identifiers associated with periodontitis risk.", "claims": [{"id": "claim-method", "statement": "To identify co-expression modules, Weighted Gene Co-expression Network Analysis (WGCNA) was conducted using the “WGCNA” R package (version 1.70.3) (Langfelder and Horvath, 2008).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39935835", "locator": "sections[7] \"2.5 Weighted gene co-expression network analysis (WGCNA)\" paragraph 2", "quote": "To identify co-expression modules, Weighted Gene Co-expression Network Analysis (WGCNA) was conducted using the “WGCNA” R package (version 1.70.3) (Langfelder and Horvath, 2008)."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:39935835", "locator": "sections[27] \"Data availability statement\" paragraph 2", "quote": "The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "partial", "objective": null, "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:39935835"], "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:GSE10334"], "outputs": ["the source data with its repository provenance"], "instruments": [], "reagents": []}, {"id": "run_analysis", "order": 3, "name": "Run the published analysis", "kind": "analysis", "state": "blocked", "blocked_on": "method:machine_learning_random_forest", "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:GSE10334"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": ["step:run_analysis blocked on method:machine_learning_random_forest"]}, "data": {"state": "partial", "assets": [{"id": "source:pmid:39935835", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.3389/fgene.2025.1505933", "sha256": "sha256:a642451ac84e6e27e786eda74341e90124d4a54fd91c34c4a4942b03edb90ae3", "bytes": 72383, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.3389/fgene.2025.1505933", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11810908", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE10334", "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=GSE10334", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE10334", "version": null, "note": "The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM261086", "GSM261087", "GSM261088", "GSM261089", "GSM261090", "GSM261091", "GSM261092", "GSM261093", "GSM261094", "GSM261095", "GSM261096", "GSM261097", "GSM261098", "GSM261099", "GSM261100", "GSM261101", "GSM261102", "GSM261103", "GSM261104", "GSM261105", "GSM261106", "GSM261107", "GSM261108", "GSM261109", "GSM261110", "GSM261111", "GSM261112", "GSM261113", "GSM261114", "GSM261115", "GSM261116", "GSM261117", "GSM261118", "GSM261119", "GSM261120", "GSM261121", "GSM261122", "GSM261123", "GSM261124", "GSM261125", "GSM261126", "GSM261127", "GSM261128", "GSM261129", "GSM261130", "GSM261131", "GSM261132", "GSM261133", "GSM261134", "GSM261135", "GSM261136", "GSM261137", "GSM261138", "GSM261139", "GSM261140", "GSM261141", "GSM261142", "GSM261143", "GSM261144", "GSM261145", "GSM261146", "GSM261147", "GSM261148", "GSM261149", "GSM261150", "GSM261151", "GSM261152", "GSM261153", "GSM261154", "GSM261155", "GSM261156", "GSM261157", "GSM261158", "GSM261159", "GSM261160", "GSM261161", "GSM261162", "GSM261163", "GSM261164", "GSM261165", "GSM261166", "GSM261167", "GSM261168", "GSM261169", "GSM261170", "GSM261171", "GSM261172", "GSM261173", "GSM261174", "GSM261175", "GSM261176", "GSM261177", "GSM261178", "GSM261179", "GSM261180", "GSM261181", "GSM261182", "GSM261183", "GSM261184", "GSM261185", "GSM261186", "GSM261187", "GSM261188", "GSM261189", "GSM261190", "GSM261191", "GSM261192", "GSM261193", "GSM261194", "GSM261195", "GSM261196", "GSM261197", "GSM261198", "GSM261199", "GSM261200", "GSM261201", "GSM261202", "GSM261203", "GSM261204", "GSM261205", "GSM261206", "GSM261207", "GSM261208", "GSM261209", "GSM261210", "GSM261211", "GSM261212", "GSM261213", "GSM261214", "GSM261215", "GSM261216", "GSM261217", "GSM261218", "GSM261219", "GSM261220", "GSM261221", "GSM261222", "GSM261223", "GSM261224", "GSM261225", "GSM261226", "GSM261227", "GSM261228", "GSM261229", "GSM261230", "GSM261231", "GSM261232", "GSM261233", "GSM261234", "GSM261235", "GSM261236", "GSM261237", "GSM261238", "GSM261239", "GSM261240", "GSM261241", "GSM261242", "GSM261243", "GSM261244", "GSM261245", "GSM261246", "GSM261247", "GSM261248", "GSM261249", "GSM261250", "GSM261251", "GSM261252", "GSM261253", "GSM261254", "GSM261255", "GSM261256", "GSM261257", "GSM261258", "GSM261259", "GSM261260", "GSM261261", "GSM261262", "GSM261263", "GSM261264", "GSM261265", "GSM261266", "GSM261267", "GSM261268", "GSM261269", "GSM261270", "GSM261271", "GSM261272", "GSM261273", "GSM261274", "GSM261275", "GSM261276", "GSM261277", "GSM261278", "GSM261279", "GSM261280", "GSM261281", "GSM261282", "GSM261283", "GSM261284", "GSM261285", "GSM261286", "GSM261287", "GSM261288", "GSM261289", "GSM261290", "GSM261291", "GSM261292", "GSM261293", "GSM261294", "GSM261295", "GSM261296", "GSM261297", "GSM261298", "GSM261299", "GSM261300", "GSM261301", "GSM261302", "GSM261303", "GSM261304", "GSM261305", "GSM261306", "GSM261307", "GSM261308", "GSM261309", "GSM261310", "GSM261311", "GSM261312", "GSM261313", "GSM261314", "GSM261315", "GSM261316", "GSM261317", "GSM261318", "GSM261319", "GSM261320", "GSM261321", "GSM261322", "GSM261323", "GSM261324", "GSM261325", "GSM261326", "GSM261327", "GSM261328", "GSM261329", "GSM261330", "GSM261331", "GSM261332"], "sample_count": 247, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Transcriptomes in Healthy and Diseased Gingival Tissues", "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:GSE16134", "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=GSE16134", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE16134", "version": null, "note": "The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM404005", "GSM404006", "GSM404007", "GSM404008", "GSM404009", "GSM404010", "GSM404011", "GSM404012", "GSM404013", "GSM404014", "GSM404015", "GSM404016", "GSM404017", "GSM404018", "GSM404019", "GSM404020", "GSM404021", "GSM404022", "GSM404023", "GSM404024", "GSM404025", "GSM404026", "GSM404027", "GSM404028", "GSM404029", "GSM404030", "GSM404031", "GSM404032", "GSM404033", "GSM404034", "GSM404035", "GSM404036", "GSM404037", "GSM404038", "GSM404039", "GSM404040", "GSM404041", "GSM404042", "GSM404043", "GSM404044", "GSM404045", "GSM404046", "GSM404047", "GSM404048", "GSM404049", "GSM404050", "GSM404051", "GSM404052", "GSM404053", "GSM404054", "GSM404055", "GSM404056", "GSM404057", "GSM404058", "GSM404059", "GSM404060", "GSM404061", "GSM404062", "GSM404063", "GSM404064", "GSM404065", "GSM404066", "GSM404067", "GSM404068", "GSM404069", "GSM404070", "GSM404071", "GSM404072", "GSM404073", "GSM404074", "GSM404075", "GSM404076", "GSM404077", "GSM404078", "GSM404079", "GSM404080", "GSM404081", "GSM404082", "GSM404083", "GSM404084", "GSM404085", "GSM404086", "GSM404087", "GSM404088", "GSM404089", "GSM404090", "GSM404091", "GSM404092", "GSM404093", "GSM404094", "GSM404095", "GSM404096", "GSM404097", "GSM404098", "GSM404099", "GSM404100", "GSM404101", "GSM404102", "GSM404103", "GSM404104", "GSM404105", "GSM404106", "GSM404107", "GSM404108", "GSM404109", "GSM404110", "GSM404111", "GSM404112", "GSM404113", "GSM404114", "GSM404115", "GSM404116", "GSM404117", "GSM404118", "GSM404119", "GSM404120", "GSM404121", "GSM404122", "GSM404123", "GSM404124", "GSM404125", "GSM404126", "GSM404127", "GSM404128", "GSM404129", "GSM404130", "GSM404131", "GSM404132", "GSM404133", "GSM404134", "GSM404135", "GSM404136", "GSM404137", "GSM404138", "GSM404139", "GSM404140", "GSM404141", "GSM404142", "GSM404143", "GSM404144", "GSM404145", "GSM404146", "GSM404147", "GSM404148", "GSM404149", "GSM404150", "GSM404151", "GSM404152", "GSM404153", "GSM404154", "GSM404155", "GSM404156", "GSM404157", "GSM404158", "GSM404159", "GSM404160", "GSM404161", "GSM404162", "GSM404163", "GSM404164", "GSM404165", "GSM404166", "GSM404167", "GSM404168", "GSM404169", "GSM404170", "GSM404171", "GSM404172", "GSM404173", "GSM404174", "GSM404175", "GSM404176", "GSM404177", "GSM404178", "GSM404179", "GSM404180", "GSM404181", "GSM404182", "GSM404183", "GSM404184", "GSM404185", "GSM404186", "GSM404187", "GSM404188", "GSM404189", "GSM404190", "GSM404191", "GSM404192", "GSM404193", "GSM404194", "GSM404195", "GSM404196", "GSM404197", "GSM404198", "GSM404199", "GSM404200", "GSM404201", "GSM404202", "GSM404203", "GSM404204", "GSM404205", "GSM404206", "GSM404207", "GSM404208", "GSM404209", "GSM404210", "GSM404211", "GSM404212", "GSM404213", "GSM404214", "GSM404215", "GSM404216", "GSM404217", "GSM404218", "GSM404219", "GSM404220", "GSM404221", "GSM404222", "GSM404223", "GSM404224", "GSM404225", "GSM404226", "GSM404227", "GSM404228", "GSM404229", "GSM404230", "GSM404231", "GSM404232", "GSM404233", "GSM404234", "GSM404235", "GSM404236", "GSM404237", "GSM404238", "GSM404239", "GSM404240", "GSM404241", "GSM404242", "GSM404243", "GSM404244", "GSM404245", "GSM404246", "GSM404247", "GSM404248", "GSM404249", "GSM404250", "GSM404251", "GSM404252", "GSM404253", "GSM404254", "GSM404255", "GSM404256", "GSM404257", "GSM404258", "GSM404259", "GSM404260", "GSM404261", "GSM404262", "GSM404263", "GSM404264", "GSM404265", "GSM404266", "GSM404267", "GSM404268", "GSM404269", "GSM404270", "GSM404271", "GSM404272", "GSM404273", "GSM404274", "GSM404275", "GSM404276", "GSM404277", "GSM404278", "GSM404279", "GSM404280", "GSM404281", "GSM404282", "GSM404283", "GSM404284", "GSM404285", "GSM404286", "GSM404287", "GSM404288", "GSM404289", "GSM404290", "GSM404291", "GSM404292", "GSM404293", "GSM404294", "GSM404295", "GSM404296", "GSM404297", "GSM404298", "GSM404299", "GSM404300", "GSM404301", "GSM404302", "GSM404303", "GSM404304", "GSM404305", "GSM404306", "GSM404307", "GSM404308", "GSM404309", "GSM404310", "GSM404311", "GSM404312", "GSM404313", "GSM404314"], "sample_count": 310, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Bacterial Correlates of Gingival Gene Expression", "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:GSE173078", "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=GSE173078", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE173078", "version": null, "note": "The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM5259431", "GSM5259432", "GSM5259433", "GSM5259434", "GSM5259435", "GSM5259436", "GSM5259437", "GSM5259438", "GSM5259439", "GSM5259440", "GSM5259441", "GSM5259442", "GSM5259443", "GSM5259444", "GSM5259445", "GSM5259446", "GSM5259447", "GSM5259448", "GSM5259449", "GSM5259450", "GSM5259451", "GSM5259452", "GSM5259453", "GSM5259454", "GSM5259455", "GSM5259456", "GSM5259457", "GSM5259458", "GSM5259459", "GSM5259460", "GSM5259461", "GSM5259462", "GSM5259463", "GSM5259464", "GSM5259465", "GSM5259466"], "sample_count": 36, "group_sizes": null, "group_sizes_basis": null, "platform": "20301", "taxon": "Homo sapiens", "title": "Differential mRNA transcription in gingival tissues in periodontal health and disease [RNA-seq]", "resolution_checked_at": "2026-11-01T18:06:43Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE10334 not downloaded", "asset:data:geo:GSE10334 licence not read", "asset:data:geo:GSE16134 not downloaded", "asset:data:geo:GSE16134 licence not read", "asset:data:geo:GSE173078 not downloaded", "asset:data:geo:GSE173078 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "family": "machine_learning", "specific": "random_forest", "label": "Machine learning", "dsl_operations": [], "missing_operations": ["machine_learning_random_forest"], "expressible": false, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "random forest"}}, {"id": "method-2", "family": "machine_learning", "specific": "support_vector_machine", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "support vector machine"}}, {"id": "method-3", "family": "machine_learning", "specific": "gradient_boosting", "label": "Machine learning", "dsl_operations": ["train_classifier", "cross_validate", "roc_auc"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["labelled_feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "Gradient Boosting"}}, {"id": "method-4", "family": "regression_modelling", "specific": "ols", "label": "Regression modelling", "dsl_operations": ["ols_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictors_and_outcome"], "evidence": {"score": 0.8, "band": "high", "quote": "linear regression"}}, {"id": "method-5", "family": "clustering", "specific": "kmeans", "label": "Clustering", "dsl_operations": ["kmeans_fit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["feature_matrix"], "evidence": {"score": 0.8, "band": "high", "quote": "k-means"}}, {"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": "model_calibration", "specific": "decision_curve", "label": "Model calibration / clinical utility", "dsl_operations": ["calibration_bins", "net_benefit"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["predictions_and_outcomes"], "evidence": {"score": 0.8, "band": "high", "quote": "decision curve analysis"}}, {"id": "method-8", "family": null, "specific": null, "label": "Weighted Gene Co-expression Network Analysis (WGCNA)", "dsl_operations": [], "missing_operations": [], "expressible": null, "parameters": {}, "data_shapes": [], "evidence": {"score": 1.0, "band": "verbatim", "quote": "To identify co-expression modules, Weighted Gene Co-expression Network Analysis (WGCNA) was conducted using the “WGCNA” R package (version 1.70.3) (Langfelder and Horvath, 2008)."}}], "targets": [], "gaps": ["method.reader_named_unmapped", "method.machine_learning_random_forest"]}, "capability": {"state": "complete", "requirements": [{"capability_id": "capability:computational_analysis", "label": "Computational analysis platform", "assay_families": ["meta_analysis", "machine_learning", "survival_analysis", "statistical_regression", "pca", "molecular_docking", "network_analysis", "differential_expression", "gwas"], "availability_state": "owned", "tier_unlocked": "R1", "candidate": "Automated Assays Laravel application and simulated adapters"}], "gaps": []}, "readiness": {"state": "complete", "tier": "R1", "blocking_axis": "none", "blocked_on": "nothing:replicable_now", "axes": {"method": {"tier": "R1", "expressible": false, "required_operations": [], "missing_operations": ["machine_learning_random_forest"], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: random_forest."}, "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": ["GSE16134", "GSE10334", "GSE173078"], "resolved_accessions": ["GSE16134", "GSE10334", "GSE173078"], "statements": ["The data presented in the study are deposited in the Gene Expression Omnibus repository, accession numbers GSE16134, GSE173078, GSE10334."], "basis": "The paper names GSE16134, GSE10334, GSE173078 in Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": [], "assets": ["source:pmid:39935835", "data:geo:GSE10334"], "steps": []}, "must_build": {"dsl_operations": [{"operation": "machine_learning_random_forest", "unlocks_papers": null, "priority": null}], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE10334"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:46:15Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 18249, "completion_tokens": 2002, "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:39935835", "type": "paper", "label": "pmid:39935835"}, {"id": "source:pmid:39935835", "type": "manuscript", "label": "PMID 39935835 full text"}, {"id": "data:geo:GSE10334", "type": "dataset", "label": "GEO GSE10334"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:39935835", "type": "paper", "label": "pmid:39935835"}, {"id": "source:pmid:39935835", "type": "manuscript", "label": "PMID 39935835 full text"}, {"id": "data:geo:GSE10334", "type": "dataset", "label": "GEO GSE10334"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-39935835", "type": "extraction", "used": ["source:pmid:39935835"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE10334", "type": "accession_resolution", "used": ["data:geo:GSE10334"], "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:39935835", "parent_hash": "sha256:5a758e852be53c278d5fd9c4d72234556915f2d1a0aec2ef3d4eb7f92e961534", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE10334 licence not read", "asset:data:geo:GSE10334 not downloaded", "asset:data:geo:GSE16134 licence not read", "asset:data:geo:GSE16134 not downloaded", "asset:data:geo:GSE173078 licence not read", "asset:data:geo:GSE173078 not downloaded", "execution.not_run", "method.machine_learning_random_forest", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique", "step:run_analysis blocked on method:machine_learning_random_forest"], "assays": [{"role": "analysis", "definition_id": "machine_learning", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["random forest"], "order_basis": "analysis_only", "id": "assay:1"}]},"meta":{"api_version":"v1","automation_ladder_snapshot":"ba34b49490d9bfaf","automation_ladder_caveats":["Method extraction is rule-based and has no hand-judged accuracy sample. Evidence bands order textual support; method agreement intervals are null (n=0), never probabilities. Work-type validation does not validate methods.","Operation coverage describes only explicitly named methods. It does not prove a complete protocol, compatible parameters, successful compilation or re-execution. Unrecognised or ambiguous methods require review.","Data reachability is a textual accession or public-data statement. No dataset was downloaded or checked for access, completeness or licence.","Capabilities are planning states seeded from the dated equipment register. No bench ownership, completed quote or partner booking is inferred. Procurement counts are dependencies, not guaranteed replications or financial returns.","Tier and blocker counts are deterministic assessments of this corpus, not measured agreement. R3 is reserved for procurement; unresolved methods and data require human work (R4). The most restrictive axis wins, with capability, method, data as tie-breaks. Resolving one blocker can leave another at the same tier."],"engine":"corpus_engine","engine_provider":"rule_based_v1+lex99e1195c7d6f","run_id":"run-20261023T122449232913","source":"esearch","source_detail":"PubMed mirror biomed_pubmed (read-only)","run_status":"complete","imported_at":"2026-11-03T20:16:52+00:00","generated_at":"2026-11-04T01:34:41+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}}}