{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:41013556", "kind": "science-record", "revision": 3, "content_hash": "sha256:a6ed1cedc69963a110eb927f22d9a60815c37dd020133701bd67042ea2df2d4a", "created_at": "2026-11-01T20:31:05Z", "updated_at": "2026-11-01T22:14:45Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Identification of hub gene and immune infiltration in Lyme disease revealed by weighted gene co-expression network analysis and machine learning.", "doi": "10.1186/s40001-025-03108-y", "pmid": "41013556", "authors": ["Yan Dong", "Meng Liu", "Yanshuang Luo", "Yantong Chen", "Xuesong Chen", "Xiaorong Liu", "Xingbo Cai", "Fusong Yang", "Chao Song", "Guozhong Zhou"], "journal": "European journal of medical research", "year": 2025, "abstract": "INTRODUCTION: Lyme disease (LD), caused by the spirochete Borrelia burgdorferi (Bb), is a multisystem disorder with early symptoms such as erythema migrans and late manifestations including arthritis and neuroborreliosis. The molecular mechanisms driving tissue damage and inflammatory dysregulation in LD remain incompletely characterized. Given the central role of peripheral blood mononuclear cells (PBMCs) in orchestrating immune responses, we aimed to identify optimal feature genes (OFGs) within PBMCs associated with LD pathogenesis and delineate their immune infiltration patterns using integrated bioinformatics.\nMETHODS: Transcriptomic datasets (GSE42606, GSE68765, GSE103481) were retrieved from GEO. Differential expression analysis identified LD-related genes. Weighted Gene Co-expression Network Analysis (WGCNA) screened disease-associated modules. Feature selection was performed via SVM-Recursive Feature Elimination (SVM-RFE), Least absolute shrinkage and selection operator (LASSO) regression, and random forest (RF) to pinpoint OFGs. Immune cell infiltration was quantified using CIBERSORT, followed by correlation analysis between OFGs and immune subsets. The Single-gene gene set enrichment analysis (GSEA) was performed to explore the functional associations of OFGs. Biological pathways linked to OFGs were inferred by single-sample GSEA (ssGSEA). Diagnostic utility was assessed via ROC curves and nomogram modeling. Finally, we used RT-qPCR to confirm the bioinformatics results.\nRESULTS: Our study identified 174 DEGs among the LD patients, with 156 genes located within the \"turquoise\" module by WGCNA, exhibiting the most robust correlation with clinical characteristics. Among these, KIAA1199 turned out to be the unique OFG, selected via three distinct machine learning methodologies, possessing exceptional diagnostic potential. The Single-gene gene set enrichment analysis showed KIAA1199 was strongly correlated with multiple immune-related pathways. Furthermore, RT-qPCR validated candidate gene expression within a THP-1 cellular model.\nCONCLUSION: In conclusion, this study integrated WGCNA and machine learning methodologies to identify one core gene associated with LD from PBMC gene expression data: KIAA1199. The predictive model constructed using these genes demonstrated robust diagnostic accuracy, providing a basis for further research on host immune responses and the development of new diagnostic methods.", "claims": [{"id": "claim-method", "statement": "Co-expression network analysis was established with the “WGCNA” R package [20] based on the gene expression data profiles of 83 PBMC samples from GSE42606 and GSE68765.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41013556", "locator": "sections[7] \"Weighted gene co-expression network analysis (WGCNA)\" paragraph 2", "quote": "Co-expression network analysis was established with the “WGCNA” R package [20] based on the gene expression data profiles of 83 PBMC samples from GSE42606 and GSE68765."}], "state": "complete"}, {"id": "claim-data-access", "statement": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:41013556", "locator": "sections[33] \"Data availability\" paragraph 2", "quote": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "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:41013556"], "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:GSE103481"], "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:GSE103481"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:41013556", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1186/s40001-025-03108-y", "sha256": "sha256:228c894805650061dbb84065fff09b99faeef34f9505dc500c951e2e190f67e2", "bytes": 48930, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1186/s40001-025-03108-y", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC12465215", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE103481", "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=GSE103481", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE103481", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM2772280", "GSM2772281", "GSM2772282", "GSM2772283", "GSM2772284", "GSM2772285"], "sample_count": 6, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "A multi-omic analysis reveals a regulatory role of CD180 during the response of macrophages to Borrelia burgdorferi [microarray]", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE42606", "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=GSE42606", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42606", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1046499", "GSM1046500", "GSM1046501", "GSM1046502", "GSM1046503", "GSM1046504", "GSM1046505", "GSM1046506", "GSM1046507", "GSM1046508", "GSM1046509", "GSM1046510", "GSM1046511", "GSM1046512", "GSM1046513", "GSM1046514", "GSM1046515", "GSM1046516", "GSM1046517", "GSM1046518", "GSM1046519", "GSM1046520", "GSM1046521", "GSM1046522", "GSM1046523", "GSM1046524", "GSM1046525", "GSM1046526", "GSM1046527", "GSM1046528", "GSM1046529", "GSM1046530", "GSM1046531", "GSM1046532", "GSM1046533", "GSM1046534", "GSM1046535", "GSM1046536", "GSM1046537", "GSM1046538", "GSM1046539", "GSM1046540", "GSM1046541", "GSM1046542", "GSM1046543", "GSM1046544", "GSM1046545", "GSM1046546", "GSM1046547", "GSM1046548", "GSM1046549", "GSM1046550", "GSM1046551", "GSM1046552", "GSM1046553", "GSM1046554", "GSM1046555", "GSM1046556", "GSM1046557", "GSM1046558", "GSM1046559", "GSM1046560", "GSM1046561", "GSM1046562", "GSM1046563", "GSM1046564", "GSM1046565", "GSM1046566", "GSM1046567", "GSM1046568", "GSM1046569", "GSM1046570", "GSM1046571", "GSM1046572", "GSM1046573", "GSM1046574", "GSM1046575", "GSM1046576", "GSM1046577", "GSM1046578", "GSM1046579", "GSM1046580", "GSM1046581", "GSM1046582", "GSM1046583", "GSM1046584", "GSM1046585", "GSM1046586", "GSM1046587", "GSM1046588", "GSM1046589", "GSM1046590", "GSM1046591", "GSM1046592", "GSM1046593", "GSM1046594", "GSM1046595", "GSM1046596", "GSM1046597", "GSM1046598", "GSM1046599", "GSM1046600", "GSM1046601", "GSM1046602", "GSM1046603", "GSM1046604", "GSM1046605", "GSM1046606", "GSM1046607", "GSM1046608", "GSM1046609", "GSM1046610", "GSM1046611", "GSM1046612", "GSM1046613", "GSM1046614", "GSM1046615", "GSM1046616", "GSM1046617", "GSM1046618", "GSM1046619", "GSM1046620", "GSM1046621", "GSM1046622", "GSM1046623", "GSM1046624", "GSM1046625", "GSM1046626", "GSM1046627", "GSM1046628", "GSM1046629", "GSM1046630", "GSM1046631", "GSM1046632", "GSM1046633", "GSM1046634", "GSM1046635", "GSM1046636", "GSM1046637", "GSM1046638", "GSM1046639", "GSM1046640", "GSM1046641", "GSM1046642", "GSM1046643", "GSM1046644", "GSM1046645", "GSM1046646", "GSM1046647", "GSM1046648", "GSM1046649", "GSM1046650", "GSM1046651", "GSM1046652", "GSM1046653", "GSM1046654", "GSM1046655", "GSM1046656", "GSM1046657", "GSM1046658", "GSM1046659", "GSM1046660", "GSM1046661", "GSM1046662", "GSM1046663", "GSM1046664", "GSM1046665", "GSM1046666", "GSM1046667", "GSM1046668", "GSM1046669", "GSM1046670", "GSM1046671", "GSM1046672", "GSM1046673", "GSM1046674", "GSM1046675", "GSM1046676", "GSM1046677", "GSM1046678", "GSM1046679", "GSM1046680", "GSM1046681", "GSM1046682", "GSM1046683", "GSM1046684", "GSM1046685", "GSM1046686", "GSM1046687", "GSM1046688", "GSM1046689", "GSM1046690", "GSM1046691", "GSM1046692", "GSM1046693", "GSM1046694", "GSM1046695", "GSM1046696", "GSM1046697", "GSM1046698", "GSM1046699", "GSM1046701", "GSM1046703", "GSM1046705", "GSM1046706", "GSM1046708", "GSM1046709", "GSM1046711", "GSM1046712", "GSM1046713", "GSM1046715", "GSM1046716", "GSM1046718", "GSM1046719", "GSM1046721", "GSM1046722", "GSM1046724", "GSM1046726", "GSM1046727", "GSM1046729", "GSM1046731", "GSM1046732", "GSM1046734", "GSM1046735", "GSM1046737", "GSM1046739", "GSM1046740", "GSM1046742", "GSM1046743", "GSM1046745", "GSM1046746", "GSM1046748", "GSM1046750", "GSM1046751", "GSM1046753", "GSM1046754", "GSM1046756", "GSM1046758", "GSM1046759", "GSM1046760", "GSM1046762", "GSM1046763", "GSM1046764", "GSM1046765", "GSM1046767", "GSM1046768", "GSM1046770", "GSM1046771", "GSM1046772", "GSM1046773", "GSM1046775", "GSM1046776", "GSM1046777", "GSM1046779", "GSM1046780", "GSM1046782", "GSM1046783", "GSM1046785", "GSM1046786", "GSM1046787", "GSM1046788", "GSM1046789", "GSM1046790", "GSM1046791", "GSM1046792", "GSM1046793", "GSM1046794", "GSM1046795", "GSM1046796", "GSM1046797", "GSM1046798", "GSM1046799", "GSM1046800", "GSM1046801", "GSM1046802", "GSM1046803", "GSM1046804", "GSM1046805", "GSM1046806", "GSM1046807", "GSM1046808", "GSM1046809", "GSM1046810", "GSM1046811", "GSM1046812", "GSM1046813", "GSM1046814", "GSM1046815", "GSM1046816", "GSM1046817", "GSM1046818", "GSM1046819", "GSM1046820", "GSM1046821", "GSM1046822", "GSM1046823", "GSM1046824", "GSM1046825", "GSM1046826"], "sample_count": 299, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Genome-wide transcriptional profiling of human PBMCs stimulated with Candida albicans and non-fungal inflammatory stimuli", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE68765", "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=GSE68765", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE68765", "version": null, "note": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article.", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1680911", "GSM1680912", "GSM1680913", "GSM1680914", "GSM1680915", "GSM1680916", "GSM1680917", "GSM1680918", "GSM1680919", "GSM1680920", "GSM1680921", "GSM1680922", "GSM1680923", "GSM1680924", "GSM1680925", "GSM1680926", "GSM1680927", "GSM1680928", "GSM1680929", "GSM1680930", "GSM1680931", "GSM1680932", "GSM1680933", "GSM1680934"], "sample_count": 24, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Expression analysis of human PBMCs stimulated with Borrelia, MDP or Pam3cys.", "resolution_checked_at": "2026-11-01T20:16:08Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}], "gaps": ["asset:data:geo:GSE103481 not downloaded", "asset:data:geo:GSE103481 licence not read", "asset:data:geo:GSE42606 not downloaded", "asset:data:geo:GSE42606 licence not read", "asset:data:geo:GSE68765 not downloaded", "asset:data:geo:GSE68765 licence not read"]}, "analysis": {"state": "partial", "methods": [{"id": "method-1", "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-2", "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": 0.7, "band": "medium", "quote": "random forest"}}, {"id": "method-3", "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": 0.7, "band": "medium", "quote": "SVM"}}, {"id": "method-4", "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-5", "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": "Co-expression network analysis was established with the “WGCNA” R package [20] based on the gene expression data profiles of 83 PBMC samples from GSE42606 and GSE68765."}}], "targets": [], "gaps": ["method.reader_named_unmapped"]}, "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": ["pca_fit"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: pca."}, "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": ["GSE42606", "GSE68765", "GSE103481"], "resolved_accessions": ["GSE42606", "GSE68765", "GSE103481"], "statements": ["The datasets presented in this study can be found in online repositories. The names of the repository/repositories and accession number(s) can be found in the article."], "basis": "The paper names GSE42606, GSE68765, GSE103481 in Gene Expression Omnibus (GEO, http://www.ncbi.nlm.nih.gov/geo) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["pca_fit"], "assets": ["source:pmid:41013556", "data:geo:GSE103481"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE103481"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T20:02:03Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 14037, "completion_tokens": 1946, "cached_tokens": 256}}, "human_critique": null, "stages": [{"id": "extraction", "state": "complete", "reader": "MiniMax-M3.1-Flash", "provider": "minimax"}], "gaps": ["review.independent_reader", "review.machine_critique", "review.human_critique"]}, "execution": {"state": "absent", "status": "not_run", "mode": null, "runs": [], "gaps": ["execution.not_run"]}, "provenance": {"entities": [{"id": "pmid:41013556", "type": "paper", "label": "pmid:41013556"}, {"id": "source:pmid:41013556", "type": "manuscript", "label": "PMID 41013556 full text"}, {"id": "data:geo:GSE103481", "type": "dataset", "label": "GEO GSE103481"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:41013556", "type": "paper", "label": "pmid:41013556"}, {"id": "source:pmid:41013556", "type": "manuscript", "label": "PMID 41013556 full text"}, {"id": "data:geo:GSE103481", "type": "dataset", "label": "GEO GSE103481"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-41013556", "type": "extraction", "used": ["source:pmid:41013556"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE103481", "type": "accession_resolution", "used": ["data:geo:GSE103481"], "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:41013556", "parent_hash": "sha256:80e4199c60cd79631d843752e912ffaac11de359d46705bd39977635518e0bbe", "fork_of": null, "generation": 2}, "gaps": ["asset:data:geo:GSE103481 licence not read", "asset:data:geo:GSE103481 not downloaded", "asset:data:geo:GSE42606 licence not read", "asset:data:geo:GSE42606 not downloaded", "asset:data:geo:GSE68765 licence not read", "asset:data:geo:GSE68765 not downloaded", "execution.not_run", "method.reader_named_unmapped", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "qpcr", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.99, "evidence": ["rves and nomogram modeling. Finally, we used RT-qPCR to confirm the bioinformatics results. RESUL", "ltiple immune-related pathways. Furthermore, RT-qPCR validated candidate gene expression within a", "s and nomogram modeling. Finally, we used RT-qPCR to confirm the bioinformatics results. RESUL", "ple immune-related pathways. Furthermore, RT-qPCR validated candidate gene expression within a"], "order_basis": "paper_text_order:1560", "id": "assay:1"}, {"role": "data_generation", "definition_id": "apoptosis_assay", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.69, "evidence": ["ated NF-κB signaling, inflammatory response, apoptosis, and extracellular matrix remodeling, simult"], "order_basis": "paper_text_order:5965", "id": "assay:2"}, {"role": "analysis", "definition_id": "principal_component_analysis", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["pca_fit"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 0.8, "evidence": ["principal component 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":"2026-11-04T01:40:46+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}}}