{"data":{"sci_version": "1.2", "schema": "https://corpus.bntrg.co.uk/sci/1.0/sci.schema.json", "id": "pmid:38935691", "kind": "science-record", "revision": 4, "content_hash": "sha256:36ca77938c7ccda8457b3080aa7e3ba839bd5f7260d3e965770d132cd50acb75", "created_at": "2026-11-01T20:29:00Z", "updated_at": "2026-11-01T22:54:35Z", "generator": {"name": "corpus-assay-engine", "run_id": "reading-sci-2026-11-01"}, "paper": {"state": "complete", "title": "Computational reassessment of RNA-seq data reveals key genes in active tuberculosis.", "doi": "10.1371/journal.pone.0305582", "pmid": "38935691", "authors": ["Rakesh Arya", "Hemlata Shakya", "Reetika Chaurasia", "Surendra Kumar", "Joseph M Vinetz", "Jong Joo Kim"], "journal": "PloS one", "year": 2024, "abstract": "BACKGROUND: Tuberculosis is a serious life-threatening disease among the top global health challenges and rapid and effective diagnostic biomarkers are vital for early diagnosis especially given the increasing prevalence of multidrug resistance.\nMETHODS: Two human whole blood microarray datasets, GSE42826 and GSE42830 were retrieved from publicly available gene expression omnibus (GEO) database. Deregulated genes (DEGs) were identified using GEO2R online tool and Gene Ontology (GO), protein-protein interaction (PPI) network analysis was performed using Metascape and STRING databases. Significant genes (n = 8) were identified using T-test/ANOVA and Molecular Complex Detection (MCODE) score ≥10, which was validated in GSE34608 dataset. The diagnostic potential of three biomarkers was assessed using Area Under Curve (AUC) of Receiver Operating Characteristic (ROC) plot. The transcriptional levels of these genes were also examined in a separate dataset GSE31348, to monitor the patterns of variation during tuberculosis treatment.\nRESULTS: A total of 62 common DEGs (57 upregulated, 7 downregulated genes) were identified in two discovery datasets. GO functions and pathway enrichment analysis shed light on the functional roles of these DEGs in immune response and type-II interferon signaling. The genes in Module-1 (n = 18) were linked to innate immune response, interferon-gamma signaling. The common genes (n = 8) were validated in GSE34608 dataset, that corroborates the results obtained from discovery sets. The gene expression levels demonstrated responsiveness to Mtb infection during anti-TB therapy in GSE31348 dataset. In GSE34608 dataset, the expression levels of three specific genes, GBP5, IFITM3, and EPSTI1, emerged as potential diagnostic makers. In combination, these genes scored remarkable diagnostic performance with 100% sensitivity and 89% specificity, resulting in an impressive Area Under Curve (AUC) of 0.958. However, GBP5 alone showed the highest AUC of 0.986 with 100% sensitivity and 89% specificity.\nCONCLUSIONS: The study presents valuable insights into the critical gene network perturbed during tuberculosis. These genes are determinants for assessing the effectiveness of an anti-TB response and distinguishing between active TB and healthy individuals. GBP5, IFITM3 and EPSTI1 emerged as candidate core genes in TB and holds potential as novel molecular targets for the development of interventions in the treatment of TB.", "claims": [{"id": "claim-method", "statement": "The significant genes were selected based on two criteria of common top 8 proteins in the heatmap analysis by T-test/ANOVA in MetaboAnalyst and MCODE score ≥10.", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38935691", "locator": "sections[7] \"Validation of important genes and ROC analysis\" paragraph 2", "quote": "The significant genes were selected based on two criteria of common top 8 proteins in the heatmap analysis by T-test/ANOVA in MetaboAnalyst and MCODE score ≥10."}], "state": "complete"}, {"id": "claim-data-access", "statement": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "kind": "methodological", "target": null, "evidence": [{"asset": "source:pmid:38935691", "locator": "sections[18] \"Data Availability\" paragraph 2", "quote": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo)."}], "state": "complete"}, {"id": "claim-target-result", "statement": "GBP5 alone showed the highest AUC of 0.986 with 100% sensitivity and 89% specificity.", "kind": "quantitative", "target": {"value": 0.986, "unit": "auc", "tolerance": null, "source": "However, GBP5 alone showed the highest AUC of 0.986 with 100% sensitivity and 89% specificity."}, "evidence": [{"asset": "source:pmid:38935691", "locator": "sections[0] \"Abstract\" paragraph 3", "quote": "However, GBP5 alone showed the highest AUC of 0.986 with 100% sensitivity and 89% specificity."}], "state": "complete"}], "gaps": []}, "experiment": {"state": "complete", "objective": "GBP5 alone showed the highest AUC of 0.986 with 100% sensitivity and 89% specificity.", "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:38935691"], "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:GSE31348"], "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:GSE31348"], "outputs": ["the replicated result and its comparison"], "instruments": [], "reagents": []}], "materials": [], "instruments": [], "reagents": [], "conditions": {}, "gaps": []}, "data": {"state": "partial", "assets": [{"id": "source:pmid:38935691", "role": "manuscript", "format": "xml", "media_type": "application/xml", "uri": "https://doi.org/10.1371/journal.pone.0305582", "sha256": "sha256:2f1eabb483caecfee254056ded1b1715e3428eef93638e5320c474a1ee335c5f", "bytes": 45801, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "10.1371/journal.pone.0305582", "version": null, "note": "Full article fetched from PMC; the checksum covers the rendered section body, not the original XML bytes.", "structure": {"pmcid": "PMC11210783", "source": "europe_pmc_fulltext", "coverage": "whole_body", "text_hash_scope": "rendered_section_body"}}, {"id": "data:geo:GSE31348", "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=GSE31348", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE31348", "version": null, "note": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM777339", "GSM777340", "GSM777341", "GSM777342", "GSM777343", "GSM777344", "GSM777345", "GSM777346", "GSM777347", "GSM777348", "GSM777349", "GSM777350", "GSM777351", "GSM777352", "GSM777353", "GSM777354", "GSM777355", "GSM777356", "GSM777357", "GSM777358", "GSM777359", "GSM777360", "GSM777361", "GSM777362", "GSM777363", "GSM777364", "GSM777365", "GSM777366", "GSM777367", "GSM777368", "GSM777369", "GSM777370", "GSM777371", "GSM777372", "GSM777373", "GSM777374", "GSM777375", "GSM777376", "GSM777377", "GSM777378", "GSM777379", "GSM777380", "GSM777381", "GSM777382", "GSM777383", "GSM777384", "GSM777385", "GSM777386", "GSM777387", "GSM777388", "GSM777389", "GSM777390", "GSM777391", "GSM777392", "GSM777393", "GSM777394", "GSM777395", "GSM777396", "GSM777397", "GSM777398", "GSM777399", "GSM777400", "GSM777401", "GSM777402", "GSM777403", "GSM777404", "GSM777405", "GSM777406", "GSM777407", "GSM777408", "GSM777409", "GSM777410", "GSM777411", "GSM777412", "GSM777413", "GSM777414", "GSM777415", "GSM777416", "GSM777417", "GSM777418", "GSM777419", "GSM777420", "GSM777421", "GSM777422", "GSM777423", "GSM777424", "GSM777425", "GSM777426", "GSM777427", "GSM777428", "GSM777429", "GSM777430", "GSM777431", "GSM777432", "GSM777433", "GSM777434", "GSM777435", "GSM777436", "GSM777437", "GSM777438", "GSM777439", "GSM777440", "GSM777441", "GSM777442", "GSM777443", "GSM777444", "GSM777445", "GSM777446", "GSM777447", "GSM777448", "GSM777449", "GSM777450", "GSM777451", "GSM777452", "GSM777453", "GSM777454", "GSM777455", "GSM777456", "GSM777457", "GSM777458", "GSM777459", "GSM777460", "GSM777461", "GSM777462", "GSM777463", "GSM777464", "GSM777465", "GSM777466", "GSM777467", "GSM777468", "GSM777469", "GSM777470", "GSM777471", "GSM777472", "GSM777473"], "sample_count": 135, "group_sizes": null, "group_sizes_basis": null, "platform": "570", "taxon": "Homo sapiens", "title": "Tuberculosis Patients Blood Gene Expression Through Treatment", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE34608", "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=GSE34608", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE34608", "version": null, "note": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM851793", "GSM851794", "GSM851795", "GSM851796", "GSM851797", "GSM851798", "GSM851799", "GSM851800", "GSM851801", "GSM851802", "GSM851803", "GSM851804", "GSM851805", "GSM851806", "GSM851807", "GSM851808", "GSM851809", "GSM851810", "GSM851811", "GSM851812", "GSM851813", "GSM851814", "GSM851815", "GSM851816", "GSM851850", "GSM851851", "GSM851852", "GSM851853", "GSM851854", "GSM851855", "GSM851856", "GSM851857", "GSM851858", "GSM851859", "GSM851860", "GSM851861", "GSM851862", "GSM851863", "GSM851864", "GSM851865", "GSM851866", "GSM851867", "GSM851868", "GSM851869", "GSM851870", "GSM851871", "GSM851872", "GSM851873", "GSM851874", "GSM851875", "GSM851876", "GSM851877", "GSM851878", "GSM851879", "GSM851880", "GSM851881", "GSM851882", "GSM851883", "GSM851884", "GSM851885", "GSM851886", "GSM851887", "GSM851888", "GSM851889", "GSM851890", "GSM851891", "GSM851892", "GSM851893"], "sample_count": 68, "group_sizes": null, "group_sizes_basis": null, "platform": "7731;6480", "taxon": "Homo sapiens", "title": "Gene and microRNA expression in pulmonary tuberculosis and sarcoidosis", "resolution_checked_at": "2026-11-01T18:46:34Z", "resolution_check": "identifier_resolution_only_no_download_no_licence_read", "downloaded": false, "licence_read": false}}, {"id": "data:geo:GSE42826", "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=GSE42826", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42826", "version": null, "note": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1050774", "GSM1050775", "GSM1050776", "GSM1050777", "GSM1050778", "GSM1050779", "GSM1050780", "GSM1050781", "GSM1050782", "GSM1050783", "GSM1050784", "GSM1050785", "GSM1050786", "GSM1050787", "GSM1050788", "GSM1050789", "GSM1050790", "GSM1050791", "GSM1050792", "GSM1050793", "GSM1050794", "GSM1050795", "GSM1050796", "GSM1050797", "GSM1050798", "GSM1050799", "GSM1050800", "GSM1050801", "GSM1050802", "GSM1050803", "GSM1050804", "GSM1050805", "GSM1050806", "GSM1050807", "GSM1050808", "GSM1050809", "GSM1050810", "GSM1050811", "GSM1050812", "GSM1050813", "GSM1050814", "GSM1050815", "GSM1050816", "GSM1050817", "GSM1050818", "GSM1050819", "GSM1050820", "GSM1050821", "GSM1050822", "GSM1050823", "GSM1050824", "GSM1050825", "GSM1050826", "GSM1050827", "GSM1050828", "GSM1050829", "GSM1050830", "GSM1050831", "GSM1050832", "GSM1050833", "GSM1050834", "GSM1050835", "GSM1050836", "GSM1050837", "GSM1050838", "GSM1050839", "GSM1050840", "GSM1050841", "GSM1050842", "GSM1050843", "GSM1050844", "GSM1050845", "GSM1050846", "GSM1050847", "GSM1050848", "GSM1050849", "GSM1050850", "GSM1050851", "GSM1050852", "GSM1050853", "GSM1050854", "GSM1050855", "GSM1050856", "GSM1050857", "GSM1050858", "GSM1050859", "GSM1050860", "GSM1050861", "GSM1050862", "GSM1050863", "GSM1050864", "GSM1050865", "GSM1050866", "GSM1050867", "GSM1050868", "GSM1050869", "GSM1050870", "GSM1050871", "GSM1050872", "GSM1050873", "GSM1050874", "GSM1050875"], "sample_count": 102, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Human whole blood microarray study to compare patients with tuberculosis, sarcoidosis, pneumonia, and lung cancer (test)", "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:GSE42830", "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=GSE42830", "sha256": null, "bytes": null, "access": "open", "state": "resolved", "reader": null, "reader_status": "reader_required", "identifier": "GSE42830", "version": null, "note": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "structure": {"repository": "GEO", "access_route": "GEO accession URL", "access_statement_verbatim": "Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo).", "access_statement_kind": "data_availability_statement", "sample_accessions": ["GSM1050928", "GSM1050929", "GSM1050930", "GSM1050931", "GSM1050932", "GSM1050933", "GSM1050934", "GSM1050935", "GSM1050936", "GSM1050937", "GSM1050938", "GSM1050939", "GSM1050940", "GSM1050941", "GSM1050942", "GSM1050943", "GSM1050944", "GSM1050945", "GSM1050946", "GSM1050947", "GSM1050948", "GSM1050949", "GSM1050950", "GSM1050951", "GSM1050952", "GSM1050953", "GSM1050954", "GSM1050955", "GSM1050956", "GSM1050957", "GSM1050958", "GSM1050959", "GSM1050960", "GSM1050961", "GSM1050962", "GSM1050963", "GSM1050964", "GSM1050965", "GSM1050966", "GSM1050967", "GSM1050968", "GSM1050969", "GSM1050970", "GSM1050971", "GSM1050972", "GSM1050973", "GSM1050974", "GSM1050975", "GSM1050976", "GSM1050977", "GSM1050978", "GSM1050979", "GSM1050980", "GSM1050981", "GSM1050982", "GSM1050983", "GSM1050984", "GSM1050985", "GSM1050986", "GSM1050987", "GSM1050988", "GSM1050989", "GSM1050990", "GSM1050991", "GSM1050992", "GSM1050993", "GSM1050994", "GSM1050995", "GSM1050996", "GSM1050997", "GSM1050998", "GSM1050999", "GSM1051000", "GSM1051001", "GSM1051002", "GSM1051003", "GSM1051004", "GSM1051005", "GSM1051006", "GSM1051007", "GSM1051008", "GSM1051009", "GSM1051010", "GSM1051011", "GSM1051012", "GSM1051013", "GSM1051014", "GSM1051015", "GSM1051016", "GSM1051017", "GSM1051018", "GSM1051019", "GSM1051020", "GSM1051021", "GSM1051022"], "sample_count": 95, "group_sizes": null, "group_sizes_basis": null, "platform": "10558", "taxon": "Homo sapiens", "title": "Human whole blood microarray study to compare patients with tuberculosis, sarcoidosis, pneumonia, and lung cancer (training)", "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:GSE31348 not downloaded", "asset:data:geo:GSE31348 licence not read", "asset:data:geo:GSE34608 not downloaded", "asset:data:geo:GSE34608 licence not read", "asset:data:geo:GSE42826 not downloaded", "asset:data:geo:GSE42826 licence not read", "asset:data:geo:GSE42830 not downloaded", "asset:data:geo:GSE42830 licence not read"]}, "analysis": {"state": "complete", "methods": [{"id": "method-1", "family": "group_comparison", "specific": "anova", "label": "Group comparison", "dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["two_or_more_groups_continuous"], "evidence": {"score": 1.0, "band": "verbatim", "quote": "The significant genes were selected based on two criteria of common top 8 proteins in the heatmap analysis by T-test/ANOVA in MetaboAnalyst and MCODE score ≥10."}}, {"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": "protein-protein interaction"}}, {"id": "method-3", "family": "network_analysis", "specific": "pathway_enrichment", "label": "Network / pathway analysis", "dsl_operations": ["pathway_enrich"], "missing_operations": [], "expressible": true, "parameters": {}, "data_shapes": ["edge_list"], "evidence": {"score": 0.7, "band": "medium", "quote": "pathway enrichment"}}], "targets": [{"id": "target-published-estimate", "claim_id": "claim-target-result", "operation": "bootstrap_mean_difference", "expected_value": 0.986, "unit": "auc", "tolerance": null, "state": "complete", "note": "The published estimate as the reader quoted it from the paper. No tolerance is published because the paper states none."}], "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": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "missing_operations": [], "basis": "The paper names the method it used and the corpus's method extractor maps it onto the DSL catalogue: anova."}, "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": ["GSE42826", "GSE42830", "GSE34608", "GSE31348"], "resolved_accessions": ["GSE42826", "GSE42830", "GSE34608", "GSE31348"], "statements": ["Availability of data and materials: Datasets including GSE42826, GSE42830, GSE34608 and GSE31348 were downloaded from NCBI Gene Expression Omnibus database (GEO, http://www.ncbi.nlm.nih.gov/geo)."], "basis": "The paper names GSE42826, GSE42830, GSE34608, GSE31348 in NCBI Gene Expression Omnibus (GEO) and the accession resolves in the repository. No dataset was downloaded and no licence was read."}}, "can_run": {"dsl_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "assets": ["source:pmid:38935691", "data:geo:GSE31348"], "steps": ["run_analysis"]}, "must_build": {"dsl_operations": [], "converters": [], "readers": [], "capabilities": [], "data_gaps": ["data:geo:GSE31348"]}, "gaps": []}, "review": {"state": "partial", "machine_critique": {"kind": "extraction_review", "reader": {"model": "MiniMax-M3.1-Flash", "provider": "minimax", "provider_family": "minimax", "read_at": "2026-11-01T19:22:28Z", "independence": "single_reader"}, "evidence_check": {"method": "verbatim", "availability": "verbatim"}, "calls": 5, "usage": {"prompt_tokens": 13161, "completion_tokens": 1468, "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:38935691", "type": "paper", "label": "pmid:38935691"}, {"id": "source:pmid:38935691", "type": "manuscript", "label": "PMID 38935691 full text"}, {"id": "data:geo:GSE31348", "type": "dataset", "label": "GEO GSE31348"}], "activities": [{"id": "activity-reading-sci-2026-11-01", "type": "classification", "used": [{"id": "pmid:38935691", "type": "paper", "label": "pmid:38935691"}, {"id": "source:pmid:38935691", "type": "manuscript", "label": "PMID 38935691 full text"}, {"id": "data:geo:GSE31348", "type": "dataset", "label": "GEO GSE31348"}], "agent": "agent:corpus-assay-engine"}, {"id": "activity-read-38935691", "type": "extraction", "used": ["source:pmid:38935691"], "agent": "agent:minimax-reader"}, {"id": "activity-resolve-GSE31348", "type": "accession_resolution", "used": ["data:geo:GSE31348"], "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:38935691", "parent_hash": "sha256:bc42d6a407ba8e279120d2bdee232b44d76da01c4c94f41f973f280d2fd6de46", "fork_of": null, "generation": 3}, "gaps": ["asset:data:geo:GSE31348 licence not read", "asset:data:geo:GSE31348 not downloaded", "asset:data:geo:GSE34608 licence not read", "asset:data:geo:GSE34608 not downloaded", "asset:data:geo:GSE42826 licence not read", "asset:data:geo:GSE42826 not downloaded", "asset:data:geo:GSE42830 licence not read", "asset:data:geo:GSE42830 not downloaded", "execution.not_run", "review.human_critique", "review.independent_reader", "review.machine_critique"], "assays": [{"role": "data_generation", "definition_id": "rna_seq", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["Computational reassessment of RNA-seq data reveals key genes in active tuberculosi"], "order_basis": "paper_text_order:0", "id": "assay:1"}, {"role": "data_generation", "definition_id": "microarray", "definition_version": "99e1195c7d6f", "definition_digest": null, "required_operations": [], "support_state": "partial", "source_hashes": {"assay_lexicon": "99e1195c7d6f"}, "confidence": 0.93, "evidence": ["g resistance. METHODS: Two human whole blood microarray datasets, GSE42826 and GSE42830 were retriev"], "order_basis": "paper_text_order:317", "id": "assay:2"}, {"role": "analysis", "definition_id": "group_comparison", "definition_version": "f2132e96ae6c7a4e", "definition_digest": null, "required_operations": ["group_summary", "welch_t", "bootstrap_mean_difference", "group_comparison_anova"], "support_state": "supported", "source_hashes": {"dsl_catalogue": "f2132e96ae6c7a4e"}, "confidence": 1.0, "evidence": ["The significant genes were selected based on two criteria of common top 8 proteins in the heatmap analysis by T-test/ANOVA in MetaboAnalyst and MCODE score ≥10."], "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":"2026-11-04T02:48:38+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}}}