{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T03:15:41Z","timestamp":1772507741731,"version":"3.50.1"},"update-to":[{"DOI":"10.1371\/journal.pcbi.1010770","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000}}],"reference-count":69,"publisher":"Public Library of Science (PLoS)","issue":"7","license":[{"start":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T00:00:00Z","timestamp":1689811200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.ploscompbiol.org"],"crossmark-restriction":false},"short-container-title":["PLoS Comput Biol"],"abstract":"<jats:p>While blood gene signatures have shown promise in tuberculosis (TB) diagnosis and treatment monitoring, most signatures derived from a single cohort may be insufficient to capture TB heterogeneity in populations and individuals. Here we report a new generalized approach combining a network-based meta-analysis with machine-learning modeling to leverage the power of heterogeneity among studies. The transcriptome datasets from 57 studies (37 TB and 20 viral infections) across demographics and TB disease states were used for gene signature discovery and model training and validation. The network-based meta-analysis identified a common 45-gene signature specific to active TB disease across studies. Two optimized random forest regression models, using the full or partial 45-gene signature, were then established to model the continuum from <jats:italic>Mycobacterium tuberculosis<\/jats:italic> infection to disease and treatment response. In model validation, using pooled multi-cohort datasets to mimic the real-world setting, the model provides robust predictive performance for incipient to active TB risk over a 2.5-year period with an AUROC of 0.85, 74.2% sensitivity, and 78.3% specificity, which approximates the minimum criteria (&gt;75% sensitivity and &gt;75% specificity) within the WHO target product profile for prediction of progression to TB. Moreover, the model strongly discriminates active TB from viral infection (AUROC 0.93, 95% CI 0.91\u20130.94). For treatment monitoring, the TB scores generated by the model statistically correlate with treatment responses over time and were predictive, even before treatment initiation, of standard treatment clinical outcomes. We demonstrate an end-to-end gene signature model development scheme that considers heterogeneity for TB risk estimation and treatment monitoring.<\/jats:p>","DOI":"10.1371\/journal.pcbi.1010770","type":"journal-article","created":{"date-parts":[[2023,7,20]],"date-time":"2023-07-20T18:13:27Z","timestamp":1689876807000},"page":"e1010770","update-policy":"https:\/\/doi.org\/10.1371\/journal.pcbi.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["Gene signature discovery and systematic validation across diverse clinical cohorts for TB prognosis and response to treatment"],"prefix":"10.1371","volume":"19","author":[{"given":"Roger","family":"Vargas","sequence":"first","affiliation":[]},{"given":"Liam","family":"Abbott","sequence":"additional","affiliation":[]},{"given":"Daniel","family":"Bower","sequence":"additional","affiliation":[]},{"given":"Nicole","family":"Frahm","sequence":"additional","affiliation":[]},{"given":"Mike","family":"Shaffer","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1671-9744","authenticated-orcid":true,"given":"Wen-Han","family":"Yu","sequence":"additional","affiliation":[]}],"member":"340","published-online":{"date-parts":[[2023,7,20]]},"reference":[{"key":"pcbi.1010770.ref001","unstructured":"Organization WH. Global tuberculosis report. 2021."},{"issue":"4","key":"pcbi.1010770.ref002","doi-asserted-by":"crossref","first-page":"e1002786","DOI":"10.1371\/journal.pmed.1002786","article-title":"Host\u2013response\u2013based gene signatures for tuberculosis diagnosis: A systematic comparison of 16 signatures.","volume":"16","author":"H Warsinske","year":"2019","journal-title":"PLoS Med."},{"issue":"1","key":"pcbi.1010770.ref003","doi-asserted-by":"crossref","first-page":"8629","DOI":"10.1038\/s41598-020-65043-8","article-title":"RISK6, a 6\u2013gene transcriptomic signature of TB disease risk, diagnosis and treatment response.","volume":"10","author":"A Penn\u2013Nicholson","year":"2020","journal-title":"Sci Rep."},{"issue":"3","key":"pcbi.1010770.ref004","doi-asserted-by":"crossref","first-page":"354","DOI":"10.1016\/S1473-3099(20)30914-2","article-title":"Biomarker\u2013guided tuberculosis preventive therapy (CORTIS): a randomised controlled trial.","volume":"21","author":"TJ Scriba","year":"2021","journal-title":"The Lancet Infectious Diseases"},{"issue":"3","key":"pcbi.1010770.ref005","doi-asserted-by":"crossref","first-page":"213","DOI":"10.1016\/S2213-2600(16)00048-5","article-title":"Genome\u2013wide expression for diagnosis of pulmonary tuberculosis: a multicohort analysis","volume":"4","author":"TE Sweeney","year":"2016","journal-title":"Lancet Respir Med"},{"issue":"18","key":"pcbi.1010770.ref006","doi-asserted-by":"crossref","first-page":"1712","DOI":"10.1056\/NEJMoa1303657","article-title":"Diagnosis of childhood tuberculosis and host RNA expression in Africa","volume":"370","author":"ST Anderson","year":"2014","journal-title":"N Engl J Med"},{"issue":"7309","key":"pcbi.1010770.ref007","doi-asserted-by":"crossref","first-page":"973","DOI":"10.1038\/nature09247","article-title":"An interferon\u2013inducible neutrophil\u2013driven blood transcriptional signature in human tuberculosis","volume":"466","author":"MP Berry","year":"2010","journal-title":"Nature"},{"issue":"8","key":"pcbi.1010770.ref008","doi-asserted-by":"crossref","first-page":"e70630","DOI":"10.1371\/journal.pone.0070630","article-title":"Transcriptional blood signatures distinguish pulmonary tuberculosis, pulmonary sarcoidosis, pneumonias and lung cancers.","volume":"8","author":"CI Bloom","year":"2013","journal-title":"PLoS One."},{"issue":"4","key":"pcbi.1010770.ref009","doi-asserted-by":"crossref","first-page":"421","DOI":"10.1016\/j.tube.2015.04.008","article-title":"A real\u2013time PCR signature to discriminate between tuberculosis and other pulmonary diseases","volume":"95","author":"L Laux da Costa","year":"2015","journal-title":"Tuberculosis (Edinb)."},{"issue":"6","key":"pcbi.1010770.ref010","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1007\/s00109-007-0157-6","article-title":"Candidate biomarkers for discrimination between infection and disease caused by Mycobacterium tuberculosis","volume":"85","author":"M Jacobsen","year":"2007","journal-title":"J Mol Med (Berl)."},{"issue":"10","key":"pcbi.1010770.ref011","doi-asserted-by":"crossref","first-page":"e1001538","DOI":"10.1371\/journal.pmed.1001538","article-title":"Detection of tuberculosis in HIV\u2013infected and\u2013uninfected African adults using whole blood RNA expression signatures: a case\u2013control study","volume":"10","author":"M Kaforou","year":"2013","journal-title":"PLoS Med"},{"key":"pcbi.1010770.ref012","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.tube.2018.01.002","article-title":"Existing blood transcriptional classifiers accurately discriminate active tuberculosis from latent infection in individuals from south India","volume":"109","author":"S Leong","year":"2018","journal-title":"Tuberculosis"},{"issue":"2","key":"pcbi.1010770.ref013","doi-asserted-by":"crossref","first-page":"86","DOI":"10.15252\/emmm.201505790","article-title":"Concise gene signature for point\u2013of\u2013care classification of tuberculosis","volume":"8","author":"J Maertzdorf","year":"2016","journal-title":"EMBO Mol Med"},{"key":"pcbi.1010770.ref014","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1016\/j.ebiom.2016.12.009","article-title":"Unbiased Identification of Blood\u2013based Biomarkers for Pulmonary Tuberculosis by Modeling and Mining Molecular Interaction Networks.","volume":"15","author":"A Sambarey","year":"2017","journal-title":"EBioMedicine"},{"key":"pcbi.1010770.ref015","doi-asserted-by":"crossref","first-page":"74","DOI":"10.1186\/1471-2164-14-74","article-title":"A predictive signature gene set for discriminating active from latent tuberculosis in Warao Amerindian children","volume":"14","author":"LM Verhagen","year":"2013","journal-title":"BMC Genomics"},{"key":"pcbi.1010770.ref016","doi-asserted-by":"crossref","first-page":"1441","DOI":"10.3389\/fmicb.2019.01441","article-title":"Detection of Tuberculosis Recurrence, Diagnosis and Treatment Response by a Blood Transcriptomic Risk Signature in HIV\u2013Infected Persons on Antiretroviral Therapy.","volume":"10","author":"F Darboe","year":"2019","journal-title":"Front Microbiol."},{"issue":"10035","key":"pcbi.1010770.ref017","doi-asserted-by":"crossref","first-page":"2312","DOI":"10.1016\/S0140-6736(15)01316-1","article-title":"A blood RNA signature for tuberculosis disease risk: a prospective cohort study","volume":"387","author":"DE Zak","year":"2016","journal-title":"The Lancet"},{"key":"pcbi.1010770.ref018","article-title":"Four\u2013gene Pan\u2013African Blood Signature Predicts Progression to Tuberculosis","author":"S Suliman","year":"2018","journal-title":"Am J Respir Crit Care Med"},{"key":"pcbi.1010770.ref019","doi-asserted-by":"crossref","first-page":"101898","DOI":"10.1016\/j.tube.2020.101898","article-title":"Cross\u2013validation of existing signatures and derivation of a novel 29\u2013gene transcriptomic signature predictive of progression to TB in a Brazilian cohort of household contacts of pulmonary TB","volume":"120","author":"S Leong","year":"2020","journal-title":"Tuberculosis"},{"issue":"16","key":"pcbi.1010770.ref020","first-page":"e87238","article-title":"Blood transcriptomic diagnosis of pulmonary and extrapulmonary tuberculosis","volume":"1","author":"JK Roe","year":"2016","journal-title":"JCI Insight"},{"issue":"1","key":"pcbi.1010770.ref021","doi-asserted-by":"crossref","first-page":"5839","DOI":"10.1038\/s41598-017-05057-x","article-title":"Novel transcriptional signatures for sputum\u2013independent diagnostics of tuberculosis in children","volume":"7","author":"JE Gjoen","year":"2017","journal-title":"Sci Rep"},{"key":"pcbi.1010770.ref022","doi-asserted-by":"crossref","first-page":"637164","DOI":"10.3389\/fimmu.2021.637164","article-title":"Identification of Reduced Host Transcriptomic Signatures for Tuberculosis Disease and Digital PCR\u2013Based Validation and Quantification.","volume":"12","author":"HD Gliddon","year":"2021","journal-title":"Front Immunol"},{"key":"pcbi.1010770.ref023","first-page":"26","article-title":"Identification of 13 blood\u2013based gene expression signatures to accurately distinguish tuberculosis from other pulmonary diseases and healthy controls","volume":"1","author":"HH Huang","year":"2015","journal-title":"Biomed Mater Eng"},{"key":"pcbi.1010770.ref024","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.3389\/fmicb.2016.01586","article-title":"Transcriptomic Biomarkers for Tuberculosis: Evaluation of DOCK9. EPHA4, and NPC2 mRNA Expression in Peripheral Blood.","volume":"7","author":"LS de Araujo","year":"2016","journal-title":"Front Microbiol."},{"key":"pcbi.1010770.ref025","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.tube.2016.04.008","article-title":"Expression of nuclear factor, erythroid 2\u2013like 2\u2013mediated genes differentiates tuberculosis","volume":"99","author":"Z Qian","year":"2016","journal-title":"Tuberculosis (Edinb)."},{"issue":"1","key":"pcbi.1010770.ref026","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1093\/cid\/ciy835","article-title":"A Novel, 5\u2013Transcript, Whole\u2013blood Gene\u2013expression Signature for Tuberculosis Screening Among People Living With Human Immunodeficiency Virus","volume":"69","author":"JV Rajan","year":"2019","journal-title":"Clin Infect Dis"},{"issue":"5","key":"pcbi.1010770.ref027","first-page":"731","article-title":"Blood Transcriptomic Stratification of Short\u2013term Risk in Contacts of Tuberculosis","volume":"70","author":"J Roe","year":"2020","journal-title":"Clin Infect Dis"},{"issue":"1","key":"pcbi.1010770.ref028","doi-asserted-by":"crossref","first-page":"2308","DOI":"10.1038\/s41467-018-04579-w","article-title":"A modular transcriptional signature identifies phenotypic heterogeneity of human tuberculosis infection","volume":"9","author":"A Singhania","year":"2018","journal-title":"Nat Commun"},{"issue":"2","key":"pcbi.1010770.ref029","doi-asserted-by":"crossref","first-page":"274","DOI":"10.1128\/JCM.01990-15","article-title":"Blood Transcriptional Biomarkers for Active Tuberculosis among Patients in the United States: a Case\u2013Control Study with Systematic Cross\u2013Classifier Evaluation","volume":"54","author":"ND Walter","year":"2016","journal-title":"J Clin Microbiol"},{"issue":"1","key":"pcbi.1010770.ref030","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1186\/s13104-021-05663-z","article-title":"A novel blood\u2013based assay for treatment monitoring of tuberculosis","volume":"14","author":"AJ Zimmer","year":"2021","journal-title":"BMC Res Notes"},{"issue":"10","key":"pcbi.1010770.ref031","doi-asserted-by":"crossref","DOI":"10.1084\/jem.20210915","article-title":"Blood transcriptomics reveal the evolution and resolution of the immune response in tuberculosis","volume":"218","author":"O Tabone","year":"2021","journal-title":"J Exp Med"},{"issue":"1","key":"pcbi.1010770.ref032","doi-asserted-by":"crossref","first-page":"13646","DOI":"10.1038\/s41598-021-93059-1","article-title":"Multi\u2013country evaluation of RISK6, a 6\u2013gene blood transcriptomic signature, for tuberculosis diagnosis and treatment monitoring.","volume":"11","author":"R Bayaa","year":"2021","journal-title":"Sci Rep."},{"key":"pcbi.1010770.ref033","article-title":"Prediction of anti\u2013tuberculosis treatment duration based on a 22\u2013gene transcriptomic model","author":"J Heyckendorf","year":"2021","journal-title":"Eur Respir J"},{"key":"pcbi.1010770.ref034","doi-asserted-by":"crossref","first-page":"102138","DOI":"10.1016\/j.tube.2021.102138","article-title":"A 10\u2013gene biosignature of tuberculosis treatment monitoring and treatment outcome prediction","volume":"131","author":"NP Long","year":"2021","journal-title":"Tuberculosis (Edinb)."},{"key":"pcbi.1010770.ref035","doi-asserted-by":"crossref","first-page":"48","DOI":"10.1016\/j.tube.2017.08.004","article-title":"Host blood RNA signatures predict the outcome of tuberculosis treatment","volume":"107","author":"EG Thompson","year":"2017","journal-title":"Tuberculosis (Edinb)."},{"issue":"4","key":"pcbi.1010770.ref036","doi-asserted-by":"crossref","DOI":"10.1128\/CMR.00021-18","article-title":"Incipient and Subclinical Tuberculosis: a Clinical Review of Early Stages and Progression of Infection.","volume":"31","author":"PK Drain","year":"2018","journal-title":"Clin Microbiol Rev"},{"key":"pcbi.1010770.ref037","article-title":"Longitudinal Dynamics of a Blood Transcriptomic Signature of Tuberculosis","author":"H Mulenga","year":"2021","journal-title":"Am J Respir Crit Care Med"},{"key":"pcbi.1010770.ref038","article-title":"Diagnostic accuracy of the Cepheid 3\u2013gene host response fingerstick blood test in a prospective, multi\u2013site study: interim results","author":"JS Sutherland","year":"2021","journal-title":"Clin Infect Dis"},{"issue":"D1","key":"pcbi.1010770.ref039","doi-asserted-by":"crossref","first-page":"D607","DOI":"10.1093\/nar\/gky1131","article-title":"STRING v11: protein\u2013protein association networks with increased coverage, supporting functional discovery in genome\u2013wide experimental datasets","volume":"47","author":"D Szklarczyk","year":"2018","journal-title":"Nucleic Acids Research"},{"key":"pcbi.1010770.ref040","doi-asserted-by":"crossref","first-page":"716809","DOI":"10.3389\/fcimb.2021.716809","article-title":"Transcriptional Profiling of Human Peripheral Blood Mononuclear Cells Stimulated by Mycobacterium tuberculosis PPE57 Identifies Characteristic Genes Associated With Type I Interferon Signaling.","volume":"11","author":"F Yi","year":"2021","journal-title":"Front Cell Infect Microbiol."},{"issue":"1","key":"pcbi.1010770.ref041","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1038\/76940","article-title":"Interferon alpha\/beta\u2013mediated inhibition and promotion of interferon gamma: STAT1 resolves a paradox","volume":"1","author":"KB Nguyen","year":"2000","journal-title":"Nat Immunol"},{"key":"pcbi.1010770.ref042","doi-asserted-by":"crossref","first-page":"1633","DOI":"10.3389\/fimmu.2017.01633","article-title":"Type I Interferons in the Pathogenesis of Tuberculosis: Molecular Drivers and Immunological Consequences.","volume":"8","author":"ML Donovan","year":"2017","journal-title":"Front Immunol"},{"issue":"4","key":"pcbi.1010770.ref043","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/S2213-2600(19)30282-6","article-title":"Concise whole blood transcriptional signatures for incipient tuberculosis: a systematic review and patient\u2013level pooled meta\u2013analysis","volume":"8","author":"RK Gupta","year":"2020","journal-title":"The Lancet Respiratory Medicine"},{"issue":"6","key":"pcbi.1010770.ref044","doi-asserted-by":"crossref","first-page":"e183779","DOI":"10.1001\/jamanetworkopen.2018.3779","article-title":"Assessment of Validity of a Blood\u2013Based 3\u2013Gene Signature Score for Progression and Diagnosis of Tuberculosis, Disease Severity, and Treatment Response.","volume":"1","author":"HC Warsinske","year":"2018","journal-title":"JAMA Netw Open."},{"issue":"1","key":"pcbi.1010770.ref045","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1186\/s12879-020-05116-1","article-title":"A blood RNA transcript signature for TB exposure in household contacts","volume":"20","author":"PKW Kwan","year":"2020","journal-title":"BMC Infect Dis"},{"key":"pcbi.1010770.ref046","doi-asserted-by":"crossref","first-page":"457","DOI":"10.3389\/fgene.2018.00457","article-title":"Meta\u2013Analysis Identification of Highly Robust and Differential Immune\u2013Metabolic Signatures of Systemic Host Response to Acute and Latent Tuberculosis in Children and Adults.","volume":"9","author":"SY Bah","year":"2018","journal-title":"Front Genet"},{"issue":"1\u20132","key":"pcbi.1010770.ref047","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.cellimm.2012.01.007","article-title":"CD19(+)CD1d(+)CD5(+) B cell frequencies are increased in patients with tuberculosis and suppress Th17 responses.","volume":"274","author":"M Zhang","year":"2012","journal-title":"Cell Immunol"},{"issue":"20","key":"pcbi.1010770.ref048","first-page":"e00662","article-title":"The Interferon\u2013Inducible Proteoglycan Testican\u20132\/SPOCK2 Functions as a Protective Barrier against Virus Infection of Lung Epithelial Cells","volume":"93","author":"N Ahn","year":"2019","journal-title":"J Virol"},{"key":"pcbi.1010770.ref049","doi-asserted-by":"crossref","DOI":"10.7554\/eLife.51071","article-title":"LRRK2 maintains mitochondrial homeostasis and regulates innate immune responses to Mycobacterium tuberculosis.","volume":"9","author":"CG Weindel","year":"2020","journal-title":"Elife"},{"key":"pcbi.1010770.ref050","unstructured":"Consensus meeting report: development of a Target Product Profile (TPP) and a framework for evaluation for a test for predicting progression from tuberculosis infection to active disease. 2017."},{"key":"pcbi.1010770.ref051","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1016\/j.tube.2017.11.001","article-title":"Diagnostic performance of an optimized transcriptomic signature of risk of tuberculosis in cryopreserved peripheral blood mononuclear cells","volume":"108","author":"F Darboe","year":"2018","journal-title":"Tuberculosis (Edinb)."},{"issue":"10","key":"pcbi.1010770.ref052","doi-asserted-by":"crossref","first-page":"1094","DOI":"10.1038\/nm.4177","article-title":"Persisting positron emission tomography lesion activity and Mycobacterium tuberculosis mRNA after tuberculosis cure","volume":"22","author":"ST Malherbe","year":"2016","journal-title":"Nat Med"},{"key":"pcbi.1010770.ref053","article-title":"Development and validation of a parsimonious TB gene signature using the digital NanoString nCounter platform","author":"V Kaipilyawar","year":"2022","journal-title":"Clin Infect Dis"},{"issue":"11","key":"pcbi.1010770.ref054","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1038\/nri.2017.69","article-title":"Heterogeneity in tuberculosis","volume":"17","author":"AM Cadena","year":"2017","journal-title":"Nat Rev Immunol"},{"issue":"6","key":"pcbi.1010770.ref055","doi-asserted-by":"crossref","first-page":"1859","DOI":"10.1021\/acsinfecdis.1c00162","article-title":"Chronological Metabolic Response to Intensive Phase TB Therapy in Patients with Cured and Failed Treatment Outcomes.","volume":"7","author":"M Opperman","year":"2021","journal-title":"ACS Infect Dis."},{"key":"pcbi.1010770.ref056","first-page":"144","article-title":"Empowering Multi\u2013Cohort Gene Expression Analysis to Increase Reproducibility.","volume":"22","author":"WA Haynes","year":"2017","journal-title":"Pac Symp Biocomput"},{"issue":"17","key":"pcbi.1010770.ref057","doi-asserted-by":"crossref","first-page":"i884","DOI":"10.1093\/bioinformatics\/bty560","article-title":"fastp: an ultra\u2013fast all\u2013in\u2013one FASTQ preprocessor","volume":"34","author":"S Chen","year":"2018","journal-title":"Bioinformatics"},{"issue":"4","key":"pcbi.1010770.ref058","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1038\/nmeth.4197","article-title":"Salmon provides fast and bias\u2013aware quantification of transcript expression.","volume":"14","author":"R Patro","year":"2017","journal-title":"Nat Methods.PubMed Central PMCID"},{"issue":"2","key":"pcbi.1010770.ref059","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1038\/nrg3868","article-title":"Methods of integrating data to uncover genotype\u2013phenotype interactions","volume":"16","author":"MD Ritchie","year":"2015","journal-title":"Nat Rev Genet"},{"issue":"2","key":"pcbi.1010770.ref060","doi-asserted-by":"crossref","first-page":"946","DOI":"10.1214\/16-AOAS920","article-title":"Robust Hyperparameter Estimation Protects against Hypervariable Genes and Improves Power to Detect Differential Expression.","volume":"10","author":"B Phipson","year":"2016","journal-title":"Ann Appl Stat."},{"issue":"3","key":"pcbi.1010770.ref061","doi-asserted-by":"crossref","first-page":"R25","DOI":"10.1186\/gb-2010-11-3-r25","article-title":"A scaling normalization method for differential expression analysis of RNA\u2013seq data","volume":"11","author":"MD Robinson","year":"2010","journal-title":"Genome Biol"},{"issue":"11","key":"pcbi.1010770.ref062","doi-asserted-by":"crossref","first-page":"2058","DOI":"10.1093\/molbev\/msh222","article-title":"Conservation and coevolution in the scale\u2013free human gene coexpression network","volume":"21","author":"IK Jordan","year":"2004","journal-title":"Mol Biol Evol"},{"issue":"W1","key":"pcbi.1010770.ref063","doi-asserted-by":"crossref","first-page":"W90","DOI":"10.1093\/nar\/gkw377","article-title":"Enrichr: a comprehensive gene set enrichment analysis web server 2016 update","volume":"44","author":"MV Kuleshov","year":"2016","journal-title":"Nucleic Acids Res"},{"issue":"2","key":"pcbi.1010770.ref064","doi-asserted-by":"crossref","DOI":"10.1214\/009053604000000067","article-title":"Least angle regression","volume":"32","author":"B Efron","year":"2004","journal-title":"The Annals of Statistics"},{"issue":"4","key":"pcbi.1010770.ref065","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1111\/j.1467-9868.2010.00740.x","article-title":"Stability selection.","volume":"72","author":"N Meinshausen","year":"2010","journal-title":"Journal of the Royal Statistical Society: Series B (Statistical Methodology)."},{"key":"pcbi.1010770.ref066","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1186\/1471-2105-7-91","article-title":"Bias in error estimation when using cross\u2013validation for model selection","volume":"7","author":"S Varma","year":"2006","journal-title":"BMC Bioinformatics"},{"key":"pcbi.1010770.ref067","first-page":"13","article-title":"Random search for hyper\u2013parameter optimization","author":"J Bergstra","year":"2012","journal-title":"Journal of machine learning research"},{"issue":"11","key":"pcbi.1010770.ref068","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1167\/iovs.61.11.29","article-title":"Calculating Sensitivity, Specificity, and Predictive Values for Correlated Eye Data","volume":"61","author":"GS Ying","year":"2020","journal-title":"Invest Ophthalmol Vis Sci"},{"issue":"3","key":"pcbi.1010770.ref069","doi-asserted-by":"crossref","first-page":"1269","DOI":"10.1214\/aop\/1176990746","article-title":"The Tight Constant in the Dvoretzky\u2013Kiefer\u2013Wolfowitz Inequality","volume":"18","author":"P. Massart","year":"1990","journal-title":"The Annals of Probability"}],"updated-by":[{"DOI":"10.1371\/journal.pcbi.1010770","type":"new_version","label":"New version","source":"publisher","updated":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000}}],"container-title":["PLOS Computational Biology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1010770","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T17:33:18Z","timestamp":1690911198000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pcbi.1010770"}},"subtitle":[],"editor":[{"given":"Marc R.","family":"Birtwistle","sequence":"first","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2023,7,20]]},"references-count":69,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2023,7,20]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pcbi.1010770","relation":{"new_version":[{"id-type":"doi","id":"10.1371\/journal.pcbi.1010770","asserted-by":"object"}]},"ISSN":["1553-7358"],"issn-type":[{"value":"1553-7358","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,20]]}}}