{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:20:10Z","timestamp":1788308410026,"version":"build-2803163510"},"reference-count":20,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T00:00:00Z","timestamp":1787616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000185","name":"Defense Advanced Research Projects Agency","doi-asserted-by":"publisher","award":["N660012324041"],"award-info":[{"award-number":["N660012324041"]}],"id":[{"id":"10.13039\/100000185","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,8,31]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Predicting physical and cognitive readiness in warfighters is critical for mission success. These predictions can be improved by identifying key biomarkers using multiple omics modalities. The MASTR-E study conducted by McKetney and colleagues is one of the most comprehensive multi-omics studies of saliva samples collected from warfighters, which also applied classic linear statistical (CLS) techniques to discover key biomarkers of readiness. Aligning with McKetney et al.\u2019s assumptions, we operationalize readiness as a binary proxy, where pre-mission samples are labeled as \u201cready\u201d to reflect a rested, unstressed physiological baseline, while post-mission samples are labeled \u201cnot ready\u201d to reflect cumulative physical and cognitive load from the mission. As such, readiness here is not a direct biological or physiological construct, but an inferred state likely dominated by stress-related physiological changes. This assumption and definition is discussed further in the Introduction and Limitations sections. Here, we apply machine learning (ML) analyses to better assess generalizability, consider hidden interactions, and identify nonlinear patterns in the data. We investigated whether ML approaches could predict readiness and identify relevant biomarkers. ML models were trained on proteomics-only or metabolomics-only datasets to classify participants as ready or not ready and important model features were considered as putative biomarkers. Training and testing datasets were curated for two objectives: (i) recognize biomolecular signatures indicative of readiness within the same donor and (ii) assess generalizability across warfighters by withholding donors for testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Proteomics-based models achieved AUCs of 0.907\u2009\u00b1\u20090.034 and 0.860\u2009\u00b1\u20090.063 for Objectives 1 and 2, respectively. Metabolomics-based models achieved Objective 1 AUC of 0.994\u2009\u00b1\u20090.007 and Objective 2 AUC of 0.993\u2009\u00b1\u20090.010. Comparative analysis with existing literature validates the model\u2019s feature importances, but the identified putative biomarkers significantly differ from those discovered through CLS analyses, as only one ML-identified biomarker overlapping with those identified through CLS methods. We show that these ML models and identified features are more robust to noise and generalizable across participants than those identified using CLS methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability<\/jats:title>\n                    <jats:p>The analysis pipelines are provided as Jupyter notebooks, including all code and documentation, and are available publicly on GitHub at {https:\/\/github.com\/netrias\/ReadinessClassification}.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btag585","type":"journal-article","created":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T11:39:23Z","timestamp":1787657963000},"source":"Crossref","is-referenced-by-count":0,"title":["Comparison of classic statistical methods and machine learning approaches to classify readiness"],"prefix":"10.1093","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-5564-0192","authenticated-orcid":false,"given":"Ashley E","family":"Copenhaver","sequence":"first","affiliation":[{"name":"Netrias, LLC , Annapolis, MD 21401,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris","family":"Puglisi","sequence":"additional","affiliation":[{"name":"Netrias, LLC , Annapolis, MD 21401,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5488-1542","authenticated-orcid":false,"given":"Mohammed A","family":"Eslami","sequence":"additional","affiliation":[{"name":"Netrias, LLC , Annapolis, MD 21401,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,8,25]]},"reference":[{"key":"2026090120062462200_btag585-B1","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1080\/17461391.2021.1962983","article-title":"Circulating biomarkers associated with performance and resilience during military operational stress","volume":"22","author":"Beckner","year":"2022","journal-title":"Eur J Sport Sci"},{"key":"2026090120062462200_btag585-B2","first-page":"C39","article-title":"Fatigue in military aviation: an overview of US military-approved pharmacological countermeasures","volume":"76","author":"Caldwell","year":"2005","journal-title":"Aviat Space Environ Med"},{"key":"2026090120062462200_btag585-B3","doi-asserted-by":"publisher","DOI":"10.3390\/jcm10030517","article-title":"Salivary biomarkers of stress, anxiety and depression","volume":"10","author":"Chojnowska","year":"2021","journal-title":"J Clin Med"},{"key":"2026090120062462200_btag585-B4","doi-asserted-by":"publisher","DOI":"10.3390\/biom13101516","article-title":"Using LLMs and explainable ML to analyze biomarkers at single-cell level for improved understanding of diseases","volume":"13","author":"Elsborg","year":"2023","journal-title":"Biomolecules"},{"key":"2026090120062462200_btag585-B5","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1136\/annrheumdis-2020-eular.5517","article-title":"OP0206 allantoin\u2014a biomarker of oxidative stress\u2014is higher in patients with gout than in healthy volunteers, and corresponds with severity of disease","volume":"79","author":"Hasikova","year":"2020","journal-title":"Ann Rheum Dis"},{"key":"2026090120062462200_btag585-B6","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cca.2018.11.030","article-title":"Effects of inter-day and intra-day variation on salivary metabolomic profiles","volume":"489","author":"Kawanishi","year":"2019","journal-title":"Clin Chim Acta"},{"key":"2026090120062462200_btag585-B7","doi-asserted-by":"publisher","first-page":"107867","DOI":"10.1016\/j.compbiolchem.2023.107867","article-title":"Peripheral blood mononuclear cell derived biomarker detection using eXplainable Artificial Intelligence (XAI) provides better diagnosis of breast cancer","volume":"104","author":"Kumar","year":"2023","journal-title":"Comput Biol Chem"},{"key":"2026090120062462200_btag585-B8","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1016\/j.biopsych.2004.11.014","article-title":"Severe decrements in cognition function and mood induced by sleep loss, heat, dehydration, and undernutrition during simulated combat","volume":"57","author":"Lieberman","year":"2005","journal-title":"Biol Psychiatry"},{"key":"2026090120062462200_btag585-B9","doi-asserted-by":"publisher","first-page":"e0321223","DOI":"10.1371\/journal.pone.0321223","article-title":"Salivary biomarkers of tactical athlete readiness: a systematic review","volume":"20","author":"Lindsey","year":"2025","journal-title":"PLoS One"},{"key":"2026090120062462200_btag585-B10","doi-asserted-by":"publisher","first-page":"241","DOI":"10.3390\/healthcare11020241","article-title":"Chronic training induces metabolic and proteomic response in male and female basketball players: salivary modifications during in-season training programs","volume":"11","author":"Luti","year":"2023","journal-title":"Healthcare (Basel)"},{"key":"2026090120062462200_btag585-B11","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1039\/D1MO00271F","article-title":"Proteomic and metabolomic profiling of acute and chronic stress events associated with military exercises","volume":"18","author":"McKetney","year":"2022","journal-title":"Mol Omics"},{"key":"2026090120062462200_btag585-B12","doi-asserted-by":"publisher","first-page":"1920226","DOI":"10.1080\/20002297.2021.1920226","article-title":"Salivette, a relevant saliva sampling device for SARS-CoV-2 detection","volume":"13","author":"Melo Costa","year":"2021","journal-title":"J Oral Microbiol"},{"key":"2026090120062462200_btag585-B13","doi-asserted-by":"publisher","first-page":"18470","DOI":"10.1038\/s41598-022-23136-6","article-title":"Saliva metabolome alterations after acute stress","volume":"12","author":"Morgan","year":"2022","journal-title":"Sci Rep"},{"key":"2026090120062462200_btag585-B14","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1007\/s00441-023-03816-z","article-title":"The benefits and pitfalls of machine learning for biomarker discovery","volume":"394","author":"Ng","year":"2023","journal-title":"Cell Tissue Res"},{"key":"2026090120062462200_btag585-B15","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1039\/C3LC51303C","article-title":"An automated integrated platform for rapid and sensitive multiplexed protein profiling using human saliva samples","volume":"14","author":"Nie","year":"2014","journal-title":"Lab Chip"},{"key":"2026090120062462200_btag585-B16","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1139\/apnm-2013-0546","article-title":"Metabolomics of salivary fatigue markers in soccer players after consecutive games","volume":"39","author":"Ra","year":"2014","journal-title":"Appl Physiol Nutr Metab"},{"key":"2026090120062462200_btag585-B17","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1016\/j.cca.2020.09.001","article-title":"Saliva for use with a point of care assay for the rapid diagnosis of COVID-19","volume":"510","author":"SoRelle","year":"2020","journal-title":"Clin Chim Acta"},{"key":"2026090120062462200_btag585-B18","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1007\/s00360-006-0088-5","article-title":"The relationship between uric acid and its oxidative product allantoin: a potential indicator for the evaluation of oxidative stress in birds","volume":"176","author":"Tsahar","year":"2006","journal-title":"J Comp Physiol B"},{"key":"2026090120062462200_btag585-B19","doi-asserted-by":"publisher","first-page":"13924","DOI":"10.1038\/s41598-025-98948-3","article-title":"Explainable machine learning framework for biomarker discovery by combining biological age and frailty prediction","volume":"15","author":"Wang","year":"2025","journal-title":"Sci Rep"},{"key":"2026090120062462200_btag585-B20","doi-asserted-by":"publisher","first-page":"2221","DOI":"10.1002\/pmic.201100228","article-title":"Dynamics of salivary proteins and metabolites during extreme endurance sports\u2013a case study","volume":"12","author":"Zauber","year":"2012","journal-title":"Proteomics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btag585\/70784326\/btag585.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag585\/70784326\/btag585.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/42\/9\/btag585\/70784326\/btag585.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T00:06:34Z","timestamp":1788307594000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btag585\/8770357"}},"subtitle":[],"editor":[{"given":"Arne","family":"Elofsson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,8,25]]},"references-count":20,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2026,8,31]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btag585","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,9]]},"published":{"date-parts":[[2026,8,25]]},"article-number":"btag585"}}