{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T12:03:49Z","timestamp":1781006629976,"version":"3.54.1"},"posted":{"date-parts":[[2026,6,5]]},"group-title":"Bioinformatics","reference-count":39,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T00:00:00Z","timestamp":1780617600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"National Institute of Health","award":["#R35GM119770"],"award-info":[{"award-number":["#R35GM119770"]}]},{"DOI":"10.13039\/100008114","name":"University of Nebraska-Lincoln","doi-asserted-by":"crossref","award":["Grand Challenges Catalyst Award"],"award-info":[{"award-number":["Grand Challenges Catalyst Award"]}],"id":[{"id":"10.13039\/100008114","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,6,5]]},"abstract":"<jats:title>SUMMARY<\/jats:title>\n                <jats:p>\n                  Identifying robust biomarkers from high-dimensional biomedical data is a central challenge in translational research, but candidate rankings produced by any single feature-selection or classification method depend on algorithmic choices and rarely reproduce across pipelines. We present a disease-agnostic machine-learning framework that addresses this dependence by systematically benchmarking 25 (feature-selection x classifier) pipelines under five-fold stratified cross-validation, aggregating per-feature evidence by two independent methods (a weighted-selection consensus score and Robust Rank Aggregation), and characterizing the direction of each candidate using Cohen\u2019s\n                  <jats:italic>d<\/jats:italic>\n                  . We demonstrate the framework on immune-response measurements from two clinical phases: SARS-CoV-2 hospitalization and intensive-care admission; obtaining cross-validated mean F1 above 0.99 with balanced classification errors and producing tiered, direction-aware biomarker lists per phase. Interleukin-18 (IL-18) reached the strongest tier in both phases with consistent direction. The framework generalizes to any binary clinical classification problem and supports principled, reproducible biomarker prioritization.\n                <\/jats:p>","DOI":"10.64898\/2026.05.30.727266","type":"posted-content","created":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T03:20:16Z","timestamp":1780716016000},"source":"Crossref","is-referenced-by-count":0,"title":["MarkerScout: A Disease-Agnostic Machine Learning Framework for Biomarker Prediction from Multi-Scale Mechanistic Models"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1818-2271","authenticated-orcid":false,"given":"Robert","family":"Moore","sequence":"first","affiliation":[{"name":"Department of Biochemistry, University of Nebraska-Lincoln, Lincoln, NE, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3418-4286","authenticated-orcid":false,"given":"Frank","family":"Agayie-Ntim","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, University of Nebraska-Lincoln, Lincoln, NE, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1248-253X","authenticated-orcid":false,"given":"Lindsey B.","family":"Crawford","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, University of Nebraska-Lincoln, Lincoln, NE, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2404-5561","authenticated-orcid":false,"given":"Prakash","family":"Packrisamy","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, University of Nebraska-Lincoln, Lincoln, NE, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4411-8433","authenticated-orcid":false,"given":"Ahmed Abdeen","family":"Hamed","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, University of Nebraska-Lincoln, Lincoln, NE, US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3653-1906","authenticated-orcid":false,"given":"Tom\u00e1\u0161","family":"Helikar","sequence":"additional","affiliation":[{"name":"Department of Biochemistry, University of Nebraska-Lincoln, Lincoln, NE, US"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026060904300727000_2026.05.30.727266v1.1","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1038\/s41435-023-00209-8","article-title":"Potential diagnostic biomarkers: 6 cuproptosis-and ferroptosis-related genes linking immune infiltration in acute myocardial infarction","volume":"24","year":"2023","journal-title":"Genes Immun"},{"key":"2026060904300727000_2026.05.30.727266v1.2","doi-asserted-by":"crossref","first-page":"4543","DOI":"10.1038\/s41598-025-33630-2","article-title":"Elevated expression of immune checkpoints and pro-inflammatory cytokines as potential biomarkers in pediatric Vulvar Lichen Sclerosus","volume":"16","year":"2026","journal-title":"Sci. Rep"},{"key":"2026060904300727000_2026.05.30.727266v1.3","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.0030116"},{"key":"2026060904300727000_2026.05.30.727266v1.4","first-page":"1","volume-title":"in Integration of AI and OR Techniques in Constraint Programming for Combinatorial Optimization Problems (eds","volume":"5547","year":"2009"},{"key":"2026060904300727000_2026.05.30.727266v1.5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-16-8881-2"},{"key":"2026060904300727000_2026.05.30.727266v1.6","doi-asserted-by":"crossref","first-page":"e1408.","DOI":"10.1002\/wcms.1408","article-title":"Formatting biological big data for modern machine learning in drug discovery","volume":"9","year":"2019","journal-title":"WIREs Comput. Mol. Sci"},{"key":"2026060904300727000_2026.05.30.727266v1.7","doi-asserted-by":"publisher","DOI":"10.3390\/ijms22062903"},{"key":"2026060904300727000_2026.05.30.727266v1.8","doi-asserted-by":"crossref","unstructured":"Liu, X. & Zhang, W. Bioinformatics in the Age of Big Data: Leveraging Computational Tools for Biological Discoveries. Comput. Mol. Biol. 14, (2024).","DOI":"10.5376\/cmb.2024.14.0020"},{"key":"2026060904300727000_2026.05.30.727266v1.9","doi-asserted-by":"crossref","first-page":"20170387","DOI":"10.1098\/rsif.2017.0387","article-title":"Opportunities and obstacles for deep learning in biology and medicine","volume":"15","year":"2018","journal-title":"J. R. Soc.Interface"},{"key":"2026060904300727000_2026.05.30.727266v1.10","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s10462-018-09679-z","article-title":"Machine Learning and Deep Learning frameworks and libraries for large-scale data mining: a survey","volume":"52","year":"2019","journal-title":"Artif. Intell. Rev"},{"key":"2026060904300727000_2026.05.30.727266v1.11","doi-asserted-by":"crossref","first-page":"9921","DOI":"10.1021\/acsomega.3c05913","article-title":"Machine Learning and Deep Learning in Synthetic Biology: Key Architectures, Applications, and Challenges","volume":"9","year":"2024","journal-title":"ACS Omega"},{"key":"2026060904300727000_2026.05.30.727266v1.12","doi-asserted-by":"crossref","first-page":"e1008098","DOI":"10.1371\/journal.pcbi.1008098","article-title":"A machine learning and network framework to discover new indications for small molecules","volume":"16","year":"2020","journal-title":"PLOS Comput. Biol"},{"key":"2026060904300727000_2026.05.30.727266v1.13","doi-asserted-by":"crossref","first-page":"260","DOI":"10.1016\/j.molcel.2021.12.011","article-title":"The use of machine learning to discover regulatory networks controlling biological systems","volume":"82","year":"2022","journal-title":"Mol. Cell"},{"key":"2026060904300727000_2026.05.30.727266v1.14","doi-asserted-by":"crossref","unstructured":"Karpatne, A. , Kannan, R. & Kumar, V. Knowledge Guided Machine Learning: Accelerating Discovery Using Scientific Knowledge and Data. (CRC Press, 2022).","DOI":"10.1201\/9781003143376"},{"key":"2026060904300727000_2026.05.30.727266v1.15","doi-asserted-by":"crossref","first-page":"MSB199198","DOI":"10.15252\/msb.20199198","article-title":"Enhancing scientific discoveries in molecular biology with deep generative models","volume":"16","year":"2020","journal-title":"Mol. Syst. Biol"},{"key":"2026060904300727000_2026.05.30.727266v1.16","doi-asserted-by":"crossref","first-page":"1581","DOI":"10.1038\/s41587-023-02033-x","article-title":"Discovery of sparse, reliable omic biomarkers with Stabl","volume":"42","year":"2024","journal-title":"Nat. Biotechnol"},{"key":"2026060904300727000_2026.05.30.727266v1.17","doi-asserted-by":"crossref","first-page":"965","DOI":"10.1038\/s41598-025-30401-x","article-title":"Explainable machine learning identifies immune-inflammatory biomarkers and therapeutic candidates in drug-resistant epilepsy","volume":"16","year":"2025","journal-title":"Sci. Rep"},{"key":"2026060904300727000_2026.05.30.727266v1.18","doi-asserted-by":"crossref","unstructured":"Li, Z. et al. Identification of immune infiltration and immune-related biomarkers of periprosthetic joint infection. Heliyon 10, (2024).","DOI":"10.1016\/j.heliyon.2024.e26062"},{"key":"2026060904300727000_2026.05.30.727266v1.19","doi-asserted-by":"publisher","DOI":"10.1016\/j.tips.2019.09.008"},{"key":"2026060904300727000_2026.05.30.727266v1.20","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr709"},{"key":"2026060904300727000_2026.05.30.727266v1.21","doi-asserted-by":"crossref","first-page":"103026","DOI":"10.1016\/j.ebiom.2020.103026","article-title":"A linear prognostic score based on the ratio of interleukin-6 to interleukin-10 predicts outcomes in COVID-19","volume":"61","year":"2020","journal-title":"EBioMedicine"},{"key":"2026060904300727000_2026.05.30.727266v1.22","doi-asserted-by":"crossref","first-page":"2755246","DOI":"10.1155\/2022\/2755246","article-title":"Associations between Serum Interleukins (IL-1\u03b2, IL-2, IL-4, IL-6, IL-8, and IL-10) and Disease Severity of COVID-19: A Systematic Review and Meta-Analysis","volume":"2022","year":"2022","journal-title":"BioMed Res. Int"},{"key":"2026060904300727000_2026.05.30.727266v1.23","doi-asserted-by":"crossref","first-page":"e06155","DOI":"10.1016\/j.heliyon.2021.e06155","article-title":"IL-6 and IL-10 as predictors of disease severity in COVID-19 patients: results from meta-analysis and regression","volume":"7","year":"2021","journal-title":"Heliyon"},{"key":"2026060904300727000_2026.05.30.727266v1.24","doi-asserted-by":"crossref","first-page":"152288","DOI":"10.1016\/j.imbio.2022.152288","article-title":"IL-6, IL-10, sFas, granulysin and indicators of intestinal permeability as early biomarkers for a fatal outcome in COVID-19","volume":"227","year":"2022","journal-title":"Immunobiology"},{"key":"2026060904300727000_2026.05.30.727266v1.25","doi-asserted-by":"crossref","first-page":"8043","DOI":"10.2147\/IJGM.S381404","article-title":"Interleukin-1\u03b2 and Interleukin-10 Profiles and Ratio in Serum of COVID-19 Patients and Correlation with COVID-19 Severity: A Time Series Study","volume":"15","year":"2022","journal-title":"Int. J. Gen. Med"},{"key":"2026060904300727000_2026.05.30.727266v1.26","doi-asserted-by":"crossref","first-page":"e139834.","DOI":"10.1172\/jci.insight.139834","article-title":"Longitudinal COVID-19 profiling associates IL-1RA and IL-10 with disease severity and RANTES with mild disease","volume":"5","year":"2020","journal-title":"JCI Insight"},{"key":"2026060904300727000_2026.05.30.727266v1.27","doi-asserted-by":"crossref","first-page":"1416715","DOI":"10.3389\/fimmu.2024.1416715","article-title":"Predictive biomarkers of mortality in patients with severe COVID-19 hospitalized in intensive care unit","volume":"15","year":"2024","journal-title":"Front. Immunol"},{"key":"2026060904300727000_2026.05.30.727266v1.28","doi-asserted-by":"crossref","first-page":"1123","DOI":"10.1080\/22221751.2020.1770129","article-title":"Profiling serum cytokines in COVID-19 patients reveals IL-6 and IL-10 are disease severity predictors","volume":"9","year":"2020","journal-title":"Emerg. Microbes Infect"},{"key":"2026060904300727000_2026.05.30.727266v1.29","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2022-067430"},{"key":"2026060904300727000_2026.05.30.727266v1.30","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-71951-w"},{"key":"2026060904300727000_2026.05.30.727266v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.cyto.2023.156287"},{"key":"2026060904300727000_2026.05.30.727266v1.32","doi-asserted-by":"crossref","first-page":"208","DOI":"10.2478\/jccm-2023-0025","article-title":"The Prognostic Utility of Cytokines in Hospitalized COVID-19 Patients","volume":"9","year":"2023","journal-title":"J. Crit. Care Med"},{"key":"2026060904300727000_2026.05.30.727266v1.33","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(20)30183-5"},{"key":"2026060904300727000_2026.05.30.727266v1.34","doi-asserted-by":"crossref","first-page":"1005636","DOI":"10.3389\/fmed.2022.1005636","article-title":"Cytokine levels as predictors of mortality in critically ill patients with severe COVID-19 pneumonia: Case-control study nested within a cohort in Colombia","volume":"9","year":"2022","journal-title":"Front. Med"},{"key":"2026060904300727000_2026.05.30.727266v1.35","doi-asserted-by":"crossref","first-page":"112","DOI":"10.1038\/s41392-025-02178-y","article-title":"Deep insight into cytokine storm: from pathogenesis to treatment","volume":"10","year":"2025","journal-title":"Signal Transduct.Target. Ther"},{"key":"2026060904300727000_2026.05.30.727266v1.36","doi-asserted-by":"crossref","first-page":"10968","DOI":"10.3390\/ijms231810968","article-title":"Correlation between Type I Interferon Associated Factors and COVID-19 Severity","volume":"23","year":"2022","journal-title":"Int. J. Mol. Sci"},{"key":"2026060904300727000_2026.05.30.727266v1.37","doi-asserted-by":"publisher","DOI":"10.1016\/j.jinf.2020.06.001"},{"key":"2026060904300727000_2026.05.30.727266v1.38","first-page":"e111208.","article-title":"Toll-like receptors matter: plasmacytoid dendritic cells in COVID-19","volume":"41","year":"2022","journal-title":"EMBO J"},{"key":"2026060904300727000_2026.05.30.727266v1.39","doi-asserted-by":"crossref","first-page":"13849","DOI":"10.18632\/aging.103582","article-title":"High neutrophil-to-lymphocyte ratio associated with progression to critical illness in older patients with COVID-19: a multicenter retrospective study","volume":"12","year":"2020","journal-title":"Aging"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.05.30.727266","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T11:30:21Z","timestamp":1781004621000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.05.30.727266"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,5]]},"references-count":39,"URL":"https:\/\/doi.org\/10.64898\/2026.05.30.727266","relation":{},"subject":[],"published":{"date-parts":[[2026,6,5]]},"subtype":"preprint"}}