{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T11:40:50Z","timestamp":1782906050834,"version":"3.54.5"},"reference-count":46,"publisher":"Oxford University Press (OUP)","issue":"3","license":[{"start":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000},"content-version":"vor","delay-in-days":7,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004410","name":"Scientific and Technological Research Council of Turkey","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004410","id-type":"DOI","asserted-by":"publisher"}]},{"name":"EU Joint Programme\u2014Neurodegenerative Disease Research","award":["124N069"],"award-info":[{"award-number":["124N069"]}]},{"name":"Scientific Research Projects Unit of Istanbul Technical University","award":["TGA-2025-46998"],"award-info":[{"award-number":["TGA-2025-46998"]}]},{"name":"National Center for High-Performance Computing","award":["1009742021"],"award-info":[{"award-number":["1009742021"]}]},{"name":"Italian Ministry of Health\u2014EU Joint Programme\u2014Neurodegenerative Disease Research"},{"DOI":"10.13039\/501100004281","name":"Polish National Science Centre","doi-asserted-by":"crossref","award":["2023\/05\/Y\/NZ3\/00160"],"award-info":[{"award-number":["2023\/05\/Y\/NZ3\/00160"]}],"id":[{"id":"10.13039\/501100004281","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100010414","name":"Health Research Board","doi-asserted-by":"publisher","award":["JPND-2023-1"],"award-info":[{"award-number":["JPND-2023-1"]}],"id":[{"id":"10.13039\/100010414","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The integration of multi-omics data holds great promise for identifying robust and clinically relevant biomarkers, yet the increasing complexity of computational methods raises questions about their practical utility. In this study, we present a comprehensive benchmarking framework that evaluates 27 feature selection strategies and 11 predictive models across three real-world disease cohorts: Alzheimer\u2019s disease, progressive supranuclear palsy, and breast cancer. We compare traditional machine learning, ensemble-based methods, and state-of-the-art deep learning models in terms of predictive performance, stability, and biological interpretability. Our results reveal that ensemble feature selection consistently improves robustness and accuracy, particularly for compact biomarker panels. Surprisingly, deep learning models did not outperform simpler classifiers such as logistic regression (L.Regression), support vector machines, or multilayer perceptrons, which often achieved comparable or superior results with lower computational cost and greater interpretability. Triple-omics yielded the highest validation, followed by dual-omics and then single-omics (Triple &amp;gt; Dual &amp;gt; Single). Biological validation against five independent databases confirmed the clinical relevance of the identified biomarkers, including both well-established and novel candidates. To support reproducibility and community adoption, we provide a web-based tool for applying our benchmarking pipeline. Our findings advocate for a pragmatic approach to biomarker discovery\u2014prioritizing methodological transparency, reproducibility, and biological insight over algorithmic complexity.<\/jats:p>","DOI":"10.1093\/bib\/bbag211","type":"journal-article","created":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T11:39:09Z","timestamp":1776253149000},"source":"Crossref","is-referenced-by-count":1,"title":["When complexity does not pay: benchmarking deep learning and ensemble methods for biomarker discovery"],"prefix":"10.1093","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-6527-9108","authenticated-orcid":false,"given":"Cyrille Mesue","family":"Njume","sequence":"first","affiliation":[{"name":"Department of Molecular Biology and Genetics, Ayazaga Campus, Istanbul Technical University , Re\u015fitpa\u015fa, Sar\u0131yer, 34467 Istanbul,","place":["Turkey"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irene","family":"Petracci","sequence":"additional","affiliation":[{"name":"Molecular Markers Laboratory, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli , 25125 Brescia,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6162-252X","authenticated-orcid":false,"given":"Sonia","family":"Bellini","sequence":"additional","affiliation":[{"name":"Molecular Markers Laboratory, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli , 25125 Brescia,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katarzyna","family":"Goljanek-Whysall","sequence":"additional","affiliation":[{"name":"Discipline of Physiology, School of Medicine, University of Galway , H91 TH33 Galway,","place":["Ireland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Leo R","family":"Quinlan","sequence":"additional","affiliation":[{"name":"Discipline of Physiology, School of Medicine, University of Galway , H91 TH33 Galway,","place":["Ireland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Agnieszka","family":"Fiszer","sequence":"additional","affiliation":[{"name":"Department of Medical Biotechnology, Institute of Bioorganic Chemistry, Polish Academy of Sciences , Noskowskiego 12\/14, 61-704 Poznan,","place":["Poland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Barbara","family":"Borroni","sequence":"additional","affiliation":[{"name":"Molecular Markers Laboratory, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli , 25125 Brescia,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Roberta","family":"Ghidoni","sequence":"additional","affiliation":[{"name":"Molecular Markers Laboratory, IRCCS Istituto Centro San Giovanni di Dio Fatebenefratelli , 25125 Brescia,","place":["Italy"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Asli","family":"Kumbasar","sequence":"additional","affiliation":[{"name":"Department of Molecular Biology and Genetics, Ayazaga Campus, Istanbul Technical University, Re\u015fitpa\u015fa , Sar\u0131yer, 34467 Istanbul,","place":["Turkey"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1382-6130","authenticated-orcid":false,"given":"Ali","family":"Cakmak","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Ayazaga Campus, Istanbul Technical University , Re\u015fitpa\u015fa, Sar\u0131yer, 34467 Istanbul,","place":["Turkey"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"2026050811330859300_ref1","article-title":"Multi-omics approaches to disease","volume":"18","author":"Hasin","year":"2017","journal-title":"Genome Biol"},{"key":"2026050811330859300_ref2","first-page":"117793221989905","article-title":"Multi-omics data integration, interpretation, and its application","volume":"14","author":"Subramanian","year":"2020","journal-title":"Bioinform Biol Insights"},{"key":"2026050811330859300_ref3","article-title":"Salmon: survival analysis learning with multi-omics neural networks on breast cancer","volume":"10","author":"Huang","year":"2019","journal-title":"Front Genet"},{"key":"2026050811330859300_ref4","article-title":"Athena: identifying interactions between different levels of genomic data associated with cancer clinical outcomes using grammatical evolution neural network","volume":"6","author":"Kim","year":"2013","journal-title":"BioData Min"},{"key":"2026050811330859300_ref5","first-page":"30","article-title":"Improved breast cancer prognosis through the combination of clinical and genetic markers","volume":"23","author":"Sun","year":"2006","journal-title":"Bioinformatics"},{"key":"2026050811330859300_ref6","first-page":"37","article-title":"The properties of high-dimensional data spaces: implications for exploring gene and protein expression data","volume":"8","author":"Clarke","year":"2008","journal-title":"Nat Rev Cancer"},{"key":"2026050811330859300_ref7","first-page":"e124","article-title":"Why most published research findings are false","volume":"2","author":"Ioannidis","year":"2005","journal-title":"PLoS Med"},{"key":"2026050811330859300_ref8","first-page":"556","article-title":"Stability and aggregation of ranked gene lists","volume":"10","author":"Boulesteix","year":"2009","journal-title":"Brief Bioinform"},{"key":"2026050811330859300_ref9","first-page":"5923","article-title":"Thousands of samples are needed to generate a robust gene list for predicting outcome in cancer","volume":"103","author":"Ein-Dor","year":"2006","journal-title":"Proc Natl Acad Sci USA"},{"key":"2026050811330859300_ref10","first-page":"488","article-title":"Prediction of cancer outcome with microarrays: a multiple random validation strategy","volume":"365","author":"Michiels","year":"2005","journal-title":"Lancet"},{"key":"2026050811330859300_ref11","first-page":"469","article-title":"Batch effect removal methods for microarray gene expression data integration: a survey","volume":"14","author":"Lazar","year":"2012","journal-title":"Brief Bioinform"},{"key":"2026050811330859300_ref12","first-page":"498","article-title":"Why batch effects matter in omics data, and how to avoid them","volume":"35","author":"Goh","year":"2017","journal-title":"Trends Biotechnol"},{"key":"2026050811330859300_ref13","first-page":"356","article-title":"A review of the stability of feature selection techniques for bioinformatics data","volume-title":"2012 IEEE 13th International Conference on Information Reuse & Integration (IRI)","author":"Awada","year":"2012"},{"key":"2026050811330859300_ref14","first-page":"95","article-title":"Stability of feature selection algorithms: a study on high-dimensional spaces","volume":"12","author":"Kalousis","year":"2006","journal-title":"Knowl Inf Syst"},{"key":"2026050811330859300_ref15","first-page":"5951","article-title":"Ensemble feature selection for high-dimensional data: a stability analysis across multiple domains","volume":"32","author":"Pes","year":"2019","journal-title":"Neural Comput Applic"},{"key":"2026050811330859300_ref16","first-page":"242","article-title":"Robust clinical marker identification for diabetic kidney disease with ensemble feature selection","volume":"26","author":"Song","year":"2019","journal-title":"J Am Med Inform Assoc"},{"key":"2026050811330859300_ref17","first-page":"227","article-title":"On developing an automatic threshold applied to feature selection ensembles","volume":"45","author":"Seijo-Pardo","year":"2019","journal-title":"Inf Fusion"},{"key":"2026050811330859300_ref18","article-title":"Ensemble feature selection with data-driven thresholding for Alzheimer\u2019s disease biomarker discovery","volume":"24","author":"Spooner","year":"2023","journal-title":"BMC Bioinformatics"},{"key":"2026050811330859300_ref19","first-page":"2353","article-title":"An ensemble feature selection approach for analysis and modeling of transcriptome data in Alzheimer\u2019s disease","volume":"13","author":"Paplomatas","year":"2023","journal-title":"Appl Sci"},{"key":"2026050811330859300_ref20","article-title":"Optimizing hybrid ensemble feature selection strategies for transcriptomic biomarker discovery in complex diseases","volume":"6","author":"Claude","year":"2024","journal-title":"NAR Genom Bioinform"},{"key":"2026050811330859300_ref21","first-page":"2085","article-title":"Homogeneous ensemble feature selection for mass spectrometry data prediction in cancer studies","volume":"12","author":"Liang","year":"2024","journal-title":"Mathematics"},{"key":"2026050811330859300_ref22","article-title":"Feature selection of omic data by ensemble swarm intelligence based approaches","volume":"12","author":"Yao","year":"2022","journal-title":"Front Genet"},{"key":"2026050811330859300_ref23","article-title":"A robust ensemble feature selection approach to prioritize genes associated with survival outcome in high-dimensional gene expression data","volume":"4","author":"Le","year":"2024","journal-title":"Front Syst Biol"},{"key":"2026050811330859300_ref24","article-title":"Filter and wrapper stacking ensemble (FWSE): a robust approach for reliable biomarker discovery in high-dimensional omics data","volume":"24","author":"Budhraja","year":"2023","journal-title":"Brief Bioinform"},{"key":"2026050811330859300_ref25","article-title":"Benchmark study of feature selection strategies for multi-omics data","volume":"23","author":"Li","year":"2022","journal-title":"BMC Bioinformatics"},{"key":"2026050811330859300_ref26","first-page":"11103","article-title":"Stability of feature selection in multi-omics data analysis","volume":"14","author":"\u0141ukaszuk","year":"2024","journal-title":"Appl Sci"},{"key":"2026050811330859300_ref27","first-page":"D1328","article-title":"Comparative toxicogenomics database\u2019s 20th anniversary: update 2025","volume":"53","author":"Davis","year":"2024","journal-title":"Nucleic Acids Res"},{"key":"2026050811330859300_ref28","first-page":"D1327","article-title":"HMDD v4.0: a database for experimentally supported human microRNA-disease associations","volume":"52","author":"Cui","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026050811330859300_ref29","first-page":"656","article-title":"GeneCards: a novel functional genomics compendium with automated data mining and query reformulation support","volume":"14","author":"Rebhan","year":"1998","journal-title":"Bioinformatics"},{"key":"2026050811330859300_ref30","article-title":"GMQN: a reference-based method for correcting batch effects and probe bias in humanmethylation beadchip","volume":"12","author":"Xiong","year":"2022","journal-title":"Front Genet"},{"key":"2026050811330859300_ref31","article-title":"Multi-omics integration of scRNA-seq time series data predicts new intervention points for Parkinson\u2019s disease","volume":"14","author":"Mihajlovi\u0107","year":"2024","journal-title":"Sci Rep"},{"key":"2026050811330859300_ref32","article-title":"Effective integration of multi-omics with prior knowledge to identify biomarkers via explainable graph neural networks","volume":"11","author":"Tripathy","year":"2025","journal-title":"NPJ Syst Biol Appl"},{"key":"2026050811330859300_ref33","first-page":"1351","article-title":"Identification and external validation of the hub genes associated with cardiorenal syndrome through time-series and network analyses","volume":"14","author":"Liang","year":"2022","journal-title":"Aging"},{"key":"2026050811330859300_ref34","article-title":"MORE: a multi-omics data-driven hypergraph integration network for biomedical data classification and biomarker identification","volume":"26","author":"Wang","year":"2024","journal-title":"Brief Bioinform"},{"key":"2026050811330859300_ref35","article-title":"MOGONET integrates multi-omics data using graph convolutional networks allowing patient classification and biomarker identification","volume":"12","author":"Wang","year":"2021","journal-title":"Nat Commun"},{"key":"2026050811330859300_ref36","article-title":"The ROSMAP project: aging and neurodegenerative diseases through omic sciences","volume":"18","author":"P\u00e9rez-Gonz\u00e1lez","year":"2024","journal-title":"Front Neuroinform"},{"key":"2026050811330859300_ref37","article-title":"Human whole genome genotype and transcriptome data for Alzheimer\u2019s and other neurodegenerative diseases","volume":"3","author":"Allen","year":"2016","journal-title":"Sci Data"},{"key":"2026050811330859300_ref38","first-page":"675","article-title":"Visualizing and interpreting cancer genomics data via the xena platform","volume":"38","author":"Goldman","year":"2020","journal-title":"Nat Biotechnol"},{"key":"2026050811330859300_ref39","first-page":"W207","article-title":"g:Profiler\u2014interoperable web service for functional enrichment analysis and gene identifier mapping (2023 update)","volume":"51","author":"Kolberg","year":"2023","journal-title":"Nucleic Acids Res"},{"key":"2026050811330859300_ref40","first-page":"628","article-title":"Overview and findings from the religious orders study","volume":"9","author":"Bennett","year":"2012","journal-title":"Curr Alzheimer Res"},{"key":"2026050811330859300_ref41","first-page":"180142","article-title":"A multi-omic atlas of the human frontal cortex for aging and Alzheimer\u2019s disease research","volume":"5","author":"De Jager","year":"2018","journal-title":"Sci Data"},{"key":"2026050811330859300_ref42","first-page":"1113","article-title":"The cancer genome atlas pan-cancer analysis project","volume":"45","author":"Weinstein","year":"2013","journal-title":"Nat Genet"},{"key":"2026050811330859300_ref43","first-page":"182","article-title":"Biomarkers: potential uses and limitations","volume":"1","author":"Mayeux","year":"2004","journal-title":"NeuroRX"},{"key":"2026050811330859300_ref44","first-page":"2027","article-title":"Blood-based biomarkers of Alzheimer\u2019s disease and incident dementia in the community","volume":"31","author":"Grande","year":"2025","journal-title":"Nat Med"},{"key":"2026050811330859300_ref45","article-title":"Biomark: biomarker analysis tool","volume":"27","author":"Balikci","year":"2026","journal-title":"BMC Bioinformatics"},{"key":"2026050811330859300_ref46","first-page":"573","article-title":"Robust rank aggregation for gene list integration and meta-analysis","volume":"28","author":"Kolde","year":"2012","journal-title":"Bioinformatics"}],"container-title":["Briefings in Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag211\/68250978\/bbag211.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bib\/article-pdf\/27\/3\/bbag211\/68250978\/bbag211.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:33:12Z","timestamp":1778254392000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bib\/article\/doi\/10.1093\/bib\/bbag211\/8673068"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":46,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,5,3]]}},"URL":"https:\/\/doi.org\/10.1093\/bib\/bbag211","relation":{},"ISSN":["1467-5463","1477-4054"],"issn-type":[{"value":"1467-5463","type":"print"},{"value":"1477-4054","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,5]]},"published":{"date-parts":[[2026,5]]},"article-number":"bbag211"}}