Benchmarking computational methods for multi-omics biomarker discovery in cancer
Briefings in Bioinformatics · 2026
DOI: 10.1093/bib/bbag200 ↗Kurz gefasst
Fachartikel in der Zeitschrift Briefings in Bioinformatics, 2026. Verfasst von Athan Z Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, University of Southern California, 1031 Downey Way, Ginsburg Hall, 90089 CA, United States. Hauptthemen laut MEDLINE: Multiomics, Biomarkers, Tumor, Neoplasms, Computational Biology. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 73 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Multi-omics profiling characterizes cancer biology and supports biomarker discovery for prognosis and therapy selection. Although numerous computational multi-omics biomarker identification methods have been proposed, their ability to identify clinically relevant biomarkers has not been systematically evaluated, leaving it unclear whether the resulting biomarker nominations are reliable for downstream validation. Here, we systematically benchmark 20 representative statistical, machine learning and deep learning methods using curated gold-standard prognostic and therapeutic biomarkers across five real-world datasets. We evaluate performance in terms of both biomarker identification accuracy and stability. Overall, DeePathNet and DeepKEGG achieve the best performance. Across methods, effective biomarker recovery is associated with the integration of biological knowledge, global feature interactions, multivariate feature attribution, and effective regularization. Analysis of omics type contributions reveals method- and modality-specific biases, highlighting the importance of broader omics integration. We further evaluate methods on simulated datasets to probe sensitivity with controlled signal and noise. By aggregating results from top-performing methods, we construct consensus biomarker panels that nominate candidates for potential investigations. Finally, we provide user-friendly interfaces to allow researchers to benchmark new methods against the 20 baselines or apply selected methods for biomarker identification on custom multi-omics datasets. Our benchmark is publicly available at https://github.com/athanzli/CancerMOBI-Bench.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Computer Science, University of Southern California, 1031 Downey Way, Ginsburg Hall, 90089 CA, United States.
- Department of Electrical Engineering, University of Texas at San Antonio, One UTSA Circle, Biotechnology Science and Engineering Building, 78249 TX, United States.
- Department of Quantitative and Computational Biology, University of Southern California, 1050 Childs Way, Ray R. Irani Hall, 90089 CA, United States.
ORCID-Profile: Athan Z Li, Yuxuan Du, Yan Liu, Liang Chen, Ruishan Liu
Zitieren
APA
Li, A. Z., Du, Y., Liu, Y., Chen, L., & Liu, R. (2026). Benchmarking computational methods for multi-omics biomarker discovery in cancer. Briefings in Bioinformatics. https://doi.org/10.1093/bib/bbag200
Vancouver
Li AZ, Du Y, Liu Y, Chen L, Liu R. Benchmarking computational methods for multi-omics biomarker discovery in cancer. Briefings in Bioinformatics. 2026. doi:10.1093/bib/bbag200
BibTeX
@article{Li2026,
author = {Li, Athan Z and Du, Yuxuan and Liu, Yan and Chen, Liang and Liu, Ruishan},
title = {Benchmarking computational methods for multi-omics biomarker discovery in cancer},
journal = {Briefings in Bioinformatics},
year = {2026},
doi = {10.1093/bib/bbag200}
}
EUVIMED