MCOF: A Multi-Channel Attention-Based Omics Fusion Framework for Cancer Subtyping and Candidate Biomarker Prioritization
International Journal of Molecular Sciences · 2026
DOI: 10.3390/ijms27198519 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2026. Verfasst von Xuezhi Liang und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Statistics, School of Public Health, Sun Yat-sen University, Guangzhou 510080, China. Hauptthemen laut MEDLINE: Biomarkers, Tumor, Neoplasms, Computational Biology, Breast Neoplasms. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Department of Science and Technology of Guangdong Province, Science and Technology Program of Guangzhou, Natural Science Foundation of Guangdong Province, China.
Abstract (Originalsprache)
Multi-omics molecular subtyping is complicated by small cohorts, heterogeneous data layers, and sensitivity to data splitting and feature selection. We developed multi-channel attention-based omics fusion (MCOF), an end-to-end framework that combines omics-specific projection, one-dimensional convolution, and integrated gradients for candidate biomarker prioritization. MCOF was evaluated against six baselines using five repeated stratified holdouts across four multi-omics datasets. In the restricted four-class breast invasive carcinoma task, MCOF achieved the highest observed mean for all five metrics, including an accuracy of 0.900 ± 0.022 and a macro-averaged area under the receiver operating characteristic curve (macro-AUC) of 0.982 ± 0.003. In the restricted three-class stomach adenocarcinoma task, it achieved the highest observed macro-F1 (0.786 ± 0.035), macro-AUC (0.934 ± 0.020), and weighted-AUC (0.930 ± 0.016), whereas support vector machines had a slightly higher accuracy and weighted F1. It also achieved the highest or near-highest AUC on the two non-cancer datasets. Compared with MOGONET, MCOF used 30.6% fewer trainable parameters on both cancer tasks. Sensitivity analyses indicated that the contribution of multi-omics fusion varied by dataset and metric. Excluding the 28 prediction analysis of microarray 50 (PAM50) genes present in the retained BRCA RNA panel produced only a modest reduction in the macro-AUC, from 0.982 ± 0.003 to 0.978 ± 0.004. Implementation tests across 20 trained checkpoints detected no batch-order effect or cross-sample gradient, while the IG rankings were moderately stable across repeated holdouts and numerically consistent across class-weighting schemes and 25–100 integration steps. MCOF provides a practical framework for multi-omics classification and candidate prioritization.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Medical Statistics, School of Public Health, Sun Yat-sen University, Guangzhou 510080, China.
- Center for Migrant Health Policy, Sun Yat-sen University, Guangzhou 510080, China.
ORCID-Profile: Wen Chen
Förderung
- Department of Science and Technology of Guangdong Province
- Science and Technology Program of Guangzhou
- Natural Science Foundation of Guangdong Province, China
Zitieren
APA
Liang, X., Wang, Q., Xie, K., Zhang, J., Feng, S., Zhong, X., Guo, T., Zhang, Y., & Chen, W. (2026). MCOF: A Multi-Channel Attention-Based Omics Fusion Framework for Cancer Subtyping and Candidate Biomarker Prioritization. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms27198519
Vancouver
Liang X, Wang Q, Xie K, Zhang J, Feng S, Zhong X, et al. MCOF: A Multi-Channel Attention-Based Omics Fusion Framework for Cancer Subtyping and Candidate Biomarker Prioritization. International Journal of Molecular Sciences. 2026. doi:10.3390/ijms27198519
BibTeX
@article{Liang2026,
author = {Liang, Xuezhi and Wang, Qi and Xie, Kun and Zhang, Jianghui and Feng, Shiyu and Zhong, Xinyuan and Guo, Tingting and Zhang, Yi and Chen, Wen},
title = {MCOF: A Multi-Channel Attention-Based Omics Fusion Framework for Cancer Subtyping and Candidate Biomarker Prioritization},
journal = {International Journal of Molecular Sciences},
year = {2026},
doi = {10.3390/ijms27198519}
}
EUVIMED