CMGL: confidence-guided multi-omics graph learning for cancer subtype classification
Bioinformatics · 2026
DOI: 10.1093/bioinformatics/btag763 ↗Kurz gefasst
Fachartikel in der Zeitschrift Bioinformatics, 2026. Verfasst von Boyang Fan und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Computer Science, Sichuan University, Chengdu 610065, China. Hauptthemen laut MEDLINE: Multiomics, Neoplasms, Computational Biology. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Postdoctoral Fellowship Program (Grade A) of CPSF, Sichuan Science and Technology.
Abstract (Originalsprache)
Motivation Multi-omics integration can improve cancer subtyping, but modality informativeness and noise vary across cancer types and patients. Most graph methods for multi-omics data learn modality contributions within the downstream classification objective, leaving predictive reliability for each patient implicit. As a result, uninformative modalities can weaken the fused representation, while unreliable omics can introduce noisy patient relationships into graph propagation. To address these two problems, we propose confidence-guided multi-omics graph learning (CMGL), which produces a separate reliability estimate before fusion and uses consensus patient neighborhoods for graph classification. Results CMGL estimates modality confidence for each patient through evidential deep learning, fixes these values during fusion across omics, and performs classification on an independently specified consistency graph. On four MLOmics cancer-subtype tasks and the 32-class pan-cancer task, CMGL consistently improves over the strongest baseline, surpassing it by 4.03% in average accuracy on the four single-cancer tasks. Its representations recover the PAM50 intrinsic subtypes of breast invasive carcinoma (BRCA), and the model trained on BRCA transfers without fine tuning to kidney renal clear cell carcinoma, stratifying patients into prognostically distinct groups. Availability and implementation The code is available at https://doi.org/10.5281/zenodo.21921069.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- College of Computer Science, Sichuan University, Chengdu 610065, China.
- Xinjiang Technical Institute of Physics and Chemistry, Chinese Academy of Sciences, Urumqi 830011, China.
- College of Mathematics, Sichuan University, Chengdu 610065, China.
- School of Artificial Intelligence and Data Science, University of International Business and Economics, Beijing 100029, China.
- School of Artificial Intelligence, Sichuan University, Chengdu 610065, China.
ORCID-Profile: Hengchuang Yin, Wei Ju
Förderung
- National Natural Science Foundation of China
- Postdoctoral Fellowship Program (Grade A) of CPSF
- Sichuan Science and Technology
- Natural Science Foundation of Xinjiang Uygur Autonomous Region
- Xinjiang Leading Talent Recruitment
Zitieren
APA
Fan, B., Yin, H., Yi, S., Wang, Y., Li, Z., Zhou, L., Lv, J., & Ju, W. (2026). CMGL: confidence-guided multi-omics graph learning for cancer subtype classification. Bioinformatics. https://doi.org/10.1093/bioinformatics/btag763
Vancouver
Fan B, Yin H, Yi S, Wang Y, Li Z, Zhou L, et al. CMGL: confidence-guided multi-omics graph learning for cancer subtype classification. Bioinformatics. 2026. doi:10.1093/bioinformatics/btag763
BibTeX
@article{Fan2026,
author = {Fan, Boyang and Yin, Hengchuang and Yi, Siyu and Wang, Yifan and Li, Zhicheng and Zhou, Leijiyu and Lv, Jiancheng and Ju, Wei},
title = {CMGL: confidence-guided multi-omics graph learning for cancer subtype classification},
journal = {Bioinformatics},
year = {2026},
doi = {10.1093/bioinformatics/btag763}
}
EUVIMED