arXiv：cs.LG· Boyang Fan, Hengchuang Yin, Siyu Yi, Yifan Wang, Zhicheng Li, Leijiyu Zhou, Jiancheng Lv, Wei Ju·· 3 小时前
CMGL：面向癌症亚型分类的置信度引导多组学图学习
CMGL: Confidence-guided Multi-omics Graph Learning for Cancer Subtype Classification
AI 导读
CMGL 通过证据深度学习为每位患者估计各模态置信度，在融合前固定这些值，并在独立构建的一致性图上做分类。在四个 MLOmics 癌症亚型任务上，其平均准确率超过最强基线 4.03%；在 32 类泛癌任务上也持续领先。其表征可恢复 BRCA 的 PAM50 内在亚型，且在 BRCA 上训练的模型无需微调即可迁移至 KIRC，将患者分为预后显著不同的组。
正文
Abstract: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 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 (KIRC), stratifying patients into prognostically distinct groups.
| Subjects: | Machine Learning (cs.LG); Genomics (q-bio.GN); Molecular Networks (q-bio.MN) |
| MSC classes: | 62H30, 68T07, 92C40 |
| ACM classes: | I.2.6; J.3 |
| Cite as: | arXiv:2604.24201 [cs.LG] |
| (or arXiv:2604.24201v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2604.24201 arXiv-issued DOI via DataCite |
Submission history
From: Boyang Fan [view email]
[v1]
Mon, 27 Apr 2026 09:02:50 UTC (4,362 KB)
[v2]
Thu, 8 Oct 2026 15:24:09 UTC (2,767 KB)
来源：arXiv：cs.LG · arxiv.org