TMO-Net: an explainable pretrained multi-omics model for multi-task learning in oncology

作者：Feng‐ao Wang, Zhenfeng Zhuang, Feng Gao, Ruikun He, Shaoting Zhang, Liansheng Wang, Junwei Liu, Y Li · 发表于：Genome biology · 年份：2024 · DOI：10.1186/s13059-024-03293-9 · 被引用次数：47 · 研究领域：Bioinformatics and Genomic Networks、Cancer Genomics and Diagnostics、Gene expression and cancer classification

Cancer is a complex disease composing systemic alterations in multiple scales. In this study, we develop the Tumor Multi-Omics pre-trained Network (TMO-Net) that integrates multi-omics pan-cancer datasets for model pre-training, facilitating cross-omics interactions and enabling joint representation learning and incomplete omics inference. This model enhances multi-omics sample representation and empowers various downstream oncology tasks with incomplete multi-omics datasets. By employing interpretable learning, we characterize the contributions of distinct omics features to clinical outcomes. The TMO-Net model serves as a versatile framework for cross-modal multi-omics learning in oncology, paving the way for tumor omics-specific foundation models.