Genome Biology: TMO-Net advances explainable multi-omics learning in oncology

Our team published TMO-Net in Genome Biology, an explainable pretrained multi-omics model designed for multi-task learning in oncology.

The work focuses on learning transferable biological representations across omics modalities while keeping model outputs interpretable for downstream cancer research and precision oncology applications.

Key points:

• Introduced a pretrained multi-omics framework for multi-task oncology modeling.
• Emphasized explainability rather than treating multi-omics prediction as a pure black box.
• Expanded the potential of shared representation learning for precision oncology workflows.

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