Deep learning based on multi-omics integration identifies potential therapeutic targets in breast cancer

Abstract

Effective and precise classification of breast cancer patients for their disease risks is critical to improve early diagnosis and patient survival. In the recent past, a significant amount of multi-omics data derived from cancer patients has emerged. However, a robust framework for integrating multi-omics data to subgroup cancer patients and predict survival prognosis is still lacking. In addition, effective therapeutic targets for treating breast cancer patients with poor prognoses are in dire need. To begin to resolve this difficulty, we developed and optimized a sophisticated deep learning-based model in breast cancer that can accurately stratify patients based on their prognosis. We built a survival-associated predictive framework integrating transcription profile, miRNA expression, somatic mutations, copy number variation, DNA methylation and protein expression. This framework achieved promising performance in distinguishing high-risk breast cancer patients from those with good prognoses. Furthermore, we constructed multiple fully connected neural networks that are trained on prioritized multi-omics signatures or even only potential single-omics signatures, based on our customized scoring system. Together, the landmark multi-omics signatures we identified may serve as potential therapeutic targets in breast cancer.