DeepProg: an ensemble of deep-learning and machine-learning models for prognosis prediction using multi-omics data

TLDR

Multi‑omics data are valuable for prognosis but difficult to integrate computationally. We introduce DeepProg, an ensemble framework that robustly predicts patient survival subtypes using multi‑omics data. DeepProg combines deep‑learning and machine‑learning models into an ensemble that integrates multi‑omics data to predict survival subtypes. DeepProg identifies two optimal survival subtypes across most cancers, achieves superior risk stratification (C‑index 0.68–0.80), links poor‑survival subtypes to extracellular matrix remodeling, immune deregulation, and mitosis, and is freely available on GitHub.

Abstract

Abstract Multi-omics data are good resources for prognosis and survival prediction; however, these are difficult to integrate computationally. We introduce DeepProg, a novel ensemble framework of deep-learning and machine-learning approaches that robustly predicts patient survival subtypes using multi-omics data. It identifies two optimal survival subtypes in most cancers and yields significantly better risk-stratification than other multi-omics integration methods. DeepProg is highly predictive, exemplified by two liver cancer (C-index 0.73–0.80) and five breast cancer datasets (C-index 0.68–0.73). Pan-cancer analysis associates common genomic signatures in poor survival subtypes with extracellular matrix modeling, immune deregulation, and mitosis processes. DeepProg is freely available at https://github.com/lanagarmire/DeepProg