Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patients

Jie Ju; Leonoor V Wismans; Dana A M Mustafa; Marcel J T Reinders; Casper H J van Eijck; Andrew P Stubbs; Yunlei Li

doi:10.1016/j.isci.2021.103415

Robust deep learning model for prognostic stratification of pancreatic ductal adenocarcinoma patients

iScience. 2021 Nov 10;24(12):103415. doi: 10.1016/j.isci.2021.103415. eCollection 2021 Dec 17.

Authors

Jie Ju¹, Leonoor V Wismans², Dana A M Mustafa¹, Marcel J T Reinders³, Casper H J van Eijck², Andrew P Stubbs¹, Yunlei Li¹

Affiliations

¹ Department of Pathology & Clinical Bioinformatics, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands.
² Department of Surgery, Erasmus MC Cancer Institute, University Medical Center Rotterdam, Rotterdam, the Netherlands.
³ The Delft Bioinformatics Lab, Delft University of Technology, Rotterdam, the Netherlands.

Abstract

A major challenge for treating patients with pancreatic ductal adenocarcinoma (PDAC) is the unpredictability of their prognoses due to high heterogeneity. We present Multi-Omics DEep Learning for Prognosis-correlated subtyping (MODEL-P) to identify PDAC subtypes and to predict prognoses of new patients. MODEL-P was trained on autoencoder integrated multi-omics of 146 patients with PDAC together with their survival outcome. Using MODEL-P, we identified two PDAC subtypes with distinct survival outcomes (median survival 10.1 and 22.7 months, respectively, log rank p = 1 × 10^-6), which correspond to DNA damage repair and immune response. We rigorously validated MODEL-P by stratifying patients in five independent datasets into these two survival groups and achieved significant survival difference, which is superior to current practice and other subtyping schemas. We believe the subtype-specific signatures would facilitate PDAC pathogenesis discovery, and MODEL-P can provide clinicians the prognoses information in the treatment decision-making to better gauge the benefits versus the risks.

Keywords: Biocomputational method; Cancer; Cancer systems biology.