Biologically informed deep neural network for prostate cancer discovery

TLDR

Identifying molecular drivers of aggressive prostate cancer remains a major challenge, but recent advances in interpretable machine learning may enable discovery and prediction in clinical cancer genomics. The study developed P‑NET, a biologically informed deep learning model, to stratify prostate cancer patients by treatment‑resistance state and evaluate molecular drivers for therapeutic targeting through complete model interpretability. P‑NET integrates molecular data into a deep neural network that predicts treatment‑resistance status and allows full interpretability of its predictions. P‑NET outperforms other models in predicting cancer state, identifies known and novel drivers such as MDM4 and FGFR1, and demonstrates that biologically informed interpretable neural networks can support preclinical discovery and clinical prediction in prostate cancer, with potential applicability to other cancers.

Abstract

Abstract The determination of molecular features that mediate clinically aggressive phenotypes in prostate cancer remains a major biological and clinical challenge 1,2 . Recent advances in interpretability of machine learning models as applied to biomedical problems may enable discovery and prediction in clinical cancer genomics 3–5 . Here we developed P-NET—a biologically informed deep learning model—to stratify patients with prostate cancer by treatment-resistance state and evaluate molecular drivers of treatment resistance for therapeutic targeting through complete model interpretability. We demonstrate that P-NET can predict cancer state using molecular data with a performance that is superior to other modelling approaches. Moreover, the biological interpretability within P-NET revealed established and novel molecularly altered candidates, such as MDM4 and FGFR1 , which were implicated in predicting advanced disease and validated in vitro. Broadly, biologically informed fully interpretable neural networks enable preclinical discovery and clinical prediction in prostate cancer and may have general applicability across cancer types.