Biologically informed deep neural network for prostate cancer discovery

Haitham A. Elmarakeby, Justin Hwang, Rand Arafeh, Jett Crowdis, Sydney Gang, David Liu, Saud H. AlDubayan, Keyan Salari, Steven Kregel, Camden Richter, Taylor E. Arnoff, Jihye Park, William C. Hahn, Eliezer M. Van Allen

Research output: Contribution to journalArticlepeer-review


The determination of molecular features that mediate clinically aggressive phenotypes in prostate cancer remains a major biological and clinical challenge1,2. Recent advances in interpretability of machine learning models as applied to biomedical problems may enable discovery and prediction in clinical cancer genomics3–5. 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.

Original languageEnglish (US)
Pages (from-to)348-352
Number of pages5
Issue number7880
StatePublished - Oct 14 2021

Bibliographical note

Funding Information:
Acknowledgements This work was supported by Fund for Innovation in Cancer Informatics (H.A.E. and E.M.V.A.), Mark Foundation Emerging Leader Award (E.M.V.), PCF-Movember Challenge Award (H.A.E. and E.M.V.A.), Physician Research Award (PC200150) of the US Department of Defense (S.H.A.), NIH U01 CA233100 (E.M.V.A.) and U01 CA176058 (W.C.H.)

Publisher Copyright:
© 2021, The Author(s), under exclusive licence to Springer Nature Limited.

PubMed: MeSH publication types

  • Journal Article
  • Research Support, N.I.H., Extramural
  • Research Support, Non-U.S. Gov't
  • Research Support, U.S. Gov't, Non-P.H.S.


Dive into the research topics of 'Biologically informed deep neural network for prostate cancer discovery'. Together they form a unique fingerprint.

Cite this