Related Experiment Video
Updated: Dec 11, 2025
Prostate Organoid Cultures as Tools to Translate Genotypes and Mutational Profiles to Pharmacological Responses
Published on: October 24, 2019
Deep Learning Modeling of Androgen Receptor Responses to Prostate Cancer Therapies
Oliver Snow1, Nada Lallous2, Martin Ester1
1School of Computing Science, Simon Fraser University, Burnaby, BC V5A 1S6, Canada.
Abstract:
Gain-of-function mutations in human androgen receptor (AR) are among the major causes of drug resistance in prostate cancer (PCa). Identifying mutations that cause resistant phenotype is of critical importance for guiding treatment protocols, as well as for designing drugs that do not elicit adverse responses. However, experimental characterization of these mutations is time consuming and costly; thus, predictive models are needed to anticipate resistant mutations and to guide the drug discovery process. In this work, we leverage experimental data collected on 68 AR mutants, either observed in the clinic or described in the literature, to train a deep neural network (DNN) that predicts the response of these mutants to currently used and experimental anti-androgens and testosterone. We demonstrate that the use of this DNN, with general 2D descriptors, provides a more accurate prediction of the biological outcome (inhibition, activation, no-response, mixed-response) in AR mutant-drug pairs compared to other machine learning approaches. Finally, the developed approach was used to make predictions of AR mutant response to the latest AR inhibitor darolutamide, which were then validated by in-vitro experiments.
Insights
Drug resistance in prostate cancer (PCa) is driven by androgen receptor (AR) mutations. A deep neural network accurately predicts AR mutant responses to anti-androgens, aiding drug discovery and treatment.
Area of Science:
- Oncology
- Genetics
- Computational Biology
Background:
- Gain-of-function mutations in the androgen receptor (AR) are a primary driver of treatment resistance in prostate cancer (PCa).
- Accurate identification of AR mutations conferring resistance is crucial for optimizing treatment strategies and developing novel therapeutics.
- Experimental characterization of AR mutants is resource-intensive, necessitating predictive computational models.
Purpose of the Study:
- To develop and validate a deep neural network (DNN) model for predicting the response of AR mutants to anti-androgen therapies.
- To assess the predictive performance of the DNN model against other machine learning approaches.
- To guide the discovery of new drugs and therapeutic strategies for resistant prostate cancer.
Main Methods:
- Trained a deep neural network (DNN) using experimental data from 68 AR mutants.
- Utilized general 2D descriptors for model input.
- Compared DNN performance against other machine learning algorithms for predicting biological outcomes (inhibition, activation, no-response, mixed-response) in AR mutant-drug pairs.
- Validated predictions for the AR inhibitor darolutamide through in-vitro experiments.
Main Results:
- The developed DNN model demonstrated superior accuracy in predicting AR mutant responses to anti-androgens compared to alternative machine learning methods.
- The model successfully predicted the biological outcome for various AR mutant-drug interactions.
- In-vitro validation confirmed the DNN's predictive capabilities for novel AR inhibitors like darolutamide.
Conclusions:
- Deep neural networks offer a powerful and accurate approach for predicting androgen receptor mutant responses in prostate cancer.
- This predictive model can accelerate the drug discovery process and inform clinical treatment decisions for resistant prostate cancer.
- The findings support the use of computational models in conjunction with experimental validation for advancing cancer therapy.
More Related Videos
07:25A Bioluminescent and Fluorescent Orthotopic Syngeneic Murine Model of Androgen-dependent and Castration-resistant Prostate Cancer
Published on: March 6, 2018
12:13Sequencing Small Non-coding RNA from Formalin-fixed Tissues and Serum-derived Exosomes from Castration-resistant Prostate Cancer Patients
Published on: November 19, 2019