Related Experiment Video
Updated: May 8, 2025
Deciphering the Structural Effects of Activating EGFR Somatic Mutations with Molecular Dynamics Simulation
Published on: May 20, 2020
Deep Modeling of Gain-of-Function Mutations on Androgen Receptor
Jiaying You1, Jane Foo1, Nada Lallous1
1Department of Urologic Sciences, Faculty of Medicine, Vancouver Prostate Centre, University of British Columbia, Vancouver, Canada.
Abstract:
The efficiency of Androgen Receptor (AR) pathway inhibitors for prostate cancer (PCa) is on decline due to resistance mechanisms including the occurrence of gain-of-function mutations on human androgen receptor (AR). Hence, understanding and predicting such mutations is crucial for developing effective PCa treatment strategies. Leveraging accu- mulated data on clinically relevant AR mutants with recent advances in deep modeling techniques, this study aims to unveil and quantify critical AR mutation-drug relation- ships. By incorporating molecular descriptors for drugs and mutated genes sequences, this work represented these features as single vectors and demonstrates their effective- ness in modeling AR mutant responses to conventional antiandrogens. The developed approach achieves above 80% accuracy in predicting the gain-of-function behavior of AR mutants and therefore can potentially uncover unknown agonist/antagonist relationships among mutant-drug pairs.
Insights
Predicting androgen receptor (AR) mutations in prostate cancer (PCa) is vital for treatment. This study uses deep learning to model AR mutant responses to drugs, achieving over 80% accuracy in predicting resistance.
Area of Science:
- Oncology
- Genetics
- Computational Biology
Background:
- Androgen receptor (AR) pathway inhibitors are crucial for prostate cancer (PCa) treatment.
- Emerging resistance to AR inhibitors, often due to AR gain-of-function mutations, limits treatment efficacy.
- Predicting the impact of these mutations is essential for developing next-generation therapies.
Purpose of the Study:
- To develop a predictive model for understanding AR mutation-drug relationships in prostate cancer.
- To quantify the impact of specific AR mutations on drug response.
- To identify potential novel agonist/antagonist relationships for AR mutants.
Main Methods:
- Utilized deep modeling techniques incorporating molecular descriptors for drugs and mutated AR gene sequences.
- Represented molecular and genetic features as single vectors for effective modeling.
- Trained and validated the model on a dataset of clinically relevant AR mutants and antiandrogen responses.
Main Results:
- The developed deep learning approach demonstrated high accuracy in predicting AR mutant behavior.
- Achieved over 80% accuracy in predicting the gain-of-function nature of AR mutants.
- Successfully modeled AR mutant responses to conventional antiandrogens.
Conclusions:
- The predictive model offers a powerful tool for understanding AR mutation-drug interactions in prostate cancer.
- This approach can aid in predicting treatment response and identifying novel therapeutic strategies.
- The study highlights the potential for deep learning in uncovering unknown AR mutant-drug relationships to overcome resistance.
