Resistance to drug treatments is common in prostate cancer (PCa), and the gain-of-function mutations in human androgen receptor (AR) represent one of the most dominant drivers of progression to resistance to AR pathway inhibitors (ARPI). Previously, we evaluated the in vitro response of 24 AR mutations, identified in men with castration-resistant PCa, to five AR antagonists. In the current work, we evaluated 44 additional PCa-associated AR mutants, reported in the literature, and thus expanded the study of the effect of darolutamide to a total of 68 AR mutants. Unlike other AR antagonists, we demonstrate that darolutamide exhibits consistent efficiency against all characterized gain-of-function mutations in a full-length AR. Additionally, the response of the AR mutants to clinically used bicalutamide and enzalutamide, as well as to major endogenous steroids (DHT, estradiol, progesterone and hydrocortisone), was also investigated. As genomic profiling of PCa patients becomes increasingly feasible, the developed “AR functional encyclopedia” could provide decision-makers with a tool to guide the treatment choice for PCa patients based on their AR mutation status.

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.

Cancer is driven by genetic mutations that dysregulate pathways important for proper cell function. Therefore, discovering these cancer pathways and their dysregulation order is key to understanding and treating cancer. However, the heterogeneity of mutations between different individuals makes this challenging and requires that cancer progression is studied in a subtype-specific way. To address this challenge, we provide a mathematical model, called Subtype-specific Pathway Linear Progression Model (SPM), that simultaneously captures cancer subtypes and pathways and order of dysregulation of the pathways within each subtype. Experiments with synthetic data indicate the robustness of SPM to problem specifics including noise compared to an existing method. Moreover, experimental results on glioblastoma multiforme and colorectal adenocarcinoma show the consistency of SPM’s results with the existing knowledge and its superiority to an existing method in certain cases. The implementation of our method is available at https://github.com/Dalton386/SPM. Different biological processes within a cell are performed through biological pathways. A biological pathway consists of a group of proteins and other molecules and complex interactions between them. It is known that cancer arises due to malfunction, also known as dysregulation, of one or more pathways. Interestingly, a dysregulation in a patient is often caused by mutations in only one (and not more) molecule in the pathway. This phenomenon is known as mutual exclusivity of mutations and can be used for identification of groups of genes forming (cancer) pathways. The same type of cancer in different patients can result due to different trajectories of dysregulations in possibly different pathways resulting in cancer heterogeneity. Cancer heterogeneity implies that cancer treatment should be personalized according to each patient’s specific characteristics and mutations. Therefore, grouping patients based on their pathway dysregulation trajectories into cancer subtypes can help identify different cancer mechanisms, inform subtype-specific treatment strategies and improve efficacy. In this paper, we provide a method that uses patients’ mutation information captured by DNA sequencing and identifies dysregulated pathways (i.e. molecules involved in each cancer pathway), cancer subtypes (i.e. groups of patients sharing a common pathway dysregulation trajectory) and subtype-specific pathway dysregulation orders (i.e. trajectories defining the different subtypes). The results on synthetic and real-world data indicate that the method can recover meaningful information about the progression of cancer in different groups of patients.

Motivation: One of the main goals of precision oncology is to predict the response of a patient to a given cancer treatment based on their genomic profile. Although current models for drug response prediction are becoming more accurate, they are also ‘black boxes’ and cannot explain their predictions, which is of particular importance in cancer treatment. Many models also do not leverage prior biological knowledge, such as the hierarchical information on how proteins form complexes and act together in pathways.Results: In this work, we use this prior biological knowledge to form the architecture of a deep neural network to predict cancer drug response from cell line gene expression data. We find that our approach not only has a low prediction error compared to baseline models but also allows meaningful interpretation of the network. These interpretations can both explain predictions made and discover novel connections in the biological knowledge that may lead to new hypotheses about mechanisms of drug action.Availability: Code at https://github.com/osnow/BDKANNSupplementary information: Included with submission

Gain-of-function mutations in human Androgen Receptor (AR) are amongst 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, and therefore predictive models are needed to anticipate resistant mutations and to guide drug discovery process. In this work, we leverage experimental data collected on 69 clinically observed and/or literature described AR mutants to train a deep neural network (DNN) to predict their responses to currently used and experimental AR anti-androgens. We demonstrate that the use of DNN provides more accurate prediction of the biological outcome (inhibition, activation, no-response) in AR mutant-drug pairs compared to other machine learning approaches and also allows the use of more general 2D descriptors. Finally, the developed approach was used to predict the effect of the latest AR inhibitor darolutamide on all reported AR mutants.