Early clinical studies have demonstrated potential uses for the selective androgen receptor modulators in the treatment of cancer-related cachexia, benign prostatic hyperplasia, hypogonadism, and breast cancer, with positive results. Accurate prediction of drug–target interactions (DTI) is crucial for drug discovery.

We present an implementation of a machine learning model that is able accurately to characterize the binding of compounds to the drug targets. In this project, we tested the performance of the machine learning model on the set of selective androgen receptor modulators.