Generation of Chemical Space of Compounds for Prostate Cancer Treatment: Biological Activity Prediction, Clustering, and Visualization of Chemical Space

Abstract

Designing molecules for pharmaceutical purposes has been a significant focus for several decades. The pursuit of novel drugs is an arduous and financially demanding undertaking. Nevertheless, the integration of computerassisted frameworks presents a swift avenue for designing and screening drug-like compounds. Within the context of this research, we introduce a comprehensive approach for the design and screening of compounds tailored to the treatment of prostate cancer. To forecast the biological activity of these compounds, we employed machine learning (ML) models. Additionally, an automated process involving the deconstruction and reconstruction of molecular building blocks leads to the generation of novel compounds. Subsequently, the ML models were utilized to predict the biological activity of the designed compounds, and the t-SNE method was employed to visualize the chemical space covered by the novel compounds. A meticulous selection process identified the most promising compounds, and their potential for synthesis was assessed, offering valuable guidance to experimental chemists in their investigative endeavors. Furthermore, fingerprint and heatmap analysis were conducted to evaluate the chemical similarity among the selected compounds. This multifaceted approach, encompassing predictive modeling, compound generation, visualization, and similarity assessment, underscores our commitment to refining the process of identifying potential candidates for further exploration in prostate cancer treatment.