Drug discovery has traditionally relied on low-throughput experimentation and trial and error. Computational methods, including machine learning or AI approaches, are transforming drug discovery by enabling more computer-based experiments and simulation-informed decision-making at an increasingly unprecedented scale. With access to extensive computer-aided insights and simulations, scientists can now explore a vastly expanded set of potential interactions and outcomes at atomistic, DNA, protein, and cellular levels, thereby significantly improving the precision with which we design drugs for the right cellular and disease context and the right patient. This symposium aims to bring together experts from connected disciplines in drug discovery who are leveraging computational methods in therapeutic compound and protein design, protein structure and protein-protein interaction predictions, disease model systems, and computational predictive toxicology. Speakers in each session will cover how computation and advanced machine-learning methods aid hypothesis generation and exemplify how the convergence of data and technology is accelerating medicine discovery and development.