Integration of Evolution to Avoid Resistance in Structure Based Drug Design Many of the most deadly diseases that plague our society evolve quickly, challenging our therapeutic strategies. Drug resistance occurs as a result of this evolution when drug pressure changes the balance of molecular recognition events, selectively weakening inhibitor binding while maintaining the biological function of the therapeutic target. Disrupting the therapeutic target’s activity is necessary but not sufficient to avoid resistance. We hypothesize that the multi-dimensional landscape of resistance evolution can be elucidated through integration of experimental and computational data to reveal the key pathways and coupled molecular mechanisms to resistance. Furthermore, we hypothesize that this strategy can be incorporated into structure-based drug design to evaluate novel inhibitors. Resistance occurs under gradual and persistent drug pressure, and interestingly the mutations are not limited to the active site of a drug target, but can occur throughout the enzyme to confer high levels of resistance. The molecular mechanism by which this resistance occurs is not clear. Our aim is to exploit the rich and versatile experimental data, integrating inhibitor potency and crystallographic structures with ensemble dynamics in an internally consistent manner using machine learning to elucidate both the molecular mechanisms of drug resistance and generate predictive models of inhibitor potency.