Integrating structure-based approaches in generative molecular

Generative molecular design for drug discovery and develop-ment has seen a recent resurgence promising to improve the efficiency of the design-make-test-analyse cycle; by compu-tationally exploring much larger chemical spaces than tradi-tional virtual screening techniques. However, most generative models thus far have only utilized small-molecule information to train and condition de novo molecule generators. Here, we instead focus on recent approaches that incorporate protein structure into de novo molecule optimization in an attempt to maximize the predicted on-target binding affinity of generated molecules. We summarize these structure integration princi-ples into either distribution learning or goal-directed optimiza-tion and for each case whether the approach is protein structure-explicit or implicit with respect to the generative model. We discuss recent approaches in the context of this categorization and provide our perspective on the future di-rection of the field.