Shape-based virtual screening is widely employed in ligand-based drug design to search chemical libraries for molecules with similar 3D shapes yet novel 2D chemical structures compared to known ligands. For instance, scaffold-hopping seeks to find molecular analogues to known actives that are shape-similar, but have improved drug-like properties, increased bioactivity, or more favorable intellectual property positioning. However, virtual screening is fundamentally limited in its ability to explore new chemical space or efficiently optimize molecules. In principle, 3D deep generative models have the potential to automate the exploration of shape-conditioned 3D chemical space for shape-constrained drug design. Yet, no existing deep learning models can generate diverse drug-like molecules in realistic 3D conformations that adopt a specific shape such as a known binding pose, while simultaneously respecting key Euclidean symmetries.<br/><br/>We introduce a new multimodal 3D generative model that enables shape-conditioned 3D molecular design by equivariantly encoding molecular shape and variationally encoding chemical identity. We ensure local geometric and chemical validity of generated molecules by using autoregressive fragment-based generation with heuristic bonding geometries, allowing the model to prioritize the scoring of rotatable bonds to best align the growing conformational structure to the target 3D shape. We showcase our 3D generative model in tasks relevant to drug design including shape-conditioned generation of chemically diverse molecular structures and shape-constrained molecular property optimization, demonstrating our model’s utility over virtual screening of enumerated libraries.

Equivariant shape-conditioned generation of 3D molecules for ligand-based drug design

Where thousands of chemistry professionals meet to share ideas and advance scientific and technical knowledge. Spring 2023 abstracts, posters, and presentations will launch at the end of March.

ACS Spring 2023

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.