A Computer Vision Approach to Align and Compare Protein Cavities: Application to Fragment-Based Drug Design

• DOI: 10.1021/acs.jmedchem.0c00422
• Publication Date: 2020-06-04T16:45:16Z
• Authors: Merveille Eguida; Didier Rognan
• Keywords: Fragment (logic); Druggability; Similarity (geometry); Ligand efficiency

Identifying local similarities in binding sites from distant proteins is a major hurdle to rational drug design. We herewith present novel method, borrowed computer vision, adapted mine fragment subpockets and compare them whole ligand-binding sites. Pockets are represented by pharmacophore-annotated point clouds mimicking ideal ligands or fragments. Point cloud registration used find the transformation enabling an optimal overlap of points sharing similar topological pharmacophoric neighborhoods. The method (ProCare) was calibrated on large set druggable cavities applied comparison entire cavities. A collection 33,953 annotated with their bound fragments screened for similarity recently described protein X-ray structures. ProCare able detect between remote pockets transfer corresponding query cavity space, thereby proposing first step fragment-based design approaches targeting orphan