PROTAC-PatentDB: A PROTAC patent compound dataset

Proteolysis-targeting chimera (PROTAC) represents an emerging and highly promising protein degradation technology with the potential to overcome critical bottlenecks in traditional small molecule drug development. However, the scarcity of publicly available compound structure data has significantly limited computational drug discovery and artificial intelligence-driven modeling in this field. Patent represents an important yet underutilized source of novel chemical structures in medicinal chemistry. In this study, we systematically collected PROTAC-related patents and associated chemical structures disclosed therein. Through rigorous manual screening and expert annotation, we obtained 63,136 unique PROTAC compounds from 590 patent families, along with 252 targets. Additionally, we employed the ADMETlab 3.0 platform to systematically predict 120 physicochemical properties for all compounds. The dataset has been publicly shared on Figshare, providing a solid foundation for computational drug discovery and structure-activity relationship analyses.