Structure-Aware Prediction of PROTAC-Mediated Protein Degradability via Graph Neural Networks
Researchers have developed DegradoMap, a new graph neural network designed to predict the degradability of proteins targeted by PROTACs. Unlike previous methods requiring complete PROTAC structures, DegradoMap uses only protein structure and E3 ligase identity, information available before synthesis. The model demonstrates strong performance on benchmarks, outperforming existing GNN and machine learning baselines, and can also recommend optimal E3 ligases. AI
IMPACT Provides computational guidance for drug discovery, potentially accelerating the identification of effective PROTAC candidates.