RAPID-Net: Accurate Pocket Identification for Binding-Site-Agnostic Docking

Accurate identification of druggable pockets and their features is essential for structure-based drug design and effective downstream docking. Here, we present RAPID-Net, a deep learning-based algorithm designed for accurate prediction of binding pockets and seamless integration with docking pipelines. On the PoseBusters benchmark, RAPID-Net-guided AutoDock Vina achieves 54.9% of Top-1 poses with RMSD < 2 Å and satisfying the PoseBusters chemical-validity criterion, compared to 49.1% for DiffBindFR. On the most challenging time split of PoseBusters, aiming to assess generalization ability (structures submitted after September 30, 2021), RAPID-Net-guided AutoDock Vina achieves 53.1% of Top-1 poses with RMSD < 2 Å and PB-valid, versus 59.5% for AlphaFold 3. Notably, in 92.2% of cases, RAPID-Net-guided Vina samples at least one pose with RMSD < 2 Å (regardless of its rank), indicating that pose ranking, rather than sampling, is the primary accuracy bottleneck. The lightweight inference, scalability, and competitive accuracy of RAPID-Net position it as a viable option for large-scale virtual screening campaigns. Across diverse benchmark data sets, it outperforms other pocket prediction tools, including PUResNet and Kalasanty, in both docking accuracy and pocket-ligand intersection rates. Furthermore, we demonstrate its potential to accelerate the development of novel therapeutics by highlighting its performance on pharmacologically relevant targets. The model accurately identifies distal functional sites, offering new opportunities for allosteric inhibitor design. In the case of the RNA-dependent RNA polymerase of SARS-CoV-2, RAPID-Net uncovers a wider array of potential binding pockets than existing predictors, which typically annotate only the orthosteric pocket and overlook secondary cavities.