DeepSite: protein-binding site predictor using 3D-convolutional neural networks

TLDR

Predicting druggable binding sites is a key step in structure‑based drug design, and numerous algorithms exploit geometric, chemical, and evolutionary protein features to detect such cavities. The study introduces a novel knowledge‑based approach that learns to predict binding sites using state‑of‑the‑art convolutional neural networks trained on examples. The method trains a 3D‑convolutional neural network on 7,622 scPDB proteins, evaluates predictions with distance and volumetric overlap, and is deployed on GPU servers where users submit PDB IDs or files via a WebGL interface. The approach outperforms two leading competitor algorithms in binding‑site prediction accuracy. DeepSite is freely available at www.playmolecule.org, with supplementary data hosted on Bioinformatics online.

Abstract

Abstract Motivation An important step in structure-based drug design consists in the prediction of druggable binding sites. Several algorithms for detecting binding cavities, those likely to bind to a small drug compound, have been developed over the years by clever exploitation of geometric, chemical and evolutionary features of the protein. Results Here we present a novel knowledge-based approach that uses state-of-the-art convolutional neural networks, where the algorithm is learned by examples. In total, 7622 proteins from the scPDB database of binding sites have been evaluated using both a distance and a volumetric overlap approach. Our machine-learning based method demonstrates superior performance to two other competitive algorithmic strategies. Availability and implementation DeepSite is freely available at www.playmolecule.org. Users can submit either a PDB ID or PDB file for pocket detection to our NVIDIA GPU-equipped servers through a WebGL graphical interface. Supplementary information Supplementary data are available at Bioinformatics online.