MetaPocket: A Meta Approach to Improve Protein Ligand Binding Site Prediction

TLDR

The identification of ligand‑binding sites is a key step for protein function annotation and structure‑based drug design, and many computational methods have been developed. We present metaPocket, a consensus method that combines predictions from LIGSITEcs, PASS, Q‑SiteFinder, and SURFNET to improve binding‑site prediction accuracy. The four constituent methods were evaluated on two datasets comprising 48 unbound/bound structures and 210 bound structures. MetaPocket increased the top‑1 success rate from about 70 % to 75 %. MetaPocket is available at http://metapocket.eml.org.

Abstract

The identification of ligand-binding sites is often the starting point for protein function annotation and structure-based drug design. Many computational methods for the prediction of ligand-binding sites have been developed in recent decades. Here we present a consensus method metaPocket, in which the predicted sites from four methods: LIGSITEcs, PASS, Q-SiteFinder, and SURFNET are combined together to improve the prediction success rate. All these methods are evaluated on two datasets of 48 unbound/bound structures and 210 bound structures. The comparison results show that metaPocket improves the success rate from ∼70 to 75% at the top 1 prediction. MetaPocket is available at http://metapocket.eml.org.