A new protein binding pocket similarity measure based on comparison of 3D atom clouds: application to ligand prediction

TL;DR

This paper introduces a novel 3D atom cloud-based similarity measure for protein binding pockets, improving ligand prediction accuracy over existing methods and docking approaches.

Contribution

A new protein pocket similarity measure using 3D atom clouds and convolution kernels, outperforming existing methods in ligand prediction tasks.

Findings

The new method outperforms existing similarity measures.

It surpasses docking programs in ligand prediction accuracy.

Evaluation using ROC AUC and classification scores favors the new approach.

Abstract

Motivation: Prediction of ligands for proteins of known 3D structure is important to understand structure-function relationship, predict molecular function, or design new drugs. Results: We explore a new approach for ligand prediction in which binding pockets are represented by atom clouds. Each target pocket is compared to an ensemble of pockets of known ligands. Pockets are aligned in 3D space with further use of convolution kernels between clouds of points. Performance of the new method for ligand prediction is compared to those of other available measures and to docking programs. We discuss two criteria to compare the quality of similarity measures: area under ROC curve (AUC) and classification based scores. We show that the latter is better suited to evaluate the methods with respect to ligand prediction. Our results on existing and new benchmarks indicate that the new method outperforms other approaches, including docking. Availability: The new method is available at http://cbio.ensmp.fr/paris/ Contact: mikhail.zaslavskiy@mines-paristech.fr