Development and evaluation of a deep learning model for protein–ligand binding affinity prediction

TLDR

Structure‑based ligand discovery is a key drug‑discovery strategy, and machine learning—particularly deep learning—is increasingly employed to automatically extract relevant features. The protein–ligand complex is encoded as a 3‑D grid and processed by a 3‑D convolutional neural network that treats protein and ligand atoms uniformly to generate a feature map. The resulting network, evaluated on the CASF‑2013 scoring‑power benchmark and the Astex Diverse Set, outperformed classical scoring functions and is available as an open‑source GitLab repository. Supplementary data are available online at Bioinformatics.

Abstract

Abstract Motivation Structure based ligand discovery is one of the most successful approaches for augmenting the drug discovery process. Currently, there is a notable shift towards machine learning (ML) methodologies to aid such procedures. Deep learning has recently gained considerable attention as it allows the model to ‘learn’ to extract features that are relevant for the task at hand. Results We have developed a novel deep neural network estimating the binding affinity of ligand–receptor complexes. The complex is represented with a 3D grid, and the model utilizes a 3D convolution to produce a feature map of this representation, treating the atoms of both proteins and ligands in the same manner. Our network was tested on the CASF-2013 ‘scoring power’ benchmark and Astex Diverse Set and outperformed classical scoring functions. Availability and implementation The model, together with usage instructions and examples, is available as a git repository at http://gitlab.com/cheminfIBB/pafnucy. Supplementary information Supplementary data are available at Bioinformatics online.