Elucidating the multiple roles of hydration for accurate protein-ligand binding prediction via deep learning

Amr H Mahmoud,Markus A Lill,Matthew R Masters,Ying Yang

doi:10.1038/s42004-020-0261-x

Amr H Mahmoud, Markus A Lill + Show 2 more

Open Access

https://doi.org/10.1038/s42004-020-0261-x

Copy DOI

Abstract

Accurate and efficient prediction of protein-ligand interactions has been a long-lasting dream of practitioners in drug discovery. The insufficient treatment of hydration is widely recognized to be a major limitation for accurate protein-ligand scoring. Using an integration of molecular dynamics simulations on thousands of protein structures with novel big-data analytics based on convolutional neural networks and deep Taylor decomposition, we consistently identify here three different patterns of hydration to be essential for protein-ligand interactions. In addition to desolvation and water-mediated interactions, the formation of enthalpically favorable networks of first-shell water molecules around solvent-exposed ligand moieties is identified to be essential for protein-ligand binding. Despite being currently neglected in drug discovery, this hydration phenomenon could lead to new avenues in optimizing the free energy of ligand binding. Application of deep neural networks incorporating hydration to docking provides 89% accuracy in binding pose ranking, an essential step for rational structure-based drug design.

Highlights

Accurate and efficient prediction of protein-ligand interactions has been a long-lasting dream of practitioners in drug discovery
The architecture of convolutional neural networks (CNNs) allows them to learn from these data important local features of protein-ligand interactions, without limitation to pre-defined scoring functions that typically rely on two-body interaction models
To apply the method to a large number of protein structures, we have developed a new accelerated WATsite implementation based on graphics processing unit (GPU) acceleration, asynchronous data output, and protein truncation

Summary

Introduction

Accurate and efficient prediction of protein-ligand interactions has been a long-lasting dream of practitioners in drug discovery. In structure-based drug design, ligands are optimized to replace energetically unfavorable water molecules, ordered water molecules in hydrophobic moieties This desolvation of free energy is often an essential driving force for strong protein-ligand association (Fig. 1a). Desolvation effects in protein-ligand scoring were modeled by an empirical term characterizing hydrophobic contacts between the protein and the ligand, for example, using counts of close hydrophobic protein-ligand atom pairs or using a term that is proportional to the solvent-accessible surface[9,10,11,12] These approaches are implicitly modeling desolvation effects, but ignore thermodynamic properties of individual binding site water molecules, which can significantly differ based on the detailed protein environment (Supplementary Note 1)[8,13,14]. Reasons for these results include the lack of consistent scoring function design and optimization, including the explicit desolvation term (desolvation term has been typically used as a subsequent add-on to existing scoring functions), inaccuracies in the other interaction terms, and the neglect of water-mediated interactions

Objectives

Methods

Results