On-the-fly Prediction of Protein Hydration Densities and Free Energies using Deep Learning

TL;DR

This paper introduces deep learning models to rapidly predict protein hydration sites and thermodynamics, replacing resource-intensive molecular simulations for better protein-ligand interaction analysis.

Contribution

The study presents two novel deep neural network approaches for on-the-fly hydration site prediction, utilizing 3D image-based and point-wise methods, enhancing efficiency over traditional simulations.

Findings

Accurate hydration site predictions using neural networks.

Improved protein-ligand scoring with hydration data.

Models outperform traditional simulation methods in speed.

Abstract

The calculation of thermodynamic properties of biochemical systems typically requires the use of resource-intensive molecular simulation methods. One example thereof is the thermodynamic profiling of hydration sites, i.e. high-probability locations for water molecules on the protein surface, which play an essential role in protein-ligand associations and must therefore be incorporated in the prediction of binding poses and affinities. To replace time-consuming simulations in hydration site predictions, we developed two different types of deep neural-network models aiming to predict hydration site data. In the first approach, meshed 3D images are generated representing the interactions between certain molecular probes placed on regular 3D grids, encompassing the binding pocket, with the static protein. These molecular interaction fields are mapped to the corresponding 3D image of hydration occupancy using a neural network based on an U-Net architecture. In a second approach, hydration occupancy and thermodynamics were predicted point-wise using a neural network based on fully-connected layers. In addition to direct protein interaction fields, the environment of each grid point was represented using moments of a spherical harmonics expansion of the interaction properties of nearby grid points. Application to structure-activity relationship analysis and protein-ligand pose scoring demonstrates the utility of the predicted hydration information.