Accelerated Hydration Site Localization and Thermodynamic Profiling
This work addresses the need for efficient computational methods in drug discovery to optimize ligand binding and selectivity, though it appears incremental by improving upon existing limited models.
The paper tackled the problem of identifying hydration sites and thermodynamic profiles around proteins, which is important for drug design, by developing a geometric deep neural network trained on explicit water molecular dynamics simulations, achieving fast and accurate results as confirmed on experimental data.
Water plays a fundamental role in the structure and function of proteins and other biomolecules. The thermodynamic profile of water molecules surrounding a protein are critical for ligand binding and recognition. Therefore, identifying the location and thermodynamic behavior of relevant water molecules is important for generating and optimizing lead compounds for affinity and selectivity to a given target. Computational methods have been developed to identify these hydration sites, but are largely limited to simplified models that fail to capture multi-body interactions, or dynamics-based methods that rely on extensive sampling. Here we present a method for fast and accurate localization and thermodynamic profiling of hydration sites for protein structures. The method is based on a geometric deep neural network trained on a large, novel dataset of explicit water molecular dynamics simulations. We confirm the accuracy and robustness of our model on experimental data and demonstrate it's utility on several case studies.