University of California, Berkeley — Publications

A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics

Preprint

In drug discovery, molecular dynamics (MD) simulation for protein-ligand binding provides a powerful tool for predicting binding affinities, estimating transport properties, and exploring pocket sites. There has been a long history of improving the efficiency of MD simulations through better numerical methods and, more recently, by utilizing machine learning (ML) methods. Yet, challenges remain, such as accurate modeling of extended-timescale simulations. To address this issue, we propose NeuralMD, the first ML surrogate that can facilitate numerical MD and provide accurate simulations in protein-ligand binding dynamics. We propose a principled approach that incorporates a novel physics-informed multi-grained group symmetric framework. Specifically, we propose (1) the BindingNet model that satisfies group symmetry using vector frames and captures the multi-level protein-ligand interactions, and (2) an augmented neural differential equation solver that learns the trajectory under Newtonian mechanics. For the experiment, we design ten single-trajectory and three multi-trajectory binding simulation tasks. We demonstrate the efficiency and effectiveness of NeuralMD, achieving over 1K$\times$ speedup compared to standard numerical MD simulations. NeuralMD also outperforms all other ML approaches, achieving up to 15$\times$ reduction in reconstruction error and 70% increase in validity. Additionally, we qualitatively illustrate that the oscillations in the predicted trajectories align more closely with ground-truth dynamics than those of other machine-learning methods. We believe NeuralMD paves the foundation for a new research paradigm in simulating protein-ligand dynamics.

Shengchao Liu, Weitao Du, Yanjing Li et al. 2024

Publications

The Role of Interpersonal Characteristics in Early and Developing Therapeutic Alliance Among Periadolescents with Anxiety

Flux Analysis of Biodiesel-Producing E. coli

A Multi-Grained Symmetric Differential Equation Model for Learning Protein-Ligand Binding Dynamics

CCDC 1022461: Experimental Crystal Structure Determination

Sequential information maximization can explain eye movements in an object learning task

Silolyl Anions and Silole Dianions: Structure of [K([18]crown‐6)<sup>+</sup>]<sub>2</sub>[C<sub>4</sub>Me<sub>4</sub>Si<sup>2−</sup>]

Josephson currents through topological insulator surfaces

Band convergence in the non-cubic chalcopyrite compounds Cu<sub>2</sub>MGeSe<sub>4</sub>

Cortisol secretion in adolescents with major depressive disorder

Elastic Scaling of Stateful Network Functions.

Nature-Inspired Hierarchical Steels

Functionalization of Alkanes by Isolated Transition Metal Boryl Complexes

High Oxidation-State (Formally d<sup>0</sup>) Tungsten Silylene Complexes via Double Si−H Bond Activation

The Pantheon+ Analysis: The Full Dataset and Light-Curve Release

Identification of Olfactory Receptors Responding to Androstenone and the Key Structure Determinant in Domestic Pig

Pubertal changes in emotional information processing: Pupillary, behavioral, and subjective evidence during emotional word identification

A numerical model for simulating the radiation regime within a deciduous forest canopy

The role of hydrogen during Pt–Ga nanocatalyst formation

Transition In Dynamical Regime By Driving: A Method of Control And

Nonlinear Dynamics for Communication Systems