MDDM: A Molecular Dynamics Diffusion Model to Predict Particle Self-Assembly

TL;DR

MDDM is a novel molecular dynamics diffusion model that efficiently predicts particle self-assembly structures from potential functions, reducing computational costs and outperforming existing models.

Contribution

The paper introduces MDDM, a diffusion model tailored for molecular dynamics, incorporating domain-specific features for accurate particle structure prediction.

Findings

MDDM outperforms baseline diffusion models in accuracy.

The model effectively predicts structures from arbitrary potentials.

It satisfies physical constraints like periodic boundaries.

Abstract

The discovery and study of new material systems rely on molecular simulations that often come with significant computational expense. We propose MDDM, a Molecular Dynamics Diffusion Model, which is capable of predicting a valid output conformation for a given input pair potential function. After training MDDM on a large dataset of molecular dynamics self-assembly results, the proposed model can convert uniform noise into a meaningful output particle structure corresponding to an arbitrary input potential. The model's architecture has domain-specific properties built-in, such as satisfying periodic boundaries and being invariant to translation. The model significantly outperforms the baseline point-cloud diffusion model for both unconditional and conditional generation tasks.