Learning Neural Generative Dynamics for Molecular Conformation Generation

TL;DR

This paper introduces a novel probabilistic framework combining flow-based and energy-based models to generate diverse and valid 3D molecular conformations from molecular graphs, outperforming existing methods.

Contribution

It presents a new generative approach that captures complex distributions and long-range dependencies in molecular conformations, improving over prior models.

Findings

Superior performance on conformation generation benchmarks

Significant improvement over existing generative models

Effective modeling of long-range atomic dependencies

Abstract

We study how to generate molecule conformations (i.e., 3D structures) from a molecular graph. Traditional methods, such as molecular dynamics, sample conformations via computationally expensive simulations. Recently, machine learning methods have shown great potential by training on a large collection of conformation data. Challenges arise from the limited model capacity for capturing complex distributions of conformations and the difficulty in modeling long-range dependencies between atoms. Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph. We propose a method combining the advantages of both flow-based and energy-based models, enjoying: (1) a high model capacity to estimate the multimodal conformation distribution; (2) explicitly capturing the complex long-range dependencies between atoms in the observation space. Extensive experiments demonstrate the superior performance of the proposed method on several benchmarks, including conformation generation and distance modeling tasks, with a significant improvement over existing generative models for molecular conformation sampling.