Torsional Diffusion for Molecular Conformer Generation

TL;DR

This paper introduces torsional diffusion, a novel diffusion-based method operating on torsion angles for molecular conformer generation, outperforming existing methods in accuracy and speed, and enabling the first generalizable Boltzmann generator.

Contribution

We develop torsional diffusion, a new diffusion framework on torsion angles, achieving superior conformer generation and likelihood estimation for molecules.

Findings

Outperforms existing methods in RMSD and chemical properties

Orders of magnitude faster than previous diffusion models

Enables the first generalizable Boltzmann generator

Abstract

Molecular conformer generation is a fundamental task in computational chemistry. Several machine learning approaches have been developed, but none have outperformed state-of-the-art cheminformatics methods. We propose torsional diffusion, a novel diffusion framework that operates on the space of torsion angles via a diffusion process on the hypertorus and an extrinsic-to-intrinsic score model. On a standard benchmark of drug-like molecules, torsional diffusion generates superior conformer ensembles compared to machine learning and cheminformatics methods in terms of both RMSD and chemical properties, and is orders of magnitude faster than previous diffusion-based models. Moreover, our model provides exact likelihoods, which we employ to build the first generalizable Boltzmann generator. Code is available at https://github.com/gcorso/torsional-diffusion.