Molecular Conformation Generation via Shifting Scores

TL;DR

This paper introduces a novel diffusion-based method for molecular conformation generation that models inter-atomic distances with shifting distributions, improving the realism and feasibility of generated molecular geometries.

Contribution

The paper proposes a new generative approach using shifting distributions for inter-atomic distances, ensuring feasible and reversible molecular conformations, outperforming existing methods.

Findings

Outperforms state-of-the-art methods in molecular conformation generation

Ensures feasible inter-atomic distance geometries

Demonstrates advantages of shifting distribution modeling

Abstract

Molecular conformation generation, a critical aspect of computational chemistry, involves producing the three-dimensional conformer geometry for a given molecule. Generating molecular conformation via diffusion requires learning to reverse a noising process. Diffusion on inter-atomic distances instead of conformation preserves SE(3)-equivalence and shows superior performance compared to alternative techniques, whereas related generative modelings are predominantly based upon heuristical assumptions. In response to this, we propose a novel molecular conformation generation approach driven by the observation that the disintegration of a molecule can be viewed as casting increasing force fields to its composing atoms, such that the distribution of the change of inter-atomic distance shifts from Gaussian to Maxwell-Boltzmann distribution. The corresponding generative modeling ensures a feasible inter-atomic distance geometry and exhibits time reversibility. Experimental results on molecular datasets demonstrate the advantages of the proposed shifting distribution compared to the state-of-the-art.