Structure-Aware E(3)-Invariant Molecular Conformer Aggregation Networks

TL;DR

This paper introduces a novel E(3)-invariant molecular conformer aggregation network that combines 2D and 3D molecular data using a differentiable Fused Gromov-Wasserstein approach, significantly improving property prediction accuracy.

Contribution

It presents a new 2D-3D aggregation mechanism based on a differentiable solver, enhancing molecular property prediction by integrating conformer ensembles with 2D graphs.

Findings

Outperforms state-of-the-art methods on established datasets

Proposes an efficient GPU implementation of the aggregation mechanism

Demonstrates E(3) invariance of the proposed aggregation method

Abstract

A molecule's 2D representation consists of its atoms, their attributes, and the molecule's covalent bonds. A 3D (geometric) representation of a molecule is called a conformer and consists of its atom types and Cartesian coordinates. Every conformer has a potential energy, and the lower this energy, the more likely it occurs in nature. Most existing machine learning methods for molecular property prediction consider either 2D molecular graphs or 3D conformer structure representations in isolation. Inspired by recent work on using ensembles of conformers in conjunction with 2D graph representations, we propose $\mathrm{E}$(3)-invariant molecular conformer aggregation networks. The method integrates a molecule's 2D representation with that of multiple of its conformers. Contrary to prior work, we propose a novel 2D-3D aggregation mechanism based on a differentiable solver for the Fused Gromov-Wasserstein Barycenter problem and the use of an efficient conformer generation method based on distance geometry. We show that the proposed aggregation mechanism is $\mathrm{E}$(3) invariant and propose an efficient GPU implementation. Moreover, we demonstrate that the aggregation mechanism helps to significantly outperform state-of-the-art molecule property prediction methods on established datasets.