Direct Molecular Conformation Generation

TL;DR

This paper introduces a novel method for directly generating 3D molecular conformations without relying on intermediate predictions, achieving state-of-the-art results and improving downstream tasks like molecular docking.

Contribution

The paper presents a direct coordinate prediction approach with roto-translation invariance and iterative refinement, outperforming previous indirect methods.

Findings

Achieves top results on GEOM-QM9 and GEOM-Drugs datasets.

Generated conformations closely match groundtruth properties like HOMO-LUMO gap.

Enhances molecular docking performance with better initial conformations.

Abstract

Molecular conformation generation aims to generate three-dimensional coordinates of all the atoms in a molecule and is an important task in bioinformatics and pharmacology. Previous methods usually first predict the interatomic distances, the gradients of interatomic distances or the local structures (e.g., torsion angles) of a molecule, and then reconstruct its 3D conformation. How to directly generate the conformation without the above intermediate values is not fully explored. In this work, we propose a method that directly predicts the coordinates of atoms: (1) the loss function is invariant to roto-translation of coordinates and permutation of symmetric atoms; (2) the newly proposed model adaptively aggregates the bond and atom information and iteratively refines the coordinates of the generated conformation. Our method achieves the best results on GEOM-QM9 and GEOM-Drugs datasets. Further analysis shows that our generated conformations have closer properties (e.g., HOMO-LUMO gap) with the groundtruth conformations. In addition, our method improves molecular docking by providing better initial conformations. All the results demonstrate the effectiveness of our method and the great potential of the direct approach. The code is released at https://github.com/DirectMolecularConfGen/DMCG