An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming

TL;DR

This paper introduces ConfVAE, an end-to-end framework using bilevel programming and variational autoencoders to predict molecular conformations directly from molecular graphs, improving over traditional two-step methods.

Contribution

The paper presents a novel end-to-end approach for molecular conformation prediction that integrates bilevel optimization within a variational autoencoder framework.

Findings

Outperforms existing state-of-the-art methods on benchmark datasets.

Provides more consistent and accurate 3D structures.

Demonstrates the effectiveness of bilevel programming in molecular modeling.

Abstract

Predicting molecular conformations (or 3D structures) from molecular graphs is a fundamental problem in many applications. Most existing approaches are usually divided into two steps by first predicting the distances between atoms and then generating a 3D structure through optimizing a distance geometry problem. However, the distances predicted with such two-stage approaches may not be able to consistently preserve the geometry of local atomic neighborhoods, making the generated structures unsatisfying. In this paper, we propose an end-to-end solution for molecular conformation prediction called ConfVAE based on the conditional variational autoencoder framework. Specifically, the molecular graph is first encoded in a latent space, and then the 3D structures are generated by solving a principled bilevel optimization program. Extensive experiments on several benchmark data sets prove the effectiveness of our proposed approach over existing state-of-the-art approaches. Code is available at https://github.com/MinkaiXu/ConfVAE-ICML21