A Generative Model for Molecular Distance Geometry

Gregor N. C. Simm, José Miguel Hernández-Lobato

Keywords: graph neural networks, variational autoencoders, distance geometry, molecular conformation

TL;DR: Neural network based generative model for molecular conformations utilizing Euclidean distance geometry.

Abstract: Computing equilibrium states for many-body systems, such as molecules, is a long-standing challenge. In the absence of methods for generating statistically independent samples, great computational effort is invested in simulating these systems using, for example, Markov chain Monte Carlo. We present a probabilistic model that generates such samples for molecules from their graph representations. Our model learns a low-dimensional manifold that preserves the geometry of local atomic neighborhoods through a principled learning representation that is based on Euclidean distance geometry. We create a new dataset for molecular conformation generation with which we show experimentally that our generative model achieves state-of-the-art accuracy. Finally, we show how to use our model as a proposal distribution in an importance sampling scheme to compute molecular properties.

Code: https://figshare.com/s/1b42bf865bd78c457354

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1909.11459/code)