CUED Publications database

A Generative Model for Molecular Distance Geometry

Simm, GNC and Hernández-Lobato, JM A Generative Model for Molecular Distance Geometry. (Unpublished)

Full text not available from this repository.

Abstract

Great computational effort is invested in generating equilibrium states for molecular systems using, for example, Markov chain Monte Carlo. We present a probabilistic model that generates statistically independent 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. In a new benchmark for molecular conformation generation, 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.

Item Type: Article
Uncontrolled Keywords: stat.ML stat.ML cs.LG
Subjects: UNSPECIFIED
Divisions: Div F > Computational and Biological Learning
Depositing User: Cron Job
Date Deposited: 25 Oct 2019 21:08
Last Modified: 27 Aug 2020 04:27
DOI: