A Generative Model for Molecular Distance Geometry

Gregor Simm, Jose Miguel Hernandez-Lobato
Proceedings of the 37th International Conference on Machine Learning, PMLR 119:8949-8958, 2020.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v119-simm20a, title = {A Generative Model for Molecular Distance Geometry}, author = {Simm, Gregor and Hernandez-Lobato, Jose Miguel}, booktitle = {Proceedings of the 37th International Conference on Machine Learning}, pages = {8949--8958}, year = {2020}, editor = {III, Hal Daumé and Singh, Aarti}, volume = {119}, series = {Proceedings of Machine Learning Research}, month = {13--18 Jul}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v119/simm20a/simm20a.pdf}, url = {https://proceedings.mlr.press/v119/simm20a.html}, 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.} }
Endnote
%0 Conference Paper %T A Generative Model for Molecular Distance Geometry %A Gregor Simm %A Jose Miguel Hernandez-Lobato %B Proceedings of the 37th International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2020 %E Hal Daumé III %E Aarti Singh %F pmlr-v119-simm20a %I PMLR %P 8949--8958 %U https://proceedings.mlr.press/v119/simm20a.html %V 119 %X 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.
APA
Simm, G. & Hernandez-Lobato, J.M.. (2020). A Generative Model for Molecular Distance Geometry. Proceedings of the 37th International Conference on Machine Learning, in Proceedings of Machine Learning Research 119:8949-8958 Available from https://proceedings.mlr.press/v119/simm20a.html.

Related Material