Molecular Geometry Prediction using a Deep Generative Graph Neural Network

Abstract

A molecule’s geometry, also known as conformation, is one of a molecule’s most important properties, determining the reactions it participates in, the bonds it forms, and the interactions it has with other molecules. Conventional conformation generation methods minimize hand-designed molecular force field energy functions that are often not well correlated with the true energy function of a molecule observed in nature. They generate geometrically diverse sets of conformations, some of which are very similar to the lowest-energy conformations and others of which are very different. In this paper, we propose a conditional deep generative graph neural network that learns an energy function by directly learning to generate molecular conformations that are energetically favorable and more likely to be observed experimentally in data-driven manner. On three large-scale datasets containing small molecules, we show that our method generates a set of conformations that on average is far more likely to be close to the corresponding reference conformations than are those obtained from conventional force field methods. Our method maintains geometrical diversity by generating conformations that are not too similar to each other, and is also computationally faster. We also show that our method can be used to provide initial coordinates for conventional force field methods. On one of the evaluated datasets we show that this combination allows us to combine the best of both methods, yielding generated conformations that are on average close to reference conformations with some very similar to reference conformations.

GraSeq: Graph and Sequence Fusion Learning for Molecular Property Prediction

“…Molecular Graph Representation Learning. With the rapid development of deep learning algorithms, graph neural networks have gained a lot of attention for learning molecular representations since they can learn appropriate molecular representations that are invariant to graph isomorphism in an end-to-end fashion [6,9,18]. Shindo et al [27] proposed gated graph recursive neural networks (GGRNet) by considering a molecule as a complete directed graph where each atom has three-dimensional coordinates, and update hidden vectors of atoms depending on the distances between them.…”

On the Discrepancy between Density Estimation and Sequence Generation

“…To ease optimization of latent variable models (Bowman et al, 2016;Higgins et al, 2017), we set the weight of the KL term to 0 for the first 5,000 SGD steps and linearly increase it to 1 over the next 20,000 steps. Similarly with Mansimov et al (2019), we find it helpful to add a small regularization term to the training objective that matches the approximate posterior with a standard Gaussian distribution: α • KL q φ (z|y, x) || N (0, I) , as the original KL term KL q φ (z|y, x) p θ (z|x) does not have a local point minimum but a valley of minima. We find α = 10 −4 to work best.…”

Machine Learning Meets Quantum Physics

“…However, three-dimensional atomic coordinates should be considered for decoding as well. Recent works are going well beyond the connectivity of a molecule to provide equilibrium geometries of molecules using generative models [216][217][218][219][220]. This is crucial to bypass expensive sampling of low-energy configurations from the potential energy surface of molecules.…”