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.

arXiv comment15 pages, 6 figures

References in corpus (2)

• Challenges in Large Scale Quantum Mechanical Calculations
• Molecular geometry prediction using a deep generative graph neural network

Cited by in corpus (21)

• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• A Comprehensive Survey on Deep Graph Representation Learning
• Perspective on integrating machine learning into computational chemistry and materials science
• Inverse design of 3d molecular structures with conditional generative neural networks
• Few-Shot Graph Learning for Molecular Property Prediction
• Molecular geometry prediction using a deep generative graph neural network
• Machine learning based energy-free structure predictions of molecules (closed and open-shell), transition states, and solids
• Codabench: Flexible, Easy-to-Use and Reproducible Benchmarking Platform
• Graph Neural Networks for Molecules
• Autonomous Reaction Network Exploration in Homogeneous and Heterogeneous Catalysis
• On the design space between molecular mechanics and machine learning force fields
• Exploring Edge Disentanglement for Node Classification
• Rethinking Graph Backdoor Attacks: A Distribution-Preserving Perspective
• MixupExplainer: Generalizing Explanations for Graph Neural Networks with Data Augmentation
• CREMP: Conformer-rotamer ensembles of macrocyclic peptides for machine learning
• Ab initio machine learning of phase space averages
• Artificial Intelligence for Science in Quantum, Atomistic, and Continuum Systems
• Physics-informed generative model for drug-like molecule conformers
• Molecular relaxation by reverse diffusion with time step prediction
• Molecular distance matrix prediction based on graph convolutional networks
• Adversarial reverse mapping of condensed-phase molecular structures: Chemical transferability