Learning Neural Generative Dynamics for Molecular Conformation Generation

Abstract

We study how to generate molecule conformations (i.e., 3D structures) from a molecular graph. Traditional methods, such as molecular dynamics, sample conformations via computationally expensive simulations. Recently, machine learning methods have shown great potential by training on a large collection of conformation data. Challenges arise from the limited model capacity for capturing complex distributions of conformations and the difficulty in modeling long-range dependencies between atoms. Inspired by the recent progress in deep generative models, in this paper, we propose a novel probabilistic framework to generate valid and diverse conformations given a molecular graph. We propose a method combining the advantages of both flow-based and energy-based models, enjoying: (1) a high model capacity to estimate the multimodal conformation distribution; (2) explicitly capturing the complex long-range dependencies between atoms in the observation space. Extensive experiments demonstrate the superior performance of the proposed method on several benchmarks, including conformation generation and distance modeling tasks, with a significant improvement over existing generative models for molecular conformation sampling.

Accepted by ICLR 2021. Code is available at \url{https://github.com/DeepGraphLearning/CGCF-ConfGen}

References in corpus (9)

• ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
• NICE: Non-linear Independent Components Estimation
• Variational Inference with Normalizing Flows
• Better Mixing via Deep Representations
• Generalized Denoising Auto-Encoders as Generative Models
• A Theory of Generative ConvNet
• Implicit Generation and Generalization in Energy-Based Models
• Generating valid Euclidean distance matrices
• Discriminator Contrastive Divergence: Semi-Amortized Generative Modeling by Exploring Energy of the Discriminator

Cited by in corpus (9)

• Inverse design of 3d molecular structures with conditional generative neural networks
• 3D Infomax improves GNNs for Molecular Property Prediction
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles
• Learning Gradient Fields for Molecular Conformation Generation
• An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
• Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
• Physics-informed generative model for drug-like molecule conformers
• Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphs
• E(n) Equivariant Normalizing Flows