Molecular Hypergraph Grammar with its Application to Molecular Optimization

Abstract

Molecular optimization aims to discover novel molecules with desirable properties. Two fundamental challenges are: (i) it is not trivial to generate valid molecules in a controllable way due to hard chemical constraints such as the valency conditions, and (ii) it is often costly to evaluate a property of a novel molecule, and therefore, the number of property evaluations is limited. These challenges are to some extent alleviated by a combination of a variational autoencoder (VAE) and Bayesian optimization (BO). VAE converts a molecule into/from its latent continuous vector, and BO optimizes a latent continuous vector (and its corresponding molecule) within a limited number of property evaluations. While the most recent work, for the first time, achieved 100% validity, its architecture is rather complex due to auxiliary neural networks other than VAE, making it difficult to train. This paper presents a molecular hypergraph grammar variational autoencoder (MHG-VAE), which uses a single VAE to achieve 100% validity. Our idea is to develop a graph grammar encoding the hard chemical constraints, called molecular hypergraph grammar (MHG), which guides VAE to always generate valid molecules. We also present an algorithm to construct MHG from a set of molecules.

arXiv comment19 pages

Cited by in corpus (24)

• Deep learning for molecular design - a review of the state of the art
• Multi-Objective Molecule Generation using Interpretable Substructures
• Constrained Bayesian Optimization for Automatic Chemical Design
• Sample-Efficient Optimization in the Latent Space of Deep Generative Models via Weighted Retraining
• CogMol: Target-Specific and Selective Drug Design for COVID-19 Using Deep Generative Models
• GraphDF: A Discrete Flow Model for Molecular Graph Generation
• Hierarchical Graph-to-Graph Translation for Molecules
• Hypergraphs: an introduction and review
• A Model to Search for Synthesizable Molecules
• BOSS: Bayesian Optimization over String Spaces
• Edge Representation Learning with Hypergraphs
• C5T5: Controllable Generation of Organic Molecules with Transformers
• Reinforced Molecular Optimization with Neighborhood-Controlled Grammars
• Barking up the right tree: an approach to search over molecule synthesis DAGs
• Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• Combining Latent Space and Structured Kernels for Bayesian Optimization over Combinatorial Spaces
• Absence of Phase Transition in Random Language Model
• Molecule Generation Experience: An Open Platform of Material Design for Public Users
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• Spanning trees in random regular uniform hypergraphs
• Graph Energy-based Model for Substructure Preserving Molecular Design
• Nonlinear Evolution Equation Associated with Hypergraph Laplacian
• Operator Autoencoders: Learning Physical Operations on Encoded Molecular Graphs