Hierarchical Graph-to-Graph Translation for Molecules

Abstract

The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties. Our work in this paper substantially extends prior state-of-the-art on graph-to-graph translation methods for molecular optimization. In particular, we realize coherent multi-resolution representations by interweaving the encoding of substructure components with the atom-level encoding of the original molecular graph. Moreover, our graph decoder is fully autoregressive, and interleaves each step of adding a new substructure with the process of resolving its attachment to the emerging molecule. We evaluate our model on multiple molecular optimization tasks and show that our model significantly outperforms previous state-of-the-art baselines.

References in corpus (20)

• Deep Convolutional Networks on Graph-Structured Data
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MolGAN: An implicit generative model for small molecular graphs
• Learning Deep Generative Models of Graphs
• How Powerful are Graph Neural Networks?
• Constrained Graph Variational Autoencoders for Molecule Design
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Syntax-Directed Variational Autoencoder for Structured Data
• Conditional molecular design with deep generative models
• NetGAN: Generating Graphs via Random Walks
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• Grammar Variational Autoencoder
• Covariant Compositional Networks For Learning Graphs
• Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
• Generating Focussed Molecule Libraries for Drug Discovery with Recurrent Neural Networks
• DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation
• Molecular Hypergraph Grammar with its Application to Molecular Optimization
• Graphite: Iterative Generative Modeling of Graphs
• Multi-Objective De Novo Drug Design with Conditional Graph Generative Model

Cited by in corpus (9)

• Multi-Objective Molecule Generation using Interpretable Substructures
• Optimizing Molecules using Efficient Queries from Property Evaluations
• MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
• Can Graph Neural Networks Count Substructures?
• MIMOSA: Multi-constraint Molecule Sampling for Molecule Optimization
• Barking up the right tree: an approach to search over molecule synthesis DAGs
• Graph-Aware Transformer: Is Attention All Graphs Need?
• Improving Molecular Design by Stochastic Iterative Target Augmentation
• Molecular Attributes Transfer from Non-Parallel Data