Adversarial Learned Molecular Graph Inference and Generation
arXiv:1905.10310 · doi:10.1007/978-3-030-67661-2_11
Abstract
Recent methods for generating novel molecules use graph representations of molecules and employ various forms of graph convolutional neural networks for inference. However, training requires solving an expensive graph isomorphism problem, which previous approaches do not address or solve only approximately. In this work, we propose ALMGIG, a likelihood-free adversarial learning framework for inference and de novo molecule generation that avoids explicitly computing a reconstruction loss. Our approach extends generative adversarial networks by including an adversarial cycle-consistency loss to implicitly enforce the reconstruction property. To capture properties unique to molecules, such as valence, we extend the Graph Isomorphism Network to multi-graphs. To quantify the performance of models, we propose to compute the distance between distributions of physicochemical properties with the 1-Wasserstein distance. We demonstrate that ALMGIG more accurately learns the distribution over the space of molecules than all baselines. Moreover, it can be utilized for drug discovery by efficiently searching the space of molecules using molecules' continuous latent representation. Our code is available at https://github.com/ai-med/almgig
arXiv commentAccepted at The European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD); Code at https://github.com/ai-med/almgig
References in corpus (18)
- GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
- Categorical Reparameterization with Gumbel-Softmax
- Automatic chemical design using a data-driven continuous representation of molecules
- Deep Reinforcement Learning for De-Novo Drug Design
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Representation Learning on Graphs with Jumping Knowledge Networks
- GuacaMol: Benchmarking Models for De Novo Molecular Design
- Junction Tree Variational Autoencoder for Molecular Graph Generation
- Adversarially Learned Inference
- Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
- MolGAN: An implicit generative model for small molecular graphs
- Learning Deep Generative Models of Graphs
- Constrained Graph Variational Autoencoders for Molecule Design
- Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
- Syntax-Directed Variational Autoencoder for Structured Data
- Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
- ALICE: Towards Understanding Adversarial Learning for Joint Distribution Matching
- A Deep Generative Model for Fragment-Based Molecule Generation