Multi-Objective Molecule Generation using Interpretable Substructures

Abstract

Drug discovery aims to find novel compounds with specified chemical property profiles. In terms of generative modeling, the goal is to learn to sample molecules in the intersection of multiple property constraints. This task becomes increasingly challenging when there are many property constraints. We propose to offset this complexity by composing molecules from a vocabulary of substructures that we call molecular rationales. These rationales are identified from molecules as substructures that are likely responsible for each property of interest. We then learn to expand rationales into a full molecule using graph generative models. Our final generative model composes molecules as mixtures of multiple rationale completions, and this mixture is fine-tuned to preserve the properties of interest. We evaluate our model on various drug design tasks and demonstrate significant improvements over state-of-the-art baselines in terms of accuracy, diversity, and novelty of generated compounds.

References in corpus (13)

• GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
• Towards A Rigorous Science of Interpretable Machine Learning
• Axiomatic Attribution for Deep Networks
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• MolGAN: An implicit generative model for small molecular graphs
• Constrained Graph Variational Autoencoders for Molecule Design
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Conditional molecular design with deep generative models
• Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry
• Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
• Molecular Hypergraph Grammar with its Application to Molecular Optimization
• Hierarchical Graph-to-Graph Translation for Molecules

Cited by in corpus (18)

• A Deep Generative Model for Molecule Optimization via One Fragment Modification
• On Explainability of Graph Neural Networks via Subgraph Explorations
• Iterative Refinement Graph Neural Network for Antibody Sequence-Structure Co-design
• Utilizing Reinforcement Learning for de novo Drug Design
• Multi-Objective Latent Space Optimization of Generative Molecular Design Models
• JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design
• Differentiable Scaffolding Tree for Molecular Optimization
• PROUD: PaRetO-gUided Diffusion Model for Multi-objective Generation
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• Recognizing Predictive Substructures with Subgraph Information Bottleneck
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• Graph Information Bottleneck for Subgraph Recognition
• Multi-objective Optimization by Learning Space Partitions
• Leveraging Active Subspaces to Capture Epistemic Model Uncertainty in Deep Generative Models for Molecular Design
• Amortized Synthesis of Constrained Configurations Using a Differentiable Surrogate
• Evening the Score: Targeting SARS-CoV-2 Protease Inhibition in Graph Generative Models for Therapeutic Candidates
• Molecular Attributes Transfer from Non-Parallel Data
• Graph2Graph Learning with Conditional Autoregressive Models