Guiding Deep Molecular Optimization with Genetic Exploration

Abstract

De novo molecular design attempts to search over the chemical space for molecules with the desired property. Recently, deep learning has gained considerable attention as a promising approach to solve the problem. In this paper, we propose genetic expert-guided learning (GEGL), a simple yet novel framework for training a deep neural network (DNN) to generate highly-rewarding molecules. Our main idea is to design a "genetic expert improvement" procedure, which generates high-quality targets for imitation learning of the DNN. Extensive experiments show that GEGL significantly improves over state-of-the-art methods. For example, GEGL manages to solve the penalized octanol-water partition coefficient optimization with a score of 31.40, while the best-known score in the literature is 27.22. Besides, for the GuacaMol benchmark with 20 tasks, our method achieves the highest score for 19 tasks, in comparison with state-of-the-art methods, and newly obtains the perfect score for three tasks.

References in corpus (13)

• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Constrained Graph Variational Autoencoders for Molecule Design
• ChemTS: An Efficient Python Library for de novo Molecular Generation
• Syntax-Directed Variational Autoencoder for Structured Data
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
• Thinking Fast and Slow with Deep Learning and Tree Search
• Learning to Generalize from Sparse and Underspecified Rewards
• MolecularRNN: Generating realistic molecular graphs with optimized properties
• DEFactor: Differentiable Edge Factorization-based Probabilistic Graph Generation
• Learning To Navigate The Synthetically Accessible Chemical Space Using Reinforcement Learning
• Neural Program Synthesis with Priority Queue Training
• Policy Gradient Search: Online Planning and Expert Iteration without Search Trees

Cited by in corpus (7)

• SELFIES and the future of molecular string representations
• A Deep Generative Model for Molecule Optimization via One Fragment Modification
• Learning to Extend Molecular Scaffolds with Structural Motifs
• Controllable Data Generation by Deep Learning: A Review
• Maximum Reward Formulation In Reinforcement Learning
• SCGG: A Deep Structure-Conditioned Graph Generative Model
• Symbolic Regression via Neural-Guided Genetic Programming Population Seeding