MolecularRNN: Generating realistic molecular graphs with optimized properties

Abstract

Designing new molecules with a set of predefined properties is a core problem in modern drug discovery and development. There is a growing need for de-novo design methods that would address this problem. We present MolecularRNN, the graph recurrent generative model for molecular structures. Our model generates diverse realistic molecular graphs after likelihood pretraining on a big database of molecules. We perform an analysis of our pretrained models on large-scale generated datasets of 1 million samples. Further, the model is tuned with policy gradient algorithm, provided a critic that estimates the reward for the property of interest. We show a significant distribution shift to the desired range for lipophilicity, drug-likeness, and melting point outperforming state-of-the-art works. With the use of rejection sampling based on valency constraints, our model yields 100% validity. Moreover, we show that invalid molecules provide a rich signal to the model through the use of structure penalty in our reinforcement learning pipeline.

References in corpus (4)

• Semi-Supervised Classification with Graph Convolutional Networks
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Objective-Reinforced Generative Adversarial Networks (ORGAN) for Sequence Generation Models
• Learning Deep Generative Models of Graphs

Cited by in corpus (17)

• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
• A Graph to Graphs Framework for Retrosynthesis Prediction
• Constrained Bayesian Optimization for Automatic Chemical Design
• Guiding Deep Molecular Optimization with Genetic Exploration
• GraphDF: A Discrete Flow Model for Molecular Graph Generation
• MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
• Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
• JANUS: Parallel Tempered Genetic Algorithm Guided by Deep Neural Networks for Inverse Molecular Design
• Practical Massively Parallel Monte-Carlo Tree Search Applied to Molecular Design
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• LMKG: Learned Models for Cardinality Estimation in Knowledge Graphs
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• Incorporating domain knowledge into neural-guided search
• Graph Energy-based Model for Substructure Preserving Molecular Design
• Realistic molecule optimization on a learned graph manifold
• Graph2Graph Learning with Conditional Autoregressive Models
• GraphGen-Redux: a Fast and Lightweight Recurrent Model for labeled Graph Generation