MARS: Markov Molecular Sampling for Multi-objective Drug Discovery

Abstract

Searching for novel molecules with desired chemical properties is crucial in drug discovery. Existing work focuses on developing neural models to generate either molecular sequences or chemical graphs. However, it remains a big challenge to find novel and diverse compounds satisfying several properties. In this paper, we propose MARS, a method for multi-objective drug molecule discovery. MARS is based on the idea of generating the chemical candidates by iteratively editing fragments of molecular graphs. To search for high-quality candidates, it employs Markov chain Monte Carlo sampling (MCMC) on molecules with an annealing scheme and an adaptive proposal. To further improve sample efficiency, MARS uses a graph neural network (GNN) to represent and select candidate edits, where the GNN is trained on-the-fly with samples from MCMC. Experiments show that MARS achieves state-of-the-art performance in various multi-objective settings where molecular bio-activity, drug-likeness, and synthesizability are considered. Remarkably, in the most challenging setting where all four objectives are simultaneously optimized, our approach outperforms previous methods significantly in comprehensive evaluations. The code is available at https://github.com/yutxie/mars.

ICLR 2021

References in corpus (7)

• Neural Message Passing for Quantum Chemistry
• MolGAN: An implicit generative model for small molecular graphs
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
• Strategies for Pre-training Graph Neural Networks
• Generative Models for Automatic Chemical Design
• MolecularRNN: Generating realistic molecular graphs with optimized properties
• Hierarchical Graph-to-Graph Translation for Molecules

Cited by in corpus (9)

• Graph Representation Learning in Biomedicine
• Learning Gradient Fields for Molecular Conformation Generation
• 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
• Amortized Tree Generation for Bottom-up Synthesis Planning and Synthesizable Molecular Design
• Differentiable Scaffolding Tree for Molecular Optimization
• Edge Representation Learning with Hypergraphs
• Realistic molecule optimization on a learned graph manifold
• GFlowNet Foundations