MARS: Markov Molecular Sampling for Multi-objective Drug Discovery

TL;DR

MARS introduces a novel graph-based, Markov chain Monte Carlo sampling method with adaptive proposals and on-the-fly GNN training to efficiently generate diverse, multi-objective drug-like molecules, outperforming existing approaches.

Contribution

MARS is the first to combine MCMC sampling with adaptive proposals and on-the-fly GNN training for multi-objective molecular generation.

Findings

Achieves state-of-the-art results in multi-objective drug discovery tasks.

Significantly outperforms previous methods in complex multi-objective optimization.

Demonstrates high sample efficiency and diversity in generated molecules.

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.