MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
This work addresses the problem of multi-objective drug discovery for pharmaceutical researchers, representing an incremental improvement by combining existing techniques like MCMC and GNNs in a novel way.
The paper tackles the challenge of discovering novel and diverse drug molecules that satisfy multiple chemical properties simultaneously, and demonstrates that their MARS method achieves state-of-the-art performance in multi-objective settings, significantly outperforming previous methods in the most challenging four-objective scenario.
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.