Utilizing Reinforcement Learning for de novo Drug Design
This work addresses the challenge of efficient drug discovery for researchers, but it is incremental as it builds on existing reinforcement learning methods for molecule generation.
The paper tackled the problem of generating novel drug molecules with specific properties by developing a unified reinforcement learning framework for de novo drug design, resulting in findings that using diverse scoring molecules can enhance structural diversity and performance stability, with off-policy algorithms potentially improving active molecule generation at the cost of longer exploration.
Deep learning-based approaches for generating novel drug molecules with specific properties have gained a lot of interest in the last few years. Recent studies have demonstrated promising performance for string-based generation of novel molecules utilizing reinforcement learning. In this paper, we develop a unified framework for using reinforcement learning for de novo drug design, wherein we systematically study various on- and off-policy reinforcement learning algorithms and replay buffers to learn an RNN-based policy to generate novel molecules predicted to be active against the dopamine receptor DRD2. Our findings suggest that it is advantageous to use at least both top-scoring and low-scoring molecules for updating the policy when structural diversity is essential. Using all generated molecules at an iteration seems to enhance performance stability for on-policy algorithms. In addition, when replaying high, intermediate, and low-scoring molecules, off-policy algorithms display the potential of improving the structural diversity and number of active molecules generated, but possibly at the cost of a longer exploration phase. Our work provides an open-source framework enabling researchers to investigate various reinforcement learning methods for de novo drug design.