Test-Time Training Scaling for Chemical Exploration in Drug Design

Chemical language models for molecular design have the potential to find solutions to multi-parameter optimization problems in drug discovery via reinforcement learning (RL). A key requirement to achieve this is the capacity to "search" chemical space to identify all molecules of interest. Here, we propose a challenging new benchmark to discover dissimilar molecules that possess similar bioactivity, a common scenario in drug discovery, but a hard problem to optimize. We show that a population of RL agents can solve the benchmark, while a single agent cannot. We also find that cooperative strategies are not significantly better than independent agents. Moreover, the performance on the benchmark scales log-linearly with the number of independent agents, showing a test-time training scaling law for chemical language models.

REINFORCE-ING Chemical Language Models in Drug Design

Chemical language models, combined with reinforcement learning, have shown significant promise to efficiently traverse large chemical spaces in drug design. However, the performance of various RL algorithms and their best practices for practical drug design are still unclear. Here, starting from the principles of the REINFORCE algorithm, we investigate the effect of different components from RL theory including experience replay, hill-climbing, baselines to reduce variance, and alternative reward shaping. Additionally we demonstrate how RL hyperparameters can be fine-tuned for effectiveness, efficiency, or chemical regularization as demonstrated using the MolOpt benchmark.

ACEGEN: Reinforcement learning of generative chemical agents for drug discovery

In recent years, reinforcement learning (RL) has emerged as a valuable tool in drug design, offering the potential to propose and optimize molecules with desired properties. However, striking a balance between capability, flexibility, and reliability remains challenging due to the complexity of advanced RL algorithms and the significant reliance on specialized code. In this work, we introduce ACEGEN, a comprehensive and streamlined toolkit tailored for generative drug design, built using TorchRL, a modern decision-making library that offers efficient and thoroughly tested reusable components. ACEGEN provides a robust, flexible, and efficient platform for molecular design. We validate its effectiveness by benchmarking it across various algorithms and conducting multiple drug discovery case studies. ACEGEN is accessible at https://github.com/acellera/acegen-open.