Retro*: Learning Retrosynthetic Planning with Neural Guided A* Search
This work addresses the problem of efficient and high-quality retrosynthetic planning for chemists, representing a strong specific gain in the domain.
The paper tackles the challenge of retrosynthetic planning in organic chemistry by proposing Retro*, a neural-guided A* search algorithm that efficiently finds high-quality synthetic routes. Experiments on USPTO datasets show it outperforms existing state-of-the-art methods in success rate and solution quality while being more efficient.
Retrosynthetic planning is a critical task in organic chemistry which identifies a series of reactions that can lead to the synthesis of a target product. The vast number of possible chemical transformations makes the size of the search space very big, and retrosynthetic planning is challenging even for experienced chemists. However, existing methods either require expensive return estimation by rollout with high variance, or optimize for search speed rather than the quality. In this paper, we propose Retro*, a neural-based A*-like algorithm that finds high-quality synthetic routes efficiently. It maintains the search as an AND-OR tree, and learns a neural search bias with off-policy data. Then guided by this neural network, it performs best-first search efficiently during new planning episodes. Experiments on benchmark USPTO datasets show that, our proposed method outperforms existing state-of-the-art with respect to both the success rate and solution quality, while being more efficient at the same time.