- Abstract: Retrosynthesis is a technique to plan the chemical synthesis of organic molecules, for example drugs, agro- and fine chemicals. In retrosynthesis, a search tree is built by analysing molecules recursively and dissecting them into simpler molecular building blocks until one obtains a set of known building blocks. The search space is intractably large, and it is difficult to determine the value of retrosynthetic positions. Here, we propose to model retrosynthesis as a Markov Decision Process. In combination with a Deep Neural Network policy trained on 5.5 million reactions, Monte Carlo Tree Search (MCTS) can be used to evaluate positions. In exploratory studies, we demonstrate that MCTS with neural network policies outperforms the traditionally used best-first search with hand-coded heuristics.
- TL;DR: Analogous to AlphaGo, chemical syntheses can be planned by combining Neural Networks that select actions with Monte Carlo Tree Search.
- Keywords: Deep learning, Applications, Games
- Conflicts: wwu.de, shu.edu.cn