A Quick Policy to Filter Reactions Based on Feasibility in AI-Guided Retrosynthetic Planning

25 November 2020, Version 1
This content is a preprint and has not undergone peer review at the time of posting.


A neural network-guided Monte Carlo tree search (MCTS) has been shown to be a promising algorithm
for computer-aided synthesis prediction. Here we train and investigate a filter policy that removes
unfeasible reactions from the search. We investigate three different methods to generate negative
data that the filter policy model can be trained on, and we show that these methods are
complementary to each other. Therefore the most robust model is one that combines all generated
negative data. The filter in itself is quick (< 0.1 s per prediction on average) but using the filter policy
in the MCTS results in a doubling of the search time. However it only leads to a small reduction in the
success rate of finding synthetic routes (< 1%) and we are able show that using filter policy the MCTS
algorithm produce more promising routes, although the predicted routes are more complex. The filter
policy has been integrated in the AiZynthFinder software.


neural networks
Monte Carlo tree search
synthesis prediction
reaction feasibility


Comments are not moderated before they are posted, but they can be removed by the site moderators if they are found to be in contravention of our Commenting Policy [opens in a new tab] - please read this policy before you post. Comments should be used for scholarly discussion of the content in question. You can find more information about how to use the commenting feature here [opens in a new tab] .
This site is protected by reCAPTCHA and the Google Privacy Policy [opens in a new tab] and Terms of Service [opens in a new tab] apply.