These are preliminary reports that have not been peer-reviewed. They should not be regarded as conclusive, guide clinical practice/health-related behavior, or be reported in news media as established information. For more information, please see our FAQs.
filter-policy-v1.1.pdf (1.89 MB)

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

submitted on 24.11.2020, 11:34 and posted on 25.11.2020, 05:15 by Samuel Genheden, Ola Engkvist, Esben Jannik Bjerrum
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.


Email Address of Submitting Author





ORCID For Submitting Author


Declaration of Conflict of Interest

No conflict of interest