Premium
Efficient Construction of a Chemical Reaction Network Guided By a Monte Carlo Tree Search
Author(s) -
Lee Kyunghoon,
Woo Kim Jin,
Youn Kim Woo
Publication year - 2020
Publication title -
chemsystemschem
Language(s) - English
Resource type - Journals
ISSN - 2570-4206
DOI - 10.1002/syst.201900057
Subject(s) - monte carlo method , computer science , monte carlo tree search , quantum chemical , quantum monte carlo , graph , chemical reaction , tree (set theory) , graph theory , theoretical computer science , mathematical optimization , computational chemistry , chemistry , mathematics , molecule , combinatorics , biochemistry , organic chemistry , statistics
Chemical reaction networks are essential for the complete elucidation of chemical reaction mechanisms. Graph‐theoretic methods combined with quantum calculations are known to be an efficient approach with broad applicability for constructing reaction networks. However, this method entails high computational cost due to quantum calculations on chemically irrelevant intermediates coming from the exploration of a large scale chemical space. To remedy this problem, we propose to apply the Monte Carlo tree search algorithm to those graph‐theoretic methods. We have combined it with ACE‐Reaction, our in‐house graph‐theoretic method, and demonstrated its performance on five organic reactions. The result shows that the computational cost for quantum calculations has been reduced by up to 75 % from that of the original ACE‐Reaction. Furthermore, cost reduction became more efficient for more complex reactions.