Work

Enhancing Monte Carlo Tree Search for Retrosynthesis

Year: 2025

Type: article

Abstract: Computer-Assisted Synthesis Programs are increasingly employed by organic chemists. Often, these tools combine neural networks for policy prediction with heuristic search algorithms. We propose two novel enhancements, which we call eUCT and dUCT, to the Monte Carlo tree search (MCTS) algorithm. The enhancements were deployed in AiZynthFinder and have been integrated into the open-source electronic lab notebook, AI4Green, available at https://ai4green.app. A memory-efficient stock file was used to reduce the computational carbon footprint. Both enhancements significantly reduced, by up to 50%, the computational clock-time to solve 1500 heavy (500-800 Da) molecules. The dUCT enhancement increased the number of routes found per molecule for the 1500 heavy molecules and a 50,000-molecule set from ChEMBL. eUCT and dUCT-v2 solved between 600 and 900 more molecules than the unenhanced MCTS algorithm across the 50,000 molecules. When limited to a 150 s time constraint, dUCT-v1 solved ∼5 million more routes to the 50,000 targets than the unenhanced algorithm.

Source: Journal of Chemical Information and Modeling

DOI: 10.1021/acs.jcim.5c00417

Authors: Ton M. Blackshaw, Joseph C. Davies, Kristian T. Spoerer, Jonathan D. Hirst

Institution: University of Nottingham

Language: English

Topic: Computational Drug Discovery Methods

Subfield: Computational Theory and Mathematics

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Estimated APC paid: $4,500

Funders: Royal Academy of Engineering, University of Nottingham