# Enhancing Monte Carlo Tree Search for Retrosynthesis

## TL;DR

This paper introduces two improvements to a search algorithm used in chemical synthesis planning, significantly speeding up the process and reducing computational costs.

## Contribution

The paper introduces eUCT and dUCT, novel enhancements to the Monte Carlo tree search algorithm for retrosynthesis.

## Key findings

- eUCT and dUCT reduced computational clock-time by up to 50% for solving heavy molecules.
- dUCT increased the number of routes found per molecule in both 1500 and 50,000 molecule sets.
- dUCT-v1 solved ∼5 million more routes than the unenhanced algorithm under a 150 s time constraint.

## 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.