Learning to Plan Chemical Syntheses

TL;DR

This paper introduces a novel computer-aided retrosynthesis method using Monte Carlo Tree Search combined with neural networks, significantly improving speed and success rate in planning organic molecule syntheses.

Contribution

The authors develop a deep learning-guided MCTS approach trained on 12 million reactions, achieving faster and more successful retrosynthesis planning than previous methods.

Findings

Solves nearly twice as many molecules as traditional methods

30 times faster in retrosynthesis planning

Routes generated are indistinguishable from literature routes

Abstract

From medicines to materials, small organic molecules are indispensable for human well-being. To plan their syntheses, chemists employ a problem solving technique called retrosynthesis. In retrosynthesis, target molecules are recursively transformed into increasingly simpler precursor compounds until a set of readily available starting materials is obtained. Computer-aided retrosynthesis would be a highly valuable tool, however, past approaches were slow and provided results of unsatisfactory quality. Here, we employ Monte Carlo Tree Search (MCTS) to efficiently discover retrosynthetic routes. MCTS was combined with an expansion policy network that guides the search, and an "in-scope" filter network to pre-select the most promising retrosynthetic steps. These deep neural networks were trained on 12 million reactions, which represents essentially all reactions ever published in organic chemistry. Our system solves almost twice as many molecules and is 30 times faster in comparison to the traditional search method based on extracted rules and hand-coded heuristics. Finally after a 60 year history of computer-aided synthesis planning, chemists can no longer distinguish between routes generated by a computer system and real routes taken from the scientific literature. We anticipate that our method will accelerate drug and materials discovery by assisting chemists to plan better syntheses faster, and by enabling fully automated robot synthesis.