Planning chemical syntheses with deep neural networks and symbolic AI

To plan the syntheses of small organic molecules, chemists use retrosynthesis, a problem-solving technique in which target molecules are recursively transformed into increasingly simpler precursors. Computer-aided retrosynthesis would be a valuable tool but at present it is slow and provides results...

Full description

Saved in:
Bibliographic Details
Published in:Nature (London) 2018-03, Vol.555 (7698), p.604-610
Main Authors: Segler, Marwin H S, Preuss, Mike, Waller, Mark P
Format: Article
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Automation
Chemical reactions
Chemists
Computer networks
Computer simulation
Design
Heuristic
Methods
Neural networks
Neural stem cells
Organic chemistry
Organic compound synthesis
Planning
Problem solving
Searching
Trees
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:To plan the syntheses of small organic molecules, chemists use retrosynthesis, a problem-solving technique in which target molecules are recursively transformed into increasingly simpler precursors. Computer-aided retrosynthesis would be a valuable tool but at present it is slow and provides results of unsatisfactory quality. Here we use Monte Carlo tree search and symbolic artificial intelligence (AI) to discover retrosynthetic routes. We combined Monte Carlo tree search with an expansion policy network that guides the search, and a filter network to pre-select the most promising retrosynthetic steps. These deep neural networks were trained on essentially all reactions ever published in organic chemistry. Our system solves for almost twice as many molecules, thirty times faster than the traditional computer-aided search method, which is based on extracted rules and hand-designed heuristics. In a double-blind AB test, chemists on average considered our computer-generated routes to be equivalent to reported literature routes.
ISSN:0028-0836
1476-4687
DOI:10.1038/nature25978