Send to

Choose Destination
Nature. 2018 Mar 28;555(7698):604-610. doi: 10.1038/nature25978.

Planning chemical syntheses with deep neural networks and symbolic AI.

Author information

Institute of Organic Chemistry and Center for Multiscale Theory and Computation, Westfälische Wilhelms-Universität, Münster, Germany.
BenevolentAI, London, UK.
European Research Center for Information Systems, Westfälische Wilhelms-Universität Münster, Germany.
Department of Physics and International Centre for Quantum and Molecular Structures, Shanghai University, Shanghai, China.


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.

Comment in

[Indexed for MEDLINE]

Supplemental Content

Full text links

Icon for Nature Publishing Group
Loading ...
Support Center