Jump to main content
Jump to site search


Molecular Transformer unifies reaction prediction and retrosynthesis across pharma chemical space

Author affiliations

Abstract

Predicting how a complex molecule reacts with different reagents, and how to synthesise complex molecules from simpler starting materials, are fundamental to organic chemistry. We show that an attention-based machine translation model – Molecular Transformer – tackles both reaction prediction and retrosynthesis by learning from the same dataset. Reagents, reactants and products are represented as SMILES text strings. For reaction prediction, the model “translates” the SMILES of reactants and reagents to product SMILES, and the converse for retrosynthesis. Moreover, a model trained on publicly available data is able to make accurate predictions on proprietary molecules extracted from pharma electronic lab notebooks, demonstrating generalisability across chemical space. We expect our versatile framework to be broadly applicable to problems such as reaction condition prediction, reagent prediction and yield prediction.

Graphical abstract: Molecular Transformer unifies reaction prediction and retrosynthesis across pharma chemical space

Back to tab navigation

Publication details

The article was received on 04 Jul 2019, accepted on 29 Aug 2019 and first published on 29 Aug 2019


Article type: Communication
DOI: 10.1039/C9CC05122H
Chem. Commun., 2019, Advance Article

  •   Request permissions

    Molecular Transformer unifies reaction prediction and retrosynthesis across pharma chemical space

    A. A. Lee, Q. Yang, V. Sresht, P. Bolgar, X. Hou, J. L. Klug-McLeod and C. R. Butler, Chem. Commun., 2019, Advance Article , DOI: 10.1039/C9CC05122H

Search articles by author

Spotlight

Advertisements