Display options
Cite
Schwaller P, Laino T, Gaudin T, et al. Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction. ACS Cent Sci. 2019;5(9):1572-1583doi: 10.1021/acscentsci.9b00576.
Schwaller, P., Laino, T., Gaudin, T., Bolgar, P., Hunter, C. A., Bekas, C., & Lee, A. A. (2019). Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction. ACS central science, 5(9), 1572-1583. https://doi.org/10.1021/acscentsci.9b00576
Schwaller, Philippe, et al. "Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction." ACS central science vol. 5,9 (2019): 1572-1583. doi: https://doi.org/10.1021/acscentsci.9b00576
Schwaller P, Laino T, Gaudin T, Bolgar P, Hunter CA, Bekas C, Lee AA. Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction. ACS Cent Sci. 2019 Sep 25;5(9):1572-1583. doi: 10.1021/acscentsci.9b00576. Epub 2019 Aug 30. PMID: 31572784; PMCID: PMC6764164.
Copy Download .nbib Format: NLM
Share it on

ACS Cent Sci. 2019 Sep 25;5(9):1572-1583. doi: 10.1021/acscentsci.9b00576. Epub 2019 Aug 30.

Molecular Transformer: A Model for Uncertainty-Calibrated Chemical Reaction Prediction.

ACS central science

Philippe Schwaller, Teodoro Laino, Théophile Gaudin, Peter Bolgar, Christopher A Hunter, Costas Bekas, Alpha A Lee

Affiliations

  1. IBM Research - Zurich, Rüschlikon 8803, Switzerland.
  2. Department of Physics, University of Cambridge, Cambridge CB3 0HE, United Kingdom.
  3. Department of Chemistry, University of Cambridge, Cambridge CB2 1EW, United Kingdom.

PMID: 31572784 PMCID: PMC6764164 DOI: 10.1021/acscentsci.9b00576

Abstract

Organic synthesis is one of the key stumbling blocks in medicinal chemistry. A necessary yet unsolved step in planning synthesis is solving the forward problem: Given reactants and reagents, predict the products. Similar to other work, we treat reaction prediction as a machine translation problem between simplified molecular-input line-entry system (SMILES) strings (a text-based representation) of reactants, reagents, and the products. We show that a multihead attention Molecular Transformer model outperforms all algorithms in the literature, achieving a top-1 accuracy above 90% on a common benchmark data set. Molecular Transformer makes predictions by inferring the correlations between the presence and absence of chemical motifs in the reactant, reagent, and product present in the data set. Our model requires no handcrafted rules and accurately predicts subtle chemical transformations. Crucially, our model can accurately estimate its own uncertainty, with an uncertainty score that is 89% accurate in terms of classifying whether a prediction is correct. Furthermore, we show that the model is able to handle inputs without a reactant-reagent split and including stereochemistry, which makes our method universally applicable.

Copyright © 2019 American Chemical Society.

Conflict of interest statement

The authors declare no competing financial interest.

References

  1. Mol Inform. 2018 Jan;37(1-2): - PubMed
  2. Acc Chem Res. 2018 May 15;51(5):1281-1289 - PubMed
  3. Chem Sci. 2018 Nov 26;10(2):370-377 - PubMed
  4. Chemistry. 2017 May 2;23(25):5966-5971 - PubMed
  5. Med Res Rev. 1996 Jan;16(1):3-50 - PubMed
  6. J Chem Inf Model. 2016 Dec 27;56(12):2336-2346 - PubMed
  7. Chem Sci. 2017 Nov 13;9(3):660-665 - PubMed
  8. Chem Sci. 2018 Jun 22;9(28):6091-6098 - PubMed
  9. J Chem Inf Model. 2015 Jan 26;55(1):39-53 - PubMed
  10. Drug Discov Today. 2018 Jun;23(6):1203-1218 - PubMed
  11. J Am Chem Soc. 2019 Jan 9;141(1):29-32 - PubMed
  12. ACS Cent Sci. 2016 Oct 26;2(10):725-732 - PubMed
  13. Org Biomol Chem. 2004 Jun 7;2(11):1563-72 - PubMed
  14. Science. 2005 Apr 15;308(5720):395-8 - PubMed
  15. Org Lett. 2019 May 17;21(10):3670-3673 - PubMed
  16. ACS Cent Sci. 2017 May 24;3(5):434-443 - PubMed
  17. Nature. 2018 Mar 28;555(7698):604-610 - PubMed
  18. Sci Adv. 2018 Jul 25;4(7):eaap7885 - PubMed
  19. Science. 1985 Apr 26;228(4698):408-18 - PubMed
  20. J Chem Inf Model. 2019 Jan 28;59(1):43-52 - PubMed
  21. Angew Chem Int Ed Engl. 2016 May 10;55(20):5904-37 - PubMed
  22. J Org Chem. 2018 Oct 5;83(19):11571-11576 - PubMed
  23. Nat Chem. 2018 Apr;10(4):383-394 - PubMed
  24. ACS Cent Sci. 2018 Feb 28;4(2):268-276 - PubMed
  25. Nat Rev Drug Discov. 2018 Oct;17(10):709-727 - PubMed
  26. J Med Chem. 2016 May 12;59(9):4385-402 - PubMed

Publication Types