Download PDF
Synlett 2021; 32(18): 1833-1836
DOI: 10.1055/a-1553-0427
cluster
Machine Learning and Artificial Intelligence in Chemical Synthesis and Catalysis

Multi-Instance Learning Approach to Predictive Modeling of Catalysts Enantioselectivity

D. Zankov
a   Laboratory of Chemoinformatics, University of Strasbourg, 4, B. Pascal, 67081 Strasbourg, France
c   Laboratory of Chemoinformatics and Molecular Modeling, Kazan Federal University, Kremlyovskaya 18, 420008 Kazan, Russia
,
P. Polishchuk
b   Institute of Molecular and Translational Medicine, Palacký University, Hnevotinska 5, 77900 Olomouc, Czech Republic
,
T. Madzhidov 
c   Laboratory of Chemoinformatics and Molecular Modeling, Kazan Federal University, Kremlyovskaya 18, 420008 Kazan, Russia
,
A. Varnek∗
a   Laboratory of Chemoinformatics, University of Strasbourg, 4, B. Pascal, 67081 Strasbourg, France
d   Institute for Chemical Reaction Design and Discovery (WPI-ICReDD), Hokkaido University, Kita 21 Nishi 10, Kita-ku, 001-0021 Sapporo, Japan
› Author AffiliationsDZ thanks the French Embassy in Russia for the PhD fellowship. TM thanks Russian Science Foundation (Grant No. 19-73-10137) for the support.
› Further Information
    Permissions and Reprints All articles of this category


Abstract

Here, we report an application of the multi-instance learning approach to predictive modeling of enantioselectivity of chiral catalysts. Catalysts were represented by ensembles of conformations encoded­ by the pmapper physicochemical descriptors capturing stereoconfiguration of the molecule. Each catalyzed chemical reaction was transformed to a condensed graph of reaction for which ISIDA fragment descriptors were generated. This approach does not require any conformations’ alignment and can potentially be used for a diverse set of catalysts bearing different scaffolds. Its efficiency has been demonstrated in predicting the selectivity of BINOL-derived phosphoric acid catalysts in asymmetric thiol addition to N-acylimines and benchmarked with previously reported models.

Key words

asymmetric catalysis - chemoinformatics - machine learning - QSSR


Publication History

Received: 10 June 2021

Accepted after revision: 16 July 2021

Accepted Manuscript online:
16 July 2021

Article published online:
12 August 2021

© 2021. Thieme. All rights reserved

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany

 

  • References

  • 1 Yang W, Fidelis TT, Sun W.-H. ACS Omega 2019; 5: 83
    CrossrefPubMed
  • 2 Yada A, Nagata K, Ando Y, Matsumura T, Ichinoseki S, Sato K. Chem. Lett. 2018; 47: 284
    Crossref
  • 3 Kozlowski MC, Dixon SL, Panda M, Lauri G. J. Am. Chem. Soc. 2003; 125: 6614
    CrossrefPubMed
  • 4 Lipkowitz KB, Pradhan M. J. Org. Chem. 2003; 68: 4648
    CrossrefPubMed
  • 5 Melville JL, Lovelock KR. J, Wilson C, Allbutt B, Burke EK, Lygo B, Hirst JD. J. Chem. Inf. Model. 2005; 45: 971
    CrossrefPubMed
  • 6 Zahrt AF, Henle JJ, Rose BT, Wang Y, Darrow WT, Denmark SE. Science 2019; 363
  • 7 Henle JJ, Zahrt AF, Rose BT, Darrow WT, Wang Y, Denmark SE. J. Am. Chem. Soc. 2020; 142: 11578
    CrossrefPubMed
  • 8 Yamaguchi S, Sodeoka M. Bull. Chem. Soc. Jpn. 2019; 92: 1701
    Crossref
  • 9 Xu L.-C, Li X, Tang M.-J, Yuan L.-T, Zheng J.-Y, Zhang S.-Q, Hong X. Synlett 2020; 31 DOI: 10.1055/s-0040-1705977.
    Article in Thieme Connect
  • 10 Dietterich TG, Lathrop RH, Lozano-Pérez T. Artif. Intell. 1997; 89: 31
    Crossref
  • 11 Kutlushina A, Khakimova A, Madzhidov T, Polishchuk P. Molecules 2018; 23: 3094
    CrossrefPubMed
  • 12 Zankov DV, Matveieva M, Nikonenko A, Nugmanov R, Varnek A, Polishchuk P, Madzhidov T. ChemRxiv 2020; DOI: 10.26434/chemrxiv.13456277.v1.
    Crossref
  • 13 Hoonakker F, Lachiche N, Varnek A, Wagner A. Int. J. Artif. Intell. Tools 2011; 20: 253
    Crossref
  • 14 Nugmanov RI, Mukhametgaleev RN, Akhmetshin T, Gimadiev TR, Afonina VA, Madzhidov TI, Varnek A. J. Chem. Inf. Model. 2019; 59: 2516
    CrossrefPubMed
  • 15 Varnek A, Fourches D, Hoonakker F, Solov’ev VP. J. Comput. Aided. Mol. Des. 2005; 19: 693
    CrossrefPubMed
  • 16 Riniker S, Landrum GA. J. Chem. Inf. Model. 2015; 55: 2562
    CrossrefPubMed
  • 17 Implemented modeling protocol is available at (accessed June 7, 2021): https://github.com/dzankov/3D-MIL-QSSR