Skip to main content

Thank you for visiting You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

Enantioselectivity prediction of pallada-electrocatalysed C–H activation using transition state knowledge in machine learning


Enantioselectivity prediction in asymmetric catalysis has been a long-standing challenge in synthetic chemistry because of the high-dimensional nature of the structure–enantioselectivity relationship. A lack of understanding of the synthetic space results in laborious and time-consuming efforts in the discovery of asymmetric reactions, even if the same transformation has already been optimized on model substrates. Here we present a data-driven workflow to achieve a holistic enantioselectivity prediction of asymmetric pallada-electrocatalysed C–H activation by implementing transition state knowledge in machine learning. The vectorization of transition state knowledge allowed for an excellent description and extrapolation of the machine learning model, and enabled the quantitative evaluation of 846,720 possibilities. Model interpretation revealed the non-intuitive olefin effect on the enantioselectivity determination. Subsequent density functional theory calculations unravelled mechanistic knowledge that the rate-determining step depends on the olefin reactivity in the insertion step. Therefore, the olefin insertion step can be involved in the overall enantioselectivity determination. These results highlight the complementary features of knowledge-based machine learning with an interpretation-driven mechanistic study, which provides the opportunity to harness widely existing catalysis screening data and transition state models in molecular synthesis.

This is a preview of subscription content, access via your institution

Access options

Rent or buy this article

Get just this article for as long as you need it


Prices may be subject to local taxes which are calculated during checkout

Fig. 1: Prediction strategies for asymmetric catalysis.
Fig. 2: Workflow design for synthetic space prediction.
Fig. 3: Dataset of the pallada-electrocatalysed C–H olefination and design of TS model-based encoding.
Fig. 4: Regression performance of the designed ML model.
Fig. 5: Model interpretation and mechanistic study of the olefin effect.
Fig. 6: Synthetic space prediction and experimental verifications.

Data availability

Data related to ML details, experimental procedures, HPLC spectra and NMR spectra are available in the Supplementary Information. Source data are provided with this paper.

Code availability

Codes for target transformation, descriptor generation, model training, feature selection, feature ranking and synthetic space exploration are freely available at


  1. Noyori, R. Asymmetric catalysis: science and opportunities (Nobel Lecture). Angew. Chem. Int. Ed. 41, 2008–2022 (2002).

    Article  CAS  Google Scholar 

  2. Trost, B. M. Asymmetric catalysis: an enabling science. Proc. Natl Acad. Sci. USA 101, 5348–5355 (2004).

    Article  CAS  PubMed Central  Google Scholar 

  3. Noyori, R. Synthesizing our future. Nat. Chem. 1, 5–6 (2009).

    Article  CAS  Google Scholar 

  4. Taylor, M. S. & Jacobsen, E. N. Asymmetric catalysis in complex target synthesis. Proc. Natl Acad. Sci. USA 101, 5368–5373 (2004).

    Article  CAS  PubMed Central  Google Scholar 

  5. Woodard, S. S., Finn, M. G. & Sharpless, K. B. Mechanism of asymmetric epoxidation. 1. Kinetics. J. Am. Chem. Soc. 113, 106–113 (1991).

    Article  CAS  Google Scholar 

  6. Cheong, P. H.-Y., Legault, C. Y., Um, J. M., Çelebi-Ölçüm, N. & Houk, K. N. Quantum mechanical investigations of organocatalysis: mechanisms, reactivities, and selectivities. Chem. Rev. 111, 5042–5137 (2011).

    Article  CAS  PubMed Central  Google Scholar 

  7. Bahmanyar, S., Houk, K. N., Martin, H. J. & List, B. Quantum mechanical predictions of the stereoselectivities of proline-catalyzed asymmetric intermolecular aldol reactions. J. Am. Chem. Soc. 125, 2475–2479 (2003).

    Article  CAS  Google Scholar 

  8. Lam, Y.-h, Grayson, M. N., Holland, M. C., Simon, A. & Houk, K. N. Theory and modeling of asymmetric catalytic reactions. Acc. Chem. Res. 49, 750–762 (2016).

    Article  CAS  Google Scholar 

  9. Knowles, R. R. & Jacobsen, E. N. Attractive noncovalent interactions in asymmetric catalysis: links between enzymes and small molecule catalysts. Proc. Natl Acad. Sci. USA 107, 20678–20685 (2010).

    Article  CAS  PubMed Central  Google Scholar 

  10. Neel, A. J., Milo, A., Sigman, M. S. & Toste, F. D. Enantiodivergent fluorination of allylic alcohols: data set design reveals structural interplay between achiral directing group and chiral Anion. J. Am. Chem. Soc. 138, 3863–3875 (2016).

    Article  CAS  PubMed Central  Google Scholar 

  11. Crawford, J. M., Kingston, C., Toste, F. D. & Sigman, M. S. Data science meets physical organic chemistry. Acc. Chem. Res. 54, 3136–3148 (2021).

    Article  CAS  Google Scholar 

  12. Zahrt, A. F., Athavale, S. V. & Denmark, S. E. Quantitative structure–selectivity relationships in enantioselective catalysis: past, present, and future. Chem. Rev. 120, 1620–1689 (2020).

    Article  CAS  Google Scholar 

  13. Oliveira, J. C. A. et al. When machine learning meets molecular synthesis. Trends Chem. 4, 863–885 (2022).

    Article  CAS  Google Scholar 

  14. Mater, A. C. & Coote, M. L. Deep learning in chemistry. J. Chem. Inf. Model. 59, 2545–2559 (2019).

    Article  CAS  Google Scholar 

  15. Tkatchenko, A. Machine learning for chemical discovery. Nat. Commun. 11, 4125 (2020).

    Article  CAS  PubMed Central  Google Scholar 

  16. Niemeyer, Z. L., Milo, A., Hickey, D. P. & Sigman, M. S. Parameterization of phosphine ligands reveals mechanistic pathways and predicts reaction outcomes. Nat. Chem. 8, 610–617 (2016).

    Article  CAS  Google Scholar 

  17. Reid, J. P. & Sigman, M. S. Holistic prediction of enantioselectivity in asymmetric catalysis. Nature 571, 343–348 (2019).

    Article  CAS  PubMed Central  Google Scholar 

  18. Zahrt, A. F. et al. Prediction of higher-selectivity catalysts by computer-driven workflow and machine learning. Science 363, eaau5631 (2019).

    Article  CAS  PubMed Central  Google Scholar 

  19. Henle, J. J. et al. Development of a computer-guided workflow for catalyst optimization. Descriptor validation, subset selection, and training set analysis. J. Am. Chem. Soc. 142, 11578–11592 (2020).

    Article  CAS  Google Scholar 

  20. Singh, S. et al. A unified machine-learning protocol for asymmetric catalysis as a proof of concept demonstration using asymmetric hydrogenation. Proc. Natl Acad. Sci. USA 117, 1339–1345 (2020).

    Article  CAS  PubMed Central  Google Scholar 

  21. Gallarati, S. et al. Reaction-based machine learning representations for predicting the enantioselectivity of organocatalysts. Chem. Sci. 12, 6879–6889 (2021).

    Article  CAS  PubMed Central  Google Scholar 

  22. Kutchukian, P. S. et al. Chemistry informer libraries: a chemoinformatics enabled approach to evaluate and advance synthetic methods. Chem. Sci. 7, 2604–2613 (2016).

    Article  CAS  PubMed Central  Google Scholar 

  23. Hase, F., Roch, L. M., Kreisbeck, C. & Aspuru-Guzik, A. Phoenics: a Bayesian optimizer for chemistry. ACS Cent. Sci. 4, 1134–1145 (2018).

    Article  CAS  PubMed Central  Google Scholar 

  24. Coley, C. W. Defining and exploring chemical spaces. Trends Chem. 3, 133–145 (2021).

    Article  CAS  Google Scholar 

  25. Shields, B. J. et al. Bayesian reaction optimization as a tool for chemical synthesis. Nature 590, 89–96 (2021).

    Article  CAS  Google Scholar 

  26. Dhawa, U. et al. Enantioselective pallada-electrocatalyzed C–H activation by transient directing groups: expedient access to helicenes. Angew. Chem. Int. Ed. 59, 13451–13457 (2020).

    Article  CAS  Google Scholar 

  27. Moskal, M., Beker, W., Szymkuc, S. & Grzybowski, B. A. Scaffold-directed face selectivity machine-learned from vectors of non-covalent interactions. Angew. Chem. Int. Ed. 60, 15230–15235 (2021).

    Article  CAS  Google Scholar 

  28. Jorner, K., Brinck, T., Norrby, P.-O. & Buttar, D. Machine learning meets mechanistic modelling for accurate prediction of experimental activation energies. Chem. Sci. 12, 1163–1175 (2021).

    Article  CAS  Google Scholar 

  29. Zhang, S. Q. & Hong, X. Mechanism and selectivity control in Ni- and Pd-catalyzed cross-couplings involving carbon–oxygen bond activation. Acc. Chem. Res. 54, 2158–2171 (2021).

    Article  CAS  Google Scholar 

  30. Tomberg, A., Johansson, M. J. & Norrby, P. O. A predictive tool for electrophilic aromatic substitutions using machine learning. J. Org. Chem. 84, 4695–4703 (2019).

    Article  CAS  Google Scholar 

  31. Guan, Y. et al. Regio-selectivity prediction with a machine-learned reaction representation and on-the-fly quantum mechanical descriptors. Chem. Sci. 12, 2198–2208 (2020).

    Article  PubMed Central  Google Scholar 

  32. Li, X., Zhang, S. Q., Xu, L. C. & Hong, X. Predicting regioselectivity in radical C–H functionalization of heterocycles through machine learning. Angew. Chem. Int. Ed. 59, 13253–13259 (2020).

    Article  CAS  Google Scholar 

  33. Gallegos, L. C., Luchini, G., St John, P. C., Kim, S. & Paton, R. S. Importance of engineered and learned molecular representations in predicting organic reactivity, selectivity, and chemical properties. Acc. Chem. Res. 54, 827–836 (2021).

    Article  CAS  Google Scholar 

  34. Ramakrishnan, R., Dral, P. O., Rupp, M. & von Lilienfeld, O. A. Big data meets quantum chemistry approximations: the delta-machine learning approach. J. Chem. Theory Comput. 11, 2087–2096 (2015).

    Article  CAS  Google Scholar 

  35. Xu, L. C. et al. Towards data-driven design of asymmetric hydrogenation of olefins: database and hierarchical learning. Angew. Chem. Int. Ed. 60, 22804–22811 (2021).

    Article  CAS  Google Scholar 

  36. Martin, T. M. et al. Does rational selection of training and test sets improve the outcome of QSAR modeling? J. Chem. Inf. Model. 52, 2570–2578 (2012).

    Article  CAS  Google Scholar 

  37. Ahneman, D. T., Estrada, J. G., Lin, S., Dreher, S. D. & Doyle, A. G. Predicting reaction performance in C–N cross-coupling using machine learning. Science 360, 186–190 (2018).

    Article  CAS  Google Scholar 

  38. Rinehart, N. I., Zahrt, A. F., Henle, J. J. & Denmark, S. E. Dreams, false starts, dead ends, and redemption: a chronicle of the evolution of a chemoinformatic workflow for the optimization of enantioselective catalysts. Acc. Chem. Res. 54, 2041–2054 (2021).

    Article  CAS  Google Scholar 

  39. Dewyer, A. L., Argüelles, A. J. & Zimmerman, P. M. Methods for exploring reaction space in molecular systems. WIREs Comput. Mol. Sci. 8, e1354 (2018).

    Article  Google Scholar 

Download references


Generous support by the National Natural Science Foundation of China (21873081 and 22122109, X. Hong; 22103070, S.-Q.Z.), the Starry Night Science Fund of Zhejiang University Shanghai Institute for Advanced Study (SN-ZJU-SIAS-006, X. Hong), Beijing National Laboratory for Molecular Sciences (BNLMS202102, X. Hong), CAS Youth Interdisciplinary Team (JCTD-2021-11, X. Hong), Fundamental Research Funds for the Central Universities (226-2022-00140 and 226-2022-00224, X. Hong), the Center of Chemistry for Frontier Technologies and Key Laboratory of Precise Synthesis of Functional Molecules of Zhejiang Province (PSFM 2021-01, X. Hong), the State Key Laboratory of Clean Energy Utilization (ZJUCEU2020007, X. Hong), China Scholarship Council (fellowship to X. Hou), the European Union (ERC advanced grant no. 101021358 conferred to L.A.) and the DFG (Gottfried-Wilhelm-Leibniz-Preis attributed to L.A. and SPP 2363) are gratefully acknowledged. Calculations and ML trainings were performed on the high‐performance computing system at the Department of Chemistry, Zhejiang University.

Author information

Authors and Affiliations



X. Hong and L.A. conceived and supervised the project. X. Hong and S.-Q.Z. designed the workflow of the ML. L.-C.X. and S.-W.L. performed the ML training and analysed the training data. J.F. and X. Hou performed the experiments and analysed the experimental data. Y.-Y.L. and J.C.A.O. performed the DFT calculations for the physical organic descriptors and the mechanistic studies. X. Hong. and L.A. wrote the manuscript with input from all the authors.

Corresponding authors

Correspondence to Lutz Ackermann or Xin Hong.

Ethics declarations

Competing interests

The authors declare no competing interests.

Peer review

Peer review information

Nature Synthesis thanks Tobias Gensch, Bartosz Grzybowski and the other, anonymous, reviewer(s) for their contribution to the peer review of this work. Primary Handling Editor: Peter Seavill, in collaboration with the Nature Synthesis team.

Additional information

Publisher’s note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary information

Supplementary Information

Machine learning and experimental details, Supplementary Figs. 1–37 and Tables 1–17.

Supplementary Data 1

Collected data of asymmetric pallada-electrocatalysed C–H activation

Source data

Source Data Fig. 4

Data for the three regression diagrams of Fig. 4a.

Source Data Fig. 5

Importance scores for top-5 features.

Source Data Fig. 6

Data for the regression diagram of Fig. 6e.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and Permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Xu, LC., Frey, J., Hou, X. et al. Enantioselectivity prediction of pallada-electrocatalysed C–H activation using transition state knowledge in machine learning. Nat. Synth 2, 321–330 (2023).

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing