The determination of descriptors for catalytic systems in machine learning models using kinetic experimental data

Capa

Citar

Texto integral

Acesso aberto Acesso aberto
Acesso é fechado Acesso está concedido
Acesso é fechado Acesso é pago ou somente para assinantes

Resumo

The problem of selection and determining the values of descriptors for the properties of chemical reactions components in mathematical models for chemical processes is one of the essential ones when creating machine learning (ML) models used to describe and predict the functioning patterns of chemical systems. Current practice in the field mainly involves the use as the descriptors physical and chemical characteristics of the components of reaction systems (ionic radii, bond lengths, energies, and other parameters related to the structure and properties of specific molecules or particles) determined experimentally or by calculation. This work presents the results of the predicting of the integral kinetic dependences, as well as approaches to determine the values of descriptors for characterizing the properties of a set of simple palladium catalyst precursors when used in the Suzuki–Miyaura reaction. The problem stated has been solved by creating the ML models that take into account experimental kinetic data. The descriptors obtained as a result of training the models make it possible to satisfactorily describe the kinetic patterns of the Suzuki–Miyaura reaction with aryl chlorides under the so-called “ligand-free” catalytic conditions possessing higher sensitivity of the reaction to small changes in the conditions.

Texto integral

Acesso é fechado

Sobre autores

A. Schmidt

Irkutsk State University

Autor responsável pela correspondência
Email: aschmidt@chem.isu.ru

Chemical Department

Rússia, K. Marx str., 1, Irkutsk, 664003

N. Sidorov

Irkutsk State University

Email: aschmidt@chem.isu.ru

Chemical Department

Rússia, K. Marx str., 1, Irkutsk, 664003

A. Kurokhtina

Irkutsk State University

Email: aschmidt@chem.isu.ru

Chemical Department

Rússia, K. Marx str., 1, Irkutsk, 664003

E. Larina

Irkutsk State University

Email: aschmidt@chem.isu.ru

Chemical Department

Rússia, K. Marx str., 1, Irkutsk, 664003

N. Lagoda

Irkutsk State University

Email: aschmidt@chem.isu.ru

Chemical Department

Rússia, K. Marx str., 1, Irkutsk, 664003

Bibliografia

  1. Fitzner M., Wuitschik G., Koller R., Adam J.-M., Schindler T. // ACS Omega. 2023. V. 8 № 3. P. 3017.
  2. Davies J.C., Pattison D., Hirst J.D. // J. Mol. Graph. Model. 2023. V. 118. P. 108356.
  3. Zahrt A.F., Henle J.J., Denmark S.E. // ACS Comb. Sci. 2020. V. 22. № 11. P. 586.
  4. Burés J., Larrosa I. // Nature. 2023. V. 613. № 7945. P. 689.
  5. Freeze J.G., Kelly H.R., Batista V.S. // Chem. Rev. 2019. V. 119. № 11. P. 6595.
  6. Orlandi M., Escudero-Casao M., Licini G. // J. Org. Chem. 2021. V. 86. № 4. P. 3555.
  7. Adebar N., Keupp J., Emenike V. N., Kühlborn J., Vom Dahl L., Möckel R., Smiatek J. // J. Phys. Chem. A. 2024. V. 128. № 5. P. 929.
  8. Clarke G.E., Firth J.D., Ledingham L.A., Horbaczewskyj C.S., Bourne R.A., Bray J.T.W., Martin P.L., Eastwood J.B., Campbell R., Pagett A., MacQuarrie D.J., Slattery J.M., Lynam J.M., Whitwood A.C., Milani J., Hart S., Wilson J., Fairlamb I.J.S. // Nat. Commun. 2024. V. 15. № 1. Art. 3968.
  9. Yada A., Matsumura T., Ando Y., Nagata K., Ichinoseki S., Sato K. // Synlett. 2021. V. 32. № 18. P. 1843.
  10. Gensch T., Dos Passos Gomes G., Friederich P., Peters E., Gaudin T., Pollice R., Jorner K., Nigam A., Lindner-D’Addario M., Sigman M. S., Aspuru-Guzik A. // J. Am. Chem. Soc. 2022. V. 144. № 3. P. 1205
  11. Mou L.-H., Han T., Smith P.E.S., Sharman E., Jiang J. // Adv. Sci. 2023. V. 10. № 22. Art. 2301020.
  12. Skoraczyński G., Dittwald P., Miasojedow B., Szymkuć S., Gajewska E.P., Grzybowski, B.A., Gambin A. // Sci. Rep. 2017. V. 7. № 1. P. 3582.
  13. Raghavan P., Haas B.C., Ruos M.E., Schleinitz J., Doyle A.G., Reisman S.E., Sigman M.S., Coley C.W. // ACS Cent. Sci. 2023. V. 9. № 12. P. 2196.
  14. Kalikadien A.V., Mirza A., Hossaini A.N., Sreenithya A., Pidko E.A. // ChemPlusChem. 2024. V. 89. № 7. Art. e202300702.
  15. Chan K., Ta L.T., Huang Y., Su H., Lin Z. // Molecules. 2023. V. 28. № 12. Art. 4730.
  16. Jorner K., Brinck T., Norrby P.-O., Buttar D. // Chem. Sci. 2021. V. 12. № 3. P. 1163.
  17. Gladstone J.H. // Sci. Am. 2023. V. 16. № 408 supp. P. 6511.
  18. Cammarota R.C., Liu W., Bacsa J., Davies H.M.L., Sigman M.S. // J. Am. Chem. Soc. 2022. V. 144. № 4. P. 1881.
  19. Lustosa D.M., Milo A. // ACS Catal. 2022. V. 12. № 13. P. 7886.
  20. Durand D.J., Fe N. // Chem. Rev. 2019. V. 119. № 11. P. 6561.
  21. Caldeweyher E., Elkin M., Gheibi G., Johansson M., Sköld C., Norrby P.-O., Hartwig J.F. // J. Am. Chem. Soc. 2023. V. 145. № 31. P. 17367.
  22. Taniike T., Fujiwara A., Nakanowatari S., García-Escobar F., Takahashi K. // Commun. Chem. 2024. V. 7. № 1. P. 11.
  23. Ebi T., Sen A., Dhital R.N., Yamada Y.M.A., Kaneko H. // ACS Omega. 2021. V. 6. № 41. P. 27578.
  24. Suzuki A. // Angew. Chem. Int. Ed. 2011. V. 50. P. 6722.
  25. Новаковский А.Б. // Вестник ИБ Коми НЦ УрО РАН. 2018. С. 26. (Novakovskiy A.B. // Vestnik of Institute of Biology Komi Scientific Centre of the Ural Branch of RAS. 2018. P. 26.)
  26. Pedregosa F., Varoquaux G., Gramfort A., Michel V., Thirion B., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., Vanderplas J., Passos A., Cournapeau D., Brucher M., Perrot M., Duchesnay É. // J. Mach. Learn. Res. 2011. V. 12. № 85. P. 2825.
  27. Grebennikov N.O., Boiko D.A., Prima D.O., Madiyeva M., Minyaev M.E., Ananikov V.P. // J. Catal. 2024. V. 429. Art. 115240.
  28. Biffis A., Centomo P., Del Zotto A., Zecca M. // Chem. Rev. 2018. V. 118. № 4. P. 2249.
  29. Widegren J.A., Finke R.G. // J. Mol. Catal. A: Chem. 2003. V. 198. № 1–2. P. 317.
  30. Schmidt A.F., Al Halaiqa A., Smirnov V.V. // Synlett. 2006. № 18. P. 2861.
  31. Shim E., Tewari A., Cernak T., Zimmerman P.M. // J. Chem. Inf. Model. 2023. V. 63. № 12. P. 3659.
  32. Schmidt A.F., Al-Halaiqa A., Smirnov V.V. // J. Mol. Catal. A: Chem. 2006. V. 250. № 1–2. P. 131.
  33. Schmidt A.F., Kurokhtina A.A., Larina E.V., Vidyaeva E.V., Lagoda N.A. // Mol. Catal. 2021. V. 499. Art. 111321.
  34. Курохтина А.А., Ларина Е.В., Лагода Н.А., Шмидт А.Ф. // Кинетика и катализ. 2022. Т. 63. № 5. С. 614. (Kurokhtina A.A., Larina E.V., Lagoda N.A., Schmidt A.F. // Kinet. Catal. 2022. V. 63. № 5. P. 543.)
  35. Galushko A.S., Prima D.O., Burykina J.V., Ananikov V.P. // Inorg. Chem. Front. 2021. V. 8. № 3. P. 620.
  36. Schmidt A.F., Kurokhtina A.A., Larina E.V., Lagoda N.A. // Organometallics. 2023. V. 42. № 24. P. 3442.
  37. Sheldon R.A. // ACS Sustain. Chem. Eng. 2018. V. 6. № 1. P. 32.
  38. Mercer S.M., Andraos J., Jessop P.G. // J. Chem. Educ. 2012. V. 89. № 2. P. 215.

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML
Baixar
2. Scheme 1. Suzuki–Miyaura reaction

Baixar (1MB)
Metadados
3. Fig. 1. Results of the experimental dataset analysis (60 experiments, 15 reaction parameters) using the principal component method. Gray areas correspond to experiments at different temperatures, red areas to experiments with different types of solvents. Red dots correspond to experiments with product yields from 0 to 10%, turquoise ones – from 10 to 20%, green ones – from 20 to 40%, blue ones – from 40% and higher.

Baixar (3MB)
Metadados
4. Fig. 2. Dependences of the experimentally determined values ​​of the Suzuki–Miyaura reaction product concentration included in the dataset (Scheme 1) on those predicted using the MP model (a) and calculated according to equation (1) using the parameters predicted by MS (b).

Baixar (1MB)
Metadados
5. Fig. 3. Preparation of data for NN training using the MS model (left) and the architecture of a fully connected NN determined based on the results of hyperparameter selection.

Baixar (1MB)
Metadados
6. Fig. 4. Dependence of experimentally determined values ​​of the concentration of the Suzuki–Miyaura reaction product (Scheme 1) on those calculated according to equation (1) using the parameters of the equation predicted by NS.

Baixar (1023KB)
Metadados
7. Fig. 5. Examples of experimental and predicted integral kinetic data (a–c) on the accumulation of the Suzuki–Miyaura reaction product (Scheme 1) under different initial conditions (nature and concentration of the base, substrate, catalyst). The calculated values ​​were obtained using the MP model, as well as the MS and NS models using catalyst descriptors.

Baixar (1MB)
Metadados

Declaração de direitos autorais © Russian Academy of Sciences, 2024