Effect of Different Factors on Predicting Constants of Acidity of Low-Molecular Organic Compounds by Means of Machine Learning

D. D. Matyushin; Матюшин Д. Д.; A. Yu. Sholokhova; Шолохова А. Ю.; A. K. Buryak; Буряк А. К.

doi:10.31857/S0044453723020152

Effect of Different Factors on Predicting Constants of Acidity of Low-Molecular Organic Compounds by Means of Machine Learning

Authors: Matyushin D.D.¹, Sholokhova A.Y.¹, Buryak A.K.¹
Affiliations:
1. Frumkin Institute of Physical Chemistry and Electrochemistry, Russian Academy of Sciences
Issue: Vol 97, No 2 (2023)
Pages: 262-269
Section: ХЕМОИНФОРМАТИКА И КОМПЬЮТЕРНОЕ МОДЕЛИРОВАНИЕ
Submitted: 15.10.2023
Published: 01.02.2023
URL: https://ogarev-online.ru/0044-4537/article/view/136524
DOI: https://doi.org/10.31857/S0044453723020152
EDN: https://elibrary.ru/ECXZUI
ID: 136524

Cite item

Full Text

Open Access
Restricted Access

Access granted
Restricted Access

Subscription Access

Abstract
About the authors
References
Supplementary files
Statistics

Abstract

A study is performed of the effect the way of standardizing the molecular structure and parameters of calculating molecular fingerprints has on the accuracy of predicting constants of acidity. It is shown that standardization (i.e., the choice of the tautomeric form and the way of writing the structure of the molecule) using OpenEye QuacPac gives the best results, but the RDKit library allows comparable accuracy to be achieved. It is established that how the charge state is chosen has a great effect on the accuracy of predictions. The accuracy of predictions depending on the radius (size of substructures) of circular molecular fingerprints is studied, and the best results are achieved using radius r = 2. A random forest, a machine learning algorithm, is used. It is also shown that the use of support vectors ensures fairly high accuracy when optimizing hyperparameters.

Keywords

constant of acidity, machine learning, tautomers

References

Baltruschat M., Czodrowski P. // F1000Res. 2020. V. 9. P. 113. https://doi.org/10.12688/f1000research.22090.2
Mansouri K., Cariello N.F., Korotcov A. et al. // J. Cheminform. 2019. V. 11. № 1. P. 60. https://doi.org/10.1186/s13321-019-0384-1
Mayr F., Wieder M., Wieder O. et al. // Front. Chem. 2022. V. 10. P. 866585. https://doi.org/10.3389/fchem.2022.866585
Lu Y., Anand S., Shirley W. et al. // J. Chem. Inf. Model. 2019. V. 59. № 11. P. 4706. https://doi.org/10.1021/acs.jcim.9b00498
Rupp M., Korner R., Tetko I. // CCHTS. 2011. V. 14. № 5. P. 307. https://doi.org/10.2174/138620711795508403
Lionta E., Spyrou G., Vassilatis D. et al. // CTMC. 2014. V. 14. № 16. P. 1923. https://doi.org/10.2174/1568026614666140929124445
Bahi M., Batouche M. // 2018 3rd International Conference on Pattern Analysis and Intelligent Systems (PAIS). Tebessa: IEEE, 2018. P. 1–5. https://doi.org/10.1109/PAIS.2018.8598488
Yang Q., Ji H., Fan X. et al. // J. Chromatogr. A. 2021. V. 1656. P. 462536. https://doi.org/10.1016/j.chroma.2021.462536
Fedorova E.S., Matyushin D.D., Plyushchenko I.V. et al. // J. Chromatogr. A. 2022. V. 1664. P. 462792. https://doi.org/10.1016/j.chroma.2021.462792
Milyushkin A.L., Matyushin D.D., Buryak A.K. // J. Chromatogr. A. 2020. V. 1613. P. 460724. https://doi.org/10.1016/j.chroma.2019.460724
Zenkevich I.G., Nikitina D.A. // Russ. J. Phys. Chem. A. 2021. V. 95. № 2. P. 395. https://doi.org/ Зенкевич И.Г., Никитина Д.А. // Журн. физ. химии. 2021. Т. 95. № 2. С. 285.https://doi.org/10.1134/S003602442102028X
Angra S., Ahuja S. // 2017 International Conference on Big Data Analytics and Computational Intelligence (ICBDAC). Chirala, Andhra Pradesh, India: IEEE, 2017. P. 57. https://doi.org/10.1109/ICBDACI.2017.8070809
Mansouri K., Grulke C.M., Judson R.S. et al. // J. Cheminform. 2018. V. 10. № 1. P. 10. https://doi.org/10.1186/s13321-018-0263-1
Parmar A., Katariya R., Patel V. // International Conference on Intelligent Data Communication Technologies and Internet of Things (ICICI) 2018 / Ed. Hemanth J., Fernando X., Lafata P. et al. Cham: Springer International Publishing, 2019. V. 26. P. 758. https://doi.org/10.1007/978-3-030-03146-6_86
Cereto-Massagué A., Ojeda M.J., Valls C. et al. // Methods. 2015. V. 71. P. 58. https://doi.org/10.1016/j.ymeth.2014.08.005
Rogers D., Hahn M. // J. Chem. Inf. Model. 2010. V. 50. № 5. P. 742. https://doi.org/10.1021/ci100050t
Xiong J., Li Z., Wang G. et al. // Bioinformatics / Ed. by Z. Lu. 2022. V. 38. № 3. P. 792. https://doi.org/10.1093/bioinformatics/btab714
Pan X., Wang H., Li C. et al. // J. Chem. Inf. Model. 2021. V. 61. № 7. P. 3159. https://doi.org/10.1021/acs.jcim.1c00075
Reza Ghiasi, Zamani A., Shamami M.K. // Russ. J. Phys. Chem. A. 2019. V. 93. № 8. P. 1537. https://doi.org/10.1134/S0036024419080247
Prasad S., Huang J., Zeng Q. et al. // J. Comput. Aided Mol. Des. 2018. V. 32. № 10. P. 1191. https://doi.org/10.1007/s10822-018-0167-1
Pracht P., Wilcken R., Udvarhelyi A. et al. // J. Comput. Aided Mol. Des. 2018. V. 32. № 10. P. 1139. https://doi.org/10.1007/s10822-018-0145-7
Pedregosa F., Varoquaux G., Gramfort A. et al. Scikit-learn: Machine Learning in Python: arXiv:1201.0490. arXiv, 2018. https://arxiv.org/abs/1201.0490
Bento A.P., Hersey A., Félix E. et al. // J. Cheminform. 2020. V. 12. № 1. P. 51. https://doi.org/10.1186/s13321-020-00456-1
Chang C.-C., Lin C.-J. // ACM Trans. Intell. Syst. Technol. 2011. V. 2. № 3. P. 1. https://doi.org/10.1145/1961189.1961199
Willighagen E.L., Mayfield J.W., Alvarsson J. et al. // J. Cheminform. 2017. V. 9. № 1. P. 33. https://doi.org/10.1186/s13321-017-0220-4
https://github.com/czodrowskilab/Machine-learning-meets-pKa
Heller S., McNaught A., Stein S. et al. // J. Cheminform. 2013. V. 5. № 1. P. 7. https://doi.org/10.1186/1758-2946-5-7
Matyushin D.D., Buryak A.K. // IEEE Access. 2020. V. 8. P. 223140. https://doi.org/10.1109/ACCESS.2020.3045047