The integrated method of machine learning used to identify side effects of polypragmasia

S.A. Kotov; O.V. Nepomnyashchy; S.Yu. Pichkovskaya; Yu.V. Krasnobaev

doi:10.18127/j19998465-202602-02

The integrated method of machine learning used to identify side effects of polypragmasia

S.A. Kotov¹, O.V. Nepomnyashchy², S.Yu. Pichkovskaya³, Yu.V. Krasnobaev⁴

research article UDC 004.89 Pages: 22-31 doi.org/10.18127/j19998465-202602-02

^1,2,3,4 Institute of Space and Information Technologies of Siberian Federal University (Krasnoyarsk, Russia)

Keywords: Computational pharmaceuticals polypragmasy drug interaction neural network salp swarm algorithm deep learning

Abstract

The article discusses the problems of complex use of medications (polypragmasia) from the point of view of computational pharmaceutics and ensuring the completeness and accuracy of results caused by the diversity of sets of interactions used in machine learning.

The goal is to test the hypothesis that the use of deep learning technologies can allow the desired function to be extracted from a set of interaction results, which in turn can improve the accuracy of forecasting.

The research results in a solution based on the combined use of a convolutional neural network and an evolutionary algorithm. The architecture of the neural network and its operation are described. A mathematical model is presented, and data sets are formed for training and testing the neural network. Training is performed, and a comparative analysis of known algorithms is carried out in various forecasting modes.

The practical significance of the study is that the combined use of a convolutional neural network and a particle swarm algorithm will improve accuracy, sensitivity, selectivity, and reliability compared to known methods on similar datasets.

Received: 02.10.2025
Approved after review: 25.11.2025
Accepted: 26.02.2026

How to cite

Котов С.А., Непомнящий О.В., Пичковская С.Ю., Краснобаев Ю.В. Интегрированный метод машинного обучения для анализа побочных эффектов полипрагмазии // Наукоемкие технологии. 2026. Т. 27. № 2. С. 22−31. DOI: https://doi.org/ 10.18127/ j19998465-202602-02

References

Baza lekarstvennyh sredstv, iz"yatyh iz obrashcheniya. URL: http://www.omdrug.ru/pro-info/drug_base/ (data obrashcheniya 14.04.2025) (in Russian).
Sbornik tezisov konferencii «Vychislitel'naya biologiya i iskusstvennyj intellekt dlya personalizirovannoj mediciny – 2024» (7–9 avgusta 2024 g., onlajn-format). GNC RF FGBU «NMIC endokrinologii» Minzdrava Rossii. 2024 (in Russian).
Marcath L.A., Coe T.D., Hoylman E.K., Redman B.G., Hertz D.L. Prevalence of drug-drug interactions in oncology patients enrolled on National Clinical Trials Network oncology clinical trials. BMC Cancer. 2018. V. 18. № 1. P. 1–8.
Zhang C., Zang T. CNN-DDI: A novel deep learning method for predicting drug-drug interactions. IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2020. P. 1708–1713.
Zhang W., Chen Y., Liu F., Luo F., Tian G., Li X. Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data. BMC Bioinformatics. 2017. V. 18. № 1. P. 18. doi: 10.1186/s12859-016-1415-9.
Sun X., Ma L., Du X., Feng J., Dong K. Deep convolution neural networks for drug-drug interaction extraction. IEEE international conference on bioinformatics and biomedicinee (bibm). 2018. P. 1662–1668.
Weng Y.-A., Deng C.-Y., Pu C. Targeting continuity of care and polypharmacy to reduce drug-drug interaction. Sci. Rep. 2020. V. 10. № 1. P. 1–9.
Alhaj F., Qutishat D., Al Harahsheh H., Obeid N., Hammo B. Detecting DDI Using Ontology: Drug Mechanism of Action. IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT). 2019. P. 179–185.
Vilar S., Harpaz R., Uriarte E., Santana L., Rabadan R., Friedman C. Drug-drug interaction through molecular structure similarity analysis. Am J. Med. Informatics Assoc. 2012. V. 19. № 6. P. 1066–1074. doi: 10.1136/amiajnl-2012-000935.
Gottlieb A., Stein G.Y., Oron Y., Ruppin E., Sharan R. INDI: a computational framework for inferring drug interactions and their associated recommendations. Mol. Syst. Biol. V. 8. № 1. P. 592. doi: 10.1038/msb.2012.26.
Salp Swarm Algorithm. URL: https://www.baeldung.com/cs/salp-swarm-algorithm (data obrashchenija 10.05.2025).
Yaqing Wang, Zaifei Yang, Quanming Yao. Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning. Communications Medicine logo. Commun Med (Lond). 2024 Mar 28;4:59. doi: 10.1038/s43856-024-00486-y.
Xie J., Zhao C., Ouyang J., He H., Huang D., Liu M., Wang J., Zhang W. TP-DDI: A Two-Pathway Deep Neural Network for Drug-Drug Interaction Prediction. Interdiscip Sci. 2022 Dec. V. 14(4). P. 895–905. doi: 10.1007/s12539-022-00524-0. Epub 2022 May 27. PMID: 35622314

[1] Baza lekarstvennyh sredstv, iz"yatyh iz obrashcheniya. URL: http://www.omdrug.ru/pro-info/drug_base/ (data obrashcheniya 14.04.2025) (in Russian).

[2] Sbornik tezisov konferencii «Vychislitel'naya biologiya i iskusstvennyj intellekt dlya personalizirovannoj mediciny – 2024» (7–9 avgusta 2024 g., onlajn-format). GNC RF FGBU «NMIC endokrinologii» Minzdrava Rossii. 2024 (in Russian).

[3] Marcath L.A., Coe T.D., Hoylman E.K., Redman B.G., Hertz D.L. Prevalence of drug-drug interactions in oncology patients enrolled on National Clinical Trials Network oncology clinical trials. BMC Cancer. 2018. V. 18. № 1. P. 1–8.

[4] Zhang C., Zang T. CNN-DDI: A novel deep learning method for predicting drug-drug interactions. IEEE International Conference on Bioinformatics and Biomedicine (BIBM). 2020. P. 1708–1713.

[5] Zhang W., Chen Y., Liu F., Luo F., Tian G., Li X. Predicting potential drug-drug interactions by integrating chemical, biological, phenotypic and network data. BMC Bioinformatics. 2017. V. 18. № 1. P. 18. doi: 10.1186/s12859-016-1415-9.

[6] Sun X., Ma L., Du X., Feng J., Dong K. Deep convolution neural networks for drug-drug interaction extraction. IEEE international conference on bioinformatics and biomedicinee (bibm). 2018. P. 1662–1668.

[7] Weng Y.-A., Deng C.-Y., Pu C. Targeting continuity of care and polypharmacy to reduce drug-drug interaction. Sci. Rep. 2020. V. 10. № 1. P. 1–9.

[8] Alhaj F., Qutishat D., Al Harahsheh H., Obeid N., Hammo B. Detecting DDI Using Ontology: Drug Mechanism of Action. IEEE Jordan International Joint Conference on Electrical Engineering and Information Technology (JEEIT). 2019. P. 179–185.

[9] Vilar S., Harpaz R., Uriarte E., Santana L., Rabadan R., Friedman C. Drug-drug interaction through molecular structure similarity analysis. Am J. Med. Informatics Assoc. 2012. V. 19. № 6. P. 1066–1074. doi: 10.1136/amiajnl-2012-000935.

[10] Gottlieb A., Stein G.Y., Oron Y., Ruppin E., Sharan R. INDI: a computational framework for inferring drug interactions and their associated recommendations. Mol. Syst. Biol. V. 8. № 1. P. 592. doi: 10.1038/msb.2012.26.

[11] Salp Swarm Algorithm. URL: https://www.baeldung.com/cs/salp-swarm-algorithm (data obrashchenija 10.05.2025).

[12] Yaqing Wang, Zaifei Yang, Quanming Yao. Accurate and interpretable drug-drug interaction prediction enabled by knowledge subgraph learning. Communications Medicine logo. Commun Med (Lond). 2024 Mar 28;4:59. doi: 10.1038/s43856-024-00486-y.

[13] Xie J., Zhao C., Ouyang J., He H., Huang D., Liu M., Wang J., Zhang W. TP-DDI: A Two-Pathway Deep Neural Network for Drug-Drug Interaction Prediction. Interdiscip Sci. 2022 Dec. V. 14(4). P. 895–905. doi: 10.1007/s12539-022-00524-0. Epub 2022 May 27. PMID: 35622314

Abstract

How to cite

Related articles