Опубликовать статью

Информационное партнерство

Инфоресурсы

Контакты

«

Vol. 23, Art. 33 (pp. 596-607)    |    2022       

»

The artificial neural networks for prediction solution effect on chemicals transdermal permiation

D.G. Ivanov, U.N.Lysenko, A.A. Kruglova, E.A. Afonkina, M. A. Yudin S. N. Subbotina

Federal State Budgetary Institution ?State Research Testing Institute of Military Medicine? of the Ministry of Defense of the Russian Federation
Federal State-Funded Education Institution of Higer Professional Education North-Western State Medical University named after I.I. Mechnikov (NWSMU), Ministry of Health of the Russian Federation

Brief summary

The artificial neural networks of permeability coefficient regression on molecular weight, number of H-bound acceptors of chemicals and solutions as well as some indicator predictors having information about animal species, diffusion cells type, form of chemicals and number solution component were analyzed. The best neural networks was multilayer perceptron with 19 neurons input in layer, 5 neurons in hidden layer and 1 in neuron output layer. The activation function of hidden layer was hyperbolic tangent and activation function of output layer was logistic function. The multilayer perceptron has root of square mean error 1.22 times less then multiple linear regression model.


Key words

multilayer perceptron, chemicals transdermal permeability, solution effect

Reference list

1. Selzer D., Schaefer U.F., Lehr C.M., Hansen S. Basic mathematics in skin absorption. Percutaneous penetration enhancers drug penetration into/through the skin. 2017. P. 9-10.


2. Gaddam P., Muthuprasanna P., Suriyaprabha K., Manojkumar J., Rao B.B., Jukanti R. Diffusion cells for measuring skin permeation in vitro. 2008. Vol. 5. P. 277-287.


3. Tsakovska I., Pajeva I., Al Sharifa M., Alova P., Fioravanzo E., Kovarich S., Worth A. P., Richarz A. N., Yang Ch., Mostrag-Szlichtyng A., Cronin M. T. Quantitative structure-skin permeability relationships. Toxicology. 2017. Vol. 387. P. 27-42.


4. Potts R.O., Richard H.G. Predicting skin permeability. Pharmaceutical research. 1992. Vol. 9. P. 663-669.


5. Abraham M. H., Martins F., Human skin permeation and partition: General linear free-energy relationship analyses. Journal of pharmaceutical sciences. 2004. Vol. 93. P. 1508-1523.


6. Kondrashov V.A. Znachenie kojnogo pyti postypleniya himicheskih veshestv v organizm i profilaktika perkytannih otravlenii. 2014. 287 s.


7. Kyndiev U.I. Vsasivanie pesticidov cherez kojy i profilaktika otravlenii. 1975. 199 s.


8. Najib O.N., Kirton S.B., Martin G.P., Botha M.J., Sallam A.S., Murnane D. Multivariate analytical approaches to identify key molecular properties of vehicles, permeants and membranes that affect permeation through membranes. Pharmaceutics. 2020. Vol. 12. P. 958. doi:10.3390/pharmaceutics12100958.


9. Riviere J. E., Brooks J. D. Predicting Skin Permeability from Complex Chemical Mixtures: Dependency of Quantitative Structure Permeation Relationships on Biology of Skin Model Used. Toxicological sciences. 2011. Vol. 119. P. 224-232.


10. Samaras E. G., Riviere J. E., Ghafourian T. The effect of formulations and experimental conditions on in vitro human skin permeation. International Journal of Pharmaceutics. 2012. Vol. 434. P. 280- 291.


11. Atobe T., Mori M., Yamashita F., Hashida M., Kouzuki H. Artificial neural network analysis for predicting human percutaneous absorption taking account of vehicle properties. Toxicology. 2015. Vol. 40. P. 277-294.


12. Baba H., Takahara J. Yamashita F. Hashida M. Modeling and prediction of solvent effect on human skin permeability using support vector regression and random forest. Pharmaceutical Research. 2015. P. 3-4. DOI 10.1007/s11095-015-1720-4.


13. Sinco J.P. Martin´s physical pharmacy and pharmaceutical sciences. Physical chemical and biopharmaceutical sciences. 2011. P. 182-196


14. Regressionnii analiz v SPSS: ychebnoe posobie / Yakovlev V. B., Yakovlev I.V. // Moskva: Editys. 2016. 69 s.


15. Vvedenie v statisticheskoe obychenie s primerami na yazike. Djeims G., Yitton D., Hasti T., Tibshirani R. DMK-Press. 2017. 254 s.


16. Neironnie seti. STATISTICA Neural Networks: Metodologiya i tehnologiya sovremennogo analiza dannih / Pod. red. V.P. Borovikova. Moskva: Telekom. 2008. 394 s


17. Klassifikaciya, regressiya i drygie algoritmi Data Mining s ispolzovaniem R. Shitikov V.K., Mastickii C.E. Tolyatti, London. 2017. 351 s.


18. Monteiro-Riviere N.A. Anatomical Factors Affecting Barrier Function. Marzulli and Maibachs Dermatotoxicology, 7th Edition. Boca Raton London New York: CRC PressTaylor & Francis Group. 2008. P. 43-52.