danДоклады Национальной академии наук БеларусиDoklady of the National Academy of Sciences of Belarus1561-83232524-2431The Republican Unitary Enterprise Publishing House "Belaruskaya Navuka"10.29235/1561-8323-2023-67-5-388-398dan-1152Research ArticleХИМИЯCHEMISTRYПрогностическая модель идентификации новых лигандов CYP19A1 на аналитической платформе KNIMEPredictive model for identifying new CYP19A1 ligands on the KNIME analytical platformШаладоноваМ. И.ShaladonovaM. I.

Марина Игоревна Шаладонова, магистрант

220070

ул. Радиальная, 38Б

Минск

Marina I. Shaladonova, Master’s Student

220070

38B, Radialnaya Str.

Minsk

shalmari@tut.byДиченкоЯ. В.DzichenkaYa. V.

Ярослав Владимирович Диченко, канд. хим. наук, доцент, вед. науч. сотрудник

220084

ул. Купревича, 5/2

Минск

Yaraslau V. Dzichenka, Ph. D. (Chemistry), Associate Professor, Leading Researcher

220084

5/2, Kuprevich Str.

Minsk

dichenko@iboch.byУсановС. А.UsanovS. A.

Сергей Александрович Усанов, член-корреспондент, д-р хим. наук, профессор

220084

ул. Купревича, 5/2

Минск

Sergei A. Usanov, Corresponding Memberr, D. Sc. (Chemistry), Professor

220084

5/2, Kuprevich Str.

Minsk

usanov@iboch.byУниверситет Национальной академии наук БеларусиUniversity of the National Academy of Sciences of BelarusИнститут биоорганической химии Национальной академии наук БеларусиInstitute of Bioorganic Chemistry of the National Academy of Sciences of Belarus202331102023675388398Copyright © Шаладонова М.И., Диченко Я.В., Усанов С.А., 20232023Шаладонова М.И., Диченко Я.В., Усанов С.А.Shaladonova M.I., Dzichenka Y.V., Usanov S.A.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://doklady.belnauka.by/jour/article/view/1152

   Сформирована база данных химических соединений – низкомолекулярных лигандов CYP19A1 (ароматазы) человека на основании проанализированных данных, полученных in vitro. С использованием полученной базы данных при помощи метода машинного обучения «случайный лес деревьев принятия решений» на аналитической платформе KNIME построены две прогностические модели для идентификации активности лигандов стероидной (I типа) и нестероидной (II типа) структуры. В качестве обучающих данных при построении модели применялись топологические дескрипторы химической структуры, учитывающие корреляцию между структурой молекулы и биологическим эффектом. Для каждой модели был осуществлен отбор наиболее значимых признаков (дескрипторов), произведено вычисление оптимальных параметров и найдена область применимости моделей. На основании результатов показателей качества AUC проведена оценка способности моделей предсказывать результаты тестовой выборки. Полученные показатели качества свидетельствуют о достаточно высокой прогностической способности моделей и перспективности их использования для идентификации новых лигандов CYP19A1 человека. Найденные таким способом соединения могут рассматриваться как потенциальные к созданию лекарственные препараты для лечения гормон-зависимых опухолей.

   The purpose of this study was to create a database of the chemical compounds – ligands of human steroid-hydroxylating cytochrome CYP19A1 (aromatase) in order to build a predictive model.

   The idea was to create a model on the basis of the machinery learning method such as random forest for two types of ligands – with steroidal (I type) and non-steroidal structure (II type). Two predictive models were built with the help of the KNIME analytical platform. Topological descriptors of the chemical structure were used as training data when building a model that takes into account their correlation between the structure of the molecule and the biological effect. The selection of the feature importance of the descriptors, optimal parameters of random forest and the definition of applicability domain of the models were carried out. The assessment of the ability to predict the results of a test sample was performed for each model. The quality marks of the obtained models indicated a rather high predictive ability of the models and the prospects of their use for identification of new human CYP19A1 ligands as potential drugs for treatment of hormone-dependent tumors.

CYP19A1 человекаингибиторы ароматазылигандтопологические дескрипторымашинное обучениепрогностическая модельобласть применимостиидентификация препаратовhuman CYP19A1aromatase inhibitorsligandtopological descriptorsmachinery learningpredictive modelapplicability domaindrug identificationReferencesGuha, R. Development of Linear, Ensemble, and Nonlinear Models for the Prediction and Interpretation of the Biological Activity of a Set of PDGFR Inhibitors / R. Guha, P. C. Jurs // J. Chem. Inf. Comput. Sci. – 2004. – Vol. 44, N 6. – P. 2179–2189. doi: 10.1021/ci049849fGuha R., Jurs P. C. Development of Linear, Ensemble, and Nonlinear Models for the Prediction and Interpretation of the Biological Activity of a Set of PDGFR Inhibitors. Journal of Chemical Information and Computer Sciences, 2004, vol. 44, no. 6, pp. 2179–2189. doi: 10.1021/ci049849fNovel triazole-tetrahydroisoquinoline hybrids as human aromatase inhibitors / C. Chamduang [et al.] // Bioorg. Chem. – 2019. – Vol. 93. – Art. 103327. doi: 10.1016/j.bioorg.2019.103327Chamduang C., Pingaew R., Prachayasittikul V., Prachayasittikul S., Ruchirawat S., Prahayasit tikul V. Novel triazole-tetrahydroisoquinoline hybrids as human aromatase inhibitors. Bioorganic Chemistry, 2019, vol. 93, art. 103327. doi: 10.1016/j.bioorg.2019.103327Brueggemeier, R. W. Aromatase Inhibitors in the Treatment of Breast Cancer / R. W. Brueggemeier, J. C. Hackett, E. S. Diaz-Cruz // Endocrine Rev. – 2005. – Vol. 26, N 3. – P. 331–345. doi: 10.1210/er.2004-0015Brueggemeier R. W., Hackett J. C., Diaz-Cruz E. S. Aromatase Inhibitors in the Treatment of Breast Cancer. Endocrine Reviews, 2005, vol. 26, no. 3, pp. 331–345. doi: 10.1210/er.2004-0015Bertelli, G. Sequencing of aromatase inhibitors / G. Bertelli // Br. J. Cancer. – 2005. – Vol. 93, N S1. – P. 6–9. doi: 10.1038/sj.bjc.6602689Bertelli G. Sequencing of aromatase inhibitors. British Journal of Cancer, 2005, vol. 93, no. S1, pp. 6–9. doi: 10.1038/sj.bjc.6602689Studies on non-steroidal inhibitors of aromatase enzyme; 4-(aryl/heteroaryl)-2-(pyrimidin-2-yl) thiazole derivatives / Z. Sahin [et al.] // Bioorg. Med. Chem. – 2018. – Vol. 26, N 8. – P. 1986–1995. doi: 10.1016/j.bmc.2018.02.048Sahin Z., Ertas M., Berk B., Biltekin S. N., Yurttas L., Demirayak S. Studies on non-steroidal inhibitors of aromatase enzyme; 4-(aryl/heteroaryl)-2-(pyrimidin-2-yl)thiazole derivatives. Bioorganic & Medicinal Chemistry, 2018, vol. 26, no. 8, pp. 1986–1995. doi: 10.1016/j.bmc.2018.02.048Aromatase Inhibitors Evolution as Potential Class of Drugs in the Treatment of Postmenopausal Brest Cancer Women / S. Avvaru [et al.] // Mini-Rev. Med. Chem. – 2018. – Vol. 18, N 7. – P. 609–621. doi: 10.2174/1389557517666171101100902Avvaru S. P., Noolvi M. N., Aminbhavi T. M., Chkraborty S., Dash A., Shukla S. S. Aromatase Inhibitors Evolution as Potential Class of Drugs in the Treatment of Postmenopausal Brest Cancer Women. Mini-Reviews in Medicinal Chemistry, 2018, vol. 18, no. 7, pp. 609–621. doi: 10.2174/1389557517666171101100902Determining the IC50 Values for Vorozole and Letrozole, on a Series of Human Liver Cytochrome P450s, to Help Determine the Binding Site of Vorozole in the Liver / L. Raymond [et al.] // Enzyme Research. – 2015. – Vol. 2015. – P. 1–4. doi: 10.1155/2015/321820Raymond L., Rayani N., Polson G., Sikorski K., Lian A., VanAlstine-Parris M. A. Determining the IC50 Values for Vorozole and Letrozole, on a Series of Human Liver Cytochrome P450s, to Help Determine the Binding Site of Vorozole in the Liver. Enzyme Research, 2015, vol. 2015, pp. 1–4. doi: 10.1155/2015/321820Synthesis of Aromatase Inhibitors and Dual Aromatase Steroid Sulfatase Inhibitors by Linking an Arylsulfamate Motif to 4-(4H-1,2,4-triazol-4-ylamino)benzonitrile: SAR, Crystal Structures, in vitro and in vivo Activities / C. Bubert [et al.] // ChemMedChem. – 2008. – Vol. 3, N 11. – P. 1708–1730. doi: 10.1002/cmdc.200800164Bubert C., Woo L. W. L., Sutcliffe O. B., Mahon M. F., Chander S. K., Purohit A., Reed M. J., Potter B. V. L. Synthesis of Aromatase Inhibitors and Dual Aromatase Steroid Sulfatase Inhibitors by Linking an Arylsulfamate Motif to 4-(4H-1,2,4-triazol-4-ylamino)benzonitrile: SAR, Crystal Structures, in vitro and in vivo Activities. ChemMedChem, 2008, vol. 3, no. 11, pp. 1708–1730. doi: 10.1002/cmdc.200800164Баскин, И. И. Введение в хемоинформатику / И. И. Баскин, Т. И. Маджидов, А. А. Варнек. – М., Казань, Страсбург, 2020. – Ч. 4: Методы машинного обучения. – 321 с.Baskin I. I., Madzhilov T. I., Varnek A. A. Introduction to Chemoinformatics. Vol. 4: Machine learning methods. Moscow, Kazan, Strasburg, 2020. 321 р. (in Russian).Application of the Random Forest Method in Studies of Local Lymph Node Assay Based Skin Sensitization Data / S. Li [et al.] // J. Chem. Inf. Model. – 2005. – Vol. 45, N 4. – P. 952–964. doi: 10.1021/ci050049uLi S., Fedorowicz A., Singh H., Soderholm S. C. Application of the Random Forest Method in Studies of Local Lymph Node Assay Based Skin Sensitization Data. Journal of Chemical Information and Modeling, 2005, vol. 45, no. 4, pp. 952–964. doi: 10.1021/ci050049uПрименение метода количественных корреляций структура–свойство (ККСС) с использованием топологического индекса Балабана на примере группы сульфаниламидов / А. В. Сыроешкин [и др.] // Вестн. Рос. ун-та дружбы народов. Сер. Медицина. – 2000. – № 2. – С. 80–83.Syroeshkin A. V., Kovaleva A. N., Kandalaft E., Pleteneva T. V. Application of a method of quantitative correlations frame – property with usage of a topological coefficient on an example of group of sulfanilamidums. Vestnik Rossiiskogo universiteta druzhby narodov. Seriya: Meditsina = RUDN Journal of Medicine, 2000, no. 2, pp. 80–83 (in Russian).Optimisation and evaluation of the random forest model in the efficacy prediction of chemoradiotherapy for advanced cervical cancer based on radiomics signature from high-resolution T2 weighted images / D. Liu [et al.] // Arch. Gynecol. Obstet. – 2021. – Vol. 303, N 3. – Р. 811–820. doi: 10.1007/s00404-020-05908-5Liu D., Zhang X., Zheng T., Shi Q., Cui Y., Wang Y., Liu L. Optimisation and evaluation of the random forest model in the efficacy prediction of chemoradiotherapy for advanced cervical cancer based on radiomics signature from high-resolution T2 weighted images. Archives of Gynecology and Obstetrics, 2021, vol. 303, no. 3, pp. 811–820. doi: 10.1007/s00404-020-05908-5Janitza, S. An AUC-based permutation variable importance measure for random forests / S. Janitza, C. Strobl, A.-L. Boulesteix // BMC Bioinformatics. – 2013. – Vol. 14, N 1. – Р. 1–11. doi: 10.1186/1471-2105-14-119Janitza S., Strobl C., Boulesteix A.-L. An AUC-based permutation variable importance measure for random forests. BMC Bioinformatics, 2013, vol. 14, no. 1, pp. 1–11. doi: 10.1186/1471-2105-14-119

The authors declare that there are no conflicts of interest present.