informИнформатикаInformatics1816-03012617-6963UIIP NASB10.37661/1816-0301-2020-17-1-7-17inform-1045Research ArticleБИОИНФОРМАТИКАBIOINFORMATICSРазработка генеративной состязательной нейронной сети для идентификации потенциальных ингибиторов ВИЧ-1 методами глубокого обученияDevelopment of a generative adversarial neural network for identification of potential HIV-1 inhibitors by deep learning methodsНиколаевГ. И.NikolaevG. I.

Николаев Григорий Игоревич, научный сотрудник

Grigory I. Nikolaev, Researcher

reshaemvsem@gmail.comШульдовН. А.ShuldovN. A.

Шульдов Никита Андреевич, студент, факультет прикладной математики и информатики

Nikita A. Shuldov, Student,  Faculty of Applied Mathematics and Computer Science

nickshuldov29@gmail.comАнищенкоА. И.Anishenko,A. I.

Анищенко Арсений Игоревич, студент, факультет прикладной математики и информатики

Arseny I. Anishenko, Student, Faculty of Applied Mathematics and          Computer Science

BatsilaBox3@gmail.comТузиковА. В.TuzikovA. V.

Тузиков Александр Васильевич, член-корреспондент, доктор физико-математических наук, профессор, директор

Alexander V. Tuzikov, Corresponding Member, Dr. Sci. (Phys.-Math.), Professor, Director

avtuzikov@gmail.comАндриановА. М.AndrianovA. M.

Андрианов Александр Михайлович, доктор химических наук, главный научный сотрудник

Alexander M. Andrianov, Dr. Sci. (Chem.), Chief Researcher

alexande.andriano@yandex.ruОбъединенный институт проблем информатики Национальной академии наук БеларусиThe United Institute of Informatics Problems of the National Academy of Sciences of BelarusБелорусский государственный университетBelorussian State UniversityИнститут биоорганической химии Национальной академии наук БеларусиInstitute of Bioorganic Chemistry of the National Academy of Sciences of Belarus202026022020171717Copyright © Николаев Г.И., Шульдов Н.А., Анищенко А.И., Тузиков А.В., Андрианов А.М., 20202020Николаев Г.И., Шульдов Н.А., Анищенко А.И., Тузиков А.В., Андрианов А.М.Nikolaev G.I., Shuldov N.A., Anishenko, A.I., Tuzikov A.V., Andrianov A.M.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://inf.grid.by/jour/article/view/1045

Методами глубокого обучения разработан генеративный состязательный автоэнкодер для рационального дизайна потенциальных ингибиторов проникновения ВИЧ-1, способных блокировать участок белка gp120 оболочки вируса, критический для его связывания с клеточным рецептором CD4. Были выполнены исследования, включающие создание архитектуры автоэнкодера, формирование молекулярной библиотеки потенциальных лигандов белка gp120 ВИЧ-1 для обучения нейронной сети, молекулярный докинг лигандов с белком gp120 и расчет свободной энергии связывания, генерацию молекулярных дескрипторов химических соединений обучающего набора данных, обучение нейронной сети, оценку результатов обучения и работы автоэнкодера.  Рассмотрены результаты тестирования автоэнкодера на широком наборе соединений из молекулярной библиотеки ZINC. Показано, что совместное использование нейронной сети с виртуальным скринингом баз данных химических соединений формирует продуктивную платформу для идентификации базовых структур, перспективных для создания новых противовирусных препаратов, ингибирующих ранние стадии развития ВИЧ-инфекции.

A generative adversarial autoencoder for the rational design of potential HIV-1 entry inhibitors able to block the region of the viral envelope protein gp120 critical for the virus binding to cellular receptor CD4 was developed using deep learning methods. The research were carried out to create the  architecture of the neural network, to form  virtual compound library of potential anti-HIV-1 agents for training the neural network, to make  molecular docking of all compounds from this library with gp120, to  calculate the values of binding free energy, to generate molecular fingerprints for chemical compounds from the training dataset. The training the neural network was implemented followed by estimation of the learning outcomes and work of the autoencoder.  The validation of the neural network on a wide range of compounds from the ZINC database was carried out. The use of the neural network in combination with virtual screening of chemical databases was shown to form a productive platform for identifying the basic structures promising for the design of novel antiviral drugs that inhibit the early stages of HIV infection.

методы глубокого обучениягенеративно-состязательный автоэнкодербелок gp120ингибиторы проникновения ВИЧ-1методы молекулярного моделированияdeep learning methodsa generative adversarial neural networkgp120 proteinHIV-1 entry inhibitorsmolecular modelingReferencesCherkasov A., Muratov E. N., Fourches D., Varnek A., Baskin I. I., …, Tropsha A. QSAR modeling: where have you been? Where are you going to? Journal of Medicinal Chemistry, 2014, vol. 201457, рр. 4977–5010.Cherkasov A., Muratov E. N., Fourches D., Varnek A., Baskin I. I., …, Tropsha A. QSAR modeling: where have you been? Where are you going to? Journal of Medicinal Chemistry, 2014, vol. 201457, рр. 4977–5010.Ali S. M., Hoemann M. Z., Aubé J., Georg G. I., Mitscher L. A., Jayasinghe L. R. Butitaxel analogues: Synthesis and structure-activity relationships. Journal of Medicinal Chemistry, 1997, vol. 40, рр. 236–241.Ali S. M., Hoemann M. Z., Aubé J., Georg G. I., Mitscher L. A., Jayasinghe L. R. Butitaxel analogues: Synthesis and structure-activity relationships. Journal of Medicinal Chemistry, 1997, vol. 40, рр. 236–241.Vamathevan J., Clark D., Czodrowski P., Dunham I., Ferran E., …, Zhao S. Applications of machine learning in drug discovery and development. Nature Reviews Drug Discovery, 2019, vol. 18(6), рр. 463–477.Vamathevan J., Clark D., Czodrowski P., Dunham I., Ferran E., …, Zhao S. Applications of machine learning in drug discovery and development. Nature Reviews Drug Discovery, 2019, vol. 18(6), рр. 463–477.Dubey A. Machine learning approaches in drug development of HIV/AIDS. International Journal of Molecular Biology: Open Access, 2018, vol. 3(1), рр. 23–25.Dubey A. Machine learning approaches in drug development of HIV/AIDS. International Journal of Molecular Biology: Open Access, 2018, vol. 3(1), рр. 23–25.Li W., Lu L., Li W., Jiang S. Small-molecule HIV-1 entry inhibitors targeting gp120 and gp41: a patent review (2010-2015). Expert Opinion on Therapeutic Patents, 2017, vol. 27, рр. 707–719.Li W., Lu L., Li W., Jiang S. Small-molecule HIV-1 entry inhibitors targeting gp120 and gp41: a patent review (2010-2015). Expert Opinion on Therapeutic Patents, 2017, vol. 27, рр. 707–719.Kadurin A., Aliper A., Kazennov A., Mamoshina P., Vanhaelen Q., Khrabrov K., Zhavoronkov A. The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology. Oncotarget, 2017, vol. 8, рр. 10883–10890.Kadurin A., Aliper A., Kazennov A., Mamoshina P., Vanhaelen Q., Khrabrov K., Zhavoronkov A. The cornucopia of meaningful leads: Applying deep adversarial autoencoders for new molecule development in oncology. Oncotarget, 2017, vol. 8, рр. 10883–10890.Xu B., Wang N., Chen T., Li M. Empirical Evaluation of Rectified Activations in Convolutional Network, 2015. Available at: https://arxiv.org/abs/1505.00853 (accessed 12.11.2019).Xu B., Wang N., Chen T., Li M. Empirical Evaluation of Rectified Activations in Convolutional Network, 2015. Available at: https://arxiv.org/abs/1505.00853 (accessed 12.11.2019).Rudoy G. I. The Choice of the Activation Function in the Prediction of Neural Networks. Machine Learning and Data Analysis, 2011, no. 1, pp. 16–39. Available at: https://arxiv.org/abs/1412.6980 (accessed 12.11.2019).Rudoy G. I. The Choice of the Activation Function in the Prediction of Neural Networks. Machine Learning and Data Analysis, 2011, no. 1, pp. 16–39. Available at: https://arxiv.org/abs/1412.6980 (accessed 12.11.2019).Kingma D., Ba J. Adam: A Method for Stochastic Optimization, 2014.Kingma D., Ba J. Adam: A Method for Stochastic Optimization, 2014.Van der Maaten L. Visualizing data using t-SNE. Journal of Machine Learning Research, 2008, vol. 9, рр. 2579–2605.Van der Maaten L. Visualizing data using t-SNE. Journal of Machine Learning Research, 2008, vol. 9, рр. 2579–2605.Kolb H. C., Finn M. G., Sharpless K. B. Click chemistry: Diverse chemical function from a few good reactions. Angewandte Chemie International Edition, 2001, vol. 40, no. 11, рр. 2004–2021.Kolb H. C., Finn M. G., Sharpless K. B. Click chemistry: Diverse chemical function from a few good reactions. Angewandte Chemie International Edition, 2001, vol. 40, no. 11, рр. 2004–2021.Irwin J. J., Shoichet B. K. ZINC  a free database of commercially available compounds for virtual screening. Journal of Chemical Information and Modeling, 2005, vol. 45, no. 1, рр. 177–182.Irwin J. J., Shoichet B. K. ZINC  a free database of commercially available compounds for virtual screening. Journal of Chemical Information and Modeling, 2005, vol. 45, no. 1, рр. 177–182.Irwin J. J., Sterling T., Mysinger M. M., Bolstad E. S., Coleman R. G. ZINC: a free tool to discover chemistry for biology. Journal of Chemical Information and Modeling, 2012, vol. 52, no. 7, рр. 1757–1768.Irwin J. J., Sterling T., Mysinger M. M., Bolstad E. S., Coleman R. G. ZINC: a free tool to discover chemistry for biology. Journal of Chemical Information and Modeling, 2012, vol. 52, no. 7, рр. 1757–1768.Courter J. R., Madani N., Sodroski J., Schön A., Freire E., …, Smith A. B. 3rd. Structure-based design, synthesis and validation of CD4-mimetic small molecule inhibitors of HIV-1 entry: Conversion of a viral entry agonist to an antagonist. Accounts of Chemical Research, 2014, vol. 47, рр. 1228–1237.Courter J. R., Madani N., Sodroski J., Schön A., Freire E., …, Smith A. B. 3rd. Structure-based design, synthesis and validation of CD4-mimetic small molecule inhibitors of HIV-1 entry: Conversion of a viral entry agonist to an antagonist. Accounts of Chemical Research, 2014, vol. 47, рр. 1228–1237.Curreli F., Kwon Y. D., Zhang H., Scacalossi D., Belov D. S., …, Debnath A. K. Structure-based design of a small molecule CD4-antagonist with broad spectrum anti-HIV-1 activity. Journal of Medicinal Chemistry, 2015, vol. 58, рр. 6909–6927.Curreli F., Kwon Y. D., Zhang H., Scacalossi D., Belov D. S., …, Debnath A. K. Structure-based design of a small molecule CD4-antagonist with broad spectrum anti-HIV-1 activity. Journal of Medicinal Chemistry, 2015, vol. 58, рр. 6909–6927.Durrant J. D., McCammon J. A. AutoClickChem: click chemistry in silico. PLOS Computational Biology, 2012, vol. 8, no. 3, e1002397. https://doi.org/10.1371/journal.pcbi.1002397Durrant J. D., McCammon J. A. AutoClickChem: click chemistry in silico. PLOS Computational Biology, 2012, vol. 8, no. 3, e1002397. https://doi.org/10.1371/journal.pcbi.1002397Lipinski C. A., Lombardo F., Dominy B. W., Feeney P. J. Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Advanced Drug Delivery Reviews, 2001, vol. 46, no. 1–3, рр. 3–26.Lipinski C. A., Lombardo F., Dominy B. W., Feeney P. J. Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settings. Advanced Drug Delivery Reviews, 2001, vol. 46, no. 1–3, рр. 3–26.Alhossary A., Handoko S. D., Mu Y., Kwoh C. K. Fast, accurate, and reliable molecular docking with QuickVina 2. Bioinformatics, 2015, vol. 31, no. 13, рр. 2214–2216.Alhossary A., Handoko S. D., Mu Y., Kwoh C. K. Fast, accurate, and reliable molecular docking with QuickVina 2. Bioinformatics, 2015, vol. 31, no. 13, рр. 2214–2216.Kwong P. D., Wyatt R., Robinson J., Sweet R. W., Sodroski J., Hendrickson W. A. Structure of an HIV gp120 envelope glycoprotein in complex with the CD4 receptor and a neutralizing human antibody. Nature, 1998, vol. 393, рр. 648–659.Kwong P. D., Wyatt R., Robinson J., Sweet R. W., Sodroski J., Hendrickson W. A. Structure of an HIV gp120 envelope glycoprotein in complex with the CD4 receptor and a neutralizing human antibody. Nature, 1998, vol. 393, рр. 648–659.Blahut R. E. Theory and Practice of Error Control Codes. Addison-Wesley, 1983, 500 р.Blahut R. E. Theory and Practice of Error Control Codes. Addison-Wesley, 1983, 500 р.Tanimoto T. T. IBM Internal Report 17th. IBM Corp., Armonk, New York, 1957.Tanimoto T. T. IBM Internal Report 17th. IBM Corp., Armonk, New York, 1957.Myszka D. G., Sweet R. W., Hensley P., Brigham-Burke M., Kwong P. D., …, Doyle M. L. Energetics of the HIV gp120-CD4 binding reaction. Proceedings of the National Academy of Sciences, 2000, vol. 97, рр. 9026–9031.Myszka D. G., Sweet R. W., Hensley P., Brigham-Burke M., Kwong P. D., …, Doyle M. L. Energetics of the HIV gp120-CD4 binding reaction. Proceedings of the National Academy of Sciences, 2000, vol. 97, рр. 9026–9031.Andrianov A. M., Nikolaev G. I., Kornoushenko Y. V., Xu W., Jiang S., Tuzikov A. V. In silico identification of novel aromatic compounds as potential HIV-1 entry inhibitors mimicking cellular receptor CD4. Viruses, 2019, vol. 11, E746. https://doi.org/10.3390/v11080746Andrianov A. M., Nikolaev G. I., Kornoushenko Y. V., Xu W., Jiang S., Tuzikov A. V. In silico identification of novel aromatic compounds as potential HIV-1 entry inhibitors mimicking cellular receptor CD4. Viruses, 2019, vol. 11, E746. https://doi.org/10.3390/v11080746Andrianov A. M., Nikolaev G. I., Kornoushenko Y. V., Huang J., Jiang S., Tuzikov A. V. Virtual screening and identification of potential HIV-1 inhibitors based on cross-reactive neutralizing antibody N6. Doklady of the National Academy of Sciences of Belarus, 2019, vol. 63, no. 4, рр. 445–456.Andrianov A. M., Nikolaev G. I., Kornoushenko Y. V., Huang J., Jiang S., Tuzikov A. V. Virtual screening and identification of potential HIV-1 inhibitors based on cross-reactive neutralizing antibody N6. Doklady of the National Academy of Sciences of Belarus, 2019, vol. 63, no. 4, рр. 445–456.Andrianov A. M., Nikolaev G. I., Kornoushenko Y. V., Karpenko A. D., Huang J., Jiang S., Tuzikov A. V. Identification of functional mimetics of the neutralizing anti-HIV antibody N6 by virtual screening and molecular modeling N6. Doklady of the National Academy of Sciences of Belarus, 2019, vol. 63, no. 5, рр. 561–571.Andrianov A. M., Nikolaev G. I., Kornoushenko Y. V., Karpenko A. D., Huang J., Jiang S., Tuzikov A. V. Identification of functional mimetics of the neutralizing anti-HIV antibody N6 by virtual screening and molecular modeling N6. Doklady of the National Academy of Sciences of Belarus, 2019, vol. 63, no. 5, рр. 561–571.Andrianov A. M., Nikolaev G. I., Kornoushenko Y. V., Huang J., Jiang S., Tuzikov A. V. In silico identification of high-affinity ligands of the HIV-1 gp120 protein, potential peptidomimetics of neutralizing antibody N6. Mathematical Biology and Bioinformatics, 2019, vol. 14, no. 2, рр. 430–449.Andrianov A. M., Nikolaev G. I., Kornoushenko Y. V., Huang J., Jiang S., Tuzikov A. V. In silico identification of high-affinity ligands of the HIV-1 gp120 protein, potential peptidomimetics of neutralizing antibody N6. Mathematical Biology and Bioinformatics, 2019, vol. 14, no. 2, рр. 430–449.Curreli F., Kwon Y. D., Belov D .S., Ramesh R. R., Kurkin A. V., …, Debnath A. K. Synthesis, antiviral potency, in vitro ADMET, and X-ray structure of potent CD4 mimics as entry inhibitors that target the Phe43 cavity of HIV-1 gp120. Journal of Medicinal Chemistry, 2017, vol. 60, рр. 3124–3153.Curreli F., Kwon Y. D., Belov D .S., Ramesh R. R., Kurkin A. V., …, Debnath A. K. Synthesis, antiviral potency, in vitro ADMET, and X-ray structure of potent CD4 mimics as entry inhibitors that target the Phe43 cavity of HIV-1 gp120. Journal of Medicinal Chemistry, 2017, vol. 60, рр. 3124–3153.

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