danДоклады Национальной академии наук БеларусиDoklady of the National Academy of Sciences of Belarus1561-83232524-2431The Republican Unitary Enterprise Publishing House "Belaruskaya Navuka"10.29235/1561-8323-2025-69-6-454-461dan-1280Research ArticleИНФОРМАТИКАINFORMATICSСравнительный анализ точности оценочных функций молекулярного докинга с использованием эталонного набора данных CASF-2016Comparative accuracy analysis of molecular docking scoring functions using the CASF-2016 benchmark datasetФурсК. В.FursK. V.

Фурс Константин Викторович – мл. науч. сотрудник 

ул. Сурганова, 6, 220012, Минск 

Furs Kanstantsin V. – Junior Researcher 

6, Surganov Str., 220012, Minsk 

kvfurs@gmail.comЛайковЯ. В.LaikouY. V.

Лайков Ян Вадимович – мл. науч. сотрудник 

ул. Сурганова, 6, 220012, Минск 

Laikou Yan V. – Junior Researcher

6, Surganov Str., 220012, Minsk 

laykovyan270599@gmail.comГончарА. В.HancharH. V.

Гончар Анна Викторовна – мл. науч. сотрудник 

ул. Сурганова, 6, 220012, Минск 

Hanchar Hanna V. – Junior Researcher 

6, Surganov Str., 220012, Minsk 

hanna.hanchar@gmail.comТузиковА. В.TuzikovA. V.

Тузиков Александр Васильевич – член-корреспондент, д-р физ.-мат. наук, профессор, заведующий лабораторией

ул. Сурганова, 6, 220012, Минск 

Tuzikov Alexander V. – Corresponding Member, D. Sc. (Physics and Mathematics), Professor, Head of the Laboratory

6, Surganov Str., 220012, Minsk 

tuzikov@newman.bas-net.byАндриановА. М.AndrianovA. M.

Андрианов Александр Михайлович – д-р хим. наук, профессор, гл. науч. сотрудник

ул. Купревича, 5/2, 220084, Минск 

Andrianov Alexander M. – D. Sc. (Chemistry), Professor, Chief Researcher

5/2, Kuprevich Str., 220084, Minsk

alexande.andriano@yandex.ruОбъединенный институт проблем информатики Национальной академии наук БеларусиUnited Institute of Informatics Problems of the National Academy of Sciences of BelarusИнститут биоорганической химии Национальной академии наук БеларусиInstitute of Bioorganic Chemistry of the National Academy of Sciences of Belarus202505012026696454461Copyright © Фурс К.В., Лайков Я.В., Гончар А.В., Тузиков А.В., Андрианов А.М., 20262026Фурс К.В., Лайков Я.В., Гончар А.В., Тузиков А.В., Андрианов А.М.Furs K.V., Laikou Y.V., Hanchar H.V., 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://doklady.belnauka.by/jour/article/view/1280

С помощью эталонного набора данных CASF-2016 осуществлен сравнительный анализ эффективности оценочных функций AutoDock Vina, NNScore2, RF-Score-4, CENsible, HGScore, OnionNet-2, PIGNet2 и PLANET, предназначенных для предсказания на основе данных молекулярного докинга аффинности связывания малых молекул с целевым белком. В результате проведенных исследований показано, что новые оценочные функции глубокого обучения PLANET и OnionNet-2 демонстрируют наиболее высокую точность, эффективно прогнозируя сродство лиганда к молекулярной мишени и увеличивая достоверность идентификации молекул-кандидатов с высоким потенциалом ингибиторной активности. Полученные данные показывают, что PLANET и OnionNet-2 могут быть использованы в вычислительных протоколах молекулярного докинга для последующего расчета экспоненциального консенсусного ранга для каждого лиганда и надежного отбора наиболее вероятных ингибиторов заданной терапевтической мишени.

In this paper, a comparative analysis of the performance of AutoDock Vina, NNScore2, RF-Score-4, CENsible, HGScore, OnionNet-2, PIGNet2, and PLANET scoring functions designed to predict the binding affinity of small molecules to a target protein based on molecular docking data was made using the CASF-2016 benchmark dataset. The study has shown that the deep learning scoring functions PLANET and OnionNet-2 demonstrate the highest accuracy, effectively predicting the affinity of the ligand to the molecular target and increasing the reliability of identifying compound candidates with high potential for inhibitory activity. The obtained data indicate that both PLANET and OnionNet-2 can be used in computational protocols of molecular docking for subsequent calculation of the exponential consensus rank for each ligand and reliable selection of the most probable inhibitors of a given therapeutic target.

оценочные функциипрогнозирование аффинности связыванияCASF-2016виртуальный скринингмолекулярный докингвзаимодействия белок–лигандмашинное обучениепоиск новых лекарственных препаратовscoring functionsbinding affinity predictionCASF-2016virtual screeningmolecular dockingproteinligand interactionsmachine learningdrug discoveryРабота выполнена при поддержке грантов Белорусского республиканского фонда фундаментальных исследований (проект Ф24КИ-001), Международного научно-технического центра (МНТЦ, проект PR150) и Консорциума и Портала программы «Лекарственно-устойчивый туберкулез» (https://tbportals.niaid.nih.gov).This work was supported by grants from the Belarusian Republican Foundation for Fundamental Research (project Ф24КИ-001), The International Science and Technology Center (ISTC, project PR150), and the Consortium and the Drug Resistant Tuberculosis Portal Program (https:// tbportals.niaid.nih.gov).ReferencesCurrent perspectives and trend of computer-aided drug design: a review and bibliometric analysis / Z. Wu, S. Chen, Y. Wang [et al.] // International Journal of Surgery. – 2024. – Vol. 110, N 6. – P. 3848–3878. https://doi.org/10.1097/js9.0000000000001289Wu Z., Chen S., Wang Y., Li F., Xu H., Li M., Zeng Y., Wu Z., Gao Y. Current perspectives and trend of computer-aided drug design: a review and bibliometric analysis. International Journal of Surgery, 2024, vol. 110, no. 6, pp. 3848–3878. https://doi.org/10.1097/js9.0000000000001289Paggi, J. M. The art and science of molecular docking / J. M. Paggi, A. Pandit, R. O. Dror // Annual Review of Biochemistry. – 2024. – Vol. 93. – P. 389–410. https://doi.org/10.1146/annurev-biochem-030222-120000Paggi J. M., Pandit A., Dror R. O. The art and science of molecular docking. Annual Review of Biochemistry, 2024, vol. 93, pp. 389–410. https://doi.org/10.1146/annurev-biochem-030222-120000Meli, R. Scoring functions for protein-ligand binding affinity prediction using structure-based deep learning: a review / R. Meli, G. M. Morris, P. C. Biggin // Frontiers in Bioinformatics. – 2022. – Vol. 2. – Art. 885983. https://doi.org/10.3389/fbinf.2022.885983Meli R., Morris G. M., Biggin P. C. Scoring functions for protein-ligand binding affinity prediction using structurebased deep learning: a review. Frontiers in Bioinformatics, 2022, vol. 2, art. 885983. https://doi.org/10.3389/fbinf.2022.885983Kontoyianni, M. Docking and virtual screening in drug discovery / M. Kontoyianni // Proteomics for Drug Discovery: Methods in Molecular Biology / eds I. Lazar, M. Kontoyianni, A. Lazar. – New York, 2017. – Vol. 1647. – P. 255–266. https://doi.org/10.1007/978-1-4939-7201-2_18Kontoyianni M. Docking and virtual screening in drug discovery. Lazar I., Kontoyianni M., Lazar A. (eds). Proteomics for Drug Discovery: Methods in molecular biology. New York, 2017, vol. 1647, pp. 255–266. https://doi.org/10.1007/978-1-4939-7201-2_18Reducing false positive rate of docking-based virtual screening by active learning / L. Wang, S.-H. Shi, H. Li [et al.] // Briefings in Bioinformatics. – 2023. – Vol. 24, N 1. – Art. bbac626. https://doi.org/10.1093/bib/bbac626Wang L., Shi S. H., Li H., Zeng X. X., Liu S. Y., Liu Z. Q., Deng Y.-F., Lu A.-P., Hou T.-J., Cao D. S. Reducing false positive rate of docking-based virtual screening by active learning. Briefings in Bioinformatics, 2023, vol. 24, no. 1, art. bbac626. https://doi.org/10.1093/bib/bbac626Comparative assessment of scoring functions: The CASF-2016 update / M. Su, Q. Yang, Y. Du [et al.] // Journal of Chemical Information and Modeling. – 2019. – Vol. 59, N 2. – P. 895–913. https://doi.org/10.1021/acs.jcim.8b00545Su M., Yang Q., Du Y., Feng G., Liu Z., Li Y., Wang R. Comparative assessment of scoring functions: The CASF-2016 update. Journal of Chemical Information and Modeling, 2019, vol. 59, no. 2, pp. 895–913. https://doi.org/10.1021/acs.jcim.8b00545Vieira, T. Tailoring specialized scoring functions for more efficient virtual screening / T. Vieira, R. Magalhaes, S. Sousa // Frontiers in Drug, Chemistry and Clinical Research. – 2019. – Vol. 2. – 4 p. https://doi.org/10.15761/FDCCR.1000118Vieira T., Magalhaes R., Sousa S. F. Tailoring specialized scoring functions for more efficient virtual screening. Frontiers in Drug, Chemistry and Clinical Research, 2019, vol. 2, 4 p. https://doi.org/10.15761/FDCCR.1000118Pairwise performance comparison of docking scoring functions: Computational approach using InterCriteria analysis / M. Angelova, P. Alov, I. Tsakovska [et al.] // Molecules. – 2025. – Vol. 30, N 13. – Art. 2777. https://doi.org/10.3390/molecules30132777Angelova M., Alov P., Tsakovska I., Jereva D., Lessigiarska I., Atanassov K., Pajeva I., Pencheva T. Pairwise performance comparison of docking scoring functions: Computational approach using InterCriteria analysis. Molecules, 2025, vol. 30, no. 13, art. 2777. https://doi.org/10.3390/molecules30132777Bhatt, R. CENsible: interpretable insights into small-molecule binding with context explanation networks / R. Bhatt, D. R. Koes, J. D. Durrant // Journal of Chemical Information and Modeling. – 2024. – Vol. 64, N 12. – P. 4651–4660. https://doi.org/10.1021/acs.jcim.4c00825Bhatt R., Koes D. R., Durrant J. D. CENsible: interpretable insights into small-molecule binding with context explanation networks. Journal of Chemical Information and Modeling, 2024, vol. 64, no. 12, pp. 4651–4660. https://doi.org/10.1021/acs.jcim.4c00825Heterogeneous graph convolutional neural network for protein-ligand scoring / K. Crampon, A. Giorkallos, X. Vigouroux [et al.] // Exploration of Drug Science. – 2023. – Vol. 1. – P. 126–139. https://doi.org/10.37349/eds.2023.00010Crampon K., Giorkallos A., Vigouroux X., Baud S., Steffenel L. A. Heterogeneous graph convolutional neural network for protein-ligand scoring. Exploration of Drug Science, 2023, vol. 1, pp. 126–139. https://doi.org/10.37349/eds.2023.00010OnionNet-2: a convolutional neural network model for predicting protein-ligand binding affinity based on residueatom contacting shells / Z. Wang, L. Zheng, Y. Liu [et al.] // Frontiers in Chemistry. – 2021. – Vol. 9. – Art. 753002. https://doi.org/10.3389/fchem.2021.753002Wang Z., Zheng L., Liu Y., Qu Y., Li Y.-Q., Zhao M., Mu Y., Li W. OnionNet-2: a convolutional neural network model for predicting protein-ligand binding affinity based on residue-atom contacting shells. Frontiers in Chemistry, 2021, vol. 9, art. 753002. https://doi.org/10.3389/fchem.2021.753002PIGNet2: a versatile deep learning-based protein-ligand interaction prediction model for binding affinity scoring and virtual screening / S. Moon, S.-Y. Hwang, J. Lim, W.-Y. Kim // Digital Discovery. – 2023. – Vol. 3. – P. 287–299. https://doi.org/10.1039/d3dd00149kMoon S., Hwang S. Y., Lim J., Kim W. Y. PIGNet2: a versatile deep learning-based protein-ligand interaction prediction model for binding affinity scoring and virtual screening. Digital Discovery, 2023, vol. 3, pp. 287–299. https://doi.org/10.1039/d3dd00149kPLANET: a multi-objective graph neural network model for protein-ligand binding affinity prediction / X. Zhang, H. Gao, H. Wang [et al.] // Journal of Chemical Information and Modeling. – 2024. – Vol. 64, N 7. – P. 2205–2220. https://doi.org/10.1021/acs.jcim.3c00253Zhang X., Gao H., Wang H., Chen Z., Zhang Z., Chen X., Li Y., Qi Y., Wang R. PLANET: a multi-objective graph neural network model for protein-ligand binding affinity prediction. Journal of Chemical Information and Modeling, 2024, vol. 64, no. 7, pp. 2205–2220. https://doi.org/10.1021/acs.jcim.3c00253Exponential consensus ranking improves the outcome in docking and receptor ensemble docking / K. PalacioRodriguez, I. Lans, C. N. Cavasotto, P. Cossio // Scientific Reports. – 2019. – Vol. 9. – Art. 5142. https://doi.org/10.1038/s41598-019-41594-3Palacio-Rodriguez K., Lans I., Cavasotto C. N., Cossio P. Exponential consensus ranking improves the outcome in docking and receptor ensemble docking. Scientific Reports, 2019, vol. 9, art. 5142. https://doi.org/10.1038/s41598-019-41594-3

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