Разработка методов глубокого обучения для обнаружения сайтов связывания в макромолекулах (Deep learning for binding site identification in macromolecules) тема диссертации и автореферата по ВАК РФ 00.00.00, кандидат наук Козловский Игорь Андреевич

• Козловский Игорь Андреевич
• кандидат наук
• 2025

Оглавление диссертации кандидат наук Козловский Игорь Андреевич

Table of contents

Page

Introduction

Chapter 1. Literature overview

1.1 Protein-small molecule binding sites

1.1.1 Sequence-based

1.1.2 Template-based

1.1.3 Geometric

1.1.4 Energetic

1.1.5 Machine learning-based

1.1.6 Deep learning-based

1.2 Protein-peptide binding sites

1.2.1 Sequence-based

1.2.2 Template-based

1.2.3 Energetic

1.2.4 Machine learning-based

1.2.5 Deep learning-based

1.2.6 Other

1.3 Nucleic acid-small molecule binding sites

1.3.1 Knowledge-based

1.3.2 Energetic

1.3.3 Machine learning-based

1.3.4 Deep learning-based

1.3.5 Other

1.4 Other applications

1.5 Metrics

Chapter 2. Protein-small molecule binding site identification

2.1 Datasets

2.2 Model

2.2.1 Model architecture

2.2.2 Model training

2.2.3 Clusterization

2.3 Results

2.3.1 Comparison with other methods

2.3.2 Case studies

2.4 Discussion

2.4.1 Binding site definition

2.4.2 Dataset preparation

2.4.3 Data augmentation

2.4.4 Model hyperparameters

2.4.5 Rotational variance

2.4.6 Metrics

Chapter 3. Protein-peptide binding site identification

3.1 Datasets

3.2 Model

3.2.1 Model architecture

3.2.2 Model training

3.2.3 Metrics

3.3 Results

3.3.1 Comparison with other methods

3.3.2 Case studies

3.4 Discussion

3.4.1 Rotational variance

3.4.2 Metrics

Chapter 4. Nucleic acid-small molecule binding site identification

4.1 Datasets

4.2 Model

4.2.1 Model architecture

4.2.2 Metrics

4.3 Results

4.3.1 Comparison with other methods

4.3.2 Case studies

Conclusion

Acknowledgments

List of abbreviations

Bibliography

Publications of the Author on the Subject of the Dissertation

List of Figures

List of Tables

Appendix A. Supplementary Material for BiteNet

A.1 Binding site definition

A.2 Statistical tests

Appendix B. Supplementery Material for BiteNetpp

Appendix C. Supplementary Material for BiteNet^

Введение диссертации (часть автореферата) на тему «Разработка методов глубокого обучения для обнаружения сайтов связывания в макромолекулах (Deep learning for binding site identification in macromolecules)»

Introduction

The relevance of the research area. The degree of its development. Proteins perform most of the functions in cells, such as enzymatic, structural, transporting or cell signaling [1]. Structurally, proteins are macromolecules consisting of long amino acid chains assembled into three-dimensional structure specific for each protein [2]. Protein functionalities are served via local intermolecular interactions that take place in spatial regions, called binding sites. Binding sites are one of the key elements in drug discovery, being «hot spots» in the pharmacological targets, where the designed drug-like molecule should bind. Identification of novel binding sites expands the «druggable genome» and opens new strategies for therapy and drug discovery [3]. Typically drug-like molecules target either orthosteric binding site, where protein interacts with endogenous molecules, or topologically distinct allosteric binding sites [4]. The latter is of special interest, because allosteric binding sites exhibit a higher degree of sequence diversity between protein subtypes, thus, allowing to design more selective ligands, in contrast to the orthosteric ligands [5-7].

However, there are obstacles to targeting the whole human genome with small molecule drugs. At first, only 1.5% of the human genome encodes proteins [8], and only 10-15% of them are thought to be disease-related [9]. Moreover, many of them are considered undruggable, meaning that they lack deep cleft-like pockets for small molecules to bind [10]. All of these are emphasized with the fact that fewer than 700 proteins have been drugged [11]. These issues bring more attention to other therapeutic modalities.

Protein-protein interactions (PPIs) control many essential biological pathways, thus representing an important class of pharmacological targets [12]. There is a growing need to design intracellular PPI inhibitors that can modulate key biological pathways. For a long time, PPIs were considered as intractable targets [13]. On the one hand, while used for targeting extracellular PPIs, large biologics cannot reach intracellular PPIs due to the limitations in crossing the cellular membrane. On the other hand, traditional small molecule scaffolds may diffuse through the membrane but are not always suitable for diverse and shallow PPI interfaces [13]. PPI interfaces possess distinctive features, including large contact area (^1500—3000Á for PPI vs. ^300—1000Á for protein-small molecule interaction [14]) and lack of pronounced

deep binding sites, typically observed for small molecules (^270A in volume [15]). Notably, PPI interfaces often contain a few small binding pockets (^100A3 in volume [16]) that are essential for the binding affinity [17].

Peptides and peptide-based molecules occupy a unique niche of chemical space with respect to small molecules (molecular weight < 0.5kDa) and biologics (molecular weight > 150kDa). They represent a promising therapeutic modality targeting intracellular PPIs, potentially combining beneficial properties of biologics (e.g., low toxicity, high specificity, and affinity) and small molecules (e.g., permeability) [13]. Structure-based design of therapeutic peptide modalities requires knowledge of the target-peptide binding site. Discovery of novel protein-peptide binding sites potentially expands 'druggable' genome, which, in turn, opens new opportunities for pharmacology.

Furthermore, nucleic acid molecules can be used as targets for drug development as well. RNA molecules are vital in many cellular processes, such as gene regulation and cell information transfer, thus, representing a promising class of pharmacological targets [18]. RNA-targeting drug discovery campaigns explore various perspectives, including the design of stabilizers of DNA G-quadruplex [19], riboswitch-targeting antibiotics [20], antisense RNA [21], and RNA-targeting antivirals, to name a few. RNA targets that expand druggable genome, including those linked to 'undruggable' protein targets or non-coding microRNAs, are of particular interest [22]. However, RNA drug development is dotted with numerous obstacles [23], among others, related to the low chemical diversity and the dynamic nature of RNA structures. Similar to proteins, RNA molecules are highly structured to form binding sites, through which small molecules can modulate them [24]. Therefore, there is a need for efficient, structure-specific RNA-small molecule ligand binding site detectors to advance RNA-targeting drug discovery.

Proteins and nucleic acids are flexible molecules, that adopt various conformations during their life cycle; and a binding site is a dynamic property of a protein mediated by its conformational changes [25; 26]. Single macromolecule structure represents only a minor part of the entire conformational space, hence, binding sites might be easy to overlook from the experimentally determined three-dimensional protein structures [27; 28]. Moreover, many proteins perform their function assembling to oligomeric structure and can form binding sites by means of oligomer's subunits [29; 30].

Experimental identification of binding sites, such as fragment screening and site-directed tethering [31; 32], using antibodies [33], small molecule microarrays [34], hydrogen-deuterium exchange [35] or site-directed mutagenesis [36] are resource-consuming and may result in negative outcome. On the other hand, computational methods allow to perform large-scale binding site identification, investigate macromolecule flexibility via molecular dynamics simulation, and probe to fit chemical compounds using virtual ligand or fragment-based screening. However, the majority of existing computational methods are computationally expensive or have low accuracy, and cannot be applied to the analysis of a large number of macromolecule conformations. Moreover, there is no reliable structure-based method for the detection of small molecule binding sites on nucleic acids at all.

Goals and problems addressed. The aim of this study is to develop a novel binding site detection method that lacks flaws of other methods described above and can be applicable for the large-scale analysis of conformational space of macromolecules.

To achieve the goal of the dissertation, the following problems are addressed:

1. Development of structure-based methods for the prediction of small molecule and peptide binding sites on proteins and small molecule binding sites on nucleic acid macromolecules.

2. Comparison of the developed method with the state-of-the-art methods on widely used benchmarks.

3. Performing case studies to verify applicability of the developed method.

Scientific novelty.

1. At the time of publication, BiteNet, a method for prediction of protein-small molecule binding sites, outperformed other methods in terms of accuracy and speed, making it suitable for application to large-scale protein analysis.

2. To the best of available knowledge, BiteNetp^ is the first structure-based deep learning method for prediction of protein-peptide binding sites, and it is the first to use domain adaptation technique for model training.

3. To available knowledge, the BiteNet^ model was the first structure-based deep learning model for nucleic acid binding site prediction that could work with both RNA and DNA structures. The largest dataset of nucleic acid-small molecule complexes suitable for training deep learning models was constructed to train the BiteNet^ model.

Theoretical and practical significance. The models developed have high accuracy and speed efficiency, making them suitable for large-scale analysis of binding sites in different conformations of macromolecular structures. This was demonstrated by several case studies involving the analysis of molecular dynamics trajectories.

Methodology and research methods. The research uses methods from machine learning, deep learning, structural bioinformatics and molecular modelling tools. All code is written in the Python and C++ programming languages.

Propositions submitted for defense.

1. A structure-based deep learning method was developed for the identification of small molecule binding sites on proteins. It was shown that this model outperforms other methods in terms of accuracy and speed, and the applicability of this model to the detection of allosteric binding sites for both soluble and transmembrane protein domains was demonstrated.

2. A structure-based deep learning method was developed for the identification of peptide binding sites on proteins. This method outperforms the state-of-the-art approaches on the widely used benchmark.

3. A structure-based deep learning method was developed for the identification of small molecule binding sites on nucleic acid macromolecules. The approach consistently outperformed other methods on the constructed test sets. The applicability of the model was demonstrated in two case studies.

Personal contribution of the author. All the results of the dissertation were obtained by the applicant personally. The applicant developed a deep learning structure-based method for identification of binding sites on macromolecules. The applicant is first on the author lists of all three major publications on the topic of the thesis.

Validity of the obtained results. All developed in this study approaches are compared with other state-of-the-art methods on the respective benchmarks. The applicability of the methods were demonstrated by applying them to several case studies. Publications in Q1 peer-reviewed journals also confirm the validity of the results.

Approbation. The results of the disseration are presented in 4 publications, all of which are indexed in Scopus and Web of Science and published in Q1 and Q2 journals, and in 1 patent and 2 certificates of state registration of computer programs.

The results obtained in this study were presented at the following conferences:

1. At the 31st Annual Intelligent Systems For Molecular Biology and the 22nd Annual European Conference on Computational Biology, 2023, Lyon, France

2. At the 11th Moscow Conference on Computational Molecular Biology, 2023, Moscow, Russia

Dissertation structure. The dissertation consists of an introduction, 4 chapters, a conclusion, a discussion and 3 appendices. The full volume of the dissertation is 202 pages with 44 figures and 29 tables. The list of references contains 390 numbers.

Organization of the Dissertation. In Chapter 1, an overview of the existing methods for prediction of protein-small molecule, protein-peptide, and nucleic acid-small molecule binding sites is provided. Then, Chapter 2 describes the development of BiteNet, a deep learning-based method for prediction of small molecule binding sites on protein structures. BiteNet demonstrated high performance compared with other methods, and its applicability was shown through case studies. In Chapter 3, BiteNetpp, a method for prediction of protein-peptide binding sites, is developed. In Chapter 4, BiteNet^, a method for prediction of nucleic acid-small molecule binding sites, is presented, compared with other methods, and its feasibility is shown by applying it to two case studies.

Заключение диссертации по теме «Другие cпециальности», Козловский Игорь Андреевич

Conclusion

In this work, BiteNet, a deep learning-based approach for spatiotemporal identification of binding sites, was introduced. BiteNet takes advantage of the computer vision methods for object detection, by representing the three-dimensional structure of a macromolecule as a 3D image with channels corresponding to the atomic densities. BiteNet goes beyond the classical problem of binding site prediction in holo protein structures, exploring macromolecule dynamics and flexibility by means of large-scale analysis of conformational ensembles. The detected conformations with the observed binding site of interest can then be used for structure-based drug design approaches, such as molecular docking and virtual ligand screening, as well as structure-based de novo drug design.

To be more specific, three versions of the BiteNet method were designed.

A model for prediction of small molecule binding sites on protein structures was demonstrated. It was shown that this model outperforms other methods in terms of accuracy and speed, and the applicability of this model for the detection of allosteric binding sites for both soluble and transmembrane protein domains was demonstrated. BiteNet takes approximately 0.1 seconds to analyze a single conformation and 1.5 minutes to analyze a molecular dynamics trajectory with 1000 frames for a protein with -2000 atoms.

BiteNetpp, a new protein-peptide binding site detection method that utilizes a 3D convolutional neural network applied to the voxelized representation of protein structures, was presented. BiteNetPp outputs coordinates of'hot spots' constituting the protein-peptide binding site along with its probability scores. The domain adaptation technique was used to improve the BiteNetp/s performance; namely, the BiteNet model trained on protein-small molecule complexes was fine-tuned on the curated protein-peptide dataset. The proposed method is fast enough for large-scale binding site detection campaigns, taking less than a second to analyze a single protein structure. The method outperforms the state-of-the-art approaches on the widely used TS125 benchmark, and for the first time, 0.49 and 0.91 milestones in terms of MCC and ROC AUC, respectively, were achieved.

A 3D convolutional neural network, BiteNet^, was developed for identifying small molecule binding sites in nucleic acid structures. A specific typization for

nucleic-acid structures that covers various nucleotides and is suitable for both DNA and RNA, as well as their multiple chain complexes, was designed. To train BiteNet^, a large dataset of —2000 nucleic acid-small molecule complexes was constructed and rigorous cross-validation using sequence- and structure-based splits to circumvent over-fitting was performed. BiteNet^ consistently outperformed the other methods on the constructed test sets. BiteNet^ is conformation-specific, as demonstrated by analyzing seven different HIV-1 TAR RNA structures bound to small molecules. It is helpful for large-scale analysis, such as conformational ensemble or mutant variant analysis, as demonstrated in the ATP-aptamer case study. Finally, BiteNet^ can operate with both RNA and DNA complexes, including multiple chains.

Список литературы диссертационного исследования кандидат наук Козловский Игорь Андреевич, 2025 год

Bibliography

1. Alberts, B. Molecular biology of the cell / B. Alberts. — Sixth. — Garland science, 2017. — P. 109-174.

2. Rodwell, V. W. Harper's illustrated biochemistry / V. W. Rodwell, D. Bender, K. M. Botham. — Thirty-first. — McGraw-Hill, 2018. — P. 36-51.

3. Hopkins, A. L. The druggable genome / A. L. Hopkins, C. R. Groom // Nature reviews Drug discovery. — 2002. — Vol. 1, no. 9. — P. 727.

4. Christopoulos, A. International Union of Basic and Clinical Pharmacology. XC. Multisite Pharmacology: Recommendations for the Nomenclature of Receptor Allosterism and Allosteric Ligands / A. Christopoulos, J.-P. Changeux, W. A. Catterall, [et al.] // Pharmacological Reviews. — 2014. — Vol. 66, no. 4. — P. 918-947.

5. Changeux, J.-P. The concept of allosteric modulation: an overview / J.-P. Changeux//Drug Discovery Today: Technologies. —2013. —Vol. 10, no. 2. — e223-e228.

6. Wagner, J. R. Emerging computational methods for the rational discovery of allosteric drugs / J. R. Wagner, C. T. Lee, J. D. Durrant, [et al.] // Chemical reviews. — 2016. — Vol. 116, no. 11. — P. 6370-6390.

7. Lu, S. Discovery of hidden allosteric sites as novel targets for allosteric drug design / S. Lu, M. Ji, D. Ni, J. Zhang // Drug Discovery Today. — 2018. — Vol. 23, no. 2.—P. 359-365.

8. Clamp, M. Distinguishing protein-coding and noncoding genes in the human genome / M. Clamp, B. Fry, M. Kamal, [et al.] // Proceedings of the National Academy of Sciences. — 2007. — Vol. 104, no. 49. — P. 19428-19433.

9. Overington, J. P. How many drug targets are there? / J. P. Overington, B. Al-Lazikani, A. L. Hopkins // Nature reviews Drug discovery. — 2006. — Vol. 5, no. 12.—P. 993-996.

10. Dixon, S. J. Identifying druggable disease-modifying gene products / S. J. Dixon, B. R. Stockwell // Current opinion in chemical biology. — 2009. — Vol. 13, no. 5/6.—P. 549-555.

11. Santos, R. A comprehensive map of molecular drug targets / R. Santos, O. Ursu, A. Gaulton, [et al.] // Nature reviews Drug discovery. — 2017. — Vol. 16, no. 1.—P. 19-34.

12. Ruffner, H. Human Protein-protein Interaction Networks and the Value for Drug Discovery / H. Ruffner, A. Bauer, T. Bouwmeester // Drug discovery today. — 2007. — Vol. 12, no. 17/18. — P. 709-716.

13. Tsomaia, N. Peptide Therapeutics: Targeting the Undruggable Space / N. Tsomaia // Eur. J. Med. Chem. — 2015. — Vol. 94. — P. 459-470.

14. Smith, M. C. Features of Protein-protein Interactions That Translate into Potent Inhibitors: Topology, Surface Area and Affinity / M. C. Smith, J. E. Gestwicki // Expert Rev. Mol. Med. — 2012. — Vol. 14. — e16.

15. Buchwald, P. Small-molecule Protein-protein Interaction Inhibitors: Therapeutic Potential in Light of Molecular Size, Chemical Space, and Ligand Binding Efficiency Considerations / P. Buchwald // IUBMB life. — 2010. — Vol. 62, no. 10. —P. 724-731.

16. Fuller, J. C. Predicting Druggable Binding Sites at the Protein-protein Interface / J. C. Fuller, N. J. Burgoyne, R. M. Jackson // Drug discovery today. — 2009. — Vol. 14, no. 3/4.—P. 155-161.

17. Clackson, T. A Hot Spot of Binding Energy in a Hormone-receptor Interface / T. Clackson, J. A. Wells//Science. —1995. — Vol. 267,no. 5196. — P. 383-386.

18. Warner, K. D. Principles for targeting RNA with drug-like small molecules / K. D. Warner, C. E. Hajdin, K. M. Weeks // Nature Reviews Drug Discovery. — 2018. — Vol. 17, no. 8. — P. 547-558.

19. Ortiz de Luzuriaga, I. Learning to Model G-Quadruplexes: Current Methods and Perspectives / I. Ortiz de Luzuriaga, X. Lopez, A. Gil // Annual Review of Biophysics. — 2021. — Vol. 50. — P. 209-243.

20. Panchal, V. Riboswitches as drug targets for antibiotics / V. Panchal, R. Brenk // Antibiotics. — 2021. — Vol. 10, no. 1. — P. 45.

21. McClorey, G. An overview of the clinical application of antisense oligonucleotides for RNA-targeting therapies / G. McClorey, M. J. Wood // Current opinion in pharmacology. — 2015. — Vol. 24. — P. 52-58.

22. Matsui, M. Non-coding RNAs as drug targets / M. Matsui, D. R. Corey // Nature reviews Drug discovery. — 2017. — Vol. 16, no. 3. — P. 167-179.

23. Falese, J. P. Targeting RNA with small molecules: from fundamental principles towards the clinic / J. P. Falese, A. Donlic, A. E. Hargrove // Chemical Society Reviews. — 2021. — Vol. 50, no. 4. — P. 2224-2243.

24. Yu, A.-M. RNA drugs and RNA targets for small molecules: Principles, progress, and challenges / A.-M. Yu, Y. H. Choi, M.-J. Tu // Pharmacological Reviews. — 2020. — Vol. 72, no. 4. — P. 862-898.

25. Laskowski, R. A. The structural basis of allosteric regulation in proteins / R. A. Laskowski, F. Gerick, J. M. Thornton // FEBS letters. — 2009. — Vol. 583, no. 11.—P. 1692-1698.

26. Changeux, J.-P. Allosteric modulation as a unifying mechanism for receptor function and regulation / J.-P. Changeux, A. Christopoulos // Cell. — 2016. — Vol. 166, no. 5. — P. 1084-1102.

27. Di Pietro, O. Unveiling a novel transient druggable pocket in BACE-1 through molecular simulations: Conformational analysis and binding mode of multisite inhibitors / O. Di Pietro, J. Juarez-Jimenez, D. Munoz-Torrero, [et al.] // PloS one. — 2017. — Vol. 12, no. 5. — e0177683.

28. Sun, Z. Structure-Based Analysis of Cryptic-Site Opening / Z. Sun, A. E. Wakefield, I. Kolossvary, [et al.] // Structure. — 2020. — Vol. 28, no. 2. — P. 223-235.

29. Ferré, S. G protein-coupled receptor oligomerization revisited: functional and pharmacological perspectives / S. Ferré, V. Casadó, L. A. Devi, [et al.] // Pharmacological reviews. — 2014. — Vol. 66, no. 2. — P. 413-434.

30. Wang, J. Druggable negative allosteric site of P2X3 receptors / J. Wang, Y. Wang, W.-W. Cui, [et al.] // Proceedings of the National Academy of Sciences. — 2018.— Vol. 115, no. 19.—P. 4939-4944.

31. Hardy, J. A. Searching for new allosteric sites in enzymes / J. A. Hardy, J. A. Wells // Current opinion in structural biology. — 2004. — Vol. 14, no. 6. — P. 706-715.

32. Ludlow, R. F. Detection of secondary binding sites in proteins using fragment screening / R. F. Ludlow, M. L. Verdonk, H. K. Saini, [et al.] // Proceedings of the National Academy of Sciences. — 2015. — Vol. 112, no. 52.—P. 15910-15915.

33. Lawson, A. D. Antibody-enabled small-molecule drug discovery / A. D. Lawson // Nature Reviews Drug Discovery. — 2012. — Vol. 11, no. 7. — P. 519.

34. Doyle, S. K. Advances in discovering small molecules to probe protein function in a systems context / S. K. Doyle, M. S. Pop, H. L. Evans, A. N. Koehler // Current opinion in chemical biology. — 2016. — Vol. 30. — P. 28-36.

35. Chalmers, M. J. Probing protein ligand interactions by automated hydrogen/deuterium exchange mass spectrometry / M. J. Chalmers, S. A. Busby, B. D. Pascal, [et al.] // Analytical chemistry. — 2006. — Vol. 78, no. 4. — P. 1005-1014.

36. Gelis, L. Prediction of a ligand-binding niche within a human olfactory receptor by combining site-directed mutagenesis with dynamic homology modeling / L. Gelis, S. Wolf, H. Hatt, [et al.] // Angewandte Chemie International Edition. — 2012.— Vol. 51, no. 5.—P. 1274-1278.

37. Kauffman, C. LIBRUS: combined machine learning and homology information for sequence-based ligand-binding residue prediction / C. Kauffman, G. Karypis // Bioinformatics. — 2009. — Vol. 25, no. 23. — P. 3099-3107.

38. López, G. firestar—prediction of functionally important residues using structural templates and alignment reliability / G. López, A. Valencia, M. L. Tress // Nucleic acids research. — 2007. — Vol. 35, suppl_2. — W573-W577.

39. Yang, J. Protein-ligand binding site recognition using complementary binding-specific substructure comparison and sequence profile alignment / J. Yang, A. Roy, Y. Zhang // Bioinformatics. — 2013. — Vol. 29, no. 20. — P. 2588-2595.

40. Yao, H. An accurate, sensitive, and scalable method to identify functional sites in protein structures / H. Yao, D. M. Kristensen, I. Mihalek, [et al.] // Journal of molecular biology. — 2003. — Vol. 326, no. 1. — P. 255-261.

41. Devos, D. Practical limits of function prediction / D. Devos, A. Valencia // Proteins: Structure, Function, and Bioinformatics. — 2000. — Vol. 41, no. 1. — P. 98-107.

42. Wilson, C. A. Assessing annotation transfer for genomics: quantifying the relations between protein sequence, structure and function through traditional and probabilistic scores / C. A. Wilson, J. Kreychman, M. Gerstein // Journal of molecular biology. — 2000. — Vol. 297, no. 1. — P. 233-249.

43. Todd, A. E. Evolution of function in protein superfamilies, from a structural perspective / A. E. Todd, C. A. Orengo, J. M. Thornton // Journal of molecular biology. — 2001. — Vol. 307, no. 4. — P. 1113-1143.

44. Kawashima, S. AAindex: amino acid index database, progress report 2008 / S. Kawashima, P. Pokarowski, M. Pokarowska, [et al.] //Nucleic acids research. — 2007. — Vol. 36, suppl_1. —P. D202-D205.

45. Chen, P. LigandRFs: random forest ensemble to identify ligand-binding residues from sequence information alone / P. Chen, J. Z. Huang, X. Gao // BMC bioinformatics. Vol. 15. — BioMed Central. 2014. — P. 1-12.

46. Chauhan, J. S. Identification of ATP binding residues of a protein from its primary sequence / J. S. Chauhan, N. K. Mishra, G. P. Raghava // BMC bioinformatics. — 2009. — Vol. 10. — P. 1-9.

47. Chen, K. Prediction and analysis of nucleotide-binding residues using sequence and sequence-derived structural descriptors / K. Chen, M. J. Mizianty, L. Kurgan // Bioinformatics. — 2012. — Vol. 28, no. 3. — P. 331-341.

48. Chen, P. A sequence-based dynamic ensemble learning system for protein ligand-binding site prediction / P. Chen, S. Hu, J. Zhang, [et al.] // IEEE/ACM transactions on computational biology and bioinformatics. — 2015. — Vol. 13, no. 5.—P. 901-912.

49. Dou, Y. L1pred: a sequence-based prediction tool for catalytic residues in enzymes with the L1-logreg classifier / Y. Dou, J. Wang, J. Yang, C. Zhang // PloS one. — 2012. — Vol. 7, no. 4. — e35666.

50. Panwar, B. Prediction of vitamin interacting residues in a vitamin binding protein using evolutionary information / B. Panwar, S. Gupta, G. P. Raghava // BMC bioinformatics. — 2013. — Vol. 14, no. 1. — P. 1-14.

51. Yu, D.-J. Constructing query-driven dynamic machine learning model with application to protein-ligand binding sites prediction / D.-J. Yu, J. Hu, Q.-M. Li, [et al.] // IEEE Transactions on Nanobioscience. — 2015. — Vol. 14, no. 1. — P. 45-58.

52. Lu, C. MPLs-Pred: predicting membrane protein-ligand binding sites using hybrid sequence-based features and ligand-specific models / C. Lu, Z. Liu, E. Zhang, [et al.] // International journal of molecular sciences. — 2019. — Vol. 20, no. 13. —P. 3120.

53. Cui, Y. Predicting protein-ligand binding residues with deep convolutional neural networks / Y. Cui, Q. Dong, D. Hong, X. Wang // BMC bioinformatics. — 2019.— Vol. 20, no. 1.—P. 1-12.

54. Lee, I. Sequence-based prediction of protein binding regions and drug-target interactions /1. Lee, H. Nam // Journal of cheminformatics. — 2022. — Vol. 14, no. 1.—P. 1-15.

55. Nguyen, T.-T.-D. Prediction of ATP-binding sites in membrane proteins using a two-dimensional convolutional neural network / T.-T.-D. Nguyen, N.-Q.-K. Le, R. M. I. Kusuma, Y.-Y. Ou // Journal of Molecular Graphics and Modelling. — 2019.— Vol. 92.—P. 86-93.

56. Vaswani, A. Attention is all you need / A. Vaswani, N. Shazeer, N. Parmar, [et al.] // Advances in neural information processing systems. — 2017. — Vol. 30.

57. Lin, Z. Evolutionary-scale prediction of atomic-level protein structure with a language model / Z. Lin, H. Akin, R. Rao, [et al.] // Science. — 2023. — Vol. 379, no. 6637.—P. 1123-1130.

58. Elnaggar, A. Prottrans: Toward understanding the language of life through self-supervised learning / A. Elnaggar, M. Heinzinger, C. Dallago, [et al.] // IEEE transactions on pattern analysis and machine intelligence. — 2021. — Vol. 44, no. 10.—P. 7112-7127.

59. Brandes, N. ProteinBERT: a universal deep-learning model of protein sequence and function / N. Brandes, D. Ofer, Y. Peleg, [et al.] // Bioinformatics. — 2022. — Vol.38, no. 8.—P. 2102-2110.

60. Devlin, J. Bert: Pre-training of deep bidirectional transformers for language understanding / J. Devlin, M.-W. Chang, K. Lee, K. Toutanova // arXiv preprint arXiv:1810.04805. — 2018.

61. Rives, A. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences / A. Rives, J. Meier, T. Sercu, [et al.] // Proceedings of the National Academy of Sciences. — 2021. — Vol. 118, no. 15. — e2016239118.

62. Zhu, Y. ULDNA: Integrating Unsupervised Multi-Source Language Models with LSTM-Attention Network for Protein-DNA Binding Site Prediction / Y. Zhu, D.-J. Yu // bioRxiv. — 2023. — P. 2023-05.

63. Liu, Y. Protein-DNA binding sites prediction based on pre-trained protein language model and contrastive learning / Y. Liu, B. Tian // arXiv preprint arXiv:2306.15912. — 2023.

64. Li, Y. MsPBRsP: Multi-scale Protein Binding Residues Prediction Using Language Model / Y. Li, S. Lu, X. Nan, [et al.] // bioRxiv. — 2023. — P. 2023-02.

65. Brylinski, M. FINDSITE-metal: Integrating evolutionary information and machine learning for structure-based metal-binding site prediction at the proteome level / M. Brylinski, J. Skolnick // Proteins: Structure, Function, and Bioinformatics. — 2011. — Vol. 79, no. 3. — P. 735-751.

66. Wass, M. N. 3DLigandSite: predicting ligand-binding sites using similar structures / M. N. Wass, L. A. Kelley, M. J. Sternberg // Nucleic acids research. — 2010. — Vol. 38, suppl_2. — W469-W473.

67. Gao, J. bSiteFinder, an improved protein-binding sites prediction server based on structural alignment: more accurate and less time-consuming / J. Gao, Q. Zhang, M. Liu, [et al.] // Journal of Cheminformatics. — 2016. — Vol. 8, no. 1. — P. 1-10.

68. Moodie, S. L. Protein recognition of adenylate: an example of a fuzzy recognition template / S. L. Moodie, J. B. Mitchell, J. M. Thornton // Journal of molecular biology. — 1996. — Vol. 263, no. 3. — P. 486-500.

69. Denessiouk, K. A. Adenine recognition: a motif present in ATP-, CoA-, NAD-, NADP-, and FAD-dependent proteins / K. A. Denessiouk, V.-V. Rantanen, M. S. Johnson// Proteins: Structure, Function, andBioinformatics. — 2001. — Vol. 44, no. 3.—P. 282-291.

70. Rinaldis, M. de. Three-dimensional profiles: a new tool to identify protein surface similarities / M. de Rinaldis, G. Ausiello, G. Cesareni, M. Helmer-Citterich // Journal of molecular biology. — 1998. — Vol. 284, no. 4.—P. 1211-1221.

71. Schmitt, S. A new method to detect related function among proteins independent of sequence and fold homology / S. Schmitt, D. Kuhn, G. Klebe // Journal of molecular biology. — 2002. — Vol. 323, no. 2. — P. 387-406.

72. Roy, A. COFACTOR: an accurate comparative algorithm for structure-based protein function annotation / A. Roy, J. Yang, Y. Zhang // Nucleic acids research. — 2012. — Vol. 40, W1. — W471-W477.

73. Barker, J. A. An algorithm for constraint-based structural template matching: application to 3D templates with statistical analysis / J. A. Barker, J. M. Thornton // Bioinformatics. — 2003. — Vol. 19, no. 13. — P. 1644-1649.

74. Gold, N. D. SitesBase: a database for structure-based protein-ligand binding site comparisons / N. D. Gold, R. M. Jackson // Nucleic acids research. — 2006. — Vol. 34, suppl_1. —P. D231-D234.

75. Rosen, M. Molecular shape comparisons in searches for active sites and functional similarity. / M. Rosen, S. L. Lin, H. Wolfson, R. Nussinov // Protein Engineering. — 1998. — Vol. 11, no. 4. — P. 263-277.

76. Shulman-Peleg, A. Recognition of functional sites in protein structures / A. Shulman-Peleg, R. Nussinov, H. J. Wolfson // Journal of molecular biology. — 2004. — Vol. 339, no. 3. — P. 607-633.

77. Bron, C. Algorithm 457: finding all cliques of an undirected graph / C. Bron, J. Kerbosch // Communications of the ACM. — 1973. — Vol. 16, no. 9. — P. 575-577.

78. Lee, H. S. Ligand binding site detection by local structure alignment and its performance complementarity / H. S. Lee, W. Im // Journal of chemical information and modeling. — 2013. — Vol. 53, no. 9. — P. 2462-2470.

79. Viet Hung, L. LIBRA: ligand binding site recognition application / L. Viet Hung, S. Caprari, M. Bizai, [et al.] // Bioinformatics. — 2015. — Vol. 31, no. 24. — P. 4020-4022.

80. Konc, J. ProBiS algorithm for detection of structurally similar protein binding sites by local structural alignment / J. Konc, D. Janezic // Bioinformatics. — 2010. — Vol. 26, no. 9. — P. 1160-1168.

81. Kinoshita, K. Identification of the ligand binding sites on the molecular surface of proteins / K. Kinoshita, H. Nakamura // Protein Science. — 2005. — Vol. 14, no. 3.—P. 711-718.

82. Spriggs, R. V. Searching for patterns of amino acids in 3D protein structures / R. V. Spriggs, P. J. Artymiuk, P. Willett // Journal of chemical information and computer sciences. — 2003. — Vol. 43, no. 2. — P. 412-421.

83. Ullmann, J. R. An algorithm for subgraph isomorphism / J. R. Ullmann // Journal of the ACM (JACM). — 1976. — Vol. 23, no. 1. — P. 31-42.

84. Stark, A. A model for statistical significance of local similarities in structure / A. Stark, S. Sunyaev, R. B. Russell // Journal of molecular biology. — 2003. — Vol. 326, no. 5. — P. 1307-1316.

85. Eguida, M. Estimating the Similarity between Protein Pockets / M. Eguida, D. Rognan // International Journal of Molecular Sciences. — 2022. — Vol. 23, no. 20.—P. 12462.

86. Laskowski, R. A. SURFNET: a program for visualizing molecular surfaces, cavities, and intermolecular interactions / R. A. Laskowski // Journal of molecular graphics. — 1995. — Vol. 13, no. 5. — P. 323-330.

87. Ho, C. M. Cavity search: an algorithm for the isolation and display of cavity-like binding regions / C. M. Ho, G. R. Marshall // Journal of computer-aided molecular design. — 1990. — Vol. 4. — P. 337-354.

88. Levitt, D. G. POCKET: a computer graphies method for identifying and displaying protein cavities and their surrounding amino acids / D. G. Levitt, L. J. Banaszak // Journal of molecular graphics. — 1992. — Vol. 10, no. 4. — P. 229-234.

89. Hendlich, M. LIGSITE: automatic and efficient detection of potential small molecule-binding sites in proteins / M. Hendlich, F. Rippmann, G. Barnickel // Journal of Molecular Graphics and Modelling. — 1997. — Vol. 15, no. 6. — P. 359-363.

90. Huang, B. LIGSITE csc: predicting ligand binding sites using the Connolly surface and degree of conservation / B. Huang, M. Schroeder // BMC structural biology. — 2006. — Vol. 6. — P. 1-11.

91. Weisel, M. PocketPicker: analysis of ligand binding-sites with shape descriptors / M. Weisel, E. Proschak, G. Schneider // Chemistry Central Journal. — 2007. — Vol. 1,no. 1.—P. 1-17.

92. Halgren, T. A. Identifying and characterizing binding sites and assessing druggability / T. A. Halgren // Journal of chemical information and modeling. — 2009. — Vol. 49, no. 2. — P. 377-389.

93. Marchand, J.-R. CAVIAR: a method for automatic cavity detection, description and decomposition into subcavities / J.-R. Marchand, B. Pirard, P. Ertl, F. Sirockin // Journal of Computer-Aided Molecular Design. — 2021. — Vol. 35, no. 6. — P. 737-750.

94. Peters, K. P. The automatic search for ligand binding sites in proteins of known three-dimensional structure using only geometric criteria / K. P. Peters, J. Fauck, C. Frommel // Journal of molecular biology. — 1996. — Vol. 256, no. 1. — P. 201-213.

95. Kawabata, T. Detection of pockets on protein surfaces using small and large probe spheres to find putative ligand binding sites / T. Kawabata, N. Go // Proteins: Structure, Function, and Bioinformatics. — 2007. — Vol. 68, no. 2. — P. 516-529.

96. Masuya, M. Detection and geometric modeling of molecular surfaces and cavities using digital mathematical morphological operations / M. Masuya, J. Doi // Journal of Molecular Graphics. —1995. — Vol. 13, no. 6. —P. 331-336.

97. Kawabata, T. Detection of multiscale pockets on protein surfaces using mathematical morphology / T. Kawabata // Proteins: Structure, Function, and Bioinformatics. — 2010. — Vol. 78, no. 5. — P. 1195-1211.

98. Yu, J. Roll: a new algorithm for the detection of protein pockets and cavities with a rolling probe sphere / J. Yu, Y. Zhou, I. Tanaka, M. Yao // Bioinformatics. — 2010. — Vol. 26, no. 1. — P. 46-52.

99. Delaney, J. S. Finding and filling protein cavities using cellular logic operations / J. S. Delaney // Journal of Molecular Graphics. — 1992. — Vol. 10, no. 3. — P. 174-177.

100. Kleywegt, G. J. Detection, delineation, measurement and display of cavities in macromolecular structures / G. J. Kleywegt, T. A. Jones // Acta Crystallographica Section D: Biological Crystallography. — 1994. — Vol. 50, no. 2. — P. 178-185.

101. Brady, G. P. Fast prediction and visualization of protein binding pockets with PASS / G. P. Brady, P. F. Stouten // Journal of computer-aided molecular design. — 2000. — Vol. 14. — P. 383-401.

102. Kim, D. Pocket extraction on proteins via the Voronoi diagram of spheres / D. Kim, C.-H. Cho, Y. Cho, [et al.] // Journal of Molecular Graphics and Modelling. — 2008. — Vol. 26, no. 7. — P. 1104-1112.

103. Volkamer, A. Analyzing the topology of active sites: on the prediction of pockets and subpockets / A. Volkamer, A. Griewel, T. Grombacher, M. Rarey // Journal of Chemical Information and Modeling. — 2010. — Vol. 50, no. 11. — P. 2041-2052.

104. Xie, Z.-R. Ligand-binding site prediction using ligand-interacting and binding site-enriched protein triangles / Z.-R. Xie, M.-. J. Hwang // Bioinformatics. — 2012.— Vol. 28, no. 12.—P. 1579-1585.

105. Binkowski, T. A. CASTp: computed atlas of surface topography of proteins / T. A. Binkowski, S. Naghibzadeh, J. Liang // Nucleic acids research. — 2003. — Vol. 31, no. 13. — P. 3352-3355.

106. Liang, J. Anatomy of protein pockets and cavities: measurement of binding site geometry and implications for ligand design / J. Liang, C. Woodward, H. Edelsbrunner // Protein science. — 1998. — Vol. 7, no. 9. — P. 1884-1897.

107. Del Carpio, C. A. A new approach to the automatic identification of candidates for ligand receptor sites in proteins:(I) Search for pocket regions / C. A. Del Carpio, Y. Takahashi, S.-i. Sasaki // Journal of molecular graphics. — 1993. —Vol. 11, no. 1.—P. 23-29.

108. Coleman, R. G. Travel depth, a new shape descriptor for macromolecules: application to ligand binding / R. G. Coleman, K. A. Sharp // Journal of molecular biology. — 2006. — Vol. 362, no. 3. — P. 441-458.

109. Bock, M. E. Effective labeling of molecular surface points for cavity detection and location of putative binding sites / M. E. Bock, C. Garutti, C. Guerra // Computational Systems Bioinformatics: (Volume 6). — World Scientific, 2007. — P. 263-274.

110. Zhu, H. MSPocket: an orientation-independent algorithm for the detection of ligand binding pockets / H. Zhu, M. T. Pisabarro // Bioinformatics. — 2011. — Vol. 27, no. 3.—P. 351-358.

111. Liu, Y. CB-Dock: A web server for cavity detection-guided protein-ligand blind docking / Y. Liu, M. Grimm, W.-t. Dai, [et al.] // Acta Pharmacologica Sinica. — 2020.— Vol. 41, no. 1.—P. 138-144.

112. Xie, L. A robust and efficient algorithm for the shape description of protein structures and its application in predicting ligand binding sites / L. Xie, P. E. Bourne // BMC bioinformatics. Vol. 8. — Springer. 2007. — P. 1-13.

113. Le Guilloux, V. Fpocket: an open source platform for ligand pocket detection / V. Le Guilloux, P. Schmidtke, P. Tuffery // BMC bioinformatics. — 2009. — Vol. 10, no. 1.—P. 1-11.

114. Glaser, F. A method for localizing ligand binding pockets in protein structures / F. Glaser, R. J. Morris, R. J. Najmanovich, [et al.] // PROTEINS: Structure, Function, and Bioinformatics. — 2006. — Vol. 62, no. 2. — P. 479-488.

115. Pupko, T. Rate4Site: an algorithmic tool for the identification of functional regions in proteins by surface mapping of evolutionary determinants within their homologues / T. Pupko, R. E. Bell, I. Mayrose, [et al.] // Bioinformatics. — 2002. — Vol. 18, suppl_1. — S71-S77.

116. Armon, A. ConSurf: an algorithmic tool for the identification of functional regions in proteins by surface mapping of phylogenetic information / A. Armon, D. Graur, N. Ben-Tal // Journal of molecular biology. — 2001. — Vol. 307, no. 1.—P. 447-463.

117. Nimrod, G. Detection of functionally important regions in "hypothetical proteins" of known structure / G. Nimrod, M. Schushan, D. M. Steinberg, N. Ben-Tal // Structure. — 2008. — Vol. 16, no. 12. — P. 1755-1763.

118. Panchenko, A. R. Prediction of functional sites by analysis of sequence and structure conservation / A. R. Panchenko, F. Kondrashov, S. Bryant // Protein science. — 2004. — Vol. 13, no. 4. — P. 884-892.

119. Capra, J. A. Predicting protein ligand binding sites by combining evolutionary sequence conservation and 3D structure / J. A. Capra, R. A. Laskowski, J. M. Thornton, [et al.] // PLoS computational biology. — 2009. — Vol. 5, no. 12. — e1000585.

120. Goodford, P. J. A computational procedure for determining energetically favorable binding sites on biologically important macromolecules / P. J. Goodford // Journal of medicinal chemistry. — 1985. — Vol. 28, no. 7. — P. 849-857.

121. Ruppert, J. Automatic identification and representation of protein binding sites for molecular docking / J. Ruppert, W. Welch, A. N. Jain // Protein Science. — 1997. — Vol. 6, no. 3. — P. 524-533.

122. An, J. Comprehensive identification of "druggable" protein ligand binding sites / J. An, M. Totrov, R. Abagyan // Genome Informatics. — 2004. — Vol. 15, no. 2.—P. 31-41.

123. Laurie, A. T. Q-SiteFinder: an energy-based method for the prediction of protein-ligand binding sites / A. T. Laurie, R. M. Jackson // Bioinformatics. — 2005.— Vol. 21, no. 9.—P. 1908-1916.

124. An, J. Pocketome via comprehensive identification and classification of ligand binding envelopes / J. An, M. Totrov, R. Abagyan // Molecular & Cellular Proteomics. — 2005. — Vol. 4, no. 6. — P. 752-761.

125. Nemethy, G. Energy parameters in polypeptides. 10. Improved geometrical parameters and nonbonded interactions for use in the ECEPP/3 algorithm, with application to proline-containing peptides / G. Nemethy, K. D. Gibson, K. A. Palmer, [et al.] // The Journal of Physical Chemistry. — 1992. — Vol. 96, no. 15.—P. 6472-6484.

126. Wade, R. C. Further development of hydrogen bond functions for use in determining energetically favorable binding sites on molecules of known structure. 1. Ligand probe groups with the ability to form two hydrogen bonds / R. C. Wade, K. J. Clark, P. J. Goodford // Journal of Medicinal Chemistry. — 1993. —Vol. 36, no. 1.—P. 140-147.

127. Ghersi, D. EasyMIFS and SiteHound: a toolkit for the identification of ligand-binding sites in protein structures / D. Ghersi, R. Sanchez // Bioinformatics. — 2009. — Vol. 25, no. 23. — P. 3185-3186.

128. Hernandez, M. SITEHOUND-web: a server for ligand binding site identification in protein structures / M. Hernandez, D. Ghersi, R. Sanchez // Nucleic acids research. — 2009. — Vol. 37, suppl_2. — W413-W416.

129. Van Der Spoel, D. GROMACS: fast, flexible, and free / D. Van Der Spoel, E. Lindahl, B. Hess, [et al.] // Journal of computational chemistry. — 2005. — Vol. 26, no. 16. —P. 1701-1718.

130. Ngan, C.-H. FTSite: high accuracy detection of ligand binding sites on unbound protein structures / C.-H. Ngan, D. R. Hall, B. Zerbe, [et al.] // Bioinformatics. — 2012. — Vol. 28, no. 2. — P. 286-287.

131. Brenke, R. Fragment-based identification of druggable 'hot spots' of proteins using Fourier domain correlation techniques / R. Brenke, D. Kozakov, G.-Y. Chuang, [et al.] // Bioinformatics. — 2009. — Vol. 25, no. 5. — P. 621-627.

132. Brooks, B. R. CHARMM: a program for macromolecular energy, minimization, and dynamics calculations / B. R. Brooks, R. E. Bruccoleri, B. D. Olafson, [et al.] // Journal of computational chemistry. — 1983. — Vol. 4, no. 2. — P. 187-217.

133. Ravindranath, P. A. AutoSite: an automated approach for pseudo-ligands prediction—from ligand-binding sites identification to predicting key ligand atoms / P. A. Ravindranath, M. F. Sanner // Bioinformatics. — 2016. — Vol. 32, no. 20.—P. 3142-3149.

134. Morris, G. M. AutoDock4 and AutoDockTools4: Automated docking with selective receptor flexibility / G. M. Morris, R. Huey, W. Lindstrom,

[et al.] // Journal of computational chemistry. — 2009. — Vol. 30, no. 16. — P. 2785-2791.

135. Huey, R. A semiempirical free energy force field with charge-based desolvation / R. Huey, G. M. Morris, A. J. Olson, D. S. Goodsell // Journal of computational chemistry. — 2007. — Vol. 28, no. 6. — P. 1145-1152.

136. Verdonk, M. L. SuperStar: improved knowledge-based interaction fields for protein binding sites / M. L. Verdonk, J. C. Cole, P. Watson, [et al.] // Journal of molecular biology. — 2001. — Vol. 307, no. 3. — P. 841-859.

137. Tsujikawa, H. Development of a protein-ligand-binding site prediction method based on interaction energy and sequence conservation / H. Tsujikawa, K. Sato, C. Wei, [et al.] // Journal of structural and functional genomics. — 2016. — Vol. 17.—P. 39-49.

138. Bhinge, A. Accurate detection of protein: ligand binding sites using molecular dynamics simulations / A. Bhinge, P. Chakrabarti, K. Uthanumallian, [et al.] // Structure. — 2004. — Vol. 12, no. 11. — P. 1989-1999.

139. Faller, C. E. Site Identification by Ligand Competitive Saturation (SILCS) simulations for fragment-based drug design / C. E. Faller, E. P. Raman, A. D. MacKerell, O. Guvench // Fragment-based methods in drug discovery. — 2015.—P. 75-87.

140. Martinez-Rosell, G. PlayMolecule CrypticScout: predicting protein cryptic sites using mixed-solvent molecular simulations / G. Martinez-Rosell, S. Lovera, Z. A. Sands, G. De Fabritiis // Journal of Chemical Information and Modeling. — 2020. — Vol. 60, no. 4. — P. 2314-2324.

141. Gu, L. A multilayer dynamic perturbation analysis method for predicting ligand-protein interactions / L. Gu, B. Li, D. Ming // BMC bioinformatics. — 2022. — Vol. 23, no. 1. — P. 456.

142. Ming, D. Interactions in native binding sites cause a large change in protein dynamics / D. Ming, M. E. Wall // Journal of molecular biology. — 2006. — Vol. 358, no. 1. —P. 213-223.

143. Gutteridge, A. Using a neural network and spatial clustering to predict the location of active sites in enzymes / A. Gutteridge, G. J. Bartlett, J. M. Thornton// Journal of molecular biology. — 2003. — Vol. 330, no. 4. — P. 719-734.

144. Petrova, N. V. Prediction of catalytic residues using Support Vector Machine with selected protein sequence and structural properties / N. V. Petrova, C. H. Wu // BMC bioinformatics. — 2006. — Vol. 7. — P. 1-12.

145. Tong, W. Partial order optimum likelihood (POOL): maximum likelihood prediction of protein active site residues using 3D Structure and sequence properties / W. Tong, Y. Wei, L. F. Murga, [et al.] // PLoS computational biology. — 2009. — Vol. 5, no. 1. — e1000266.

146. Qiu, Z. Improved prediction of protein ligand-binding sites using random forests / Z. Qiu, X. Wang // Protein and peptide letters. — 2011. — Vol. 18, no. 12.—P. 1212-1218.

147. Jian, J.-W. Predicting ligand binding sites on protein surfaces by 3-dimensional probability density distributions of interacting atoms / J.-W. Jian, P. Elumalai, T. Pitti, [et al.] // PloS one. — 2016. — Vol. 11, no. 8. — e0160315.

148. Santana, C. A. GRaSP: a graph-based residue neighborhood strategy to predict binding sites / C. A. Santana, S. d. A. Silveira, J. P. Moraes, [et al.] // Bioinformatics. — 2020. — Vol. 36, Supplement_2. — P. i726-i734.

149. Bradford, J. R. Improved prediction of protein-protein binding sites using a support vector machines approach / J. R. Bradford, D. R. Westhead // Bioinformatics. — 2005. — Vol. 21, no. 8. — P. 1487-1494.

150. Krivak, R. P2Rank: machine learning based tool for rapid and accurate prediction of ligand binding sites from protein structure / R. Krivak, D. Hoksza // Journal of cheminformatics. — 2018. — Vol. 10. — P. 1-12.

151. Gagliardi, L. SiteFerret: beyond simple pocket identification in proteins / L. Gagliardi, W. Rocchia // Journal of Chemical Theory and Computation. — 2023. — Vol. 19, no. 15. — P. 5242-5259.

152. Nayal, M. On the nature of cavities on protein surfaces: application to the identification of drug-binding sites / M. Nayal, B. Honig // Proteins: Structure, Function, and Bioinformatics. — 2006. — Vol. 63, no. 4. — P. 892-906.

153. Bagley, S. C. Characterizing the microenvironment surrounding protein sites / S. C. Bagley, R. B. Altman // Protein Science. — 1995. — Vol. 4, no. 4. — P. 622-635.

154. Bagley, S. C. Conserved features in the active site of nonhomologous serine proteases / S. C. Bagley, R. B. Altman // Folding and Design. — 1996. — Vol. 1, no. 5.—P. 371-379.

155. Wei, L. Recognizing protein binding sites using statistical descriptions of their 3D environments. /L. Wei, R. B. Altman//Pacific Symposium onBiocomputing. Pacific Symposium on Biocomputing. — 1998. — P. 497-508.

156. Wei, L. Recognizing complex, asymmetric functional sites in protein structures using a Bayesian scoring function / L. Wei, R. B. Altman // Journal of bioinformatics and computational biology. — 2003. — Vol. 1, no. 01. — P. 119-138.

157. Liang, M. P. WebFEATURE: an interactive web tool for identifying and visualizing functional sites on macromolecular structures / M. P. Liang, D. R. Banatao, T. E. Klein, [et al.] // Nucleic acids research. — 2003. — Vol. 31, no. 13.—P. 3324-3327.

158. Zhang, Z. Identification of cavities on protein surface using multiple computational approaches for drug binding site prediction / Z. Zhang, Y. Li, B. Lin, [et al.] // Bioinformatics. — 2011. — Vol. 27, no. 15. — P. 2083-2088.

159. Broomhead, N. K. Can we rely on computational predictions to correctly identify ligand binding sites on novel protein drug targets? Assessment of binding site prediction methods and a protocol for validation of predicted binding sites / N. K. Broomhead, M. E. Soliman // Cell biochemistry and biophysics. — 2017. — Vol. 75, no. 1.—P. 15-23.

160. Jumper, J. Highly accurate protein structure prediction with AlphaFold / J. Jumper, R. Evans, A. Pritzel, [et al.] // Nature. — 2021. — Vol. 596, no. 7873.—P. 583-589.

161. Baek, M. Accurate prediction of protein structures and interactions using a three-track neural network / M. Baek, F. DiMaio, I. Anishchenko, [et al.] // Science. — 2021. — Vol. 373, no. 6557. — P. 871-876.

162. Karlov, D. S. graphDelta: MPNN scoring function for the affinity prediction of protein-ligand complexes / D. S. Karlov, S. Sosnin, M. V. Fedorov, P. Popov // ACS omega. — 2020. — Vol. 5, no. 10. — P. 5150-5159.

163. Jiménez, J. DeepSite: protein-binding site predictor using 3D-convolutional neural networks / J. Jiménez, S. Doerr, G. Martinez-Rosell, [et al.] // Bioinformatics. — 2017. — Vol. 33, no. 19. — P. 3036-3042.

164. Desaphy, J. sc-PDB: a 3D-database of ligandable binding sites—10 years on / J. Desaphy, G. Bret, D. Rognan, E. Kellenberger // Nucleic acids research. — 2015. — Vol. 43, no. D1. — P. D399-D404.

165. Jiang, M. A novel protein descriptor for the prediction of drug binding sites / M. Jiang, Z. Li, Y. Bian, Z. Wei // BMC bioinformatics. — 2019. — Vol. 20, no. 1.—P. 1-13.

166. Aggarwal, R. DeepPocket: ligand binding site detection and segmentation using 3D convolutional neural networks / R. Aggarwal, A. Gupta, V. Chelur, [et al.] // Journal of Chemical Information and Modeling. — 2021. — Vol. 62, no. 21. — P. 5069-5079.

167. Sunseri, J. Libmolgrid: graphics processing unit accelerated molecular gridding for deep learning applications / J. Sunseri, D. R. Koes // Journal of chemical information and modeling. — 2020. — Vol. 60, no. 3. — P. 1079-1084.

168. Ronneberger, O. U-net: Convolutional networks for biomedical image segmentation / O. Ronneberger, P. Fischer, T. Brox // Medical Image Computing and Computer-Assisted Intervention-MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. — Springer 2015. — P. 234-241.

169. Mylonas, S. K. DeepSurf: a surface-based deep learning approach for the prediction of ligand binding sites on proteins / S. K. Mylonas, A. Axenopoulos, P. Daras // Bioinformatics. — 2021. — Vol. 37, no. 12. — P. 1681-1690.

V _

170. Petrovski, Z. H. CAT-Site: Predicting Protein Binding Sites Using a

V

Convolutional Neural Network / Z. H. Petrovski, B. Hribar-Lee, Z. Bosnie // Pharmaceutics. — 2022. — Vol. 15, no. 1. — P. 119.

171. Wang, T. SAPocket: Finding pockets on protein surfaces with a focus towards position and voxel channels / T. Wang, Y. He, F. Zhu // Expert Systems with Applications. — 2023. — Vol. 227. — P. 120235.

172. Jiang, M. Frsite: protein drug binding site prediction based on faster R-CNN / M. Jiang, Z. Wei, S. Zhang, [et al.] // Journal of Molecular Graphics and Modelling. — 2019. — Vol. 93. — P. 107454.

173. Stepniewska-Dziubinska, M. M. Improving detection of protein-ligand binding sites with 3D segmentation / M. M. Stepniewska-Dziubinska, P. Zielenkiewicz, P. Siedlecki // Scientific reports. — 2020. — Vol. 10, no. 1. — P. 5035.

174. Kandel, J. PUResNet: prediction of protein-ligand binding sites using deep residual neural network / J. Kandel, H. Tayara, K. T. Chong // Journal of cheminformatics. — 2021. — Vol. 13, no. 1. — P. 1-14.

175. Li, P. RecurPocket: Recurrent Lmser Network with Gating Mechanism for Protein Binding Site Detection / P. Li, B. Cao, S. Tu, L. Xu // 2022 IEEE International Conference on Bioinformatics and Biomedicine (BIBM). — IEEE.

2022.—P. 334-339.

176. Li, P. GLPocket: A multi-scale representation learning approach for protein binding site prediction / P. Li, Y. Liu, S. Tu, L. Xu // Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence. —

2023.—P. 4821-4828.

177. Nazem, F. 3D U-Net: A voxel-based method in binding site prediction of protein structure / F. Nazem, F. Ghasemi, A. Fassihi, A. M. Dehnavi // Journal of Bioinformatics and Computational Biology. — 2021. — Vol. 19, no. 02. — P. 2150006.

178. Liu, Y. RefinePocket: An Attention-Enhanced and Mask-Guided Deep Learning Approach for Protein Binding Site Prediction / Y. Liu, P. Li, S. Tu, L. Xu // IEEE/ACM Transactions on Computational Biology and Bioinformatics. — 2023. — Vol. 20, no. 5. —P. 3314-3321.

179. Wang, X. DUnet: A deep learning guided protein-ligand binding pocket prediction / X. Wang, B. Zhao, P. Yang, [et al.] // bioRxiv. — 2022. — P. 2022-08.

180. Huang, G. Densely connected convolutional networks / G. Huang, Z. Liu, L. Van Der Maaten, K. Q. Weinberger // Proceedings of the IEEE conference on computer vision and pattern recognition. — 2017. — P. 4700-4708.

181. Mallet, V. InDeep: 3D fully convolutional neural networks to assist in silico drug design on protein-protein interactions / V. Mallet, L. Checa Ruano, A. Moine Franel, [et al.] // Bioinformatics. — 2022. — Vol. 38, no. 5. — P. 1261-1268.

182. Yan, X. PointSite: a point cloud segmentation tool for identification of protein ligand binding atoms / X. Yan, Y. Lu, Z. Li, [et al.] // Journal of Chemical Information and Modeling. — 2022. — Vol. 62, no. 11. — P. 2835-2845.

183. Gainza, P. Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning / P. Gainza, F. Sverrisson, F. Monti, [et al.] // Nature Methods. — 2020. — Vol. 17, no. 2. — P. 184-192.

184. Sverrisson, F. Fast end-to-end learning on protein surfaces / F. Sverrisson, J. Feydy, B. E. Correia, M. M. Bronstein // Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. — 2021. — P. 15272-15281.

185. Evteev, S. A. SiteRadar: Utilizing Graph Machine Learning for Precise Mapping of Protein-Ligand-Binding Sites / S. A. Evteev, A. V. Ereshchenko, Y. A. Ivanenkov // Journal of Chemical Information and Modeling. — 2023. — Vol. 63, no. 4.—P. 1124-1132.

186. Li, S. PocketAnchor: Learning structure-based pocket representations for protein-ligand interaction prediction / S. Li, T. Tian, Z. Zhang, [et al.] // Cell Systems. — 2023. — Vol. 14, no. 8. — P. 692-705.

187. Shi, W. GraphSite: Ligand Binding Site Classification with Deep Graph Learning / W. Shi, M. Singha, L. Pu, [et al.] // Biomolecules. — 2022. — Vol. 12, no. 8.—P. 1053.

188. Xia, Y. GraphBind: protein structural context embedded rules learned by hierarchical graph neural networks for recognizing nucleic-acid-binding residues / Y. Xia, C.-Q. Xia, X. Pan, H.-B. Shen // Nucleic acids research. — 2021. — Vol. 49, no. 9. — e51-e51.

189. Wang, W. GraphPLBR: Protein-ligand binding residue prediction with deep graph convolution network / W. Wang, B. Sun, M. Yu, [et al.] // IEEE/ACM Transactions on Computational Biology and Bioinformatics. — 2023. — Vol. 20, no. 3.—P. 2223-2232.

190. Pei, Q. FABind: Fast and Accurate Protein-Ligand Binding / Q. Pei, K. Gao, L. Wu, [et al.] // arXiv preprint arXiv:2310.06763. — 2023.

191. Smith, Z. Graph attention site prediction (grasp): Identifying druggable binding sites using graph neural networks with attention / Z. Smith, M. Strobel, B. P. Vani, P. Tiwary // bioRxiv. — 2023.

192. Nazem, F. A GU-Net-based architecture predicting ligand-Protein-binding atoms / F. Nazem, F. Ghasemi, A. Fassihi, [et al.] // Journal of Medical Signals and Sensors. —2023. — Vol. 13, no. 1. — P. 1.

193. Gao, H. Graph u-nets / H. Gao, S. Ji // international conference on machine learning. — PMLR. 2019. — P. 2083-2092.

194. Zhang, Y. EquiPocket: an E (3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction / Y. Zhang, W. Huang, Z. Wei, [et al.] // arXiv preprint arXiv:2302.12177. — 2023.

195. Satorras, V. G. E (n) equivariant graph neural networks / V. G. Satorras, E. Hoogeboom, M. Welling // International conference on machine learning. — PMLR. 2021. — P. 9323-9332.

196. Song, Y. Accurately identifying nucleic-acid-binding sites through geometric graph learning on language model predicted structures / Y. Song, Q. Yuan, H. Zhao, Y. Yang // Briefings in Bioinformatics. — 2023. — Vol. 24, no. 6. — bbad360.

197. Gamouh, H. Hybrid protein-ligand binding residue prediction with protein language models: Does the structure matter? / H. Gamouh, D. Hoksza, M. Novotny // bioRxiv. — 2023. — P. 2023-08.

198. Roche, R. EquiPNAS: improved protein-nucleic acid binding site prediction using protein-language-model-informed equivariant deep graph neural networks / R. Roche, B. Moussad, M. H. Shuvo, [et al.] // bioRxiv. — 2023.—P. 2023-09.

199. Xia, Y. LigBind: Identifying Binding Residues for Over 1000 Ligands with Relation-Aware Graph Neural Networks / Y. Xia, X. Pan, H.-B. Shen // Journal of Molecular Biology. — 2023. — Vol. 435, no. 13. — P. 168091.

200. Yang, J. BioLiP: a semi-manually curated database for biologically relevant ligand-protein interactions / J. Yang, A. Roy, Y. Zhang // Nucleic acids research. —2012. — Vol. 41, no. D1. — P. D1096-D1103.

201. Kryshtafovych, A. Critical assessment of methods of protein structure prediction (CASP)—Round XIV / A. Kryshtafovych, T. Schwede, M. Topf, [et al.] // Proteins: Structure, Function, andBioinformatics. — 2021. — Vol. 89, no. 12. — P. 1607-1617.

202. Littmann, M. Protein embeddings and deep learning predict binding residues for various ligand classes / M. Littmann, M. Heinzinger, C. Dallago, [et al.] // Scientific Reports. — 2021. — Vol. 11, no. 1. — P. 23916.

203. Ho, Q.-T. FAD-BERT: improved prediction of FAD binding sites using pre-training of deep bidirectional transformers / Q.-T. Ho, T.-T.-D. Nguyen, N. Q. Khanh Le, Y.-Y. Ou // Computers in Biology and Medicine. — 2021. — Vol. 131.—P. 104258.

204. Seo, S. Pseq2Sites: Enhancing protein sequence-based ligand binding-site prediction accuracy via the deep convolutional network and attention mechanism / S. Seo, J. Choi, S. Choi, [et al.] // Engineering Applications of Artificial Intelligence. — 2024. — Vol. 127. — P. 107257.

205. Yuan, Q. AlphaFold2-aware protein-DNA binding site prediction using graph transformer / Q. Yuan, S. Chen, J. Rao, [et al.] // Briefings in Bioinformatics. —

2022. — Vol. 23, no. 2. — bbab564.

206. Zhang, S. Protein Language Model-Powered 3D Ligand Binding Site Prediction from Protein Sequence / S. Zhang, L. Xie // arXiv preprint arXiv:2312.03016. —

2023.

207. Fang, Y. DeepProSite: structure-aware protein binding site prediction using ESMFold and pretrained language model / Y. Fang, Y. Jiang, L. Wei, [et al.] // Bioinformatics. — 2023. — Vol. 39, no. 12. — btad718.

208. Gazizov, A. AF2BIND: Predicting ligand-binding sites using the pair representation of AlphaFold2 / A. Gazizov, A. Lian, C. A. Goverde, [et al.] // bioRxiv. — 2023. — P. 2023-10.

209. Chang, L. Ranking peptide binders by affinity with AlphaFold / L. Chang, A. Perez // Angewandte Chemie. — 2023. — Vol. 135, no. 7. — e202213362.

211. Polizzi, N. F. A defined structural unit enables de novo design of small-molecule-binding proteins / N. F. Polizzi, W. F. DeGrado // Science. — 2020. — Vol. 369, no. 6508. — P. 1227-1233.

212. Meller, A. Predicting the locations of cryptic pockets from single protein structures using the PocketMiner graph neural network / A. Meller, M. D. Ward, J. H. Borowsky, [et al.] // Biophysical Journal. — 2023. — Vol. 122, no. 3. — 445a.

213. Jing, B. Learning from protein structure with geometric vector perceptrons / B. Jing, S. Eismann, P. Suriana, [etal.] // arXiv preprint arXiv:2009.01411. — 2020.

214. Canner, S. W. Structure-based neural network protein-carbohydrate interaction predictions at the residue level / S. W. Canner, S. Shanker, J. J. Gray // Frontiers in Bioinformatics. — 2023. — Vol. 3. — P. 1186531.

215. Xia, C.-Q. Protein-ligand binding residue prediction enhancement through hybrid deep heterogeneous learning of sequence and structure data / C.-Q. Xia, X. Pan, H.-B. Shen // Bioinformatics. — 2020. — Vol. 36, no. 10. — P. 3018-3027.

216. Xia, Y. BindWeb: A web server for ligand binding residue and pocket prediction from protein structures / Y. Xia, C. Xia, X. Pan, H.-B. Shen // Protein Science. — 2022. — Vol. 31, no. 12. — e4462.

217. Taherzadeh, G. Sequence-based prediction of protein-peptide binding sites using support vector machine / G. Taherzadeh, Y. Yang, T. Zhang, [et al.] // Journal of computational chemistry. — 2016. — Vol. 37, no. 13. — P. 1223-1229.

218. Zhao, Z. Improving Sequence-Based Prediction of Protein-Peptide Binding Residues by Introducing Intrinsic Disorder and a Consensus Method / Z. Zhao, Z. Peng, J. Yang // Journal of chemical information and modeling. — 2018. — Vol. 58, no. 7. — P. 1459-1468.

219. Iqbal, S. PBRpredict-Suite: a suite of models to predict peptide-recognition domain residues from protein sequence / S. Iqbal, M. T. Hoque // Bioinformatics. — 2018. — Vol. 34, no. 19. — P. 3289-3299.

220. Shafiee, S. SPPPred: Sequence-based Protein-Peptide binding residue Prediction using genetic programming and ensemble learning / S. Shafiee, A. Fathi,

G. Taherzadeh // IEEE/ACM Transactions on Computational Biology and Bioinformatics. — 2022. — Vol. 20, no. 3. — P. 2029-2040.

221. Wardah, W. Predicting protein-peptide binding sites with a Deep Convolutional Neural Network / W. Wardah, A. Dehzangi, G. Taherzadeh, [et al.] // Journal of Theoretical Biology. — 2020. — P. 110278.

222. Sun, Z. To improve prediction of binding residues with DNA, RNA, carbohydrate, and peptide via multi-task deep neural networks / Z. Sun, S. Zheng,

H. Zhao, [et al.] // IEEE/ACM transactions on computational biology and bioinformatics. — 2021. — Vol. 19, no. 6. — P. 3735-3743.

223. Wang, R. Predicting protein-peptide binding residues via interpretable deep learning / R. Wang, J. Jin, Q. Zou, [et al.] // Bioinformatics. — 2022. — Vol. 38, no. 13.—P. 3351-3360.

224. Abdin, O. PepNN: a deep attention model for the identification of peptide binding sites / O. Abdin, S. Nim, H. Wen, P. M. Kim // Communications biology. — 2022. — Vol. 5, no. 1. — P. 503.

225. Litfin, T. Spot-peptide: template-based prediction of peptide-binding proteins and peptide-binding sites / T. Litfin, Y. Yang, Y. Zhou // Journal of chemical information and modeling. — 2019. — Vol. 59, no. 2. — P. 924-930.

226. Johansson-Ákhe, I. Predicting protein-peptide interaction sites using distant protein complexes as structural templates / I. Johansson-Ákhe, C. Mirabello,

B. Wallner // Scientific reports. — 2019. — Vol. 9, no. 1. — P. 1-13.

227. Lavi, A. Detection of peptide-binding sites on protein surfaces: The first step toward the modeling and targeting of peptide-mediated interactions / A. Lavi,

C. H. Ngan, D. Movshovitz-Attias, [et al.] // Proteins: Structure, Function, and Bioinformatics. — 2013. — Vol. 81, no. 12. — P. 2096-2105.

228. Yan, C. Predicting peptide binding sites on protein surfaces by clustering chemical interactions / C. Yan, X. Zou// Journal of Computational Chemistry. — 2014. — Vol. 1, no. 36. — P. 49-61.

230. Vanhee, P. BriX: a database of protein building blocks for structural analysis, modeling and design / P. Vanhee, E. Verschueren, L. Baeten, [et al.] // Nucleic acids research. — 2011. — Vol. 39, suppl_1. — P. D435-D442.

231. Taherzadeh, G. Structure-based prediction of protein-peptide binding regions using Random Forest / G. Taherzadeh, Y. Zhou, A. W.-C. Liew, Y. Yang // Bioinformatics. — 2018. — Vol. 34, no. 3. — P. 477-484.

232. Segura, J. A holistic in silico approach to predict functional sites in protein structures / J. Segura, P. F. Jones, N. Fernandez-Fuentes // Bioinformatics. — 2012.— Vol. 28, no. 14.—P. 1845-1850.

233. Liang, S. Protein binding site prediction using an empirical scoring function / S. Liang, C. Zhang, S. Liu, Y. Zhou//Nucleic acids research. — 2006. — Vol. 34, no. 13.—P. 3698-3707.

234. Krivák, R. Peptide-Binding site prediction from protein structure via points on the solvent accessible surface / R. Krivák, L. Jendele, D. Hoksza // Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. — 2018. — P. 645-650.

235. Trabuco, L. G. PepSite: prediction of peptide-binding sites from protein surfaces / L. G. Trabuco, S. Lise, E. Petsalaki, R. B. Russell // Nucleic acids research. — 2012. — Vol. 40, W1. — W423-W427.

236. Chandra, A. PepCNN deep learning tool for predicting peptide binding residues in proteins using sequence, structural, and language model features / A. Chandra, A. Sharma, I. Dehzangi, [et al.] // Scientific Reports. — 2023. — Vol. 13, no. 1.—P. 20882.

237. Li, K. Simultaneous Prediction of Interaction Sites on the Protein and Peptide Sides of Complexes through Multilayer Graph Convolutional Networks / K. Li, L. Quan, Y. Jiang, [et al.] // Journal of Chemical Information and Modeling. — 2023. — Vol. 63, no. 7. — P. 2251-2262.

239. Raveh, B. Rosetta FlexPepDock ab-initio: simultaneous folding, docking and refinement of peptides onto their receptors / B. Raveh, N. London, L. Zimmerman, O. Schueler-Furman // PloS one. — 2011. — Vol. 6, no. 4. — e18934.

240. De Vries, S. J. The HADDOCK web server for data-driven biomolecular docking / S. J. De Vries, M. Van Dijk, A. M. Bonvin // Nature protocols. — 2010. — Vol. 5, no. 5. — P. 883-897.

241. Saladin, A. PEP-SiteFinder: a tool for the blind identification of peptide binding sites on protein surfaces / A. Saladin, J. Rey, P. Thevenet, [et al.] // Nucleic acids research. — 2014. — Vol. 42, W1. — W221-W226.

242. Donsky, E. PepCrawler: a fast RRT-based algorithm for high-resolution refinement and binding affinity estimation of peptide inhibitors / E. Donsky, H. J. Wolfson // Bioinformatics. — 2011. — Vol. 27, no. 20. — P. 2836-2842.

243. Lee, H. GalaxyPepDock: a protein-peptide docking tool based on interaction similarity and energy optimization / H. Lee, L. Heo, M. S. Lee, C. Seok//Nucleic acids research. — 2015. — Vol. 43, W1. — W431-W435.

244. Zhou, P. HPEPDOCK: a web server for blind peptide-protein docking based on a hierarchical algorithm / P. Zhou, B. Jin, H. Li, S.-Y. Huang // Nucleic acids research. — 2018. — Vol. 46, W1. — W443-W450.

245. Chen, J.-N. Accurate Prediction for Protein-Peptide Binding Based on High-Temperature Molecular Dynamics Simulations / J.-N. Chen, F. Jiang, Y.-D. Wu // Journal of Chemical Theory and Computation. — 2022. — Vol. 18, no. 10.—P. 6386-6395.

246. Lei, Y. CAMP: a Convolutional Attention-based Neural Network for Multifaceted Peptide-protein Interaction Prediction / Y. Lei, S. Li, Z. Liu, [et al.] // bioRxiv. — 2020.

247. Han, Y. Deep convolutional neural networks for pan-specific peptide-MHC class I binding prediction / Y. Han, D. Kim // BMC bioinformatics. — 2017. — Vol. 18, no. 1.—P. 1-9.

248. Cunningham, J. M. Biophysical prediction of protein-peptide interactions and signaling networks using machine learning / J. M. Cunningham, G. Koytiger, P. K. Sorger, M. AlQuraishi // Nature methods. — 2020. — Vol. 17, no. 2. — P. 175-183.

249. Obarska-Kosinska, A. PepComposer: computational design of peptides binding to a given protein surface / A. Obarska-Kosinska, A. Iacoangeli, R. Lepore, A. Tramontano//Nucleic acids research. — 2016. — Vol. 44, W1. — W522-W528.

250. Unal, E. B. VitAL: Viterbi algorithm for de novo peptide design / E. B. Unal, A. Gursoy, B. Erman // PLoS One. — 2010. — Vol. 5, no. 6. — e10926.

251. King, C. A. Structure-based prediction of protein-peptide specificity in rosetta / C. A. King, P. Bradley // Proteins: Structure, Function, and Bioinformatics. — 2010. — Vol. 78, no. 16. — P. 3437-3449.

252. Bhattacherjee, A. Exploring protein-peptide binding specificity through computational peptide screening / A. Bhattacherjee, S. Wallin // PLoS Computational Biology. — 2013. — Vol. 9, no. 10. — e1003277.

253. Motmaen, A. Peptide-binding specificity prediction using fine-tuned protein structure prediction networks / A. Motmaen, J. Dauparas, M. Baek, [et al.] // Proceedings ofthe National Academy of Sciences. — 2023. — Vol. 120, no. 9. — e2216697120.

254. Zeng, P. Rsite: a computational method to identify the functional sites of noncoding RNAs / P. Zeng, J. Li, W. Ma, Q. Cui // Scientific Reports. — 2015. — Vol. 5, no. 1.—P. 9179.

255. Zeng, P. Rsite2: an efficient computational method to predict the functional sites of noncoding RNAs / P. Zeng, Q. Cui // Scientific Reports. — 2016. — Vol. 6, no. 1.—P. 19016.

256. Wang, K. RBind: computational network method to predict RNA binding sites / K. Wang, Y. Jian, H. Wang, [et al.] // Bioinformatics. — 2018. — Vol. 34, no. 18.—P. 3131-3136.

Kognole, A. A. SILCS-RNA: Toward a Structure-Based Drug Design Approach for Targeting RNAs with Small Molecules / A. A. Kognole, A. Hazel, A. D. MacKerell Jr // Journal of Chemical Theory and Computation. — 2022.

259. Su, H. Recognition of small molecule-RNA binding sites using RNA sequence and structure / H. Su, Z. Peng, J. Yang // Bioinformatics. — 2021.

260. Rekand, I. H. DrugPred_RNA—A Tool for Structure-Based Druggability Predictions for RNA Binding Sites /1. H. Rekand, R. Brenk// Journal of chemical information and modeling. — 2021.

261. Chen, T. Xgboost: A scalable tree boosting system / T. Chen, C. Guestrin // Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. — 2016. — P. 785-794.

262. Wang, K. RLBind: a deep learning method to predict RNA-ligand binding sites / K. Wang, R. Zhou, Y. Wu, M. Li // Briefings in Bioinformatics. — 2023. — Vol. 24, no. 1.—bbac486.

263. Möller, L. Translating from Proteins to Ribonucleic Acids for Ligand-binding Site Detection / L. Möller, L. Guerci, C. Isert, [et al.] // Molecular Informatics. — 2022. — Vol. 41, no. 10. — P. 2200059.

264. Wang, J. Computational modeling of binding site for RNA-ligand complex by learning Multi-modal features / J. Wang, Z. jin, H. Wu, [et al.] // Authorea Preprints. — 2023.

265. Kalicki, C. H. RNABERT: RNA Family Classification and Secondary Structure Prediction with BERT pretrained on RNA sequences / C. H. Kalicki, E. D. Haritaoglu. —.

266. Philips, A. MetalionRNA: computational predictor of metal-binding sites in RNA structures / A. Philips, K. Milanowska, G. Lach, [et al.] // Bioinformatics. — 2012. — Vol. 28, no. 2. — P. 198-205.

267. Zhou, Y. Graph deep learning locates magnesium ions in RNA / Y. Zhou, S.-J. Chen // QRB discovery. — 2022. — Vol. 3. — e20.

268. Zhao, Y. Identification of metal ion-binding sites in RNA structures using deep learning method / Y. Zhao, J. Wang, F. Chang, [et al.] // Briefings in Bioinformatics. — 2023. — bbad049.

270. Panwar, B. Identification of protein-interacting nucleotides in a RNA sequence using composition profile of tri-nucleotides / B. Panwar, G. P. Raghava // Genomics. — 2015. — Vol. 105, no. 4. — P. 197-203.

271. Choi, S. Predicting protein-binding RNA nucleotides using the feature-based removal of data redundancy and the interaction propensity of nucleotide triplets / S. Choi, K. Han // Computers in Biology and Medicine. — 2013. — Vol. 43, no. 11.—P. 1687-1697.

272. Zhan, Z.-H. Accurate prediction of ncRNA-protein interactions from the integration of sequence and evolutionary information / Z.-H. Zhan, Z.-H. You, L.-P. Li, [et al.] // Frontiers in genetics. — 2018. — Vol. 9. — P. 458.

273. Zhao, X. DFpin: Deep learning-based protein-binding site prediction with feature-based non-redundancy from RNA level / X. Zhao, Y. Zhang, X. Du // Computers in biology and medicine. — 2022. — Vol. 142. — P. 105216.

274. Huang, L. LGFC-CNN: prediction of lncRNA-protein interactions by using multiple types of features through deep learning / L. Huang, S. Jiao, S. Yang, [et al.]//Genes. — 2021. — Vol. 12, no. 11.—P. 1689.

275. Choi, D. Predicting protein-binding regions in RNA using nucleotide profiles and compositions / D. Choi, B. Park, H. Chae, [et al.] // BMC systems biology. — 2017.— Vol. 11.—P. 1-12.

276. Pan, X. RBPsuite: RNA-protein binding sites prediction suite based on deep learning / X. Pan, Y. Fang, X. Li, [et al.] // BMC genomics. — 2020. — Vol. 21.—P. 1-8.

277. Tahir, M. kDeepBind: prediction of RNA-Proteins binding sites using convolution neural network and k-gram features / M. Tahir, H. Tayara, M. Hayat, K. T. Chong // Chemometrics and Intelligent Laboratory Systems. — 2021. — Vol. 208.—P. 104217.

278. Uhl, M. GraphProt2: A graph neural network-based method for predicting binding sites of RNA-binding proteins / M. Uhl, V. D. Tran, F. Heyl, R. Backofen // bioRxiv. — 2019. — P. 850024.

280. Luo, J. RPI-Bind: a structure-based method for accurate identification of RNA-protein binding sites / J. Luo, L. Liu, S. Venkateswaran, [et al.] // Scientific reports. —2017. — Vol. 7, no. 1. — P. 614.

281. Ray, D. Rapid and systematic analysis of the RNA recognition specificities of RNA-binding proteins / D. Ray, H. Kazan, E. T. Chan, [et al.] // Nature biotechnology. — 2009. — Vol. 27, no. 7. — P. 667-670.

282. Ray, D. A compendium of RNA-binding motifs for decoding gene regulation / D. Ray, H. Kazan, K. B. Cook, [et al.] // Nature. — 2013. — Vol. 499, no. 7457. — P. 172-177.

283. Alipanahi, B. Predicting the sequence specificities of DNA-and RNA-binding proteins by deep learning / B. Alipanahi, A. Delong, M. T. Weirauch, B. J. Frey // Nature biotechnology. — 2015. — Vol. 33, no. 8. — P. 831-838.

284. Ding, P. DeepSTF: predicting transcription factor binding sites by interpretable deep neural networks combining sequence and shape / P. Ding, Y. Wang, X. Zhang, [et al.] // Briefings in Bioinformatics. — 2023. — bbad231.

285. Mukherjee, S. Rapid analysis of the DNA-binding specificities of transcription factors with DNA microarrays / S. Mukherjee, M. F. Berger, G. Jona, [et al.] // Nature genetics. — 2004. — Vol. 36, no. 12. — P. 1331-1339.

286. Kharchenko, P. V. Design and analysis of ChIP-seq experiments for DNA-binding proteins / P. V. Kharchenko, M. Y. Tolstorukov, P. J. Park // Nature biotechnology. — 2008. — Vol. 26, no. 12. — P. 1351-1359.

287. Jolma, A. Multiplexed massively parallel SELEX for characterization of human transcription factor binding specificities / A. Jolma, T. Kivioja, J. Toivonen, [et al.] // Genome research. — 2010. — Vol. 20, no. 6. — P. 861-873.

288. Philips, A. LigandRNA: computational predictor of RNA-ligand interactions / A. Philips, K. Milanowska, G. Lach, J. M. Bujnicki // RNA. — 2013. — Vol. 19, no. 12.—P. 1605-1616.

290. Ruiz-Carmona, S. rDock: a fast, versatile and open source program for docking ligands to proteins and nucleic acids / S. Ruiz-Carmona, D. Alvarez-Garcia, N. Foloppe, [et al.] // PLoS computational biology. — 2014. — Vol. 10, no. 4. — e1003571.

291. Pfeffer, P. DrugScoreRNA Knowledge-Based Scoring Function To Predict RNA-Ligand Interactions / P. Pfeffer, H. Gohlke // Journal of chemical information and modeling. — 2007. — Vol. 47, no. 5. — P. 1868-1876.

292. Lang, P. T. DOCK 6: Combining techniques to model RNA-small molecule complexes / P. T. Lang, S. R. Brozell, S. Mukherjee, [et al.] // Rna. — 2009. — Vol. 15, no. 6.—P. 1219-1230.

293. Guilbert, C. Docking to RNA via root-mean-square-deviation-driven energy minimization with flexible ligands and flexible targets / C. Guilbert, T. L. James // Journal of chemical information and modeling. — 2008. — Vol. 48, no. 6.—P. 1257-1268.

294. Oliver, C. Augmented base pairing networks encode RNA-small molecule binding preferences. / C. Oliver, V. Mallet, R. S. Gendron, [et al.] // bioRxiv. — 2020.—P. 701326.

295. Yan, J. A review about RNA-protein-binding sites prediction based on deep learning / J. Yan, M. Zhu // Ieee Access. — 2020. — Vol. 8. — P. 150929-150944.

296. Xiao, H. RNA-targeted small-molecule drug discoveries: a machine-learning perspective / H. Xiao, X. Yang, Y. Zhang, [et al.] // RNA biology. — 2023. — Vol. 20, no. 1.—P. 384-397.

297. Hendrix, S. G. DeepDISE: DNA binding site prediction using a deep learning method / S. G. Hendrix, K. Y. Chang, Z. Ryu, Z.-R. Xie // International Journal of Molecular Sciences. — 2021. — Vol. 22, no. 11. — P. 5510.

298. Wei, J. Protein-RNA interaction prediction with deep learning: structure matters / J. Wei, S. Chen, L. Zong, [et al.] // Briefings in bioinformatics. — 2022. — Vol. 23, no. 1. — bbab540.

299. Tubiana, J. ScanNet: an interpretable geometric deep learning model for structure-based protein binding site prediction / J. Tubiana, D. Schneidman-Duhovny, H. J. Wolfson // Nature Methods. — 2022. — Vol. 19, no. 6.—P. 730-739.

300. Gao, Z. Hierarchical graph learning for protein-protein interaction / Z. Gao, C. Jiang, J. Zhang, [et al.] // Nature Communications. — 2023. — Vol. 14, no. 1. — P. 1093.

301. Jha, K. Graph-BERT and language model-based framework for protein-protein interaction identification / K. Jha, S. Karmakar, S. Saha// Scientific Reports. — 2023. —Vol. 13, no. 1.—P. 5663.

302. Fout, A. Protein interface prediction using graph convolutional networks / A. Fout, J. Byrd, B. Shariat, A. Ben-Hur // Advances in neural information processing systems. — 2017. — Vol. 30.

303. Renaud, N. DeepRank: a deep learning framework for data mining 3D protein-protein interfaces /N. Renaud, C. Geng, S. Georgievska, [et al.] //Nature communications. — 2021. — Vol. 12, no. 1. — P. 7068.

304. Krapp, L. F. PeSTo: parameter-free geometric deep learning for accurate prediction of protein binding interfaces / L. F. Krapp, L. A. Abriata, F. Cortés Rodriguez, M. Dal Peraro // Nature Communications. — 2023. — Vol. 14, no. 1.—P. 2175.

305. Dai, B. Protein interaction interface region prediction by geometric deep learning / B. Dai, C. Bailey-Kellogg // Bioinformatics. — 2021. — Vol. 37, no. 17.—P. 2580-2588.

306. Giambasu, G. M. Predicting site-binding modes of ions and water to nucleic acids using molecular solvation theory / G. M. Giambasu, D. A. Case, D. M. York// Journal of the American Chemical Society. — 2019. — Vol. 141, no. 6. — P. 2435-2445.

307. Yu, D.-J. Designing template-free predictor for targeting protein-ligand binding sites with classifier ensemble and spatial clustering / D.-J. Yu, J. Hu, J. Yang, [et al.] // IEEE/ACM transactions on computational biology and bioinformatics. — 2013. — Vol. 10, no. 4. — P. 994-1008.

309. Bai, P. Interpretable bilinear attention network with domain adaptation improves drug-target prediction / P. Bai, F. Miljkovic, B. John, H. Lu // Nature Machine Intelligence. — 2023. — Vol. 5, no. 2. — P. 126-136.

310. Lee, I. DeepConv-DTI: Prediction of drug-target interactions via deep learning with convolution on protein sequences / I. Lee, J. Keum, H. Nam // PLoS computational biology. — 2019. — Vol. 15, no. 6. — e1007129.

311. Jiménez, J. K deep: protein-ligand absolute binding affinity prediction via 3d-convolutional neural networks / J. Jiménez, M. Skalic, G. Martinez-Rosell, G. De Fabritiis // Journal of chemical information and modeling. — 2018. — Vol. 58, no. 2.—P. 287-296.

312. Karimi, M. DeepAffinity: interpretable deep learning of compound-protein affinity through unified recurrent and convolutional neural networks / M. Karimi, D. Wu, Z. Wang, Y. Shen // Bioinformatics. — 2019. — Vol. 35, no. 18. — P. 3329-3338.

313. Dhakal, A. Artificial intelligence in the prediction of protein-ligand interactions: recent advances and future directions / A. Dhakal, C. McKay, J. J. Tanner, J. Cheng // Briefings in Bioinformatics. — 2022. — Vol. 23, no. 1. — bbab476.

314. McNutt, A. T. GNINA 1.0: molecular docking with deep learning / A. T. McNutt, P. Francoeur, R. Aggarwal, [et al.] // Journal of cheminformatics. — 2021. — Vol. 13, no. 1.—P. 1-20.

315. Stärk, H. Equibind: Geometric deep learning for drug binding structure prediction / H. Stärk, O. Ganea, L. Pattanaik, [et al.] // International conference on machine learning. — PMLR. 2022. — P. 20503-20521.

316. Corso, G. Diffdock: Diffusion steps, twists, and turns for molecular docking / G. Corso, H. Stärk, B. Jing, [et al.] // arXiv preprint arXiv:2210.01776. — 2022.

317. Everingham, M. The pascal visual object classes (voc) challenge / M. Everingham, L. Van Gool, C. K. Williams, [et al.] // International journal of computer vision. — 2010. — Vol. 88, no. 2. — P. 303-338.

318. Girshick, R. Rich feature hierarchies for accurate object detection and semantic segmentation / R. Girshick, J. Donahue, T. Darrell, J. Malik // Proceedings of the IEEE conference on computer vision and pattern recognition. — 2014. — P. 580-587.

319. Lin, T.-Y. Microsoft coco: Common objects in context / T.-Y. Lin, M. Maire, S. Belongie, [et al.] // European conference on computer vision. — Springer. 2014.—P. 740-755.

320. Liu, W. Ssd: Single shot multibox detector / W. Liu, D. Anguelov, D. Erhan, [et al.] // European conference on computer vision. — Springer. 2016. — P. 21-37.

321. Redmon, J. You only look once: Unified, real-time object detection / J. Redmon, S. Divvala, R. Girshick, A. Farhadi // Proceedings of the IEEE conference on computer vision and pattern recognition. — 2016. — P. 779-788.

322. Gagliardi, L. SHREC 2022: protein-ligand binding site recognition / L. Gagliardi, A. Raffo, U. Fugacci, [et al.] // Computers & Graphics. — 2022. — Vol. 107.—P. 20-31.

323. Berman, H. M. The protein data bank / H. M. Berman, P. E. Bourne, J. Westbrook, C. Zardecki // Protein Structure. — CRC Press, 2003. — P. 394-410.

324. Zhang, Y. TM-align: a protein structure alignment algorithm based on the TM-score / Y. Zhang, J. Skolnick // Nucleic acids research. — 2005. — Vol. 33, no. 7. — P. 2302-2309.

325. Johnson, S. C. Hierarchical clustering schemes / S. C. Johnson // Psychometrika. — 1967. — Vol. 32, no. 3. — P. 241-254.

326. Pedregosa, F. Scikit-learn: Machine learning in Python / F. Pedregosa, G. Varoquaux, A. Gramfort, [et al.] // Journal of machine learning research. — 2011. — Vol. 12, Oct. — P. 2825-2830.

327. He, K. Spatial pyramid pooling in deep convolutional networks for visual recognition / K. He, X. Zhang, S. Ren, J. Sun // IEEE transactions on pattern analysis and machine intelligence. — 2015. — Vol. 37, no. 9. — P. 1904-1916.

328. Girshick, R. Fast r-cnn / R. Girshick // Proceedings of the IEEE international conference on computer vision. — 2015. — P. 1440-1448.

330. Dai, J. R-fcn: Object detection via region-based fully convolutional networks / J. Dai, Y. Li, K. He, J. Sun // Advances in neural information processing systems. — 2016.— Vol. 29.

331. Lin, T.-Y. Feature pyramid networks for object detection / T.-Y. Lin, P. Dollar, R. Girshick, [et al.] // Proceedings of the IEEE conference on computer vision and pattern recognition. — 2017. — P. 2117-2125.

332. He, K. Mask r-cnn / K. He, G. Gkioxari, P. Dollar, R. Girshick // Proceedings of the IEEE international conference on computer vision. — 2017. — P. 2961-2969.

333. Szegedy, C. Deep neural networks for object detection / C. Szegedy, A. Toshev, D. Erhan // Proceedings of the 27th International Conference on Neural Information Processing Systems. — 2013. — P. 2553-2561.

334. Pinheiro, P. O. Learning to segment object candidates / P. O. Pinheiro, R. Collobert, P. Dollar // Proceedings of the 29th International Conference on Neural Information Processing Systems. — 2015. — P. 1990-1998.

335. Erhan, D. Scalable object detection using deep neural networks / D. Erhan,

C. Szegedy, A. Toshev, D. Anguelov // Proceedings of the IEEE conference on computer vision and pattern recognition. — 2014. — P. 2147-2154.

336. Yoo, D. Attentionnet: Aggregating weak directions for accurate object detection /

D. Yoo, S. Park, J.-Y. Lee, [et al.] // Proceedings of the IEEE international conference on computer vision. — 2015. — P. 2659-2667.

337. Derevyanko, G. Deep convolutional networks for quality assessment of protein folds / G. Derevyanko, S. Grudinin, Y. Bengio, G. Lamoureux // Bioinformatics. — 2018. — Vol. 34, no. 23. — P. 4046-4053.

338. Martin Abadi. TensorFlow: Large-Scale Machine Learning on Heterogeneous Systems / Martin Abadi, Ashish Agarwal, Paul Barham, [et al.]. — 2015 ; — Software available from tensorflow.org.

339. Comaniciu, D. Mean shift: A robust approach toward feature space analysis / D. Comaniciu, P. Meer // IEEE Transactions on Pattern Analysis & Machine Intelligence. — 2002. — No. 5. — P. 603-619.

341. Schubert, E. DBSCAN revisited, revisited: why and how you should (still) use DBSCAN / E. Schubert, J. Sander, M. Ester, [et al.] // ACM Transactions on Database Systems (TODS). — 2017. — Vol. 42, no. 3. — P. 19.

342. Schmidtke, P. Large-scale comparison of four binding site detection algorithms / P. Schmidtke, C. Souaille, F. Estienne, [et al.] // Journal of chemical information and modeling. — 2010. — Vol. 50, no. 12. — P. 2191-2200.

343. Coddou, C. Activation and regulation of purinergic P2X receptor channels / C. Coddou, Z. Yan, T. Obsil, [et al.] // Pharmacological reviews. — 2011. — Vol. 63, no. 3.—P. 641-683.

344. Hattori, M. Molecular mechanism of ATP binding and ion channel activation in P2X receptors / M. Hattori, E. Gouaux // Nature. — 2012. — Vol. 485, no. 7397. — P. 207.

345. Karasawa, A. Structural basis for subtype-specific inhibition of the P2X7 receptor / A. Karasawa, T. Kawate // elife. — 2016. — Vol. 5. — e22153.

346. Thress, K. S. Acquired EGFR C797S mutation mediates resistance to AZD9291 in non-small cell lung cancer harboring EGFR T790M / K. S. Thress, C. P. Paweletz, E. Felip, [et al.] // Nature medicine. — 2015. — Vol. 21, no. 6. — P. 560-562.

347. Jia, Y. Overcoming EGFR (T790M) and EGFR (C797S) resistance with mutant-selective allosteric inhibitors / Y. Jia, C.-H. Yun, E. Park, [et al.] // Nature. — 2016. — Vol. 534, no. 7605. — P. 129.

348. Lee, J. CHARMM-GUI input generator for NAMD, GROMACS, AMBER, OpenMM, and CHARMM/OpenMM simulations using the CHARMM36 additive force field / J. Lee, X. Cheng, S. Jo, [et al.] // Biophysical journal. — 2016. — Vol. 110, no. 3. — 641a.

349. Wootten, D. Emerging paradigms in GPCR allostery: implications for drug discovery / D. Wootten, A. Christopoulos, P. M. Sexton // Nature reviews Drug discovery. — 2013. — Vol. 12, no. 8. — P. 630-644.

351. Rodriguez Espigares, I. GPCRmd-A web platform for collection, visualization and analysis of molecular dynamics data for G protein-coupled receptors: Bridging the gap between dynamics and receptor functionality /

I. Rodriguez Espigares. — 2018.

352. Mitchell, A. L. Interpro in 2019: Improving Coverage, Classification and Access to Protein Sequence Annotations / A. L. Mitchell, T. K. Attwood, P. C. Babbitt, [et al.] // Nucleic Acids Res. — 2019. — Vol. 47, no. D1. — P. D351-D360.

353. Zoph, B. Neural architecture search with reinforcement learning / B. Zoph, Q. V. Le // arXiv preprint arXiv:1611.01578. — 2016.

354. Liu, H. DARTS: Differentiable Architecture Search / H. Liu, K. Simonyan, Y. Yang // arXiv preprint arXiv:1806.09055. — 2018.

355. Popov, P. Eurecon: Equidistant uniform rigid-body ensemble constructor / P. Popov, S. Grudinin // Journal of Molecular Graphics and Modelling. — 2018.— Vol. 80.—P. 313-319.

356. Weiler, M. 3d steerable cnns: Learning rotationally equivariant features in volumetric data / M. Weiler, M. Geiger, M. Welling, [et al.] // Advances in Neural Information Processing Systems. — 2018. — Vol. 31.

357. Cock, P. J. A. Biopython: Freely Available Python Tools for Computational Molecular Biology and Bioinformatics / P. J. A. Cock, T. Antao, J. T. Chang, [et al.] // Bioinformatics. — 2009. — Vol. 25, no. 11. — P. 1422-1423.

358. Mitternacht, S. Freesasa: An Open Source C Library for Solvent Accessible Surface Area Calculations / S. Mitternacht // F1000Research. — 2016. — Vol. 5.

359. Berman, H. M. The protein data bank / H. M. Berman, J. Westbrook, Z. Feng, [et al.] // Nucleic acids research. — 2000. — Vol. 28, no. 1. — P. 235-242.

360. Gong, S. RNA-align: quick and accurate alignment of RNA 3D structures based on size-independent TM-scoreRNA / S. Gong, C. Zhang, Y. Zhang // Bioinformatics. — 2019. — Vol. 35, no. 21. — P. 4459-4461.

361. Coimbatore Narayanan, B. The Nucleic Acid Database: new features and capabilities / B. Coimbatore Narayanan, J. Westbrook, S. Ghosh, [et al.] // Nucleic acids research. — 2014. — Vol. 42, no. D1. — P. D114-D122.

363. Bannwarth, S. HIV-1 TAR RNA: the target of molecular interactions between the virus and its host / S. Bannwarth, A. Gatignol // Current HIV research. — 2005.— Vol. 3, no. 1.—P. 61-71.

364. Abulwerdi, F. A. Recent advances in targeting the HIV-1 Tat/TAR complex / F. A. Abulwerdi, S. F. Le Grice // Current pharmaceutical design. — 2017. — Vol. 23, no. 28. — P. 4112-4121.

365. Aboul-ela, F. The structure of the human immunodeficiency virus type-1 TAR RNA reveals principles of RNA recognition by Tat protein / F. Aboul-ela, J. Karn, G. Varani // Journal of molecular biology. — 1995. — Vol. 253, no. 2. — P. 313-332.

366. Du, Z. Structure of TAR RNA complexed with a Tat-TAR interaction nanomolar inhibitor that was identified by computational screening / Z. Du, K. E. Lind, T. L. James // Chemistry & biology. — 2002. — Vol. 9, no. 6. — P. 707-712.

367. Faber, C. Structural rearrangements of HIV-1 Tat-responsive RNA upon binding of neomycin B / C. Faber, H. Sticht, K. Schweimer, P. Rösch // Journal of Biological Chemistry. — 2000. — Vol. 275, no. 27. — P. 20660-20666.

368. Murchie, A. I. Structure-based drug design targeting an inactive RNA conformation: exploiting the flexibility of HIV-1 TAR RNA / A. I. Murchie, B. Davis, C. Isel, [et al.] // Journal of molecular biology. — 2004. — Vol. 336, no. 3.—P. 625-638.

369. Davis, B. Rational design of inhibitors of HIV-1 TAR RNA through the stabilisation of electrostatic "hot spots" / B. Davis, M. Afshar, G. Varani, [et al.] // Journal of molecular biology. — 2004. — Vol. 336, no. 2. — P. 343-356.

370. Davidson, A. A small-molecule probe induces a conformation in HIV TAR RNA capable of binding drug-like fragments / A. Davidson, D. W. Begley, C. Lau, G. Varani//Journal of molecular biology. — 2011. — Vol. 410, no. 5. —P. 984-996.

371. Davidson, A. Simultaneous recognition of HIV-1 TAR RNA bulge and loop sequences by cyclic peptide mimics of Tat protein / A. Davidson, T. C. Leeper, Z. Athanassiou, [et al.] // Proceedings of the National Academy of Sciences. — 2009.— Vol. 106, no. 29.—P. 11931-11936.

372. Davidson, A. Essential structural requirements for specific recognition of HIV TAR RNA by peptide mimetics of Tat protein / A. Davidson, K. Patora-Komisarska, J. A. Robinson, G. Varani // Nucleic acids research. — 2011. —Vol. 39, no. 1.—P. 248-256.

373. Borkar, A. N. Structure of a low-population binding intermediate in protein-RNA recognition / A. N. Borkar, M. F. Bardaro, C. Camilloni, [et al.] // Proceedings of the National Academy of Sciences. — 2016. — Vol. 113, no. 26. — P. 7171-7176.

374. Shortridge, M. D. An ultra-high affinity ligand of HIV-1 TAR reveals the RNA structure recognized by P-TEFb / M. D. Shortridge, P. T. Wille, A. N. Jones, [et al.] // Nucleic acids research. — 2019. — Vol. 47, no. 3. — P. 1523-1531.

375. Dunn, M. R. Analysis of aptamer discovery and technology / M. R. Dunn, R. M. Jimenez, J. C. Chaput // Nature Reviews Chemistry. — 2017. — Vol. 1, no. 10. — P. 1-16.

376. Röthlisberger, P. Aptamer chemistry / P. Röthlisberger, M. Hollenstein // Advanced drug delivery reviews. — 2018. — Vol. 134. — P. 3-21.

377. Kim, Y. S. Aptamer-based nanobiosensors / Y. S. Kim, N. H. A. Raston, M. B. Gu // Biosensors and Bioelectronics. — 2016. — Vol. 76. — P. 2-19.

378. Zhu, G. Aptamer-based targeted therapy / G. Zhu, X. Chen // Advanced drug delivery reviews. — 2018. — Vol. 134. — P. 65-78.

379. Huizenga, D. E. A DNA aptamer that binds adenosine and ATP / D. E. Huizenga, J. W. Szostak // Biochemistry. — 1995. — Vol. 34, no. 2. — P. 656-665.

380. Biniuri, Y. Redox-switchable binding properties of the ATP-aptamer / Y. Biniuri, G.-F. Luo, M. Fadeev, [et al.] // Journal of the American Chemical Society. — 2019. — Vol. 141, no. 39. — P. 15567-15576.

381. Lin, C. H. Structural basis of DNA folding and recognition in an AMP-DNA aptamer complex: distinct architectures but common recognition motifs for DNA and RNA aptamers complexed to AMP / C. H. Lin, D. J. Patei // Chemistry & biology. — 1997. — Vol. 4, no. 11. — P. 817-832.

382. Xie, Y.-c. Molecular dynamics study of the recognition of ATP by nucleic acid aptamers / Y.-c. Xie, L. A. Eriksson, R.-b. Zhang // Nucleic acids research. — 2020. — Vol. 48, no. 12. — P. 6471-6480.

383. Zacharov, I. "Zhores"—Petaflops Supercomputer for Data-driven Modeling, Machine Learning and Artificial Intelligence Installed in Skolkovo Institute of Science and Technology /1. Zacharov, R. Arslanov, M. Gunin, [et al.] // Open Eng.— 2019.— Vol. 9, no. 1.—P. 512-520.

Publications of the Author on the Subject of the Dissertation

384. Kozlovskii, I. Spatiotemporal Identification of Druggable Binding Sites Using Deep Learning /1. Kozlovskii, P. Popov // Communications biology. — 2020. — Vol. 3, no. 1.—P. 1-12.

385. Kozlovskii, I. Protein-Peptide Binding Site Detection Using 3D Convolutional Neural Networks /1. Kozlovskii, P. Popov // Journal of chemical information and modeling. — 2021. — Vol. 61, no. 8. — P. 3814-3823.

386. Kozlovskii, I. Structure-based deep learning for binding site detection in nucleic acid macromolecules / I. Kozlovskii, P. Popov // NAR Genomics and Bioinformatics. — 2021. — Vol. 3, no. 4. — lqab111.

387. Schimunek, J. A community effort in SARS-CoV-2 drug discovery / J. Schimunek, P. Seidl, K. Elez, [et al.] // Molecular Informatics. — 2024. — Vol. 43. —e202300262.

388. Certificate of State Registration of a Computer Program No. 2020661135. BiteNet / P. Popov, I. Kozlovskii. — Application No. 2020660046. Submitted on September 7, 2020. Registered in the Register of Computer Programs on September 18, 2020.

389. Patent No. 2743316. Method for identification of binding sites of protein complexes / P. Popov, I. Kozlovskii. — Application No. 2020127322. Filed on August 15, 2020. Registered in the State Register of Inventions of the Russian Federation on February 17, 2021.

390. Certificate of State Registration of a Computer Program No. 2023613561. BiteNet (v1.2) / P. Popov, I. Kozlovskii. — Application No. 2023612228. Submitted on February 9, 2023. Registered in the Register of Computer Programs on February 16, 2023.