Identifying protein binding sites is essential for mechanistic biology and structure-based drug discovery. However, single static structures often fail to capture functionally relevant sites that are shallow, transient, allosteric, or cryptic. This review focuses primarily on protein binding-site prediction and presents a unified biophysical framework emphasizing conformational dynamics, thermodynamics, and solvent-mediated recognition. We evaluated current experimental and computational approaches, with particular attention to molecular dynamics, enhanced sampling, Markov state models, and mixed-solvent molecular dynamics for identifying transient cavities and chemically favorable hotspots across conformational ensembles. Rather than relying on single-score predictions, we propose a multi-factor evidence framework that integrates pocket emergence, probe enrichment, local chemistry, reproducibility, and functional or ligand-based support. RNA binding regions and macromolecular interfaces are discussed as important extensions, where related principles of conformational heterogeneity, electrostatics, hydration, and molecular recognition also apply. Finally, we examine the emerging role of ensemble-aware artificial intelligence in integrating structural, dynamic, thermodynamic, and experimental information, and highlight the need for interpretable, uncertainty-aware, and prospectively validated prediction strategies.
Citation: Qiu Yue. Dynamic prediction of protein binding sites: Integrating structural biology, molecular simulation, solvent probe mapping, and artificial intelligence[J]. AIMS Biophysics, 2026, 13(3): 396-423. doi: 10.3934/biophy.2026021
Identifying protein binding sites is essential for mechanistic biology and structure-based drug discovery. However, single static structures often fail to capture functionally relevant sites that are shallow, transient, allosteric, or cryptic. This review focuses primarily on protein binding-site prediction and presents a unified biophysical framework emphasizing conformational dynamics, thermodynamics, and solvent-mediated recognition. We evaluated current experimental and computational approaches, with particular attention to molecular dynamics, enhanced sampling, Markov state models, and mixed-solvent molecular dynamics for identifying transient cavities and chemically favorable hotspots across conformational ensembles. Rather than relying on single-score predictions, we propose a multi-factor evidence framework that integrates pocket emergence, probe enrichment, local chemistry, reproducibility, and functional or ligand-based support. RNA binding regions and macromolecular interfaces are discussed as important extensions, where related principles of conformational heterogeneity, electrostatics, hydration, and molecular recognition also apply. Finally, we examine the emerging role of ensemble-aware artificial intelligence in integrating structural, dynamic, thermodynamic, and experimental information, and highlight the need for interpretable, uncertainty-aware, and prospectively validated prediction strategies.
| [1] |
Stank A, Kokh DB, Fuller JC, et al. (2016) Protein binding pocket dynamics. Acc Chem Res 49: 809-815. https://doi.org/10.1021/acs.accounts.5b00516 
|
| [2] |
Vajda S, Beglov D, Wakefield AE, et al. (2018) Cryptic binding sites on proteins: definition, detection, and druggability. Curr Opin Chem Biol 44: 1-8. https://doi.org/10.1016/j.cbpa.2018.05.003
|
| [3] |
Kuzmanic A, Bowman GR, Juarez-Jimenez J, et al. (2020) Investigating cryptic binding sites by molecular dynamics simulations. Acc Chem Res 53: 654-661. https://doi.org/10.1021/acs.accounts.9b00613
|
| [4] |
Hopkins AL, Groom CR (2002) The druggable genome. Nat Rev Drug Discov 1: 727-730. https://doi.org/10.1038/nrd892
|
| [5] |
Hajduk PJ, Huth JR, Fesik SW (2005) Druggability indices for protein targets derived from NMR-based screening data. J Med Chem 48: 2518-2525. https://doi.org/10.1021/jm049131r
|
| [6] |
Halgren TA (2009) Identifying and characterizing binding sites and assessing druggability. J Chem Inf Model 49: 377-389. https://doi.org/10.1021/ci800324m
|
| [7] |
Clackson T, Wells JA (1995) A hot spot of binding energy in a hormone-receptor interface. Science 267: 383-386. https://doi.org/10.1126/science.7529940
|
| [8] |
Sun LZ, Zhang D, Chen SJ (2017) Theory and modeling of RNA structure and interactions with metal ions and small molecules. Annu Rev Biophys 46: 227-246. https://doi.org/10.1146/annurev-biophys-070816-033920
|
| [9] |
Baron R, McCammon JA (2013) Molecular recognition and ligand association. Annu Rev Phys Chem 64: 151-175. https://doi.org/10.1146/annurev-physchem-040412-110047
|
| [10] |
Bellissent-Funel MC, Hassanali A, Havenith M, et al. (2016) Water determines the structure and dynamics of proteins. Chem Rev 116: 7673-7697. https://doi.org/10.1021/acs.chemrev.5b00664
|
| [11] |
Koshland DE (1958) Application of a theory of enzyme specificity to protein synthesis. Proc Natl Acad Sci USA 44: 98-104. https://doi.org/10.1073/pnas.44.2.98
|
| [12] |
Monod J, Wyman J, Changeux JP (1965) On the nature of allosteric transitions: a plausible model. J Mol Biol 12: 88-118. https://doi.org/10.1016/S0022-2836(65)80285-6
|
| [13] |
Boehr DD, Nussinov R, Wright PE (2009) The role of dynamic conformational ensembles in biomolecular recognition. Nat Chem Biol 5: 789-796. https://doi.org/10.1038/nchembio.232
|
| [14] |
Henzler-Wildman K, Kern D (2007) Dynamic personalities of proteins. Nature 450: 964-972. https://doi.org/10.1038/nature06522
|
| [15] |
Burley SK, Berman HM, Bhikadiya C, et al. (2019) RCSB Protein Data Bank: biological macromolecular structures enabling research and education in fundamental biology, biomedicine, biotechnology and energy. Nucleic Acids Res 47: D464-D474. https://doi.org/10.1093/nar/gky1004
|
| [16] |
Bai XC, McMullan G, Scheres SH (2015) How cryo-EM is revolutionizing structural biology. Trends Biochem Sci 40: 49-57. https://doi.org/10.1016/j.tibs.2014.10.005
|
| [17] |
Williamson MP (2013) Using chemical shift perturbation to characterise ligand binding. Prog Nucl Magn Reson Spectrosc 73: 1-16. https://doi.org/10.1016/j.pnmrs.2013.02.001
|
| [18] |
Masson GR, Burke JE, Ahn NG, et al. (2019) Recommendations for performing, interpreting and reporting hydrogen deuterium exchange mass spectrometry (HDX-MS) experiments. Nat Methods 16: 595-602. https://doi.org/10.1038/s41592-019-0459-y
|
| [19] |
Leney AC, Heck AJ (2017) Native mass spectrometry: what is in the name?. J Am Soc Mass Spectrom 28: 5-13. https://doi.org/10.1007/s13361-016-1545-3
|
| [20] |
Patching SG (2014) Surface plasmon resonance spectroscopy for characterisation of membrane protein-ligand interactions and its potential for drug discovery. Biochim Biophys Acta 1838: 43-55. https://doi.org/10.1016/j.bbamem.2013.04.028
|
| [21] |
Erlanson DA, Fesik SW, Hubbard RE, et al. (2016) Twenty years on: the impact of fragments on drug discovery. Nat Rev Drug Discov 15: 605-619. https://doi.org/10.1038/nrd.2016.109
|
| [22] |
Smith E, Collins I (2015) Photoaffinity labeling in target- and binding-site identification. Future Med Chem 7: 159-183. https://doi.org/10.4155/fmc.14.152
|
| [23] |
Laskowski RA (1995) SURFNET: a program for visualizing molecular surfaces, cavities, and intermolecular interactions. J Mol Graph 13: 323-330. https://doi.org/10.1016/0263-7855(95)00073-9
|
| [24] |
Dundas J, Ouyang Z, Tseng J, et al. (2006) CASTp: computed atlas of surface topography of proteins with structural and topographical mapping of functionally annotated residues. Nucleic Acids Res 34: W116-W118. https://doi.org/10.1093/nar/gkl282
|
| [25] |
Le Guilloux V, Schmidtke P, Tuffery P (2009) Fpocket: an open source platform for ligand pocket detection. BMC Bioinformatics 10: 168. https://doi.org/10.1186/1471-2105-10-168
|
| [26] |
Volkamer A, Kuhn D, Grombacher T, et al. (2012) Combining global and local measures for structure-based druggability predictions. J Chem Inf Model 52: 360-372. https://doi.org/10.1021/ci200454v
|
| [27] |
Halgren T (2007) New method for fast and accurate binding-site identification and analysis. Chem Biol Drug Des 69: 146-148. https://doi.org/10.1111/j.1747-0285.2007.00483.x
|
| [28] |
Goodford PJ (1985) A computational procedure for determining energetically favorable binding sites on biologically important macromolecules. J Med Chem 28: 849-857. https://doi.org/10.1021/jm00145a002
|
| [29] |
Kozakov D, Grove LE, Hall DR, et al. (2015) The FTMap family of web servers for determining and characterizing ligand-binding hot spots of proteins. Nat Protoc 10: 733-755. https://doi.org/10.1038/nprot.2015.043
|
| [30] |
Ashkenazy H, Abadi S, Martz E, et al. (2016) ConSurf 2016: an improved methodology to estimate and visualize evolutionary conservation in macromolecules. Nucleic Acids Res 44: W344-W350. https://doi.org/10.1093/nar/gkw408
|
| [31] |
Armon A, Graur D, Ben-Tal N (2001) ConSurf: an algorithmic tool for the identification of functional regions in proteins by surface mapping of phylogenetic information. J Mol Biol 307: 447-463. https://doi.org/10.1006/jmbi.2000.4474
|
| [32] |
Brylinski M, Skolnick J (2008) A threading-based method (FINDSITE) for ligand-binding site prediction and functional annotation. Proc Natl Acad Sci USA 105: 129-134. https://doi.org/10.1073/pnas.0707684105
|
| [33] |
Krivak R, Hoksza D (2018) P2Rank: machine learning based tool for rapid and accurate prediction of ligand binding sites from protein structure. J Cheminform 10: 39. https://doi.org/10.1186/s13321-018-0285-8
|
| [34] |
Jimenez J, Doerr S, Martinez-Rosell G, et al. (2017) DeepSite: protein-binding site predictor using 3D-convolutional neural networks. Bioinformatics 33: 3036-3042. https://doi.org/10.1093/bioinformatics/btx350
|
| [35] |
Gainza P, Sverrisson F, Monti F, et al. (2020) Deciphering interaction fingerprints from protein molecular surfaces using geometric deep learning. Nat Methods 17: 184-192. https://doi.org/10.1038/s41592-019-0666-6
|
| [36] |
Tubiana J, Schneidman-Duhovny D, Wolfson HJ (2022) ScanNet: an interpretable geometric deep learning model for structure-based protein binding site prediction. Nat Methods 19: 730-739. https://doi.org/10.1038/s41592-022-01490-7
|
| [37] |
Krapp LF, Abriata LA, Cortes Rodriguez F, et al. (2023) PeSTo: parameter-free geometric deep learning for accurate prediction of protein binding interfaces. Nat Commun 14: 2175. https://doi.org/10.1038/s41467-023-37701-8
|
| [38] |
Meller A, Ward M, Borowsky J, et al. (2023) Predicting locations of cryptic pockets from single protein structures using the PocketMiner graph neural network. Nat Commun 14: 1177. https://doi.org/10.1038/s41467-023-36699-3
|
| [39] |
Zhang Z, Quan L, Wang J, et al. (2025) LABind: identifying protein binding ligand-aware sites via learning interactions between ligand and protein. Nat Commun 16: 7712. https://doi.org/10.1038/s41467-025-62899-0
|
| [40] |
Qiu Y, Hong WL, Wang X, et al. (2025) Discovery of inhibitors of SARS-CoV-2 papain-like protease using molecular simulation and Markov state model. J Phys Chem A 129: 9110-9118. https://doi.org/10.1021/acs.jpca.5c04728
|
| [41] |
Bowman GR, Geissler PL (2012) Equilibrium fluctuations of a single folded protein reveal a multitude of potential cryptic allosteric sites. Proc Natl Acad Sci USA 109: 11681-11686. https://doi.org/10.1073/pnas.1209309109
|
| [42] |
Karplus M (2002) Molecular dynamics simulations of biomolecules. Acc Chem Res 35: 321-323. https://doi.org/10.1021/ar020082r
|
| [43] |
Schmidtke P, Bidon-Chanal A, Luque FJ, et al. (2011) MDpocket: open-source cavity detection and characterization on molecular dynamics trajectories. Bioinformatics 27: 3276-3285. https://doi.org/10.1093/bioinformatics/btr550
|
| [44] |
Kokh DB, Richter S, Henrich S, et al. (2013) TRAPP: a tool for analysis of transient binding pockets in proteins. J Chem Inf Model 53: 1235-1252. https://doi.org/10.1021/ci4000294
|
| [45] |
Yuan JH, Han SB, Richter S, et al. (2020) Druggability assessment in TRAPP using machine learning approaches. J Chem Inf Model 60: 1685-1699. https://doi.org/10.1021/acs.jcim.9b01185
|
| [46] |
Laio A, Parrinello M (2002) Escaping free-energy minima. Proc Natl Acad Sci USA 99: 12562-12566. https://doi.org/10.1073/pnas.202427399
|
| [47] |
Hamelberg D, Mongan J, McCammon JA (2004) Accelerated molecular dynamics: a promising and efficient simulation method for biomolecules. J Chem Phys 120: 11919-11929. https://doi.org/10.1063/1.1755656
|
| [48] |
Miao Y, Feher VA, McCammon JA (2015) Gaussian accelerated molecular dynamics: unconstrained enhanced sampling and free energy calculation. J Chem Theory Comput 11: 3584-3595. https://doi.org/10.1021/acs.jctc.5b00436
|
| [49] | Zhou R (2007) Replica exchange molecular dynamics method for protein folding simulation. Methods Mol Biol 350: 205-223. https://doi.org/10.1385/1-59745-189-4:205 |
| [50] |
Zimmerman MI, Bowman GR (2015) FAST conformational searches by balancing exploration/exploitation trade-offs. J Chem Theory Comput 11: 5747-5757. https://doi.org/10.1021/acs.jctc.5b00737
|
| [51] |
Huber GA, Kim S (1996) Weighted-ensemble Brownian dynamics simulations for protein association reactions. Biophys J 70: 97-110. https://doi.org/10.1016/S0006-3495(96)79552-8
|
| [52] |
Abou-Hatab S, Abrams CF (2025) Minimal collective variables for conformational transitions in steered and temperature-accelerated MD simulations: a T4 lysozyme case study. J Phys Chem B 129: 5176-5188. https://doi.org/10.1021/acs.jpcb.5c01129
|
| [53] |
Prinz JH, Wu H, Sarich M, et al. (2011) Markov models of molecular kinetics: generation and validation. J Chem Phys 134: 174105. https://doi.org/10.1063/1.3565032
|
| [54] |
Bowman GR, Beauchamp KA, Boxer G, et al. (2009) Progress and challenges in the automated construction of Markov state models for full protein systems. J Chem Phys 131: 124101. https://doi.org/10.1063/1.3216567
|
| [55] |
Perez-Hernandez G, Paul F, Giorgino T, et al. (2013) Identification of slow molecular order parameters for Markov model construction. J Chem Phys 139: 015102. https://doi.org/10.1063/1.4811489
|
| [56] |
Röblitz S, Weber M (2013) Fuzzy spectral clustering by PCCA+: application to Markov state models and data classification. Adv Data Anal Classif 7: 147-179. https://doi.org/10.1007/s11634-013-0134-6
|
| [57] |
Scherer MK, Trendelkamp-Schroer B, Paul F, et al. (2015) PyEMMA 2: a software package for estimation, validation, and analysis of Markov models. J Chem Theory Comput 11: 5525-5542. https://doi.org/10.1021/acs.jctc.5b00743
|
| [58] |
Amaro RE, Baudry J, Chodera J, et al. (2018) Ensemble docking in drug discovery. Biophys J 114: 2271-2278. https://doi.org/10.1016/j.bpj.2018.02.038
|
| [59] |
Ferruz N, Doerr S, Vanase-Frawley MA, et al. (2018) Dopamine D3 receptor antagonist reveals a cryptic pocket in aminergic GPCRs. Sci Rep 8: 897. https://doi.org/10.1038/s41598-018-19345-7
|
| [60] |
Meller A, De Oliveira S, Davtyan A, et al. (2023) Discovery of a cryptic pocket in the AI-predicted structure of PPM1D phosphatase explains the binding site and potency of its allosteric inhibitors. Front Mol Biosci 10: 1171143. https://doi.org/10.3389/fmolb.2023.1171143
|
| [61] |
Ghanakota P, Carlson HA (2016) Moving beyond active-site detection: MixMD applied to allosteric systems. J Phys Chem B 120: 8685-8695. https://doi.org/10.1021/acs.jpcb.6b03515
|
| [62] |
Smith RD, Carlson HA (2021) Identification of cryptic binding sites using MixMD with standard and accelerated molecular dynamics. J Chem Inf Model 61: 1287-1299. https://doi.org/10.1021/acs.jcim.0c01002
|
| [63] |
Ung PM, Ghanakota P, Graham SE, et al. (2016) Identifying binding hot spots on protein surfaces by mixed-solvent molecular dynamics: HIV-1 protease as a test case. Biopolymers 105: 21-34. https://doi.org/10.1002/bip.22742
|
| [64] |
Ghanakota P, DasGupta D, Carlson HA (2019) Free energies and entropies of binding sites identified by MixMD cosolvent simulations. J Chem Inf Model 59: 2035-2045. https://doi.org/10.1021/acs.jcim.8b00925
|
| [65] |
MacKerell AD, Jo S, Lakkaraju SK, et al. (2020) Identification and characterization of fragment binding sites for allosteric ligand design using the site identification by ligand competitive saturation hotspots approach (SILCS-Hotspots). Biochim Biophys Acta Gen Subj 1864: 129519. https://doi.org/10.1016/j.bbagen.2020.129519
|
| [66] |
Qiu Y, Liu Q, Xie JW (2026) Mixed-Solvent MD Suite: modular tools for building and analyzing mixed-solvent molecular dynamics systems. J Comput Aided Mol Des 40: 128. https://doi.org/10.1007/s10822-026-00829-y
|
| [67] |
Lexa KW, Goh GB, Carlson HA (2014) Parameter choice matters: validating probe parameters for use in mixed-solvent simulations. J Chem Inf Model 54: 2190-2199. https://doi.org/10.1021/ci400741u
|
| [68] |
Van Der Spoel D, Lindahl E, Hess B, et al. (2005) GROMACS: fast, flexible, and free. J Comput Chem 26: 1701-1718. https://doi.org/10.1002/jcc.20291
|
| [69] | Case DA, Aktulga HM, Belfon K, et al. (2021). Amber 2021 reference manual. University of California, San Francisco |
| [70] |
Roe DR, Cheatham TE (2013) PTRAJ and CPPTRAJ: software for processing and analysis of molecular dynamics trajectory data. J Chem Theory Comput 9: 3084-3095. https://doi.org/10.1021/ct400341p
|
| [71] |
Eastman P, Swails J, Chodera JD, et al. (2017) OpenMM 7: rapid development of high performance algorithms for molecular dynamics. PLoS Comput Biol 13: e1005659. https://doi.org/10.1371/journal.pcbi.1005659
|
| [72] | Ester M, Kriegel HP, Sander J, Xu X (1996) A density-based algorithm for discovering clusters in large spatial databases with noise. Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (KDD-96) . AAAI Press 226-231. |
| [73] |
Mukhopadhyay S, Chakrabarty S (2026) Mapping protein-protein interaction hotspots and unveiling a cryptic allosteric pocket in PLK1 PBD via mixed-solvent molecular dynamics. ChemPhysChem 27: e202500907. https://doi.org/10.1002/cphc.202500907
|
| [74] |
Qiu Y, Liu Q, Tu G, et al. (2022) Discovery of the cryptic sites of SARS-CoV-2 papain-like protease and analysis of its druggability. Int J Mol Sci 23: 11265. https://doi.org/10.3390/ijms231911265
|
| [75] |
Qiu Y, Jiang HJ, Yang YS, et al. (2025) Review of the crystallized structures of the SARS-CoV-2 papain-like protease. J Mol Struct 1333: 141730. https://doi.org/10.1016/j.molstruc.2025.141730
|
| [76] |
Franke L, Globisch C, Karakurt MC, et al. (2024) Atomistic simulations reveal crucial role of metal ions for ligand binding in guanidine-I riboswitch. Macromol Rapid Commun 45: e2400606. https://doi.org/10.1002/marc.202400606
|
| [77] |
Yuan Y, Pei J, Lai L (2020) LigBuilder V3: a multi-target de novo drug design approach. Front Chem 8: 142. https://doi.org/10.3389/fchem.2020.00142
|
| [78] |
Cuchillo R, Pinto-Gil K, Michel J (2015) A collective variable for the rapid exploration of protein druggability. J Chem Theory Comput 11: 1292-1307. https://doi.org/10.1021/ct501072t
|
| [79] |
Xia Y, Pan X, Shen HB (2024) A comprehensive survey on protein-ligand binding site prediction. Curr Opin Struct Biol 86: 102793. https://doi.org/10.1016/j.sbi.2024.102793
|
| [80] |
Han J, Zhang S, Guan M, et al. (2024) GeoNet enables the accurate prediction of protein-ligand binding sites through interpretable geometric deep learning. Structure 32: 2435-2448.e5. https://doi.org/10.1016/j.str.2024.10.011
|
| [81] |
Rives A, Meier J, Sercu T, et al. (2021) Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc Natl Acad Sci USA 118: e2016239118. https://doi.org/10.1073/pnas.2016239118
|
| [82] |
Jumper J, Evans R, Pritzel A, et al. (2021) Highly accurate protein structure prediction with AlphaFold. Nature 596: 583-589. https://doi.org/10.1038/s41586-021-03819-2
|
| [83] |
Lin Z, Akin H, Rao R, et al. (2023) Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379: 1123-1130. https://doi.org/10.1126/science.ade2574
|
| [84] |
Batzner S, Musaelian A, Sun L, et al. (2022) E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials. Nat Commun 13: 2453. https://doi.org/10.1038/s41467-022-29939-5
|
| [85] |
Schütt KT, Sauceda HE, Kindermans PJ, et al. (2018) SchNet: a deep learning architecture for molecules and materials. J Chem Phys 148: 241722. https://doi.org/10.1063/1.5019779
|
| [86] | Ho J, Jain A, Abbeel P (2020) Denoising diffusion probabilistic models. Adv Neural Inf Process Syst 33: 6840-6851. |
| [87] |
Motono C, Yanagisawa K, Koseki J, et al. (2025) CrypTothML: an integrated mixed-solvent molecular dynamics simulation and machine learning approach for cryptic site prediction. Int J Mol Sci 26: 4710. https://doi.org/10.3390/ijms26104710
|
| [88] | Gal Y, Ghahramani Z (2016) Dropout as a Bayesian approximation: representing model uncertainty in deep learning. Proceedings of the 33rd International Conference on Machine Learning. Proc Mach Learn Res 48: 1050-1059. |
Figures(2) / Tables(4)
Qiu Yue. Dynamic prediction of protein binding sites: Integrating structural biology, molecular simulation, solvent probe mapping, and artificial intelligence[J]. AIMS Biophysics, 2026, 13(3): 396-423. doi: 10.3934/biophy.2026021
DownLoad: