Prediction of complexation constants and binding free energies of β-cyclodextrin inclusion complexes using machine learning methods
DOI:
https://doi.org/10.56782/pps.925Keywords:
β-cyclodextrin, inclusion complexes, machine learning, molecular descriptors, Iso2vec embeddingsAbstract
Accurate prediction of complexation constants for cyclodextrin inclusion complexes remains a challenging task due to experimental limitations and the high computational cost of theoretical approaches. In this study, machine learning methods were applied as computational tools to predict the complexation constants of β-cyclodextrin inclusion complexes based on experimentally derived data. A curated dataset of β-cyclodextrin–guest complexes measured at 273 K and pH 7 was combined with a comprehensive set of classical molecular descriptors and SMILES-derived Iso2vec embeddings. Classical descriptors were calculated using the Materials Studio software and included fragment-based structural counts and surface-related Jurs descriptors, while Iso2vec embeddings provided an additional representation of molecular structure and stereochemistry. Feature selection was performed using Heat Map–Based Feature Ranking, enabling the identification of compact and informative feature subsets. Several regression models were evaluated, including linear models and tree-based ensemble methods. Among them, gradient-boosted decision tree models, particularly LightGBM, demonstrated the best predictive performance. The inclusion of Iso2vec embeddings consistently improved model accuracy across architectures, indicating that these features capture structural information not accessible through conventional descriptors alone. Model interpretability analysis using SHAP values revealed that both classical descriptors and Iso2vec components contribute to the final predictions. The proposed approach offers a practical and interpretable framework for data-driven prediction of cyclodextrin complexation constants and may support early-stage decision-making in cyclodextrin-based pharmaceutical formulation development.
Downloads
References
1. Pyrak, B.; Gubica, T.; Rogacka-Pyrak, K. Cyclodextrin nanosponges as bioenhancers of phytochemicals. Prospect. Pharm. Sci. 2024, 22(3), 170–177. DOI: 10.56782/pps.272 DOI: https://doi.org/10.56782/pps.272
2. Zielińska-Pisklak, M.; Michalik, K.A.; Szeleszczuk, Ł. Complexes of Fat-Soluble Vitamins with Cyclodextrins. Int. J. Mol. Sci. 2025, 26(13), Art. No: 6110. DOI: 10.3390/ijms26136110 DOI: https://doi.org/10.3390/ijms26136110
3. Araj, S.K.; Szeleszczuk, Ł. A Review on Cyclodextrins/Estrogens Inclusion Complexes. Int. J. Mol. Sci. 2023, 24(10), Art. No: 8780. DOI: 10.3390/ijms24108780 DOI: https://doi.org/10.3390/ijms24108780
4. Pyrak, B.; Rogacka-Pyrak, K.; Gubica, T.; Szeleszczuk, Ł. Exploring Cyclodextrin-Based Nanosponges as Drug Delivery Systems: Understanding the Physicochemical Factors Influencing Drug Loading and Release Kinetics. Int. J. Mol. Sci. 2024, 25(6), Art. No: 3527. DOI: 10.3390/ijms25063527 DOI: https://doi.org/10.3390/ijms25063527
5. Napiórkowska, E.; Szeleszczuk, Ł. Review of Applications of β-Cyclodextrin as a Chiral Selector for Effective Enantioseparation. Int. J. Mol. Sci. 2024, 25(18), Art. No: 10126. DOI: 10.3390/ijms251810126 DOI: https://doi.org/10.3390/ijms251810126
6. Crini, G. A History of Cyclodextrins. Chem. Rev. 2014, 114(21), 10940–10975. DOI: 10.1021/cr500081p DOI: https://doi.org/10.1021/cr500081p
7. Christoforides, E.; Andreou, A.; Koskina, P.; Bethanis, K. Selective Crystallization of Trans-Nerolidol in
β-Cyclodextrin: Crystal Structure and Molecular Dynamics Analysis. Crystals 2025, 15(9), Art. No: 802. DOI: 10.3390/cryst15090802 DOI: https://doi.org/10.3390/cryst15090802
8. Napiórkowska, E.; Szeleszczuk, Ł. Conformational landscape of β-cyclodextrin: a computational resource for host-guest modeling in supramolecular systems. J. Comput. Aided Mol. Des. 2025, 39, Art. No: 117. DOI: 10.1007/s10822-025-00694-1 DOI: https://doi.org/10.1007/s10822-025-00694-1
9. Gackowski, M.; Madriwala, B.; Studzińska, R.; Koba, M. Novel Isosteviol-Based FXa Inhibitors: Molecular Modeling, In Silico Design and Docking Simulation. Molecules 2023, 28(13), Art. No: 4977. DOI: 10.3390/molecules28134977 DOI: https://doi.org/10.3390/molecules28134977
10. Spirande, E.; Miryashkin, T.; Kolmakov, A.; Shapeev, A. Automated prediction of thermodynamic properties via Bayesian free-energy reconstruction from molecular dynamics. Comput. Condens. Matter 2025, 45, Art. No: e01163. DOI: 10.1016/j.cocom.2025.e01163 DOI: https://doi.org/10.1016/j.cocom.2025.e01163
11. Boczar, D.; Michalska, K. A Review of Machine Learning and QSAR/QSPR Predictions for Complexes of Organic Molecules with Cyclodextrins. Molecules 2024, 29(13), Art. No: 3159. DOI: 10.3390/molecules29133159 DOI: https://doi.org/10.3390/molecules29133159
12. Gackowski, M.; Szewczyk-Golec, K.; Pluskota, R.; Koba, M.; Mądra-Gackowska, K.; Woźniak, A. Application of Multivariate Adaptive Regression Splines (MARSplines) for Predicting Antitumor Activity of Anthrapyrazole Derivatives. Int. J. Mol. Sci. 2022, 23(9), Art. No: 5132. DOI: 10.3390/ijms23095132 DOI: https://doi.org/10.3390/ijms23095132
13. Gackowski, M.; Madriwala, B.; Koba, M. In silico design, docking simulation, and ANN-QSAR model for predicting the anticoagulant activity of thiourea isosteviol compounds as FXa inhibitors. Chem. Pap. 2023, 77, 7027–7044. DOI: 10.1007/s11696-023-02994-y DOI: https://doi.org/10.1007/s11696-023-02994-y
14. Todkar, R.; Shirote, P.; Mohite, S. In Silico Screening and DFT Analysis of Nelumbo nucifera Phytochemicals as Potential BACE-1 Inhibitors for Alzheimer’s disease. Prospect. Pharm. Sci. 2025, 23(4), 29–36. DOI: 10.56782/pps.379 DOI: https://doi.org/10.56782/pps.379
15. Tahıl, G.; Delorme, F.; Le Berre, D.; Monflier, É.; Sayede, A.; Tilloy, S. Curated dataset of association constants between a cyclodextrin and a guest for machine learning. Chem. Data Collect. 2023, 45, Art. No: 101022. DOI: 10.1016/j.cdc.2023.101022 DOI: https://doi.org/10.1016/j.cdc.2023.101022
16. Mikolov, T.; Chen, K.; Corrado, G.; Dean, J. Efficient Estimation of Word Representations in Vector Space. arXiv 2013, arXiv:1301.3781. DOI: 10.48550/arXiv.1301.3781
17. Huertas, C.; Juárez-Ramírez, R.; Raymond, C. Heat Map based Feature Ranker: In Depth Comparison with Popular Methods. Intell. Data Anal. 2018, 22(5), 1009–1037. DOI: 10.3233/IDA-173481 DOI: https://doi.org/10.3233/IDA-173481
18. Pedregosa, F.; Varoquaux, G.; Gramfort, A.; Michel, V.; Thirion, B.; Grisel, O.; Blondel, M.; Prettenhofer, P.; Weiss, R.; Dubourg, V.; Vanderplas, J.; Passos, A.; Cournapeau, D.; Brucher, M.; Perrot, M.; Duchesnay, É. Scikit-learn: Machine Learning in Python. J. Mach. Learn. Res. 2011, 12(85), 2825–2830.
19. Chen, T.; Guestrin, C. XGBoost: A Scalable Tree Boosting System. Proc. KDD 2016, 2016, 785–794. DOI: 10.1145/2939672.2939785 DOI: https://doi.org/10.1145/2939672.2939785
20. Ke, G.; Meng, Q.; Finley, T.; Wang, T.; Chen, W.; Ma, W.; Ye, Q.; Liu, T.-Y. LightGBM: A Highly Efficient Gradient Boosting Decision Tree. Adv. Neural Inf. Process. Syst. 2017, 30, 3146–3154.
21. Prokhorenkova, L.; Gusev, G.; Vorobev, A.; Dorogush, A.V.; Gulin, A. CatBoost: Unbiased Boosting with Categorical Features. Adv. Neural Inf. Process. Syst. 2018, 31, 6638–6648.
22. Friedman, J.H. Greedy Function Approximation: A Gradient Boosting Machine. Ann. Stat. 2001, 29(5), 1189–1232. DOI: 10.1214/aos/1013203451 DOI: https://doi.org/10.1214/aos/1013203451
23. Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. DOI: 10.1023/A:1010933404324 DOI: https://doi.org/10.1023/A:1010933404324
24. Akiba, T.; Sano, S.; Yanase, T.; Ohta, T.; Koyama, M. Optuna: A Next-generation Hyperparameter Optimization Framework. Proc. KDD 2019, 2019, 2623–2631. DOI: 10.1145/3292500.3330701 DOI: https://doi.org/10.1145/3292500.3330701
25. Hyndman, R.J.; Koehler, A.B. Another Look at Measures of Forecast Accuracy. Int. J. Forecast. 2006, 22(4), 679–688. DOI: 10.1016/j.ijforecast.2006.03.001 DOI: https://doi.org/10.1016/j.ijforecast.2006.03.001
26. Lundberg, S.M.; Lee, S.-I. A Unified Approach to Interpreting Model Predictions. Adv. Neural Inf. Process. Syst. 2017, 30, 4765–4774.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jakub Jarząbek, Szymon Araj, Dariusz Maciej Pisklak, Aleksandra Kowalska, Łukasz Szeleszczuk
This work is licensed under a Creative Commons Attribution 4.0 International License.
For all articles published in Prospects in Pharmaceutical Sciences copyright is retained by the authors. The journal publishes articles in the Open Access policy, within the CC BY 4.0 licence.
This is a human-readable summary of (and not a substitute for) the license. Disclaimer.
You are free to:
Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material for any purpose, even commercially.
The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation.
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
How to Cite
