Model for Parameterization of Interatomic Interaction Potentials by Quantum-Mechanical Descriptors on the Basis of a Graph Neural Network
DOI:
https://doi.org/10.15407/ujpe71.7.573Keywords:
machine learning, interatomic interaction potentials, biomolecule conformers, quantum-mechanical descriptors, neural networks, biomolecular bindingAbstract
Based on graph neural networks, a machine learning model has been developed to predict the total energy of biomolecules from their structural formulas and quantum-mechanical descriptors by predicting the parameters of the functions that approximate interatomic potentials. The applicability of the created model for predicting the total energy of biomolecules, their interaction energy, and the ordering of conformers by energies has been proven. The physical validity of the obtained parameter values was demonstrated, which opens opportunities for further application of the model in molecular modeling problems.
References
1. R. Parr, Y. Weitao. Density-Functional Theory of Atoms and Molecules, International Series of Monographs on Chemistry (Oxford University Press, 1994).
https://doi.org/10.1093/oso/9780195092769.001.0001
2. D. Frenkel, B. Smit. Understanding Molecular Simulation: From Algorithms to Applications, Computational Science (Academic Press, 2001).
3. D.B. Kitchen, H. Decornez, J.R. Furr, J. Bajorath. Docking and scoring in virtual screening for drug discovery: Methods and applications. Nature Rev. Drug Disc. 3, 935 (2004).
https://doi.org/10.1038/nrd1549
4. R. Johnston. Atomic and Molecular Clusters (Taylor and Francis, 2002).
https://doi.org/10.1201/9780367805814
5. Y. Xiang, D.Y. Sun, X.G. Gong. Generalized simulated annealing studies on structures and properties of Nin (n = 2-55) clusters. J. Phys. Chem. A 104, 2746 (2000).
https://doi.org/10.1021/jp992923q
6. P.N. Day, R. Pachter, M.S. Gordon, G.N. Merrill. A study of water clusters using the effective fragment potential and Monte Carlo simulated annealing. J. Chem. Phys. 112, 2063 (2000).
https://doi.org/10.1063/1.480775
7. K.A. Dill, J.L. MacCallum. The protein-folding problem, 50 years on. Science 338, 1042 (2012).
https://doi.org/10.1126/science.1219021
8. S. Mayewski. A multibody, whole-residue potential for protein structures, with testing by Monte Carlo simulated annealing. Proteins Struct. Func. Bioinform. 59, 152 (2005).
https://doi.org/10.1002/prot.20397
9. M. Allen, D. Tildesley. Computer Simulation of Liquids, Computer Simulation of Liquids (Clarendon Press, 1989).
https://doi.org/10.1063/1.2810937
10. Q. Zhao, D.M. Anstine, O. Isayev, B.M. Savoie. Δ² machine learning for reaction property prediction. Chem. Sci. 14, 13392 (2023).
https://doi.org/10.1039/D3SC02408C
11. U.V. Ucak, I. Ashyrmamatov, J. Ko, J. Lee. Retrosynthetic reaction pathway prediction through neural machine translation of atomic environments. Nature Commun. 13, 1186 (2022).
https://doi.org/10.1038/s41467-022-28857-w
12. R. Souza, J. Duarte, R. Goldschmidt, I. Borges, Jr. Machine learning prediction of electronic molecular excited state properties. J. Braz. Chem. Soc. 36, 1 (2025).
https://doi.org/10.26434/chemrxiv-2024-xkt1j
13. Š. Sršeň, O.A. von Lilienfeld, P. Slavíček. Fast and accurate excited states predictions: Machine learning and diabatization. Phys. Chem. Chem. Phys. 26, 4306 (2024).
https://doi.org/10.1039/D3CP05685F
14. D. Zhang, Q. Chu, D. Chen. Predicting the enthalpy of formation of energetic molecules via conventional machine learning and GNN. Phys. Chem. Chem. Phys. 26, 7029 (2024).
https://doi.org/10.1039/D3CP05490J
15. M.R. Dobbelaere, I. Lengyel, C.V. Stevens, K.M. Van Geem. Geometric deep learning for molecular property predictions with chemical accuracy across chemical space. J. Cheminform. 16, 99 (2024).
https://doi.org/10.1186/s13321-024-00895-0
16. U.K. Ghosh, F. Al Abir, N. Rifaat, S.M. Shovan, A. Sayeed, M.A.M. Hasan. Most dominant metabolomic biomarkers identification for lung cancer. Inform. Med. Unlock. 28, 100824 (2022).
https://doi.org/10.1016/j.imu.2021.100824
17. X. Zhang, I. Jonassen, A. Goksøyr. Machine Learning Approaches for Biomarker Discovery Using Gene Expression Data (Exon Publications, 2021).
https://doi.org/10.36255/exonpublications.bioinformatics.2021.ch4
18. Z. Zhang, Z.-P. Liu. Intelligent Computing Theories and Application: Proceedings of the 15th International Conference ICIC 2019, Nanchang, China, August 3-6, 2019 (Springer, 2019), Part II, p. 517 [ISBN: 978-3-030-26968-5, 978-3-030-26969-2].
https://doi.org/10.1007/978-3-030-26969-2_49
19. J. Behler. Perspective: Machine learning potentials for atomistic simulations. J. Chem. Phys. 145, 170901 (2016).
https://doi.org/10.1063/1.4971792
20. L. Seute, E. Hartmann, J. Stühmer, F. Gräter. Grappa - a machine learned molecular mechanics force field. Chem. Sci. 16, 2907 (2025).
https://doi.org/10.1039/D4SC05465B
21. X. Gao, F. Ramezanghorbani, O. Isayev, J.S. Smith, A.E. Roitberg. TorchANI: A free and open source pytorch-based deep learning implementation of the ANI neural network potentials. J. Chem. Inform. Model. 60, 3408 (2020).
https://doi.org/10.1021/acs.jcim.0c00451
22. S. Doerr, M. Majewski, A. Pérez, A. Krämer, C. Clementi, F. Noé, T. Giorgino, G. De Fabritiis. TorchMD: A deep learning framework for molecular simulations. J. Chem. Theor. Comput. 17, 2355 (2021).
https://doi.org/10.1021/acs.jctc.0c01343
23. S.J. Pan, Q. Yang. A survey on transfer learning. IEEE Trans. Knowledg. Data Eng. 22, 1345 (2010).
https://doi.org/10.1109/TKDE.2009.191
24. E. Weislinger, G. Olivier. The classical and quantum mechanical virial theorem. Int. J. Quant. Chem. 8, 389 (1974).
https://doi.org/10.1002/qua.560080842
25. F. Jensen. Introduction to Computational Chemistry (Wiley, 2017).
https://doi.org/10.14293/S2199-1006.1.SOR-CHEM.CLYWQK5.v1
26. C. Isert, K. Atz, J. Jiménez-Luna, G. Schneider. QMugs, quantum mechanical properties of drug-like molecules. Sci. Data 9, 273 (2022).
https://doi.org/10.1038/s41597-022-01390-7
27. D. Mendez, A. Gaulton, A.P. Bento, J. Chambers, M. De Veij, E. Félix, M. Magariños, J. Mosquera, P. Mutowo, M. Nowotka et al. ChEMBL: towards direct deposition of bioassay data. Nucl. Acids Res. 47, D930 (2018).
https://doi.org/10.1093/nar/gky1075
28. D.G.A. Smith, L.A. Burns, A.C. Simmonett, R.M. Parrish, M.C. Schieber, R. Galvelis, P. Kraus, H. Kruse, R. Di Remigio, A. Alenaizan et al. Psi4 1.4: Open-source software for high-throughput quantum chemistry. J. Chem. Phys. 152, 184108 (2020).
https://doi.org/10.26434/chemrxiv.11930031.v1
29. Z. Guo, K. Guo, B. Nan, Y. Tian, R.G. Iyer, Y. Ma, O. Wiest, X. Zhang, W. Wang, C. Zhang, N.V. Chawla. Graph-based molecular representation learning. In: Proc. of the 32nd International Joint Conference on Artificial Intelligence IJCAI '23 (Publisher, 2023), p. XXX.
https://doi.org/10.24963/ijcai.2023/744
30. M. Wang, D. Zheng, Z. Ye, Q. Gan, M. Li, X. Song, J. Zhou, C. Ma, L. Yu, Y. Gai, T. Xiao, T. He, G. Karypis, J. Li, Z. Zhang. Deep graph library: A graph-centric, highly-performant package for graph neural networks. arXiv:1909.01315.
31. J. Gilmer, S.S. Schoenholz, P.F. Riley. Neural Message Passing for Quantum Chemistry. In: Proc. of the 34th International Conference on Machine Learning. Edited by D. Precup, Y.W. Teh (PMLR, 2017), p. 1263.
32. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga, A. Desmaison, A. Kopf, E. Yang, Z. DeVito, M. Raison, A. Tejani, S. Chilamkurthy, B. Steiner, L. Fang, J. Bai, S. Chintala. PyTorch: An imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems 32 (NeurIPS 2019) (Publisher, 2019), p. 8024.
33. D.P. Kingma, J. Ba. A method for stochastic optimization. arXiv:1412.6980.
34. Y. Mo. Probing the nature of hydrogen bonds in DNA base pairs. J. Mol. Model. 12, 665 (2006).
https://doi.org/10.1007/s00894-005-0021-y
35. C. Bannwarth, S. Ehlert, S. Grimme. GFN2-xTB - an accurate and broadly parametrized self-consistent tight-binding quantum chemical method with multipole electrostatics and density-dependent dispersion contributions. J. Chem. Theor. Comput. 15, 1652 (2019).
https://doi.org/10.1021/acs.jctc.8b01176
36. L. Goerigk, A. Hansen, C. Bauer, S. Ehrlich, A. Najibi, S. Grimme. A look at the density functional theory zoo with the advanced GMTKN55 database for general main group thermochemistry, kinetics and noncovalent interactions. Phys. Chem. Chem. Phys. 19, 32184 (2017).
https://doi.org/10.1039/C7CP04913G
37. J. Řezáč, K.E. Riley, P. Hobza. S66: A well-balanced database of benchmark interaction energies relevant to biomolecular structures. J. Chem. Theor. Comput. 7, 2427 (2011).
https://doi.org/10.1021/ct2002946
38. J.-D. Chai, M. Head-Gordon. Long-range corrected hybrid density functionals with damped atom-atom dispersion corrections. Phys. Chem. Chem. Phys. 10, 6615 (2008).
https://doi.org/10.1039/b810189b
39. S. Boys, F. Bernardi. The calculation of small molecular interactions by the differences of separate total energies. Some procedures with reduced errors. Mol. Phys. 19, 553 (1970).
https://doi.org/10.1080/00268977000101561
40. K. Raghavachari, G.W. Trucks, J.A. Pople, M. Head-Gordon. A fifth-order perturbation comparison of electron correlation theories. Chem. Phys. Lett. 157, 479 (1989).
https://doi.org/10.1016/S0009-2614(89)87395-6
41. H.N. Motlagh, J.O. Wrabl, J. Li, V.J. Hilser. The ensemble nature of allostery. Nature 508, 331 (2014).
https://doi.org/10.1038/nature13001
42. A. Kovács, A.Y. Ivanov. Vibrational analysis of α-D-glucose trapped in Ar matrix. J. Phys. Chem. B 113, 2151 (2009).
https://doi.org/10.1021/jp8087308
43. I. Peña, E.J. Cocinero, C. Cabezas, A. Lesarri, S. Mata, P. Écija, A.M. Daly, A. Cimas, C. Bermúdez, F.J. Basterretxea, S. Blanco, J.A. Fernández, J.C. López, F. Castaño, J.L. Alonso. Six pyranoside forms of free 2-deoxy-D-ribose. Angew. Chem. Int. Ed. 52, 11840 (2013).
https://doi.org/10.1002/anie.201305589
44. M. Nakata, T. Shimazaki. PubChemQC Project: A large-scale first-principles electronic structure database for data-driven chemistry. J. Chem. Inf. Model. 57, 1300 (2017).
https://doi.org/10.1021/acs.jcim.7b00083
45. P. Pracht, F. Bohle, S. Grimme. Automated exploration of the low-energy chemical space with fast quantum chemical methods. Phys. Chem. Chem. Phys. 22, 7169 (2020).
https://doi.org/10.1039/C9CP06869D
46. N. Schmid, A.P. Eichenberger, A. Choutko, S. Riniker, M. Winger, A.E. Mark, W.F. van Gunsteren. Definition and testing of the GROMOS force-field versions 54A7 and 54B7. Eur. Biophys. J. 40, 843 (2011).
Downloads
Published
Issue
Section
License
Copyright Agreement
License to Publish the Paper
Kyiv, Ukraine
The corresponding author and the co-authors (hereon referred to as the Author(s)) of the paper being submitted to the Ukrainian Journal of Physics (hereon referred to as the Paper) from one side and the Bogolyubov Institute for Theoretical Physics, National Academy of Sciences of Ukraine, represented by its Director (hereon referred to as the Publisher) from the other side have come to the following Agreement:
1. Subject of the Agreement.
The Author(s) grant(s) the Publisher the free non-exclusive right to use the Paper (of scientific, technical, or any other content) according to the terms and conditions defined by this Agreement.
2. The ways of using the Paper.
2.1. The Author(s) grant(s) the Publisher the right to use the Paper as follows.
2.1.1. To publish the Paper in the Ukrainian Journal of Physics (hereon referred to as the Journal) in original language and translated into English (the copy of the Paper approved by the Author(s) and the Publisher and accepted for publication is a constitutive part of this License Agreement).
2.1.2. To edit, adapt, and correct the Paper by approval of the Author(s).
2.1.3. To translate the Paper in the case when the Paper is written in a language different from that adopted in the Journal.
2.2. If the Author(s) has(ve) an intent to use the Paper in any other way, e.g., to publish the translated version of the Paper (except for the case defined by Section 2.1.3 of this Agreement), to post the full Paper or any its part on the web, to publish the Paper in any other editions, to include the Paper or any its part in other collections, anthologies, encyclopaedias, etc., the Author(s) should get a written permission from the Publisher.
3. License territory.
The Author(s) grant(s) the Publisher the right to use the Paper as regulated by sections 2.1.1–2.1.3 of this Agreement on the territory of Ukraine and to distribute the Paper as indispensable part of the Journal on the territory of Ukraine and other countries by means of subscription, sales, and free transfer to a third party.
4. Duration.
4.1. This Agreement is valid starting from the date of signature and acts for the entire period of the existence of the Journal.
5. Loyalty.
5.1. The Author(s) warrant(s) the Publisher that:
– he/she is the true author (co-author) of the Paper;
– copyright on the Paper was not transferred to any other party;
– the Paper has never been published before and will not be published in any other media before it is published by the Publisher (see also section 2.2);
– the Author(s) do(es) not violate any intellectual property right of other parties. If the Paper includes some materials of other parties, except for citations whose length is regulated by the scientific, informational, or critical character of the Paper, the use of such materials is in compliance with the regulations of the international law and the law of Ukraine.
6. Requisites and signatures of the Parties.
Publisher: Bogolyubov Institute for Theoretical Physics, National Academy of Sciences of Ukraine.
Address: Ukraine, Kyiv, Metrolohichna Str. 14-b.
Author: Electronic signature on behalf and with endorsement of all co-authors.
.png){kind=small}
