Leveraging Graph Neural Networks for Enhanced Prediction of Molecular Solubility via Transfer Learning
Corressponding author's email:
datnp@hcmute.edu.vnDOI:
https://doi.org/10.54644/jte.2024.1571Keywords:
Molecular property prediction, Machine learning, Deep learning, Graph neural network, Transfer learningAbstract
In this study, we explore the potential of graph neural networks (GNNs), in combination with transfer learning, for the prediction of molecular solubility, a crucial property in drug discovery and materials science. Our approach begins with the development of a GNN-based model to predict the dipole moment of molecules. The extracted dipole moment, alongside a selected set of molecular descriptors, feeds into a subsequent predictive model for water solubility. This two-step process leverages the inherent correlations between molecular structure and its physical properties, thus enhancing the accuracy and generalizability. Our data showed that GNN models with attention mechanism and those utilize bond properties outperformed other models. Especially, 3D GNN models such as ViSNet exhibited outstanding performance, with an R2 value of 0.9980. For the prediction of water solubility, the inclusion of dipole moments greatly enhanced the predictive power of various machine learning models. Our methodology demonstrates the effectiveness of GNNs in capturing complex molecular features and the power of transfer learning in bridging related predictive tasks, offering a novel approach for computational predictions in chemistry.
Downloads: 0
References
A. Saunders and P. B. Harrington, “Advances in activity/property prediction from chemical structures,” Critical Reviews in Analytical Chemistry, vol. 54, no. 1, pp. 135– 147, 2024, pMID: 35482792. DOI: https://doi.org/10.1080/10408347.2022.2066461
J. Shen and C. A. Nicolaou, “Molecular property prediction: Recent trends in the era of artificial intelligence,” Drug Discovery Today: Technologies, vol. 32-33, pp. 29–36, 2019, artificial Intelligence. DOI: https://doi.org/10.1016/j.ddtec.2020.05.001
K. Ham, J. Yoon, and L. Sael, “Towards accurate and certain molecular properties prediction,” in 2022 13th International Conference on Information and Communication Technology Convergence (ICTC), 2022, pp. 1621–1624. DOI: https://doi.org/10.1109/ICTC55196.2022.9952716
J. A. Keith et al., “Combining machine learning and computational chemistry for predictive insights into chemical systems,” Chemical Reviews, vol. 121, no. 16, pp. 9816–9872, 2021, pMID: 34232033. DOI: https://doi.org/10.1021/acs.chemrev.1c00107
G. B. Goh, N. O. Hodas, and A. Vishnu, “Deep learning for computational chemistry,” Journal of Computational Chemistry, vol. 38, no. 16, pp. 1291–1307, 2017. DOI: https://doi.org/10.1002/jcc.24764
P. Reiser et al., “Graph neural networks for materials science and chemistry,” Communications Materials, vol. 3, no. 1, p. 93, 2022. DOI: https://doi.org/10.1038/s43246-022-00315-6
O. Wieder et al., “A compact review of molecular property prediction with graph neural networks,” Drug Discovery Today: Technologies, vol. 37, pp. 1–12, 2020. DOI: https://doi.org/10.1016/j.ddtec.2020.11.009
J. Xiong, Z. Xiong, K. Chen, H. Jiang, and M. Zheng, “Graph neural networks for automated de novo drug design,” Drug Discovery Today, vol. 26, no. 6, pp. 1382–1393, 2021. DOI: https://doi.org/10.1016/j.drudis.2021.02.011
Y. Kwon, D. Lee, Y. S. Choi, and S. Kang, “Uncertainty-aware prediction of chemical reaction yields with graph neural networks,” Journal of Cheminformatics, vol. 14, pp. 1– 10, 2022. DOI: https://doi.org/10.1186/s13321-021-00579-z
L. Ferretti, A. Cini, G. Zacharopoulos, C. Alippi, and L. Pozzi, “Graph neural networks for high-level synthesis design space exploration,” ACM Trans. Des. Autom. Electron. Syst., vol. 28, no. 2, 2022. DOI: https://doi.org/10.1145/3570925
H. Jiang et al., “Predicting protein–ligand docking structure with graph neural network,” Journal of Chemical Information and Modeling, vol. 62, no. 12, pp. 2923–2932, 2022, pMID: 35699430. DOI: https://doi.org/10.1021/acs.jcim.2c00127
W. Gong and Q. Yan, “Graph-based deep learning frameworks for molecules and solid-state materials,” Computational Materials Science, vol. 195, p. 110332, 2021. DOI: https://doi.org/10.1016/j.commatsci.2021.110332
R. Ramakrishnan, P. O. Dral, M. Rupp, and O. A. V. Lilienfeld, “Quantum chemistry structures and properties of 134 kilo molecules,” Scientific data, vol. 1, no. 1, pp. 1–7, 2014. DOI: https://doi.org/10.1038/sdata.2014.22
Z. Wu et al., “MoleculeNet: a benchmark for molecular machine learning,” Chem. Sci., vol. 9, pp. 513–530, 2018. DOI: https://doi.org/10.1039/C7SC02664A
J. S. Delaney, “ESOL: Estimating aqueous solubility directly from molecular structure,” Journal of Chemical Information and Computer Sciences, vol. 44, no. 3, pp. 1000–1005, 2004, pMID: 15154768. DOI: https://doi.org/10.1021/ci034243x
T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks” 2017. arXiv:1609.02907.
W. L. Hamilton, R. Ying, and J. Leskovec, “Inductive representation learning on large graphs” 2018. arXiv:1706.02216.
F. Wu, T. Zhang, A. H. de Souza Jr., C. Fifty, T. Yu, and K. Q. Weinberger, “Simplifying graph convolutional networks,” 2019. arXiv:1902.07153.
W. L. Chiang et al., “An efficient algorithm for training deep and large graph convolutional networks,” in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery; Data Mining, KDD 19, ACM, 2019, doi:10.1145/3292500.3330925. DOI: https://doi.org/10.1145/3292500.3330925
C. Morris et al., “Weisfeiler and leman go neural: Higher-order graph neural networks” 2021. arXiv:1810.02244.
E. Ranjan, S. Sanyal, and P. P. Talukdar, “ASAP: Adaptive structure aware pooling for learning hierarchical graph representations,” 2020. arXiv:1911.07979. DOI: https://doi.org/10.1609/aaai.v34i04.5997
S. A. Tailor, F. L. Opolka, P. Lio, and N. D. Lane, “Do we need anisotropic graph neural networks?” 2022. arXiv:2104.01481.
D. Duvenaud et al., “Convolutional networks on graphs for learning molecular fingerprints,” 2015. arXiv:1509.09292.
J. Du, S. Zhang, G. Wu, J. M. F. Moura, and S. Kar, “Topology adaptive graph convolutional networks,” 2018. arXiv:1710.10370.
F. M. Bianchi, D. Grattarola, L. Livi, and C. Alippi, “Graph neural networks with convolutional ARMA filters”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021, doi:10.1109/tpami.2021.3054830. DOI: https://doi.org/10.1109/TPAMI.2021.3054830
M. Brockschmidt, “GNN-FiLM: Graph neural networks with feature-wise linear modulation,” 2020, arXiv:1906.12192.
B. Rozemberczki, P. Englert, A. Kapoor, M. Blais, and B. Perozzi, “Pathfinder discovery networks for neural message passing,” 2021. arXiv:2010.12878. DOI: https://doi.org/10.1145/3442381.3449882
G. Li, C. Xiong, A. Thabet, and B. Ghanem, “DeeperGCN: All you need to train deeper GCNs,” 2020. arXiv:2006.07739.
X. Bresson and T. Laurent, “Residual gated graph convnets,” 2018. arXiv:1711.07553.
P. Veličković, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio, “Graph attention networks,” 2018. arXiv:1710.10903.
S. Brody, U. Alon, and E. Yahav, “How attentive are graph attention networks?” 2022. arXiv:2105.14491.
Y. Shi, Z. Huang, S. Feng, H. Zhong, W. Wang, and Y. Sun, “Masked label prediction: Unified message passing model for semi-supervised classification,” 2021. arXiv:2009.03509. DOI: https://doi.org/10.24963/ijcai.2021/214
D. Kim and A. Oh, “How to find your friendly neighborhood: Graph attention design with self-supervision,” arXiv:2204.04879.
J. You, R. Ying, and J. Leskovec, “Design space for graph neural networks,” 2021. arXiv:2011.08843. DOI: https://doi.org/10.1609/aaai.v35i12.17283
K. T. Schütt, P. J. Kindermans, H. E. Sauceda, S. Chmiela, A. Tkatchenko, and K. R. Müller, “SchNet: A continuous-filter convolutional neural network for modeling quantum interactions,” 2017.
J. Gasteiger, S. Giri, J. T. Margraf, and S. Günnemann, “Fast and uncertainty-aware directional message passing for non-equilibrium molecules,” 2022.
Y. Wang et al., “ViSNet: An equivariant geometry-enhanced graph neural network with vector-scalar interactive message passing for molecules,” 2023.
Downloads
Published
How to Cite
License
Copyright (c) 2024 Journal of Technical Education Science
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Copyright © JTE.
