Hyperparameter Tuning on Graph Neural Network for the Classification of SARS-CoV-2 Inhibitors
Abstract
COVID-19 is caused by the SARS-CoV-2 virus, which results in a range of symptoms, from mild to severe, and can lead to fatalities. As of October 2023, WHO has recorded 771 cases of COVID-19 globally. Various efforts have been made to control the spread of the virus, including vaccination, isolation measures, and intensive medical care. The emergence of new SARS-CoV-2 variants has led to the ongoing evolution of virus transmission. Continued research is essential to understand this virus and develop strategies to address the pandemic. Inhibitors of SARS-CoV-2 play a crucial role in the vaccine development process. Inhibitors can impede the virus's development, helping reduce disease severity and control the pandemic. The classification of inhibitors is expected to serve as a foundation for selecting compounds that can be developed into vaccines. This research develops a Graph Neural Network model for inhibitor classification and uses the random search method for hyperparameter tuning. Graph Neural Networks are chosen due to their excellent performance in modelling graph data. This study demonstrates the success of hyperparameter tuning in improving the performance of the Graph Neural Network for accurate classification of SARS-CoV-2 inhibitors.
Downloads
References
World Health Organization, “Current COVID-19 Situation: Overview Of SARS-CoV-2 Circulating Variants,” 2023.
F. Touret et al., “In vitro screening of a FDA approved chemical library reveals potential inhibitors of SARS-CoV-2 replication,” Sci Rep, vol. 10, no. 1, p. 13093, 2020, doi: 10.1038/s41598-020-70143-6.
V. Gawriljuk et al., “Machine Learning Models Identify Inhibitors of SARS-CoV-2,” J Chem Inf Model, vol. 61, Aug. 2021, doi: 10.1021/acs.jcim.1c00683.
R. S. I. Salamet Nur Himawan, “Klasifikasi Inhibitor Sars-Cov-2 Menggunakan Geometric Deep Learning,” in Prosiding Seminar SeNTIK, 2023, pp. 78–82.
M. M. Bronstein, J. Bruna, Y. LeCun, A. Szlam, and P. Vandergheynst, “Geometric Deep Learning: Going beyond Euclidean data,” IEEE Signal Process Mag, vol. 34, no. 4, pp. 18–42, 2017, doi: 10.1109/MSP.2017.2693418.
F. Scarselli, M. Gori, A. C. Tsoi, M. Hagenbuchner, and G. Monfardini, “The Graph Neural Network Model,” IEEE Trans Neural Netw, vol. 20, no. 1, pp. 61–80, 2009, doi: 10.1109/TNN.2008.2005605.
S. Kearnes, K. McCloskey, M. Berndl, V. Pande, and P. Riley, “Molecular graph convolutions: moving beyond fingerprints,” J Comput Aided Mol Des, vol. 30, no. 8, pp. 595–608, 2016, doi: 10.1007/s10822-016-9938-8.
H. Stärk, O. Ganea, L. Pattanaik, Dr. R. Barzilay, and T. Jaakkola, “EquiBind: Geometric Deep Learning for Drug Binding Structure Prediction,” in Proceedings of the 39th International Conference on Machine Learning, K. Chaudhuri, S. Jegelka, L. Song, C. Szepesvari, G. Niu, and S. Sabato, Eds., in Proceedings of Machine Learning Research, vol. 162. PMLR, Nov. 2022, pp. 20503–20521. [Online]. Available: https://proceedings.mlr.press/v162/stark22b.html
A. C. P. L. G. C. A. R. Y. B. Petar Velickovic, “Graph attention networks,” 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings, 2018.
Y. Shi, H. Zhengjie, S. Feng, H. Zhong, W. Wang, and Y. Sun, Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification. 2021. doi: 10.24963/ijcai.2021/214.
Z. Wu, S. Pan, F. Chen, G. Long, C. Zhang, and P. S. Yu, “A Comprehensive Survey on Graph Neural Networks,” IEEE Trans Neural Netw Learn Syst, vol. 32, no. 1, pp. 4–24, 2021, doi: 10.1109/TNNLS.2020.2978386.
Copyright (c) 2023 Salamet Nur Himawan, Robieth Sohiburoyyan, Iryanto Iryanto
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
