Multimodal Neural Network for Drug Activity Regression Model with Augmented Drug Graphs and Gene Expressions of Amyotrophic Lateral Sclerosis and Alzheimer’s Diseases
DOI:
https://doi.org/10.22399/ijcesen.3571Keywords:
Amyotrophic lateral Sclerosis, Alzheimer’s, Graph Attention Network, Graph Isomorphism Network, Multimodal Neural NetworkAbstract
The proposed work aims for precise drug activity regression that is crucial in treating neurodegenerative diseases such as Amyotrophic Lateral Sclerosis and Alzheimer’s. Two drug activity scores Half-Maximal Inhibitory Concentration and Half-Maximal Effective Concentration are used as regression targets in model building. To increase the performance of model equivariance is required which is made possible by extracting invariant features through data augmentation namely rotation and translation. The augmented data is passed to the permutation invariant architecture Graph Isomorphism Network and compared with the Graph Attention Network. The equivariant drug features obtained from the graph-based networks are combined with gene expression profiles using a multimodal neural network. The Multimodal Neural Network is trained with original, rotated, translated drug graphs and gene expression profiles. The trials use a carefully chosen dataset containing 665 graphs. Using proper hyperparameters tuning, the prediction results reveal that the GIN-Multimodal model performs exceptionally well, with an R2 Score of 0.94, a Mean Absolute Error of 0.16, and a Root Mean Square Error of 0.15.
References
[1] Botella Lucena, P., & Heneka, M. T. (2024). Inflammatory aspects of Alzheimer’s disease. Acta Neuropathologica, 148(1), 1.
[2] Mead, R. J., Shan, N., Reiser, H. J., Marshall, F., & Shaw, P. J. (2023). Amyotrophic lateral sclerosis: A neurodegenerative disorder poised for successful therapeutic translation. Nature Reviews Drug Discovery, 22(3), 185–212. https://doi.org/10.1038/s41573-022-00612-2
[3] Pang, W., & Hu, F. (2021). Cellular and physiological functions of C9ORF72 and implications for ALS/FTD. Journal of Neurochemistry, 157(3), 334–350. https://doi.org/10.1111/jnc.15255
[4] Miller, T. M., et al. (2022). Trial of antisense oligonucleotide Tofersen for SOD1 ALS. New England Journal of Medicine, 387(12), 1099–1110. https://doi.org/10.1056/nejmoa2204705
[5] Moglia, C., et al. (2024). Cognitive and behavioral features of patients with amyotrophic lateral sclerosis who are carriers of the TARDBP pathogenic variant. Neurology, 102(4), e208082. https://doi.org/10.1212/WNL.0000000000208082
[6] Baek, H., et al. (2022). Clinical intervention using focused ultrasound (FUS) stimulation of the brain in diverse neurological disorders. Frontiers in Neurology, 13, 880814. https://doi.org/10.3389/fneur.2022.880814
[7] Wang, H., Guan, L. P., & Deng, M. (2023). Recent progress of the genetics of amyotrophic lateral sclerosis and challenges of gene therapy. Frontiers in Neuroscience, 17. https://doi.org/10.3389/fnins.2023.1170996
[8] Beckers, J., et al. (2023). A toxic gain-of-function mechanism in C9orf72 ALS impairs the autophagy-lysosome pathway in neurons. Acta Neuropathologica Communications, 11(1), 1. https://doi.org/10.1186/s40478-023-01648-0
[9] Chen, W., Guo, L., Li, M., Wei, C., Li, S., & Xu, R. (2022). The pathogenesis of amyotrophic lateral sclerosis: Mitochondrial dysfunction, protein misfolding and epigenetics. Brain Research, 1786, 147904. https://doi.org/10.1016/j.brainres.2022.147904
[10] Hanna, L., Poluyi, E., Ikwuegbuenyi, C., Morgan, E., & Imaguezegie, G. (2022). Peripheral inflammation and neurodegeneration; a potential for therapeutic intervention in Alzheimer’s disease (AD), Parkinson’s disease (PD), and amyotrophic lateral sclerosis (ALS). Egyptian Journal of Neurosurgery, 37(1), 1. https://doi.org/10.1186/s41984-022-00150-4
[11] Rauf, A., et al. (2022). Neuroinflammatory markers: Key indicators in the pathology of neurodegenerative diseases. Molecules, 27(10), 10. https://doi.org/10.3390/molecules27103194
[12] Askr, H., Elgeldawi, E., Aboul Ella, H., Elshaier, Y. A. M. M., Gomaa, M. M., & Hassanien, A. E. (2023). Deep learning in drug discovery: An integrative review and future challenges. Artificial Intelligence Review, 56(7), 5975–6037. https://doi.org/10.1007/s10462-022-10306-1
[13] Srinivasan, B., & Lloyd, M. D. (2024). Dose-response curves and the determination of IC50 and EC50 values. Journal of Medicinal Chemistry, 67(20), 17931–17934. https://doi.org/10.1021/acs.jmedchem.4c02052
[14] Gaspar, A. T. S. C. (2023). Prediction of drug-target binding affinity: A regression approach for IC50 prediction.
[15] Sidorov, M. Y., et al. (2024). Machine learning-enabled prediction of ecotoxicity (EC50) of diverse organic compounds via infrared spectroscopy. Mendeleev Communications, 34(6), 780–782. https://doi.org/10.1016/j.mencom.2024.10.004
[16] Schapin, N., Majewski, M., Varela-Rial, A., Arroniz, C., & De Fabritiis, G. (2023). Machine learning small molecule properties in drug discovery. Artificial Intelligence Chemistry, 1(2), 100020. https://doi.org/10.1016/j.aichem.2023.100020
[17] Ahmed, H., Shedeed, H., Hamad, S., & Saad, A. (2023). Convolutional neural network models for cancer treatment response prediction. International Journal of Intelligent Computing and Information Sciences, 23(1), 98–105. https://doi.org/10.21608/ijicis.2023.180508.1239
[18] Devipriya, S., & Vijaya, M. S. (2024). Gated recurrent unit with attention mechanism for IC50 prediction model using amyotrophic lateral sclerosis related proteins. In International Conference on Power Engineering and Intelligent Systems (PEIS). Springer, Singapore.
[19] Devipriya, S., & Vijaya, M. S. (2024). Graph convolutional neural network for IC50 prediction model using amyotrophic lateral sclerosis targets. Lecture Notes in Networks and Systems, 819(1), 77–91. https://doi.org/10.1007/978-981-99-7820-5_7
[20] Hemkiran, S., & Sudha, S. G. (2022). Prediction of drug bioactivity in Alzheimer’s disease using machine learning techniques and community networks. Current Bioinformatics, 17(8), 698–709. https://doi.org/10.2174/1574893617666220329181607
[21] Kofinas, M., et al. (2024). Graph neural networks for learning equivariant representations of neural networks.
[22] C. Mallick et al., “Transportation problem solver for drug delivery in pharmaceutical companies using steppingstone method,” International Journal of Intelligent Systems and Applications in Engineering, vol. 11, no. 5, pp. 343–352, 2023.
[23] Berrone, S., Della Santa, F., Mastropietro, A., Pieraccini, S., & Vaccarino, F. (2022). Graph-informed neural networks for regressions on graph-structured data. Mathematics, 10(5), 786. https://doi.org/10.3390/math10050786
[24] Peng, Y., Lin, Y., Jing, X. Y., Zhang, H., Huang, Y., & Luo, G. S. (2020). Enhanced graph isomorphism network for molecular ADMET properties prediction. IEEE Access, 8, 168344–168360. https://doi.org/10.1109/ACCESS.2020.3022850
[25] R. Basheer, S. S. Y. Rahmawati, M. Lee, N. B. M. Rashid, N. S. B. Azhari, and K. Hussain, “Data Retrieval Machine Learning Approaches for Enhancing Denial of Service Attack Detection in Industrial Control Systems,” Available at SSRN 5136845.
[26] Satorras, V. G., Hoogeboom, E., & Welling, M. (2021). E(n) equivariant graph neural networks. In Proceedings of Machine Learning Research (pp. 9323–9332). Retrieved from http://proceedings.mlr.press/v139/satorras21a/satorras21a.pdf
[27] Njanko, A., & Rawat, D. B. (2022). On the identification of isomorphic graphs for graph neural network using multi-graph approach. In 2022 IEEE 13th Annual Information Technology, Electronics and Mobile Communication Conference (IEMCON) (pp. 61–66). https://doi.org/10.1109/IEMCON56893.2022.9946631
[28] Azizian, W., & Lelarge, M. (2021). Expressive power of invariant and equivariant graph neural networks. Retrieved from https://openreview.net/pdf?id=lxHgXYN4bwl
[29] Wei, D., Liu, C., Zheng, X., & Li, Y. (2019). Comprehensive anticancer drug response prediction based on a simple cell line-drug complex network model. BMC Bioinformatics, 20(1), 44. https://doi.org/10.1186/s12859-019-2608-9
[30] B. Riskhan, H. A. J. Saufan, J. B. Ladan, M. A. U. Sheikh, K. Hussain, and M. Hussain, “Reshaping Secure Coding Through Generative AI Approach to Minimizing Programming Challenges,” in Reshaping CyberSecurity With Generative AI Techniques, IGI Global, 2025, pp. 265–280.
[31] Wang, S., & Li, J. (2020). Modular within and between score for drug response prediction in cancer cell lines. Molecular Omics, 16(1), 31–38. https://doi.org/10.1039/c9mo00162j
[32] Kim, S., Bae, S., Piao, Y., & Jo, K. (2021). Graph convolutional network for drug response prediction using gene expression data. Mathematics, 9(7), 7. https://doi.org/10.3390/math9070772
[33] Graber, D., et al. (n.d.). GEMS: A generalizable GNN framework for protein-ligand binding affinity prediction through robust data filtering and language model integration.
[34] Devipriya, S., & Vijaya, M. S. (2024). Graph convolutional neural network for IC50 prediction model with drug SMILES graphs and gene expressions of amyotrophic lateral sclerosis. Journal of Theoretical and Applied Information Technology, 101(1), 133–143. https://www.jatit.org/volumes/Vol102No1/12Vol102No1.pdf
[35] Jabeen, S., Li, X., Amin, M. S., Bourahla, O., Li, S., & Jabbar, A. (2023). A review on methods and applications in multimodal deep learning. ACM Transactions on Multimedia Computing, Communications, and Applications, 19(2s), 1–41. https://doi.org/10.1145/3545572
[36] R. M. Basheer Riskhan, “Virtual Machine Performance Approaches in the Online Education System,” in Proceedings of the International MultiConference of Engineers and Computer Scientists, 2016.
[37] Qiu, S., Miller, M. I., Joshi, P. S., Lee, J. C., Xue, C., Ni, Y., ... & Kolachalama, V. B. (2022). Multimodal deep learning for Alzheimer’s disease dementia
assessment. Nature communications, 13(1),
3404.
[38] Venugopalan, J., Tong, L., Hassanzadeh, H. R., & Wang, M. D. (2021). Multimodal deep learning models for early detection of Alzheimer’s disease stage. Scientific reports, 11(1), 3254.
[39] Xiao, J., Yang, L., & Wang, S. (2024). Graph isomorphism network for materials property prediction along with explainability analysis. Computational Materials Science, 233, 112619. https://doi.org/10.1016/j.commatsci.2023.112619
[40] Wang, Z., Lin, Z., Li, S., Wang, Y., Zhong, W., Wang, X., & Xin, J. (2023). Dynamic multi-task graph isomorphism network for classification of alzheimer’s disease. Applied Sciences, 13(14), 8433.
[41] Wang, S., Su, X., Zhao, B., Hu, P., Bai, T., & Hu, L. (2023). An Improved Graph Isomorphism Network for Accurate Prediction of Drug–Drug
Interactions. Mathematics, 11(18), 3990.
[42] Veličković, P., Casanova, A., Liò, P., Cucurull, G., Romero, A., & Bengio, Y. (2018). Graph attention networks. 6th International Conference on Learning Representations (ICLR 2018) - Conference Track Proceedings. https://doi.org/10.1007/978-3-031-01587-8_7
[43] Vrahatis, A. G., Lazaros, K., & Kotsiantis, S. (2024). Graph attention networks: a comprehensive review of methods and applications. Future Internet, 16(9), 318.
[44] Wang, T., Sun, J., & Zhao, Q. (2023). Investigating cardiotoxicity related with hERG channel blockers using molecular fingerprints and graph attention mechanism. Computers in biology and medicine, 153, 106464.
[45] Wang, M., et al. (2019). Deep Graph Library: A graph-centric, highly-performant package for graph neural networks. International Conference on Learning Representations (ICLR), 1–7. Available at http://arxiv.org/abs/1909.01315
[46] Imambi, S., Prakash, K. B., & Kanagachidambaresan, G. R. (2021). PyTorch. In Programming with TensorFlow: Solution for edge computing applications (pp. 87–104).
[47] Attaullah, M., Ali, M., Almufareh, M. F., Ahmad, M., Hussain, L., Jhanjhi, N., & Humayun, M. (2022). Initial Stage COVID-19 Detection System Based on Patients’ Symptoms and Chest X-Ray Images. Applied Artificial Intelligence, 36(1). https://doi.org/10.1080/08839514.2022.2055398
[48] Aherwadi N, Mittal U, Singla J, Jhanjhi NZ, Yassine A, Hossain MS. Prediction of Fruit Maturity, Quality, and Its Life Using Deep Learning Algorithms. Electronics. 2022; 11(24):4100. https://doi.org/10.3390/electronics11244100
[49] Taj, I., & Zaman, N. (2022). Towards industrial revolution 5.0 and explainable artificial intelligence: Challenges and opportunities. International Journal of Computing and Digital Systems, 12(1), 295-320.
[50] C. Diwaker et al., "A New Model for Predicting Component-Based Software Reliability Using Soft Computing," in IEEE Access, vol. 7, pp. 147191-147203, 2019, doi: 10.1109/ACCESS.2019.2946862.
[51] Loveleen, G., Mohan, B., Shikhar, B. S., Nz, J., Shorfuzzaman, M., & Masud, M. (2023). Explanation-driven HCI model to examine the mini-mental state for Alzheimer’s disease. ACM Transactions on Multimedia Computing, Communications and Applications, 20(2), 1-16.
[52] Aldughayfiq B, Ashfaq F, Jhanjhi NZ, Humayun M. Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP. Diagnostics. 2023; 13(11):1932. https://doi.org/10.3390/diagnostics13111932
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Journal of Computational and Experimental Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
