Enhanced ResNet50 Model for Aqueous Solubility Prediction of Drug Compounds Using Deep Learning Techniques
Omprakash Dewangan 1*, Vasani Vaibhav Prakash 1
Journal of Angiotherapy 8(9) 1-6 https://doi.org/10.25163/angiotherapy.899869
Submitted: 09 July 2024 Revised: 29 August 2024 Published: 01 September 2024
Abstract
Background: Aqueous Solubility (AS) is a critical factor in drug discovery (DD), directly influencing a drug’s bioavailability and overall efficacy. Accurate prediction of AS remains a challenge despite the advancement in machine learning techniques, which are essential for improving the pharmacokinetics and formulation of new compounds. Methods: This study determines an enhanced ResNet50 deep learning architecture for predicting AS in drug compounds. Deep-net models with 8, 16, and 20-layer ResNet50 Convolutional Neural Network (CNN) architectures were developed. A dataset of 9,532 drug compounds, represented by molecular footprints, was used to train the models. The training process utilized a ten-fold cross-validation technique to optimize the model's predictive performance. Results: The 20-layer ResNet50 model outperformed human experts and shallower models, achieving an R² value of 0.423 and an RMSE of 0.678. The model also demonstrated an impressive ASP accuracy rate of 90.6%, significantly surpassing the predictions made by human experts and simpler neural network models. Conclusion: This study demonstrates that deeper-net architectures, particularly the 20-layer ResNet50 model, offer superior performance in predicting AS. These deep learning models provide a reliable and efficient solution for improving solubility predictions, crucial for advancing drug discovery efforts.
Keywords: Aqueous Solubility, Drug Discovery, Prediction, ResNet50, Convolutional Neural Network, Deep Learning.
References
Bennett-Lenane, H., Griffin, B. T., & O'Shea, J. P. (2022). Machine learning methods for prediction of food effects on bioavailability: A comparison of support vector machines and artificial neural networks. European Journal of Pharmaceutical Sciences, 168, 106018.
Bobir, A.O., Askariy, M., Otabek, Y.Y., Nodir, R.K., Rakhima, A., Zukhra, Z.Y., & Sherzod, A.A. (2024). Utilizing deep learning and the internet of things to monitor the health of aquatic ecosystems to conserve biodiversity. Natural and Engineering Sciences, 9(1), 72-83.
Cai, H., Chen, T., Niu, R., & Plaza, A. (2021). Landslide detection using densely connected convolutional networks and environmental conditions. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 5235-5247.
Deore, A. B., Dhumane, J. R., Wagh, R., & Sonawane, R. (2019). The stages of drug discovery and development process. Asian Journal of Pharmaceutical Research and Development, 7(6), 62-67.
Fan, Y., & Yang, W. (2022). A backpropagation learning algorithm with graph regularization for feedforward neural networks. Information Sciences, 607, 263-277.
Francoeur, P. G., & Koes, D. R. (2021). SolTranNet–A machine learning tool for fast aqueous solubility prediction. Journal of Chemical Information and Modeling, 61(6), 2530-2536.
Francoeur, P. G., & Koes, D. R. (2021). SolTranNet–A machine learning tool for fast aqueous solubility prediction. Journal of Chemical Information and Modeling, 61(6), 2530–2536.
Gupta, R., Srivastava, D., Sahu, M., Tiwari, S., Ambasta, R. K., & Kumar, P. (2021). Artificial intelligence to deep learning: Machine intelligence approach for drug discovery. Molecular Diversity, 25, 1315-1360.
Huuskonen, J. (2000). Estimation of aqueous solubility for a diverse set of organic compounds based on molecular topology. Journal of Chemical Information and Computer Sciences, 40(3), 773-777.
Huuskonen, J. (2000). Estimation of aqueous solubility for a diverse set of organic compounds based on molecular topology. Journal of Chemical Information and Computer Sciences, 40(3), 773–777.
Lovric, M., Pavlovic, K., Žuvela, P., Spataru, A., Lucic, B., Kern, R., & Wong, M. W. (2021). Machine learning in prediction of intrinsic aqueous solubility of drug-like compounds: Generalization, complexity, or predictive ability? Journal of Chemometrics, 35(7-8), e3349.
P. Vijayakumar, Sivasubramaniyan, G., & Saraswati Rao, M. (2019). Bibliometric analysis of Indian Journal of Nuclear Medicine (2014–2018). Indian Journal of Information Sources and Services, 9(1), 122-127.
Rika, R., Bob, S. R., & Suparni, S. (2023). Comparative analysis of support vector machine and convolutional neural network for malaria parasite classification and feature extraction. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 14(3), 194-217.
Rutba-Aman, Rahnuma Tasmin et al. (2023). Unveiling the Veiled: Leveraging Deep Learning and Network Analysis for De-Anonymization in Social Networks, Journal of Primeasia, 4(1), 1-6, 40042
Salman, R., & Banu, A. A. (2023). DeepQ residue analysis of computer vision dataset using support vector machine. Journal of Internet Services and Information Security, 13(1), 78-84.
Sovannarith, H., Phet, A., & Chakchai, S. (2023). A novel video-on-demand caching scheme using hybrid fuzzy logic least frequency and recently used with support vector machine. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 14(1), 15-36.
Surendar, A., Veerappan, S., Sadulla, S., & Arvinth, N. (2024). Lung cancer segmentation and detection using KMP algorithm. Onkologia i Radioterapia, 18(4).
Tanvir Anjum Labir, Poly Rani Ghosh et al. (2023). Enhancing Emotion Recognition through Deep Learning and Brain-Computer Interface Technology, Journal of Primeasia, 4(1), 1-6, 40046
Tetko, I. V., Tanchuk, V. Y., Kasheva, T. N., & Villa, A. E. (2001). Estimation of aqueous solubility of chemical compounds using E-state indices. Journal of Chemical Information and Computer Sciences, 41(6), 1488-1493.
Wang, G., & Qiao, J. (2021). An efficient self-organizing deep fuzzy neural network for nonlinear system modeling. IEEE Transactions on Fuzzy Systems, 30(7), 2170-2182.
Wu, K., Zhao, Z., Wang, R., & Wei, G. W. (2018). TopP–S: Persistent homology-based multi-task deep neural networks for simultaneous predictions of partition coefficient and aqueous solubility. Journal of Computational Chemistry, 39(20), 1444-1454.
Zheng, H., Wu, Y., Deng, L., Hu, Y., & Li, G. (2021, May). Going deeper with directly-trained larger spiking neural networks. In Proceedings of the AAAI Conference on Artificial Intelligence (Vol. 35, No. 12, pp. 11062-11070).
View Dimensions
View Altmetric
Save
Citation
View
Share