Engineered Nanoparticles Cytotoxicity Prediction Using an Enhanced Convolutional Neural Network
Engineered Nanoparticles Cytotoxicity Prediction Using an Enhanced Convolutional Neural Network |
||
 |
 |
|
| © 2025 by IJETT Journal | ||
| Volume-73 Issue-6 |
||
| Year of Publication : 2025 | ||
| Author : Lilibeth P. Coronel, Rey Y. Capangpangan, Ruji P. Medina | ||
| DOI : 10.14445/22315381/IJETT-V73I6P126 | ||
How to Cite?
Lilibeth P. Coronel, Rey Y. Capangpangan, Ruji P. Medina, "Engineered Nanoparticles Cytotoxicity Prediction Using an Enhanced Convolutional Neural Network," International Journal of Engineering Trends and Technology, vol. 73, no. 6, pp.309-317, 2025. Crossref, https://doi.org/10.14445/22315381/IJETT-V73I6P126
Abstract
Engineered nanoparticles (ENPs) possess distinctive physicochemical properties that drive innovation across various fields. However, their potential cytotoxic effects, combined with the inherent complexity of their biological interactions, pose significant challenges for accurate toxicity assessment. Traditional machine learning methods often fall short in modeling the nonlinear and high-dimensional nature of ENP data. To address this limitation, this study introduces a novel feature aggregation technique called Horizontal Sequence Pooling (HSP) integrated within a Convolutional Neural Network framework to improve cytotoxicity prediction. The dataset employed was compiled from multiple peer-reviewed sources published between 2010 and 2022, comprising 4,863 samples characterized by 28 descriptors. Data preprocessing involved median-based univariate imputation for handling missing values and one-hot encoding of categorical variables to ensure compatibility with the CNN architecture. The CNN-HSP model was evaluated against CNN variants utilizing conventional max and average pooling strategies. Experimental results demonstrate that the CNN-HSP model consistently achieved superior performance, reflected in significantly reduced error metrics (MSE, MAE, and RMSE) and a high coefficient of determination R-squared value of 0.9975, indicating strong alignment between predicted and observed values. The enhanced pooling method effectively preserved critical spatial data relationships, allowing the model to learn complex toxicity-related patterns more accurately. Overall, the CNN-HSP model provides a robust and interpretable framework for ENP cytotoxicity prediction, offering a valuable tool for risk assessment and safer nanomaterial development.
Keywords
Engineered Nanoparticles, Cytotoxicity, Convolutional Neural Networks, Pooling algorithms, Prediction.
References
[1] Ayush Thakur, and Renu Kathpalia, “Engineered Nanoparticles (ENPs): Unexplored Potential and Limitations,” Indian Journal of Biochemistry and Biophysics, vol. 59, no. 12, pp. 1163-1170, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[2] Keita Djibril Sekou, and Harshad Patel, “A Review on the Interaction Between Nanoparticles and Toxic Metals in Soil: Meta-Analysis of their Effects on Soil, Plants and Human Health,” Soil and Sediment Contamination: An International Journal, vol. 32, no. 4, pp. 417-447, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Wajhul Qamar et al., “An Insight into Impact of Nanomaterials Toxicity on Human Health,” PeerJ, vol. 12, pp. 1-45, 2024.
[CrossRef] [Google Scholar] [Publisher Link]
[4] A. Valeriano et al., “Predicting Cytotoxicity of Engineered Nanoparticles Using Regularized Regression Models: An in Silico Approach,” SAR and QSAR in Environmental Research, vol. 34, no. 7, pp. 591-604, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Robert A. Yokel, and Robert C. MacPhail, “Engineered Nanomaterials: Exposures, Hazards, and Risk Prevention,” Journal of Occupational Medicine and Toxicology, vol. 6, no. 1, pp. 1-27, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Edith Dube, and Grace Emily Okuthe, “Engineered Nanoparticles in Aquatic Systems: Toxicity and Mechanism of Toxicity in Fish,” Emerging Contaminants, vol. 9, no. 2, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Xiaoke Hu et al., “In Vitro Evaluation of Cytotoxicity of Engineered Metal Oxide Nanoparticles,” Science of the Total Environment, vol. 407, no. 8, pp. 3070-3072, 2009.
[CrossRef] [Google Scholar] [Publisher Link]
[8] N. Prajitha, S.S. Athira, and P.V. Mohanan, “Bio-Interactions and Risks of Engineered Nanoparticles,” Environmental Research, vol. 172, pp. 98-108, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Efaq Ali Noman et al., “Challenges and Opportunities in the Application of Bioinspired Engineered Nanomaterials for the Recovery of Metal Ions from Mining Industry Wastewater,” Chemosphere, vol. 308, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Gulsah Gul, Ramazan Yildirim, and Nazar Ileri-Ercan, “Cytotoxicity Analysis of Nanoparticles by Association Rule Mining,” Environmental Science: Nano, vol. 8, no. 4, pp. 937-949, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[11] Hagar I. Labouta et al., “Meta-Analysis of Nanoparticle Cytotoxicity via Data-Mining the Literature,” American Chemical Society Nano, vol. 13, no. 2, pp. 1583-1594, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[12] Virupaksha Bastikar, Alpana Bastikar, and Pramodkumar Gupta, Chapter 10 - Quantitative Structure-Activity Relationship-Based Computational Approaches, Computational Approaches for Novel Therapeutic and Diagnostic Designing to Mitigate SARS-CoV-2 Infection, Academic Press, pp. 191-205, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Moez Krichen, “Convolutional Neural Networks: A Survey,” Computers, vol. 12, no. 8, pp. 1-41, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[14] Yann LeCun et al., “Gradient-Based Learning Applied to Document Recognition,” Proceedings of the IEEE, vol. 86, no. 11, pp. 2278-2324, 1998.
[CrossRef] [Google Scholar] [Publisher Link]
[15] Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton, “ImageNet Classification with Deep Convolutional Neural Networks,” Advances in Neural Information Processing Systems, vol. 25, pp. 1097-1105, 2012.
[Google Scholar] [Publisher Link]
[16] Kaiming He et al., “Deep Residual Learning for Image Recognition,” 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 770-778, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[17] Mingxing Tan, and Quoc Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” ArXiv Preprint, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[18] Daniel Jimenez-Carretero et al., “Tox_(R)CNN: Deep Learning-Based Nuclei Profiling Tool for Drug Toxicity Screening,” PLOS Computational Biology, vol. 14, no. 11, pp. 1-23, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[19] Sebastian Raschka, and Benjamin Kaufman, “Machine Learning and AI-Based Approaches for Bioactive Ligand Discovery and GPCR-Ligand Recognition,” Methods, vol. 180, pp. 89-110, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[20] Wenjing Guo et al., “Review of Machine Learning and Deep Learning Models for Toxicity Prediction,” Experimental Biology and Medicine, vol. 248, no. 21, pp. 1-22, 2023.
[Google Scholar] [Publisher Link]
[21] Y-Lan Boureau, Jean Ponce, and Yann Lecun, “A Theoretical Analysis of Feature Pooling in Visual Recognition,” Proceedings of the 27th International Conference on Machine Learning, Haifa, Israel, 2010.
[Google Scholar] [Publisher Link]
[22] Afia Zafar et al., “A Comparison of Pooling Methods for Convolutional Neural Networks,” Applied Sciences, vol. 12, no. 17, pp. 1-21, 2022.
[CrossRef] [Google Scholar] [Publisher Link]
[23] Dingjun Yu et al., “Mixed Pooling for Convolutional Neural Networks,” International Conference on Rough Sets and Knowledge Technology, Shanghai, China, pp. 364-375, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[24] Zenglin Shi, Yangdong Ye, and Yunpeng Wu, “Rank-Based Pooling for Deep Convolutional Neural Networks,” Neural Networks, vol. 83, pp. 21-31, 2016.
[CrossRef] [Google Scholar] [Publisher Link]
[25] Shuangfei Zhai et al., “S3Pool: Pooling with Stochastic Spatial Sampling,” 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 4970-4978, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[26] Manli Sun et al., “Learning Pooling for Convolutional Neural Network,” Neurocomputing, vol. 224, pp. 96-104, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[27] Min Lin, Qiang Chen, and Shuicheng Yan, “Network In Network,” ArXiv Preprint, 2013.
[CrossRef] [Google Scholar] [Publisher Link]
[28] Vincent Christlein et al., “Deep Generalized Max Pooling,” 2019 International Conference on Document Analysis and Recognition (ICDAR), Sydney, NSW, Australia, pp. 1090-1096, 2019.
[CrossRef] [Google Scholar] [Publisher Link]
[29] Ka-Hou Chan, Giovanni Pau, and Sio-Kei Im, “Chebyshev Pooling: An Alternative Layer for the Pooling of CNNs-Based Classifier,” IEEE 4th International Conference on Computer and Communication Engineering Technology, Beijing, China, pp. 106-110, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[30] Pravendra Singh, Prem Raj, and Vinay P. Namboodiri, “EDS Pooling Layer,” Image and Vision Computing, vol. 98, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[31] Yash More, Kunal Dumbre, and Bahubali Shiragapur, “Horizontal Max Pooling a Novel Approach for Noise Reduction in Max Pooling for Better Feature Detect,” 2023 International Conference on Emerging Smart Computing and Informatics (ESCI), Pune, India, pp. 1-5, 2023.
[CrossRef] [Google Scholar] [Publisher Link]
[32] Geoffrey E. Hinton et al., “Improving Neural Networks by Preventing Co-Adaptation of Feature Detectors,” ArXiv Preprint, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[33] Diederik P. Kingma, and Jimmy Ba, “Adam: A Method for Stochastic Optimization,” ArXiv Preprint, 2014.
[CrossRef] [Google Scholar] [Publisher Link]