Title: Predicting Ionic Liquid Toxicity with Graph Attention Networks

Abstract: Ionic liquid toxicity is a major cause of morbidity and mortality worldwide. However, determining the toxicity of ionic liquids is still a challenge for the industry. In this study, we propose a graph attention network (GAT) based framework specifically adapted for predicting ionic liquid toxicity using graph-based molecular representations. In order to improve the model’s accuracy, we added physicochemical descriptors and hyperparameter optimization using the Optuna framework. In addition, Grad-CAM (gradient-weighted class activation mapping) visualizations and permutation feature importance analysis were employed to visualize the significance of the nodes and edges in the graphs. Experimental results demonstrate that the EnhancedGAT achieves lower prediction errors and stronger correlations compared to traditional baselines, indicating high predictive reliability.

Keywords: Ionic liquids, Toxicity prediction, Graph Attention Network, Molecular graphs, Physiochemical descriptors, Permutation feature importance

• N. V. Plechkova and K. R. Seddon, “Applications of ionic liquids in the chemical industry,” Chemical Society Reviews, vol. 37, no. 1, pp. 123–150, 2008.
• G. A. Tabaaza, B. N. Tackie-Otoo, D. B. Zaini, D. A. Otchere, and B. Lal, “Application of machine learning models to predict cytotoxicity of ionic liquids using volsurf principal properties,” Computational Toxicology, vol. 26, p. 100266, 2023.
• N. Abramenko, L. Kustov, L. Metelytsia, V. Kovalishyn, I. Tetko, and W. Peijnenburg, “A review of recent advances towards the development of qsar models for toxicity assessment of ionic liquids,” Journal of hazardous materials, vol. 384, p. 121429, 2020.
• C. N. Cavasotto and V. Scardino, “Machine learning toxicity prediction: latest advances by toxicity end point,” ACS omega, vol. 7, no. 51, pp. 47 536–47 546, 2022.
• A. Narin and Y. Isler, “Detection of new coronavirus disease from chest x-ray images using pre-trained convolutional neural networks,” Journal of the Faculty of Engineering and Architecture of Gazi UniversityKnowledge-Based Systems, vol. 36214, pp. 2095–2 107 106 685, 2021.
• M. Surucu, Y. Isler, M. Perc, and R. Kara, “Convolutional neural networks predict the onset of paroxysmal atrial fibrillation: Theory and applications,” Chaos: An Interdisciplinary Journal of Nonlinear ScienceKnowledge-Based Systems, vol. 31214, p. 11311906685, 2021.
• M. Surucu, Y. Isler, and R. Kara, “Diagnosis of paroxysmal atrial fibrillation from thirty-minute heart rate variability data using convolutional neural networks,” Turkish Journal of Electrical Engineering & Computer Science, vol. 2914, pp. 2886–2 900 106 685, 2021.
• J. Gilmer, S. S. Schoenholz, P. F. Riley, O. Vinyals, and G. E. Dahl, “Neural message passing for quantum chemistry,” in International conference on machine learning. PMLR, 2017, pp. 1263–1272.
• Z. Xiong, D. Wang, X. Liu, F. Zhong, X. Wan, X. Li, Z. Li, X. Luo, K. Chen, H. Jiang et al., “Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism,” Journal of medicinal chemistry, vol. 63, no. 16, pp. 8749–8760, 2019.
• L. Xu, T. Zhang, K. Lin, and Y. Wang, “Comparative evaluation of graph neural networks in molecular property prediction,” Biomolecules, vol. 13, no. 2, p. 298, 2023.
• Y. Cai, H. Liu, and W. Chen, “Gat-based interpretable learning for biomedical molecular property prediction,” IEEE Journal of Biomedical and Health Informatics, vol. 29, no. 1, p. 112–123, 2025.
• P. Velickovic, G. Cucurull, A. Casanova, A. Romero, P. Lio, Y. Bengio et al., “Graph attention networks,” stat, vol. 1050, no. 20, pp. 10–48 550, 2017.
• R. Ketkar, Y. Liu, H. Wang, and H. Tian, “A benchmark study of graph models for molecular acute toxicity prediction,” International Journal of Molecular Sciences, vol. 24, no. 15, p. 11966, 2023.
• B. Chen, R. Barzilay, and T. Jaakkola, “Path-augmented graph transformer network,” arXiv preprint arXiv:1905.12712, 2019.
• W. Ahmad, Z. Wang, X. Liu, F. Xu, B. Chang, and et al., “Chemberta: Large-scale self-supervised pretraining for molecular property prediction,” arXiv preprint, vol. arXiv:2010.09885, 2021.
• G. Chen, Z. Song, Z. Qi, and K. Sundmacher, “Generalizing property prediction of ionic liquids from limited labeled data: a one-stop framework empowered by transfer learning,” Digital Discovery, vol. 2, no. 3, pp. 591–601, 2023.
• S. Sadaghiyanfam, H. Kamberaj, and Y. Isler, “Enhanced prediction of ionic liquid toxicity using a meta-ensemble learning framework with data augmentation,” Artificial Intelligence Chemistry, vol. 3, no. 1, p. 100087, 2025.
• S. Sadaghiyanfam, H. Kamberaj, and Y. Isler, “Leveraging chemberta and machine learning for accurate toxicity prediction of ionic liquids,” Journal of the Taiwan Institute of Chemical Engineers, vol. 171, p. 106030, 2025.
• G. Landrum, “RDKit: Open-source cheminformatics,” 2006, http://www.rdkit.org.
• T. Akiba, S. Sano, T. Yanase, T. Ohta, and M. Koyama, “Optuna: A next-generation hyperparameter optimization framework,” in Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 2019, pp. 2623–2631.
• Y. Isler, U. Ozturk, and E. Sayilgan, “A new sample reduction method for decreasing the running time of the k-nearest neighbors algorithm to diagnose patients with congestive heart failure: backward iterative elimination,” Sadhana, vol. 48, p. 35, 2023.
• V. Svetnik, A. Liaw, C. Tong, J. C. Culberson, R. P. Sheridan, and B. P. Feuston, “Random forest: a classification and regression tool for compound classification and qsar modeling,” Journal of chemical information and computer sciences, vol. 43, no. 6, pp. 1947–1958, 2003.
• E. Byvatov, U. Fechner, J. Sadowski, and G. Schneider, “Comparison of support vector machine and artificial neural network systems for drug/nondrug classification,” Journal of chemical information and computer sciences, vol. 43, no. 6, pp. 1882–1889, 2003.
• R. R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, and D. Batra, “Grad-cam: Visual explanations from deep networks via gradient-based localization,” in Proceedings of the IEEE international conference on computer vision, 2017, pp. 618–626.
• L. Breiman, “Random forests,” Machine learning, vol. 45, pp. 5–32, 2001.
• F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg et al., “Scikit-learn: Machine learning in python,” the Journal of machine Learning research, vol. 12, pp. 2825–2830, 2011.