Logo PTI Logo FedCSIS

Communication Papers of the 19th Conference on Computer Science and Intelligence Systems (FedCSIS)

Annals of Computer Science and Information Systems, Volume 41

Toxic Molecule Classification Using Graph Neural Networks and Few Shot Learning.

, , ,

DOI: http://dx.doi.org/10.15439/2024F3810

Citation: Communication Papers of the 19th Conference on Computer Science and Intelligence Systems (FedCSIS), M. Bolanowski, M. Ganzha, L. Maciaszek, M. Paprzycki, D. Ślęzak (eds). ACSIS, Vol. 41, pages 105–110 ()

Full text

Abstract. Traditional methods like Graph Convolutional Networks (GCNs) face challenges with limited data and class imbalance, leading to suboptimal performance in graph classification tasks during toxicity prediction of molecules as a whole. To address these issues, we harness the power of Graph Isomorphic Networks, Multi Headed Attention and Free Large-scale Adversarial Augmentation separately on Graphs for precisely capturing the structural data of molecules and their toxicological properties. Additionally, we incorporate Few-Shot Learning to improve the model's generalization with limited annotated samples. Extensive experiments on a diverse toxicology dataset demonstrate that our method achieves an impressive state-of-art AUC-ROC value of 0.816, surpassing the baseline GCN model by 11.4\%. This highlights the significance of our proposed methodology and Few Shot Learning in advancing Toxic Molecular Classification, with the potential to enhance drug discovery and environmental risk assessment processes

References

  1. Y. Jiang, D.-W. Sun, H. Pu, and Q. Wei, “Surface enhanced raman spectroscopy (sers): A novel reliable technique for rapid detection of common harmful chemical residues,” Trends in Food Science & Technology, vol. 75, pp. 10–22, 2018. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0924224417307045
  2. M. E. E. Alahi and S. C. Mukhopadhyay, “Detection methodologies for pathogen and toxins: A review,” Sensors, vol. 17, no. 8, 2017. [Online]. Available: https://www.mdpi.com/1424-8220/17/8/1885
  3. O. Vinyals, C. Blundell, T. P. Lillicrap, K. Kavukcuoglu, and D. Wierstra, “Matching networks for one shot learning,” CoRR, vol. abs/1606.04080, 2016. [Online]. Available: http://arxiv.org/abs/1606.04080
  4. C. Finn, P. Abbeel, and S. Levine, “Model-agnostic meta-learning for fast adaptation of deep networks,” CoRR, vol. abs/1703.03400, 2017. [Online]. Available: http://arxiv.org/abs/1703.03400
  5. N. Ma, J. Bu, J. Yang, Z. Zhang, C. Yao, Z. Yu, S. Zhou, and X. Yan, “Adaptivestep graph meta-learner for few-shot graph classification,” in Proceedings of the 29th ACM International Conference on Information & Knowledge Management, ser. CIKM ’20. New York, NY, USA: Association for Computing Machinery, 2020, p. 1055–1064. [Online]. Available: https://doi.org/10.1145/3340531.3411951
  6. R. C. Staudemeyer and E. R. Morris, “Understanding LSTM - a tutorial into long short-term memory recurrent neural networks,” CoRR, vol. abs/1909.09586, 2019. [Online]. Available: http://arxiv.org/abs/1909.09586
  7. T. N. Kipf and M. Welling, “Semi-supervised classification with graph convolutional networks,” in International Conference on Learning Representations, 2017. [Online]. Available: https://openreview.net/forum?id=SJU4ayYgl
  8. K. Xu, W. Hu, J. Leskovec, and S. Jegelka, “How powerful are graph neural networks?” CoRR, vol. abs/1810.00826, 2018. [Online]. Available: http://arxiv.org/abs/1810.00826
  9. K. Kong, G. Li, M. Ding, Z. Wu, C. Zhu, B. Ghanem, G. Taylor, and T. Goldstein, “Robust optimization as data augmentation for large-scale graphs,” 2022.
  10. A. Mayr, G. Klambauer, T. Unterthiner, and S. Hochreiter, “DeepTox: Toxicity prediction using deep learning,” Frontiers in Environmental Science, vol. 3, Feb. 2016. [Online]. Available: https://doi.org/10.3389/fenvs.2015.00080
  11. Z. Alperstein, A. Cherkasov, and J. T. Rolfe, “All SMILES VAE,” CoRR, vol. abs/1905.13343, 2019. [Online]. Available: http://arxiv.org/abs/1905.13343
  12. X. Jiang, P. Ji, and S. Li, “Censnet: Convolution with edge-node switching in graph neural networks,” in Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19. International Joint Conferences on Artificial Intelligence Organization, 7 2019, pp. 2656–2662. [Online]. Available: https://doi.org/10.24963/ijcai.2019/369
  13. G. Zhou, Z. Gao, Q. Ding, H. Zheng, H. Xu, Z. Wei, L. Zhang, and G. Ke, “Uni-mol: A universal 3d molecular representation learning framework,” May 2022. [Online]. Available: https://doi.org/10.26434/chemrxiv-2022-jjm0j
  14. J. Baek, M. Kang, and S. J. Hwang, “Accurate learning of graph representations with graph multiset pooling,” CoRR, vol. abs/2102.11533, 2021. [Online]. Available: https://arxiv.org/abs/2102.11533
  15. Z. Guo, C. Zhang, W. Yu, J. Herr, O. Wiest, M. Jiang, and N. V. Chawla, “Few-shot graph learning for molecular property prediction,” CoRR, vol. abs/2102.07916, 2021. [Online]. Available: https://arxiv.org/abs/2102.07916
  16. J. Chen, Y.-W. Si, C.-W. Un, and S. W. I. Siu, “Chemical toxicity prediction based on semi-supervised learning and graph convolutional neural network,” Journal of Cheminformatics, vol. 13, no. 1, Nov. 2021. [Online]. Available: https://doi.org/10.1186/s13321-021-00570-8
  17. C. Özdemir, “Avg-topk: A new pooling method for convolutional neural networks,” Expert Systems with Applications, vol. 223, p. 119892, 2023. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S0957417423003937
  18. N. T. Huang and S. Villar, “A short tutorial on the weisfeiler-lehman test and its variants,” in ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, jun 2021. [Online]. Available: https://doi.org/10.1109%2Ficassp39728.2021.9413523