Abstract
Knowledge about certain features of molecules is crucial in many fields such as drug design. Toxicity of a compound gives information on the degree to which it can be harmful to a living organism. Experimental evaluation of a molecule’s toxicity requires specialised staff and equipment and generates high costs. Deep learning is a tool used in many fields and can also be helpful in the case of predicting the molecule’s toxicity. For the dataset we used a free database called ‘SMILES Toxicity’ which is available on kaggle. This dataset consists of 6698 non-toxic molecules and 964 toxic ones. Its imbalance creates the problem called ‘overfitting’. In this article, we describe several methods for overcoming the overfitting problem. We developed two models with well-balanced true positives to false positives ratio. With the first model, we achieved 96% accuracy on the training set, 89% on the validation set and 65% on the test set. The second model scored the following values of accuracy: 80% on the training set, 78% on the validation set and 77% on the test set.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Parasuraman, S.: Toxicological screening. J. Pharmacol. Pharmacotherap. 2(2), 74–79, (2011)
Chen, J., Cheong, H.-H., Siu, S.W.I.: BESTox: a convolutional neural network regression model based on binary-encoded SMILES for acute oral toxicity prediction of chemical compounds. In: Martín-Vide, C., Vega-Rodríguez, M.A., Wheeler, T. (eds.) AlCoB 2020. LNCS, vol. 12099, pp. 155–166. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-42266-0_12
Karim, A.: Toxicity prediction by multimodal deep learning. In: Ohara, K., Bai, Q. (eds.) Knowledge Management and Acquisition for Intelligent Systems, pp. 142–152. Springer International Publishing, Cham (2019)
Hirohara, M., Saito, Y., Koda, Y., Sato, K., Sakakibara, Y.: Convolutional neural network based on smiles representation of compounds for detecting chemical motif. In: Proceedings of the 29th International Conference on Genome Informatics (GIW 2018): Bioinformatics, vol. 19. BMC Bioinformatics (2018)
Fanconi, C.: Smiles toxicity, August 2019. https://www.kaggle.com/fanconic/smiles-toxicity
Smith, L.N.: Cyclical learning rates for training neural networks. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 464–472 (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Duraj, K.M., Piaseczna, N.J. (2022). Predicting Molecule Toxicity Using Deep Learning. In: Piaseczna, N., Gorczowska, M., Łach, A. (eds) Innovations and Developments of Technologies in Medicine, Biology and Healthcare. EMBS ICS 2020. Advances in Intelligent Systems and Computing, vol 1360. Springer, Cham. https://doi.org/10.1007/978-3-030-88976-0_3
Download citation
DOI: https://doi.org/10.1007/978-3-030-88976-0_3
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-88975-3
Online ISBN: 978-3-030-88976-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)