EUVIMEDEUVIMED entdecken
Crossref

A deep learning based multi-model approach for predicting drug-like chemical compound’s toxicity

Konda Mani Saravanan, Jiang-Fan Wan, Liujiang Dai, Jiajun Zhang, John Z H Zhang, Haiping Zhang

Methods · 2024

DOI: 10.1016/j.ymeth.2024.04.020 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Methods, 2024. Verfasst von Konda Mani Saravanan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biotechnology, Bharath Institute of Higher Education and Research, Chennai 600073, Tamil Nadu, India. Hauptthemen laut MEDLINE: Deep Learning. Die Arbeit wurde bisher 26-mal zitiert (Crossref) und nennt 48 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Shenzhen Key Laboratory Formation Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Ensuring the safety and efficacy of chemical compounds is crucial in small-molecule drug development. In the later stages of drug development, toxic compounds pose a significant challenge, losing valuable resources and time. Early and accurate prediction of compound toxicity using deep learning models offers a promising solution to mitigate these risks during drug discovery. In this study, we present the development of several deep-learning models aimed at evaluating different types of compound toxicity, including acute toxicity, carcinogenicity, hERG_cardiotoxicity (the human ether-a-go-go related gene caused cardiotoxicity), hepatotoxicity, and mutagenicity. To address the inherent variations in data size, label type, and distribution across different types of toxicity, we employed diverse training strategies. Our first approach involved utilizing a graph convolutional network (GCN) regression model to predict acute toxicity, which achieved notable performance with Pearson R 0.76, 0.74, and 0.65 for intraperitoneal, intravenous, and oral administration routes, respectively. Furthermore, we trained multiple GCN binary classification models, each tailored to a specific type of toxicity. These models exhibited high area under the curve (AUC) scores, with an impressive AUC of 0.69, 0.77, 0.88, and 0.79 for predicting carcinogenicity, hERG_cardiotoxicity, mutagenicity, and hepatotoxicity, respectively. Additionally, we have used the approved drug dataset to determine the appropriate threshold value for the prediction score in model usage. We integrated these models into a virtual screening pipeline to assess their effectiveness in identifying potential low-toxicity drug candidates. Our findings indicate that this deep learning approach has the potential to significantly reduce the cost and risk associated with drug development by expediting the selection of compounds with low toxicity profiles. Therefore, the models developed in this study hold promise as critical tools for early drug candidate screening and selection.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningHumansDrug DiscoveryAnimalsDrug-Related Side Effects and Adverse ReactionsCardiotoxicity

Stichwörter der Autor:innen

Deep learning modelsDrug screeningMulti-model approachSmall moleculesToxicity prediction

Autor:innen und Institutionen

  • Department of Biotechnology, Bharath Institute of Higher Education and Research, Chennai 600073, Tamil Nadu, India.
  • Guangdong-Hong Kong-Macao Greater Bay Area Center for Drug Evaluation and Inspection of NMPA, Shenzhen 518000, China.
  • Guangdong Immune Cell Therapy Engineering and Technology Research Center, Center for Protein and Cell-Based Drugs, Institute of Biomedicine and Biotechnology, Shenzhen Institute of Advanced Technology, Chinese Academy o…
  • Faculty of Synthetic Biology and Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China; College of Science, Hunan University of Technology and Bu…
  • Faculty of Synthetic Biology and Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China.
  • Faculty of Synthetic Biology and Institute of Synthetic Biology, Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen 518055, China. Electronic address: hp.zhang@siat.ac.cn.

Förderung

  • National Natural Science Foundation of China
  • Shenzhen Key Laboratory Formation Project

Zitieren

APA

Saravanan, K. M., Wan, J. F., Dai, L., Zhang, J., Zhang, J. Z. H., & Zhang, H. (2024). A deep learning based multi-model approach for predicting drug-like chemical compound’s toxicity. Methods. https://doi.org/10.1016/j.ymeth.2024.04.020

Vancouver

Saravanan KM, Wan JF, Dai L, Zhang J, Zhang JZH, Zhang H. A deep learning based multi-model approach for predicting drug-like chemical compound’s toxicity. Methods. 2024. doi:10.1016/j.ymeth.2024.04.020

BibTeX
@article{Saravanan2024,
  author = {Saravanan, Konda Mani and Wan, Jiang-Fan and Dai, Liujiang and Zhang, Jiajun and Zhang, John Z H and Zhang, Haiping},
  title = {A deep learning based multi-model approach for predicting drug-like chemical compound’s toxicity},
  journal = {Methods},
  year = {2024},
  doi = {10.1016/j.ymeth.2024.04.020}
}
Kostenlos starten →