Structural alerts for the prediction of drug toxicity: a mini-review
DOI:
https://doi.org/10.60988/p.v37i2S.249Keywords:
structural alerts; toxicity prediction; drug discovery; machine learning; molecular reactivityAbstract
An essential part of drug research and development is the prediction of drug toxicity, which aims at recognizing possible hazards early on. Toxicophores, another name for structural alerts, are functional groups or molecular substructures linked to harmful biological effects. In computational toxicology, these signals are frequently used to forecast the possible toxicity of drug candidates. This mini-review explores structural alerts and their relevance in forecasting drug toxicity. We discuss the design and implementation of structural alert systems, their integration with machine learning and quantitative structure-activity relationship models, and their limitations, including the risk of over-prediction and the requirement for contextual interpretation. In addition, we discuss recent advances in the field, such as the incorporation of mechanistic insights and the use of large-scale toxicity databases. While structural alerts are still a useful technique for predicting toxicity, their effectiveness is increased when supplemented with other computational and experimental methodologies in order to provide a more thorough assessment of medication safety. This mini-review emphasizes the significance of structural alerts in guiding drug design and reducing the risk of toxicity within the preclinical development.
References
1. Hua Y., Cui X., Liu B., Shi Y., Guo H., Zhang R., et al. SApredictor: an expert system for screening chemicals against structural alerts. Front. Chem. 10, 916614, 2022. DOI: 10.3389/fchem.2022.916614
2. Yang H., Lou C., Li W., Liu G., Tang Y. Computational approaches to identify structural alerts and their applications in environmental toxicology and drug discovery. Chem. Res. Toxicol. 33(6), 1312–1322, 2020. DOI: 10.1021/acs.chemrestox.0c00006
3. Limban C., Nuţă D.C., Chiriţă C., Negreș S., Arsene A.L., Goumenou M., et al. The use of structural alerts to avoid the toxicity of pharmaceuticals. Toxicol. Rep. 5: 943–953, 2018. DOI: 10.1016/j.toxrep.2018.08.017
4. Liu R., Yu X., Wallqvist A. Data-driven identification of structural alerts for mitigating the risk of drug-induced human liver injuries. J. Cheminform. 7, 4, 2015. DOI: 10.1186/s13321-015-0053-y
5. Cremer J., Medrano Sandonas L., Tkatchenko A., Clevert D.A., De Fabritiis G. Equivariant graph neural networks for toxicity prediction. Chem. Res. Toxicol. 36(10), 1561–1573, 2023. DOI: 10.1021/acs.chemrestox.3c00032
6. Wedlake A.J. Structure-based predictions for molecular initiating events. PhD Thesis. Cambridge: University of Cambridge, 2019. DOI: 10.17863/CAM.44741
7. Honma M. An assessment of mutagenicity of chemical substances by (quantitative) structure-activity relationship. Genes Environ. 42, 23, 2020. DOI: 10.1186/s41021-020-00163-1
8. Baranwal M., Magner A., Elvati P., Saldinger J., Violi A., Hero A.O. A deep learning architecture for metabolic pathway prediction. Bioinformatics 36(8), 2547–2553, 2020. DOI: 10.1093/bioinformatics/btz954
9. Choo M.Z.Y., Chai C.L.L. The polypharmacology of natural products in drug discovery and development. Annu. Rep. Med. Chem. 61, 55–100, 2023. DOI: 10.1016/bs.armc.2023.10.002
