Review
 
J Environ Sci Health C Environ Carcinog Ecotoxicol Rev. 2018;36(4):169-191.
 doi: 10.1080/10590501.2018.1537118. Epub 2019 Jan 10.
A review on machine learning methods for in silico toxicity prediction
Gabriel Idakwo[ ][1], Joseph Luttrell[ ][1], Minjun Chen[ ][2], Huixiao Hong[ ][2], Zhaoxian Zhou[ ][1], Ping Gong[ ][3], Chaoyang Zhang[ ][1]
Affiliations expand
 PMID: 30628866
 DOI: 10.1080/10590501.2018.1537118
Abstract
In silico toxicity prediction plays an important role in the regulatory decision making and selection of leads in drug design as in vitro/vivo methods are often limited by ethics, time, budget, and other resources. Many computational methods have been employed in predicting the toxicity profile of chemicals. This review provides a detailed end-to-end overview of the application of machine learning algorithms to Structure-Activity Relationship (SAR)-based predictive toxicology. From raw data to model validation, the importance of data quality is stressed as it greatly affects the predictive power of derived models. Commonly overlooked challenges such as data imbalance, activity cliff, model evaluation, and definition of applicability domain are highlighted, and plausible solutions for alleviating these challenges are discussed.
Keywords: Toxicity prediction; machine learning; model reliability; molecular descriptors; prediction accuracy; structure-activity relationship.
Similar articles
 Machine learning models for predicting endocrine disruption potential of environmental chemicals.
      Chierici M, Giulini M, Bussola N, Jurman G, Furlanello C.J Environ Sci Health C Environ Carcinog Ecotoxicol Rev. 2018;36(4):237-251. doi: 10.1080/10590501.2018.1537155. Epub 2019 Jan 10.PMID: 30628533
 Target-specific toxicity knowledgebase (TsTKb): a novel toolkit for in silico predictive toxicology.
      Li Y, Idakwo G, Thangapandian S, Chen M, Hong H, Zhang C, Gong P.J Environ Sci Health C Environ Carcinog Ecotoxicol Rev. 2018;36(4):219-236. doi: 10.1080/10590501.2018.1537148. Epub 2018 Nov 14.PMID: 30426823
 In Silico Prediction of Chemical-Induced Hepatocellular Hypertrophy Using Molecular Descriptors.
      Ambe K, Ishihara K, Ochibe T, Ohya K, Tamura S, Inoue K, Yoshida M, Tohkin M.Toxicol Sci. 2018 Apr 1;162(2):667-675. doi: 10.1093/toxsci/kfx287.PMID: 29309657
 Deep learning for predicting toxicity of chemicals: a mini review.
      Tang W, Chen J, Wang Z, Xie H, Hong H.J Environ Sci Health C Environ Carcinog Ecotoxicol Rev. 2018;36(4):252-271. doi: 10.1080/10590501.2018.1537563. Epub 2019 Mar 1.PMID: 30821199 Review.
 Computational prediction models for assessing endocrine disrupting potential of chemicals.
      Sakkiah S, Guo W, Pan B, Kusko R, Tong W, Hong H.J Environ Sci Health C Environ Carcinog Ecotoxicol Rev. 2018;36(4):192-218. doi: 10.1080/10590501.2018.1537132. Epub 2019 Jan 11.PMID: 30633647 Review.
Show more similar articles See all similar articles
Cited by 3 articles
 Computational Models Using Multiple Machine Learning Algorithms for Predicting Drug Hepatotoxicity with the DILIrank Dataset.
      Ancuceanu R, Hovanet MV, Anghel AI, Furtunescu F, Neagu M, Constantin C, Dinu M.Int J Mol Sci. 2020 Mar 19;21(6):2114. doi: 10.3390/ijms21062114.PMID: 32204453 Free PMC article.
 Use of QSAR Global Models and Molecular Docking for Developing New Inhibitors of c-src Tyrosine Kinase.
      Ancuceanu R, Tamba B, Stoicescu CS, Dinu M.Int J Mol Sci. 2019 Dec 18;21(1):19. doi: 10.3390/ijms21010019.PMID: 31861445 Free PMC article.
 Nano-(Q)SAR for Cytotoxicity Prediction of Engineered Nanomaterials.
      Buglak AA, Zherdev AV, Dzantiev BB.Molecules. 2019 Dec 11;24(24):4537. doi: 10.3390/molecules24244537.PMID: 31835808 Free PMC article. Review.
Publication types
 Research Support, U.S. Gov't, Non-P.H.S.
 Review
MeSH terms
 Algorithms
 
 Computer Simulation
 
 Environmental Pollutants / toxicity*
 
 Machine Learning
 
 Quantitative Structure-Activity Relationship
 
 Support Vector Machine
 
 Toxicity Tests / methods*
Substances
 Environmental Pollutants
 
LinkOut - more resources
 Full Text Sources
       Taylor & Francis
 Miscellaneous
       NCI CPTAC Assay Portal

