In silico toxicology: comprehensive benchmarking of multi-label classification methods applied to chemical toxicity data
Name:
Raies_et_al-2017-Wiley_Interdisciplinary_Reviews__Computational_Molecular_Science.pdf
Size:
2.812Mb
Format:
PDF
Description:
Main article
Name:
wcms1352-sup-0001-AppendixS1.pdf
Size:
159.8Kb
Format:
PDF
Description:
Supplemental files
Name:
wcms1352-sup-0002-AppendixS2.pdf
Size:
1.370Mb
Format:
PDF
Description:
Supplemental files
Name:
wcms1352-sup-0003-AppendixS3.pdf
Size:
487.8Kb
Format:
PDF
Description:
Supplemental files
Type
ArticleAuthors
Raies, Arwa B.
Bajic, Vladimir B.

KAUST Department
Computational Bioscience Research Center (CBRC)Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Applied Mathematics and Computational Science Program
KAUST Grant Number
BAS/1/1606-01-01URF/1/1976-02
Date
2017-12-04Online Publication Date
2017-12-04Print Publication Date
2018-05Permanent link to this record
http://hdl.handle.net/10754/626320
Metadata
Show full item recordAbstract
One goal of toxicity testing, among others, is identifying harmful effects of chemicals. Given the high demand for toxicity tests, it is necessary to conduct these tests for multiple toxicity endpoints for the same compound. Current computational toxicology methods aim at developing models mainly to predict a single toxicity endpoint. When chemicals cause several toxicity effects, one model is generated to predict toxicity for each endpoint, which can be labor and computationally intensive when the number of toxicity endpoints is large. Additionally, this approach does not take into consideration possible correlation between the endpoints. Therefore, there has been a recent shift in computational toxicity studies toward generating predictive models able to predict several toxicity endpoints by utilizing correlations between these endpoints. Applying such correlations jointly with compounds' features may improve model's performance and reduce the number of required models. This can be achieved through multi-label classification methods. These methods have not undergone comprehensive benchmarking in the domain of predictive toxicology. Therefore, we performed extensive benchmarking and analysis of over 19,000 multi-label classification models generated using combinations of the state-of-the-art methods. The methods have been evaluated from different perspectives using various metrics to assess their effectiveness. We were able to illustrate variability in the performance of the methods under several conditions. This review will help researchers to select the most suitable method for the problem at hand and provide a baseline for evaluating new approaches. Based on this analysis, we provided recommendations for potential future directions in this area.Citation
Raies AB, Bajic VB (2017) In silico toxicology: comprehensive benchmarking of multi-label classification methods applied to chemical toxicity data. Wiley Interdisciplinary Reviews: Computational Molecular Science: e1352. Available: http://dx.doi.org/10.1002/wcms.1352.Sponsors
Research reported in this publication were supported by the King Abdullah University of Science and Technology (KAUST) (BAS/1/1606-01-01) and by the KAUST Office of Sponsored Research (OSR) under Awards No URF/1/1976-02.Publisher
WileyAdditional Links
http://onlinelibrary.wiley.com/doi/10.1002/wcms.1352/fullae974a485f413a2113503eed53cd6c53
10.1002/wcms.1352
Scopus Count
Except where otherwise noted, this item's license is described as This is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and
reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.