Imperial College London
Portrait Picture

DrLeonBarron

Faculty of Medicine, School of Public Health

Reader in Analytical & Environmental Sciences
 
 
 
//

Contact

 

leon.barron

 
 
//

Location

 

Norfolk PlaceSt Mary's Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Miller:2019:10.1016/j.scitotenv.2018.08.122,
author = {Miller, TH and Gallidabino, MD and MacRae, JI and Owen, SF and Bury, NR and Barron, LP},
doi = {10.1016/j.scitotenv.2018.08.122},
journal = {Science of the Total Environment},
pages = {80--89},
title = {Prediction of bioconcentration factors in fish and invertebrates using machine learning},
url = {http://dx.doi.org/10.1016/j.scitotenv.2018.08.122},
volume = {648},
year = {2019}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The application of machine learning has recently gained interest from ecotoxicological fields for its ability to model and predict chemical and/or biological processes, such as the prediction of bioconcentration. However, comparison of different models and the prediction of bioconcentration in invertebrates has not been previously evaluated. A comparison of 24 linear and machine learning models is presented herein for the prediction of bioconcentration in fish and important factors that influenced accumulation identified. R2 and root mean square error (RMSE) for the test data (n=110 cases) ranged from 0.23–0.73 and 0.34–1.20, respectively. Model performance was critically assessed with neural networks and tree-based learners showing the best performance. An optimised 4-layer multi-layer perceptron (14 descriptors) was selected for further testing. The model was applied for cross-species prediction of bioconcentration in a freshwater invertebrate, Gammarus pulex. The model for G. pulex showed good performance with R2 of 0.99 and 0.93 for the verification and test data, respectively. Important molecular descriptors determined to influence bioconcentration were molecular mass (MW), octanol-water distribution coefficient (logD), topological polar surface area (TPSA) and number of nitrogen atoms (nN) among others. Modelling of hazard criteria such as PBT, showed potential to replace the need for animal testing. However, the use of machine learning models in the regulatory context has been minimal to date and is critically discussed herein. The movement away from experimental estimations of accumulation to in silico modelling would enable rapid prioritisation of contaminants that may pose a risk to environmental health and the food chain.
AU  - Miller,TH
AU  - Gallidabino,MD
AU  - MacRae,JI
AU  - Owen,SF
AU  - Bury,NR
AU  - Barron,LP
DO  - 10.1016/j.scitotenv.2018.08.122
EP  - 89
PY  - 2019///
SN  - 0048-9697
SP  - 80
TI  - Prediction of bioconcentration factors in fish and invertebrates using machine learning
T2  - Science of the Total Environment
UR  - http://dx.doi.org/10.1016/j.scitotenv.2018.08.122
UR  - https://www.sciencedirect.com/science/article/pii/S0048969718330869?via%3Dihub
UR  - http://hdl.handle.net/10044/1/85150
VL  - 648
ER  -
Download