10779/crick.11379798.v1
Thomas H Miller
Thomas H
Miller
Matteo D Gallidabino
Matteo D
Gallidabino
James R MacRae
James R
MacRae
Stewart F Owen
Stewart F
Owen
Nicolas R Bury
Nicolas R
Bury
Leon P Barron
Leon P
Barron
Prediction of bioconcentration factors in fish and invertebrates using machine learning
The Francis Crick Institute
2019
BCF
Bioconcentration
Machine learning
Modelling
PBT
Pharmaceutical
Amphipoda
Animals
Carps
Ecotoxicology
Environmental Exposure
Machine Learning
Models, Biological
Pharmaceutical Preparations
Water Pollutants, Chemical
MET
Environmental Sciences
2019-12-17 16:38:42
Journal contribution
https://crick.figshare.com/articles/journal_contribution/Prediction_of_bioconcentration_factors_in_fish_and_invertebrates_using_machine_learning/11379798
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.