Research data supporting "Neural network activation similarity: A new measure to assist decision making in chemical toxicology"
View / Open Files
MetadataShow full item record
Allen, T., Wedlake, A., Gelzinyte, E., Gong, C., Goodman, J., Gutsell, S., & Russell, P. (2020). Research data supporting "Neural network activation similarity: A new measure to assist decision making in chemical toxicology" [Dataset]. https://doi.org/10.17863/CAM.50429
Datasets and codes for the recreation and deployment of predictive toxicology models developed to predict 79 human molecular initiating events (MIEs) using neural networks (DOI: 10.1039/D0SC01637C). Python codes are included to generate molecular fingerprints, generate chemical clusters, build models and recall those models. Model files generated during clustered cross-validation and for comparison to structural alerts and random forests are also included. Input biological data used in model construction is included for reference as complete datasets (Total), files divided as training and test for comparison to other models (Comparison), and clustered files used in clustered cross-validation (Clustered).
Python 3 Keras TensorFlow
Artificial Intelligence, Machine Learning, Predictive Toxicology, Molecular Initiating Event
Publication Reference: https://doi.org/10.1039/D0SC01637Chttps://www.repository.cam.ac.uk/handle/1810/307290
The authors acknowledge the financial support of Unilever.
This record's DOI: https://doi.org/10.17863/CAM.50429