Publication Details

Category Text Publication
Reference Category Journals
DOI 10.1038/s42004-021-00528-9
Licence creative commons licence
Title (Primary) Exploring the octanol-water partition coefficient dataset using deep learning techniques and data augmentation
Author Ulrich, N.; Goss, K.U.; Ebert, A.
Journal Communications Chemistry
Year 2021
Department OEC; AUC
Volume 4
Page From art. 90
Language englisch
Topic T9 Healthy Planet
Supplements https://static-content.springer.com/esm/art%3A10.1038%2Fs42004-021-00528-9/MediaObjects/42004_2021_528_MOESM1_ESM.pdf
Abstract Today more and more data are freely available. Based on these big datasets deep neural networks (DNNs) rapidly gain relevance in computational chemistry. Here, we explore the potential of DNNs to predict chemical properties from chemical structures. We have selected the octanol-water partition coefficient (log P) as an example, which plays an essential role in environmental chemistry and toxicology but also in chemical analysis. The predictive performance of the developed DNN is good with an rmse of 0.47‚ÄČlog units in the test dataset and an rmse of 0.33 for an external dataset from the SAMPL6 challenge. To this end, we trained the DNN using data augmentation considering all potential tautomeric forms of the chemicals. We further demonstrate how DNN models can help in the curation of the log P dataset by identifying potential errors, and address limitations of the dataset itself.
Persistent UFZ Identifier https://www.ufz.de/index.php?en=20939&ufzPublicationIdentifier=24737
Ulrich, N., Goss, K.U., Ebert, A. (2021):
Exploring the octanol-water partition coefficient dataset using deep learning techniques and data augmentation
Comm. Chem. 4 , art. 90