Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation
Deep neural networks are potent tools for computational chemistry, but experimental feed data can limit their reach. Here the authors develop deep neural network data augmentation models to predict octanol–water partition coefficients (log P) of a variety of tautomers.
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Publishing Group
2021-06-01
|
| Series: | Communications Chemistry |
| Online Access: | https://doi.org/10.1038/s42004-021-00528-9 |
| id |
doaj-9d61fbcad06746a6a19e36cf2342853f |
|---|---|
| record_format |
Article |
| spelling |
doaj-9d61fbcad06746a6a19e36cf2342853f2021-06-20T11:05:35ZengNature Publishing GroupCommunications Chemistry2399-36692021-06-014111010.1038/s42004-021-00528-9Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentationNadin Ulrich0Kai-Uwe Goss1Andrea Ebert2Department of Analytical Environmental Chemistry, Helmholtz Centre for Environmental Research—UFZDepartment of Analytical Environmental Chemistry, Helmholtz Centre for Environmental Research—UFZDepartment of Analytical Environmental Chemistry, Helmholtz Centre for Environmental Research—UFZDeep neural networks are potent tools for computational chemistry, but experimental feed data can limit their reach. Here the authors develop deep neural network data augmentation models to predict octanol–water partition coefficients (log P) of a variety of tautomers.https://doi.org/10.1038/s42004-021-00528-9 |
| collection |
DOAJ |
| language |
English |
| format |
Article |
| sources |
DOAJ |
| author |
Nadin Ulrich Kai-Uwe Goss Andrea Ebert |
| spellingShingle |
Nadin Ulrich Kai-Uwe Goss Andrea Ebert Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation Communications Chemistry |
| author_facet |
Nadin Ulrich Kai-Uwe Goss Andrea Ebert |
| author_sort |
Nadin Ulrich |
| title |
Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation |
| title_short |
Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation |
| title_full |
Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation |
| title_fullStr |
Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation |
| title_full_unstemmed |
Exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation |
| title_sort |
exploring the octanol–water partition coefficient dataset using deep learning techniques and data augmentation |
| publisher |
Nature Publishing Group |
| series |
Communications Chemistry |
| issn |
2399-3669 |
| publishDate |
2021-06-01 |
| description |
Deep neural networks are potent tools for computational chemistry, but experimental feed data can limit their reach. Here the authors develop deep neural network data augmentation models to predict octanol–water partition coefficients (log P) of a variety of tautomers. |
| url |
https://doi.org/10.1038/s42004-021-00528-9 |
| work_keys_str_mv |
AT nadinulrich exploringtheoctanolwaterpartitioncoefficientdatasetusingdeeplearningtechniquesanddataaugmentation AT kaiuwegoss exploringtheoctanolwaterpartitioncoefficientdatasetusingdeeplearningtechniquesanddataaugmentation AT andreaebert exploringtheoctanolwaterpartitioncoefficientdatasetusingdeeplearningtechniquesanddataaugmentation |
| _version_ |
1721370471803387904 |