Regression model (regression)
Open in:QDB ExplorerQDB Predictor
Name | Type | n |
R2 |
σ |
---|---|---|---|---|
Training set | training | 134 | 0.666 | 0.588 |
Validation set | external validation | 44 | 0.636 | 0.604 |
External validation set | external validation | 60 | 0.634 | 0.630 |
Regression model (regression)
Open in:QDB ExplorerQDB Predictor
Name | Type | n |
R2 |
σ |
---|---|---|---|---|
Training set | training | 134 | 0.626 | 0.612 |
Validation set | external validation | 44 | 0.611 | 0.615 |
External validation set | external validation | 60 | 0.559 | 0.650 |
Regression model (regression)
Open in:QDB ExplorerQDB Predictor
Name | Type | n |
R2 |
σ |
---|---|---|---|---|
Training set | training | 134 | 0.731 | 0.598 |
Validation set | external validation | 44 | 0.632 | 0.706 |
External validation set | external validation | 60 | 0.704 | 0.565 |
Regression model (regression)
Open in:QDB ExplorerQDB Predictor
Name | Type | n |
R2 |
σ |
---|---|---|---|---|
Training set | training | 134 | 0.762 | 0.594 |
Validation set | external validation | 44 | 0.719 | 0.646 |
External validation set | external validation | 60 | 0.712 | 0.582 |
Regression model (regression)
Open in:QDB ExplorerQDB Predictor
Name | Type | n |
R2 |
σ |
---|---|---|---|---|
Training set | training | 134 | 0.753 | 0.580 |
Validation set | external validation | 44 | 0.704 | 0.635 |
External validation set | external validation | 60 | 0.596 | 0.606 |
Regression model (regression)
Open in:QDB ExplorerQDB Predictor
Name | Type | n |
R2 |
σ |
---|---|---|---|---|
Training set | training | 134 | 0.745 | 0.957 |
Validation set | external validation | 44 | 0.757 | 0.911 |
External validation set | external validation | 60 | 0.645 | 0.827 |
Regression model (classification)
Open in:QDB ExplorerQDB Predictor
Name | Type | n | Accuracy |
---|---|---|---|
Training set | training | 134 | 0.903 |
Validation set | external validation | 44 | 0.909 |
External validation set | external validation | 60 | 0.900 |
Regression model (classification)
Open in:QDB ExplorerQDB Predictor
Name | Type | n | Accuracy |
---|---|---|---|
Training set | training | 134 | 0.866 |
Validation set | external validation | 44 | 0.750 |
External validation set | external validation | 60 | 0.783 |
Regression model (classification)
Open in:QDB ExplorerQDB Predictor
Name | Type | n | Accuracy |
---|---|---|---|
Training set | training | 134 | 0.918 |
Validation set | external validation | 44 | 0.909 |
External validation set | external validation | 60 | 0.817 |
Regression model (classification)
Open in:QDB ExplorerQDB Predictor
Name | Type | n | Accuracy |
---|---|---|---|
Training set | training | 134 | 0.933 |
Validation set | external validation | 44 | 0.932 |
External validation set | external validation | 60 | 0.750 |
Regression model (classification)
Open in:QDB ExplorerQDB Predictor
Name | Type | n | Accuracy |
---|---|---|---|
Training set | training | 134 | 0.933 |
Validation set | external validation | 44 | 0.909 |
External validation set | external validation | 60 | 0.817 |
Regression model (classification)
Open in:QDB ExplorerQDB Predictor
Name | Type | n | Accuracy |
---|---|---|---|
Training set | training | 134 | 0.918 |
Validation set | external validation | 44 | 0.886 |
External validation set | external validation | 60 | 0.833 |
When using this QDB archive, please cite (see details) it together with the original article:
Oja, M.; Maran, U. Data for: pH-permeability profiles for drug substances: Experimental detection, comparison with human intestinal absorption and modelling. QsarDB repository, QDB.203. 2018. https://doi.org/10.15152/QDB.203
Oja, M.; Maran, U. pH-permeability profiles for drug substances: Experimental detection, comparison with human intestinal absorption and modelling. Eur. J. Pharm. Sci. 2018, 123, 429-440. https://doi.org/10.1016/j.ejps.2018.07.014
Title: | Oja, M.; Maran, U. pH-permeability profiles for drug substances: Experimental detection, comparison with human intestinal absorption and modelling. Eur. J. Pharm. Sci. 2018, 123, 429-440. |
Abstract: | The influence of pH on human intestinal absorption is frequently not considered in early drug discovery studies in the modelling and subsequent prediction of intestinal absorption for drug candidates. To bridge this gap, in this study, experimental membrane permeability data were measured for current and former drug substances with a parallel artificial membrane permeability assay (PAMPA) at different pH values (3, 5, 7.4 and 9). The presented data are in good agreement with human intestinal absorption, showing a clear influence of pH on the efficiency of intestinal absorption. For the measured data, simple and general quantitative structure-activity relationships (QSARs) were developed for each pH that makes it possible to predict the pH profiles for passive membrane permeability (i.e., a pH-permeability profile), and these predictions coincide well with the experimental data. QSARs are also proposed for the data series of highest and intrinsic membrane permeability. The molecular descriptors in the models were analysed and mechanistically related to the interaction pattern of permeability in membranes. In addition to the regression models, classification models are also proposed. All models were successfully validated and blind tested with external data. |
URI: | http://hdl.handle.net/10967/203
http://dx.doi.org/10.15152/QDB.203 |
Date: | 2018-07-06 |
Funding: | This work was supported by the Ministry of Education and Research, Republic of Estonia [grant number IUT34-14] and the European Union European Regional Development Fund [grant number TK143, Centre of Excellence in Molecular Cell Engineering]. |
Name | Description | Format | Size | View |
---|---|---|---|---|
2018EJPS429.zip | QSAR and classification models for membrane permeability | application/zip | 333.7Kb | View/ |