Exploring Quantitative Structure-Activity Relationships (QSARs) of Non-Tri cyclic Cyclooxygenase-2 (COX-2) Inhibitors by MLR and PC-ANN
| dc.contributor.author | Omar Deeb | |
| dc.contributor.author | Zatari, N. | |
| dc.date.accessioned | 2018-08-13T14:00:57Z | |
| dc.date.available | 2018-08-13T14:00:57Z | |
| dc.date.issued | 2014-12-24 | |
| dc.description.abstract | Quantitative structure–activity relationship study using principal component artificial neural network (PC-ANN) methodology was conducted to predict the inhibitory activities expressed as pIC50 of 73 non-tri cyclic cyclooxygenase-2 (COX-2) inhibitors. The results obtained by MLR shows that the best two models are close to each other with regression coefficient of 0.85. These optimal models were further analyzed by PC-ANN and the best model obtained was with regression coefficient of 0.823 for the test set. The lowest prediction sum of squares (PRESS) value obtained for the prediction set is 4.727 which accounts for predictability of the model. Artificial neural networks provide improved models for heterogeneous data sets without splitting them into families. Both the external and cross-validation methods are used to validate the performances of the resulting models. Randomization test is employed to check the suitability of the models. | en_US |
| dc.identifier.issn | 2321-807X | |
| dc.identifier.uri | https://dspace.alquds.edu/handle/20.500.12213/734 | |
| dc.language.iso | en_US | en_US |
| dc.publisher | Council for Innovative Research | en_US |
| dc.subject | QSAR | en_US |
| dc.subject | MLR | en_US |
| dc.subject | PC- ANN | en_US |
| dc.subject | Non-tri cyclic cyclooxygenase-2 (COX-2) inhibitors | en_US |
| dc.subject | Inhibitory activity | en_US |
| dc.title | Exploring Quantitative Structure-Activity Relationships (QSARs) of Non-Tri cyclic Cyclooxygenase-2 (COX-2) Inhibitors by MLR and PC-ANN | en_US |
| dc.type | Article | en_US |