Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptor
Quantitative structure–activity relationship (QSAR) approaches were used to estimate the volume of distribution (Vd) using an artificial neural network (ANN). The data set consisted of the volume of distribution of 129 pharmacologically important compounds, i.e., benzodiazepines, barbiturates, nonst...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Serbian Chemical Society
2011-07-01
|
| Series: | Journal of the Serbian Chemical Society |
| Subjects: | |
| Online Access: | http://www.shd.org.rs/JSCS/Vol76/No7/07_4923_4179.pdf |
| _version_ | 1819123784600256512 |
|---|---|
| author | MOHAMMAD H. FATEMI ZAHRA GHORBANNEZHAD |
| author_facet | MOHAMMAD H. FATEMI ZAHRA GHORBANNEZHAD |
| author_sort | MOHAMMAD H. FATEMI |
| collection | DOAJ |
| description | Quantitative structure–activity relationship (QSAR) approaches were used to estimate the volume of distribution (Vd) using an artificial neural network (ANN). The data set consisted of the volume of distribution of 129 pharmacologically important compounds, i.e., benzodiazepines, barbiturates, nonsteroidal anti-inflammatory drugs (NSAIDs), tricyclic anti-depressants and some antibiotics, such as betalactams, tetracyclines and quinolones. The descriptors, which were selected by stepwise variable selection methods, were: the Moriguchi octanol–water partition coefficient; the 3D-MoRSE-signal 30, weighted by atomic van der Waals volumes; the fragment-based polar surface area; the d COMMA2 value, weighted by atomic masses; the Geary autocorrelation, weighted by the atomic Sanderson electronegativities; the 3D-MoRSE – signal 02, weighted by atomic masses, and the Geary autocorrelation – lag 5, weighted by the atomic van der Waals volumes. These descriptors were used as inputs for developing multiple linear regressions (MLR) and artificial neural network models as linear and non-linear feature mapping techniques, respectively. The standard errors in the estimation of Vd by the MLR model were: 0.104, 0.103 and 0.076 and for the ANN model: 0.029, 0.087 and 0.082 for the training, internal and external validation test, respectively. The robustness of these models were also evaluated by the leave-5-out cross validation procedure, that gives the statistics Q2 = 0.72 for the MLR model and Q2 = 0.82 for the ANN model. Moreover, the results of the Y-randomization test revealed that there were no chance correlations among the data matrix. In conclusion, the results of this study indicate the applicability of the estimation of the Vd value of drugs from their structural molecular descriptors. Furthermore, the statistics of the developed models indicate the superiority of the ANN over the MLR model. |
| first_indexed | 2024-12-22T07:13:51Z |
| format | Article |
| id | doaj.art-36e9cda965734bb1807216522160fcf8 |
| institution | Directory Open Access Journal |
| issn | 0352-5139 |
| language | English |
| last_indexed | 2024-12-22T07:13:51Z |
| publishDate | 2011-07-01 |
| publisher | Serbian Chemical Society |
| record_format | Article |
| series | Journal of the Serbian Chemical Society |
| spelling | doaj.art-36e9cda965734bb1807216522160fcf82022-12-21T18:34:27ZengSerbian Chemical SocietyJournal of the Serbian Chemical Society0352-51392011-07-0176710031014Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptorMOHAMMAD H. FATEMIZAHRA GHORBANNEZHADQuantitative structure–activity relationship (QSAR) approaches were used to estimate the volume of distribution (Vd) using an artificial neural network (ANN). The data set consisted of the volume of distribution of 129 pharmacologically important compounds, i.e., benzodiazepines, barbiturates, nonsteroidal anti-inflammatory drugs (NSAIDs), tricyclic anti-depressants and some antibiotics, such as betalactams, tetracyclines and quinolones. The descriptors, which were selected by stepwise variable selection methods, were: the Moriguchi octanol–water partition coefficient; the 3D-MoRSE-signal 30, weighted by atomic van der Waals volumes; the fragment-based polar surface area; the d COMMA2 value, weighted by atomic masses; the Geary autocorrelation, weighted by the atomic Sanderson electronegativities; the 3D-MoRSE – signal 02, weighted by atomic masses, and the Geary autocorrelation – lag 5, weighted by the atomic van der Waals volumes. These descriptors were used as inputs for developing multiple linear regressions (MLR) and artificial neural network models as linear and non-linear feature mapping techniques, respectively. The standard errors in the estimation of Vd by the MLR model were: 0.104, 0.103 and 0.076 and for the ANN model: 0.029, 0.087 and 0.082 for the training, internal and external validation test, respectively. The robustness of these models were also evaluated by the leave-5-out cross validation procedure, that gives the statistics Q2 = 0.72 for the MLR model and Q2 = 0.82 for the ANN model. Moreover, the results of the Y-randomization test revealed that there were no chance correlations among the data matrix. In conclusion, the results of this study indicate the applicability of the estimation of the Vd value of drugs from their structural molecular descriptors. Furthermore, the statistics of the developed models indicate the superiority of the ANN over the MLR model.http://www.shd.org.rs/JSCS/Vol76/No7/07_4923_4179.pdfquantitative structure–activity relationshipmolecular descriptorvolume of distributionartificial neural network. |
| spellingShingle | MOHAMMAD H. FATEMI ZAHRA GHORBANNEZHAD Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptor Journal of the Serbian Chemical Society quantitative structure–activity relationship molecular descriptor volume of distribution artificial neural network. |
| title | Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptor |
| title_full | Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptor |
| title_fullStr | Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptor |
| title_full_unstemmed | Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptor |
| title_short | Estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptor |
| title_sort | estimation of the volume of distribution of some pharmacologically important compounds from their structural descriptor |
| topic | quantitative structure–activity relationship molecular descriptor volume of distribution artificial neural network. |
| url | http://www.shd.org.rs/JSCS/Vol76/No7/07_4923_4179.pdf |
| work_keys_str_mv | AT mohammadhfatemi estimationofthevolumeofdistributionofsomepharmacologicallyimportantcompoundsfromtheirstructuraldescriptor AT zahraghorbannezhad estimationofthevolumeofdistributionofsomepharmacologicallyimportantcompoundsfromtheirstructuraldescriptor |