QSAR studies for the acute toxicity of nitrobenzenes to the Tetrahymena pyriformis
| Autor: | Wang Dan-Dan, Feng Lin-Lin, He Guang-Yu, Chen Hai-Qun |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2014 |
| Předmět: | |
| Zdroj: | Journal of the Serbian Chemical Society, Vol 79, Iss 9, Pp 1111-1125 (2014) |
| Druh dokumentu: | article |
| ISSN: | 0352-5139 1820-7421 |
| DOI: | 10.2298/JSC130910025W |
| Popis: | Quantitative structure-activity relationship (QSAR) models play a key role in finding the relationship between molecular structures and the toxicity of nitrobenzenes to Tetrahymena pyriformis. In this work, genetic algorithm, along with partial least square (GA-PLS) was employed to select optimal subset of descriptors that have significant contribution to the toxicity of nitrobenzenes to Tetrahymena pyriformis. A set of five descriptors, namely G2, HOMT, G(Cl…Cl), Mor03v and MAXDP, was used for the prediction of the toxicity of 45 nitrobenzene derivatives and then were used to build the model by multiple linear regression (MLR) method. It turned out that the built model, whose stability was confirmed using the leave-one-out validation and external validation test, showed high statistical significance (R2=0.963, Q2LOO=0.944). Moreover, Y-scrambling test indicated there was no chance correlation in this model. |
| Databáze: | Directory of Open Access Journals |
| Externí odkaz: |
|