A QSRR model for predicting gas chromatography retention indices of essential oils using an improved chemical reaction optimization algorithm | ||||
| Egyptian Journal of Chemistry | ||||
| Article 1, Volume 65, Issue 7, July 2022, Page 1-9 PDF (378.25 K) | ||||
| Document Type: Original Article | ||||
| DOI: 10.21608/ejchem.2021.32116.2682 | ||||
 View on SCiNiTO | ||||
| Author | ||||
Maimoonah Kh. Qasim 
| ||||
| Department of General Science, University of Mosul, Mosul, Iraq | ||||
| Abstract | ||||
| A quantitative structure–retention relationship (QSRR) model with chemical reaction optimization algorithm (CROA) for predicting retention indices (RI) of 169 constituents of essential oils is proposed. The proposed model was internal and external validated based on , , , , Y-randomization test, , , and the applicability domain (AD). The validation results indicate that the model is robust and not due to chance correlation. In addition, the results indicate that the descriptors selection and prediction performance of the proposed model for training dataset outperforms the other two used modeling methods. The proposed model shows the highest , , and , and the lowest . For the test dataset, proposed model shows higher external validation value ( = 0.936), and lower value of compared with the other methods, indicating its higher predictive ability. In conclusion, the results reveal that the proposed model is an efficient approach for modeling high dimensional QSRRs and useful for the estimation of RI of essential oils that have not been experimentally tested. | ||||
| Keywords | ||||
| Chemical reaction optimization algorithm; lasso; descriptor selection; QSRR; Essential oils | ||||
|
Statistics Article View: 247 PDF Download: 194 |
||||
