eduzhai > Life Sciences > Biochemistry >

Quantitative structure-activity relationship of hydroxybenzoates based on support vector machine

  • sky
  • (0) Download
  • 20211118
  • Save

... pages left unread,continue reading

Document pages: 10 pages

Abstract: Hydroxybenzoate is a preservative, which is widely used in food, medicine and cosmetics. In order to explore the relationship between the molecular structure and antibacterial activity of these compounds and predict the compounds with similar structures, quantitative structure-activity relationship (QSAR) established the quantum chemical parameters and molecular connectivity index models of 25 hydroxybenzoates based on R language and support vector machine (SVM). The predicted external standard deviation (), fitting correlation coefficient () and omission cross validation () are used to evaluate the reliability, stability and prediction ability of the model. The results show that the sum of the four nonlinear models is greater than 0.6, which are 0.213, 0.222 and 0 respectively189, and 0.218, respectively. Compared with the multiple linear regression (MLR) model (, RSD = 0.260), the correlation coefficient and the standard deviation are both better than MLR. The reliability, stability, robustness, and external predictive ability of models are good, particularly of the model of linear kernel function and eps-regression type. This model can predict the antimicrobial activity of the compounds with similar structure in the applicability domain.

Please select stars to rate!


0 comments Sign in to leave a comment.

    Data loading, please wait...