Cargando…

A QSAR Study Based on SVM for the Compound of Hydroxyl Benzoic Esters

Hydroxyl benzoic esters are preservative, being widely used in food, medicine, and cosmetics. 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 (QSA...

Descripción completa

Detalles Bibliográficos
Autores principales: Wen, Li, Li, Qing, Li, Wei, Cai, Qiao, Cai, Yong-Ming
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Hindawi 2017
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5512106/
https://www.ncbi.nlm.nih.gov/pubmed/28757813
http://dx.doi.org/10.1155/2017/4914272
_version_ 1783250446976024576
author Wen, Li
Li, Qing
Li, Wei
Cai, Qiao
Cai, Yong-Ming
author_facet Wen, Li
Li, Qing
Li, Wei
Cai, Qiao
Cai, Yong-Ming
author_sort Wen, Li
collection PubMed
description Hydroxyl benzoic esters are preservative, being widely used in food, medicine, and cosmetics. 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) models of 25 kinds of hydroxyl benzoic esters with the quantum chemical parameters and molecular connectivity indexes are built based on support vector machine (SVM) by using R language. The External Standard Deviation Error of Prediction (SDEP(ext)), fitting correlation coefficient (R(2)), and leave-one-out cross-validation (Q(2)(LOO)) are used to value the reliability, stability, and predictive ability of models. The results show that R(2) and Q(2)(LOO) of 4 kinds of nonlinear models are more than 0.6 and SDEP(ext) is 0.213, 0.222, 0.189, and 0.218, respectively. Compared with the multiple linear regression (MLR) model (R(2) = 0.421, 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.
format Online
Article
Text
id pubmed-5512106
institution National Center for Biotechnology Information
language English
publishDate 2017
publisher Hindawi
record_format MEDLINE/PubMed
spelling pubmed-55121062017-07-30 A QSAR Study Based on SVM for the Compound of Hydroxyl Benzoic Esters Wen, Li Li, Qing Li, Wei Cai, Qiao Cai, Yong-Ming Bioinorg Chem Appl Research Article Hydroxyl benzoic esters are preservative, being widely used in food, medicine, and cosmetics. 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) models of 25 kinds of hydroxyl benzoic esters with the quantum chemical parameters and molecular connectivity indexes are built based on support vector machine (SVM) by using R language. The External Standard Deviation Error of Prediction (SDEP(ext)), fitting correlation coefficient (R(2)), and leave-one-out cross-validation (Q(2)(LOO)) are used to value the reliability, stability, and predictive ability of models. The results show that R(2) and Q(2)(LOO) of 4 kinds of nonlinear models are more than 0.6 and SDEP(ext) is 0.213, 0.222, 0.189, and 0.218, respectively. Compared with the multiple linear regression (MLR) model (R(2) = 0.421, 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. Hindawi 2017 2017-07-03 /pmc/articles/PMC5512106/ /pubmed/28757813 http://dx.doi.org/10.1155/2017/4914272 Text en Copyright © 2017 Li Wen et al. https://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
spellingShingle Research Article
Wen, Li
Li, Qing
Li, Wei
Cai, Qiao
Cai, Yong-Ming
A QSAR Study Based on SVM for the Compound of Hydroxyl Benzoic Esters
title A QSAR Study Based on SVM for the Compound of Hydroxyl Benzoic Esters
title_full A QSAR Study Based on SVM for the Compound of Hydroxyl Benzoic Esters
title_fullStr A QSAR Study Based on SVM for the Compound of Hydroxyl Benzoic Esters
title_full_unstemmed A QSAR Study Based on SVM for the Compound of Hydroxyl Benzoic Esters
title_short A QSAR Study Based on SVM for the Compound of Hydroxyl Benzoic Esters
title_sort qsar study based on svm for the compound of hydroxyl benzoic esters
topic Research Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5512106/
https://www.ncbi.nlm.nih.gov/pubmed/28757813
http://dx.doi.org/10.1155/2017/4914272
work_keys_str_mv AT wenli aqsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT liqing aqsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT liwei aqsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT caiqiao aqsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT caiyongming aqsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT wenli qsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT liqing qsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT liwei qsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT caiqiao qsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters
AT caiyongming qsarstudybasedonsvmforthecompoundofhydroxylbenzoicesters