Support vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds

Abstract The Support vector regression (SVR) was used to investigate quantitative structure–activity relationships (QSAR) of 75 phenolic compounds with Trolox-equivalent antioxidant capacity (TEAC). Geometric structures were optimized at the EF level of the MOPAC software program. Using Pearson corr...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Ying Shi
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/efc2fc9d3bf54a7fb4f364a855a3796a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:efc2fc9d3bf54a7fb4f364a855a3796a
record_format	dspace
spelling	oai:doaj.org-article:efc2fc9d3bf54a7fb4f364a855a3796a2021-12-02T18:27:47ZSupport vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds10.1038/s41598-021-88341-12045-2322https://doaj.org/article/efc2fc9d3bf54a7fb4f364a855a3796a2021-04-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-88341-1https://doaj.org/toc/2045-2322Abstract The Support vector regression (SVR) was used to investigate quantitative structure–activity relationships (QSAR) of 75 phenolic compounds with Trolox-equivalent antioxidant capacity (TEAC). Geometric structures were optimized at the EF level of the MOPAC software program. Using Pearson correlation coefficient analysis, four molecular descriptors [n(OH), Cosmo Area (CA), Core-Core Repulsion (CCR) and Final Heat of Formation (FHF)] were selected as independent variables. The QSAR model was developed from the training set consisting of 57 compounds and then used the leave-one-out cross-validation (LOOCV) correlation coefficient to evaluate the prediction ability of the QSAR model. Used Artificial neural network (ANN) and multiple linear regression (MLR) for comparing. The RMSE (root mean square error) values of LOOCV in SVR, ANN and MLR models were 0.44, 0.46 and 0.54. The RMSE values of prediction of external 18 compounds were 0.41, 0.39 and 0.54 for SVR, ANN and MLR models, respectively. The obtained result indicated that the SVR models exhibited excellent predicting performance and competent for predicting the TEAC of phenolic compounds.Ying ShiNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-9 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Ying Shi Support vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds
description	Abstract The Support vector regression (SVR) was used to investigate quantitative structure–activity relationships (QSAR) of 75 phenolic compounds with Trolox-equivalent antioxidant capacity (TEAC). Geometric structures were optimized at the EF level of the MOPAC software program. Using Pearson correlation coefficient analysis, four molecular descriptors [n(OH), Cosmo Area (CA), Core-Core Repulsion (CCR) and Final Heat of Formation (FHF)] were selected as independent variables. The QSAR model was developed from the training set consisting of 57 compounds and then used the leave-one-out cross-validation (LOOCV) correlation coefficient to evaluate the prediction ability of the QSAR model. Used Artificial neural network (ANN) and multiple linear regression (MLR) for comparing. The RMSE (root mean square error) values of LOOCV in SVR, ANN and MLR models were 0.44, 0.46 and 0.54. The RMSE values of prediction of external 18 compounds were 0.41, 0.39 and 0.54 for SVR, ANN and MLR models, respectively. The obtained result indicated that the SVR models exhibited excellent predicting performance and competent for predicting the TEAC of phenolic compounds.
format	article
author	Ying Shi
author_facet	Ying Shi
author_sort	Ying Shi
title	Support vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds
title_short	Support vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds
title_full	Support vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds
title_fullStr	Support vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds
title_full_unstemmed	Support vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds
title_sort	support vector regression-based qsar models for prediction of antioxidant activity of phenolic compounds
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/efc2fc9d3bf54a7fb4f364a855a3796a
work_keys_str_mv	AT yingshi supportvectorregressionbasedqsarmodelsforpredictionofantioxidantactivityofphenoliccompounds
_version_	1718378072597594112

Support vector regression-based QSAR models for prediction of antioxidant activity of phenolic compounds

Ejemplares similares