Prediction of xylanase optimal temperature by support vector regression

Prediction of xylanase optimal temperature by support vector regression

Background: Support vector machine (SVM), a novel powerful machine learning technology, was used to develop the non-linear quantitative structure-property relationship (QSPR) model of the G/11 xylanase based on the amino acid composition. The uniform design (UD) method was applied to optimize the ru...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Zhang,Guangya, Ge,Huihua
Lenguaje:English
Publicado: Pontificia Universidad Católica de Valparaíso 2012
Materias:
amino acid composition
optimum temperature
support vector machine
uniform design
xylanase
Acceso en línea:http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0717-34582012000100007
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:scielo:S0717-34582012000100007
record_format dspace
spelling oai:scielo:S0717-345820120001000072012-06-06Prediction of xylanase optimal temperature by support vector regressionZhang,GuangyaGe,Huihua amino acid composition optimum temperature support vector machine uniform design xylanase Background: Support vector machine (SVM), a novel powerful machine learning technology, was used to develop the non-linear quantitative structure-property relationship (QSPR) model of the G/11 xylanase based on the amino acid composition. The uniform design (UD) method was applied to optimize the running parameters of SVM for the first time. Results: Results showed that the predicted optimum temperature of leave-one-out (LOO) cross-validation fitted the experimental optimum temperature very well, when the running parameter C, ξ, and γ was 50, 0.001 and 1.5, respectively. The average root-mean-square errors (RMSE) of the LOO cross-validation were 9.53ºC, while the RMSE of the back propagation neural network (BPNN), was 11.55ºC. The predictive ability of SVM is a minor improvement over BPNN, but it is superior to the reported method based on stepwise regression. Two experimental examples proved the validation of the model for predicting the optimal temperature of xylanase. Conclusion: The results indicated that UD might be an effective method to optimize the parameters of SVM, which could be used as an alternative powerful modeling tool for QSPR studies of xylanase.info:eu-repo/semantics/openAccessPontificia Universidad Católica de ValparaísoElectronic Journal of Biotechnology v.15 n.1 20122012-01-01text/htmlhttp://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0717-34582012000100007en
institution Scielo Chile
collection Scielo Chile
language English
topic amino acid composition
optimum temperature
support vector machine
uniform design
xylanase
spellingShingle amino acid composition
optimum temperature
support vector machine
uniform design
xylanase
Zhang,Guangya
Ge,Huihua
Prediction of xylanase optimal temperature by support vector regression
description Background: Support vector machine (SVM), a novel powerful machine learning technology, was used to develop the non-linear quantitative structure-property relationship (QSPR) model of the G/11 xylanase based on the amino acid composition. The uniform design (UD) method was applied to optimize the running parameters of SVM for the first time. Results: Results showed that the predicted optimum temperature of leave-one-out (LOO) cross-validation fitted the experimental optimum temperature very well, when the running parameter C, ξ, and γ was 50, 0.001 and 1.5, respectively. The average root-mean-square errors (RMSE) of the LOO cross-validation were 9.53ºC, while the RMSE of the back propagation neural network (BPNN), was 11.55ºC. The predictive ability of SVM is a minor improvement over BPNN, but it is superior to the reported method based on stepwise regression. Two experimental examples proved the validation of the model for predicting the optimal temperature of xylanase. Conclusion: The results indicated that UD might be an effective method to optimize the parameters of SVM, which could be used as an alternative powerful modeling tool for QSPR studies of xylanase.
author Zhang,Guangya
Ge,Huihua
author_facet Zhang,Guangya
Ge,Huihua
author_sort Zhang,Guangya
title Prediction of xylanase optimal temperature by support vector regression
title_short Prediction of xylanase optimal temperature by support vector regression
title_full Prediction of xylanase optimal temperature by support vector regression
title_fullStr Prediction of xylanase optimal temperature by support vector regression
title_full_unstemmed Prediction of xylanase optimal temperature by support vector regression
title_sort prediction of xylanase optimal temperature by support vector regression
publisher Pontificia Universidad Católica de Valparaíso
publishDate 2012
url http://www.scielo.cl/scielo.php?script=sci_arttext&pid=S0717-34582012000100007
work_keys_str_mv AT zhangguangya predictionofxylanaseoptimaltemperaturebysupportvectorregression
AT gehuihua predictionofxylanaseoptimaltemperaturebysupportvectorregression
_version_ 1718441851165343744

Ejemplares similares