Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences

@article{citeulike:2664987, abstract = {Compared to the available protein sequences of different organisms, the number of revealed proteinprotein interactions (PPIs) is still very limited. So many computational methods have been developed to facilitate the identification of novel PPIs. However, the methods only using the information of protein sequences are more universal than those that depend on some additional information or predictions about the proteins. In this article, a sequence-based method is proposed by combining a new feature representation using auto covariance (AC) and support vector machine (SVM). AC accounts for the interactions between residues a certain distance apart in the sequence, so this method adequately takes the neighbouring effect into account. When performed on the PPI data of yeast Saccharomyces cerevisiae, the method achieved a very promising prediction result. An independent data set of 11 474 yeast PPIs was used to evaluate this prediction model and the prediction accuracy is 88.09\%. The performance of this method is superior to those of the existing sequence-based methods, so it can be a useful supplementary tool for future proteomics studies. The prediction software and all data sets used in this article are freely available at http://www.scucic.cn/Predict\_PPI/index.htm. 10.1093/nar/gkn159}, author = {Guo, Yanzhi and Yu, Lezheng and Wen, Zhining and Li, Menglong }, citeulike-article-id = {2664987}, doi = {http://dx.doi.org/10.1093/nar/gkn159}, journal = {Nucl. Acids Res.}, keywords = {interaction, prediction, protein, svm}, month = {April}, pages = {gkn159+}, posted-at = {2008-06-16 03:51:12}, priority = {4}, title = {Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences}, url = {http://dx.doi.org/10.1093/nar/gkn159}, year = {2008} }

TY - JOUR ID - citeulike:2664987 L3 - citeulike-article-id:2664987 TI - Using support vector machine combined with auto covariance to predict protein-protein interactions from protein sequences JF - Nucl. Acids Res. SP - gkn159 N2 - Compared to the available protein sequences of different organisms, the number of revealed proteinprotein interactions (PPIs) is still very limited. So many computational methods have been developed to facilitate the identification of novel PPIs. However, the methods only using the information of protein sequences are more universal than those that depend on some additional information or predictions about the proteins. In this article, a sequence-based method is proposed by combining a new feature representation using auto covariance (AC) and support vector machine (SVM). AC accounts for the interactions between residues a certain distance apart in the sequence, so this method adequately takes the neighbouring effect into account. When performed on the PPI data of yeast Saccharomyces cerevisiae, the method achieved a very promising prediction result. An independent data set of 11 474 yeast PPIs was used to evaluate this prediction model and the prediction accuracy is 88.09%. The performance of this method is superior to those of the existing sequence-based methods, so it can be a useful supplementary tool for future proteomics studies. The prediction software and all data sets used in this article are freely available at http://www.scucic.cn/Predict_PPI/index.htm. 10.1093/nar/gkn159 KW - interaction KW - prediction KW - protein KW - svm AU - Guo, Yanzhi AU - Yu, Lezheng AU - Wen, Zhining AU - Li, Menglong PY - 2008/04/04/ UR - http://dx.doi.org/10.1093/nar/gkn159 ER -