摘要： The function of a protein is generally related to its subcellular localization. Therefore, knowing its subcellular localization is helpful in understanding its potential functions and roles in biological processes. This work develops a hybrid method for computationally predicting the subcellular localization of eukaryotic protein. The method is called EuLoc and incorporates the Hidden Markov Model (HMM) method, homology search approach and the support vector machines (SVM) method by fusing several new features into Chou’s pseudo-amino acid composition. The proposed SVM module overcomes the shortcoming of the homology search approach in predicting the subcellular localization of a protein which only finds low-homologous or non-homologous sequences in a protein subcellular localization annotated database. The proposed HMM modules overcome the shortcoming of SVM in predicting subcellular localizations using few data on protein sequences. Several features of a protein sequence are considered, including the sequence-based features, the biological features derived from PROSITE, NLSdb and Pfam, the post-transcriptional modification features and others. The overall accuracy and location accuracy of EuLoc are 90.5 and 91.2 %, respectively, revealing a better predictive performance than obtained elsewhere. Although the amounts of data of the various subcellular location groups in benchmark dataset differ markedly, the accuracies of 12 subcellular localizations of EuLoc range from 82.5 to 100 %, indicating that this tool is much more balanced than other tools. EuLoc offers a high, balanced predictive power for each subcellular localization. EuLoc is now available on the web at http://euloc.mbc.nctu.edu.tw/ . 其他題名： J Comput Aided Mol Des 出版者： Dordrecht: Springer Netherlands 出版日期： 2013-01 出處： Journal of computer-aided molecular design, 2013-01, Vol.27 (1), p.91-103 資源來源： EBSCOhost Academic Search Premier 版權： Springer Science+Business Media Dordrecht 2012 版權： Springer Science+Business Media Dordrecht 2013 識別號： ISSN: 0920-654X 識別號： ISSN: 1573-4951 識別號： EISSN: 1573-4951 識別號： DOI: 10.1007/s10822-012-9628-0 識別號： PMID: 23283513
