Analysis of Kernel Based Protein Classification Strategies Using Pairwise Sequence Alignment Measures

详细信息    查看全文

• 作者：Dino Franklin ; Somdutta Dhir ; S¨¢ndor Pongor
• 刊名：Lecture Notes in Computer Science
• 出版年：2009
• 出版时间：2009
• 年：2009
• 卷：5488
• 期：1
• 页码：222-231
• 全文大小：223.2 KB

文摘

We evaluated methods of protein classification that use kernels built from BLAST output parameters. Protein sequences were represented as vectors of parameters (e.g. similarity scores) determined with respect to a reference set, and used in Support Vector Machines (SVM) as well as in simple nearest neighbor (1NN) classification. We found, using ROC analysis, that aggregate representations that use aggregate similarities with respect to a few object classes, were as accurate as the full vectorial representations, and that a jury of 6 1NN-based aggregate classifiers performed as well as the best SVM classifiers, while they required much less computational time.