Using position-specific-value method for remote protein classification

An important research topic in Bioinformatics is to understand the meaning and function of each protein encoded in the genome. One of the most successful approaches to this problem is via sequence similarity with one or more proteins whose functions are known. The SVM based methods are among the most successful ones. Currently, one of the most accurate homology detection methods is the SVM-pairwise method. This method combines the pairwise sequence similarity with Support Vector Machine. The current work presents an alternative for SVM-based protein classification. The method, SVM-PSV, uses a new sequence similarity kernel, the Position Specific Values (PSV) kernel, for use with Support Vector Machines to solve the protein classification problem. Our kernel is conceptually simple, efficient to compute, and showing better performance in the comparison with state-of-art methods in the experiments of the detection of the homology based on the SCOP database.