Surface Glycoprotein Classification Using Repeat Sequences

Correct recognition of sequence characteristics is one of the most important steps in bioinformatics. The paper presents a method for the characterization of surface glycoprotein in different viruses. The method uses amino-acid and nucleotide repeat sequences to form a virus/protein profile that is used to characterize and predict the type of protein. Based on a set of characteristic repetitive sequences, a classification model for predicting the type of virus was constructed.