Predicting Of Ordered-Disordered Protein Structures Using Fuzzy And Kernel-Based Discriminant Analysis

Abstract

In bioinformatics, proteins are large molecular structures that are composed of one or more chains of amino acids with a variety of shapes, size and chemical properties. Different types of protein sequences have specific biochemical function. Therefore, classification of protein sequences is very essential process to identify their tasks in the biological cycle. Experimental classification is costly and time-consuming because of great amount of raw sequences. Therefore, computational solutions have become a useful tool for analysis. In this study we proposed fuzzy and kernel discriminant analysis techniques in order to classify the protein sequences as “ordered” or “disordered” structures by mathematically and algorithmically.

The overall prediction accuracies for LDA, FDA and KDA are obtained as 78.95%, 94.74% and 100%, respectively. It can be referred that kernel discriminant analysis can be a very robust method to identify whether a protein has a disordered or ordered structure.