Protein Local Structure Prediction through Improved Clustering Support Vector Machines (ICSVM)

Main Article Content

Sasmita Rout
Tripti Swarnkar,Debabrata Senapati, Saswati Mahapatra

Abstract

Accurate protein secondary structure prediction plays an important role in direct tertiary structure modeling, and can also significantly enhance sequence analysis and sequence-structure threading for structure and function determination. Understanding the sequence-to-structure relationship is a central task in bioinformatics. Adequate knowledge about this can improve the accuracy for protein structure prediction. The conventional algorithm such as clustering and SVM can not reveal the complex nonlinear relationship adequately on a huge amount of data individually. So the model CSVMs (Clustering Support Vector Machines) was designed by merging the concept of both clustering and SVM. It has been seen that the generalization power for CSVMs is strong enough to recognize the complicated pattern of sequence-to-structure relationships. CSVMs can only predict the protein local structure with which it is being trained. But if a new type of protein segment comes then it may happen that the CSVMs will fail. That is, none of the cluster will treat it as a positive sample. So in this paper we introduced another robust method called Improved Support Vector Machines (ICSVM) which can handle the unseen example efficiently.

Keywords: Clustering algorithm, SVM, Protein structure prediction, CSVMs, ICSVM.

Downloads

Download data is not yet available.

Article Details

Section
Articles