Experimental Result Using K-Means Clustering In Incorporation Local Protein Structure Information

Abstract

In this paper, an overview of structural classes prediction was conducted using classification method to boost the prediction accuracy. Besides, an effective computational method to precisely predict the structural classes of protein was introduced. This paper covers the importance of identifying the optimal number of clusters for predicting structural classes using Kmeans clustering algorithm that was investigated in this paper. The impacts of using fixed length to obtain the protein secondary structure on prediction of structural classes have been analyzed in this paper. Several limitations that occur as well as contributions are also highlighted. Generally, an overview on results and achievements is mentioned. Lastly, this paper outlines a general conclusion based on the methods that have been carried out in this work. Several recommendations on prospective area for future work are emphasized as well.