Authors

Abstract

The aim of this research is to predict the protein structural classes of given sequences using

computational method and algorithm. Some reviews and definitions of protein is explained to understand

the literature of protein structural classes in order to develop better understanding of this research.

Followed after that, the threshold-based classification rule applied for structural class prediction is

explained. Besides that, the taxonomy of local protein structures based on secondary structure is identified.

The selection of optimal number of clusters is described briefly because this research practically focuses

on this section to classify the non-identical structural classes.

In addition, we will need to understand the nature of clustering based algorithms that are available

particularly concerning on K-means algorithm that was used in this work. Some related research on

structural class prediction is also included in this chapter. Literature review is very important as it is a

process of gathering information from other sources and documenting it, also a critical and in depth

evaluation of previous research. It is a summary and synopsis of a particular area of research acting as a

precursor to convey the knowledge and ideas that have been established on a topic and what are their

strengths and weaknesses.