Receiver Operating Characteristic Curves in Binary Classification of Protein Secondary Structure Data

Abstract

In the field of protein secondary structure prediction three states of secondary structures are used, namely, alpha helices (H) beta strands (E), and coils (C). Protein secondary structure prediction is a fundamental step in determining the final structure and functions of a protein. In this chapter we are going to investigate the amino acids benchmark data sets, it was observed that the data is grouped into two distinct states or groups almost 50% each. In this scheme, researchers classify any state which is not classified as helix or strands or coils. Hence, in this work a new way of looking to the data set is adopted. For this type of data, the Receiver Operating Characteristic (ROC) analysis is considered for analysing and interpreting the results of our protein secondary structure classifier. The results revealed that ROC analysis showed similar results to that obtained using other non-ROC classification methods. The ROC curves were able to discriminate the coil states from non-coil states by 72% prediction accuracy with very small standard error.