On the Variability of Neural Network Classification Measures in the Protein Secondary Structure Prediction Problem. (31st January 2013)

• Record Type: Journal Article
• Authors: Sakk, Eric; Alexander, Ayanna
• Other Names: Lin Cheng-Jian Academic Editor.
• Is Part Of: Applied computational intelligence and soft computing. Volume 2013(2013)
• Publication Date: 2013-01-31
• Subjects: Computational intelligence -- Periodicals; Soft computing -- Periodicals; 006.305
• DOI: 10.1155/2013/794350
• Languages: English
• ISSNs: 1687-9724

Abstract

Abstract : We revisit the protein secondary structure prediction problem using linear and backpropagation neural network architectures commonly applied in the literature. In this context, neural network mappings are constructed between protein training set sequences and their assigned structure classes in order to analyze the class membership of test data and associated measures of significance. We present numerical results demonstrating that classifier performance measures can vary significantly depending upon the classifier architecture and the structure class encoding technique. Furthermore, an analytic formulation is introduced in order to substantiate the observed numerical data. Finally, we analyze and discuss the ability of the neural network to accurately model fundamental attributes of protein secondary structure.