On the variability of neural network classification measures in the protein secondary structure prediction problem

Authors:
Eric Sakk;Ayanna Alexander
Affiliations:
Department of Computer Science, Morgan State University, Baltimore, MD;Department of Computer Science, Morgan State University, Baltimore, MD
Venue:
Applied Computational Intelligence and Soft Computing
Year:
2013

Citing 8
Cited 0

Probabilistic neural networks

Neural Networks
Neural network design

Neural network design
Orthogonal RBF Neural Network Approximation

Neural Processing Letters
Protein secondary structure: entropy, correlations and prediction

Bioinformatics
Improving protein secondary structure prediction by using the residue conformational classes

Pattern Recognition Letters
Parallel protein secondary structure prediction schemes using Pthread and OpenMP over hyper-threading technology

The Journal of Supercomputing
Fast learning in networks of locally-tuned processing units

Neural Computation
The effect of target vector selection on the invariance of classifier performance measures

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

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.