Hot spot identification by means of classification methods employing wavelet transform-based features

Abstract

Background: Proteins can interact with one another by an interface composed of two proteins. Some of the interface residues - called hot spots - have the greatest impact on binding energy in a protein complex. This paper introduces the application of continuous wavelet transform based on the fast Fourier transform (CWTFT) to the analysis of hot spots in proteins.Results: The algorithm was evaluated by using data sets containing 30 proteins. From the number of tested classifiers the best 10 models were preferred. The classifiers achieved sensitivity of 52% - 71%, specificity of 70% - 83% and accuracy of 70% - 74%.Conclusion: The analyses show that the method combining CWTFT and classification algorithms is able to identify hot spot residues with valuable results.Methods: The basis of the algorithm is extraction of features from spectra obtained by using CWTFT with different wavelet functions including Morlet, m^th order derivative of Gaussian, Paul and Bump wavelets. Then, the classifiers that are able to separate hot spot from non-hot spot residues according to these features are applied.