Prediction of Protein Structural Class by Functional Link Artificial Neural Network Using Hybrid Feature Extraction Method
During last few decades’ accurate prediction of protein structural class has been a challenging problem. Efficient and meaningful representation of protein molecule plays a significant role. In this paper Chou’s pseudo amino acid composition along with amphiphillic correlation factor and the spectral characteristics of the protein has been used to represent protein data. Thus a protein sample is represented by a set of discrete components which incorporate both the sequence order and the sequence length effects. On the basis of such a statistical framework a simple functionally linked artificial neural network has been used for structural class prediction.
KeywordsAAC AmPseAAC DCTAmPseAAC Functional link artificial neural network (FLANN) Protein Domain Structural Class
Unable to display preview. Download preview PDF.
- 6.Panda, B., Mishra, A.P., Majhi, B., Rout, M.: Development and performance evaluation of FLANN based model for protein structural class prediction (in press)Google Scholar