Predict the Tertiary Structure of Protein with Flexible Neural Tree
Predicting the tertiary structure of protein from its primary amino acid sequence is a challenging mission for bioinformatics. In this paper we proposes a novel approach of predicting the tertiary structure of protein using the flexible neural tree (FNT) to construct a tree classification model. Two feature extraction methods (the physicochemical composition (PCC)) and the recurrence quantification analysis (RQA)) are employed to extract the features of protein sequence. To value the efficiencies of the proposed method we select two benchmark protein sequence datasets (1189 dataset and 640 dataset), as the test data set. The experimental results show that the proposed method is efficient for the protein structure prediction.
KeywordsTertiary structure of protein Tree classification model FNT PCC RQA
Unable to display preview. Download preview PDF.
- 3.Metfessel, B.A., Saurugger, P.N., Connelly, D.P., Rich, S.T.: Cross-validation of Protein Structural Class Prediction using Statistical clustering and neural networks. Protein Sci. 1171–1182 (1993)Google Scholar
- 5.Chen, Y.H., Abraham, A., Yang, J.: Feature Selection and Intrusion Detection Using Hybrid Flexible Neural Tree, pp. 439–444. Springer, Heidelberg (2005)Google Scholar
- 13.Wang, Z.X., Yuan, Z.: How Good Is The Prediction of Protein Structural Class by The Component-coupled Method? Pattern Recogn. 38, 165–175 (2000)Google Scholar