Structural class prediction of protein using novel feature extraction method from chaos game representation of predicted secondary structure. (7th July 2016)

• Record Type: Journal Article
• Authors: Zhang, Lichao; Kong, Liang; Han, Xiaodong; Lv, Jinfeng
• Is Part Of: Journal of theoretical biology. Volume 400(2016)
• Page Start: 1
• Page End: 10
• Publication Date: 2016-07-07
• Subjects: Protein structural class -- Secondary protein structure -- Sequence similarity -- Support vector machines; Biology -- Periodicals; Biological Science Disciplines -- Periodicals; Biology -- Periodicals; Biologie -- Périodiques; Theoretische biologie; Biology; Periodicals; 571.05
• DOI: 10.1016/j.jtbi.2016.04.011
• Languages: English
• ISSNs: 0022-5193

Abstract

Abstract: Protein structural class prediction plays an important role in protein structure and function analysis, drug design and many other biological applications. Extracting good representation from protein sequence is fundamental for this prediction task. In recent years, although several secondary structure based feature extraction strategies have been specially proposed for low-similarity protein sequences, the prediction accuracy still remains limited. To explore the potential of secondary structure information, this study proposed a novel feature extraction method from the chaos game representation of predicted secondary structure to mainly capture sequence order information and secondary structure segments distribution information in a given protein sequence. Several kinds of prediction accuracies obtained by the jackknife test are reported on three widely used low-similarity benchmark datasets (25PDB, 1189 and 640). Compared with the state-of-the-art prediction methods, the proposed method achieves the highest overall accuracies on all the three datasets. The experimental results confirm that the proposed feature extraction method is effective for accurate prediction of protein structural class. Moreover, it is anticipated that the proposed method could be extended to other graphical representations of protein sequence and be helpful in future research. Abstract : Highlights: Features are extracted from chaos game representation of secondary structure. Secondary structure distribution features can improve prediction significantly. Experimental results show that our feature extraction method is very promising.