All Title Author
Keywords Abstract


Prediction of protein homo-oligomer types with a novel approach of glide zoom window feature extraction
基于多策略滑动伸缩窗特征提取方法预测蛋白质同源寡聚体

Keywords: Homo-oligomers,Support vector machines (SVM),Feature extraction,Multi-strategy glide zoom window,Multi-strategy glide zoom window features
同源寡聚体
,支持向量机,特征提取,多策略滑动伸缩窗,多策略滑动伸缩窗特征

Full-Text   Cite this paper   Add to My Lib

Abstract:

Protein homo-oligomers play an important role in varous life processes .The concept of multi-strategy glide zoom window was proposed and a novel approach of multi-strategy glide zoom window feature extraction was used for predicting protein homo-oligomers. Based on the concept of multi-strategy glide zoom window, the authors chose two strategy glide zoom windows: whole protein sequence glide zoom window and kin amino acid glide zoom window, and for each strategy glide zoom window, three feature vectors of amino acids distance sum, amino acids mean distance and amino acids distribution, were extracted. A series of feature sets were constructed by combining these feature vectors with amino acids composition to form pseudo amino acid compositions (PseAAC). The support vector machine (SVM) was used as base classifier. The 75.37% total accuracy is arrived in jackknife test in the weighted factor conditions, which is 10.05% and 3.82% higher than that of conventional amino acid composition method and that of BG_Zhang in the same condition. The results show that multi-strategy glide zoom window method of extracting feature vectors from protein sequence is effective and feasible, and the feature vectors of multi-strategy glide zoom window may contain more protein structure information.

Full-Text

comments powered by Disqus