Abstract

The fast growth of protein sequencing and protein structure data has promoted the development of the protein structural class prediction. Several prediction methods have been proposed to study protein folding rate, DNA binding sites, as well as reducing the search of conformational space and realizing the prediction of tertiary structure. This paper introduces the current approaches of protein structural class prediction and emphasizes their steps from information extraction to classification algorithms.

Keywords: Sequence feature, secondary structural characteristic, classification algorithm, protein structural class prediction, DNA Blast, DNA binding sites.