Jun Zhang and Bin Liu*
Proteins play a crucial role in life activities, such as catalyzing metabolic reactions, DNA replication, responding to stimuli, etc. Identification of protein structures and functions are critical for both basic research (uncover their function) and applications (disease treatment, precision medicine, etc.). Because the traditional experiments for studying the structures and functions of proteins is expensive and time consuming, the computational approaches are highly desired. In this regard, many computational methods have been proposed to predict the structures and functions of proteins only based on the sequence information with low cost, which are suitable for high throughout analysis. In key for these methods is how to efficiently extract the features from the protein sequences. During the last decade, many powerful feature extraction algorithms have been proposed, significantly promoting the development of the studies of protein structures and functions. In this paper, we give a comprehensive on the feature extractions for protein sequences, especially focusing on the recent developments in this field.
review, protein structure and function prediction, feature extraction, protein representation
School of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, Guangdong 518055, School of Computer Science and Technology, Harbin Institute of Technology Shenzhen Graduate School, Shenzhen, Guangdong 518055