Review of Advances in Machine Learning Based Protein Secondary Structure Prediction

Protein secondary structure prediction plays a fundamental role in bioinformatics. Extracting valuable information from big biological data that can give an insight into understanding the 3-dimensional protein structure and later learn its biological function is quit challenging. In the past decade, many machine learning approaches have been applied in bioinformatics to extract knowledge from protein data. In this paper, a critical review on the recent development in machine learning based protein secondary structure prediction methods are presented. Next generation method (Deep learning) is also introduced to provide interested researchers with first-hand information on the future trend in this field. Although many approaches have yielded an appreciable prediction performance, machine learning approaches are far from fulfilling its potentials in biological research because of the difficulty in interpreting how particular model feature correlate with input features to yield that desired output in biological perspective. Therefore, this study has found that several further improvements are possible with the emergence of deep learning techniques.