A STUDY OF INTELLIGENT TECHNIQUES FOR PROTEIN SECONDARY STRUCTURE PREDICTION

Protein secondary structure prediction has been and will continue to be a rich research field. This is because the protein structure and shape directly affect protein behavior. Moreover, the number of known secondary and tertiary structures versus primary structures is relatively small. Although the secondary prediction started in the seventies but it has been together with the tertiary structure prediction a topic that is always under research. This paper presents a technical study on recent methods used for secondary structure prediction using amino acid sequence. The methods are studied along with their accuracy levels. The most known methods like Neural Networks and Support Vector Machines are shown and other techniques as well. The paper shows different approaches for predicting the protein structures that showed different accuracies that ranged from 50% to over than 90%. The most commonly used technique is Neural Networks. However, Case Based Reasoning and Mixed Integer Linear Optimization showed the best accuracy among the machine learning techniques and provided accuracy of approximately 83%.