ANALYSIS OF GROUP CODING OF MULTIPLE AMINO ACIDS IN ARTIFICIAL NEURAL NETWORK APPLIED TO THE PREDICTION OF PROTEIN SECONDARY STRUCTURE
In this paper, a new method involving group coding is introduced into Artificial Neural Network in the prediction of the secondary structure of the proteins. This method, to a larger degree, take advantage of information of amino acids groups which possibly plays a significant role in determining the secondary structure of the particular position. Experiments are conducted to test the efficiency of this method. The result shows that the prediction accuracy is significantly improved, compared to the former method using single residue coding. We further discuss the mechanism of group coding in the model and discuss its further improvement in secondary prediction and other significant fields on structure and function prediction of bio-macromolecule based on sequence analysis.
Froup coding Artificial Neural Network(ANN) secondary structure prediction
Hongjie Zhu Bin Dai Yafeng Zhang Jiali Bao
College of Life Science, Zhejiang University, Hangzhou 310006, China Department of Mathematics, Zhejiang University, Hangzhou 310006, China College of Medicine, Zhejiang University, Hangzhou 310006, China
国际会议
The 4th International Forum on Post-genome Technologies(4IFPT)(第四届国际后基因组生命科学技术学术论坛)
杭州
英文
192-196
2006-09-25（万方平台首次上网日期，不代表论文的发表时间）