Abstract
It is necessary to know both the primary and secondary structure of proteins in order to predict their biological functions. Neural networks are effective for secondary structure prediction of proteins. In this study, the self-organizing map (SOM) algorithm, and the self-organizing global ranking (SOGR) algorithm were investigated with different window sizes of amino acid sequences to predict the protein secondary structure from the protein primary structure. In this study, all of the data were obtained from PDB (protein data bank). Then, the letter data were converted to numerical data and processed with ANNs. 17 different types of data with a number of sliding window lengths were used. In general, results were very satisfactory, and the SOGR had the highest testing accuracies and faster speed of learning.