Prediction of a-helix and b-strand segments of globular proteins
Our segment-oriented method is designed to locate secondary structure elements and uses linear discriminant analysis to assign segments of a given amino acid sequence to a particular type of secondary structure, by taking into account the amino acid composition of internal parts of segments as well as their terminal and adjacent regions. Four linear discriminant functions were constructed for recognition of short and long a-helix and b-strand segments, respectively. These functions combine 3 characteristics: hydrophobic moment, segment singlet and pair preferences to an a-helix or b-strand. To improve the prediction accuracy of the method, a simple version which treats multiple sequence alignments that are used as input in place of single sequences has been developed.