Three Dimensional Representation of Amino Acid Characteristics
BOGAZICI UNIV ISTANBUL (TURKEY)
Pagination or Media Count:
Amino acid substitution matrices which shows the similarity scores between pairs of amino acids have been widely used in protein sequence alignments. These matrices are based on the Dayhoff model of evolutionary substitution rates. Using machine learning techniques we obtained three dimensional representations of these matrices while preserving most of the information obtained in the matrices. Vector representation of amino acids has many applications in pattern recognition.