Three dimensional representation of amino acid characteristics

Author

Sezerman, O.U. ; Islamaj, R. ; Alpaydin, E.

Author_Institution

Laborotory of Computational Biol., Sabanci Univ., Istanbul, Turkey

Volume

3

fYear

2001

fDate

2001

Firstpage

2903

Abstract

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.

Keywords

evolution (biological); learning (artificial intelligence); matrix algebra; molecular biophysics; organic compounds; pattern recognition; physiological models; Dayhoff model; database searches; distance mapping; evolutionally related sequences; evolutionary substitution rates; information preservation; machine learning; protein similarity score matrices; sequence profiles; similarity scores; substitution matrices; three dimensional representations; Amino acids; Artificial neural networks; Biological system modeling; Biology computing; Computational biology; Eigenvalues and eigenfunctions; Extraterrestrial measurements; Machine learning; Matrices; Protein sequence;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE

ISSN

1094-687X

Print_ISBN

0-7803-7211-5

Type

conf

DOI

10.1109/IEMBS.2001.1017397

Filename

1017397