Predicting N-terminal acetylation based on feature selection method.

Methionine aminopeptidase and N-terminal acetyltransferase are two enzymes that contribute most to the N-terminal acetylation, which has long been recognized as a frequent and important kind of co-translational modifications [R.A. Bradshaw, W.W. Brickey, K.W. Walker, N-terminal processing: the methionine aminopeptidase and N alpha-acetyl transferase families, Trends Biochem. Sci. 23 (1998) 263-267]. The combined action of these two enzymes leads to two types of N-terminal acetylated proteins that are with/without the initiator methionine after the N-terminal acetylation. To accurately predict these two types of N-terminal acetylation, a new method based on feature selection has been developed. 1047 N-terminal acetylated and non-acetylated decapeptides retrieved from Swiss-Prot database (http://cn.expasy.org) are encoded into feature vectors by amino acid properties collected in Amino Acid Index database (http://www.genome.jp/aaindex). The Maximum Relevance Minimum Redundancy method (mRMR) combining with Incremental Feature Selection (IFS) and Feature Forward Selection (FFS) is then applied to extract informative features. Nearest Neighbor Algorithm (NNA) is used to build prediction models. Tested by Jackknife Cross-Validation, the correct rate of predictors reach 91.34% and 75.49% for each type, which are both better than that of 84.41% and 62.99% acquired by using motif methods [S. Huang, R.C. Elliott, P.S. Liu, R.K. Koduri, J.L. Weickmann, J.H. Lee, L.C. Blair, P. Ghosh-Dastidar, R.A. Bradshaw, K.M. Bryan, et al., Specificity of cotranslational amino-terminal processing of proteins in yeast, Biochemistry 26 (1987) 8242-8246; R. Yamada, R.A. Bradshaw, Rat liver polysome N alpha-acetyltransferase: substrate specificity, Biochemistry 30 (1991) 1017-1021]. Furthermore, the analysis of the informative features indicates that at least six downstream residues might have effect on the rules that guide the N-terminal acetylation, besides the penultimate residue. The software is available upon request.

[1]  Ralph A. Bradshaw,et al.  N-Terminal processing: the methionine aminopeptidase and Nα-acetyl transferase families , 1998 .

[2]  G von Heijne,et al.  Structures of N-terminally acetylated proteins. , 1985, European journal of biochemistry.

[3]  R A Bradshaw,et al.  Eukaryotic methionyl aminopeptidases: two classes of cobalt-dependent enzymes. , 1995, Proceedings of the National Academy of Sciences of the United States of America.

[4]  Fuhui Long,et al.  Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy , 2003, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[5]  F. Sherman,et al.  N-terminal acetyltransferases and sequence requirements for N-terminal acetylation of eukaryotic proteins. , 2003, Journal of molecular biology.

[6]  Kuo-Chen Chou,et al.  Predicting membrane protein type by functional domain composition and pseudo-amino acid composition. , 2006, Journal of theoretical biology.

[7]  S. Arfin,et al.  Cotranslational processing and protein turnover in eukaryotic cells. , 1988, Biochemistry.

[8]  M. Gautschi,et al.  The Yeast Nα-Acetyltransferase NatA Is Quantitatively Anchored to the Ribosome and Interacts with Nascent Polypeptides , 2003, Molecular and Cellular Biology.

[9]  F Sherman,et al.  Methionine or not methionine at the beginning of a protein , 1985, BioEssays : news and reviews in molecular, cellular and developmental biology.

[10]  R. Bradshaw,et al.  Rat liver polysome N alpha-acetyltransferase: substrate specificity. , 1991, Biochemistry.

[11]  R A Bradshaw,et al.  Specificity of cotranslational amino-terminal processing of proteins in yeast. , 1987, Biochemistry.

[12]  Minoru Kanehisa,et al.  AAindex: Amino Acid index database , 2000, Nucleic Acids Res..

[13]  W. D. de Jong,et al.  The mechanism of N-terminal acetylation of proteins. , 1985, CRC critical reviews in biochemistry.

[14]  K. Chou,et al.  Prediction of protein structural classes. , 1995, Critical reviews in biochemistry and molecular biology.

[15]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[16]  R. Bradshaw,et al.  N-terminal processing: the methionine aminopeptidase and N alpha-acetyl transferase families. , 1998, Trends in biochemical sciences.