Skip Navigation



Bioinformatics Advance Access published online on April 23, 2009
Bioinformatics, doi:10.1093/bioinformatics/btp257
This Article
Right arrow Advance Access manuscript (PDF)
Right arrow All Versions of this Article:
25/12/1492    most recent
btp257v1
Right arrow Comments: Submit a response
Right arrow Alert me when this article is cited
Right arrow Alert me when Comments are posted
Right arrow Alert me if a correction is posted
Services
Right arrow Email this article to a friend
Right arrow Similar articles in this journal
Right arrow Similar articles in PubMed
Right arrow Alert me to new issues of the journal
Right arrow Add to My Personal Archive
Right arrow Download to citation manager
Right arrowRequest Permissions
Google Scholar
Right arrow Articles by Spriggs, R.V.
Right arrow Articles by Jones, S.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Spriggs, R.V.
Right arrow Articles by Jones, S.
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?

© The Author (2009). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oxfordjournals.org

Protein function annotation from sequence: prediction of residues interacting with RNA

R.V. Spriggs 1,#, Y. Murakami 2,#, H. Nakamura 2 and S. Jones 1,*

1Department of Chemistry and Biochemistry, School of Life Sciences, John Maynard-Smith Building, University of Sussex, Falmer, Brighton, BN1 9QG, UK.
2Research Centre for Structural and Functional Proteomics, Institute for Protein Research, Osaka University, Japan.

*To whom correspondence should be addressed. Dr. Susan Jones, E-mail: s.jones{at}sussex.ac.uk


  Abstract

Motivation: All eukaryotic proteomes are characterised by a significant percentage of proteins of unknown function. Computational function prediction methods are therefore essential as initial steps in the function annotation process. This paper describes an annotation method (PiRaNhA) for the prediction of RNA-binding residues from protein sequence information. A series of sequence properties (posi-tion specific scoring matrices, interface propensities, predicted ac-cessibility and hydrophobicity) are used to train a support vector machine. This method is then evaluated for its potential to be ap-plied to RNA-binding function prediction at the level of the complete protein.

Results: Five-fold cross-validation of PiRaNhA on a dataset of 81 RNA-binding proteins achieves a Matthews Correlation Coefficient (MCC) of 0.50 and accuracy of 87.2%. When used to predict RNA-binding residues in 42 proteins not used in training, PiRaNhA achieves an MCC of 0.41 and accuracy of 84.5%. Decision values from the PiRaNhA predictions were used in a second SVM to make predictions of RNA-binding function at the protein level, achieving an MCC of 0.53 and accuracy of 76.1%. The PiRaNhA RNA-binding residue predictions allow experimentalists to perform more targeted experiments for function annotation; and the prediction of RNA-binding function at the protein level shows promise for proteome-wide annotations.

Availability and Implementation: Freely available on the web at www.bioinformatics.sussex.ac.uk/PIRANHA or http://piranha.protein.osaka-u.ac.jp.

Contact: s.jones{at}sussex.ac.uk.

Supplementary Information: Supplementary material is available at the journal's web site.

Associate Editor: Prof. Burkhard Rost

# Joint first authors

Received on January 28, 2009; revised on March 24, 2009; accepted on April 8, 2009

Add to CiteULike CiteULike   Add to Connotea Connotea   Add to Del.icio.us Del.icio.us    What's this?




Disclaimer: Please note that abstracts for content published before 1996 were created through digital scanning and may therefore not exactly replicate the text of the original print issues. All efforts have been made to ensure accuracy, but the Publisher will not be held responsible for any remaining inaccuracies. If you require any further clarification, please contact our Customer Services Department.