Skip Navigation

This Article
Right arrow FREE Full Text (Print PDF) Freely available
Right arrow FREE Full Text (Screen PDF)
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 ISI Web of Science
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 arrow Search for citing articles in:
ISI Web of Science (7)
Right arrowRequest Permissions
Google Scholar
Right arrow Articles by Lin, K.
Right arrow Articles by Taylor, W. R.
Right arrow Search for Related Content
PubMed
Right arrow PubMed Citation
Right arrow Articles by Lin, K.
Right arrow Articles by Taylor, W. R.
Social Bookmarking
Add to CiteULike   Add to Connotea   Add to Del.icio.us  
What's this?

Bioinformatics Vol. 18 no. 10 2002
Pages 1350-1357
© 2002 Oxford University Press

Threading Using Neural nEtwork (TUNE): the measure of protein sequence—structure compatibility

Kuang Lin 1, Alex C.W. May 1 and William R. Taylor 1,*

1 Division of Mathematical Biology, National Institute for Medical Research, The Ridgeway, Mill Hill NW7 1AA, UK

Received on November 13, 2001 ; revised on February 25, 2002 ; accepted on March 13, 2002

Motivation: Fold recognition programs align a probe protein sequence onto protein three-dimensional (3D) structure templates. The alignment between the probe sequence and the most suitable template can be used to predict the 3D structure and often biological function of the probe. Here we present a new threading scoring function of protein sequence–structure compatibility. An artificial neural network model is trained to predict compatibility of amino acid side-chains with structural environments. Log-odds scores of predicted probabilities from this model can then be used to construct protein sequence–structure alignments.

Results: Our model is tested on discrimination of native and decoy protein 3D structures. With a residue level structural description, its performance is comparable to those of pseudo-energy functions with atom level structural descriptions, better than the two functions with residue level structural descriptions.

Availability: The C++ source code of our neural network model is available at http://mathbio.nimr.mrc.ac.uk/~kxlin.

Contact: wtaylor{at}nimr.mrc.ac.uk

* To whom correspondence should be addressed.


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.