Format

Send to

Choose Destination
J Comput Biol. 2005 Jul-Aug;12(6):777-95.

Wrap-and-Pack: a new paradigm for beta structural motif recognition with application to recognizing beta trefoils.

Author information

1
Computer Science and Artificial Intelligence Lab, Massachusetts Institute of Technology, Cambridge, MA 02139, USA.

Abstract

A method is presented that uses beta-strand interactions at both the sequence and the atomic level, to predict beta-structural motifs of protein sequences. A program called Wrap-and- Pack implements this method and is shown to recognize beta-trefoils, an important class of globular beta-structures, in the Protein Data Bank with 92% specificity and 92.3% sensitivity in cross-validation. It is demonstrated that Wrap-and-Pack learns each of the ten known SCOP beta-trefoil families, when trained primarily on beta-structures that are not beta-trefoils, together with three-dimensional structures of known beta-trefoils from outside the family. Wrap-and-Pack also predicts many proteins of unknown structure to be beta-trefoils. The computational method used here may generalize to other beta-structures for which strand topology and profiles of residue accessibility are well conserved.

PMID:
16108716
DOI:
10.1089/cmb.2005.12.777
[Indexed for MEDLINE]

Supplemental Content

Loading ...
Support Center