Genome Biology

official impact factor 6.89

Open Access Method

The SeqFEATURE library of 3D functional site models: comparison to existing methods and applications to protein function annotation

Shirley Wu1, Mike P Liang2 and Russ B Altman3,4,1*

Author Affiliations

1 Program in Biomedical Informatics, Stanford University, Stanford, CA, 94305 USA

2 Google, Inc., Amphitheatre Pkwy, Mountain View, CA, 94043 USA

3 Department of Genetics, Stanford University, Stanford, CA, 94305 USA

4 Department of Bioengineering, Stanford University, Stanford, CA, 94305 USA

For all author emails, please log on.

Genome Biology 2008, 9:R8 doi:10.1186/gb-2008-9-1-r8

Published: 16 January 2008

Abstract

Structural genomics efforts have led to increasing numbers of novel, uncharacterized protein structures with low sequence identity to known proteins, resulting in a growing need for structure-based function recognition tools. Our method, SeqFEATURE, robustly models protein functions described by sequence motifs using a structural representation. We built a library of models that shows good performance compared to other methods. In particular, SeqFEATURE demonstrates significant improvement over other methods when sequence and structural similarity are low.