Method
The SeqFEATURE library of 3D functional site models: comparison to existing methods and applications to protein function annotation
-
* Corresponding author: Russ B Altman russ.altman@stanford.edu
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
Genome Biology 2008, 9:R8 doi:10.1186/gb-2008-9-1-r8
Published: 16 January 2008Abstract
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.