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

Program in Biomedical Informatics, Stanford University, Stanford, CA, 94305 USA. russ.altman@stanford.edu.

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.

PMID: 18197987 [PubMed - as supplied by publisher]