1097-0134/asset/PROT_centre.gif?v=1&s=77b56b1f2cdaba74cb3bb149bd9b029cd8803cdb)
Predictions from Automatic Servers
Automatic consensus-based fold recognition using Pcons, ProQ, and Pmodeller
Article first published online: 15 OCT 2003
DOI: 10.1002/prot.10536
Copyright © 2003 Wiley-Liss, Inc.
Issue
1097-0134/asset/cover.gif?v=1&s=d817e79b67ba6cacf8bdcce1a819c04de300a7e3 "Proteins: Structure, Function, and Bioinformatics")
Proteins: Structure, Function, and Bioinformatics
Supplement: Fifth Meeting on the Critical Assessment of Techniques for Protein Structure Prediction
Volume 53, Issue Supplement 6, pages 534–541, 2003
Additional Information
How to Cite
Wallner, B., Fang, H. and Elofsson, A. (2003), Automatic consensus-based fold recognition using Pcons, ProQ, and Pmodeller. Proteins, 53: 534–541. doi: 10.1002/prot.10536
Publication History
- Issue published online: 15 OCT 2003
- Article first published online: 15 OCT 2003
- Manuscript Accepted: 8 APR 2003
- Manuscript Received: 11 FEB 2003
Funded by
- Swedish Research Council
- Foundation for Strategic Research
- Carl Trygger Foundation
- Graduate Research School in Genomics and Bioinformatics
- Abstract
- Article
- References
- Cited By
Keywords:
- fold recognition;
- threading;
- LiveBench;
- CASP;
- CAFASP;
- protein structure prediction
Abstract
CASP provides a unique opportunity to compare the performance of automatic fold recognition methods with the performance of manual experts who might use these methods. Here, we show that a novel automatic fold recognition server, Pmodeller, is getting close to the performance of manual experts. Although a small group of experts still perform better, most of the experts participating in CASP5 actually performed worse even though they had full access to all automatic predictions. Pmodeller is based on Pcons (Lundström et al., Protein Sci 2001; 10(11):2354–2365) the first “consensus” predictor that uses predictions from many other servers. Therefore, the success of Pmodeller and other consensus servers should be seen as a tribute to the collective of all developers of fold recognition servers. Furthermore we show that the inclusion of another novel method, ProQ2, to evaluate the quality of the protein models improves the predictions. Proteins 2003;53:534–541. © 2003 Wiley-Liss, Inc.