TY - JOUR
AU - Rychlewski, Leszek
AB - Motivation: Consensus structure prediction methods (meta-predictors) have higher accuracy than individual structure prediction algorithms(their  components). The goal for the development of the 3D-Jurysystem is to create  a simple but powerful procedure forgenerating meta-predictions using  variable sets of modelsobtained from diverse sources. The resulting  protocol shouldhelp to improve the quality of structural annotations of  novelproteins.Results: The 3D-Jury system generates meta-predictions from sets ofmodels  created using variable methods. It is not necessary toknow prior  characteristics of the methods. The system is ableto utilize immediately  new components (additional predictionproviders). The accuracy of the system  is comparable with otherwell-tuned prediction servers. The algorithm  resembles methodsof selecting models generated using ab initio foldingsimulations.  It is simple and offers a portable solution to improvethe accuracy of other  protein structure prediction protocols.Availability: The 3D-Jury system is available via the Structure PredictionMeta Server (http://BioInfo.PL/Meta/)to the academic community.Contact: leszek@bioinfo.plSupplementary information:  3D-Jury is coupled to the continuous online server evaluation program, LiveBench(http://BioInfo.PL/LiveBench/)*To whom correspondenceshould be addressed.
TI - 3D-Jury: a simple approach to improve protein structure predictions
JF - Bioinformatics
DO - 10.1093/bioinformatics/btg124
DA - 2003-05-22
UR - https://www.deepdyve.com/lp/oxford-university-press/3d-jury-a-simple-approach-to-improve-protein-structure-predictions-Vxir5C2A0H
SP - 1015
EP - 1018
VL - 19
IS - 8
DP - DeepDyve
ER -