The Jnet secondary structure prediction method.  Jnet (1999) predicts the secondary structure of globular proteins from multiple sequence alignments, PSIBLAST profiles and HMMER2 profiles.  Jnet also predicts the relative solvent accesibility.  Jnet gives 76.4% average accuracy on a large test set of proteins.
  
See the Jnet distribution page  to download this program.

JNet is the default prediction method in the JPred server.

This site was last updated: Thursday, 23 June, 2005

Geoff Barton, Bioinformatics and Computational Biology Research, University of Dundee, Scotland