Updated May 23, 2012
This server provides a simultaneous prediction of secondary structure and trans-membrane spans from the protein sequence thus eliminating the necessity to create a consensus prediction from possibly contradicting outputs of several predictors. An Artificial Neural Network was trained on databases of membrane proteins and soluble proteins. The output is a 3x3-dimensional matrix for each residue in the sequence containing probabilities for combinations of three secondary structure types (helix, strand, coil) and three environment types (membrane core, interface, solution). The prediction accuracies are 70.3% for nine possible states, 73.2% for three-state secondary structure prediction and 94.8% for three-state trans-membrane span prediction. These accuracies are comparable to highest quality predictors such as PsiPred or OCTOPUS but integrate secondary structure prediction with membrane environment.
Licenses (including the binary) for academic (free of charge) or commercial users (a fee applies) can be obtained from our BCL license server.
The newest version of JUFO, which is used by this server, will be available starting in version BCL 2.5.
Please cite Koehler-Leman J, Mueller R, Karakas M, Woetzel N, Meiler J, "Simultaneous prediction of protein secondary structure and trans membrane spans." Proteins 2013