The PDEXK server is developed for detecting new protein families of the PD-(D/E)XK superfamily using Support Vector Machines trained on data derived from profile-profile alignments. Using a number of both superfamily-specific and general features, SVMs were trained to identify true positive alignments of PD-(D/E)XK representatives.
JPred is a Protein Secondary Structure Prediction server. JPred incorporates the Jnet algorithm in order to make more accurate predictions. In addition to protein secondary structure JPred also makes predictions on Solvent Accessibility and Coiled-coil regions (Lupas method).
MARNA (Multiple Alignment of RNAs) is a multiple alignment of RNAs taking into consideration both the primary sequence and the secondary structure. It is based on pairwise comparisons using costs of edit operations. The edit operations can be divided into edit operations on arcs and edit operations on bases. Additionally, MARNA predicts a consensus sequence as well as a consensus structure.
MP-T is a sequence-structure alignment algorithm for membrane proteins. It produces accurate sequence alignments for use in homology modelling. The inputs are a fasta-formatted sequence and an annotated structure file from the iMembrane webserver.
RCD (Random Coordinate Descent) is a versatile loop closure tool to efficiently generate loop ensembles. The algorithm solves the loop closure problem by optimizing randomly selected bonds and updating loop conformations using spinor matrices (geometric algebra).