Spritz

A predictor of protein disorder based on kernel machines. Spritz achieves state of the art performance on cross-validation and independent assessment on CASP6 targets. A paper describing Spritz has been published in the journal Nucleic Acid Research. Access it here (toll-free link).
Spritz was developed in collaboration with Silvio Tosatto's lab at the University of Padua.

Distill@UCD

A suite of public servers for the prediction of structural features of proteins. The servers can be accessed all from a single interface which also allows the submission of multiple queries, or individually (click links below). Distill currently includes:

• Porter@UCD

  Porter is a system for the prediction of protein secondary structure in three classes (Helix, Strand, Coil). Porter's accuracy, measured by 5-fold cross-validation on a non-redundant set of 2171 proteins, exceeds 79%. An article on Porter has been published in the journal Bioinformatics. Access it here (toll-free link).

• Porter+@UCD

  Prediction of backbone structural motifs in 14 classes. A paper on Porter+'s methods has been published in the Journal of Computational Biology.

• PaleAle@UCD

  Prediction of protein relative solvent accessibility in 4 classes.

• XStout@UCD

  Prediction of protein coarse contact maps and coarse protein structures.
  A paper on X-Stout's methods has been published in the Journal of Computational Biology.

• BrownAle@UCD

  BrownAle is a server for the prediction of protein Contact Density (CD). Contact Density is a sequential encoding of the notion of contact among residues, which holds most of the information contained in the contact map, and hence provides a compact but highly informative representation of a protein's structure. A paper on BrownAle has been published in the journal BMC Bioinformatics. Access it here (toll-free link).

• Shandy@UCD

  Shandy is a server for the prediction of protein Domain Boundaries. A paper on Shandy has been published in the journal BMC Bioinformatics. Access it here (toll-free link).

• XXStout@UCD

  Prediction of protein residue contact maps. Two papers on XX-Stout's methods have been published in the journals BMC Bioinformatics and BMC Structural Biology. Access them here (toll-free link) and here (toll-free link).

• SCLpred@UCD

  SCLpred is a server for the ab initio prediction of protein subcellular localisation in eukaryotes. The server has three components, trained on proteins from: Animals; Plants; Fungi. The subcellular localisation classes we predict are 4 for Animals and Fungi (Cytoplasm; Mitochondrion; Nucleus; Secretory) and 5 for plants (the same 4 as for Animals and Fungi, plus Chloroplast). The server is based on a new neural network we have developed, and, in our tests, achieves state-of-the-art results, with correct classification rates of approximately 66-68% for plants, 70-76% for fungi and 76-78% for animals.
  A paper on SCLpred has been published in the journal Bioinformatics. Access it here.