NetNES 1.1 server predicts leucine-rich nuclear export signals (NES) in eukaryotic proteins using a combination of neural networks and hidden Markov models.
NetNGlyc predicts N-Glycosylation sites in human proteins using artificial neural networks that examine the sequence context of Asn-Xaa-Ser/Thr sequons.
Neural network predictions of mucin type GalNAc O-glycosylation sites in mammalian proteins.
NetPhos produces neural network predictions for serine, threonine and tyrosine phosphorylation sites in eukaryotic proteins.
The NetPhosK 1.0 server produces neural network predictions of kinase specific eukaryotic protein phosphorylation sites. Currently NetPhosK covers the following kinases: PKA, PKC, PKG, CKII, Cdc2, CaM-II, ATM, DNA PK, Cdk5, p38 MAPK, GSK3, CKI, PKB, RSK, INSR, EGFR and Src.
predict serine and threonine phosphorylation sites in yeast proteins
The NetPicoRNA 1.0 server produces neural network predictions of cleavage sites of picornaviral proteases.
Prediction of N-terminal N-myristoylation of proteins
PATS identifies amino acid sequences that are potentially targeted to the apicoplast matrix of Plasmodium falciparum. Secondary analysis of candidate sequences is required for confirmation.
Cleave a protein sequence with a chosen enzyme/protease, and computes the masses of the generated peptides. The tool also returns theoretical isoelectric point and mass values for the protein of interest. If desired, PeptideMass can return the mass of peptides known to carry post-translational modifications, and can highlight peptides whose masses may be affected by database conflicts, polymorphisms or splice variants.
Predotar was designed for systematic screening of large batches of proteins for identifying putative targeting sequences, and recognizes the N-terminal targeting sequences of classically targeted precursor proteins. It provides a probability estimate as to whether the sequence contains a mitochondrial, plastid or ER targeting sequence.
The prenylation prediction suite (PrePS) combines three predictors for protein CaaX farnesylation, CaaX geranylgeranylation and Rab geranylgeranylation in one webinterface. The predictors aim to model the substrate-enzyme interactions based on refinement of the recognition motifs for each of the prenyltransferases.
ProP 1.0 server predicts arginine and lysine propeptide cleavage sites in eukaryotic protein sequences using an ensemble of neural networks. Furin-specific prediction is the default. It is also possible to perform a general proprotein convertase (PC) prediction.
PSORT family of programs for subcellular localization prediction
predict peroxisomal targeting signal 1 containing proteins
QuickMod is a spectral library search based MSMS data analysis tool, designed to identify modified peptides. The QuickMod algorithm assumes that the precursor mass difference between a query spectrum and a candidate library spectrum can be explained by a modification. Based on this assumption the two spectra are aligned and the fit of the spectral alignment is assigned a similarity score. In a second step the most likely attachment position of the modification is determined.
The SecretomeP 2.0 server produces ab initio predictions of non-classical i.e. not signal peptide triggered protein secretion. The method queries a large number of other feature prediction servers to obtain information on various post-translational and localizational aspects of the protein, which are integrated into the final secretion prediction.
SignalP predicts the presence and location of signal peptide cleavage sites in amino acid sequences from different organisms: Gram-positive prokaryotes, Gram-negative prokaryotes, and eukaryotes. The method incorporates a prediction of cleavage sites and a signal peptide/non-signal peptide prediction based on a combination of several artificial neural networks.
This database provides a list of known carbohydrate sequences to which pathogenic organisms specifically adhere. The data were compiled through an exhaustive search of literature published over the past 30 years by glycobiologists, microbiologists, and medical histologists.
The Sulfinator is a software tool able to predict tyrosine sulfation sites in protein sequences. It employs four different Hidden Markov Models that were built to recognise sulfated tyrosine residues located N-terminally, within sequence windows of more than 25 amino acids and C-terminally, as well as sulfated tyrosines clustered within 25 amino acid windows, respectively. All four HMMs contain the distilled information from one multiple sequence alignment.