Services are gradually being migrated to
Please try out the new site.

Prediction Servers

This page is the main entry to the on-line prediction services at CBS. All the servers are available as interactive input forms. In order to view the full documentation and use a server click on the appropriate link in the list below. The access to all the servers is free and unlimited for all academic users. For other users the access is also free but limited (see the details of the access policy).

Most of the servers are also available as stand-alone software packages to install and run at the user's site, with the same functionality. Ready-to-ship packages exist for the most common UNIX platforms. See the new Health Tech site for downloads.

On this page all the available options for a given service become visible on mouse over the name of the service.


Gene finding and splice sites

« EasyGene
Genes in prokaryotes
« HMMgene
Genes in eukaryotes
Identification of risk genes in complex phenotypes
Intron splice sites in Aspergillus DNA
« NetGene2
Intron splice sites in human, C. elegans and A. thaliana DNA
Intron splice sites in Arabidopsis thaliana DNA
« NetStart
Translation start in vertebrate and A. thaliana DNA
Splice sites in 5' UTR regions of human genes
« Promoter
Transcription start sites in vertebrate DNA
« RNAmmer
Ribosomal RNA sub units

Analysis of DNA microarray data

« OligoWiz
Design of oligonucleotides for DNA microarrays

Genomic epidemiology

Prediction of bacterial species using a fast K-mer algorithm
Multi Locus Sequence Typing (MLST) from an assembled genome or from a set of reads
Phylogenic tree from reads using nucleotide difference method
Prediction of a bacteria's pathogenicity towards human hosts
Identifcation of acquired antibiotic resistance genes
SNPs phylogenetic tree from assembled genomes or sets of reads
Fast DNA search engine


Analysing DNA barcode sequencing data
Assembles Sanger reads, identifies and blasts ORFs, annotation
Tissue of origin of tumors from genomics data


Chemical-protein interactions
Food-disease associations
pH-dependent aqueous solubility of druglike molecules


Protein sorting

ChloroP »
Chloroplast transit peptides and their cleavage sites in plant proteins
DeepLoc »
Prediction of eukaryotic protein subcellular localization using deep learning
LipoP »
Signal peptidase I & II cleavage sites in gram- bacteria
NetNES »
Leucine-rich nuclear export signals (NES) in eukaryotic proteins
SecretomeP »
Non-classical and leaderless secretion of proteins
SignalP »
Signal peptides and cleavage sites in amino acid sequences from all domains of life
TargetP »
Subcellular location of proteins: mitochondrial, chloroplastic, secretory pathway, or other
TatP »
Twin-arginine signal peptides

Post-translational modifications of proteins

O-(alpha)-GlcNAc glycosylation sites (trained on Dictyostelium discoideum proteins)
N-terminal acetylation in eukaryotic proteins
NetCGlyc »
C-mannosylation sites in mammalian proteins
Coronavirus 3C-like proteinase cleavage sites in proteins
Glycation of ε amino groups of lysines in mammalian proteins
NetNGlyc »
N-linked glycosylation sites in human proteins
NetOGlyc »
O-GalNAc (mucin type) glycosylation sites in mammalian proteins
Linear motif atlas for phosphorylation-dependent signaling
NetPhos »
Generic phosphorylation sites in eukaryotic proteins
Generic phosphorylation sites in bacterial proteins
Kinase specific phosphorylation sites in eukaryotic proteins
Prediction of phosphorylation using convolutional neural networks
Serine and threonine phosphorylation sites in yeast proteins
In vivo kinase-substrate relationships
ProP »
Arginine and lysine propeptide cleavage sites in eukaryotic protein sequences
YinOYang »
O-(beta)-GlcNAc glycosylation and Yin-Yang sites (intracellular/nuclear proteins)

Immunological features

Residue-level epitope mapping of antigens based on peptide microarray data
BepiPred »
Linear B-cell epitopes
DiscoTope »
Discontinuous B-cell epitopes
Patient-specific HLA restriction elements and optimal epitopes within peptides
Lymphocyte receptor automated modelling
MHCcluster: MHC clustring based on binding specififcity
Prediction of neo-epitopes from tumor sequencing data
NetChop »
Proteasomal cleavages (MHC ligands)
NetCTL »
Integrated class I antigen presentation
NetCTLpan »
Pan-specific integrated class I antigen presentation
Version of NetMHCpan dedicated to mouse MHC molecules
NetMHC »
NetMHC: Binding of peptides to MHC class I molecules
NetMHCcons »
Binding of peptides to any known MHC class I molecule
NetMHCII: Binding of peptides to MHC class II molecules
NetMHCIIpan »
Pan-specific binding of peptides to MHC class II alleles of known sequence
NetMHCpan »
Pan-specific binding of peptides to MHC class I alleles of known sequence
NetMHCstab »
Stability of peptide:MHC-I complexes
NetMHCstabpan »
Pan-specific stability of peptide:MHC-I complexes
NetTepi »
T-cell epitopes restricted to prevalent HLA-A and HLA-B molecules
NNAlign »
Identifying sequence motifs in quantitative peptide data
PickPocket »
Binding of peptides to any known MHC class I molecule using binding pocket matrix extrapolation
VDJsolver »
Analysis of human immunoglobulin VDJ recombination

Protein function and structure

Enzyme/non-enzyme and enzyme class (Archaea)
Cofactory »
Identification of Rossmann folds and prediction of FAD, NAD and NADP specificity
Protein structure from sequence: distance constraints
Protein distance constraints
Functional differences of protein variants
Co-evolving amino acids in proteins
Predicts whether a single non-synonymous SNP causes a disease or is invariant
NetSurfP »
Protein secondary structure and relative solvent accessibility
NetTurnP »
β-turns and β-turn types in proteins
Protein functional category and enzyme class (Eukarya)
Reduction of sequence similarity in a data set
Identification of residue-level genotype-phenotype correlations in protein multiple sequence alignments
Prediction of GH enzyme melting temperature at pH 5.0
Transmembrane helices in proteins
Domains in the malaria antigen family PfEMP1