1 - 15 of 15 results


star_border star_border star_border star_border star_border
star star star star star
A pipeline for the computational design of peptides binding to a given protein surface. PepComposer only requires the target protein structure and an approximate definition of the binding site as input. It first retrieves a set of peptide backbone scaffolds from monomeric proteins that harbor the same backbone arrangement as the binding site of the protein of interest. Next, it designs optimal sequences for the identified peptide scaffolds. The method is fully automatic and available as a web server.


Predicts peptides binding to the Hsp70 chaperone Binding immunoglobulin Protein (BiP). BiPPred is based on the amino acid probability at each specific sequence position of the bound peptide. It was able to correctly predict about 80 % of the strong binders and nonbinders in the benchmark set. The tool allows the development of sequence-based prediction models for protein-peptide systems for which no or only few experimental data sets are available and for which no sequence-based prediction models exist currently.


Predicts peptide-binding sites giving a protein structure and a peptide sequence. PEP-SiteFinder is a service that identifies the peptide-binding site without any knowledge of the potential interaction site. The software combines the 3D de novo prediction of the peptide structure and the blind docking of peptide predicted conformations using a coarse-grained representation. It provides useful information to guide mutagenesis experiments to probe peptide–protein interactions or to provide starting points for more accurate peptide–protein docking experiments.

SPRINT-str / Structure-based prediction of protein-Peptide Residue-level INTeraction

Predicts protein-peptide binding residues from protein 3D structure. SPRINT-Str is a machine learning-based approach to calculates putative protein-peptide binding residues and binding sites. These predicted binding residues are then employed to infer the peptide-binding site by a clustering algorithm. This application achieves consistent results for prediction of protein-peptide binding regions in terms of residues and sites.


Predicts protein-protein, protein-peptide, protein-DNA and protein-RNA binding sites. Multi-VORFFIP utilizes a wide range of structural, evolutionary, experimental and energy-based information that is integrated into a common probabilistic framework by means of a Random Forest (RF) ensemble classifier. It is a centralized resource for the prediction of functional sites and is interfaced by a powerful web application tailored to facilitate the use of the method and analysis of predictions to non-expert end-users.

OSML / On-Site Model for Ligand binding sites prediction

Predicts protein-ligand binding sites. OSML constructs query-driven prediction model and optimizes it before the prediction task. It is able to perform protein-ligand binding sites prediction for ten different ligand types on three different levels. The tool uses the hypothesis that similar sequences will have similar functionalities. It can be enriched by incorporating new ligand types and new annotated sequences into the base dataset.

SPRINT / Sequence-based prediction of Protein–peptide Residue-level Interaction sites

Makes Sequence-based prediction of Protein–peptide Residue-level Interactions. SPRINT shows comparable or more accurate than structure-based methods for peptide-binding site prediction. It yields a robust and consistent performance for 10-fold cross validations and independent test. The tool, based on a support vector machine (SVM) model, uses known protein– peptide complex structures for training and independent test.