GraphRBF

Note: GraphRBF is a model specifically designed to predict binding sites between proteins and proteins, as well as between proteins and nucleic acids. Users can choose the fast and the standard mode of the GraphRBF, the former just need to upload the protein structure file, while the latter need users to upload the pssm and hmm file for each protein chain. For DNA-binding protein and RNA-binding protein data, we only use monomers as training data. Users can use our service to predict protein binding sites as well as nucleic acid binding sites for query proteins.

Examples: We provide 3 test proteins corresponding to the predictions of Protein-DNA, Protein-RNA, and Protein-protein below.
GraphRBF_test_examples.zip

This work is openly licensed via CC0 1.0

Upload a PDB file (Note: the name of the file comprises the pdbID and chain(s), e.g., 6ide_B.pdb, 1a7n_AB.pdb)

Choose the ligand type

DNA

RNA

Protein

Choose the model mode

Fast mode

Standard mode

Upload the pssm File corresponding to each chain (e.g., 6ide_B.pssm or 1a7n_A.pssm, 1a7n_B.pssm). You can run PSI-BLAST against the Uniref90 protein database to generate PSSM file.

Upload the hhm File corresponding to each chain (e.g., 6ide_B.hhm or 1a7n_A.hhm, 1a7n_B.hhm). You can run HHblits against the Uniclust30_2018_08 protein database to generate HMM file.