PepBind is a sequence-based method for protein-peptide binding residues prediction. It combines the predictions from an ab-initio method SVMpep and two template-based methods S-SITE and TM-SITE.
SVMpep was trained with features from four complementary sequence profiles. S-SITE and TM-SITE predict the binding residues by transferring the annotations from homologous templates in a peptide-specific template library.
For a submitted query protein sequence, the returned results include the predicted peptide-binding residues with propensity scores. Read more about the PepBind algorithm...
- Z. Zhao, Z. Peng, J. Yang, Improving sequence-based prediction of protein-peptide binding residues by introducing intrinsic disorder and a consensus method, Journal of Chemical Information and Modeling, 58: 1459-1468 (2018).