This server predicts protein-protein binding affinity change upon mutation using sequence-based features and functional class. ProAffiMuSeq shows a correlation of 0.73 and a mean absolute error (MAE) of 0.86 kcal/mol in cross-validation. In the test dataset, the performance remains consistent with a correlation of 0.75 with MAE of 0.94 kcal/mol. In a blind dataset of 473 mutations (Geng et al. 2019, Proteins 87, 110-119) it showed a correlation and MAE of 0.27 and 1.06 kcal/mol, respectively, comparable to structure-based methods. Further, our method showed a MAE of 1.21 kcal/mol, when tested with a set of 552 additional non-redundant interface mutations in 80 complexes deposited in SKEMPI 2.0 (Jankauskaitė et al. 2019, Bioinformatics 35, 462-469).
Click here to predict the binding affinity for mutations in protein-protein complexes.
Click here to learn more about the Protein Bioinformatics Lab at the Department of Biotechnology, Indian Institute of Technology Madras.