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.
ProAffiMuSeq is available online.
You can view the latest updates here.
Click here to learn more about the Protein Bioinformatics Lab at the Department of Biotechnology, Indian Institute of Technology Madras.