Protein-protein interactions (PPIs) mediate the majority of key cellular activities, and it is well established that disease causing mutations are enriched at these interfaces. In addition, changes in binding affinity caused by single-point mutations are known to directly disturb PPIs involved in in signalling pathways tightly related to Mendelian diseases and cancer.
We have developed a platform of programs using a novel machine learning method that uses graph-based structural signatures called mCSM. This has been shown to be an accurate and high-throughput approach to predict the impact of mutations on protein structure and function, and was one of the first methods capable of assessing the impact of mutations on protein interaction binding affinity. Here we present mCSM-PPI2, a tool that implements an integrated computational approach for predicting effects of missense mutations in protein-protein affinity. To train mCSM-PPI2 we collected experimental data from the recently updated SKEMPI2 database, comprising 4169 point mutations (25% and 75% of which increased and decreased protein-protein affinity, respectively. Our new predictive model was capable of achieving a Pearson correlation of up to 0.83 during cross-validation, outperforming similar methods and presenting a balanced performance between increase and decrease affinity mutations with a Pearson correlation of 0.75 and 0.76 respectively. mCSM-PPI2 also performed better in low-redundancy data sets achieving a correlation coefficient of up to 0.77 and 0.71 (on leave-one complex out cross-validation and low-redundancy on protein-level, respectively). Our method was further validated against the CAPRI round 26 (targets 55 and 56), which comprised 1862 mutations that have been experimentally tested, mCSM-PPI2 achieved a Kendall’s score of up 0.41 and 0.34, respectively, ranking first amongst 23 other methods.
To facilitate the rapid characterisation of how variants are likely to affect PPIs, we have made mCSM-PPI2 freely available as a user friendly and easy to use web server at http://biosig.unimelb.edu.au/mcsm_ppi2/.