Inter-protein residue covariation information unravels physically interacting protein dimers

Abstract

Background Predicting physical interaction between proteins is one of the greatest challenges in computational biology. There are considerable various protein interactions and a huge number of protein sequences and synthetic peptides with unknown interacting counterparts. Most of co-evolutionary methods discover a combination of physical interplays and functional associations. However, there are only a handful of approaches which specifically infer physical interactions. Hybrid co-evolutionary methods exploit inter-protein residue coevolution to unravel specific physical interacting proteins. In this study, we introduce a hybrid co-evolutionary-based approach to predict physical interplays between pairs of protein families, starting from protein sequences only. Results In the present analysis, pairs of multiple sequence alignments are constructed for each dimer and the covariation between residues in those pairs are calculated by CCMpred (Contacts from Correlated Mutations predicted) and three mutual information based approaches for ten accessible surface area threshold groups. Then, whole residue couplings between proteins of each dimer are unified into a single Frobenius norm value. Norms of residue contact matrices of all dimers in different accessible surface area thresholds are fed into support vector machine as single or multiple feature models. The results of training the classifiers by single features show no apparent different accuracies in distinct methods for different accessible surface area thresholds. Nevertheless, mutual information product and context likelihood of relatedness procedures may roughly have an overall higher and lower performances than other two methods for different accessible surface area cut-offs, respectively. The results also demonstrate that training support vector machine with multiple norm features for several accessible surface area thresholds leads to a considerable improvement of prediction performance. In this context, CCMpred roughly achieves an overall better performance than mutual information based approaches. The best accuracy, sensitivity, specificity, precision and negative predictive value for that method are 0.98, 1, 0.962, 0.96, and 0.962, respectively. Conclusions In this paper, by feeding norm values of protein dimers into support vector machines in different accessible surface area thresholds, we demonstrate that even small number of proteins in pairs of multiple alignments could allow one to accurately discriminate between positive and negative dimers.

Evolutionary Rate Covariation is a reliable predictor of co-functional interactions but not necessarily physical interactions

“…There are two hypotheses addressing the relative contributions of physical interaction versus co-function to correlated evolutionary rates. The idea that physical interactions contribute more to correlated evolutionary rates hinges on the maintenance of proper binding [11][12][13] . Under this hypothesis, a mutation in one binding partner will result in a compensatory mutation in the other, i.e.…”

The Importance of Weakly Co-Evolving Residue Networks in Proteins is Revealed by Visual Analytics

“…The most successful have either been restricted to specific proteins, placed cumbersome restrictions on the sequences analyzed, or applied complex models from which biological understanding is hard to extract ( Halperin et al, 2006 ; Gomes et al, 2012 ; Ovchinnikov et al, 2014 ; Jia et al, 2020 ). Machine Learning has demonstrated that co-evolution data, in its entirety, does contain information about structure ( Schaarschmidt et al, 2018 ; Salmanian et al, 2020 ; Li et al, 2021 ). In particular AlphaFold and AlphaFold2 have shown that deep learning that incorporates covariation in homologous sequences can significantly improve the prediction of tertiary structure ( Senior et al, 2020 ; Jumper et al, 2021 ).…”