An accurate classification of native and non-native protein-protein interactions using supervised and semi-supervised learning approaches

Abstract

The progress in experimental and computational structural biology has led to a rapid growth of experimentally resolved structures and computational models of proteinprotein interactions. However, distinguishing between the physiological and non-physiological interactions remains a challenging problem. In this work, two related problems of interface classification have been addressed. The first problem is concerned with classification of the physiological and crystalpacking interactions. The second problem deals with the classification of the physiological interactions, or their accurate models, and decoys obtained from the inaccurate docking models. We have defined a universal set of interface features and employed supervised and semi-supervised learning approaches to accurately classify the interactions in both problems. Furthermore, we formulated the second problem as a semi-supervised learning problem and employed a transductive SVM to improve the accuracy of classification. Finally, we showed that using the scoring functions from the obtained classifiers, one can improve the accuracy of the docking methods.

An Ensemble Classifiers for Improved Prediction of Native–Non-Native Protein–Protein Interaction

“…Each of the eight features provided from MD simulations plays a specific role in differentiating between native and non-native protein–protein interactions (PPIs). The term “native” refers to interactions that occur under physiological conditions within an organism; on the other hand, “non-native” refers to interactions that occur under non-physiological conditions [ 71 , 72 ]. Native interactions, on average more stable [ 73 ], involve properly folded proteins in their native conformations, engaging in specific and biologically relevant interactions that contribute to various cellular processes [ 74 ], while non-native interactions involve proteins that are not properly folded, leading to aberrant protein conformations [ 75 ].…”