Algorithmic approaches to protein-protein interaction site prediction

Abstract

Interaction sites on protein surfaces mediate virtually all biological activities, and their identification holds promise for disease treatment and drug design. Novel algorithmic approaches for the prediction of these sites have been produced at a rapid rate, and the field has seen significant advancement over the past decade. However, the most current methods have not yet been reviewed in a systematic and comprehensive fashion. Herein, we describe the intricacies of the biological theory, datasets, and features required for modern protein-protein interaction site (PPIS) prediction, and present an integrative analysis of the state-of-the-art algorithms and their performance. First, the major sources of data used by predictors are reviewed, including training sets, evaluation sets, and methods for their procurement. Then, the features employed and their importance in the biological characterization of PPISs are explored. This is followed by a discussion of the methodologies adopted in contemporary prediction programs, as well as their relative performance on the datasets most recently used for evaluation. In addition, the potential utility that PPIS identification holds for rational drug design, hotspot prediction, and computational molecular docking is described. Finally, an analysis of the most promising areas for future development of the field is presented.

Are protein-protein interfaces special regions on a protein’s surface?

“…Thus, protein-protein interfaces were viewed as being special, and many efforts were made to predict these surface regions. 16,56,57 In this study, we showed that the ratio of the interface to surface residues for currently known HIs is correlated (Pearson coefficient of 0.31 with P-value of 10 −16 ) with the number of experimentally solved structures for a given protein (Figure 3(a)). Next, we calculated the interface to surface ratio including "geometric HIs" by copying HIs from the same fold templates irrespective of their sequence identity.…”

“…We examine the fraction of a protein's surface that is geometrically consistent with protein-protein interactions and compare this to the currently known ratio of interface to surface residues. Though different studies 16 use different definitions for surface and interface residues, all report the same range of values (between 25% and 35% on average) for the percent of known interface to surface amino acids.…”

“…When copying HIs from high sequence identity templates, the interface to surface ratio is almost one third, agreeing well with ratios reported in previous studies. 16 As the sequence identity cutoff of the templates for copying HIs is relaxed by including distant homologous and analogous proteins, the ratio of interface to surface residues starts to increase. The growth is at first slow (around 10%) until 30% sequence identity.…”

“…In addition, the performance of these methods was relatively poor compared to computational methods for predicting protein structures 25,37,38 or determining the catalytic sites for an enzyme. [39][40][41] The low success rates 16 of predicting PPIs suggest that there might be flaws in our understanding of the nature of PPIs. Thus, it is appropriate to revisit the fundamental concepts and assumptions about protein interfaces.…”

Utilizing knowledge base of amino acids structural neighborhoods to predict protein-protein interaction sites

“…The trained model is subsequently used when an unknown protein needs to be characterized. A number of descriptors have been utilized for the purpose of PPI identification, such as hydrophobicity [5], energy of solvatation [6], propensity [5] or RASA (Relative Solvent Accessible Surface Area) [3][4][5][6], with RASA being especially popular [7]. As for machine learning approaches, the best performing methods utilize Support Vector Machines (SVM) [3,5], Neural networks [8], Decision trees [6] or Conditional Random Fields (CRF) [9,10].…”