BIPSPI: a method for the prediction of partner-specific protein-protein interfaces.

Ruben Sanchez-Garcia,J M Carazo,C O S Sorzano,Joan Segura,Alfonso Valencia

doi:10.1093/bioinformatics/bty647

Ruben Sanchez-Garcia, J M Carazo + Show 3 more

Open Access

https://doi.org/10.1093/bioinformatics/bty647

Copy DOI

Abstract

MotivationProtein–Protein Interactions (PPI) are essentials for most cellular processes and thus, unveiling how proteins interact is a crucial question that can be better understood by identifying which residues are responsible for the interaction. Computational approaches are orders of magnitude cheaper and faster than experimental ones, leading to proliferation of multiple methods aimed to predict which residues belong to the interface of an interaction.ResultsWe present BIPSPI, a new machine learning-based method for the prediction of partner-specific PPI sites. Contrary to most binding site prediction methods, the proposed approach takes into account a pair of interacting proteins rather than a single one in order to predict partner-specific binding sites. BIPSPI has been trained employing sequence-based and structural features from both protein partners of each complex compiled in the Protein–Protein Docking Benchmark version 5.0 and in an additional set independently compiled. Also, a version trained only on sequences has been developed. The performance of our approach has been assessed by a leave-one-out cross-validation over different benchmarks, outperforming state-of-the-art methods.Availability and implementationBIPSPI web server is freely available at http://bipspi.cnb.csic.es. BIPSPI code is available at https://github.com/bioinsilico/BIPSPI. Docker image is available at https://hub.docker.com/r/bioinsilico/bipspi/.Supplementary information Supplementary data are available at Bioinformatics online.

Highlights

Protein–Protein Interactions (PPI’s) are at the basis of virtually every cellular process
Many experimental methodologies exist for the characterization of protein–protein interfaces, including mass spectrometry (Sobott and Robinson, 2002), mutagenesis (Chen et al, 2014), X-ray crystallography (Shi, 2014) or nuclear magnetic resonance (O’Connell et al, 2009)
We have presented BIPSPI, a partner-specific predictor of residue–residue contacts and protein binding sites that uses as input either protein sequences or structures

Summary

Introduction

Protein–Protein Interactions (PPI’s) are at the basis of virtually every cellular process. Several protein–protein docking approaches (Rodrigues et al, 2015; Zhang et al, 2016) have been developed to obtain atomic models for the interaction of two proteins when solved structures of both partners are available. For those other cases in which there is no structural information, or it only exists at low resolution, other methods to identify which pairs of domains are likely to bind in PPI’s have been proposed (Segura et al, 2015b; Segura et al, 2016; Wang et al, 2007)

Methods

Results

Conclusion