IntPred: a structure-based predictor of protein–protein interaction sites

Abstract Motivation Protein–protein interactions are vital for protein function with the average protein having between three and ten interacting partners. Knowledge of precise protein–protein interfaces comes from crystal structures deposited in the Protein Data Bank (PDB), but only 50% of structures in the PDB are complexes. There is therefore a need to predict protein–protein interfaces in silico and various methods for this purpose. Here we explore the use of a predictor based on structural features and which exploits random forest machine learning, comparing its performance with a number of popular established methods. Results On an independent test set of obligate and transient complexes, our IntPred predictor performs well (MCC = 0.370, ACC = 0.811, SPEC = 0.916, SENS = 0.411) and compares favourably with other methods. Overall, IntPred ranks second of six methods tested with SPPIDER having slightly better overall performance (MCC = 0.410, ACC = 0.759, SPEC = 0.783, SENS = 0.676), but considerably worse specificity than IntPred. As with SPPIDER, using an independent test set of obligate complexes enhanced performance (MCC = 0.381) while performance is somewhat reduced on a dataset of transient complexes (MCC = 0.303). The trade-off between sensitivity and specificity compared with SPPIDER suggests that the choice of the appropriate tool is application-dependent. Availability and implementation IntPred is implemented in Perl and may be downloaded for local use or run via a web server at www.bioinf.org.uk/intpred/. Supplementary information Supplementary data are available at Bioinformatics online.

[1]  Trevor Hastie,et al.  The Elements of Statistical Learning , 2001 .

[2]  Ian H. Witten,et al.  The WEKA data mining software: an update , 2009, SKDD.

[3]  Peng Chen,et al.  Predicting protein interaction sites from residue spatial sequence profile and evolution rate , 2006, FEBS Letters.

[4]  Robert P. Sheridan,et al.  Random Forest: A Classification and Regression Tool for Compound Classification and QSAR Modeling , 2003, J. Chem. Inf. Comput. Sci..

[5]  Kesheng Liu,et al.  Information Flow Analysis of Interactome Networks , 2009, PLoS Comput. Biol..

[6]  T. Takagi,et al.  Prediction of protein-protein interaction sites using support vector machines. , 2004, Protein engineering, design & selection : PEDS.

[7]  A. Bogan,et al.  Anatomy of hot spots in protein interfaces. , 1998, Journal of molecular biology.

[8]  B. Dijkstra,et al.  Model building of disulfide bonds in proteins with known three-dimensional structure. , 1988, Protein engineering.

[9]  R. Nussinov,et al.  Principles of protein-protein interactions: what are the preferred ways for proteins to interact? , 2008, Chemical reviews.

[10]  R. Raz,et al.  ProMate: a structure based prediction program to identify the location of protein-protein binding sites. , 2004, Journal of molecular biology.

[11]  Xiaoying Wang,et al.  Protein-protein interaction sites prediction by ensemble random forests with synthetic minority oversampling technique , 2018, Bioinform..

[12]  Huan‐Xiang Zhou,et al.  Prediction of protein interaction sites from sequence profile and residue neighbor list , 2001, Proteins.

[13]  Alexandre M J J Bonvin,et al.  How proteins get in touch: interface prediction in the study of biomolecular complexes. , 2008, Current protein & peptide science.

[14]  Aleksey A. Porollo,et al.  Prediction‐based fingerprints of protein–protein interactions , 2006, Proteins.

[15]  R. Doolittle,et al.  A simple method for displaying the hydropathic character of a protein. , 1982, Journal of molecular biology.

[16]  Song Liu,et al.  Protein binding site prediction using an empirical scoring function , 2006, Nucleic acids research.

[17]  Andrew C. R. Martin,et al.  BiopLib and BiopTools—a C programming library and toolset for manipulating protein structure , 2015, Bioinform..

[18]  David A. Lee,et al.  Functional classification of CATH superfamilies: a domain-based approach for protein function annotation , 2015, Bioinform..

[19]  Huan-Xiang Zhou,et al.  Prediction of interface residues in protein–protein complexes by a consensus neural network method: Test against NMR data , 2005, Proteins.

[20]  David R. Westhead,et al.  Improved prediction of protein-protein binding sites using a support vector machines approach. , 2005, Bioinformatics.

[21]  Huan-Xiang Zhou,et al.  meta-PPISP: a meta web server for protein-protein interaction site prediction , 2007, Bioinform..

[22]  Andrew C. R. Martin.  Databases and ontologies Mapping PDB chains to UniProtKB entries , 2005 .

[23]  B. Rost,et al.  Predicted protein–protein interaction sites from local sequence information , 2003, FEBS letters.

[24]  Jingpu Zhang,et al.  XGBPRH: Prediction of Binding Hot Spots at Protein–RNA Interfaces Utilizing Extreme Gradient Boosting , 2019, Genes.

[25]  Ian H. Witten,et al.  Data mining: practical machine learning tools and techniques, 3rd Edition , 1999 .

[26]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[27]  Huan-Xiang Zhou,et al.  Interaction-site prediction for protein complexes: a critical assessment , 2007, Bioinform..

[28]  E. Baker,et al.  Hydrogen bonding in globular proteins. , 1984, Progress in biophysics and molecular biology.

[29]  C. Chothia,et al.  The atomic structure of protein-protein recognition sites. , 1999, Journal of molecular biology.

[30]  András Fiser,et al.  Protein—protein binding supersites , 2019, PLoS Comput. Biol..

[31]  Ruben Abagyan,et al.  Statistical analysis and prediction of protein–protein interfaces , 2005, Proteins.

[32]  E. Myers,et al.  Basic local alignment search tool. , 1990, Journal of molecular biology.

[33]  Andrew C. R. Martin,et al.  The SAAP pipeline and database: tools to analyze the impact and predict the pathogenicity of mutations , 2013, BMC Genomics.

[34]  Nelson Gil,et al.  Discovery of receptor‐ligand interfaces in the immunoglobulin superfamily , 2020, Proteins.

[35]  Erich E. Wanker,et al.  Comparison of Human Protein-Protein Interaction Maps , 2007, German Conference on Bioinformatics.

[36]  J. Thornton,et al.  Protein–protein interfaces: Analysis of amino acid conservation in homodimers , 2001, Proteins.

[37]  Robert C. Edgar,et al.  MUSCLE: multiple sequence alignment with high accuracy and high throughput. , 2004, Nucleic acids research.

[38]  A. Valencia,et al.  Prediction of protein--protein interaction sites in heterocomplexes with neural networks. , 2002, European journal of biochemistry.

[39]  S. Jones,et al.  Analysis of protein-protein interaction sites using surface patches. , 1997, Journal of molecular biology.

[40]  W. Kabsch,et al.  Dictionary of protein secondary structure: Pattern recognition of hydrogen‐bonded and geometrical features , 1983, Biopolymers.

[41]  Guoli Wang,et al.  PISCES: a protein sequence culling server , 2003, Bioinform..

[42]  S. Fletcher,et al.  Targeting protein–protein interactions by rational design: mimicry of protein surfaces , 2006, Journal of The Royal Society Interface.

[43]  Andrew C. R. Martin,et al.  Automatically extracting functionally equivalent proteins from SwissProt , 2008, BMC Bioinformatics.

[44]  Ruben Abagyan,et al.  PIER: Protein interface recognition for structural proteomics , 2007, Proteins.

[45]  P. Bourne,et al.  Exploiting sequence and structure homologs to identify protein–protein binding sites , 2005, Proteins.

[46]  Arun K. Ramani,et al.  Protein interaction networks from yeast to human. , 2004, Current opinion in structural biology.

[47]  Frank K. Pettit,et al.  HotPatch: a statistical approach to finding biologically relevant features on protein surfaces. , 2007, Journal of molecular biology.

[48]  Steve Horvath,et al.  Tumor classification by tissue microarray profiling: random forest clustering applied to renal cell carcinoma , 2005, Modern Pathology.

[49]  Jean-Christophe Nebel,et al.  Progress and challenges in predicting protein interfaces , 2015, Briefings Bioinform..

[50]  Adele Cutler,et al.  An application of Random Forests to a genome-wide association dataset: Methodological considerations & new findings , 2010, BMC Genetics.

[51]  Andrew C. R. Martin,et al.  The structural effects of mutations can aid in differential phenotype prediction of beta-myosin heavy chain (Myosin-7) missense variants , 2016, Bioinform..

[52]  K. Henrick,et al.  Inference of macromolecular assemblies from crystalline state. , 2007, Journal of molecular biology.

[53]  Hongbo Zhu,et al.  NOXclass: prediction of protein-protein interaction types , 2006, BMC Bioinformatics.