BACKGROUND: Protein-protein interactions (PPI) play a key role in an investigation of various biochemical processes, and their identification is thus of great importance. Although computational prediction of which amino acids take part in a PPI has been an active field of research for some time, the quality of in-silico methods is still far from perfect. RESULTS: We have developed a novel prediction method called INSPiRE which benefits from a knowledge base built from data available in Protein Data Bank. All proteins involved in PPIs were converted into labeled graphs with nodes corresponding to amino acids and edges to pairs of neighboring amino acids. A structural neighborhood of each node was then encoded into a bit string and stored in the knowledge base. When predicting PPIs, INSPiRE labels amino acids of unknown proteins as interface or non-interface based on how often their structural neighborhood appears as interface or non-interface in the knowledge base. We evaluated INSPiRE's behavior with respect to different types and sizes of the structural neighborhood. Furthermore, we examined the suitability of several different features for labeling the nodes. Our evaluations showed that INSPiRE clearly outperforms existing methods with respect to Matthews correlation coefficient. CONCLUSION: In this paper we introduce a new knowledge-based method for identification of protein-protein interaction sites called INSPiRE. Its knowledge base utilizes structural patterns of known interaction sites in the Protein Data Bank which are then used for PPI prediction. Extensive experiments on several well-established datasets show that INSPiRE significantly surpasses existing PPI approaches.

Department of Software Engineering Faculty of Mathematics and Physics Charles University Ke Karlovu 3 Prague 2 Czech Republic

Zobrazit více v PubMed

Esmaielbeiki R, Krawczyk K, Knapp B, Nebel JC, Deane CM. Progress and challenges in predicting protein interfaces. Brief Bioinform. 2015. doi:10.1093/bib/bbv027. http://bib.oxfordjournals.org/content/early/2015/05/12/bib.bbv027.full.pdf+html. PubMed DOI PMC

Reš I, Mihalek I, Lichtarge O. An evolution based classifier for prediction of protein interfaces without using protein structures. Bioinformatics. 2005;21(10):2496–501. doi: 10.1093/bioinformatics/bti340. PubMed DOI

Zhang QC, Petrey D, Norel R, Honig BH. Protein interface conservation across structure space. Proc Natl Acad Sci. 2010;107(24):10896–901. doi: 10.1073/pnas.1005894107. PubMed DOI PMC

Zhang QC, Deng L, Fisher M, Guan J, Honig B, Petrey D. Predus: a web server for predicting protein interfaces using structural neighbors. Nucleic Acids Res. 2011;39(suppl 2):283–7. doi: 10.1093/nar/gkr311. PubMed DOI PMC

Zellner H, Staudigel M, Trenner T, Bittkowski M, Wolowski V, Icking C, Merkl R. Prescont: Predicting protein-protein interfaces utilizing four residue properties. Proteins Struct Funct Bioinforma. 2012;80(1):154–68. doi: 10.1002/prot.23172. PubMed DOI

Bendell CJ, Liu S, Aumentado-Armstrong T, Istrate B, Cernek PT, Khan S, Picioreanu S, Zhao M, Murgita RA. Transient protein-protein interface prediction: datasets, features, algorithms, and the rad-t predictor. BMC Bioinformatics. 2014;15(1):1–12. doi: 10.1186/1471-2105-15-82. PubMed DOI PMC

Aumentado-Armstrong TT, Istrate B, Murgita RA. Algorithmic approaches to protein-protein interaction site prediction. Algoritm Mol Biol. 2015;10(1):1–21. doi: 10.1186/s13015-014-0028-y. PubMed DOI PMC

Chen H, Zhou HX. Prediction of interface residues in protein–protein complexes by a consensus neural network method: Test against nmr data. Proteins Struct Funct Bioinforma. 2005;61(1):21–35. doi: 10.1002/prot.20514. PubMed DOI

Dong Z, Wang K, Linh Dang TK, Gültas M, Welter M, Wierschin T, Stanke M, Waack S. Crf-based models of protein surfaces improve protein-protein interaction site predictions. BMC Bioinformatics. 2014;15(1):1–14. doi: 10.1186/1471-2105-15-277. PubMed DOI PMC

Wierschin T, Wang K, Welter M, Waack S, Stanke M. Combining features in a graphical model to predict protein binding sites. Proteins Struct Funct Bioinforma. 2015;83(5):844–52. doi: 10.1002/prot.24775. PubMed DOI

Hoksza D, Jelínek J. Using neo4j for mining protein graphs: A case study. In: 2015 26th International Workshop on Database and Expert Systems Applications (DEXA). 2015. p. 230–4. doi:10.1109/DEXA.2015.59. DOI

Jelínek J, Škoda P, Hoksza D. Utilizing knowledge base of amino acids structural neighborhoods to predict protein-protein interaction sites. In: 2016 IEEE 6th International Conference on Computational Advances in Bio and Medical Sciences (ICCABS). 2016. p. 1–1. doi:10.1109/ICCABS.2016.7802780. PubMed DOI PMC

Berman HM, Westbrook J, Feng Z, Gilliland G, Bhat TN, Weissig H, Shindyalov IN, Bourne PE. The protein data bank. Nucleic Acids Res. 2000;28(1):235–42. doi: 10.1093/nar/28.1.235. PubMed DOI PMC

Carhart RE, Smith DH, Venkataraghavan R. Atom pairs as molecular features in structure-activity studies: definition and applications. J Chem Inform Comput Sci. 1985;25(2):64–73. doi: 10.1021/ci00046a002. DOI

Plewczynski D, Spieser SAH, Koch U. Performance of machine learning methods for ligand-based virtual screening. Comb Chem High Throughput Screen. 2009;12(4):358–68. doi: 10.2174/138620709788167962. PubMed DOI

Rogers D, Hahn M. Extended-Connectivity Fingerprints. J Chem Inf Model. 2010;50(5):742–54. doi: 10.1021/ci100050t. PubMed DOI

Riniker S, Landrum GA. Open-source platform to benchmark fingerprints for ligand-based virtual screening. J Cheminformatics. 2013;5(1):1–17. doi: 10.1186/1758-2946-5-1. PubMed DOI PMC

Duan J, Dixon SL, Lowrie JF, Sherman W. Analysis and comparison of 2d fingerprints: Insights into database screening performance using eight fingerprint methods. J Mol Graph Model. 2010;29(2):157–70. doi: 10.1016/j.jmgm.2010.05.008. PubMed DOI

Keskin O, Tsai CJ, Wolfson H, Nussinov R. A new, structurally nonredundant, diverse data set of protein–protein interfaces and its implications. Protein Sci. 2004;13(4):1043–55. doi: 10.1110/ps.03484604. PubMed DOI PMC

Matthews BW. Comparison of the predicted and observed secondary structure of t4 phage lysozyme. Biochim Biophys Acta (BBA) Protein Struct. 1975;405(2):442–51. doi: 10.1016/0005-2795(75)90109-9. PubMed DOI

Porollo A, Meller J. Prediction-based fingerprints of protein–protein interactions. Proteins Struct Funct Bioinforma. 2007;66(3):630–45. doi: 10.1002/prot.21248. PubMed DOI

Qin S, Zhou HX. meta-ppisp: a meta web server for protein-protein interaction site prediction. Bioinformatics. 2007;23(24):3386–7. doi: 10.1093/bioinformatics/btm434. PubMed DOI

Jordan RA, EL-Manzalawy Y, Dobbs D, Honavar V. Predicting protein-protein interface residues using local surface structural similarity. BMC Bioinformatics. 2012;13(1):1–14. doi: 10.1186/1471-2105-13-41. PubMed DOI PMC

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