Skip to content
BY-NC-ND 3.0 license Open Access Published by De Gruyter March 26, 2011

PPI_SVM: Prediction of protein-protein interactions using machine learning, domain-domain affinities and frequency tables

  • Piyali Chatterjee EMAIL logo , Subhadip Basu , Mahantapas Kundu , Mita Nasipuri and Dariusz Plewczynski

Abstract

Protein-protein interactions (PPI) control most of the biological processes in a living cell. In order to fully understand protein functions, a knowledge of protein-protein interactions is necessary. Prediction of PPI is challenging, especially when the three-dimensional structure of interacting partners is not known. Recently, a novel prediction method was proposed by exploiting physical interactions of constituent domains. We propose here a novel knowledge-based prediction method, namely PPI_SVM, which predicts interactions between two protein sequences by exploiting their domain information. We trained a two-class support vector machine on the benchmarking set of pairs of interacting proteins extracted from the Database of Interacting Proteins (DIP). The method considers all possible combinations of constituent domains between two protein sequences, unlike most of the existing approaches. Moreover, it deals with both single-domain proteins and multi domain proteins; therefore it can be applied to the whole proteome in high-throughput studies. Our machine learning classifier, following a brainstorming approach, achieves accuracy of 86%, with specificity of 95%, and sensitivity of 75%, which are better results than most previous methods that sacrifice recall values in order to boost the overall precision. Our method has on average better sensitivity combined with good selectivity on the benchmarking dataset. The PPI_SVM source code, train/test datasets and supplementary files are available freely in the public domain at: http://code.google.com/p/cmater-bioinfo/.

[1] Ito, T., Tashiro, K., Muta, S., Ozawa, R., Chiba, T., Nishizawa, M., Yamamoto, K., Kuhara, S. and Sakaki, Y. Toward a protein-protein interaction map of the budding yeast: a comprehensive system to examine two-hybrid interactions in all possible combinations between the yeast proteins. Proc. Natl. Acad. Sci. USA 97 (2000) 1143–1147. http://dx.doi.org/10.1073/pnas.97.3.114310.1073/pnas.97.3.1143Search in Google Scholar

[2] Plewczynski, D. and Basu, S. AMS 3.0: prediction of post-translational modifications. BMC Bioinformatics 11 (2010) 210 DOI: 10.1186/1471- 2105-11-210. http://dx.doi.org/10.1186/1471-2105-11-21010.1186/1471-2105-11-210Search in Google Scholar

[3] Gharakhanian, E., Takahashi, J., Clever, J. and Kasamatsu, H. In vitro assay for protein-protein interaction: carboxyl-terminal 40 residues of simian virus 40 structural protein VP3 contain a determinant for interaction with VP1. Proc. Natl. Acad. Sci. USA 85 (1998) 6607–6611. http://dx.doi.org/10.1073/pnas.85.18.660710.1073/pnas.85.18.6607Search in Google Scholar

[4] Hu, C.D., Chinenov, Y. and Kerppola, T.K. Visualization of interactions among bZIP and Rel family proteins in living cells using bimolecular fluorescence complementation. Mol. Cell. 9 (2002) 789–798. http://dx.doi.org/10.1016/S1097-2765(02)00496-310.1016/S1097-2765(02)00496-3Search in Google Scholar

[5] Rigaut, G., Shevchenko, A., Rutz, B., Wilm, M., Mann, M. and Seraphin, B. A generic protein purification method for protein complex characterization and proteome exploration. Nat. Biotechnol. 17 (1999) 1030–1032. http://dx.doi.org/10.1038/1373210.1038/13732Search in Google Scholar PubMed

[6] Klingström, T. and Plewczynski D. Protein-protein interaction and pathway databases, a graphical review. Brief. Bioinform. (2010) DOI: 10.1093/bib/bbq064. 10.1093/bib/bbq064Search in Google Scholar PubMed

[7] Salwinski, L., Miller, C.S., Smith, A.J., Pettit, F.K., Bowie, J.U. and Eisenberg, E. The Database of Interacting Proteins: 2004 update. Nucleic Acids Res. 32 (2004) 449–451. http://dx.doi.org/10.1093/nar/gkh08610.1093/nar/gkh086Search in Google Scholar PubMed PubMed Central

[8] Pagel, P., Kovac, S., Oesterheld, M., Brauner, B., Dunger-Kaltenbach, I., Frishman, G., Montrone, C., Mark, P., Stümpflen, V., Mewes, H.W., Ruepp, A. and Frishman, D. The MIPS mammalian protein-protein interaction database. Bioinformatics 21 (2005) 832–834. http://dx.doi.org/10.1093/bioinformatics/bti11510.1093/bioinformatics/bti115Search in Google Scholar PubMed

[9] Bader, G.D., Betel, D. and Hogue, C.W. BIND: the Biomolecular Interaction Network Database. Nucleic Acids Res. 31 (2003) 248–250. http://dx.doi.org/10.1093/nar/gkg05610.1093/nar/gkg056Search in Google Scholar PubMed PubMed Central

[10] Aranda, B., Achuthan, P., Alam-Faruque, Y., Armean, I., Bridge, A., Derow, C., Feuermann, M., Ghanbarian, A.T., Kerrien, S., Khadake, J., Kerssemakers, J., Leroy, C., Menden, M., Michaut, M., Montecchi-Palazzi, L., Neuhauser, L.N., Orchard, S., Perreau, V., Roechert, B., van Eijk, K. and Hermjakob, H. The IntAct molecular interaction database in 2010. Nucleic Acids Res. 38 (2009) 525–531. http://dx.doi.org/10.1093/nar/gkp87810.1093/nar/gkp878Search in Google Scholar PubMed PubMed Central

[11] Ceol, A., Chatr, Aryamontri, A., Licata, L., Peluso, D., Briganti, L., Perfetto, L., Castagnoli, L. and Cesareni, G. MINT, the molecular interaction database: 2009 update. Nucleic Acids Res. 38 (2010) 532–539. http://dx.doi.org/10.1093/nar/gkp98310.1093/nar/gkp983Search in Google Scholar PubMed PubMed Central

[12] Plewczynski, D., Łaźniewski, M., Augustyniak, R. and Ginalski, K. Can we trust docking results? Evaluation of seven commonly used programs on PDBbind database. J. Comput. Chem. 32 (2011) 742–755. http://dx.doi.org/10.1002/jcc.2164310.1002/jcc.21643Search in Google Scholar PubMed

[13] Plewczynski, D., Łaźniewski, M., von Grotthuss, M., Rychlewski, L. and Ginalski, K. VoteDock: Consensus docking method for prediction of protein-ligand interactions. J. Comput. Chem. 32 (2011) 568–581. http://dx.doi.org/10.1002/jcc.2164210.1002/jcc.21642Search in Google Scholar PubMed PubMed Central

[14] Bock, J.R. and Gough, A.D., A. Predicting protein-protein interactions from primary structure. Bioinformatics 17 (2001) 455–460. http://dx.doi.org/10.1093/bioinformatics/17.5.45510.1093/bioinformatics/17.5.455Search in Google Scholar PubMed

[15] Gomez, S.M., Noble, W.S. and Rzhetsky, A. Learning to predict protein-protein interactions from protein sequences. Bioinformatics 19 (2003) 1875–1881. http://dx.doi.org/10.1093/bioinformatics/btg35210.1093/bioinformatics/btg352Search in Google Scholar PubMed

[16] Zaki, N. Prediction of protein-protein interactions using pairwise alignment and inter-domain linker region. Engin. Letter 16 (2008) 505–511. Search in Google Scholar

[17] Wojcik, J. and Schachter, V. Protein-protein interaction map inference using interacting domain profile pairs. Bioinformatics 17 (2001) 296–305. Search in Google Scholar

[18] Kim, W.K., Park, J. and Suh, J.K. Large scale statistical prediction of protein-protein interaction by potentially interacting domain (PID) pair. Genome Inform. 13 (2002) 42–50. Search in Google Scholar

[19] Alashwal, H., Deris, S. and Othman, R.M. One-class support vector machines for protein-protein interactions prediction. J. Biomed. Sci. 1 (2006) 120–127. Search in Google Scholar

[20] Chen, X.W. and Liu, M. Domain-based predictive models for proteinprotein interaction prediction. Eurasip Jasp. 1 (2006) 1–8. DOI: 10.1155/ASP/2006/32767. 10.1155/ASP/2006/32767Search in Google Scholar

[21] Han, D.S., Kim, H.S., Jang, W.H., Lee, S.D. and Suh, J.K. PreSPI: a domain combination based prediction system for protein-protein interaction. Nucleic Acids Res. 132 (2004) 6312–6320. http://dx.doi.org/10.1093/nar/gkh97210.1093/nar/gkh972Search in Google Scholar PubMed PubMed Central

[22] Alashwal, H., Deris, S. and Othman, R.M. A Bayesian kernel for the Prediction of Protein-Protein Interactions. World Academy of Science, Engineering and Technology 51 (2009) 928–933. Search in Google Scholar

[23] Vapnik, V. The nature of statistical learning theory, Springer-Verlag, New York, 1995. 10.1007/978-1-4757-2440-0Search in Google Scholar

[24] Xenarios, I., Salwinski, L., Duan, X.J., Higney, P., Kim, S.M. and Eisenberg, D. DIP, the Database of Interacting Proteins: a research tool for studying cellular networks of protein interactions. Nucleic Acids Res. 30 (2002) 303–305. http://dx.doi.org/10.1093/nar/30.1.30310.1093/nar/30.1.303Search in Google Scholar PubMed PubMed Central

[25] Joachims, T. Making Large-Scale SVM Learning Practical. in: Advances in Kernel Methods — Support Vector Learning (Schölkopf, B., Burges. C. and Smola. A., Eds.), MIT Press Cambridge, 1999, 169–284. Search in Google Scholar

[26] Plewczynski, D. and Ginalski, K. The interactome: Predicting the proteinprotein interactions in cells. Cell. Mol. Biol. Lett. 14 (2009) 1–22. http://dx.doi.org/10.2478/s11658-008-0024-710.2478/s11658-008-0024-7Search in Google Scholar PubMed PubMed Central

[27] Plewczynski D. Brainstorming: weighted voting prediction of inhibitors for protein targets. J. Mol. Model. (2010) DOI 10.1007/s00894-010-0854-x. 10.1007/s00894-010-0854-xSearch in Google Scholar PubMed PubMed Central

Published Online: 2011-3-26
Published in Print: 2011-6-1

© 2011 University of Wrocław, Poland

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Downloaded on 28.3.2024 from https://www.degruyter.com/document/doi/10.2478/s11658-011-0008-x/html
Scroll to top button