Learning Sequence Determinants of Protein: Protein Interaction Specificity with Sparse Graphical Models

  • Hetunandan Kamisetty
  • Bornika Ghosh
  • Christopher James Langmead
  • Chris Bailey-Kellogg
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8394)


In studying the strength and specificity of interaction between members of two protein families, key questions center on which pairs of possible partners actually interact, how well they interact, and why they interact while others do not. The advent of large-scale experimental studies of interactions between members of a target family and a diverse set of possible interaction partners offers the opportunity to address these questions. We develop here a method, DgSpi (Data-driven Graphical models of Specificity in Protein:protein Interactions), for learning and using graphical models that explicitly represent the amino acid basis for interaction specificity (why) and extend earlier classification-oriented approaches (which) to predict the \(\varDelta{G}\) of binding (how well). We demonstrate the effectiveness of our approach in analyzing and predicting interactions between a set of 82 PDZ recognition modules, against a panel of 217 possible peptide partners, based on data from MacBeath and colleagues. Our predicted \(\varDelta{G}\) values are highly predictive of the experimentally measured ones, reaching correlation coefficients of 0.69 in 10-fold cross-validation and 0.63 in leave-one-PDZ-out cross-validation. Furthermore, the model serves as a compact representation of amino acid constraints underlying the interactions, enabling protein-level \(\varDelta{G}\) predictions to be naturally understood in terms of residue-level constraints. Finally, the model, DgSpi readily enables the design of new interacting partners, and we demonstrate that designed ligands are novel and diverse.


protein:protein interaction specificity \(\varDelta{G}\) prediction graphical model PDZ 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Balakrishnan, S., Kamisetty, H., Carbonell, J., Lee, S., Langmead, C.: Learning generative models for protein fold families. Proteins: Structure, Function, and Bioinformatics 79(4), 1061–1078 (2011)CrossRefGoogle Scholar
  2. 2.
    Bordner, A., Mittelmann, H.: MultiRTA: A simple yet accurate method for predicting peptide binding affinities for multiple class II MHC allotypes. BMC Bioinformatics 11, 482 (2010)CrossRefGoogle Scholar
  3. 3.
    Brannetti, B., Via, A., Cestra, G., Cesareni, G., Citterich, M.H.: SH3-SPOT: an algorithm to predict preferred ligands to different members of the SH3 gene family. Journal of Molecular Biology 298(2), 313–328 (2000)CrossRefGoogle Scholar
  4. 4.
    Chen, J., Chang, B., Allen, J., Stiffler, M., MacBeath, G.: Predicting PDZ domain-peptide interactions from primary sequences. Nat. Biotechnol. 26(9), 1041–1045 (2008)CrossRefGoogle Scholar
  5. 5.
    Fields, S., Song, O.: A novel genetic system to detect protein-protein interactions. Nature 340(6230), 245–246 (1989)CrossRefGoogle Scholar
  6. 6.
    Fong, J., Keating, A., Singh, M.: Predicting specificity in bZIP coiled-coil protein interactions. Genome Biology 5(2), R11 (2004)Google Scholar
  7. 7.
    Fuh, G., Pisabarro, M., Li, Y., Quan, C., Lasky, L., Sidhu, S.: Analysis of PDZ domain-ligand interactions using carboxyl-terminal phage display. J. Biol. Chem. 275(28), 21486–21491 (2000)Google Scholar
  8. 8.
    Grigoryan, G., Reinke, A., Keating, A.: Design of protein-interaction specificity gives selective bZIP-binding peptides. Nature 458(7240), 859–864 (2009)CrossRefGoogle Scholar
  9. 9.
    Guerois, R., Nielsen, J.E., Serrano, L.: Predicting changes in the stability of proteins and protein complexes: a study of more than 1000 mutations. Journal of Molecular Biology 320, 369–387 (2002)CrossRefGoogle Scholar
  10. 10.
    Jones, D.T., Buchan, D.W., Cozzetto, D., Pontil, M.: Psicov: precise structural contact prediction using sparse inverse covariance estimation on large multiple sequence alignments. Bioinformatics 28(2), 184–190 (2012)CrossRefGoogle Scholar
  11. 11.
    Kamisetty, H., Ghosh, B., Bailey-Kellogg, C., Langmead, C.: Modeling and Inference of Sequence-Structure Specificity. In: Proc. of the 8th International Conference on Computational Systems Bioinformatics (CSB), pp. 91–101 (2009)Google Scholar
  12. 12.
    Kamisetty, H., Ovchinnikov, S., Baker, D.: Assessing the utility of coevolution-based residue–residue contact predictions in a sequence-and structure-rich era. Proceedings of the National Academy of Sciences 110(39), 15674–15679 (2013)CrossRefGoogle Scholar
  13. 13.
    Kamisetty, H., Ramanathan, A., Bailey-Kellogg, C., Langmead, C.: Accounting for conformational entropy in predicting binding free energies of protein-protein interactions. Proteins 79(2), 444–462 (2011)CrossRefGoogle Scholar
  14. 14.
    Kamisetty, H., Xing, E., Langmead, C.: Free Energy Estimates of All-atom Protein Structures Using Generalized Belief Propagation. J. Comp. Bio. 15(7), 755–766 (2008)CrossRefMathSciNetGoogle Scholar
  15. 15.
    Kamisetty, H., Xing, E., Langmead, C.: Approximating Correlated Equilibria using Relaxations on the Marginal Polytope. In: Proc. of the 28th International Conference on Machine Learning (ICML), pp. 1153–1160 (2011)Google Scholar
  16. 16.
    Kortemme, T., Baker, D.: A simple physical model for binding energy hot spots in protein-protein complexes. Proceedings of the National Academy of Sciences 99(22), 14116–14121 (2002)CrossRefGoogle Scholar
  17. 17.
    Kurakin, A., Swistowski, A., Wu, S., Bredesen, D.: The pdz domain as a complex adaptive system. PLoS One 2(9) 2(9), e953 (2007)Google Scholar
  18. 18.
    Li, J., Yi, Z.P., Laskowski, M., Laskowski Jr., M., Bailey-Kellogg, C.: Analysis of sequence-reactivity space for protein-protein interactions. Proteins: Structure, Function, and Bioinformatics 58(3), 661–671 (2005)CrossRefGoogle Scholar
  19. 19.
    Liu, Y., Carbonell, J., Gopalakrishnan, V., Weigele, P.: Conditional graphical models for protein structural motif recognition. Journal of Computational Biology 16(5), 639–657 (2009)CrossRefMathSciNetGoogle Scholar
  20. 20.
    Lockless, S.W., Ranganathan, R.: Evolutionarily conserved pathways of energetic connectivity in protein families. Science 286(5438), 295–299 (1999)CrossRefGoogle Scholar
  21. 21.
    Lu, S., Lu, W., Qasim, M., Anderson, S., Apostol, I., Ardelt, W., Bigler, T., Chiang, Y., Cook, J., James, M., Kato, I., Kelly, C., Kohr, W., Komiyama, T., Lin, T., Ogawa, M., Otlewski, J., Park, S., Qasim, S., Ranjbar, M., Tashiro, M., Warne, N., Whatley, H., Wieczorek, A., Wieczorek, M., Wilusz, T., Wynn, R., Zhang, W., Laskowski Jr., M.: Predicting the reactivity of proteins from their sequence alone: Kazal family of protein inhibitors of serine proteinases. Proceedings of the National Academy of Sciences 98(4), 1410–1415 (2001)CrossRefGoogle Scholar
  22. 22.
    Marks, D.S., Colwell, L.J., Sheridan, R., Hopf, T.A., Pagnani, A., Zecchina, R., Sander, C.: Protein 3d structure computed from evolutionary sequence variation. PLoS One 6(12), e28766 (2011)Google Scholar
  23. 23.
    Meinshausen, N., Bühlmann, P.: High-dimensional graphs and variable selection with the lasso. The Annals of Statistics 34(3), 1436–1462 (2006)CrossRefzbMATHMathSciNetGoogle Scholar
  24. 24.
    Menke, M., Berger, B., Cowen, L.: Markov random fields reveal an n-terminal double beta-propeller motif as part of a bacterial hybrid two-component sensor system. PNAS 107(9), 4069–4074 (2010)CrossRefGoogle Scholar
  25. 25.
    Moitra, S., Tirupula, K., Klein-Seetharaman, J., Langmead, C.: A minimal ligand binding pocket within a network of correlated mutations identified by multiple sequence and structural analysis of G protein coupled receptors. BMC Biophysics 5(13) (2012), doi:10.1186/2046–1682–5–13Google Scholar
  26. 26.
    Morcos, F., Pagnani, A., Lunt, B., Bertolino, A., Marks, D.S., Sander, C., Zecchina, R., Onuchic, J.N., Hwa, T., Weigt, M.: Direct-coupling analysis of residue coevolution captures native contacts across many protein families. Proceedings of the National Academy of Sciences 108(49), E1293–E1301 (2011)Google Scholar
  27. 27.
    Nielsen, M., Lundegaard, C., Blicher, T., Lamberth, K., Harndahl, M., Justesen, S., Roder, G., Peters, B., Sette, A., Lund, O., Buus, S.: NetMHCpan, a method for quantitative predictions of peptide binding to any HLA-A and -B locus protein of known sequence. PLoS One 2, e796 (2007)Google Scholar
  28. 28.
    Nugent, T., Jones, D.T.: Accurate de novo structure prediction of large transmembrane protein domains using fragment-assembly and correlated mutation analysis. Proceedings of the National Academy of Sciences 109(24), E1540–E1547 (2012)Google Scholar
  29. 29.
    Peters, B., Sidney, J., Bourne, P., Bui, H.H., Buus, S., Doh, G., Fleri, W., Kronenberg, M., Kubo, R., Lund, O., Nemazee, D., Ponomarenko, J.V., Sathiamurthy, M., Schoenberger, S., Stewart, S., Surko, P., Way, S., Wilson, S., Sette, A.: The immune epitope database and analysis resource: from vision to blueprint. PLoS Biol. 3, e91 (2005)Google Scholar
  30. 30.
    Razavian, N., Kamisetty, H., Langmead, C.: Learning generative models of molecular dynamics. BMC Genomics 13(suppl. 1) (2012), doi:10.1186/1471–2164–13–S1–S5Google Scholar
  31. 31.
    Saro, D., Li, T., Rupasinghe, C., Paredes, A., Caspers, N., Spaller, M.: A thermodynamic ligand binding study of the third pdz domain (pdz3) from the mammalian neuronal protein psd-95. Biochemistry 46(21), 6340–6352 (2007)CrossRefGoogle Scholar
  32. 32.
    Schmidt, M., van der Berg, E., Friedlander, M.P., Murphy, K.: Optimizing costly functions with simple constraints:a limited-memory projected quasi-newton algorithm. AISTATS 5, 456–463 (2009)Google Scholar
  33. 33.
    Shao, X., Tan, C., Voss, C., Li, S., Deng, N., Bader, G.: A regression framework incorporating quantitative and negative interaction data improves quantitative prediction of PDZ domain-peptide interaction from primary sequence. Bioinformatics 27(3), 383–390 (2010)CrossRefGoogle Scholar
  34. 34.
    Sheng, M., Sala, C.: Pdz domains and the organization of supramolecular complexes. Annu. Rev. Neurosci. 24, 1–29 (2001)CrossRefGoogle Scholar
  35. 35.
    Smith, C., Kortemme, T.: Structure-based prediction of the peptide sequence space recognized by natural and synthetic pdz domains. Journal of Molecular Biology 402(2), 460–474 (2010)CrossRefGoogle Scholar
  36. 36.
    Stiffler, M., Chen, J., Grantcharova, V., Lei, Y., Fuchs, D., Allen, J., Zaslavskaia, L., MacBeath, G.: Pdz domain binding selectivity is optimized across the mouse proteome. Science 317(5836), 364–369 (2007)CrossRefGoogle Scholar
  37. 37.
    Thomas, J., Ramakrishnan, N., Bailey-Kellogg, C.: Graphical models of residue coupling in protein families. IEEE/ACM Transactions on Computational Biology and Bioinformatics 5(2), 183–197 (2008)CrossRefGoogle Scholar
  38. 38.
    Thomas, J., Ramakrishnan, N., Bailey-Kellogg, C.: Graphical models of protein-protein interaction specificity from correlated mutations and interaction data. Proteins: Structure, Function, and Bioinformatics 76(4), 911–929 (2009)CrossRefGoogle Scholar
  39. 39.
    Thomas, J., Ramakrishnan, N., Bailey-Kellogg, C.: Protein design by sampling an undirected graphical model of residue constraints. IEEE/ACM Transactions on Computational Biology and Bioinformatics 6(3), 506–516 (2009)CrossRefGoogle Scholar
  40. 40.
    Tonikian, R., Zhang, Y., Sazinsky, S., Currell, B., Yeh, J., Reva, B., Held, H., Appleton, B., Evangelista, M., Wu, Y., Xin, X., Chan, A., Seshagiri, S., Lasky, L., Sander, C., Boone, C., Bader, G., Sidhu, S.: A specificity map for the PDZ domain family. Plos Biology 6(9), e239 (2008)Google Scholar
  41. 41.
    Wang, P., Sidney, J., Dow, C., Mothe, B., Sette, A., Peters, B.: A systematic assessment of MHC class II peptide binding predictions and evaluation of a consensus approach. PLoS Comp. Biol. 4, e1000048 (2008)Google Scholar
  42. 42.
    Xu, J., Jiao, F., Berger, B.: A parameterized algorithm for protein structure alignment. In: Apostolico, A., Guerra, C., Istrail, S., Pevzner, P.A., Waterman, M. (eds.) RECOMB 2006. LNCS (LNBI), vol. 3909, pp. 488–499. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  43. 43.
    Zhang, L., Udaka, K., Mamitsuka, H., Zhu, S.: Toward more accurate pan-specific MHC-peptide binding prediction: a review of current methods and tools. Brief. Bioinform. 13, 350–364 (2012)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Hetunandan Kamisetty
    • 1
  • Bornika Ghosh
    • 2
  • Christopher James Langmead
    • 3
  • Chris Bailey-Kellogg
    • 2
  1. 1.Department of BiochemistryUniversity of WashingtonUSA
  2. 2.Department of Computer ScienceDartmouthUSA
  3. 3.School of Computer ScienceCarnegie Mellon UniversityUSA

Personalised recommendations