Advertisement

Neural Network Pairwise Interaction Fields for Protein Model Quality Assessment

  • Alberto J. M. Martin
  • Alessandro Vullo
  • Gianluca Pollastri
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5851)

Abstract

We present a new knowledge-based Model Quality Assessment Program (MQAP) at the residue level which evaluates single protein structure models. We use a tree representation of the C α trace to train a novel Neural Network Pairwise Interaction Field (NN-PIF) to predict the global quality of a model. We also attempt to extract local quality from global quality. The model allows fast evaluation of multiple different structure models for a single sequence. In our tests on a large set of structures, our model outperforms most other methods based on different and more complex protein structure representations in both local and global quality prediction. The method is available upon request from the authors. Method-specific rankers may also built by the authors upon request.

Keywords

Hide State Global Quality Protein Structure Prediction Fold Recognition Model Quality Assessment 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Cozzetto, D., Kryshtafovych, A., Ceriani, M., Tramontano, A.: Assessment of predictions in the model quality assessment category. Proteins 69(suppl. 8), 175–183 (2007)CrossRefGoogle Scholar
  2. 2.
    Cornell, W., Cieplak, P., Bayly, C., Gould, I., Merz, K., Ferguson, D., Spellmeyer, D., Fox, T., Caldwell, J., Kollman, P.: A second generation force field for the simulation of proteins, nucleic acids, and organic molecules. J. Am. Chem. Soc. 117, 5179–5197 (1995)CrossRefGoogle Scholar
  3. 3.
    MacKerell, A., Bashford, D., Bellott, M., Dunbrack, R., Evanseck, J., Field, M., Fischer, S., Gao, J., Guo, H., Ha, S., Joseph-McCarthy, D., Kuchnir, L., Kuczera, K., Lau, F., Mattos, C., Michnick, S., Ngo, T., Nguyen, D., Prodhom, B., Reiher, W., Roux, B., Schlenkrich, M., Smith, J., Stote, R., Straub, J., Watanabe, M., Wiorkiewicz-Kuczera, J., Yin, D., Karplus, M.: All-atom empirical potential for molecular modelling and dynamics studies of proteins. J. Phys. Chem. 102, 3586–3616 (1998)Google Scholar
  4. 4.
    Scott, W., Hünenberger, P., Tironi, I., Mark, A., Billeter, S., Fennen, J., Torda, A., Huber, T., Krüger, P., van Gunsteren, W.F.: The gromos biomolecular simulation program package. J. Phys. Chem. 103, 3596–3607 (1999)Google Scholar
  5. 5.
    Krieger, E., Koraimann, G., Vriend, G.: Increasing the precision of comparative models with yasara nova a self-parameterising force field. PROTEINS: Structure, Function, and Bioinformatics 47, 393–402 (2002)CrossRefGoogle Scholar
  6. 6.
    Krieger, E., Darden, T., Nabuurs, S., Finkelstein, A., Vriend, G.: Making optimal use of empirical energy functions: Force-field parameterisation in crystal space. PROTEINS: Structure, Function, and Bioinformatics 57, 678–683 (2004)CrossRefGoogle Scholar
  7. 7.
    Colubri, A., Jha, A., Shen, M., Sali, A., Berry, R., Sosnick, T., Freed, K.: Minimalist representations and the importance of nearest neighbour effects in protein folding simulations. J. Mol. Biol. 363, 835–857 (2006)CrossRefGoogle Scholar
  8. 8.
    Fitzgerald, J., Jha, A., Colubri, A., Sosnick, T., Freed, K.: Reduced cβ statistical potentials can outperform all-atom potentials in decoy identification. Protein Science 16, 2123–2139 (2001)CrossRefGoogle Scholar
  9. 9.
    Wu, Y., Lu, M., Chen, M., Li, J., Ma, J.: Opus-c α: A knowledge-based potential function requiring only c α positions. Protein Science 16, 1449–1463 (2007)CrossRefGoogle Scholar
  10. 10.
    Lu, M., Dousis, A., Ma, J.: Opuspsp: An orientation-dependent statistical all-atom potential derived from side-chain packing. J. Mol. Biol. 376, 288–301 (2008)CrossRefGoogle Scholar
  11. 11.
    Leherte, L.: Application of multiresolution analyses to electron density maps of small molecules: Critical point representations for molecular superposition. J. of Math. Chem. 29(1), 47–83 (2001)CrossRefMathSciNetzbMATHGoogle Scholar
  12. 12.
    Simons, K., Kooperberg, T., Huang, E., Baker, D.: Assembly of protein tertiary structures from fragments with similar local sequences using simulated annealing and bayesian scoring functions. J. Mol. Biol. 268, 209–225 (1997)CrossRefGoogle Scholar
  13. 13.
    Baú, D., Pollastri, G., Vullo, A.: Distill: a machine learning approach to ab initio protein structure prediction. In: Bandyopadhyay, S., Maulik, U., Wang, J.T.L. (eds.) Analysis of Biological Data: A Soft Computing Approach. World Scientific, Singapore (2006)Google Scholar
  14. 14.
    Wu, S., Skolnick, J., Zhang, Y.: Ab initio modelling of small proteins by iterative tasser simulations. BMC Biology 5, 17 (2007)CrossRefGoogle Scholar
  15. 15.
    Pettitt, C., McGuffin, L., Jones, D.: Improving sequence-based fold recognition by using 3d model quality assessment. Bioinformatics 21(17), 3509–3515 (2005)CrossRefGoogle Scholar
  16. 16.
    Adcock, S.: Peptide backbone reconstruction using dead-end elimination and a knowledge-based forcefield. J. Comput. Chem. 25, 16–27 (2004)CrossRefGoogle Scholar
  17. 17.
    Bower, M., Cohen, F., Dunbrack, R.: Prediction of protein side-chain rotamers from a backbone-dependent rotamer library: A new homology modelling tool. J. Mol. Biol. 267, 1268–1282 (1997)CrossRefGoogle Scholar
  18. 18.
    Khatun, J., Khare, S., Dokhlyan, N.: Can contact potentials reliably predict stability of proteins? J. Mol. Biol. 336, 1223–1238 (2004)CrossRefGoogle Scholar
  19. 19.
    Zhou, H., Zhou, Y.: Distance-scaled, finite ideal-gas reference state improves and stability prediction structure-derived potentials of mean force for structure selection. Protein Science 11, 2714–2726 (2002)CrossRefGoogle Scholar
  20. 20.
    Hoppe, C., Schomburg, D.: Prediction of protein thermostability with a direction- and distance-dependent knowledge-based potential. Protein Science 14, 2682–2692 (2005)CrossRefGoogle Scholar
  21. 21.
    Shao, Y., Bystroff, C.: Predicting interresidue contacts using templates and pathways. PROTEINS: Structure, Function, and Bioinformatics 53, 497–502 (2003)CrossRefGoogle Scholar
  22. 22.
    Vullo, A., Walsh, I., Pollastri, G.: A two-stage approach for improved prediction of residue contact maps. BMC Bioinformatics 7, 18 (2006)CrossRefGoogle Scholar
  23. 23.
    Martin, A., Baú, D., Walsh, I., Vullo, A., Pollastri, G.: Long-range information and physicality constraints improve predicted protein contact maps. Journal of Bioinformatics and Computational Biology 6(5) (2008)Google Scholar
  24. 24.
    Kleywegt, G.: Validation of protein models from c-alpha coordinates alone. J. Mol. Biol. 273, 371–376 (1997)CrossRefGoogle Scholar
  25. 25.
    Ngan, S., Inouye, M., Samudrala, R.: A knowledge-based scoring function based on residue triplets for protein structure prediction. Protein Engineering, Desing & Selection 19(5), 187–193 (2006)CrossRefGoogle Scholar
  26. 26.
    Feng, Y., Kloczkowski, A., Jernigan, R.: Four-body contact potentials derived from two protein datasets to discriminate native structures from decoys. PROTEINS: Structure, Function, and Bioinformatics 68, 57–66 (2007)CrossRefGoogle Scholar
  27. 27.
    Loose, C., Klepeis, J., Floudas, C.: A new pairwise folding potential based on improved decoy generation and side-chain packing. PROTEINS: Structure, Function, and Bioinformatics 54, 303–314 (2004)CrossRefGoogle Scholar
  28. 28.
    Heo, M., Kim, S., Moon, E., Cheon, M., Chung, K., Chang, I.: Perceptron learning of pairwise contact energies for proteins incorporating the amino acid environment. Phys. Rev. E Stat. Nonlin. Soft Matter Phys. 72, 011906 (2005)Google Scholar
  29. 29.
    Sippl, M.: Recognition of errors in three-dimensional structures of proteins. PROTEINS: Structure, Function, and Bioinformatics 17, 355–362 (1993)CrossRefGoogle Scholar
  30. 30.
    Benkert, P., Tosatto, S., Schomburg, D.: Qmean: A comprehensive scoring function for model quality assessment. PROTEINS: Structure, Function, and Bioinformatics 71(1), 261–277 (2008)CrossRefGoogle Scholar
  31. 31.
    Dong, Q., Wang, X., Lin, L.: Novel knowledge-based mean force potential at the profile level. BMC Bioinformatics 7, 324 (2006)CrossRefGoogle Scholar
  32. 32.
    Zhang, C., Kim, S.: Environment-dependent residue contact energies for proteins. PNAS 97(6), 2550–2555 (2000)CrossRefGoogle Scholar
  33. 33.
    Fogolari, F., Pieri, L., Dovier, A., Bortolussi, L., Giugliarelli, G., Corazza, A., Esposito, G., Viglino, P.: Scoring predictive models using a reduced representation of proteins: model and energy definition. BMC Structural Biology 7(15), 17 (2007)Google Scholar
  34. 34.
    Wallner, B., Elofsson, A.: Can correct protein models be identified? Protein Science 12, 1073–1086 (2003)CrossRefGoogle Scholar
  35. 35.
    Wallner, B., Elofsson, A.: Identification of correct regions in protein models using structural, alignment, and consensus information. Protein Science 15, 900–913 (2006)CrossRefGoogle Scholar
  36. 36.
    Samudrala, R., Moult, J.: An all-atom distance-dependent conditional probability discriminatory function for protein structure prediction. J. Mol. Biol. 275, 895–916 (1998)CrossRefGoogle Scholar
  37. 37.
    Eisenberg, D., Lthy, R., Bowie, J.: Verify 3d: assessment of protein models with three-dimensional profiles. Methods Enzymol. 277, 396–404 (1997)CrossRefGoogle Scholar
  38. 38.
    Wallner, B., Fang, H., Elofsson, A.: Automatic consensus-based fold recognition using pcons, proq, and pmodeller. PROTEINS: Structure, Function, and Genetics 53, 534–541 (2003)CrossRefGoogle Scholar
  39. 39.
    McGuffin, L.: Benchmarking consensus model quality assessment for protein fold recognition. BMC Bioinformatics 8, 15 (2007)CrossRefGoogle Scholar
  40. 40.
    Wallner, B., Elofsson, A.: Prediction of global and local model quality in casp7 using pcons and proq. PROTEINS: Structure, Function, and Bioinformatics 69(suppl. 8), 184–193 (2007)CrossRefGoogle Scholar
  41. 41.
    Ginalski, K., Elofsson, A., Fischer, D., Rychlewski, L.: 3d-jury: a simple approach to improve protein structure predictions. Bioinformatics 19(8), 1015–1018 (2003)CrossRefGoogle Scholar
  42. 42.
    Qiu, J., Sheffler, W., Baker, D., Noble, W.: Ranking predicted protein structures with support vector regression. PROTEINS: Structure, Function, and Bioinformatics 71, 1175–1182 (2008)CrossRefGoogle Scholar
  43. 43.
    Zhou, H., Skolnick, J.: Protein model quality assessment prediction by combining fragment comparisons and a consensus ca contact potential. PROTEINS: Structure, Function, and Bioinformatics 71, 1211–1218 (2008)CrossRefGoogle Scholar
  44. 44.
    Battey, J., Kopp, J., Bordoli, L., Read, R., Clarke, N., Schwede, T.: Automated server predictions in casp7. Proteins 69(suppl. 8), 68–82 (2007)CrossRefGoogle Scholar
  45. 45.
    Sperduti, A., Starita, A.: Supervised neural networks for the classification of structures. IEEETNN 8(3), 714–735 (1997)Google Scholar
  46. 46.
    Frasconi, P.: An introduction to learning structured information. In: Giles, C.L., Gori, M. (eds.) IIASS-EMFCSC-School 1997. LNCS (LNAI), vol. 1387, pp. 99–120. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  47. 47.
    Frasconi, P., Gori, M., Sperduti, A.: A general framework for adaptive processing of data structures. IEEETNN 9(5), 768–786 (1998)Google Scholar
  48. 48.
    Martin, J., Letellier, G., Marin, A., Taly, J., de Brevern, A.G., Gibrat, J.F.: Protein secondary structure assignment revisited: a detailed analysis of different assignment methods. BMC Struct. Biol. 5, 17 (2005)CrossRefGoogle Scholar
  49. 49.
    Majumdar, I., Krishna, S., Grishin, N.: Palsse: A program to delineate linear secondary structural elements from protein structures. BMC Bioinformatics 6(202), 24 (2005)Google Scholar
  50. 50.
    Labesse, G., Colloc’h, N., Pothier, J., Mornon, J.: P-sea: a new efficient assignment of secondary structure from c alpha trace of proteins. CABIOS 13(3), 291–295 (1997)Google Scholar
  51. 51.
    Hamelryck, T.: An amino acid has two sides: A new 2d measure provides a different view of solvent exposure. PROTEINS: Structure, Function, and Bioinformatics 59, 38–48 (2005)CrossRefGoogle Scholar
  52. 52.
    Zemla, A., Venclovas, C., Moult, J., Fidelis, K.: Processing and analysis of casp3 protein structure predictions. Proteins 37(suppl. 3), 22–29 (1999)CrossRefGoogle Scholar
  53. 53.
    Siew, N., Elofsson, A., Rychlewski, L., Fischer, D.: MaxSub: an automated measure for the assessment of protein structure prediction quality. Bioinformatics 16(9), 776–785 (2000)CrossRefGoogle Scholar
  54. 54.
    Cristobal, S., Zemla, A., Fischer, D., Rychlewski, L., Elofsson, A.: A study of quality measures for protein threading models. BMC Bioinformatics 2(5), 15 (2001)Google Scholar
  55. 55.
    Zhang, Y., Skolnick, J.: Scoring function for automated assessment of protein structure template quality. PROTEINS: Structure, Function, and Bioinformatics 57, 702–710 (2004)CrossRefGoogle Scholar
  56. 56.
    Tsai, J., Bonneau, R., Morozov, A., Kuhlman, B., Rohl, C., Baker, D.: An improved protein decoy set for testing energy functions for protein structure prediction. PROTEINS: Structure, Function, and Bioinformatics 53, 76–87 (2003)CrossRefGoogle Scholar
  57. 57.
    Tosatto, S.: The victor/FRST function for model quality estimation. J. Comput. Biol. 12(10), 1316–1327 (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Alberto J. M. Martin
    • 1
  • Alessandro Vullo
    • 1
  • Gianluca Pollastri
    • 1
  1. 1.School of Computer Science and Informatics and Complex and Adaptive Systems LaboratoryUniversity College DublinBelfieldIreland

Personalised recommendations