3D-Judge : a metaserver approach to protein structure prediction

• Autorzy: Jaśkowski W. , Błażewicz J. , Łukasiak P. , Miłostan M. , Krasnogor N.
• Języki publikacji: EN

Abstrakty

EN

Analysing arid predicting the detailed three dimensional conformation of protein structures is a critical and important task within structural bioinformatics with impact on other fields, e.g.. drug design and delivery, sensing technologies, etc. Unfortunately, it is hard to identify one methodology that will give the best prediction of the three-dimensional structure for any sequence. That is, some predictors are best suited for some sequences and not for others. In trying to address this drawback of current prediction algorithms the research community introduced the concept of protein prediction metaservers. In this paper we propose a new metaserver method called 3D-Judge that uses an artificial neural network (ANN) to select the best model from among models produced by individual servers. The fundamental innovation we introduce is that the AXN is not only used to decide which models and servers to use as good predictions but, crucially, it is also used to analyse and "remember" the past performances of the servers it has access to. Thus, our method acts as both a kind of majority voting algorithm, by selecting models arising from different servers based on their mutual similarity, and also a reinforced learning method that takes cues from historical data of previously solved structures. We train and evaluate our metaserver based on previous GASP results and we compare SD-Judge with a popular and effective metaserver, namely. 3D-Jury. The obtained results indicate that 3D-Judge is competitive with 3D-Jury, outperforming it on many cases. We also present a discussion on future extensions to 3D-Judge.

Słowa kluczowe

EN

protein structure prediction; neural network; meta-server; protein structure similarity

• Wydawca: Wydawnictwo Politechniki Poznańskiej
• Czasopismo: Foundations of Computing and Decision Sciences
• Rocznik: 2007
• Tom: Vol. 32, No. 1
• Strony: 3--14
• Opis fizyczny: Bibliogr. 59 poz.

Twórcy

autor

Jaśkowski W.

autor

Błażewicz J.

autor

Łukasiak P.

autor

Miłostan M.

autor

Krasnogor N.

• Institute of Computing Science, Poznan University of Technology, Poznan

Bibliografia

• [1] M. Arbib, The handbook of brain theory and neural networks. Bradford Books/The MIT Press, Cambridge, MA. 1995-
• [2] J. Bacardit, M. Stout, J.D. Hirst, J. Blazewicz, and N. Krasnogor. "Coordination number prediction using learning classifier systems: performance and interpretabil-ity," Proceedings of the 2006 Genetic and Evolutionary Computation Conference (GECCO), pp. 247 - 254. ACM Press New York, NY, USA: 2006.
• [3] N. Krasnogor. W.E. Hart, J. Smith, and D. Pelta. "Protein structure prediction with evolutionary algorithms". Proceedings of the Genetic and Evolutionary Computation Conference (GECCO99), pages 1569-1601. Morgan Kaufmann, 1999.
• [4] D. Chivian, D.E. Kirn, L. Malmstrom, J. Schonbrun, C.A. Rohl, D. Baker, "The Robetta and Robetta_04 protocols", CASP6 Abstracts, pp. 12-13, 2004.
• [5] D. Barthel, J.D. Hirst, J. Blazewicz and N. Krasnogor. "ProCKSi: A Meta-Server for Protein Comparison using Kolniogorov and other Similarity Measures," European Conference on Computational Biology, 2007 (submitted).
• [6] H.M. Berman, J. Westbrook, 2. Feng, G- Gilliland, T.N. Bhat, H. Weissig, IN. Shindyalov, P.E. Bourne, "The Protein Data Bank," Nucleic Acids Research, vol. 28; pp. 235-242, 2000.
• [7] J. Blazewicz, P. Lukasiak Piotr, M. Milostan "Some operations research methods for analyzing protein sequences and structures," ĄOR: A Quarterly Journal of Operations Research, vol. 4, no. 2. pp. 91-123, 2006.
• [8] J. Blazewicz. P. Lukasiak, M. Milostan "Application of tabu search strategy for finding low energy structure of protein," Artificial Intelligence in Medicine, vol. 35, pp. 135-145, 2005.
• [9] H. Bohr, J. Bohr, S. Brunak, R.M. Cotterill, B. Lantrup, L. Norskov, O.K. Olscn, S.B. Petersen, "Protein secondary structure and homology by neural networks. The alpha-helices in rhodopsin," FEBS Lett, vol. 241, pp. 223-228, 1988.
• [10] J.M. Bujnicki, A. Elofsson. D. Fischer, L. Rychlewski, "Structure prediction meta server," Bioinformatics, vol. 17, pp. 750-751. 2001.
• [11] J.M. Bujnick, A. Elofsson, D. Fischer, L. Rychlewski. "LiveBench-2: Large-scale automated evaluation of protein structure prediction servers," Proteins, vol. 45, 184-191, 2001. . .
• [12] C. Bystroff, D. Baker, "Prediction of local structure in proteins using a library of sequence-structure motifs." J Mol Biol, vol. 281, pp. 565-77. 1998.
• [13] http://predictionceiiter.org
• [14] J. Drerith, Principles of protein X-ray crystallography. Springer-Verlag Inc. NY: 1999.
• [15] K. Ginalski, A. Elofsson, D. Fischer, L. Rychlewski, "3D-Jury: a simple approach to improve protein structure predictions," Bioinformatics. vol. 19(8), pp. 1015-18, 2003.
• [16] J. Guo, W.J. Chung, K. Ellrott, R. Zhou, D. Gelonia, B.D. Silverman, A.K. Royyuru, A. Curioni, A. Logean, Y. Xu, "Fold recognition using PROSPECT", CASP6 Abstracts, pp. 149-150, 2004.
• [17] J.E. Hansen, O. Lund, N. Tolstrup, A.A. Gooley, K.L. Williams, S. Brunak, "Ne-tOglyc: Prediction of mucin type O-glycosylation sites based on sequence context and surface accessibility." Glyconjug. J., vol. 15, pp. 115-130. 1998.
• [18] M. Hao, H. A. Scheraga, " On foldable protein-like models; a statistical-mechanical study with Monte Carlo simulations," Physica A, vol. 244, issue: 1-4, pp. 124-146, October 1, 1997.
• [19] J.D. Hirst, M.J.E. Sternberg, "Prediction of ATP-binding motifs a comparison of a perceptron-type neural network and a consensus sequence method," Protein Engineering, vol. 4, pp. 615-623, 1991.
• [20] J.D. Hirst, M.J.E. Sternberg, "Prediction of structural and functional features of protein and nucleic acid sequences by artificial neural networks," Biochem., vol. 31, pp. 615-623, 1992.
• [21] H. Holley, M. Karplus, "Protein Secondary Structure Prediction with a Neural Network," Proc. Natl Acad. Sci. USA, vol. 86, pp. 152-156, 1989.
• [22] M. Iwadate, K. Kanou, G. Terashi, D. Takaya, M. Takeda-Shitaka, H. Umeyarna, "Pull automatic homology modeling server including the transformation of amino acid residues: SKE(Sophia Kai Ergon) FAMS", CASP6 Abstracts, pp. 55-56, 2004.
• [23] DT. Jones, "GenTHREADER: an efficient and reliable protein fold recognition method for genornic sequences," Journal of Molecular Biology, vol. 287, pp. TOT-SIS, 1999.
• [24] D. Kneller, F. Cohen, R. Langridge, "Improvements in protein secondary structure prediction by an enhanced neural network," Journal of Molecular Biology, vol. 214, pp. 171-182, 1990.
• [25] T. Kohonen, "Self-organized formation of topologically correct feature maps," Biol. Cybern., vol. 43, pp. 59-69, 1982.
• [26] A. Kolinski arid J. Skolnick, "Reduced Models of proteins and their applications," Polymer, vol. 45, pp. 511-524, 2004.
• [2T] N. Krasnogor, B. Blackburneni, J.D. Hirst, and E.K. Burke. "Multimeme algorithms for protein structure prediction," In H.-G. Beyer J.-L. Feriiandez-Villacanas H.-P. Schwefel J.J. Merelo Gucrvos, Adamidis, editor, 7th International Conference Parallel Problem Solving from Nature, Springer Lecture Notes in Computer Science, vol. 2439, pp. 769-778, Granada, Spain, September 2002
• [28] I. Ladunga, F. Czako, L, Csabai. T. Geszti, "Improving signal peplide prediction accuracy by simulated neural network," CABIOS, vol. 7, pp. 485-487, 1991.
• [29] J. Lundstrorn, L. Rychlewski, J. Bujnicki, A. Elofssou. "Peons: A neural-network based consensus predictor that improves fold recognition." Protein Sci., vol. 10, pp. 2354 - 2362, Nov 2001.
• [30] L.J. McGuffin, J.S. Sodhi. K. Bryson. D.T. Jones "Fully automated fold recognition using nFOLD and mGenTHREADER", CASP6 Abstracts, pp. 99-100, 2004.
• [31] H. Nielseri, J. Engelbrecht, S. Brunak, G. von Heijne, "Identification of prokary-otic and eukaryotic signal peptides and prediction of their cleavage sites." Protein Engineering, vol. 10, pp. 1-6, 1997.
• [32] S. Nissen, "Implementation of a fast artificial neural network library (FANN)," Departament of Computer Science University of Copenhagen, The University Report, October 31, 2003.
• [33] S. Oldziej. J. Lagiewka, A. Liwo, C. Czaplewski, M. Chinchio, M. Nanias, H. A. Scheraga, "Optimization of the UNRES Force Field by Hierarchical Design of the Potential-Energy Landscape. 3. Use of Many Proteins in Optimization," J. Phys. Chem. B., vol. 108(43), pp. 16950-16959, 2004.
• [34] A.R. Ortiz, A. Kolinski, J. Skolnick, "Fold Assembly of Small Proteins Using Monte Carlo Simulations Driven by Restraints Derived from Multiple Sequence Alignments," J Mol Biol, vol. 277, pp. 419-448, 1998.
• [35] A.R. Ortiz, A. Kolinski, J. Skolnick, "Nativelike topology assembly of small proteins using predicted restraints in Monte Carlo folding simulations." Proc Natl Acad Sci USA, vol. 95, pp. 1020-1025, 1998.
• [36] A. Poleksic, J.F. Danzer, D.A. Debe, "Automated structure modeling with Ei-dogeu's suite of algorithms", h Up ://www. foracasp.org, 2004.
• [37] N. Qian, T. Sejnowski, "Predicting the secondary structure of globular proteins using neural network models," Journal of Molecular Biology, vol. 202, pp. 865-884, 1988.
• [38] J. Qiu, J. Pillanly, T. Galor, C.B. Lowe, L. Meyerguz, R. Elber, "Fold recognition by machine learning approach", CASP6 Abstracts, pp. 91-92, 2004.
• [39] B. R,ost, C. Sander, "Improved Prediction of Protein Secondary Structure by Use of Sequence Profiles and Neural Networks," Proc. Natl Acad. Sci. USA, vol. 90, pp. 7558-7562, 1993.
• [40] B. Rost, C. Sander, "Prediction of protein secondary structure at better than 70% accuracy," Journal of Molecular Biology, vol. 232, pp. 584-599, 1993.
• [41] B. Rost, C. Sander. R. Sclineider, "PHD - an automatic server for protein secondary structure prediction," CABIOS, vol. 10, pp. 53-60, 1994.
• [42] D.E. Rumelhart, J.L. McClelland, Parallel distributed processing. Explorations in the micro structure of cognition. MIT Press, Cambridge, M.A., U.S.A. 1986
• [43] L. Rychlewski, D. Fischer "LiveBench-S: the large-scale, continuous assessment of automated protein structure prediction." Protein Sci, vol. 14, pp. 240-245, 2005.
• [44] G. Sclineider, P. Wrede, "Development of artificial neural filters for pattern recognition in protein sequences," J. Mol. Evol, vol. 36, pp. 586-595, 1993.
• [45] N. Siew. A. Elofsson, L. Rychlewski. D. Fischer, "An Automated Measure for the Assessment of Protein Structure Prediction," Bioinformatics, vol. 16, pp. 776-785; 2000.
• [46] J. Skolnick, A. Kolinski, C. Brooks. A. Godzik, A. Rey, "A method for predicting protein structure from sequence," Curr Biol, vol. 3, pp. 414-423, 1993.
• [47] M. Stout, J. Bacardit, J.D. Hirst, N. Krasnogor, J. Blazewicz, "From hp lattice models to real proteins: coordination number prediction using learning classifier systems,'' Ąth European Workshop on Evolutionary Computation and Machine Learning in Bioinformatics, Springer Lecture Notes in Computer Science, vol. 3907, pp. 208-220, Budapest, Hungary, April 2006.
• [48] K. Tomii, "FORTE1: a simple profile-profile comparison method applied to fold recognition", CASP6 Abstracts, p. 58, 2004.
• [49] K. Tomii. "FORTE1T: profile-profile comparison with improved profiles for fold recognition", CASP6 Abstracts, p. 59, 2004.
• [50] K. Tomii, "FORTE2: automated fold recognition server with enhanced profile library", GASP6 Abstracts, pp. 59-60, 2004.
• [51] C. Venclovas. M. Margeleviius. "Comparative modeling in CASP6 using consensus approach to template selection, sequence-structure alignment, and structure assessment,'' Proteins: Structure, Function, and Bioinformatics, vol. 61, issue ST. pp. 99-105, 2005.
• [52] K. Wuthrich. NMR of proteins and nucleic acids. John Wiley &; Sons, 1986.
• [53] J. Xu and M. Li "Regression-based approaches to fold recognition", CASP6 Abstracts, pp. 123-124, 2004.
• [54] L. Yu, J. Xu and M Li, 'TACE: Consensus Fold Recognition by Predicted Model Quality", http://www.foracasp.org. 2004.
• [55] A. Zemla, "LGA - a Method for Finding 3D Similarities in Protein Structures;" Nucleic Acids Research, vol. 31, no. 13, pp. 3370-3374, 2003.
• [56] H. Zhou and Y. Zhou. "Fold recognition by combining sequence profiles derived from evolution and from depth-dependent structural alignment of fragments in CASP6," CASP6 Abstracts, pp. 154-155, 2004.
• [57] H. Zhou and Y. Zhou. "Application of SPARKS 2.0 fold recognition server in CASP6", CASP6 Abstracts, pp. 155-156, 2004.
• [58] N. Krasnogor and D.A. Pelta. "Measuring the similarity of protein structures by means of the universal similarity metric". Bioinformatics. 20(7):1015-1021, 2004.
• [59] D.A. Pelta, N. Krasnogor, C. Bousono-Calzon. J.L. Verdegay. J. Hirst, and E.K. Burke. A fuzzy sets based generalization of contact maps for the overlap of protein structures. Journal of Fuzzy Sets and Systems, 152(2):103-123. 2005.