Journal of Computer Science and Technology

, Volume 34, Issue 1, pp 3–15 | Cite as

Decoding the Structural Keywords in Protein Structure Universe

  • Wessam Elhefnawy
  • Min Li
  • Jian-Xin Wang
  • Yaohang LiEmail author
Regular Paper


Although the protein sequence-structure gap continues to enlarge due to the development of high-throughput sequencing tools, the protein structure universe tends to be complete without proteins with novel structural folds deposited in the protein data bank (PDB) recently. In this work, we identify a protein structural dictionary (Frag-K) composed of a set of backbone fragments ranging from 4 to 20 residues as the structural “keywords” that can effectively distinguish between major protein folds. We firstly apply randomized spectral clustering and random forest algorithms to construct representative and sensitive protein fragment libraries from a large scale of high-quality, non-homologous protein structures available in PDB. We analyze the impacts of clustering cut-offs on the performance of the fragment libraries. Then, the Frag-K fragments are employed as structural features to classify protein structures in major protein folds defined by SCOP (Structural Classification of Proteins). Our results show that a structural dictionary with ~400 4- to 20-residue Frag-K fragments is capable of classifying major SCOP folds with high accuracy.


protein fragment fold recognition protein structure universe 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Supplementary material

11390_2019_1895_MOESM1_ESM.pdf (722 kb)
ESM 1 (PDF 721 kb)


  1. [1]
    Schwede T. Protein modeling: What happened to the protein structure gap? Structure, 2013, 21(9): 1531-1540.CrossRefGoogle Scholar
  2. [2]
    Chothia C. Proteins. One thousand families for the molecular biologist. Nature, 1992, 357(6379): 543-544.CrossRefGoogle Scholar
  3. [3]
    Andreeva A, Howorth D, Chandonia J M, Brenner S E, Hubbard T J P, Chothia C, Murzin A G. Data growth and its impact on the SCOP database: New developments. Nucleic Acids Research, 2008, 36: D419-D425.CrossRefGoogle Scholar
  4. [4]
    Sillitoe I, Cuff A L, Dessailly B H, Dawson D L, Furnham N, Lee D, Lees J G, Lewis T E, Studer R A, Rentzsch R, Yeats C, Thornton J M, Orengo C A. New functional families (FunFams) in CATH to improve the mapping of conserved functional sites to 3D structures. Nucleic Acids Research, 2013, 41(D1): D490-D498.CrossRefGoogle Scholar
  5. [5]
    Chen D. Structural genomics: Exploring the 3D protein landscape, 2010. Biomedical Computation Review., Nov. 2018.
  6. [6]
    Kolinski A. Protein modeling and structure prediction with a reduced representation. Acta Biochimica Polonica, 2004, 51(2): 349-371.Google Scholar
  7. [7]
    Schwede T, Kopp J, Guex N, Peitsch M C. SWISS-MODEL: An automated protein homology-modeling server. Nucleic Acids Research, 2003, 31(13): 3381-3385.CrossRefGoogle Scholar
  8. [8]
    Zhou J F, Grigoryan G. Rapid search for tertiary fragments reveals protein sequence-structure relationships. Protein Science, 2015, 24(4): 508-524.CrossRefGoogle Scholar
  9. [9]
    Simons K T, Kooperberg C, Huang E, Baker D. Assembly of protein tertiary structures from fragments with similar local sequences using simulated annealing and Bayesian scoring functions. Journal of Molecular Biology, 1997, 268(1): 209-225.CrossRefGoogle Scholar
  10. [10]
    Li Y. Conformational sampling in template-free protein loop structure modeling: An overview. Computational and Structural Biotechnology Journal, 2013, 5: Article No. e201302003.Google Scholar
  11. [11]
    Li Y, Rata I, Jakobsson E. Integrating multiple scoring functions to improve protein loop structure conformation space sampling. In Proc. IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology, May 2010.Google Scholar
  12. [12]
    Li Y, Rata I, Chiu S W, Jakobsson E. Improving predicted protein loop structure ranking using a Pareto-optimality consensus method. BMC Structural Biology, 2010, 10: Article No. 22.Google Scholar
  13. [13]
    Simons K T, Ruczinski I, Kooperberg C, Fox B A, Bystroff C, Baker D. Improved recognition of native-like protein structures using a combination of sequence-dependent and sequence-independent features of proteins. Proteins: Structure, Function, and Genetics, 1999, 34(1): 82-95.CrossRefGoogle Scholar
  14. [14]
    Kolodny R, Koehl P, Guibas L, Levitt M. Small libraries of protein fragments model native protein structures accurately. Journal of Molecular Biology, 2002, 323(2): 297-307.CrossRefGoogle Scholar
  15. [15]
    Budowski-Tal I, Nov Y, Kolodny R. FragBag, an accurate representation of protein structure, retrieves structural neighbors from the entire PDB quickly and accurately. Proceedings of the National Academy of Sciences of the United States of America, 2010, 107(8): 3481-3486.CrossRefGoogle Scholar
  16. [16]
    Handl J, Knowles J, Vernon R, Baker D, Lovell S C. The dual role of fragments in fragment-assembly methods for de novo protein structure prediction. Proteins: Structure, Function, and Bioinformatics, 2012, 80(2): 490-504.CrossRefGoogle Scholar
  17. [17]
    Ji H, Yu W, Li Y. A rank revealing randomized singular value decomposition (R3SVD) algorithm for low-rank matrix approximations. arXiv:1605.08134, 2016. https://ar, September 2018.
  18. [18]
    Elhefnawy W, Li M, Wang J, Li Y. Construction of protein backbone fragments libraries on large protein sets using a randomized spectral clustering algorithm. In Proc. the 13th International Symposium on Bioinformatics Research and Applications, May 2016, pp.108-119.Google Scholar
  19. [19]
    Wang G L, Dunbrack R L. PISCES: A protein sequence culling server. Bioinformatics, 2003, 19(12): 1589-1591.CrossRefGoogle Scholar
  20. [20]
    Dong Q W, Zhou S G, Guan J H. A new taxonomybased protein fold recognition approach based on autocrosscovariance transformation. Bioinformatics, 2009, 25(20): 2655-2662.CrossRefGoogle Scholar
  21. [21]
    Ding C H Q, Dubchak I. Multi-class protein fold recognition using support vector machines and neural networks. Bioinformatics, 2001, 17(4): 349-358.CrossRefGoogle Scholar
  22. [22]
    Fox N K, Brenner S E, Chandonia J M. SCOPe: Structural classification of proteins-extended, integrating SCOP and ASTRAL data and classification of new structures. Nucleic Acids Research, 2014, 42(D1): D304-D309.CrossRefGoogle Scholar
  23. [23]
    von Luxburg U. A tutorial on spectral clustering. Statistics and Computing, 2007, 17(4): 395-416.MathSciNetCrossRefGoogle Scholar
  24. [24]
    Shi J B, Malik J. Normalized cuts and image segmentation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2000, 22(8): 888-905.CrossRefGoogle Scholar
  25. [25]
    Ng A Y, Jordan M I, Weiss Y. On spectral clustering: Analysis and an algorithm. In Proc. the 14th International Conference on Neural Information Processing Systems: Natural and Synthetic, December 2001, pp.849-856.Google Scholar
  26. [26]
    Halko N, Martinsson P G, Tropp J A. Finding structure with randomness: Probabilistic algorithms for constructing approximate matrix decompositions. SIAM Review, 2011, 53(2): 217-288.MathSciNetCrossRefzbMATHGoogle Scholar
  27. [27]
    Gu Y, Yu W, Li J, Liu S, Li Y. Single-pass PCA of large high-dimensional data. In Proc. the 26th International Joint Conference on Artificial Intelligence, August 2017, pp.3350-3356.Google Scholar
  28. [28]
    Li Y, YuW. A fast implementation of singular value thresholding algorithm using recycling rank revealing randomized singular value decomposition. arXiv:1704.05528, 2017., September 2018.
  29. [29]
    Strobl C, Boulesteix A L, Zeileis A, Hothorn T. Bias in random forest variable importance measures: Illustrations, sources and a solution. BMC Bioinformatics, 2007, 8: Article No. 25.Google Scholar
  30. [30]
    Chiang Y S, Gelfand T I, Kister A E, Gelfand I M. New classification of supersecondary structures of sandwich-like proteins uncovers strict patterns of strand assemblage. Proteins: Structure, Function, and Bioinformatics, 2007, 68(4): 915-921.CrossRefGoogle Scholar
  31. [31]
    Holmes J B, Tsai J. Some fundamental aspects of building protein structures from fragment libraries. Protein Science, 2004, 13(6): 1636-1650.CrossRefGoogle Scholar
  32. [32]
    Le Q, Pollastri G, Koehl P. Structural alphabets for protein structure classification: A comparison study. Journal of Molecular Biology, 2009, 387(2): 431-450.CrossRefGoogle Scholar
  33. [33]
    Bazzoli A, Tettamanzi A G B, Zhang Y. Computational protein design and large-scale assessment by I-TASSER structure assembly simulations. Journal of Molecular Biology, 2011, 407(5): 764-776.CrossRefGoogle Scholar
  34. [34]
    Elhefnawy W, Chen L, Han Y, Li Y. ICOSA: A distancedependent, orientation-specific coarse-grained contact potential for protein structure modeling. Journal of Molecular Biology, 2015, 427(15): 2562-2576.CrossRefGoogle Scholar
  35. [35]
    Li Y, Liu H, Rata I, Jakobsson E. Building a knowledgebased statistical potential by capturing high-order interresidue interactions and its applications in protein secondary structure assessment. Journal of Chemical Information and Modeling, 2013, 53(2): 500-508.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2019

Authors and Affiliations

  • Wessam Elhefnawy
    • 1
  • Min Li
    • 2
  • Jian-Xin Wang
    • 2
  • Yaohang Li
    • 1
    Email author
  1. 1.Department of Computer ScienceOld Dominion UniversityNorfolkUSA
  2. 2.Department of Computer ScienceCentral South UniversityChangshaChina

Personalised recommendations