The Scientific World Journal

The Scientific World Journal / 2014 / Article
Special Issue

Application of Machine Learning Method in Genomics and Proteomics

View this Special Issue

Research Article | Open Access

Volume 2014 |Article ID 978503 | 5 pages | https://doi.org/10.1155/2014/978503

Prediction of Four Kinds of Simple Supersecondary Structures in Protein by Using Chemical Shifts

Academic Editor: Hao Lin
Received07 May 2014
Revised03 Jun 2014
Accepted04 Jun 2014
Published18 Jun 2014

Abstract

Knowledge of supersecondary structures can provide important information about its spatial structure of protein. Some approaches have been developed for the prediction of protein supersecondary structure. However, the feature used by these approaches is primarily based on amino acid sequences. In this study, a novel model is presented to predict protein supersecondary structure by use of chemical shifts (CSs) information derived from nuclear magnetic resonance (NMR) spectroscopy. Using these CSs as inputs of the method of quadratic discriminant analysis (QD), we achieve the overall prediction accuracy of 77.3%, which is competitive with the same method for predicting supersecondary structures from amino acid compositions in threefold cross-validation. Moreover, our finding suggests that the combined use of different chemical shifts will influence the accuracy of prediction.

1. Introduction

The prediction of protein structure is always one of the most important research topics in the field of bioinformatics. However, it is very difficult to predict the spatial structure directly from the protein sequence. Therefore, the prediction of supersecondary structure is an important step in the prediction of protein spatial structure. The supersecondary structural motifs are composed of a few secondary structural elements (namely, or ) connected by loops. At present, there are four kinds of simple supersecondary structures, namely, , , , and . These motifs play an important role in protein folding and stability because a large number of motifs exist in protein spatial structure. Many researches have focused on exploring methods for protein supersecondary structure prediction [1, 2]. In 1995, Sun et al. predicted protein supersecondary structure and achieved an accuracy of between 70 and 80% by using neural networks [3]. Chou and Blinn presented a method for predicting beta turns [46], alpha turns [7], and all the tight turns [6]. Cruz et al. identified -hairpin and non--hairpin [8]. Hu and Li identified four kinds of simple supersecondary structures in 2088 proteins and achieved an accuracy of 78~83 % [9]. Zou et al. also predicted four kinds of simple supersecondary structures from 3088 proteins by using support vector machine [10]. And the overall accuracy of 78% was achieved. The features of these studies were mainly derived from the amino acid compositions or dipeptide compositions.

Nuclear magnetic resonance (NMR) technique plays an important role in the determination of three-dimensional biological macromolecule structures. NMR chemical shifts encode subtle information about the local chemical environment of nuclear spins. For many years, there has been growing interest to access this information and utilize it for biomolecular structure determination [11, 12]. Recent progress was made by combining chemical shifts with protein structure prediction programs [1320], showing that chemical shifts information is a power parameter for the determination of protein structure. In this paper, we utilized chemical shifts as parameters to predict four kinds of simple supersecondary structures in protein by the method of quadratic discriminant analysis. Using the benchmark dataset, we achieved the average of sensitivity of 76.3% and specificity of 74.3% and the overall prediction accuracy of 77.3% in threefold cross-validation by using six CSs () as features. Moreover, we have performed the prediction by combining the different chemical shifts as features. Results showed that the redundant information has great influence on the accuracy.

2. Materials and Methods

2.1. Database

The chemical shifts of all nuclei () in proteins were extracted from re-referenced protein chemical shift database (namely, RefDB [21]). The following steps were performed to construct the dataset. Firstly, only proteins with six nuclei assigned CSs were considered. Secondly, only proteins with the supersecondary structures information in ArchDB40 [22] were available. We finally utilized the PISCES program [23] to remove the highly similar sequences. After strictly following the aforementioned procedures, 114 proteins were obtained which have both CSs and supersecondary structures. Among 114 proteins, 92% (105 sequences) proteins have less than 25% sequence identity, and the sequence identity of the remains ranges from 25 to 30%. The appendix lists 114 proteins used in this study. Finally, we obtained 90 (HH), 89 (HE), 97 (EH), and 122 (EE) motifs, including the link and hairpin.

2.2. Feature Parameter

In the four data subsets , we calculated the averaged CSs of six nuclei for a sequence of length using the following formula: where . Therefore, a sequence can be converted into a six-dimensional vector .

2.3. Prediction Algorithm

To design an efficient and accurate predicted algorithm the key step is in protein supersecondary structure prediction. The quadratic discriminant analysis [24] is a power algorithm that has been widely applied in genomic and proteomic bioinformatics. Thus, we used it here to perform prediction.

2.4. Quadratic Discriminant Analysis (QD)

For a sequence to be classified, we calculated the averaged CSs of six nuclei using (1). So, the sequence is converted into a six-dimensional vector : Here we integrated six-dimensional vector by using quadratic discriminant analysis function. Consider a sequence is classified into four groups (). The discriminant analysis function between group and group is defined by

According to Bayes’ Theorem, we deduce The result can be generalized to four groups directly and described as follows.

Set where where denotes the number of samples in group , is the square mahalanobis distance between and with respect to (note: and are calculated in training set), and denotes chemical shift values of six nuclei averaged over group ; is the determinant of matrix .

The six-dimensional vector can be written as where ; ,; is the covariance matrix of dimension, quantifying correlations between the chemical shifts of six nuclei: where the element Here ; .

From (4) and (5), we have concluded

It can be easily proved that is the maximum of , if is the maximal one in (). Then, we predict that belongs to group .

2.5. Correction in the Error Allowed Scope

A sequence is predicted for four kinds of supersecondary structures by using (1)~(10). If is the maximal one in (), then we predict that belongs to group . However, there are slight differences among (). To correct predicted results, we define the coefficient of the error allowed scope as where denotes belonging to itself class, denotes being predicted another class . For example, if is the super-secondary structure of , then is and is the maximum among , , .

2.6. Performance Evaluation

In statistical prediction, independent dataset test, cross-validation test, and jackknife test can be used to examine a predictor for its effectiveness in practical application. Among the three test methods, the jackknife test is deemed to be the least arbitrary that can always yield a unique result for a given benchmark dataset [25] and has been widely used to examine the performance of various predictors [2637]. However, in this study we have used the threefold cross-validation to examine the performance of our method; in order to reduce the computational time, we randomly divided the training set into three parts, two of which are for training and the rest for testing. The process is repeated three times. The following three parameters: sensitivity (), specificity (), and overall accuracy (), are used to evaluate the predictive performance of our approach: where and , ,, and denote, respectively, true positives, false positives, true negatives, and false positives. is total number of sequences in four data subsets.

3. Results and Discussion

Under the benchmark dataset, we calculated the average chemical shift values using (1). The sequences from four data subsets are converted, respectively, into six-dimensional vectors, which are derived from chemical shift values of six nuclei; then is also a six-dimensional mean vector, which is calculated in each of the datasets. In the training sets, determinant and inverse matrix of covariance matrix are calculated. Given a sequence of the testing sets, we may calculate by using (4)~(10) and compare the results. Then the class of sequence was determined by the maximum of (). Moreover, the coefficient given in (11) is used to correct predicted results. The current study utilized . The results of threefold cross-validation are listed in Table 1.


Class
structure
SN (%)SP (%)Average 
SN (%)
Average 
SP (%)
(%)
< 0.4

HH 73.071.0 76.3 74.377.3
EH 75.878.1
HE 69.066.7
EE 87.581.4

From Table 1, we can see that the averaged sensitivity, specificity, and overall accuracy of four kinds of supersecondary structures are 76.3%, 74.3%, and 77.3%, respectively, indicating that CSs are highly informative with regard to supersecondary structures.

Generally speaking, chemical shift measurements can be incomplete for a multitude of reasons. Often, chemical shifts can only be assigned partially or are missing. To assess the impact of incomplete chemical shift assignments, we performed the prediction by using the combination of the different chemical shifts as features. The results are shown in Table 2.


Feature
combinations
HH EH HE EE Average 
SN (%)
Average 
SP (%)
(%)
SN (%)SP (%)SN (%)SP (%)SN (%)SP (%)SN (%)SP (%)

63.377.084.545.634.810071.377.063.474.964.6
90.085.366.097.085.486.493.475.583.786.184.2
55.687.761.98044.993.095.152.564.478.366.8
90.087.194.883.679.893.491.091.788.989.089.2
90.073.675.382.079.881.673.880.479.779.479.1
AAC73.373.673.077.872.471.377.575.874.174.675.8

From Table 2, we found that omission of some CSs can result in radically different accuracy. Theoretically, incomplete chemical shifts provide relatively less information, so the predicted accuracy is also declined. But it actually did not in prediction. We used CSs of ,, as features and achieved the highest accuracy of prediction, indicating that the results are affected by the redundant data. According to the performances, we concluded that CSs of ,, are the most informative features in the prediction of four kinds of protein supersecondary structures. In addition, the information of ,, is commonly provided in protein database; we achieved the prediction accuracy of 79.1% by using CSs of ,, as the only inputs.

To test the method and facilitate comparison with other features, we used amino acid compositions (AAC) as inputs of the method of quadratic discriminant analysis. The compared results are recorded in Table 2. Compared results show that the performances of CSs are superior to that of AAC for supersecondary structures prediction, except HE structure (compared with six CSs).

4. Conclusions

In this paper, we have introduced a prediction model for supersecondary structures from protein chemical shifts. Our model is both simple and easy to perform. However, owing to the limitation of both information of supersecondary structures and corresponding chemical shifts of six nuclei that should be considered, only 114 proteins have been selected in this study. Based on the benchmark dataset, we investigated the relationship between supersecondary structures and chemical shifts. We achieved the overall accuracy of 77.3% by using six CSs as features and the maximum overall accuracy of 89.2% by using the combination of CSs of ,,. Results show that chemical shift is a good parameter for the prediction of four kinds of protein supersecondary structures. In summary, the chemical shifts will become a new parameter in prediction of the protein supersecondary structures in the near future.

Appendix

See Table 3.


1a6g1a6j1a7g1ail1akh1am71avs1b2v
1b561bdo1bed1bgf1bja1by91byf1c44
1cex1cy51dfu1dhn1dqe1dtl1dyt1e0c
1edh1ejf1ekg1epf1ew41f2l1f351f3v
1f801F8H1fdq1ff31fil1g6a1g6h1gaw
1gns1gnu1go41gwy1gwy1h4a1h701hcb
1hfc1hh81hrh1hsl1huu1i4f1ifo1iho
1iko1iw01iwm1j1v1j541j7d1j971jr1
1jiw1jr21jl31jrl1jhf1k821l0s1l1d
1l6x1lfo1ljp1lld1m1f1ml41mo11mxe
1naq1ng21o151o5u1oqr1osp1php1ppf
1pz41q4r1qav1qfj1qg71qog1qst1r5r
1rro1rsy1scj1slm1snc1t151tkv1tn3
1tph1umu1uoh1uuh1uv01vap1vjh1ycq
1ze3256b

Conflict of Interests

The author declares that there is no conflict of interests regarding the publication of this paper.

Acknowledgments

The author is grateful to the anonymous reviewers for their valuable suggestions and comments, which have led to the improvement of this paper. The work was supported by Inner Mongolia Agriculture University PhD Research Fund (no. BJ08-30) and Basic Science of Inner Mongolia Agriculture University Research Fund (no. JC2013004).

References

  1. T. Blundell, D. Carney, S. Gardner et al., “Knowledge-based protein modelling and design,” European Journal of Biochemistry, vol. 172, no. 3, pp. 513–520, 1988. View at: Google Scholar
  2. H. J. Dyson and P. E. Wright, “Peptide conformation and protein folding,” Current Opinion in Structural Biology, vol. 3, no. 1, pp. 60–65, 1993. View at: Publisher Site | Google Scholar
  3. Z. Sun, X. Rao, L. Peng, and D. Xu, “Prediction of protein supersecondary structures based on the artificial neural network method,” Protein Engineering, vol. 10, no. 7, pp. 763–769, 1997. View at: Google Scholar
  4. K. C. Chou, “Prediction of beta-turns in proteins,” Journal of Peptide Research, vol. 49, pp. 120–144, 1997. View at: Google Scholar
  5. K.-C. Chou and J. R. Blinn, “Classification and prediction of β-turn types,” Journal of Protein Chemistry, vol. 16, no. 6, pp. 575–595, 1997. View at: Google Scholar
  6. K.-C. Chou, “Prediction of tight turns and their types in proteins,” Analytical Biochemistry, vol. 286, no. 1, pp. 1–16, 2000. View at: Publisher Site | Google Scholar
  7. K.-C. Chou, “Prediction and classification of α-turn types,” Biopolymers, vol. 42, no. 7, pp. 837–853, 1997. View at: Google Scholar
  8. X. de la Cruz, E. G. Hutchinson, A. Shepherd, and J. M. Thornton, “Toward predicting protein topology: an approach to identifying β hairpins,” Proceedings of the National Academy of Sciences of the United States of America, vol. 99, no. 17, pp. 11157–11162, 2002. View at: Publisher Site | Google Scholar
  9. X. Z. Hu and Q. Z. Li, “Prediction of the β-hairpins in proteins using support vector machine,” Protein Journal, vol. 27, no. 2, pp. 115–122, 2008. View at: Publisher Site | Google Scholar
  10. D. S. Zou, Z. S. He, J. Y. He, and Y. Xia, “Supersecondary structure prediction using Chou's pseudo amino acid composition,” Journal of Computational Chemistry, vol. 32, no. 2, pp. 271–278, 2011. View at: Publisher Site | Google Scholar
  11. D. A. Case, “The use of chemical shifts and their anisotropies in biomolecular structure determination,” Current Opinion in Structural Biology, vol. 8, no. 5, pp. 624–630, 1998. View at: Publisher Site | Google Scholar
  12. D. S. Wishart and D. A. Case, “Use of chemical shifts in macromolecular structure determination,” Methods in Enzymology, vol. 338, pp. 3–34, 2001. View at: Publisher Site | Google Scholar
  13. A. Cavalli, X. Salvatella, C. M. Dobson, and M. Vendruscolo, “Protein structure determination from NMR chemical shifts,” Proceedings of the National Academy of Sciences of the United States of America, vol. 104, no. 23, pp. 9615–9620, 2007. View at: Publisher Site | Google Scholar
  14. Y. Shen, O. Lange, F. Delaglio et al., “Consistent blind protein structure generation from NMR chemical shift data,” Proceedings of the National Academy of Sciences of the United States of America, vol. 105, no. 12, pp. 4685–4690, 2008. View at: Publisher Site | Google Scholar
  15. H. Lin, C. Ding, Q. Song et al., “The prediction of protein structural class using averaged chemical shifts,” Journal of Biomolecular Structure & Dynamics, vol. 29, no. 6, pp. 643–649, 2012. View at: Google Scholar
  16. M. Mechelke and M. Habeck, “A probabilistic model for secondary structure prediction from protein chemical shifts,” Proteins, vol. 81, no. 6, pp. 984–993, 2013. View at: Publisher Site | Google Scholar
  17. S. P. Mielke and V. V. Krishnan, “Protein structural class identification directly from NMR spectra using averaged chemical shifts,” Bioinformatics, vol. 19, no. 16, pp. 2054–2064, 2003. View at: Publisher Site | Google Scholar
  18. A. Pastore and V. Saudek, “The relationship between chemical shift and secondary structure in proteins,” Journal of Magnetic Resonance, vol. 90, no. 1, pp. 165–176, 1990. View at: Google Scholar
  19. Y. Wang, “Secondary structural effects on protein NMR chemical shifts,” Journal of Biomolecular NMR, vol. 30, no. 3, pp. 233–244, 2004. View at: Publisher Site | Google Scholar
  20. W. S. Mao, P. S. Cong, Z. H. Wang, L. J. Lu, Z. L. Zhu, and T. H. Li, “NMRDSP: an accurate prediction of protein shape strings from NMR chemical shifts and sequence data,” PLoS ONE, vol. 8, no. 12, Article ID e83532, 2013. View at: Google Scholar
  21. H. Zhang, S. Neal, and D. S. Wishart, “RefDB: a database of uniformly referenced protein chemical shifts,” Journal of Biomolecular NMR, vol. 25, no. 3, pp. 173–195, 2003. View at: Publisher Site | Google Scholar
  22. N. Fernandez-Fuentes, A. Hermoso, J. Espadaler, E. Querol, F. X. Aviles, and B. Oliva, “Classification of common functional loops of kinase super-families,” Proteins, vol. 56, no. 3, pp. 539–555, 2004. View at: Publisher Site | Google Scholar
  23. G. Wang and R. L. Dunbrack Jr., “PISCES: recent improvements to a PDB sequence culling server,” Nucleic Acids Research, vol. 33, no. 2, pp. W94–W98, 2005. View at: Publisher Site | Google Scholar
  24. Y. Feng and L. Luo, “Use of tetrapeptide signals for protein secondary-structure prediction,” Amino Acids, vol. 35, no. 3, pp. 607–614, 2008. View at: Publisher Site | Google Scholar
  25. K.-C. Chou and H.-B. Shen, “Cell-PLoc: a package of Web servers for predicting subcellular localization of proteins in various organisms,” Nature Protocols, vol. 3, no. 2, pp. 153–162, 2008. View at: Publisher Site | Google Scholar
  26. K.-C. Chou, “Some remarks on protein attribute prediction and pseudo amino acid composition,” Journal of Theoretical Biology, vol. 273, no. 1, pp. 236–247, 2011. View at: Publisher Site | Google Scholar
  27. M. Esmaeili, H. Mohabatkar, and S. Mohsenzadeh, “Using the concept of Chou's pseudo amino acid composition for risk type prediction of human papillomaviruses,” Journal of Theoretical Biology, vol. 263, no. 2, pp. 203–209, 2010. View at: Publisher Site | Google Scholar
  28. M. Hayat and A. Khan, “Discriminating outer membrane proteins with fuzzy K-nearest neighbor algorithms based on the general form of Chou's PseAAC,” Protein and Peptide Letters, vol. 19, no. 4, pp. 411–421, 2012. View at: Google Scholar
  29. C. Ding, L.-F. Yuan, S.-H. Guo, H. Lin, and W. Chen, “Identification of mycobacterial membrane proteins and their types using over-represented tripeptide compositions,” Journal of Proteomics, vol. 77, pp. 321–328, 2012. View at: Publisher Site | Google Scholar
  30. C. Chen, Z.-B. Shen, and X.-Y. Zou, “Dual-layer wavelet SVM for predicting protein structural class via the general form of Chou's pseudo amino acid composition,” Protein and Peptide Letters, vol. 19, no. 4, pp. 422–429, 2012. View at: Google Scholar
  31. K.-C. Chou and H.-B. Shen, “Plant-mPLoc: a top-down strategy to augment the power for predicting plant protein subcellular localization,” PLoS ONE, vol. 5, no. 6, Article ID e11335, 2010. View at: Publisher Site | Google Scholar
  32. W. Chen, P.-M. Feng, H. Lin, and K.-C. Chou, “IRSpot-PseDNC: identify recombination spots with pseudo dinucleotide composition,” Nucleic Acids Research, vol. 41, no. 6, article e68, 2013. View at: Publisher Site | Google Scholar
  33. W. Chen, H. Lin, P.-M. Feng, C. Ding, Y.-C. Zuo, and K.-C. Chou, “iNuc-PhysChem: a sequence-based predictor for identifying nucleosomes via physicochemical properties,” PLoS ONE, vol. 7, no. 10, Article ID e47843, 2012. View at: Publisher Site | Google Scholar
  34. H. Lin, W. Chen, L.-F. Yuan, Z.-Q. Li, and H. Ding, “Using over-represented tetrapeptides to predict protein submitochondria locations,” Acta Biotheoretica, vol. 61, no. 2, pp. 259–268, 2013. View at: Publisher Site | Google Scholar
  35. H. Lin, C. Ding, L.-F. Yuan et al., “Predicting subchloroplast locations of proteins based on the general form of Chou's pseudo amino acid composition: approached from optimal tripeptide composition,” International Journal of Biomathematics, vol. 6, no. 2, Article ID 13500034, 2013. View at: Publisher Site | Google Scholar
  36. W.-Z. Lin, J.-A. Fang, X. Xiao, and K.-C. Chou, “ILoc-Animal: a multi-label learning classifier for predicting subcellular localization of animal proteins,” Molecular BioSystems, vol. 9, no. 4, pp. 634–644, 2013. View at: Publisher Site | Google Scholar
  37. X. Xiao, P. Wang, W.-Z. Lin, J.-H. Jia, and K.-C. Chou, “IAMP-2L: a two-level multi-label classifier for identifying antimicrobial peptides and their functional types,” Analytical Biochemistry, vol. 436, no. 2, pp. 168–177, 2013. View at: Publisher Site | Google Scholar

Copyright © 2014 Feng Yonge. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

995 Views | 417 Downloads | 4 Citations
 PDF  Download Citation  Citation
 Download other formatsMore
 Order printed copiesOrder

We are committed to sharing findings related to COVID-19 as quickly and safely as possible. Any author submitting a COVID-19 paper should notify us at help@hindawi.com to ensure their research is fast-tracked and made available on a preprint server as soon as possible. We will be providing unlimited waivers of publication charges for accepted articles related to COVID-19.