Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the  prediction of Protein Secondary Structure

Çakmak Ezgi; Selvi İhsan

doi:https://dx.doi.org/10.26650/acin.1008075

Research Article

DOI :10.26650/acin.1008075 IUP :10.26650/acin.1008075 Full Text (PDF)

Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure

Proteins play a crucial function in the biological processes of living organisms. Knowing the function of the protein offers significant insight into future biological and medical research. Since a protein’s shape determines its function, it is important to understand the protein’s 3D structure. Although experimental methods such as X-ray crystallography and nuclear magnetic resonance (NMR) have been used to examine the shape of proteins, so far the results have been insufficient. As a result, predicting the 3D structure of proteins is crucial. Determining the 3D structure of a protein from its primary structure is challenging. Therefore, predicting the protein secondary structure becomes important for studying its structure and function. Many emerging methods, including machine learning, as well as deep learning, have been used to predict the secondary structure of proteins and comprise a crucial part of Structural Bioinformatics. The goal of this study is to compare the results generated by predictive models that were created using the four most frequently utilized deep learning methods: convolutional neural networks (CNN), recurrent neural networks (RNN), long short term memory networks (LSTM), and gated recurrent units (GRU). The CB513 dataset was used to train and test these models, and performance evaluation metrics viz. accuracy, f1 score, recall, and precision were applied. The CNN, RNN, LSTM, and GRU models had an accuracy of 82.54%, 82.06%, 81.1%, and 81.48%, respectively.

Keywords: Protein Secondary Structure Prediction, CNN, RNN, GRU

DOI :10.26650/acin.1008075 IUP :10.26650/acin.1008075 Full Text (PDF)

Derin Öğrenme (CNN, RNN, LSTM, GRU) Kullanarak Protein İkincil Yapı Tahmini

Ezgi Çakmak, İhsan Hakan Selvi

Protein, canlı organizmaların biyolojik süreçlerinde çok önemli bir role sahiptir. Proteinin işlevini bilmek, biyoloji ve tıp alanında gelecekteki çalışmalara büyük katkı sağlar. Proteinin fonksiyonunu anlamak için üç boyutlu yapısını anlamak önemlidir. Protein yapısını çözümlemek için X-ışını kristalografisi ve NMR gibi deneysel yöntemler kullanılmasına rağmen, sonuçların yetersiz olduğu kanıtlanmıştır. Bu nedenle, proteinlerin üç boyutlu yapısının tahmini, süreçlerdeki en önemli konulardan biri haline gelmektedir. Birincil yapı olarak bilinen amino asit dizisinden proteinin üç boyutlu şeklinin belirlenmesi zorlu olarak tanımlandığından, ikincil yapının tahmin edilmesi bu konuda önemli bir rol oynamaktadır. Literatürde protein ikincil yapısını tahmin etmek için makine öğrenmesi ve son zamanlarda derin öğrenme gibi birçok yöntem kullanılmıştır. Bu makale, yaygın olarak uygulanan dört derin öğrenme yöntemi olan CNN, RNN, LSTM ve GRU kullanılarak geliştirilen modellerin performanslarının bir karşılaştırmasını sağlamayı amaçlamaktadır. Bu modellerin eğitimi ve test edilmesi amacıyla CB513 veri seti kullanılmış, buna ek olarak doğruluk, f1 skoru, doğruluk ve kesinlik gibi performans değerlendirme ölçütleri uygulanmıştır. CNN, RNN, LSTM ve GRU modellerinin doğruluk oranları sırasıyla %82,54, %82,06, %81,1 ve %81,48’dir.

Keywords: Protein İkincil Yapı Tahmini, CNN, RNN, GRU

References

Allison, L. A. (2007). From gene to protein. In Fundamental Molecular Biology (1. Baskı). Blackwell Publishing. google scholar
Altschul, S. F., Madden, T. L., Schaffer, A. A., Zhang, J., Zhang, Z, Miller, W., & Lipman, D. J. (1997). Gapped BLAST and PSI-BLAST: a new generation of protein database search programs. Nucleic Acids Research, 25(17), 3389-3402. https://doi.org/10.1093/nar/25.17.3389 google scholar
Aydin, Z., Kaynar, O., & Görmez, Y. (2018). Comparison of NR and UniClust databases for protein secondary structure prediction. 2018 26th Signal Processing and Communications Applications Conference (SIU), 1-4. https://doi.org/10.1109/SIU.2018.8404285 google scholar
Baldi, P., Brunak, S., Frasconi, P., Soda, G., & Pollastri, G. (1999). Exploiting the past and the future in protein secondary structure prediction. Bioinformatics, 15(11). https://doi.org/10.1093/bioinformatics/15.11.937 google scholar
Branden, C. I., & Tooze, J. (2012). Introduction to Protein Structure. In Introduction to Protein Structure. https://doi.org/10.1201/9781136969898 google scholar
Chen, C., Tian, Y., Zou, X., Cai, P., & Mo, J. (2007). Prediction of protein secondary structure content using support vector machine. Talanta. https://doi. org/10.1016/j.talanta.2006.09.015 google scholar
Chou, P. Y., & Fasman, G. D. (1974). Prediction of Protein Conformation. Biochemistry. https://doi.org/10.1021/bi00699a002 google scholar
Colab. (n.d.). Retrieved from https://research.google.com/colaboratory/intl/tr/faq.html google scholar
Cuff, J. A., & Barton, G. J. (1999). Evaluation and improvement of multiple sequence methods for protein secondary structure prediction. Proteins: Structure, Function, and Bioinformatics, 34(4), 508-519. https://doi.org/https://doi.org/10.1002/(SICI)1097-0134(19990301)34:4<508::AID-PROT10>3.0.CO;2-4 google scholar
Dill, K. A., & MacCallum, J. L. (2012). The protein-folding problem, 50 years on. Science. https://doi.org/10.1126/science.1219021 google scholar
Garnier, J., Osguthorpe, D. J., & Robson, B. (1978). Analysis of the accuracy and implications of simple methods for predicting the secondary structure of globular proteins. Journal of Molecular Biology. https://doi.org/10.1016/0022-2836(78)90297-8 google scholar
Heffernan, R., Yang, Y., Paliwal, K., & Zhou, Y. (2017). Capturing non-local interactions by long short-term memory bidirectional recurrent neural networks for improving prediction of protein secondary structure, backbone angles, contact numbers and solvent accessibility. Bioinformatics. https:// doi.org/10.1093/bioinformatics/btx218 google scholar
Kneller, D. G., Cohen, F. E., & Langridge, R. (1990). Improvements in protein secondary structure prediction by an enhanced neural network. Journal of Molecular Biology. https://doi.org/10.1016/0022-2836(90)90154-E google scholar
Liu, H. L., & Hsu, J. P. (2005). Recent developments in structural proteomics for protein structure determination. Proteomics. https://doi.org/10.1002/ pmic.200401104 google scholar
Mirabello, C., & Pollastri, G. (2013). Porter, PaleAle 4.0: High-accuracy prediction of protein secondary structure and relative solvent accessibility. Bioinformatics. https://doi.org/10.1093/bioinformatics/btt344 google scholar
Moraes, I., Evans, G., Sanchez-Weatherby, J., Newstead, S., & Stewart, P. D. S. (2014). Membrane protein structure determination—the next generation. Biochimica et Biophysica Acta (BBA)-Biomembranes, 1838(1), 78-87. google scholar
Nguyen, M. N., & Rajapakse, J. C. (2003). Multi-class support vector machines for protein secondary structure prediction. Genome Informatics. International Conference on Genome Informatics. https://doi.org/10.11234/gi1990.14.218 google scholar
Pollastri, G., & McLysaght, A. (2005). Porter: A new, accurate server for protein secondary structure prediction. Bioinformatics. https://doi.org/10.1093/ bioinformatics/bti203 google scholar
Rost, B., & Sander, C. (2000). Third generation prediction of secondary structures. In Webster, D. (Ed.), Protein Structure Prediction: Methods and Protocols (pp. 71-95). https://doi.org/10.1385/1-59259-368-2:71 google scholar
Rost, B. (2003). Rising Accuracy of Protein Secondary Structure Prediction. 207-249. google scholar
Rost, Burkhard, & Sander, C. (1994). Combining evolutionary information and neural networks to predict protein secondary structure. Proteins: Structure, Function, and Bioinformatics. https://doi.org/10.1002/prot.340190108 google scholar
Salamov, A. A., & Solovyev, V. V. (1995). Prediction of protein secondary structure by combining nearest-neighbor algorithms and multiple sequence alignments. Journal of Molecular Biology. https://doi.org/10.1006/jmbi.1994.0116 google scholar
Wang, J., Cheng, J., Zhao, Z., & Lu, W. (2019). Protein Secondary Structure Prediction Using Ensemble of LSTM Neural Networks. 2019 2nd International Conference on Information Systems and Computer Aided Education, ICISCAE 2019. https://doi.org/10.1109/ICISCAE48440.2019.221626 google scholar
Wang, Y., Mao, H., & Yi, Z. (2017). Protein secondary structure prediction by using deep learning method. Knowledge-Based Systems, 118, 115-123. https://doi.org/10.1016/j.knosys.2016.11.015 google scholar
Yi, T. M., & Lander, E. S. (1993). Protein secondary structure prediction using nearest-neighbor methods. Journal of Molecular Biology. https://doi.org/10.1006/jmbi.1993.1464 google scholar

Citations

Copy and paste a formatted citation or use one of the options to export in your chosen format

EXPORT

APA

Çakmak, E., & Selvi, İ.H. (2022). Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure. Acta Infologica, 6(1), 43-52. https://doi.org/10.26650/acin.1008075

AMA

Çakmak E, Selvi İ H. Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure. Acta Infologica. 2022;6(1):43-52. https://doi.org/10.26650/acin.1008075

ABNT

Çakmak, E.; Selvi, İ.H. Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure. Acta Infologica, [Publisher Location], v. 6, n. 1, p. 43-52, 2022.

Chicago: Author-Date Style

Çakmak, Ezgi, and İhsan Hakan Selvi. 2022. “Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure.” Acta Infologica 6, no. 1: 43-52. https://doi.org/10.26650/acin.1008075

Chicago: Humanities Style

Çakmak, Ezgi, and İhsan Hakan Selvi. “Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure.” Acta Infologica 6, no. 1 (May. 2024): 43-52. https://doi.org/10.26650/acin.1008075

Harvard: Australian Style

Çakmak, E & Selvi, İH 2022, 'Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure', Acta Infologica, vol. 6, no. 1, pp. 43-52, viewed 19 May. 2024, https://doi.org/10.26650/acin.1008075

Harvard: Author-Date Style

Çakmak, E. and Selvi, İ.H. (2022) ‘Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure’, Acta Infologica, 6(1), pp. 43-52. https://doi.org/10.26650/acin.1008075 (19 May. 2024).

MLA

Çakmak, Ezgi, and İhsan Hakan Selvi. “Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure.” Acta Infologica, vol. 6, no. 1, 2022, pp. 43-52. [Database Container], https://doi.org/10.26650/acin.1008075

Vancouver

Çakmak E, Selvi İH. Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure. Acta Infologica [Internet]. 19 May. 2024 [cited 19 May. 2024];6(1):43-52. Available from: https://doi.org/10.26650/acin.1008075 doi: 10.26650/acin.1008075

ISNAD

Çakmak, Ezgi - Selvi, İhsanHakan. “Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure”. Acta Infologica 6/1 (May. 2024): 43-52. https://doi.org/10.26650/acin.1008075

Volume 6, Issue 12022, P. 43-52

TIMELINE

Submitted	11.10.2021
Accepted	14.03.2022
Published Online	28.04.2022

LICENCE

Attribution-NonCommercial (CC BY-NC)

This license lets others remix, tweak, and build upon your work non-commercially, and although their new works must also acknowledge you and be non-commercial, they don’t have to license their derivative works on the same terms.

Acta Infologica