Journals / Acta Infologica / 2022 / Cilt: 6 - Sayı: 1

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

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

Pages
43–52
Publication Date
2022-09-15
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The CNN, RNN, LSTM, and GRU models had an accuracy of 82.54%, 82.06%, 81.1%, and 81.48%, respectively.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Proteins play a crucial function in the biological processes of living organisms.
📊
Key Findings & Data:Knowing the function of the protein offers significant insight into future biological and medical research.
💡
Conclusion & Impact:The CNN, RNN, LSTM, and GRU models had an accuracy of 82.54%, 82.06%, 81.1%, and 81.48%, respectively.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

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.

Özet

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.

🔖

Cite This Article

Çakmak, E., Selvi, İ. H. (2022). Using Deep Learning (CNN, RNN, LSTM, GRU) methods for the prediction of Protein Secondary Structure. Acta Infologica, Cilt: 6 - Sayı: 1, 43–52. https://ajindex.com/articles/425955

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (9)

  1. Allison, L. A. (2007). From gene to protein. In Fundamental Molecular Biology (1. Baskı). Blackwell Publishing. Altschul, S. F., Madden, T. L., Schäffer, 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
  2. 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
  3. 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
  4. Branden, C. I., & Tooze, J. (2012). Introduction to Protein Structure. In Introduction to Protein Structure. https://doi.org/10.1201/9781136969898
  5. 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 Chou, P. Y., & Fasman, G. D. (1974). Prediction of Protein Conformation. Biochemistry. https://doi.org/10.1021/bi00699a002 Colab. (n.d.). Retrieved from https://research.google.com/colaboratory/intl/tr/faq.html
  6. Cuff, J. A., & Barton, G. J. (1999). Evaluation and improvement of multiple sequence methods for protein secondary structure prediction. Proteins: S t r u c t u r e, F u n c t i o n, a n d B i o i n f o r m a t i c s, 3 4 (4 ), 5 0 8 – 51 9. h t t p s: / / d o i. o r g / h t t p s: / / d o i. o r g / 1 0. 1 0 0 2 / (SICI)1097-0134(19990301)34:4 3.0.CO;2-4
  7. Dill, K. A., & MacCallum, J. L. (2012). The protein-folding problem, 50 years on. Science. https://doi.org/10.1126/science.1219021
  8. 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
  9. 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 Kneller, D.