基于生成对抗和卷积神经网络的蛋白质二级结构预测
Protein Secondary Structure Prediction Based on Generative Confrontation and Convolutional Neural Network
DOI: 10.12677/HJCB.2020.104006, PDF,  被引量    国家自然科学基金支持
作者: 赵亚武, 张华兰, 刘毅慧：齐鲁工业大学(山东省科学院)计算机科学与技术学院，山东 济南
关键词: 生物信息学；生成对抗网络；卷积神经网络；蛋白质二级结构预测；Bioinformatics； Generative Adversarial Network； Convolutional Neural Network； Protein Secondary Structure Prediction
摘要: 在生物信息学领域，对于蛋白质二级结构预测是一项具有挑战性的任务，对于确定蛋白质的结构和功能有着极其重要的意义。本文融合了生成对抗网络和卷积神经网络模型进行蛋白质二级结构预测，首先利用生成对抗网络提取蛋白质特征，其次将生成对抗网络提取的特征结合PSSM矩阵作为卷积神经网络的输入，得到预测结果。在测试集CASP9，CASP10，CASP11，CASP12，CB513和PDB25获得了87.06%，87.24%，87.31%，87.39%，88.13%和88.93%，比单独使用卷积神经网络提高了3.88%，4.6%，7.97%，5.85%，5.78%，4.25%。实验结果表明，生成对抗网络特征提取能力是非常显著的。
Abstract: In the field of bioinformatics, the prediction of protein secondary structure is a challenging task, and it is extremely important for determining the structure and function of proteins. In this paper, the generation of adversarial networks and convolutional neural network models are combined for protein secondary structure prediction. First, the anti-network is generated to extract protein fea-tures. Secondly, the extracted features of the anti-network are combined with the PSSM matrix as the input of the convolutional neural network to obtain the prediction results. In the test set CASP9, CASP10, CASP11, CASP12, CB513 and PDB25 obtained 87.06%, 87.24%, 87.31%, 87.39%, 88.13% and 88.93%, which is 3.88%, 4.6%, 7.97%, 5.85%, 5.78%, 4.25% higher than the convolutional neural network alone. The experimental results show that the feature extraction ability of generat-ing adversarial networks is very significant.
文章引用：赵亚武, 张华兰, 刘毅慧. 基于生成对抗和卷积神经网络的蛋白质二级结构预测[J]. 计算生物学, 2020, 10(4): 49-56. https://doi.org/10.12677/HJCB.2020.104006

参考文献

[1] Chou, K.C. (2005) Progress in Protein Structural Class Prediction and Its Impact to Bioinformatics and Proteomics. Current Protein & Peptide Science, 6, 423-436. [Google Scholar] [CrossRef] [PubMed]
[2] Costantini, S. and Facchiano, A.M. (2009) Prediction of the Protein Structural Class by Specific Peptide Frequencies. Biochimie, 91, 226-229. [Google Scholar] [CrossRef] [PubMed]
[3] Yang, Y., Gao, J., Wang, J., Heffernan, R., Hanson, J., Paliwal, K. and Zhou, Y. (2018) Sixty-Five Years of the Long March in Protein Secondary Structure Prediction: The Fi-nal Stretch? Briefings in Bioinformatics, 19, 482-494.
[4] Hu, H., Pan, Y., Harrison, R., et al. (2004) Improved Protein Secondary Structure Prediction Using Support Vector Machine with a New Encoding Scheme and an Advanced Tertiary Classifier. IEEE Transactions on Nanobioscience, 3, 265. [Google Scholar] [CrossRef] 
[5] Wang, Y., Cheng, J., Liu, Y., et al. (2016) Prediction of Protein Secondary Structure Using Support Vector Machine with PSSM Profiles. Information Technology, Networking, Electronic & Automation Control Conference, Chongqing, 20-22 May 2016. [Google Scholar] [CrossRef] 
[6] Zheng, X., Li, C. and Wang, J. (2010) An Infor-mation-Theoretic Approach to the Prediction of Protein Structural Class. Journal of Computational Chemistry, 31, 1201-1206.
[7] Robles, V., Larrañaga, P., Peña, J., et al. (2004) Bayesian Network Multi-Classifiers for Protein Sec-ondary Structure Prediction. Artificial Intelligence in Medicine, 31, 117-136. [Google Scholar] [CrossRef] [PubMed]
[8] Liu, Y. and Cheng, J. (2016) Protein Secondary Structure Pre-diction Based on Wavelets and 2D Convolutional Neural Network. International Conference on Computational Systems Biology & Bioinformatics, 53-57. [Google Scholar] [CrossRef] 
[9] Pollastri, G., Przybylski, D., Rost, B., et al. (2002) Improving the Prediction of Protein Secondary Structure in Three and Eight Classes Using Recurrent Neural Networks and Profiles. Proteins, 47, 228-235. [Google Scholar] [CrossRef] [PubMed]
[10] Heffernan, R., Yang, Y., Paliwal, K., et al. (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, 33, 2842-2849. [Google Scholar] [CrossRef] [PubMed]
[11] Hanson, J., Paliwal, K., Litfin, T., et al. (2018) Improving Pre-diction of Protein Secondary Structure, Backbone Angles, Solvent Accessibility, and Contact Numbers by Using Pre-dicted Contact Maps and an Ensemble of Recurrent and Residual Convolutional Neural Networks. Bioinformatics, 35, 2403-2410. [Google Scholar] [CrossRef] [PubMed]
[12] Ma, Y., Liu, Y. and Cheng, J. (2018) Protein Secondary Structure Prediction Based on Data Partition and Semi-Random Subspace Method. Scientific Reports, 8, Arti-cle No. 9856. [Google Scholar] [CrossRef] [PubMed]
[13] Chao, F., Yi, S. and Dong, X. (2018) MUFOLD-SS: New Deep Inception-inside-Inception Networks for Protein Secondary Structure Prediction. Proteins: Structure, Function, and Bioinformatics, 86, 592-598. [Google Scholar] [CrossRef] [PubMed]
[14] 陈人和, 赖振意, 钱育蓉. 改进的生成对抗网络图像去噪算法[J/OL]. 计算机工程与应用, 1-8. https://kns.cnki.net/kcms/detail/11.2127.TP.20200529.1705.020.html, 2020-11-26.
[15] 秦月红, 王敏. 基于生成对抗网络的跨视角步态特征提取[J]. 计算机系统应用, 2020, 29(1): 164-170.
[16] Jones, D.T. (1999) Protein Secondary Structure Prediction Based on Position-Specific Scoring Matrices. Journal of Molecular Biology, 292, 195-202. [Google Scholar] [CrossRef] [PubMed]
[17] Kabsch, W. and Sander, C. (2010) Dictionary of Protein Secondary Structure: Pattern Recognition of Hydrogen-Bonded and Geometrical Features. Biopolymers, 22, 2577-2637. [Google Scholar] [CrossRef] [PubMed]
[18] Fox, N., Brenner, S. and Chandonia, J. (2014) SCOPe: Structural Classification of Proteins-Extended, Integrating SCOP and ASTRAL Data and Classification of New Structures. Nucleic Acids Research, 42, 304-309. [Google Scholar] [CrossRef] [PubMed]
[19] Wang, G. and Dunbrack, R. (2005) PISCES: Recent Improvements to a PDB Sequence Culling Server. Nucleic Acids Research, 33, W94-W98. [Google Scholar] [CrossRef] [PubMed]
[20] Moult, J., Fidelis, K., Kryshtafovych, A., et al. (2011) Critical Assessment of Methods of Protein Structure Prediction (CASP)—Round IX. Proteins, 79, 1-5. [Google Scholar] [CrossRef] [PubMed]
[21] Moult, J., Fidelis, K., Kryshtafovych, A., et al. (2014) Critical Assessment of Methods of Protein Structure Prediction (CASP)—Round X. Proteins: Structure, Function, and Bioinformatics, 82, 1-6. [Google Scholar] [CrossRef] [PubMed]
[22] Moult, J., Fidelis, K., Kryshtafovych, A., et al. (2012) Critical As-sessment of Methods of Protein Structure Prediction (CASP)—Round X. Proteins: Structure, Function, and Bioinfor-matics.
[23] Cuff, J., Barton, G., et al. (1999) Evaluation and Improvement of Multiple Sequence Methods for Protein Secondary Structure Prediction. Proteins: Structure, Function and Genetics, 34, 508-519. [Google Scholar] [CrossRef] 
[24] Kedarisetti, K., Kurgan, L., Dick, S., et al. (2006) Classifier Ensembles for Protein Structural Class Prediction with Varying Homology. Biochemical and Biophysical Research Communications, 348, 981-988. [Google Scholar] [CrossRef] [PubMed]
[25] Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., et al. (2014) Gen-erative Adversarial Nets. In: International Conference on Neural Information Processing Systems, MIT Press, Cam-bridge, 2672-2680.
[26] Chartrand, G., Cheng, P.M., Vorontsov, E., et al. (2017) Deep Learning: A Primer for Radiol-ogists. Radiographics, 37, 2113-2131. [Google Scholar] [CrossRef] [PubMed]
[27] 卢宏涛, 张秦川. 深度卷积神经网络在计算机视觉中的应用研究综述[J]. 数据采集与处理, 2016, 31(1): 1-17.
[28] Bishop, C. (2006) Pattern Recognition and Machine Learning. Springer, New York.

为你推荐