利用双树复小波特征进行蛋白质二级结构预测

doi:10.3778/j.issn.1002-8331.2009-0119

摘要/Abstract

摘要： 识别蛋白质二级结构对于蛋白质的特征和性质研究具有很重要的作用。用[Cα]原子三维空间坐标把蛋白质序列映射为距离矩阵，针对距离矩阵中隐含的纹理信息，用双树复小波变换对矩阵进行4级分解，提取不同方向的子带能量和标准偏差，得到48维特征向量来表示蛋白质的二级结构特征，再将提取的特征输入KNN和SVM分类器分类，通过实验验证，双树复小波特征能改善传统特征提取方法的纹理粒度和方向局限问题，提高蛋白质二级结构的预测准确率。

关键词: 蛋白质, 二级结构预测, 双树复小波变换, 纹理特征, 支持向量机

Abstract: Recognizing the secondary structure of the protein plays an important part in studying on the characteristics and properties of proteins. In the article, the distance matrix is obtained through the three-dimensional coordinates of [Cα]in the protein. For the implicit texture information of the distance matrix, the different directions subband energy and standard deviation are extracted through the level 4 decomposition of the matrix by the double tree complex wavelet transform. Thus, 48 dimensional eigenvectors are got to represent the secondary structural characteristics of proteins. Then, extracted feature is inputted into KNN and SVM classifiers to forecast the secondary structure of protein. Finally, through experimental verification, the dual-tree complex wavelet feature can improve the grain size and direction limitation of traditional feature extraction methods and improve the accuracy of protein secondary structure prediction.

Key words: protein, prediction of secondary structure, dual-tree complex wavelet transform, texture feature, support vector machine

陈璐, 高翠芳, 鲁海燕. 利用双树复小波特征进行蛋白质二级结构预测[J]. 计算机工程与应用, 2022, 58(3): 230-234.

CHEN Lu, GAO Cuifang, LU Haiyan. Prediction of Secondary Structure of Protein Using Dual-Tree Complex Wavelet Transform[J]. Computer Engineering and Applications, 2022, 58(3): 230-234.

参考文献

[1] KONG L，ZHANG L C，LI J F.Accurate prediction of protein structural classes by incorporating predicted secondary structure information into the general form of Chou’s pseudo amino acid composition[J].Journal of Theoretical Biology，2014，344：12-18.
[2] XIAO X，SHAO S，DING Y，et al.Using cellular automata to generate image representation for biological sequences[J].Amino Acids，2005，28（1）：29-35.
[3] CHOU K C.Prediction of protein cellular attributes using pseudo-amino acid composition[J].Proteins-Structure Function & Bioinformatics，2010，43（3）：246-255.
[4] GAO C F，WU X Y.Feature extraction method for proteins based on Markov tripeptide by compressive sensing[J].BMC Bioinformatics，2018，19（1）：229.
[5] LIN H，CHEN W，YUAN L F，et al.Using over-represented tetrapeptides to predict protein submitochondria locations[J].Acta Biotheoretica，2013，61（2）：259-268.
[6] 杜月寒，鹿文鹏，刘毅慧，等.基于多重进化矩阵的蛋白质特征向量构造方法[J].计算机系统应用，2018，27（2）：180-185.
DU Y H，LU W P，LIU Y H，et al，Protein secondary structure prediction based on multiple evolutionary matrix[J].Computer Systems & Applications，2018，27（2）：180-185.
[7] CHENG X，XIAO X，CHOU K C.Ploc-meuk：predict subcellular localization of multi-label eukaryotic proteins by extracting the key go information into general pseaac[J].Genomics，2017，110（1）：50-58.
[8] COVER T M，HART P E.Nearest neighbor pattern classification[J].IEEE Transactions on Information Theory，1967，13（1）：21-27.
[9] 吴晓明，宋长新，王波，等.隐马尔可夫模型用于蛋白质序列分析[J].生物医学工程学杂志，2002，19（3）：455-458.
WU X M，SONG C X，WANG B，et al.Hidden markov model used in protein sequence analysis[J].Journal of Biomedical Engineering，2002，19（3）：455-458.
[10] CHEN J N，HUANG H K，TIAN S F，et al.Feature selection for text classification with Nave Bayes[J].Expert Systems with Applications，2009，36（3）：5432-5435.
[11] 鲁静，崔波.人工神经网络在蛋白质结构预测和QSAR 中的应用[J].广东化工，2009，36（11）：92-93.
LU J，CUI B.Artificial neural network in protein structure prediction and QSAR application[J].Guangdong Chemical Industry，2009，36（11）：92-93.
[12] BUTT A H，RASOOL N，KHAN Y D.A treatise to computational approaches towards prediction of membrane protein and its subtypes[J].Journal of Membrane Biology，2017，250（1）：55-76.
[13] KENNEL P，FIORIO C，BORNE F.Supervised image segmentation using q-shift dual-tree complex wavelet transform coefficients with a texton approach[J].Pattern Analysis Applications，2017，20（1）：227-237.
[14] SUN B，ZHU W D，LUO C W，et al.Fusion of noisy images based on joint distribution model in dual-tree complex wavelet domain[J].International Journal of Imaging Systems and Technology，2019，29（1）：29-41.
[15] 肖绚，肖纯材，王普.基于距离矩阵灰度图的蛋白质二级结构类型预测[J].计算机应用研究，2010，27（10）：104-106.
XIAO X，XIAO C C，WANG P.Secondary structure prediction by grayscale image of distance matrix[J].Application Research of Computers，2010，27（10）：104-106.
[16] KURGAN L A，HOMAEIAN L.Prediction of structural classes for protein sequences and domains—impact of prediction algorithms，sequence representation and homology，and test procedures on accuracy[J].Pattern Recognition，2006，39（12）：2323-2343.
[17] TAYLOR W R，ORENGO C A.Protein structure alignment[J].Journal of Molecular Biology，1989，208（1）：1-22.
[18] KINGSBURY N.Complex wavelets for shift invariant analysis and filtering of signals[J].Applied & Computational Harmonic Analysis，2001，10（3）：234-253.
[19] KOKARE M.Texture image retrieval using new rotated complex wavelet filters[J].IEEE Transactions System Man，and Cybernetics，Part B，2005，35（6）：1168-1178.
[20] KOKARE M，BISWAS P K，CHATTERJI B N.Rotation-invariant texture image retrieval using rotated complex wavelet filters[J].IEEE Transactions on Systems Man & Cybernetics Part B Cybernetics A Publication of the IEEE Systems Man & Cybernetics Society，2006，36（6）：1273-1282.
[21] LU Z，CHOU K C.pLoc_Deep-mGpos：predict subcellular localization of gram positive bacteria proteins by deep learning[J].Journal of Biomedical Science and Engineering，2020，13（5）：55-65.
[22] 施建宇，张艳宁.使用图像特征构建快速有效的蛋白质折叠识别方法[J].生物物理学报，2009（2）：106-116.
SHI J Y，ZHANG Y N.A fast and effective approach of fold recognition based on image feature[J].Acta Biophysica Sinica，2009（2）：106-116.