Protein secondary structure prediction using modular reciprocal bidirectional recurrent neural networks

被引:20
作者
Babaei, Sepideh [2 ]
Geranmayeh, Amir [1 ]
Seyyedsalehi, Seyyed Ali [2 ]
机构
[1] Tech Univ Darmstadt, Dept Elect Engn & Informat Technol, D-64289 Darmstadt, Hessen, Germany
[2] Amirkabir Univ Technol, Tehran Polytech, Dept Biomed Engn, Tehran 15914, Iran
关键词
Bidirectional recurrent neural; networks; Intermolecular interactions; Modular networks; Reciprocal recurrent neural network; Secondary structure correlation; ALGORITHMS;
D O I
10.1016/j.cmpb.2010.04.005
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The supervised learning of recurrent neural networks well-suited for prediction of protein secondary structures from the underlying amino acids sequence is studied. Modular reciprocal recurrent neural networks (MRR-NN) are proposed to model the strong correlations between adjacent secondary structure elements. Besides, a multilayer bidirectional recurrent neural network (MBR-NN) is introduced to capture the long-range intramolecular interactions between amino acids in formation of the secondary structure. The final modular prediction system is devised based on the interactive integration of the MRR-NN and the MBR-NN structures to arbitrarily engage the neighboring effects of the secondary structure types concurrent with memorizing the sequential dependencies of amino acids along the protein chain. The advanced combined network augments the percentage accuracy (Q(3)) to 79.36% and boosts the segment overlap (SOV) up to 70.09% when tested on the PSIPRED dataset in three-fold cross-validation. (c) 2010 Elsevier Ireland Ltd. All rights reserved.
引用
收藏
页码:237 / 247
页数:11
相关论文
共 34 条
[1]  
AHMED A, 2007, P 7 IEEE C BIOINF, P1355
[2]  
ANSARY L, 2004, P 8 INT C SPOK LANG, P1657
[3]   Bayesian protein secondary structure prediction with near-optimal segmentations [J].
Aydin, Zafer ;
Altunbasak, Yucel ;
Erdogan, Hakan .
IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2007, 55 (07) :3512-3525
[4]   A signal processing application in genomic research: Protein secondary structure prediction [J].
Aydin, Zafer ;
Altunbasak, Yucel .
IEEE SIGNAL PROCESSING MAGAZINE, 2006, 23 (04) :128-131
[5]  
BABAEI S, 2008, P 8 IEEE C BIOINF BI, P1
[6]   Exploiting the past and the future in protein secondary structure prediction [J].
Baldi, P ;
Brunak, S ;
Frasconi, P ;
Soda, G ;
Pollastri, G .
BIOINFORMATICS, 1999, 15 (11) :937-946
[7]  
BALDI P, 2001, BIOINFORMATICS MACHI, pCH1
[8]   Learning protein secondary structure from sequential and relational data [J].
Ceroni, A ;
Frasconi, P ;
Pollastri, G .
NEURAL NETWORKS, 2005, 18 (08) :1029-1039
[9]   Cascaded bidirectional recurrent neural networks for protein secondary structure prediction [J].
Chen, Jinmiao ;
Chaudhari, Narendra S. .
IEEE-ACM TRANSACTIONS ON COMPUTATIONAL BIOLOGY AND BIOINFORMATICS, 2007, 4 (04) :572-582
[10]   Three-stage prediction of protein β-sheets by neural networks, alignments and graph algorithms [J].
Cheng, JL ;
Baldi, P .
BIOINFORMATICS, 2005, 21 :I75-I84