DocumentCode :
620013
Title :
Predicting protein structural classes with autoencoder neural networks
Author :
Liu Jian-wei ; Chi Guang-hui ; Liu Ze-yu ; Liu Yuan ; Li Hai-en ; Luo Xiong-lin
Author_Institution :
Res. Inst. of Autom., China Univ. of Pet., Beijing, China
fYear :
2013
fDate :
25-27 May 2013
Firstpage :
1894
Lastpage :
1899
Abstract :
Autoencoder neural networks was firstly introduced by G.E.Hinton to reduce the dimensionality of data.In this paper, we propose a new way to classify protein structural classes using autoencoder neural networks. The optimum configurations with respect to the size of hidden layers are identified. The problem of training a deep autoencoder for classifying protein structural classes is addressed. Stacked autoencoder is used for reducing the convergence time of training. We design a series of experiments to testify the effectiveness of using autoencoder networks to tackle the problem of predicting protein structure. The experimental results show that our proposed method is competitive with state-of-the-art SVM methods in predicting protein structure class.
Keywords :
biology computing; molecular biophysics; neural nets; pattern classification; proteins; autoencoder neural networks; convergence time reduction; data dimensionality reduction; deep autoencoder training problem; hidden layer size; optimum configuration identification; protein structural class classification; protein structural class prediction; stacked autoencoder; Amino acids; Error analysis; Mathematical model; Neural networks; Proteins; Support vector machines; Vectors; autoencoders network; protein structural class; pseudo amino acid model;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control and Decision Conference (CCDC), 2013 25th Chinese
Conference_Location :
Guiyang
Print_ISBN :
978-1-4673-5533-9
Type :
conf
DOI :
10.1109/CCDC.2013.6561242
Filename :
6561242
Link To Document :
بازگشت