1.南京航空航天大學 計算機科學與技術學院，江蘇省 南京市，210016；
2.南昌陸軍學院 戰斗實驗室，江西省 南昌市，330103)
摘要：蛋白質二級結構是研究蛋白質結構和功能的基礎和重要組成部分。為了提高蛋白質二級結構的預測精度，本文利用Profile編碼對蛋白質一級結構序列進行編碼，并利用BP神經網絡作為預測算法來預測蛋白質二級結構；實驗結果表明對于窗口大小13和隱含層神經元數量為30時，Profile編碼預測結果達到最優。
關鍵詞：蛋白質；二級結構；預測；BP；Profile編碼
中圖分類號：TP03 文獻標識碼：A 文章編號：
Predicting Protein Secondary Structure Based on Profile and BP Neutral Networks
XIE Feng-sen1, ZHANG Yong1, LI Jian2
(1.Dept of Computer science and technology, Nanjing University of Aeronautics and Astronautics, Nanjing Jiangsu, 210016, China; 2.Nanchang Army College, Battle Laboratory, Nanchang, 330103, China.)
Abstract：Protein secondary structure prediction is a fundamental and important component in the study of protein structure and functions. For improving the accuracy of the protein secondary structure prediction, this paper uses profile encoding to represent the primary sequence of protein and adopts BP neutral networks as the predicting
algorithm to predict protein secondary structure. The experiment results suggested that, the prediction accuracy based on profile encoding get the optimal result when the size of window is 13 and the cell number of hide layout is 30.
Keywords：Protein; Secondary Structure; Prediction; BP; Profile Encoding
參考文獻
[1]Sitanshu Sekhar Sahu, Ganapati Panda. A novel feature representation method based on Chou’s pseudo amino acid composition for protein structural class prediction [J]. Computational Biology and Chemistry, 2010, 34:320-327.
[2]Chou.K.C. Prediction of protein cellular attributes using pseudo amino acid composition [J]. Proteins Structure Function and Genetics, 2001, 43:246-255.
[3]Chou.K.C. Progress in Protein Structural Class Prediction and its Impact to Bioinformatics and Proteomics[J]. Current Protein and Peptide Science, 2005, 6: 423-436.
[4]孫海軍, 阮曉鋼．氨基酸序列編碼對蛋白質二級結構預測的影響[A]．第二十二屆控制會議論文集—神經網絡[C].武漢市: 武漢理工大學出版社,2003，522-525．
SUN Hai-jun, Ruan Xiao-gang. Encoding of Amino Acids Influences Protein Secondary Structure Predication[A]. Proceeding of the 22nd Chinese Control Conference-Neutral Network[C]. Wuhan: Wuhan University of Technology Press, 2003, 522-525.
[5]修春波．人工智能原理[M]．北京：機械工業出版社，2011．
XIU Chun-bo. Artificial Intelligence Principle[M]. Beijing: China Machine Press, 2011.
[6]景楠，周春光，夏斌．基于徑向基函數蛋白質二級結構預測方法[J]．計算機工程與應用，2005，29(04)：4-7．
JING Nan, ZHOU Chun-guang, XIA Bin. A Study of Protein Secondary Structure Prediction Methods Based on Radial Basis Function[J]. Computer Engineering and Applications, 2005, 29(04):4-7.
[7]飛思科技產品研發中心．神經網絡理論與MATLAB實現[M]．北京：電子工業出版社，2005．
Feisi Technology Product R&D Center. Theory of Neutral Network and the implementation of MATLAB[M]. Beijing: Publishing House of Electronics Industry, 2005.
作者簡介：
謝峰森，男，1986年生，安徽省銅陵市人,碩士研究生，研究方向：生物信息學和人工智能。
