Cancer classification algorithm with improved emerging pattern

doi:10.3778/j.issn.1002-8331.2010.26.071

Computer Engineering and Applications ›› 2010, Vol. 46 ›› Issue (26): 233-237.DOI: 10.3778/j.issn.1002-8331.2010.26.071

• 工程与应用 • Previous Articles Next Articles

Cancer classification algorithm with improved emerging pattern

LU Xin-guo¹，LI Dan¹，WANG Hai-jun²

1.School of Computer and Communication，Hunan University，Changsha 410082，China
2.School of Science，Henan University of Science and Technology，Luoyang，Henan 471003，China

Received:2009-02-24 Revised:2009-04-17 Online:2010-09-11 Published:2010-09-11
Contact: LU Xin-guo

一种增强显现模式的癌症分类算法

卢新国¹，李丹¹，王海军²

1.湖南大学计算机与通信学院，长沙 410082
2.河南科技大学理学院，河南洛阳 471003

通讯作者: 卢新国

Abstract

Abstract: Cancer detection with gene expression profiles is important for cancer treatment.Emerging Patterns（EPs） can discover the hidden gene expression patterns related to the cancer.And EPs based cancer classification algorithm can identify the cancer for the sample.For shortcoming in the estimation of probability with frequency when the size of samples is small in the EPs mining，Bayes estimation is introduced into the mining for increasing the reliability of entropy，then the Improved Emerging Patterns（EPIs） is extracted in cancer expressing，and a cancer classification algorithm with Improved Emerging Patterns（CCEPI） is proposed.The experiment is taken on the Leukemia dataset and the results show CCEPI can improve the correction in cancer detection.

Key words: emerging patterns, cancer classification, gene expression profiles

摘要： 基于基因表达谱的癌症检测对癌症的治疗具有十分重要的意义。显现模式（Emerging Patterns，EPs）能够挖掘隐含的具有生物意义的基因表达模式，基于显现模式的癌症分类方法可以检测出癌症样本。针对提取显现模式时在小样本情况下将频率近似于概率的缺陷，引入贝叶斯估计以提高熵的可靠度，提取癌症表达中的增强显现模式（Improved Emerging Patterns，EPIs），并提出一种基于增强显现模式的基因分类算法（A Cancer Classification Algorithm with Improved Emerging Patterns CCEPI）。最后在急性白血病数据集上进行实验，实验结果表明算法提高了癌症检测的正确率。

关键词: 显现模式, 癌症分类, 基因表达谱

CLC Number:

LU Xin-guo¹，LI Dan¹，WANG Hai-jun². Cancer classification algorithm with improved emerging pattern[J]. Computer Engineering and Applications, 2010, 46(26): 233-237.

卢新国¹，李丹¹，王海军². 一种增强显现模式的癌症分类算法[J]. 计算机工程与应用, 2010, 46(26): 233-237.

[1]	TANG Xiwei, LI Yongfan, HU Qiuling. Predicting protein complex via integration of multiply data sources [J]. Computer Engineering and Applications, 2012, 48(27): 105-108.
[2]	YI Bo, WEN Tianzhu, ZHANG Yuan. Study of disposal of noises in gene expression profiles of colon tumor [J]. Computer Engineering and Applications, 2012, 48(10): 146-149.
[3]	ZHANG Yuchun1，HAO Pingbo2，WANG Mingyu1，GUO Chunhong1. Research on classification and detection of colon cancer’s gene expression profiles [J]. Computer Engineering and Applications, 2011, 47(17): 244-248.
[4]	YANG Shao-lin,WANG Shu-lin. Multi-class tumor subtype recognition based on neural networks [J]. Computer Engineering and Applications, 2008, 44(11): 237-240.
[5]	. An Approach to Subtype Recognition and Selection of Informative Genes for SRBCT [J]. Computer Engineering and Applications, 2007, 43(3期): 223-223.
[6]	MENG Fan-jing¹,LIU Yi-hui¹,WANG Hong-guo²,CHENG Jin-yong¹. Cancer classification for microarray gene data based on SVM [J]. Computer Engineering and Applications, 2007, 43(34): 246-248.
[7]	WANG Hai-jun^1,3,LIN Ya-ping^2,1,LU Xin-guo¹,NIE Ya-lin¹. Gene classification algorithm based on emerging patterns [J]. Computer Engineering and Applications, 2007, 43(32): 180-184.
[8]	HE Ai-xiang. Gene selection and classification for microarray data of colon and normal tissues using genetic algorithms [J]. Computer Engineering and Applications, 2007, 43(18): 242-245.

Cancer classification algorithm with improved emerging pattern

一种增强显现模式的癌症分类算法

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 8

Recommended Articles

Metrics