人工智能-数据分析-基于连续小波变换分析的基因表达谱数据分析.pdf
版权申诉
9 浏览量
2022-07-08
17:51:56
上传
评论
收藏 1.22MB PDF 举报
摘 要
Abstract
High through-put biological technology allows biologists to simultaneously monitor
the expression for hundreds of thousands of genes in organisms, and the resulting
expression data have become one of bases supporting modern biological genetics and
modern medicine. Currently, genome-wise research of cancer using gene expression
profile data receives more and more concerns in bioinformatics community. Generally,
gene expression data are highly dimensional, highly noisy, highly redundant, highly
variable but with small sample, so that many traditional pattern recognition methods
and statistical methods are non-applicable or perform badly.
By viewing gene expression profile as a ”time-series” signal, this thesis proposes
to apply continuous wavelet transform methods to analyze gene expression data. Es-
pecially, we focus on gene expression pattern extraction and cancer classification. As
we all know, wavelet transform can efficiently decompose and reconstruct time-series
signal and has been applied to various areas. Generally, wavelet transform can be im-
plemented in two ways, i.e., discrete wavelet transform (DWT) and continuous wavelet
transform (CWT). Researchers have applied DWT to gene expression data analysis
and the results were good. In this thesis, in view of the better flexibility in extracting
information of CWT compared to DWT, we consider developing CWT-based methods
to analyze gene expression data. Because there are lots of useful information hidden
behind gene expression data, using CWT to extract local details of gene expression
profile is promising to perform better. In particular, we explore CWT-based methods
for analyzing gene expression data in the following aspects: (1) How different types
of wavelet base functions influence the performance of CWT in extracting expression
patterns; (2) How varying values of the scale and translation parameters influence the
performance of CWT in extracting expression patterns;(3) How to integrate the well-
known SNR gene selection method and CWT for better extracting gene expression
patterns; (4) How the order of genes input to CWT influences the performance of
CWT in extracting gene expression patterns.
Finally, on multiple publicly available cancer data sets, we tested the proposed
CWT-based methods and extensively compared with previous methods. Experimental
results show the better performance of CWT for gene expression data analysis com-
pared with the previous methods. In summary, this work in this thesis has important
reference value for feature recognition and classification of tumors.
Key words:continuous wavelet transform (CWT); cancer classification; discrete
wavelet transform (DWT); feature transformation; gene expression profile.
– II –
万方数据
剩余50页未读，继续阅读
资源评论
