人類基因體中CpG位置之甲基化狀態預測

以作者查詢圖書館館藏

、以作者查詢臺灣博碩士

、以作者查詢全國書目

、勘誤回報

、線上人數：15

、訪客IP：18.118.32.116

姓名

廖偉吏(Wei-li Liao) 查詢紙本館藏

畢業系所

資訊工程學系

論文名稱

人類基因體中CpG位置之甲基化狀態預測
(Prediction of CpG Sites Methylation Status in Human Genome)

相關論文

★ 應用嵌入式系統於呼吸肌肉群訓練儀之系統開發	★ 勃起障礙與缺血性心臟病的雙向研究: 以台灣全人口基礎的世代研究
★ 基質輔助雷射脫附飛行時間式串聯質譜儀微生物抗藥性資料視覺化工具	★ 使用穿戴式裝置分析心律變異及偵測心律不整之應用程式
★ 建立一個自動化分析系統用來分析任何兩種疾病之間的關聯性透過世代研究設計以及使用承保抽樣歸人檔	★ 青光眼病患併發糖尿病,使用Metformin及Sulfonylurea治療得到中風之風險:以台灣人口為基礎的觀察性研究
★ 利用組成識別和序列及空間特性構成之預測系統來針對蛋白質交互作用上的特殊區段點位進行分析及預測辨識	★ 新聞語意特徵擷取流程設計與股價變化關聯性分析
★ 藥物與疾病關聯性自動化分析平台設計與實作	★ 建立財務報告自動分析系統進行股價預測
★ 建立一個分析疾病與癌症關聯性的自動化系統	★ 基於慣性感測器虛擬鍵盤之設計與實作
★ 一個醫療照護監測系統之實作	★ 應用手機開發手握球握力及相關資料之量測
★ 利用關聯分析全面性的搜索癌症關聯疾病	★ 全面性尋找類風濕性關節炎之關聯疾病

檔案

[Endnote RIS 格式]

[Bibtex 格式]

[相關文章]

[文章引用]

[完整記錄]

[館藏目錄]

[檢視]

[下載]

本電子論文使用權限為同意立即開放。
已達開放權限電子全文僅授權使用者為學術研究之目的，進行個人非營利性質之檢索、閱讀、列印。
請遵守中華民國著作權法之相關規定，切勿任意重製、散佈、改作、轉貼、播送，以免觸法。

摘要(中)

於後基因體時代，表觀基因體學對於生物學家而言是一項重要的研究領域。 DNA甲基化是一種附加到DNA上的化學修飾，研究指出發生於CpG位置上的甲基化狀態與DNA表現以及一些疾病相關，例如癌症。如果不正常的甲基化發生於轉錄因子結合位點時，可能會影響轉錄因子的結合而進一步影響DNA的表現，因此找出不正常甲基化的位置是非常重要的。我們使用轉錄因子結合位點以及DNA的特殊序列出現次數做為建立預測模型的特徵，並且為了去了解不同組織以及不同DNA區域間甲基化差異，我們建立的不同的預測模型來分析這些預測模型所使用的特徵差異。於結果中，我們的預測模型有良好的預測結果，我們使用10折交叉驗證特異性80.54%、敏感性為80.54%以及準確度為86.01%。針對不同組織細胞以及不同區域所建立預測模型的準確度也都高於80%，並且比較不同區域間前七十名的特徵發現，共同的特徵約佔50%，由此結果可推測不同區域間的特徵與甲基化狀態存在著差異。

摘要(英)

DNA methylation is a biochemical modification in epigenetics. The 80% cytosines at CpG dinucleotide are found methylation. The DNA methylation is important for gene expression and cancer. The transcription factor binding will be affected if aberrant DNA methylation occurred in TFBSs. To figure out where be methylated is an important research. To reveal the effective features for different tissues and regions, we develop models to compare differences between 4-regions and 12-tissues. The TFBS and DNA properties and distribution are features for classification. From our results, we found some TFBS (e.g. SP1, ZF5 and etc.) that would discriminate methylated or not. The sensitivity and specificity and accuracy by using 10-fold cross validation are about 90.8%, 80.54%, and 86.07%, respectively. According to four-regions and twelve-tissues, the performances (ACC) are all 80% highly. We conjecture that the differential features or methylation are between different regions because the common features of each region are only 50% in the top 70 feature.

關鍵字(中)

★ 甲基化
★ 調控
★ 轉錄結合位點
★ 去氧核醣核酸

關鍵字(英)

★ DNA methylation
★ CpG
★ TFBS
★ expression

論文目次

Chapter 1 Introduction ...................................................................................... 1
1.1 Background .................................................................................................... 1
1.2 Motivation ...................................................................................................... 3
1.3 Goal ................................................................................................................ 4
Chapter 2 Related Works .................................................................................. 5
2.1 Human Epigenome Project (HEP) ................................................................. 5
2.2 DNA Methylation Databases (MethDB) ........................................................ 5
2.3 Methylator ...................................................................................................... 6
2.4 HDMFinder .................................................................................................... 6
2.5 TRANSFAC and MATCH ............................................................................. 7
Chapter 3 Materials and Method ..................................................................... 8
3.1 Data Source .................................................................................................... 8
3.2 Windows Size and Threshold....................................................................... 10
3.3 System Flow................................................................................................. 11
3.4 Classification Tool ....................................................................................... 13
3.4.1 LIBLINEAR ........................................................................................ 13
3.5 Performance Evaluation ............................................................................... 13
3.6 Features ........................................................................................................ 14
3.6.1 Transcription Factor Binding Sites (TFBSs) ....................................... 14
3.6.2 CpG Island, DNA Sequence Properties and Patterns........................... 15
3.7 Feature Selection .......................................................................................... 15
Chapter 4 Results ............................................................................................. 17
4.1 Prediction Performance ................................................................................ 17
4.2 Comparison with Other Prediction Tools ..................................................... 27
4.3 Independent Test that Using 132 CpG Islands of 21q ................................. 32
4.4 Discriminative Transcription Factor Binding Sites...................................... 34
Chapter 5 Discussion........................................................................................ 36
References ................................................................................................................... 40
APPENDIX A ............................................................................................................. 43
APPENDIX B ............................................................................................................. 45
APPENDIX C ............................................................................................................. 46
APPENDIX D ............................................................................................................. 48
APPENDIX E ............................................................................................................. 49
APPENDIX F ............................................................................................................. 49
APPENDIX G ............................................................................................................. 50

參考文獻

1. Bird, A., DNA methylation patterns and epigenetic memory. Genes Dev, 2002. 16(1): p. 6-21.
2. Bird, A.P., CpG-rich islands and the function of DNA methylation. Nature, 1986. 321(6067): p. 209-13.
3. Ballestar, E. and M. Esteller, The impact of chromatin in human cancer: linking DNA methylation to gene silencing. Carcinogenesis, 2002. 23(7): p. 1103-9.
4. Karymov, M.A., et al., DNA methylation-dependent chromatin fiber compaction in vivo and in vitro: requirement for linker histone. FASEB J, 2001. 15(14): p. 2631-41.
5. Singal, R. and G.D. Ginder, DNA methylation. Blood, 1999. 93(12): p. 4059-70.
6. Gardiner-Garden, M. and M. Frommer, CpG islands in vertebrate genomes. J Mol Biol, 1987. 196(2): p. 261-82.
7. Takai, D. and P.A. Jones, Comprehensive analysis of CpG islands in human chromosomes 21 and 22. Proc Natl Acad Sci U S A, 2002. 99(6): p. 3740-5.
8. Matsuo, K., et al., Evidence for erosion of mouse CpG islands during mammalian evolution. Somat Cell Mol Genet, 1993. 19(6): p. 543-55.
9. Eckhardt, F., et al., DNA methylation profiling of human chromosomes 6, 20 and 22. Nat Genet, 2006. 38(12): p. 1378-85.
10. Bhasin, M., et al., Prediction of methylated CpGs in DNA sequences using a support vector machine. FEBS Lett, 2005. 579(20): p. 4302-8.
11. Das, R., et al., Computational prediction of methylation status in human genomic sequences. Proc Natl Acad Sci U S A, 2006. 103(28): p. 10713-6.
12. Illingworth, R., et al., A novel CpG island set identifies tissue-specific methylation at developmental gene loci. PLoS Biol, 2008. 6(1): p. e22.
13. Grunau, C., et al., MethDB--a public database for DNA methylation data. Nucl. Acids Res., 2001. 29(1): p. 270-274.
14. Amoreira, C., W. Hindermann, and C. Grunau, An improved version of the DNA Methylation database (MethDB). Nucleic Acids Res, 2003. 31(1): p. 75-7.
15. Rollins, R.A., et al., Large-scale structure of genomic methylation patterns. Genome Res, 2006. 16(2): p. 157-63.
16. Wingender, E., et al., TRANSFAC: an integrated system for gene expression regulation. Nucleic Acids Res, 2000. 28(1): p. 316-9.
17. Matys, V., et al., TRANSFAC and its module TRANSCompel: transcriptional gene regulation in eukaryotes. Nucleic Acids Res, 2006. 34(Database issue): p. D108-10.
18. Kel, A.E., et al., MATCH: A tool for searching transcription factor binding sites in DNA sequences. Nucleic Acids Res, 2003. 31(13): p. 3576-9.
19. Grunau, C., S.J. Clark, and A. Rosenthal, Bisulfite genomic sequencing: systematic investigation of critical experimental parameters. Nucleic Acids Res, 2001. 29(13): p. E65-5.
20. Lewin, J., et al., Quantitative DNA methylation analysis based on four-dye trace data from direct sequencing of PCR amplificates. Bioinformatics, 2004. 20(17): p. 3005-12.
21. Curwen, V., et al., The Ensembl automatic gene annotation system. Genome Res, 2004. 14(5): p. 942-50.
22. Chih-Jen, L., C.W. Ruby, and S.S. Keerthi, Trust region Newton methods for large-scale logistic regression, in Proceedings of the 24th international conference on Machine learning. 2007, ACM: Corvalis, Oregon.
23. Cristianini, N. and J. Shawe-Taylor, An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. 2000: {Cambridge University Press}.
24. Jiawei Han, M.K., Data mining : concepts and techniques. 2 edition ed. 2006: Morgan Kaufmann.
25. Fang, F., et al., Predicting methylation status of CpG islands in the human brain. Bioinformatics, 2006. 22(18): p. 2204-9.
26. Bock, C., et al., CpG island methylation in human lymphocytes is highly correlated with DNA sequence, repeats, and predicted DNA structure. PLoS Genet, 2006. 2(3): p. e26.
27. Frank, I.H.W.a.E., Data Mining: Practical machine learning tools and

指導教授

洪炯宗(Jorng-tzong Horng)

審核日期

2008-7-19

推文