請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/45270
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 陳中明(Chung-Ming Chen) | |
dc.contributor.author | Cheng-Long Chuang | en |
dc.contributor.author | 莊欽龍 | zh_TW |
dc.date.accessioned | 2021-06-15T04:11:42Z | - |
dc.date.available | 2010-02-04 | |
dc.date.copyright | 2010-02-04 | |
dc.date.issued | 2010 | |
dc.date.submitted | 2010-01-27 | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/45270 | - |
dc.description.abstract | 在後基因組世代,如何針對高通量技術所產生之大量資料進行分析,已成為各生資領域受矚目的議題之一。許多計算方法已被提出,利用近代電腦之高速運算能力,進行基因調控網路或轉錄調控網路之預測。而學者們希望透過調控網路的預測,用於開發藥物與新式的疾病療法。因此,近年來已有許多針對調控網路的計算分析方法被發表與廣泛應用。本論文依循過去學者的研究經驗與成果,提出三種不同的計算方法,分別可用於預測基因調控網路或轉錄調控網路,並使這些結果具有高準確率與生醫應用上的意義。
首先,本論文提出之第一個計算方法(PARE)利用基因微陣列資料,以模式識別方法為基礎,預測基因間具時間差之調控關係。PARE包含非線性的指標分數,可用於萃取基因微陣列資料中,每對基因表現模式間的三項特徵,分別是一階關係、二階關係與封閉面積。經由訓練的方法,PARE可學習成對且已知調控關係之基因表現模式,並利用學習的結果來預測其它基因對間未知之調控關係。本論文提出之第二個演算法,是一個非線性曲線擬合方法。此方法具有兩個主要元件,分別是強健相關係數預測法,以及非線性迴歸模型。此方法透過非線性曲線擬合方法,已非監督式方式來模擬並探掘基因網路調控關係。本論文分別利用酵母菌基因表現量資料,驗證了此方法在預測一般調控網路之有效性。另外,本論文亦使用人類基因表現量資料,進行疾病調控路徑之預測,並且找出一些可深入探討的疾病調控關係。第三個方法(AdaFuzzy)則是一個整合基因序列資料、基因微陣列資料,以及染色質免疫沉澱法資料,進行轉錄調控網路之預測。其中,AdaFuzzy提出了一個強健位置加權矩陣,可用於找尋各轉錄因子之結合序列中具有保守共通特徵之片段。AdaFuzzy亦可將預測所得之啟動子片段分類至四個啟動子結構。本論文利用酵母菌之資料,驗證了AdaFuzzy在調控網路預測上的可用性。 | zh_TW |
dc.description.abstract | In the post-genome era, the analysis of high-throughput data has become a critical requirement in many laboratories. Many computational approaches have been developed to identify genetic or transcriptional interactions that may be used to prevent or disable unwanted state, such as those associated with oncogenesis or a disease. Therefore, inferring genetic interactions and transcriptional interactions through inspection of high-throughput data are essential issues in post-genomic research. In this study, we developed three computational models to extract the nonlinear relationship between genes, and also construct transcription regulatory networks and genetic regulatory networks with higher accuracy and larger biological significance.
The first method is a pattern recognition (called PARE) approach that infers time-lagged genetic interactions from time-course microarray data. A non-linear score extracts some characteristics, the first and second derivatives and the enclosed area, of paired gene-expression curves to approximate the non-linear association and dynamics between the curves. Such non-linear score is then used to identify subclasses of gene pairs with different time lags. Finally, PARE integrates both MGED and existing knowledge via machine learning, and subsequently predicts the other genetic interactions in the subclass. The second method consists of two components, a robust correlation estimator and a nonlinear recurrent model. The method was used to simulate the underlying nonlinear regulatory mechanisms in biological organisms without any prior knowledge. The proposed algorithm was applied to infer the regulatory mechanisms of the general network in Saccharomyces cerevisiae and the pulmonary disease pathways in Homo sapiens with interesting outcomes. The third method is a fuzzy-logic approach, called AdaFuzzy, which integrates DNA sequence, microarray and ChIP-chip data to infer TIs. A robust position weight matrix and a feature vector are proposed in AdaFuzzy to search for consensus sequence motifs. AdaFuzzy was also able to classify all predicted TIs into one or more of the four promoter architectures. The validated success in the prediction results implies that AdaFuzzy can be applied to uncover TIs in yeast. | en |
dc.description.provenance | Made available in DSpace on 2021-06-15T04:11:42Z (GMT). No. of bitstreams: 1 ntu-99-D94548012-1.pdf: 2988402 bytes, checksum: 9bbd3ae7f0f5f6ea50a172352c6c6d49 (MD5) Previous issue date: 2010 | en |
dc.description.tableofcontents | 口試委員會審定書 ...i
Acknowledgements (Chinese) ...ii Abstract (Chinese) ...iii Abstract ...iv Table of Contents ...v List of Illustrations ...vii List of Tables ...ix Chapter 1. Introduction ...1 1.1 Overview ...1 1.2 Genomics ...2 1.3 Genetic Interactions ...4 1.4 Transcriptional Interactions ...7 1.5 Motivation ...10 Chapter 2. A pattern recognition approach to infer time-lagged genetic interactions ...12 Summary ...13 2.1 Introduction ...14 2.2 Systems and methods ...19 2.2.1 Applying mean filter to smooth microarray data ...19 2.2.2 Two paired gene-expression patterns uncovered ...19 2.2.3 The proposed pattern recognition approach ...21 2.2.3.1 The condition for applicability of PARE ...21 2.2.3.2 A score to capture non-linearity in paired gene-expression curves ...23 2.2.3.3 Identifying subclasses of gene pairs with different time lags ...25 2.2.3.4 Predicting gene interactions using known interactions ...26 2.2.3.5 Optimizing the weights of the decision score ...27 2.3 Experimental Results ...28 2.3.1 Microarray gene expression data ...28 2.3.2 Predicting TC and TD genetic interactions ...29 2.3.3 Predicting transcriptional regulatory interactions ...31 2.3.4 Several predicted TC/TD interactions coinciding with existing pathways ...32 2.4 Discussion ...33 Chapter 3. A robust correlation estimator and nonlinear recurrent model to infer genetic interactions in Saccharomyces cerevisiae and pathways of pulmonary disease in Homo sapiens ...35 Summary ...36 3.1 Introduction ...37 3.2 Methods ...39 3.2.1 Overview ...39 3.2.2 Robust correlation estimator ...40 3.2.3 Nonlinear recurrent model ...45 3.2.3.1 Gene activity extraction ...45 3.2.4 Recurrent network model ...48 3.2.4.1 Feedforward prediction process ...48 3.2.4.2 Tuning process ...52 3.2.4.3 Interpretation of the tuned parameters ...54 3.3 Results and discussion ...55 3.3.1 Simulated data ...55 3.3.2 Inferring genetic interactions in S. cerevisiae ...57 3.3.2.1 Data preparation ...57 3.3.2.2 Prediction of genetic interactions in yeast ...58 3.3.3 Predict pathways of pulmonary disease in H. sapiens ...66 3.3.3.1 Experiment conditions and data preparation ...66 3.3.3.2 Prediction of interactions in human disease pathways ...68 3.4 Conclusions ...75 Chapter 4. Uncovering transcriptional interactions via an adaptive fuzzy logic approach ...78 Summary ...79 4.1 Introduction ...81 4.2 Methods ...83 4.2.1 Identifying consensus sequence motif ...83 4.2.2 Uncovering TF binding sites ...86 4.2.3 Identifying TIs using ANFIS... 87 4.2.4 Classification of promoter architecture ...91 4.2.5 Classification of AT/RT interactions ...93 4.3 Experimental results ...94 4.3.1 Inferring TIs using cell cycle/stress condition data in yeast ...96 4.3.2 Classifying promoter architectures ...99 4.4 Conclusions ...103 Chapter 5. Future works for inferring genetic and transcriptional regulatory interactions ...106 References ...109 Appendix ...132 Appendix 1. Quantitative RT-polymerase chain reaction (qRT-PCR) experiments ...132 Appendix 2. Results of Chi-Square Test for 112 genetic interactions confirmed by qRT-PCR experiments ...134 Appendix 3. Particle swarm optimization (PSO) ...139 Appendix 4. Results of Chi-Square Test in ...132 Transcriptional Interactions (TIs) ...146 Appendix 5. 132 Transcriptional Interactions (TIs) and prediction results yielded by PARE ...152 Appendix 6. The frequency table of degenerate characters defined in IUPAC ...158 | |
dc.language.iso | en | |
dc.title | 以多種生物訊息與智慧型演算法進行基因網路預測 | zh_TW |
dc.title | Inferring genetic network based on various types of biological data using machine learning algorithms | en |
dc.type | Thesis | |
dc.date.schoolyear | 98-1 | |
dc.description.degree | 博士 | |
dc.contributor.coadvisor | 謝叔蓉(Grace S. Shieh) | |
dc.contributor.oralexamcommittee | 歐陽彥正(Yen-Jen Oyang),蔣榮先(John Chiang),王逢盛(Feng-Shen Wang),江明格(Ming-Ko Chiang) | |
dc.subject.keyword | 基因調控,轉錄調控,機器學習,疾病路徑,基因微陣列表現量,染色質免疫沉澱法,非線性擬合, | zh_TW |
dc.subject.keyword | Genetic interactions,Transcriptional interactions,Machine learning,Disease pathway,Microarray gene expression,ChIP,Nonlinear fitting, | en |
dc.relation.page | 159 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2010-01-27 | |
dc.contributor.author-college | 工學院 | zh_TW |
dc.contributor.author-dept | 醫學工程學研究所 | zh_TW |
顯示於系所單位: | 醫學工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-99-1.pdf 目前未授權公開取用 | 2.92 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。