【摘要】：在癌癥研究和醫(yī)學(xué)領(lǐng)域,生物標(biāo)志物能夠在早期對(duì)癌癥病人的病情進(jìn)行診斷,及時(shí)提供治療方法,并且還可以對(duì)癌癥的病情進(jìn)行預(yù)測(cè),對(duì)于癌癥的治療具有極高的指導(dǎo)價(jià)值。許多研究已經(jīng)報(bào)道基因可作為候選的生物標(biāo)志物,被應(yīng)用于疾病或者癌癥的診斷、預(yù)后和療效等方面。隨著高通測(cè)序技術(shù)的發(fā)展,癌癥生物標(biāo)志物的研究也開始從單一組學(xué)數(shù)據(jù)到多組學(xué)數(shù)據(jù)發(fā)展,但是多組學(xué)數(shù)據(jù)的整合還停留在簡(jiǎn)單整合階段,不能發(fā)現(xiàn)多組學(xué)數(shù)據(jù)的內(nèi)在聯(lián)系。我們整合基因表達(dá)數(shù)據(jù)和DNA甲基化數(shù)據(jù)進(jìn)行癌癥生物標(biāo)志物的研究與分析。本論文的研究?jī)?nèi)容如下:1、傳統(tǒng)的特征選擇方法在高維小樣本數(shù)據(jù)中往往考慮特征選擇結(jié)果的高分類性能,而忽略了特征選擇結(jié)果的穩(wěn)定性。對(duì)此,本文提出在對(duì)基因表達(dá)數(shù)據(jù)進(jìn)行特征選擇的時(shí)候,保留研究者公認(rèn)的與癌癥相關(guān)的重要基因,得到一個(gè)穩(wěn)定性高的基因特征組合的方法。2、由于450K甲基化芯片僅覆蓋全部甲基化位點(diǎn)的2%,采用簡(jiǎn)單融合的方式可能導(dǎo)致結(jié)果有偏。本文首次提出使用擴(kuò)展后的450K甲基化芯片數(shù)據(jù)與基因表達(dá)數(shù)據(jù)進(jìn)行融合的方法,從多個(gè)層面分析癌癥生物標(biāo)志物,并且盡可能的利用現(xiàn)有的DNA甲基化數(shù)據(jù),融合多組學(xué)數(shù)據(jù)的時(shí)候保留更多的信息,得到穩(wěn)定可靠的具有推廣價(jià)值的潛在癌癥生物標(biāo)志物。本文的方法比傳統(tǒng)的方法分類精確度和可靠性更高。本文分析了多種癌癥特定的潛在癌癥生物標(biāo)志物和多種癌癥共有的潛在癌癥生物標(biāo)志物,為醫(yī)學(xué)研究和臨床治療提供指導(dǎo)和幫助。3、構(gòu)建基于模糊規(guī)則的分類器模型來驗(yàn)證本文選擇的潛在癌癥生物標(biāo)志物對(duì)于正常和癌癥樣本的分類效果,通過交叉驗(yàn)證對(duì)比本文的方法和傳統(tǒng)的基因表達(dá)數(shù)據(jù)和DNA甲基化數(shù)據(jù)的簡(jiǎn)單的融合方法,發(fā)現(xiàn)本文的方法要優(yōu)于傳統(tǒng)方法,并且本文的方法對(duì)獨(dú)立樣本的預(yù)測(cè)結(jié)果也優(yōu)于傳統(tǒng)的方法,最后基于找到的潛在癌癥生物標(biāo)志物得到了魯棒性更高、易于理解的分類規(guī)則。
[Abstract]:In the field of cancer research and medicine, biomarkers can diagnose the condition of cancer patients in the early stage, provide timely treatment methods, and can also predict the condition of cancer, which has a very high guiding value for the treatment of cancer. Many studies have reported that genes can be used as candidate biomarkers for the diagnosis, prognosis and efficacy of diseases or cancer. With the development of high-pass sequencing technology, the research of cancer biomarkers has also begun to develop from single group data to multi-group data, but the integration of multi-group data is still in the stage of simple integration, and the internal relationship of multi-group data can not be found. We integrate gene expression data and DNA methylation data to study and analyze cancer biomarkers. The research contents of this paper are as follows: 1. The traditional feature selection methods often consider the high classification performance of feature selection results in high-dimensional small sample data, but ignore the stability of feature selection results. In order to select the characteristics of gene expression data, this paper proposes to preserve the important genes related to cancer recognized by researchers, and to obtain a stable method of gene feature combination. 2, because 450K methylated chip covers only 2% of all methylated sites, simple fusion may lead to biased results. In this paper, a method of fusion between extended 450K methylated chip data and gene expression data is proposed for the first time, and cancer biomarkers are analyzed from many levels, and as much as possible, more information is retained when fusion of multigroup data, and stable and reliable potential cancer biomarkers with popularizing value are obtained. The classification accuracy and reliability of this method are higher than those of the traditional method. In this paper, a variety of cancer specific potential cancer biomarkers and potential cancer biomarkers common to a variety of cancers are analyzed to provide guidance and help for medical research and clinical treatment. 3. A classification model based on fuzzy rules is constructed to verify the classification effect of the potential cancer biomarkers selected in this paper for normal and cancer samples. By cross-verifying and comparing the traditional method of gene expression and the simple fusion method of DNA methylation data, it is found that the method in this paper is superior to the traditional method, and the prediction results of independent samples are also better than the traditional method. Finally, based on the potential cancer biomarkers found, a classification rule with higher robustness and easy to understand is obtained.
【學(xué)位授予單位】：電子科技大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2017
【分類號(hào)】：R730.4

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 方福德;生物標(biāo)志物(biological marker)[J];中華預(yù)防醫(yī)學(xué)雜志;2001年01期

2 王三虎,高星;鉛的生物標(biāo)志物研究[J];中國(guó)職業(yè)醫(yī)學(xué);2002年01期

3 鄭玉新,莊志雄;基因組時(shí)代生物標(biāo)志物研究的機(jī)遇與挑戰(zhàn)[J];中華預(yù)防醫(yī)學(xué)雜志;2005年03期

4 黃忠;;生物標(biāo)志物的蛋白組學(xué)研究-高通量質(zhì)譜分析[J];瀘州醫(yī)學(xué)院學(xué)報(bào);2011年05期

5 葉細(xì)標(biāo),倪為民,傅華;分子生物標(biāo)志物及其應(yīng)用[J];中國(guó)工業(yè)醫(yī)學(xué)雜志;2002年01期

6 邵華;生物標(biāo)志物的研究進(jìn)展[J];職業(yè)與健康;2002年09期

7 胡訓(xùn)軍;肖萍;王文靜;陳良;盧偉;;三氯乙烯生物標(biāo)志物的研究進(jìn)展[J];環(huán)境與職業(yè)醫(yī)學(xué);2006年01期

8 肖忠海;王林;;癌癥生物標(biāo)志物[J];國(guó)外醫(yī)學(xué).藥學(xué)分冊(cè);2006年06期

9 賈光;沈惠麒;;以生物標(biāo)志物研究為切入點(diǎn)推動(dòng)生物監(jiān)測(cè)的發(fā)展[J];中華預(yù)防醫(yī)學(xué)雜志;2006年06期

10 ;《生物監(jiān)測(cè)與生物標(biāo)志物理論基礎(chǔ)及應(yīng)用》新書預(yù)告[J];中華勞動(dòng)衛(wèi)生職業(yè)病雜志;2006年12期

相關(guān)會(huì)議論文 前10條

1 陳建平;鄧春萍;宋孚慶;張大江;;應(yīng)用生物標(biāo)志物定量計(jì)算混合原油油源的數(shù)學(xué)模型[A];第十屆全國(guó)有機(jī)地球化學(xué)學(xué)術(shù)會(huì)議論文摘要匯編[C];2005年

2 王曉蓉;;分子生物標(biāo)志物在水環(huán)境有機(jī)污染的早期預(yù)警研究進(jìn)展[A];有機(jī)污染環(huán)境化學(xué)前沿與環(huán)境可持續(xù)發(fā)展戰(zhàn)略論文集[C];2006年

3 申秀萍;賈長(zhǎng)虹;;十二五“重大新藥創(chuàng)制”毒性生物標(biāo)志物與人源化動(dòng)物模型關(guān)鍵技術(shù)課題簡(jiǎn)介[A];2013年（第三屆）中國(guó)藥物毒理學(xué)年會(huì)暨藥物非臨床安全性評(píng)價(jià)研究論壇論文摘要[C];2013年

4 申秀萍;賈長(zhǎng)虹;;十二五“重大新藥創(chuàng)制”毒性生物標(biāo)志物與人源化動(dòng)物模型關(guān)鍵技術(shù)課題簡(jiǎn)介[A];中國(guó)藥理學(xué)與毒理學(xué)雜志(2013年6月第27卷第3期)[C];2013年

5 謝鑫友;;新技術(shù)在生物標(biāo)志物篩選中的應(yīng)用(英文)[A];2007年浙江省醫(yī)學(xué)檢驗(yàn)學(xué)學(xué)術(shù)年會(huì)論文匯編[C];2007年

6 馬t，

本文編號(hào)：2502961