跳到主要內容

臺灣博碩士論文加值系統

(3.236.84.188) 您好!臺灣時間:2021/08/05 01:11
字體大小: 字級放大   字級縮小   預設字形  
回查詢結果 :::

詳目顯示

: 
twitterline
研究生:王毓傑
研究生(外文):YU-JIE WANG
論文名稱:應用各種基因選取方法探討攝護腺癌的基因生物標誌
論文名稱(外文):The Exploration of Gene Selection Methods in Identifying Gene Biomarkers in Prostate Cancer
指導教授:陳信志陳信志引用關係
指導教授(外文):Austin H Chen
學位類別:碩士
校院名稱:慈濟大學
系所名稱:醫學資訊學系碩士班
學門:醫藥衛生學門
學類:醫學技術及檢驗學類
論文種類:學術論文
論文出版年:2012
畢業學年度:101
語文別:中文
論文頁數:67
中文關鍵詞:基因選取支持向量機攝護腺癌隨機森林基因演算法粒子族群最佳化參數最佳化
外文關鍵詞:prostate cancerparameter optimizeparticle swarm optimizationFeature Selection
相關次數:
  • 被引用被引用:0
  • 點閱點閱:284
  • 評分評分:
  • 下載下載:26
  • 收藏至我的研究室書目清單書目收藏:0
近十多年來攝護腺癌的發生率迅速竄升,在這方面的研究投入有所增多,隨著新的高通量分子篩查技術的發展,在這般繁多的原始資料,研究人員最需要的是找出符合生物醫學解釋的資訊。在資料量近乎天文數字下,粹取有用的資訊是項十分重要的工作。要提高早期攝護腺癌診斷率,需要從基因微陣列資料中,找到新的參與到攝護腺癌的發生發展過程中,能早期診斷、判斷預後的生物標誌。
本研究開發六種基因選取方法,包括三種生物統計的基因選取方法,以及三種機器學習的基因選取方法,從攝護腺癌微陣列基因表現資料中篩選出顯著的基因集合。此三種生物統計分析方法分別為: t-Test,Golub,及Minimum Distance to Modal Ranking;三種機器學習方法則分別為:Random Forests Gene Selection (RFGS), Genetic Algorithm Gene Selection (GAGS),及Genetic Algorithm –Particle Swarm Optimization (GAPSO)。在六種基因選取下選出來的基因,經過Novoseek disease relationships的相關性分數來尋找可能和攝護腺癌相關的基因,一共有50個不重複的基因。這50個內,經文獻查證已證實是攝護腺癌相關的基因有18個,其中有許多高相關性分數的基因已被用來做為攝護腺癌檢定、治療的應用上了。
本研究所開發的分類器,將支持向量機結合粒子群的最佳化演算法,每次分類都能自動地搜尋最佳參數。將六種基因選取選出來的基因用PSOSVM做分類的準確率做比較,相較於傳統SVM,PSOSVM的平均準確率在六種基因選取之下都有所提升,整體分類準確率平均提升3.5%的預測準確率,機器學習基因選取的分類準確率整體平均更達到93%以上。而平均敏感度與特異度部分在部分基因選取雖較傳統SVM有些微落差,但是依然有達到平均87%以上的敏感度與特異度,代表PSOSVM的預測結果可以提供診斷攝護腺癌重要的參考價值。
In this paper, we describe a framework for selecting informative genes.We combines six gene selection methods with Novoseek disease relationships to We combines six gene selection methods with Novoseek disease relationships to explored identifying gene biomarkers in prostate cancer.With this framework,we found 18 identifying gene biomarkers.
Aiming at the randomness of parameter selection, a PSO-SVM model is constructed by using particle swarm optimization (PSO) to achieve higher classification accuracy in support vector machine (SVM). The application results indicate that PSO-SVM model gets high classification accuracy of 93% . The parameters in SVM are optimized by PSO, so that randomness of parameter selection is avoided and the model shows strong robustness in classification problems.
第一章 緒論
1.1 研究背景
1.2 研究動機
1.3 研究目的
第二章 文獻探討
2.1 攝護腺癌
2.2 攝護腺癌基因的相關研究
2.3 基因選取
2.4 粒子族群最佳化
2.5 最佳化參數
第三章 研究方法
3.1 研究流程
3.2 生物統計基因選取方法
3.2.1 t-Test
3.2.2 Golub
3.2.3 MDMR (Minimum Distance to Modal Ranking)
3.3 機器學習基因選取方法
3.3.1 Random Forest Gene Selection
3.3.2 Genetic Algorithm Gene Selection
3.3.3 GA-PSO
3.4 分類方法
3.4.1 SVM
3.4.2 PSO-SVM
3.5 醫學驗證攝護腺癌的生物標誌
第四章 實驗架構
4.1資料來源
4.2實驗流程
4.2.1資料正規化
4.2.2基因選取
4.2.3分類器
4.2.4三摺交互驗證
第五章 結果與討論
5.1基因生物標誌
5.2分類準確度
第六章 結論與未來展望
6.1 結論
6.2 未來展望
參考文獻
Alba E. et al.(2007). "Gene Selection in Cancer Classification using PSO/SVM and A/SVM Hybrid A lgorithms."CECS,2007

Alicia, L.,et al.(2004). "Caveolin-1 and MAL are located on prostasomes secreted by the prostate cancer PC-3 cell line."Cell Science17, 5343-5351.

Anne-Laure B.,et al.(2004). "Microarray-based classification and clinical predictors value: on combined classifiers and additional predictive value."Bioinformatics (2008) 24 (15):1698-1706.

AVCI E. (2009) . " A new intelligent diagnosis system for the heart valve diseases by using Genetic – SVM Classifier." Expert Systems with Applications,2009, 10618–10626

Chen, A., et al. (2010). " Novel methods to identify biologically relevant genes for leukemia and prostate cancer from gene expression profiles. "BioMed Central.

Cheng, W. S., et al. (2004). "A novel TARP-promoter-based adenovirus against hormone-dependent and hormone-refractory prostate cancer." Mol Ther 10(2): 355-364.

Cimino, A., et al. (2010). "Epithelial cell adhesion molecule (EpCAM) is overexpressed in breast cancer metastases." Breast Cancer Res Treat 123(3): 701-708.

Georg S. et al.,(2005) . " Polymorphism in ARE-I region of prostate-specific antigen gene associated with low serum testosterone level and high-grade prostate cancer." The Journal of Urology 65 1141-1145

Glen K., et al. (2002)."ALCAM/CD166 is up-regulated in low-grade prostate cancer and progressively lost in high-grade lesions." The Prostate 54

Golub, T. R., (1999) ."Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring." science.286.5439.531

Huang,C.L., et al. (2006)."A GA-based feature selection and parameters optimization for support vector machines. " Expert Systems with Applications,2006, 231–240

Hui, J., et al. (2012). "Association of prostate cancer with PDLIM5, SLC22A3 and NKX3-1 in Chinese men." Zhonghua Nan Ke Xue 18(5): 404-411.

Jeronimo, C., et al. (2004). "Aberrant cellular retinol binding protein 1 (CRBP1) gene expression and promoter methylation in prostate cancer." J Clin Pathol 57(8): 872-876.

Karlsson, E., et al. (2008). "Gene expression variation to predict 10-year survival in lymph-node-negative breast cancer." BMC Cancer 8: 254.

Kennedy J., Eberhart R.,(1995) "Particle Swarm Optimization." in Proc.of the IEEE International Conference on Neural Networks ,vol.4

Kim, J. H., et al. (2011). "Deep sequencing reveals distinct patterns of DNA methylation in prostate cancer." Genome Res 21(7): 1028-1041.

Lee, Y. et al. (2004). "Classification of multiple cancer types by multicategory support vector machines using gene expression data. " Bioinformatics

Lisitskaia, K. V., et al. (2010). "A study of the single nucleotide polymorphism in seven genes (GHR, IGFBP3, IGFR1, IRS1, FMN1, ANXA2, TaGLN) in ethnic Russians and in patients with prostate cancer." Mol Gen Mikrobiol Virusol(2): 34-37.

Lu Y., et al. (2003) . "Cancer classification using gene expression data." Expert Systems with Applications,2003, 243–268

Medeiros, R., et al. (2004). " Metabolic susceptibility genes and prostate cancer risk in a southern European population: the role of glutathione S-transferases GSTM1, GSTM3, and GSTT1 genetic polymorphisms." Prostate 58(4): 414-420.

Olga K., et al. (2004) . " Hepsin promotes prostate cancer progression and metastasis."Cancer Cell,004.07.008

Osamu G., et al. (2009). " Accurate molecular classification of cancer using simple rules."BMC medical genomics, 2009

Park, P. J., et al. (2001). "A nonparametric scoring algorithm for identifying informative genes from microarray data." Pac Symp Biocomput: 52-63.

Schena M., (1999) ." DNA MICROARRAYS: A PRACTICAL APPROACH. . Practical Approach Series No. 205." ISBN: 0-19-963776-8

Statnikov A. , et al. (2009). "A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification."BioMed Central

SUN, M., et al. (2009) . "Comparative study of the expression of S100A4 and E -cadherin in prostate carcinoma and correlation with histological grade and clinical stage."Modern Oncology

Thomas A.S.,et al.,(2001)."Molecular genetic profiling of Gleason grade 4/5 prostate cancers compared to benign prostatic hyperplasia." The Journal of Urology 166 , 2171-2177

Tu C.J. ,et al.,(2007) ."Feature Selection using PSO-SVM." IAENG International Journal of Computer Science, 33:1

WANG, H.,et al.(2010)." Expression of AGR2 in prostate cancers and its clinicopathologic significance." Chinese Journal of Cancer;201005

Xu, Q. Y., et al. (2008). "Identification of differential gene expression profiles of radioresistant lung cancer cell line established by fractionated ionizing radiation in vitro." Chin Med J (Engl) 121(18): 1830-1837.

國民健康局.(2008). "中華民國九十六年癌症登記報告" 行政院衛生署

台灣癌症臨床研究發展基金會.(2008). "認識攝護腺癌”台灣癌症防治網http://cisc.twbbs.org/index.php

詹俊彥.,et al.(2009). "攝護腺癌之診斷與治療"家庭醫學與基層醫療第26卷第5期201-208
QRCODE
 
 
 
 
 
                                                                                                                                                                                                                                                                                                                                                                                                               
第一頁 上一頁 下一頁 最後一頁 top
無相關期刊