臺灣博碩士論文加值系統

在本研究中，我們進一步改良了基因的選取方法，結合7個基因的挑選方法，稱為整體學習演算法(Ensemble Voting)。基因表現資料包含有白血病、前列腺癌和乳癌的資料。從三種微陣列表現資料中，我們發現由七個基礎學習演算法，針對每次產生的結果進行投票的Ensemble Voting得到的結果比單一種特徵選取方法的準確度還高，而在每一種基因表現資料集合或者是不同的基因數量都有著相當不錯的結果，不會因為基因表現資料集合或者基因數目的不同，準確度就大大的降低，都會維持在水準以上，是一個較適合針對基因表現資料進行處理的分析技術。
利用Ensemble Voting的方式整合生物統計分析和機器學習的七種特徵選取方法，是一個強而有力的有效方法，並且能提高分類性能，得到比原先方法更高的準確性。

In this paper, we describe a framework for selecting informative genes, called Ensemble Voting method, which combines seven gene selection methods. We conducted experiments using leukemia, prostate cancer, and breast cancer data sets. The results show that the ensemble voting framework is a robust and efficient approach to identify informative genes and to improve classification performance from microarray data. The ensemble voting approach had an equal or better performance than each individual feature selection method almost in all range of genes selected. The results indicate that ensemble voting method might be a viable and feasible approach for the microarray gene expression analysis.

第一章、序論 - 1 -
1.1 研究背景 - 1 -
1.3 研究目的 - 3 -
第二章、文獻探討 - 5 -
2.1 分類問題 - 10 -
2.2 特徵選取 - 11 -
第三章、研究方法 - 14 -
3.1生物統計分析特徵選取方法 - 15 -
3.1.1 t-Test - 15 -
3.1.2 Fisher - 17 -
3.1.3 Golub - 19 -
3.1.4 TNoM - 20 -
3.1.5 MDMR - 22 -
3.1.6 WEPO - 23 -
3.2 機器學習特徵選取方法 RANDOM FORESTS - 26 -
3.3 ENSEMBLE VOTING - 29 -
3.4 分類方法 - 32 -
3.5 尋找具有生物意義的重要基因 - 34 -
第四章、系統建構 - 35 -
4.1 資料庫與資料結構設計 - 36 -
4.2 系統架構設計與流程圖 - 37 -
4.3 系統介面 - 39 -
4.4 使用說明 - 40 -
第五章、結果與討論 - 42 -
5.1微陣列基因表現資料 - 42 -
5.2七種特徵選取方法研究結果與比較分析 - 43 -
5.2.1分類準確度 - 43 -
5.2.2探討生物意義的重要基因 - 50 -
5.3 ENSEMBLE VOTING研究結果與比較分析 - 52 -
第六章、結論與未來展望 - 57 -
6.1 結論 - 57 -
6.2 未來展望 - 59 -
參考文獻 - 60 -

1.Allwein, E.L., Schapire, R.E. and Singer, Y., “Reducing Multiclass to Binary: A Unifying Approach for Margin Classifiers”, SIC on Machine Learning, 2000.
2.Amir, B.D. et al., “Tissue Classification with Gene Expression Profiles”, Journal of Computational Biology, 2000.
3.Bioshop, C. “Neural networks for pattern recognition”, Oxford University Press, New York, 1995.
4.Chen, T.Y., Poon, P.L. and Tse, T.H., “A New Restructuring Algorithm for the Classification-Tree Method”, Software Technology and Engineering, 1999.
5.Chuang, H.Y. et al., “Ranking genes for discriminability on microarray data”, Journal of Information Science and Engineering, 2003.
6.Chuang, H.Y. et al.: “Identifying Significant Genes from Microarray Data”, IEEE 2004.
7.Cover, T. and Hart, P. “Nearest Neighbor Pattern Classification”, IEEE Transactions Information Theory, 1967.
8.Dasarathy, B.V. et al., “Concepts and Techniques, Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques”, IEEE Computer Society Press, 1991.
9.Dietterich, T.G.. and Bakiri, G. “Error-Correcting Output Codes: A General Method for Improving Multiclass Inductive Learning Programs”, Ninth National Conference on Artificial Intelligence, 1995.
10.Dietterich, T.G. and Bakiri, G., “Solving Multiclass Learning Problems Via Error-Correcting Output Codes”, Journal of Artificial Intelligence Research, 1995.
11.Dudoit, S., Fridlyand J. and Speed, T.P., “Comparison of Discrimination Methods for the Classification of Tumors using Gene Expression Data”, Department of Statistics, 2000.
12.Gevaert, O. et al.,” Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks”, BMC Bioinformatics 2006.
13.Golub, T. R. et al., “Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring”, Science, 1999.
14.Hastie, T. and Tibshirani, R. et al., “Classification by Pairwise Coupling”, Neural Information Processing Systems, 1998.
15.Hastie, T., Tibshirani, R. and Friedman, J. “The Elements of Statistical Learning:Data Mining”, Springers Series in Statistics, 2001.
16.Hedenfalk, I .et al., “Gene-expression profiles in hereditary breast cancer”, New England J. Med., 2001.
17.Hettemansperger, T. P. “Statistical Inference based on ranks”, Wiley, New York, 1984.
18.Karlsson, E. et al., ” Gene expression variation to predict 10-year survival in lymph-node-negative breast cancer”, BMC Cancer 2008.
19.Kim, S.Y. et al., ” A gene sets approach for identifying prognostic gene signatures for outcome prediction”, BMC Genomics 2008.
20.Kre�惷l, U. et al., “Pairwise Classification and Support Vector Machines, Advances in Kernel Methods: Support Vector Learning”, MA, MIT Press, 1999.
21.McCallum, A.K. and Nigam, K. “A Comparison of Event Models for Naive Bayes Text Classification”, AAAI-98 Workshop on Learning for Text Categorization, 1998.
22.Mitchell, T.M., “Machine Learning”, McGraw-Hill, 1997.
23.Park, P.J. et al., “A Nonparametric Scoring Algorithm for Identifying Informative Genes from Microarray Data”, Pacific Symposium on Biocomputing, 2001.
24.Safavian, R.S. and Landgrebe, D., “A Survey of Decision Tree Classifier Methodology”, IEEE Transactions of Systems, 1991.
25.Sahami, M., Dumais, S., Heckerman, D. and Horvitz, E., “A Bayesian Approach to Filtering Junk E-Mail, Learning for Text Categorization”, AAAI-98 Workshop on Learning for Text Categorization, 1998.
26.Schena, M. et al., “DNA Microarrays : A Pratical Approach”, Oxford University Press, 1999.
27.Singh. D. et al.,” Gene expression correlates of clinical prostate cancer behavior”, Cancer Cell, 2002.
28.Statnikov, A. et al., “A Comprehensive Evaluation of Multicategory Classification Methods for Microarray Gene Expression Cancer Diagnosis”, BMC Bioinformatics 2004.
29.Statnikov, A. et al., “A comprehensive comparison of random forests and support vector machines for microarray-based cancer classification”, BMC Bioinformatics 2008.
30.Specht, D.F., “Probabilistic Neural Network”, Neural Networks, 1990.
31.Van’t Veer. et al, “Gene expression profiling predicts clinical outcome of breast cancer” , Nature 2002
32.Vogt, C.C. and G.W. Cotrell, “Fusion via a linear combination of scores”, Info. Ret., 1999.
33.Weston, J. and Watkins, C., “Multi-Class Support Vector Machines”, Department of Computer Science, 1998.
34.Yang, J.H. and Honavar, V., “Feature Subset Selection Using a Genetic Algorithm”, IEEE on Intelligent Systems, 1998.