在生物組織中，基因是無法單獨作用的。基因間的互相影響，才能使得生物功能顯現出來。藉由觀察這些作用，可以了解基因間的關係為何，甚至也可找出關於疾病發生原因的線索。建構出基因關聯圖，可以讓觀察基因間的相互作用更為簡單，因此在這個領域上，有許多的研究與方法已經被發表或採用。現今，在建構基因關聯圖的問題的解法上，最主要有兩種模式。一種是利用文獻，搜尋現存中有提到的基因與基因間的關係的文獻，並且取出兩者間的關係。而另一種，則是利用基因表現的資料來做計算，找出兩兩基因間有所關聯者，並且將之做連結。在本篇論文中，提出了一個綜合前述的兩個方法。貝氏網路利用使用者輸入的基因表現資料來建構基本的基因關聯圖。接著，再利用文字探勘的方法，從文獻的資料庫中，搜尋並擷取出基因間的關係詞。最後將兩者的結果，做一個結合，藉此得到最終且較為完善的結果。實驗結果顯示，相關性高的基因會被連結在一起，此外，更有基因與基因的關係詞可供參考。

In the organism, genes don’t work independently. The interaction of genes shows how the functional task affects. Observing the interaction can understand what the relation between genes and how the disease caused. Several methods are adopted to observe the interaction to construct gene relation network. Existing algorithms to construct gene relation network can be classified into two types. One is to use literatures to extract the relation between genes. The other is to construct the network, but the relations between genes are not described. In this thesis, we proposed a hybrid method based on these two methods. Bayesian network is applied to the microarray gene expression data to construct gene network. Text mining is used to extract the gene relations from the documents database. The proposed algorithm integrates gene network and gene relations into gene relation networks. Experimental results show that the related genes are connected in the network. Besides, the relations are also marked on the links of the related genes.

1. Introduction 1
2. Background materials and literature review 4
2.1 Background materials 4
2.1.1 Text mining 4
2.1.2 Bayesian network 5
2.2 Literature reviews 9
2.2.1 Text mining 9
2.2.2 Bayesian network 10
3. The proposed algorithm 12
3.1 Undirected gene network construction 18
3.2 Gene network direction assignment 20
3.3 The K2 algorithm 23
3.4 Documents retrieval 25
3.5 Information extraction 27
3.6 Combination of relations and gene network 29
4. Experiments and discussions 32
5. Conclusions 39
REFERENCES 39

[1] Quackenbusch, J. (2001) Computational analysis of microarray data, Nature Genetics, 2, 418-427
[2] Tamayo, P. (1999) Interpreting patterns of gene expression with self-organizing maps: method sand application to hematopoietic differentiation, Proceedings of the National Academy of Sciences, 96, 2907-2912
[3] Golub, T. et al. (1999) Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring, Science, 286, 531-537
[4] Thykjaer, T. et al. (2001) Identification of gene expression patterns in superficial and invasive human bladder cancer, Cancer Research, 61, 2492-2499
[5] Khan, J. et al. (2001) Classification and diagnostic prediction of cancers using gene expression profiling and artificial neural networks, Nature Medicine, 7(6), 673-679
[6] Friedman, N. et al. (2000) Using Bayesian networks to analyze expression data, Journal of Computational Biology, 7, 601-620
[7] Chen, X.W., Anantha, G. and Wang, X. (2006) An effective structure learning method for constructing gene networks, Bioinformatics, 1367-1374
[8] Gregory F. Cooper and Edward Herskovits (1992) A Bayesian method for the induction of probabilistic networks form data, Machine Learning, 9, 309-347
[9] Shmulevich, I. et al. (2002) Probabilistic Boolean networks: a rule-based uncertainty model for gene regulatory networks, Bioinformatics, 8, 261-274
[10] Chen, K.C. et al. (2005) A stochastic differential equation model for quantifying transcriptional regulatory network in Saccharomyces cerevisiae, Bioinformatics, 21, 2883-2890.
[11] De Jong, H. (2000) Modeling and simulation of genetic regulatory systems: a literature review, Journal of Computational Biology, 9(1), 67-103
[12] Karopka, T., Scheel, T., Bansemer, S. and Glass, A. (2004) Automatic construction of gene relation networks using text mining and gene expression data, 169-183
[13] Murphy, K. and Mian, S. (1999) Modeling gene expression data using dynamic Bayesian networks, Technical Report, Computer Science Division, University of California, Berkeley, CA
[14] Friedman, N., Goldszmidt, M. and Wyner, A. (1999) Data analysis with Bayesian network: a bootstrap approach. Morgan Kaufmann, In Proceeding of 15th Conference on Uncertainty in Aftificial Intelligence, Stockholm, Sweden, 206-215
[15] Heckerman, D., Geiger, D. and David M. Chickering (1995) Learning Bayesian networks: the combination of knowledge and statistical data, Machine Learning, 20, 197-234
[16] Friedman N., Goldszmidt M. (1998) Learning Bayesian networks with local structure, Jordan, M.I. (ed.), Kluwer Academic Publishers, 421-459
[17] Imoto, S., Goto, T., Miyano S. (2002) Estimation of genetic networks and functional structures between genes by using Bayesian networks and nonparametric regression, Pacific Symposium on Biocomputing, 7, 175-186
[18] Bander, G. et al. (2002) BIND-The biomolecular interaction network database. Nucleic Acids Research, 29, 242-245
[19] Zanzoni, A. et al. (2002) MINT: a Molecular INTeraction database. FEBS Letters, 513, 135-140
[20] Olesen, K. and Madsen, A. (2002) Maximal prime sub-graph decomposition of Bayesian Network, IEEE Trans. Syst. Man Cybern. B, 32, 21-31
[21] Spellman, P.T. et al. (1998) Comprehensive identification of cell cycle-regulated genes of the yeast Saccharomyces cerevisiae by microarray hybridization, Mol. Biol. Cell, 9, 3273-3297
[22] Whitfield, M.L. et al. (2002) Identification of genes periodically expressed in the human cell cycle and their expression in tumors, Mol. Biol. Cell,13, 1977-2000
[23] HUGO Nomenclature Committee, http://www.gene.ucl.ac.uk/nomenclature
[24] OMIM, http://www.ncbi.nlm.nih.gov:80/entrez/query.fcgi?db=OMIM
[25] GeneCards, http://bioinformatics.weizmann.ac.il/cards/
[26] PubGene, http://www.pubgene.org
[27] NCBI, http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed
[28] Gene, http://www.ncbi.nlm.nih.gov/sites/entrez?db=gene
[29] Chiang J.H, Yu H.C, Hsu H.J (2004) GIS: a biomedical text-mining system for gene information discovery, Bioinformatics, 20(1), 120-121