臺灣博碩士論文加值系統

結腸癌目前是人類癌症致死率在全球排名第二的疾病。近期，越來越多的研究著重在結腸癌幹細胞(Colon cancer stem cells)的探索，因為這些癌幹細胞會誘導更嚴重的疾病或者治療過後仍有較差的存活率。結腸癌幹細胞的生物標記(biomarker)能夠幫助我們去評估疾病階段的嚴重性，以及藥物治療的可靠度。找出新的癌症預後標記能幫助我們鑑定在表現量下的存活率並且對症下藥。
在這研究中，我們從12組微陣列資料根據8個著名癌幹細胞標記利用StepMiner algorithm將患者分成負表現群和正表現群。我們利用這兩群分別建出所相對應的負表現和正表現蛋白質蛋白質交互網路(PPINs)。我們接著提出並計算預後蛋白相關係數並且得出共12個高PPRV值的顯著蛋白。此外，我們用深度學習演算法(深度類神經網路，DNN)和支持向量機演算法(SVM)用來預測的5年存活率結腸癌患者。我們結果顯示12個新定義標記在DNN模型下的預測精準度(AUC = 0.811; Accuracy = 77.3)比8個著名癌幹細胞標記還來的好(AUC = 0.738; Accuracy = 72.7)；同樣地，我們結果顯示12個新定義標記在SVM模型下的預測精準度(AUC = 0.816; Accuracy = 79.0)比8個著名癌幹細胞標記還來的好(AUC = 0.766; Accuracy = 76.9)。
根據我們所建出來的網路以及計算出的PPRVs，我們能夠找出12個新的預測標記與結腸癌幹細胞有高度關聯。這項研究用已知的癌幹細胞結合系統生物和深度學習方法能夠定義出新的預測標記，並且對5年結腸癌復發的資料有精確的預測。我們相信以我們的系統式方法找出新的癌症預後標記並做癌症復發預測在未來提供了癌症治療能研發較好的治療方針。

Background:
Colon cancer is the second leading cause of human death worldwide. Recently, there has been an increasing amount of studies investigating colon cancer stem cells (CCSCs), which encompass characteristics of self-renewal, mature tumor cells generation through differentiation, drug resistance and metastasis. Patients with genetic signatures of CSCs were shown to have worse survival rate and higher chance of cancer relapse. It is hence of interest to identify novel prognostic markers for colon cancer relapse via the genetic signatures of CSC markers.
Result:
Based on 12 primary integrated microarray datasets, we divided colon cancer patients into marker- and marker+ subgroups according to 8 well-known CSC markers. Then, we constructed their corresponding protein-protein interaction networks (PPINs) for both marker- and marker+ subgroups. We then proposed and calculated prognostic proteins relevance values (PPRV) and obtained a total of 12 significant proteins high in PPRVs for colon cancer patients. In addition, we applied a deep learning algorithm (a deep neural network, DNN) and support vector machine (SVM) algorithm to predict the 5-year relapse rate of colon cancer patients. Our results showed that the prediction accuracy of 12 of our identified markers (AUC = 0.811; Accuracy = 77.3) is much better than the 8 well-known CSC markers (AUC = 0.738; Accuracy = 72.7) via DNN; and the prediction accuracy of 12 of our identified markers (AUC = 0.816; Accuracy = 79.0) is again much better than the 8 well-known CSC markers (AUC = 0.766; Accuracy = 76.9) via SVM.
Conclusion:
According to our constructed PPINs and calculated PPRVs, we were able to identify 12 novel prognostic markers for colon CSC markers. This study integrates systems biology and deep learning methodologies that allows for the identification of novel prognostic markers via existing CSC markers, and accurate prediction of colon cancer 5-year relapse. We believe that such a systemic approach to uncover novel cancer prognostic markers and to predict cancer relapse provides the foundation for the design of better therapeutic strategy for cancer treatment in the future.
Keywords:
Cancer stem cells, colon cancer, prognostic markers, deep learning, SVM, systems biology.

Abstract i
Background: i
Result: i
Conclusion: i
Keywords: ii
Content v
Chapter 1 Introduction 1
Chapter 2 Results 3
Strategy 3
Threshold calculation for separating negative and positive patient samples 5
Construction of CSC marker- and marker+ protein-protein interaction networks 8
Pathway analysis of the refined marker- and marker+ PPINs 11
Determination of PPRVs via comparing CSC marker-/marker+ PPINs 17
Identification of novel CCCP markers 18
A deep learning approaches to comparing well-known markers with novel CCCP markers in colon cancer relapse prediction 21
Chapter 3 Conclusion 25
Chapter 4 Methods 26
Dataset selection 26
Colon cancer gene expression datasets 26
Statistical Analysis 27
Reference 28

[1] Ricchi, P., et al. Nonsteroidal anti-inflammatory drugs in colorectal cancer: from prevention to therapy. British journal of cancer 2003; 88(6):803-807.
[2] Tsukuma, H., Ajiki, W. and Oshima, A. [Cancer incidence in Japan]. Gan to kagaku ryoho. Cancer & chemotherapy 2004; 31(6):840-846.
[3] Siegel, R.L., Miller, K.D. and Jemal, A. Cancer statistics, 2015. CA: a cancer journal for clinicians 2015; 65(1):5-29.
[4] Chua, Y.J. and Zalcberg, J.R. Progress and challenges in the adjuvant treatment of stage II and III colon cancers. Expert review of anticancer therapy 2008;8(4):595-604.
[5] Speetjens, F.M., et al. Induction of p53-specific immunity by a p53 synthetic long peptide vaccine in patients treated for metastatic colorectal cancer. Clinical Cancer Research 2009; 15(3):1086-1095.
[6] Vaiopoulos, A.G., et al. Colorectal cancer stem cells. Stem cells 2012; 30(3):363-371.
[7] Klonisch, T., et al. Cancer stem cell markers in common cancers–therapeutic implications. Trends in molecular medicine 2008; 14(10):450-460.
[8] Reya, T., et al. Stem cells, cancer, and cancer stem cells. nature 2001;414(6859):105-111.
[9] Baeuerle, P. and Gires, O. EpCAM (CD326) finding its role in cancer. British journal of cancer 2007; 96(3):417-423.
[10] Du, L., et al. CD44-positive cancer stem cells expressing cellular prion protein contribute to metastatic capacity in colorectal cancer. Cancer research 2013; 73(8):2682-2694.
[12] Horst, D., et al. CD133 expression is an independent prognostic marker for low survival in colorectal cancer. British journal of cancer 2008; 99(8):1285-1289.
[13] Dalerba, P., et al. Phenotypic characterization of human colorectal cancer stem cells. Proceedings of the National Academy of Sciences 2007; 104(24):10158-10163.
[14] Schatton, T., et al. Identification of cells initiating human melanomas. Nature 2008; 451(7176):345-349.
[15] Bunting, K.D. ABC transporters as phenotypic markers and functional regulators of stem cells. Stem cells 2002; 20(1):11-20.
[16] Dean, M. ABC transporters, drug resistance, and cancer stem cells. Journal of mammary gland biology and neoplasia 2009; 14(1):3-9.
[17] Stelzl, U., et al. A human protein-protein interaction network: a resource for annotating the proteome. Cell 2005; 122(6):957-968.
[18] Wang, Y.-C. and Chen, B.-S. A network-based biomarker approach for molecular investigation and diagnosis of lung cancer. BMC medical genomics 2011; 4(1): 1.
[19] Eschrich, S., et al. Systems biology modeling of the radiation sensitivity network: a biomarker discovery platform. International Journal of Radiation Oncology* Biology* Physics 2009; 75(2):497-505.
[20] John Lu, Z. The elements of statistical learning: data mining, inference, and prediction. Journal of the Royal Statistical Society: Series A (Statistics in Society) 2010; 173(3):693-694.
[21] Murphy, K.P. Machine learning: a probabilistic perspective. MIT press; 2012.
[22] Michalski, R.S., Carbonell, J.G. and Mitchell, T.M. Machine learning: An artificial intelligence approach. Springer Science & Business Media; 2013.
[23] Ahn, J., et al. Integrative gene network construction for predicting a set of complementary prostate cancer genes. Bioinformatics 2011; 27(13):1846-1853.
[24] Gevaert O, Smet F, Timmerman D, Moreau Y, De Moor B: Predicting the prognosis of breast cancer by integrating clinical and microarray data with Bayesian networks. Bioinformatics 2006, 22:e184–e190.
[25] Boulesteix AL, Porzelius C, Daumer M: Microarray-based classification and clinical predictors: on combined classifiers and additional predictive value. Bioinformatics 2008, 24:1698–1706.
[26] Nicole Rusk: Deep learning. Nature Methods 2016, 13, 35
[27] Debashis Sahoo, David L. Dill , Rob Tibshirani and Sylvia K. Plevritis: Extracting binary signals from microarray time-course data. Nucl. Acids Res. (2007), 35 (11):3705-3712.