臺灣博碩士論文加值系統

G蛋白(G-Protein,鳥苷酸結合蛋白（guanine nucleotide-binding protein）)，這是一群很特殊的膜蛋白，它們在細胞中扮演著信號傳導開關的角色，而且跟蛋白質與其他分子的傳輸有密切的關係，G蛋白的活性由GTP(Guanosine triphosphate, 鳥嘌呤核苷三磷酸)來控制，當它們與GTP結合後，進入激活狀態，進而影響下游各種作用與分子，而當與GDP (guanosine diphosphate, 鳥嘌呤核苷二磷酸)結合的時候，就進入失活狀態，借用這樣的網路制衡關係來調控著細胞中的各種作用。與GTP結合的蛋白質影響著許多重要的疾病，如癌症、帕金森症等等，所以鑑別蛋白質中的GTP結合位置是一個很受重視的問題。
在本論文中，我們適當的選擇了與GTP有產生作用的運輸蛋白，並分為訓練資料集與獨立測試資料集。首先，我們用交叉驗證評估的準確度為95.6％，用獨立數據集檢驗性能的準確度為98.7％。基本上我們的方法優於之前的類似的方法，如GTPBinder，NsitePred和TargetSOS。
在這個論文中，我們針對運輸蛋白序列中與GTP結合的區段位置，開發出一個基於位置加權相似矩陣（PSSM）與有意義的胺基酸配對(SAAPs) 來鑑別運輸蛋白的GTP結合位置的具體方法，我們期望所提出的新方法可以作為一個標註運輸蛋白中GTP結合位置的有效工具，進而幫助生物學家了解運輸蛋白中與GTP作用的相關機制，協助提升大家對運輸蛋白的了解。

Guanonine-protein (G-protein) is known as molecular switches inside cells, and is very important in signals transmission from outside to inside cell. Especially in transport protein, most of G-proteins play an important role in membrane trafficking; necessary for transferring proteins and other molecules to a variety of destinations outside and inside of the cell. The function of membrane trafficking is controlled by G-proteins via Guanosine triphosphate (GTP) binding sites. The GTP binding sites active G-proteins initiated to membrane vesicles by interacting with specific effector proteins. Without the interaction from GTP binding sites, G-proteins could not be active in membrane trafficking and consequently cause many diseases, i.e. cancer, Parkinson... Thus it is very important to identify GTP binding sites in membrane trafficking, in particular, and in transport protein, in general.
We developed the proposed model with a cross-validation and examined with an independent dataset. We achieved an accuracy of 95.6% for evaluating with cross-validation and 98.7% for examining the performance with the independent data set. For newly discovered transport protein sequences, our approach performed remarkably better than similar methods such as GTPBinder, NsitePred and TargetSOS.
We approached a computational technique using PSSM profiles and SAAPs for identifying GTP binding residues in transport proteins. When we included SAAPs into PSSM profiles, the predictive performance achieved a significant improvement in all measurement metrics. Furthermore, the proposed method could be a power tool for determining new proteins that belongs into GTP binding sites in transport proteins and can provide useful information for biologists.

摘要 iii
ABSTRACT v
誌 謝 vii
目錄 viii
圖目錄 x
表目錄 xi
第一章 簡介 1
1-1 背景知識 1
1-2 相關研究 8
1-3 動機和目標 12
第二章 實驗資料與收集 13
2-1 Universal Protein Resource 13
2-2 資料集合(Data Set) 13
第三章 研究方法 18
3-1 實驗流程 18
3-2 分類器之使用 19
3-3 滑動視窗之屬性集合 22
3-4 屬性之分析與萃取 22
3-5 效能評估的方法 32
3-6 驗證方法 33
3-7 預測結果與分析 34
第四章 結論 40
第五章 參考文獻 41

1. Jr, S.M., T. CV, and B. RD, TCDB: the Transporter Classification Database for membrane transport protein analyses and information. Nucleic acids research, 2006. 34(Database issue): p. 181-186.
2. Bairoch, A., et al., The Universal Protein Resource (UniProt). Nucleic Acids Research, 2005. 33(Database issue): p. 154-159.
3. ZHANG, M., et al., Rab7: roles in membrane trafficking and disease. Bioscience reports, 2009. 29: p. 193-209.
4. Chauhan, J.S., N.K. Mishra, and G.P. Raghava. Prediction of GTP interacting residues, dipeptides and tripeptides in a protein from its evolutionary information. BMC Bioinformatics 2010; Available from: http://www.biomedcentral.com/1471-2105/11/301.
5. Ou, Y.-Y., et al., TMBETADISC-RBF: Discrimination of β-barrel membrane proteins using RBF networks and PSSM profiles. Computational Biology and Chemistry, 2008. 32: p. 227-231.
6. Chen, K., M.J. Mizianty, and L. Kurgan, Prediction and analysis of nucleotide-binding residues using sequence and sequence-derived structural descriptors. bioinformatics, 2012. 28: p. 331-341.
7. Hu, J., et al. A New Supervised Over-Sampling Algorithm with Application to Protein-Nucleotide Binding Residue Prediction. PloS one 2014; Available from: http://dx.doi.org/10.1371/journal.pone.0107676.
8. Johnson, M., et al., NCBI BLAST: a better web interface. Nucleic Acids Research, 2008,. 36(Web Server issue): p. 5-9.
9. Ou, Y.-Y. QuickRBF: a package for efficient radial basis function networks. 2005; Available from: http://csie.org/~yien/QuickRBF/.
10. Frank, E., et al., The WEKA Data Mining Software: An Update. ACM SIGKDD explorations newsletter, 2009. 11: p. 10-18.
11. Frank, E., et al., Data Mining in Bioinformatics using Weka. Bioinformatics, 2004. 20: p. 2479-2481.
12. Chang, C.-C. and C.-J. Lin, LIBSVM: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST), 2011. 2: p. 27.
13. Bradley, A.P., The use of the area under the ROC curve in the evaluation of machine learning algorithms. Pattern recognition, 1997. 30: p. 1145-1159.
14. Hanley, J.A., et al., The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology, 1982. 143: p. 29-36.
15. HENIKOFF, S. and J.G. HENIKOFF, Amino acid substitution matrices from protein blocks. Proceedings of the National Academy of Sciences 1992. 89: p. 10915-10919.
16. Dayhoff, M.O., R.M. Schwartz, and O. B. C, 22 A Model of Evolutionary Change in Proteins. Atlas of protein sequence and structure, 1972. 5: p. 345-352.
17. Crooks, G.E., et al., WebLogo: a sequence logo generator. Genome Research, 2004. 14: p. 1188-1190.