生物學中最重要的分子是嵌入細胞外層脂肪膜中的蛋白質，它們就像守門員一樣探測細胞外的重要化合物，決定哪些可進入細胞中，近年來網路上有很多預測膜蛋白的工具提供預測，且大多是針對在螺旋(helice)結構上，雖然這些工具的預測準確性佔有50-70%，但有10%的錯誤預測是因為無法正確辨識球蛋白部分，以至於使其研究發展預期過高，本研究希望利用類神經網路的方式來預測膜蛋白，資料來源取自PDB資料庫裡的593條已知的膜蛋白及500條非膜蛋白，建立資料庫並運用到目前為止可用的預測工具，來評估其準確性，再用類神經網路的方法加以整合，希望能提供一個最佳化的類神經網路來正確預測膜蛋白。

Membrane proteins are crucial for survival﹒They constitute the key components for cell–cell signal transduction﹐transport of ions or solutes across the membrane, and are crucial for recognition. Many methods predict membrane helices, but few predict membrane strands﹒The good news is that most methods for helical membrane proteins are available and have higher accuracy﹒Current prediction methods predict membrane helices for about 50%–70% accuracy, and 10%false prediction for the globular protein﹒The bad news is that developers have seriously overestimated the accuracy of their methods﹒
This research utilized neural network to predict membrane protein. The protein data were collected from PDB database. The standard data set contains 593 membrane protein sequences and 500 non-membrane protein sequences. Nine popular prediction tools on the internet were used to assess its accuracy. Then, we take the way of neural network to integrate these tools and to predict membrane protein more precise.

目 錄

摘 要.....................................................i
Abstract.................................................ii
目 錄...................................................iii
第一章 簡介…………………………………………………………1
1.1 研究背景與動機………………………………………………1
1.1.1 膜蛋白構造介紹 ………………………………………1
1.1.2 膜蛋白功能 ……………………………………………5
1.1.3 研究動機 ……………………………………………5

第二章 文獻探討及應用原理 ………………………………………7
2.1 預測基本概念 ……………………………………………7
2.1.1 穿膜螺旋位置及拓撲學………………………………7
2.1.2 跨膜蛋白方向性………………………………………7
2.1.3 穿膜桶狀蛋白預測概念………………………………8
2.2 應用工具介紹 ………………………………………………9
2.2.1 文獻應用回顧…………………………………………9
2.2.2 類神經網路概論……..................................................21
2.2.3 蛋白質資料庫介紹 …………………………………25

第三章 材料與方法 ………………………………………………28
3.1 膜蛋白預測流程 ………………………………………… 28
3.2 膜蛋白預測方法介紹 …………………………………… 30
3.2.1 蛋白質結構資料庫 ……………………………… 30
3.3.2 應用工具預測 …………………………………… 31
3.3 研究方法架構 …………………………………………… 33
3.3.1 類神經網路軟體介紹-Joone ……………………… 33
3.3.2 膜蛋白預測的類神經網路架構 ……………………37

第四章 結果與討論…………………………………………………39
4.1 膜蛋白與非膜蛋白預測結果分析 .................. 39
4.2 尋找門檻 ...................................... 40

第五章 結論…………………………………………………………44

參考文獻 ………………………………………………………………45
參考網站.................................................50


表目錄

表一: 胺基酸親水數………………………………………………… 11
表二:蛋白質資料庫的分子類................................26
表三: 膜蛋白資料收集例 ………………………………………… 30
表四: 九種工具預測結果示意表 ……………………………………31
表五: 九種工具預測統計結果 ………………………………………32
表六: XOR表格…………………………………………………………34
表七: 訓練資料結果 …………………………………………………42
表八: 測試資料結果 …………………………………………………43









圖目錄

圖一: 膜蛋白構造示意圖………………………………………………3
圖二: 蛋白與膜的結合方式示圖………………………………………3
圖三: 螺旋式膜蛋白……………………………………………………4
圖四: 桶狀式(β-barrel)膜蛋白 ……………………………………4
圖五: KD預測果……………………………………………………… 11
圖六: ALOM2預測結果…………………………………………………12
圖七: 跨膜地區終端示意圖 …………………………………………13
圖八: PRED-TMR預測結果 ……………………………………………14
圖九: TM Finder預測結果……………………………………………15
圖十: Tmpred預測結果 ………………………………………………16
圖十一: (A)SOSUI預測結果(表格顯示) ……………………………17
圖十一: (B)SOSUI預測結果(圖形顯示)…………………………… 17
圖十二: MEMSAT預測結果 ……………………………………………18
圖十三: DAS預測結果…………………………………………………19
圖十四: 胺基酸依其側鏈在膜上狀態的示意圖 ……………………20
圖十五: TMHMM預測結果………………………………………………20
圖十六: 類神經網路輸入輸出示意圖 ………………………………21
圖十七: 類神經網路架構示意圖 ……………………………………23
圖十八: 蛋白質資料庫銀行(PDB)首頁………………………………27
圖十九: 實驗架構流圖……………………………………………… 29
圖二十: 九種工具預測準確度示圖………………………………… 32
圖二十一: 簡單的XOR類神經路…………………………………… 34
圖二十二: Joone 編輯3層XOR示意圖……………………………… 35
圖二十三: Joone 編輯加入訓練網路示意圖……………………… 36
圖二十四: Joone膜蛋白預測架構示意圖……………………………37
圖二十五: 膜蛋白預測的類神經網路示意圖……………………… 38
圖二十六: 已知的膜蛋白預測結果...........................39
圖二十七: 已知的膜蛋白預測結果...........................40
圖二十八: 膜蛋白預測結果分布圖………………………………… 41
圖二十九: 非膜蛋白預測結果分布圖……………

參考文獻

[1] von Heijne G.. Recent. 1992 "advances in the understanding of membrane protein
assembly and function", Q. Rev. Biophys, 32, , pp285–307.

[2] Schulz GE. 2003 "Transmembrane beta-barrel proteins"., Adv Protein Chem ,
63, pp47–70.

[3] Wimley WC.2003 "The versatile beta-barrel membrane protein"., Curr Opin Struct Biol , 13, pp404–411.

[4] Stack JH, Horazdovsky B, Emr SD. 1995 "Receptor-mediated protein sorting to the vacuole in yeast: roles for a protein kinase, a lipid kinase and GTP-binding proteins"., Annu Rev Cell Dev Biol, pp1–33.

[5] Le Borgne R, Hoflack B.1998 "Protein transport from the secretory to the endocytic pathway in mammalian cells"., Biochim Biophys Acta,1404,pp195–209.

[6] Truscott KN, Pfanner N. 1999 "Import of carrier proteins into mitochondria. "., Biol Chem, 380, pp1151–1156.

[7] Mitochondrial processing peptidase. 2000 "multiple-site recognition of precursor proteins"., TICB, 10, pp25–31.

[8] Thanassi DG, Hutltgren SJ. 2000 "Multiple pathways allow protein secretion across the bacterial outer membrane"., Curr Opin Cell Biol,12,pp420–430.

[9] Attwood TK. 2001"A compendium of specific motifs for diagnosing GPCR subtypes"., Trends Pharmacol Sci,22, pp162–165.

[10] Gudermann T, Nurnberg, B, Schultz G. 1995 "Receptors and G proteins as primary components of transmembrane signal transduction. Part 1.G-protein-coupled receptors: structure and function"., J Mol Med, 73, pp51–63.

[11] Wallin E, von Heijne G. 1998 "Genome-wide analysis of integral Membrane proteins from eubacterial, archaean, and eukaryotic organisms".,Protein Sci, 7, pp1029–1038.

[12] Liu J, Rost B. 2001 "Comparing function and structure between entire proteomes"., Protein Sci, 10, pp1970–1979.

[13] von Heijne G. 1989 "Control of topology and mode of assembly of a polytopic membrane protein by positively charged residues"., Nature, 341, pp456–458.

[14] von Heijne G. 1986 "The distribution of positively charged residues in bacterial inner membrane proteins correlates with the trans-membranetopology"., EMBO J, 5, pp3021–3027.

[15] Hartmann E, Rapoport TA, Lodish HF.1989 "Predicting the orientation of eukaryotic membrane spanning proteins"., Proc Natl Acad Sci USA, 86, pp5786–5790.

[16] Kyte J, Doolittle RF. 1982 "A simple method for displaying the hydrophathic
character of a protein"., J Mol Biol, 157, pp105–132.

[17] Nakai K, Kanehisa M. 1992 "A knowledge base for predicting protein
localization sites in eukaryotic cells"., Genomics, 14 ,pp897–911.

[18] Pasquier C, Promponas VJ, Palaios GA, Hamodrakas JS, Hamodrakas SJ. 1999 "A novel method for predicting transmembrane segments in proteins based on a statistical analysis of the SwissProt database: the PRED-TMR algorithm"., Protein Engin, 12, pp381–385.

[19] Deber CM, Wang C, Liu LP, Prior AS, Agrawal S, Muskat BL, Cuticchia AJ. 2001 "TM Finder:a prediction program for transmembrane protein segments using a combination of hydrophobicity and nonpolar phasehelicity scales"., Protein Sci, 10, pp212–219.

[20] Hofmann K, Stoffel W. 1993 "TMBASE –a database of membrane spanning protein segments"., Biol Chem Hoppe-Seyler, 374, pp166.

[21] Hirokawa T, Boon-Chieng S, Mitaku S. 1998 "SOSUI:classification and secondary structure prediction system for membrane proteins"., Bioinformatics, 14, pp378–379.

[22] Jones DT, Taylor WR, Thornton JM. 1994 "A model recognition approach to the prediction of all-helical membrane protein structure and topology"., Biochem, 33, pp3038–3049.
[23] Cserzo M, Wallin E, Simon I, von Heijne G, Elofsson A. 1997 "Prediction of
transmembrane α-helices in prokaryotic membrane proteins: the dense alignment
surface method"., Protein Engin, 10, pp673–676.

[24] Krogh A, Larsson B, von Heijne G, Sonnhammer EL. 2001 "Predicting transmembrane protein topology with a hidden Markov model:application to
complete genomes"., J Mol Biol, 305, pp567–580.

[25] Frode S. Berven, Kristian Flikka1,*, Harald B. Jensen and Ingvar Eidhammer. 2004 "BOMP:a program to predict integral b-barrel outer membrane proteins encoded within genomes of Gram-negative bacteria"., Nucleic Acids Research, 32, pp394–399.

[26] Casadio,R., Fariselli,P., Finocchiaro,G. and Martelli,P.L. 2003 "Fishing new proteins in the twilight zone of genomes: the test case of outer membrane proteins in Escherichia coli K12, Escherichia coli 157:H7, and other Gram-negative bacteria"., Protein Sci, 12, pp1158–1168.

[27] Zhai,Y. and Saier,H.M.J. 2002 "The beta-barrel finder (BBF) program, allowing identification of outer membrane beta-barrel proteins ncoded within prokaryotic genomes"., Protein Sci, 11, pp2196–2207.

[28] Wimley,C.W. 2002 "Towards genomic identification of beta-barrel membrane proteins: composition and architecture of known structures"., Protein Sci, 11, pp301–312.

[29] Hartmann E, Rapoport TA, Lodish, HF. 1989 "Predicting the orientation of eukaryotic membrane spanning proteins"., Proc Natl Acad Sci USA, 86, pp5786–5790.

[30] Peitsang Wu, Shu-Cherng Fang, Henry L.W. Nuttle, James R. Wilson, and Russell E. King. 1995 "Guided Neural Network Learning Using a Fuzzy Controller with an Application to Textile Spinning"., International Transactions of Operations Research, 2, pp259-272.

[31] Peitsang Wu, Shu-Cherng Fang, Henry L.W. Nuttle, and Russell E. King. 1995 "Decision Surface Modeling of Apparel Retail Operations using Neural Network Technology"., International Journal of Operations and Quantitative Management, 1, pp33-47.

[32] 葉怡成， 1997 "應用類神經網路"，儒林圖書有限公司

[33] 蘇木春、張孝德， 1999 "機械學習：類神經網路、模糊系統以及基因演算
法則"，全華科技圖書股份有限公司