Genomic protein functionality classification algorithms in frequency domain.

• Other Authors: Lau, Tak-Chung.
• Format: Others
• Language: English; Chinese
• Published: 2004
• Subjects: Genomics > Data processing; Genes > Analysis > Data processing; Proteins > Analysis > Data processing
• Online Access: http://library.cuhk.edu.hk/record=b5892030; http://repository.lib.cuhk.edu.hk/en/item/cuhk-324586

Tak-Chung Lau. === Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. === Includes bibliographical references (leaves 190-198). === Abstracts in English and Chinese. === Abstract --- p.i === Acknowledgement --- p.iv === Chapter 1 --- Introduction --- p.1 === Chapter 1.1 --- Background Information --- p.4 === Chapter 1.2 --- Importance of the Problem --- p.6 === Chapter 1.3 --- Problem Definition and Proposed Algorithm Outline --- p.7 === Chapter 1.4 --- Simple Illustration --- p.10 === Chapter 1.5 --- Outline of the Thesis --- p.12 === Chapter 2 --- Survey --- p.14 === Chapter 2.1 --- Introduction --- p.14 === Chapter 2.2 --- Dynamic Programming (DP) --- p.15 === Chapter 2.2.1 --- Introduction --- p.15 === Chapter 2.2.2 --- Algorithm --- p.15 === Chapter 2.2.3 --- Example --- p.16 === Chapter 2.2.4 --- Complexity Analysis --- p.20 === Chapter 2.2.5 --- Summary --- p.21 === Chapter 2.3 --- General Alignment Tools --- p.21 === Chapter 2.4 --- K-Nearest Neighbor (KNN) --- p.22 === Chapter 2.4.1 --- Value of K --- p.22 === Chapter 2.4.2 --- Example --- p.23 === Chapter 2.4.3 --- Variations in KNN --- p.24 === Chapter 2.4.4 --- Summary --- p.24 === Chapter 2.5 --- Decision Tree --- p.25 === Chapter 2.5.1 --- General Information of Decision Tree --- p.25 === Chapter 2.5.2 --- Classification in Decision Tree --- p.26 === Chapter 2.5.3 --- Disadvantages in Decision Tree --- p.27 === Chapter 2.5.4 --- Comparison on Different Types of Trees --- p.28 === Chapter 2.5.5 --- Conclusion --- p.29 === Chapter 2.6 --- Hidden Markov Model (HMM) --- p.29 === Chapter 2.6.1 --- Markov Process --- p.29 === Chapter 2.6.2 --- Hidden Markov Model --- p.31 === Chapter 2.6.3 --- General Framework in HMM --- p.32 === Chapter 2.6.4 --- Example --- p.34 === Chapter 2.6.5 --- Drawbacks in HMM --- p.35 === Chapter 2.7 --- Chapter Summary --- p.36 === Chapter 3 --- Related Work --- p.37 === Chapter 3.1 --- Resonant Recognition Model (RRM) --- p.37 === Chapter 3.1.1 --- Introduction --- p.37 === Chapter 3.1.2 --- Encoding Stage --- p.39 === Chapter 3.1.3 --- Transformation Stage --- p.41 === Chapter 3.1.4 --- Evaluation Stage --- p.43 === Chapter 3.1.5 --- Important Conclusion in RRM --- p.47 === Chapter 3.1.6 --- Summary --- p.48 === Chapter 3.2 --- Motivation --- p.49 === Chapter 3.2.1 --- Example --- p.51 === Chapter 3.3 --- Chapter Summary --- p.53 === Chapter 4 --- Group Classification --- p.54 === Chapter 4.1 --- Introduction --- p.54 === Chapter 4.2 --- Design --- p.55 === Chapter 4.2.1 --- Data Preprocessing --- p.55 === Chapter 4.2.2 --- Encoding Stage --- p.58 === Chapter 4.2.3 --- Transformation Stage --- p.63 === Chapter 4.2.4 --- Evaluation Stage --- p.64 === Chapter 4.2.5 --- Classification --- p.72 === Chapter 4.2.6 --- Summary --- p.75 === Chapter 4.3 --- Experimental Settings --- p.75 === Chapter 4.3.1 --- "Statistics from Database of Secondary Structure in Pro- teins (DSSP) [27], [54]" --- p.76 === Chapter 4.3.2 --- Parameters Used --- p.77 === Chapter 4.3.3 --- Experimental Procedure --- p.79 === Chapter 4.4 --- Experimental Results --- p.79 === Chapter 4.4.1 --- Reference Group - Neurotoxin --- p.80 === Chapter 4.4.2 --- Reference Group - Biotin --- p.82 === Chapter 4.4.3 --- Average Results of all the Groups --- p.84 === Chapter 4.4.4 --- Conclusion in Experimental Results --- p.88 === Chapter 4.5 --- Discussion --- p.89 === Chapter 4.5.1 --- Discussion on the Experimental Results --- p.89 === Chapter 4.5.2 --- Complexity Analysis --- p.94 === Chapter 4.5.3 --- Other Discussion --- p.99 === Chapter 4.6 --- Chapter Summary --- p.102 === Chapter 5 --- Individual Classification --- p.103 === Chapter 5.1 --- Design --- p.103 === Chapter 5.1.1 --- Group Profile Generation --- p.104 === Chapter 5.1.2 --- Preparation of Each Testing Examples --- p.104 === Chapter 5.2 --- Design with Clustering --- p.104 === Chapter 5.2.1 --- Motivation --- p.105 === Chapter 5.2.2 --- Data Exception --- p.105 === Chapter 5.2.3 --- Clustering Technique --- p.110 === Chapter 5.2.4 --- Classification --- p.116 === Chapter 5.3 --- Hybridization of Our Approach and Sequence Alignment --- p.116 === Chapter 5.3.1 --- AlignRemove and AlignChange --- p.117 === Chapter 5.3.2 --- Classification --- p.119 === Chapter 5.4 --- Experimental Settings --- p.120 === Chapter 5.4.1 --- Parameters Used --- p.120 === Chapter 5.4.2 --- Choosing of Protein Functional Groups --- p.121 === Chapter 5.5 --- Experimental Results --- p.122 === Chapter 5.5.1 --- Experimental Results Setup --- p.122 === Chapter 5.5.2 --- Receiver Operating Characteristics (ROC) Curves --- p.123 === Chapter 5.5.3 --- Interpretation of Comparison Results --- p.125 === Chapter 5.5.4 --- Area under the Curve --- p.138 === Chapter 5.5.5 --- Classification with KNN --- p.141 === Chapter 5.5.6 --- Three Types of KNN --- p.142 === Chapter 5.5.7 --- Results in Three Types of KNN --- p.143 === Chapter 5.6 --- Complexity Analysis --- p.144 === Chapter 5.6.1 --- Complexity in Individual Classification --- p.144 === Chapter 5.6.2 --- Complexity in Individual Clustering Classification --- p.146 === Chapter 5.6.3 --- Complexity of Individual Classification in DP --- p.148 === Chapter 5.6.4 --- Conclusion --- p.148 === Chapter 5.7 --- Discussion --- p.149 === Chapter 5.7.1 --- Domain Expert Opinions --- p.149 === Chapter 5.7.2 --- Choosing the Threshold --- p.149 === Chapter 5.7.3 --- Statistical Support in an Individual Protein --- p.150 === Chapter 5.7.4 --- Discussion on Clustering --- p.151 === Chapter 5.7.5 --- Poor Performance in Hybridization --- p.154 === Chapter 5.8 --- Chapter Summary --- p.155 === Chapter 6 --- Application --- p.157 === Chapter 6.1 --- Introduction --- p.157 === Chapter 6.1.1 --- Construct the Correlation Graph --- p.157 === Chapter 6.1.2 --- Minimum Spanning Tree (MST) --- p.161 === Chapter 6.2 --- Application in Group Classification --- p.164 === Chapter 6.2.1 --- Groups with Weak Relationship --- p.164 === Chapter 6.2.2 --- Groups with Strong Relationship --- p.166 === Chapter 6.3 --- Application in Individual Classification --- p.168 === Chapter 6.4 --- Chapter Summary --- p.171 === Chapter 7 --- Discussion on Other Analysis --- p.172 === Chapter 7.1 --- Distanced MLN Encoding Scheme --- p.172 === Chapter 7.2 --- Unique Encoding Method --- p.174 === Chapter 7.3 --- Protein with Multiple Functions? --- p.175 === Chapter 7.4 --- Discussion on Sequence Similarity --- p.176 === Chapter 7.5 --- Functional Blocks in Proteins --- p.177 === Chapter 7.6 --- Issues in DSSP --- p.178 === Chapter 7.7 --- Flexible Encoding --- p.179 === Chapter 7.8 --- Advantages over Dynamic Programming --- p.179 === Chapter 7.9 --- Novel Research Direction --- p.180 === Chapter 8 --- Future Works --- p.182 === Chapter 8.1 --- Improvement in Encoding Scheme --- p.182 === Chapter 8.2 --- Analysis on Primary Protein Sequences --- p.183 === Chapter 8.3 --- In Between Spectrum Scaling --- p.184 === Chapter 8.4 --- Improvement in Hybridization --- p.185 === Chapter 8.5 --- Fuzzy Threshold Boundaries --- p.185 === Chapter 8.6 --- Optimal Parameters Setting --- p.186 === Chapter 8.7 --- Generalization Tool --- p.187 === Chapter 9 --- Conclusion --- p.188 === Bibliography --- p.190 === Chapter A --- Fourier Transform --- p.199 === Chapter A.1 --- Introduction --- p.199 === Chapter A.2 --- Example --- p.201 === Chapter A.3 --- Physical Meaning of Fourier Transform --- p.201