Overview

Comprehensively covers protein subcellular localization from single-label prediction to multi-label prediction, and includes prediction strategies for virus, plant, and eukaryote species. Three machine learning tools are introduced to improve classification refinement, feature extraction, and dimensionality reduction.

Full Product Details

Author:   Shibiao Wan ,  Man-Wai Mak
Publisher:   De Gruyter
Imprint:   De Gruyter
Weight:   0.495kg
ISBN:  

9781501510489

ISBN 10:   1501510487
Pages:   209
Publication Date:   24 April 2015
Recommended Age:   College Graduate Student
Audience:   Professional and scholarly ,  Professional & Vocational ,  Professional & Vocational
Format:   Hardback
Publisher's Status:   Active
Availability:   Manufactured on demand  
We will order this item for you from a manufactured on demand supplier.

Table of Contents

1  Introduction     1.1 Proteins and Their Subcellular Locations     1.2 Why Computationally Predicting Protein Subcellular Localization?     1.3 Organization of The Thesis 2  Literature Review     2.1 Sequence-Based Methods     2.2 Knowledge-Based Methods     2.3 Limitations of Existing Methods 3  Legitimacy of Using Gene Ontology Information     3.1 Direct Table Lookup?     3.2 Only Using Cellular Component GO Terms?     3.3 Equivalent to Homologous Transfer?     3.4 More Reasons for Using GO Information 4  Single-Location Protein Subcellular Localization     4.1 GOASVM: Extracting GO from Gene Ontology Annotation Database     4.2 FusionSVM: Fusion of Gene Ontology and Homology-Based Features      4.3 Summary 5  From Single-Location to Multi-Location      5.1 Significance of Multi-Location Proteins     5.2 Multi-Label Classification      5.3 mGOASVM: A Predictor for Both Single- and Multi-Location Proteins     5.4 AD-SVM: An Adaptive-decision Multi-Label Predictor     5.5 mPLR-Loc: A Multi-Label Predictor Based on Penalized Logistic-          Regression       5.6 Summary  6  Mining Deeper on GO for Protein  Subcellular Localization     6.1 Related Work     6.2 SS-Loc: Using Semantic Similarity Over GO     6.3 HybridGO-Loc: Hybridizing GO Frequency and Semantic Similarity           Features     6.4 Summary 7  Ensemble Random Projection for Large-Scale Predictions     7.1 Related Work      7.2 RP-SVM: A Multi-Label Classifier with Ensemble Random Projection     7.3 R3P-Loc: A Predictor Based on Ridge Regression and Random           Projection     7.4 Summary  8  Experimental Setup     8.1 Prediction of Single-Label Proteins     8.2 Prediction of Multi-Label Proteins     8.3 Statistical Evaluation Methods     8.4 Summary 9  Results and Analysis     9.1 Performance of GOASVM     9.2 Performance of FusionSVM     9.3 Performance of mGOASVM     9.4 Performance of AD-SVM     9.5 Performance of mPLR-Loc     9.6 Performance of SS-Loc     9.7 Performance of HybridGO-Loc      9.8 Performance of Performance of RP-SVM     9.9 Performance of R3P-Loc     9.10 Comprehensive Comparison of Proposed Predictors     9.11 Summary 10  Discussions       10.1 Analysis of Single-label Predictors       10.2 Advantages of mGOASVM       10.3 Analysis for HybridGO-Loc       10.4 Analysis for RP-SVM       10.5 Comparing the Proposed Multi-Label Predictors       10.6 Summary 11  Conclusions A  Web-Servers for Protein  Subcellular Localization B  Proof of No Bias in LOOCV Bibliography    

Reviews

Author Information

Shibiao Wan, Man-Wai Mak, Hong Kong Polytechnic University, Hong Kong.

Tab Content 6

Author Website:  

Customer Reviews

Recent Reviews

No review item found!

Add your own review!

Countries Available

All regions