Pattern Recognition in Bioinformatics

Name: Pattern Recognition in Bioinformatics | 6th IAPR International Conference, PRIB 2011, Delft, The Netherlands, November 2-4, 2011, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

6th IAPR International Conference, PRIB 2011, Delft, The Netherlands, November 2-4, 2011, Proceedings

Marco Loog Lodewyk Wessels Marcel J.T. Reinders Dick de Ridder(Herausgeber*in)

Springer (Verlag)

Erschienen am 29. Oktober 2011

XII, 344 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-642-24855-9 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

7036
Preface
Organization
Table of Contents
Session 1: Clustering
A New Framework for Co-clustering of Gene Expression Data
Introduction
A New Generic Framework for Co-clustering
Background of Tensor Operations
The Optimization Model of the Co-clustering Problem
A Generic Algorithm for Co-clustering
Algorithm for Co-clustering 2D Matrix Data
Experimental Results
Implementation Details and Some Discussions
Testing Results Using Microarray Datasets
Testing Using 3D Synthesis Dataset
Summary and Future Works
References
Biclustering of Expression Microarray Data Using Affinity Propagation
Introduction
Background: Affinity Propagation
The Proposed Approach
Stability Criterion
Assembling Biclusters
Experimental Evaluation
Conclusions and Future Works
References
A Two-Way Bayesian Mixture Model for Clustering in Metagenomics
Introduction
Related Work
Methods
Bayesian Mixture of Poissons
Two-Way Bayesian Mixture of Poissons
Bayesian Mixture of Multinomials
Results
Conclusion
References
CRiSPy-CUDA: Computing Species Richness in 16S rRNA Pyrosequencing Datasets with CUDA
Introduction
PGA Approach and ESPRIT
CRiSPy
Parallel k-mer Distance Computation
Parallel Genetic Distance Computation
Space-Efficient Hierarchical Clustering
Results
Performance Comparison of k-mer Distance Computation
Performance Comparison of Genetic Distance Computation
Execution Time of CRiSPy Full Run
Assessment of Microbial Richness Estimation Accuracy by CRiSPy
Conclusion
References
Session 2: Biomarker Selection and Classification (1)
New Gene Subset Selection Approaches Based on Linear Separating Genes and Gene-Pairs
Introduction
Linear Separability of Gene Expression Datasets
Feature Ranking Criteria
LS-Pair Ranking Criterion
LS-Gene Ranking Criterion
Gene Subset Selection
Computational Experiments
Benchmark Datasets
Conclusion
References
Identification of Biomarkers for Prostate Cancer Prognosis Using a Novel Two-Step Cluster Analysis
Introduction
Theory and Method
Step 1: Unsupervised Cluster Analysis
Mixture Model of Gene Expression.
EM Algorithm for Cluster Analysis.
Step 2: Gene Identification Based on Correlation Analysis
Application
Simulation Study
Real Data Analysis
Discussion
References
Renal Cancer Cell Classification Using Generative Embeddings and Information Theoretic Kernels
Introduction
The Tissue Microarray (TMA) Pipeline
Tissue Micro Arrays
Image Normalization and Patching
Segmentation
Feature Extraction
The Proposed Nuclei Classification Scheme
Overview
Generative Model Training
Generative Embedding
Discriminative Classification
Experiments
One Model for Both Classes
One Model Per Class
Conclusions
References
Session 3: Network Inference and Analysis (1)
Integration of Epigenetic Data in Bayesian Network Modeling of Gene Regulatory Network
Introduction
Methods
Experiments and Results
Conclusion
Metabolic Pathway Inference from Time Series Data: A Non Iterative Approach
Introduction
Metabolic Network Reconstruction
Modeling Metabolic Interactions
Derivation of the Objective Function
Experiments with Artificial Data
Experiments with Flavonoid Data
Conclusions
Highlighting Metabolic Strategies Using Network Analysis over Strain Optimization Results
Introduction
Methods
Overall Workflow
Flux Balance Analysis
Strain Optimization
Solution Set Pre-processing
Network Representation and Simulation Filtering
Network Comparison
Exclusivity.
Decision points.
Inversions.
Variation Analysis
Experiments and Results
Case Study and Experimental Setup
Results and Discussion
Main Knockouts and Succinate Production.
dGDP Consumption.
Alternative L-Threonine Production.
Conclusions
References
Session 4: Biomarker Selection and Classification (2)
Wrapper- and Ensemble-Based Feature Subset Selection Methods for Biomarker Discovery in Targeted Metabolomics
Introduction
Background
State of the Art
Methods
Plasma Samples
Data Acquisition
Feature Subset Selection
Experimental Design
Results and Discussion
Benefit of Feature Subset Selection
Performance of Feature Subset Selection Procedures
Ensemble Method
Discriminative Potential of Compound Classes
Conclusions
References
Ensemble Logistic Regression for Feature Selection
Introduction
Feature Selection Methods
Regularized Logistic Regression
Ensemble Logistic Regression with Feature Resampling
Experiments
Microarray Datasets
Evaluation Metrics
Experimental Methodology
Results
Conclusion and Future Work
References
Gene Selection in Time-Series Gene Expression Data
Introduction
Time-Series Gene Expression Dataset
Methodology of Pipeline
Normalization of Micro-Array Data
Gene Expression Analysis
Swap Randomization
Test Statistic.
Null Distribution
p-Values
Experiments and Results
Swap Randomization and Convergence Analysis
Selection of Genes
Summary and Conclusions
References
Multi-task Drug Bioactivity Classification with Graph Labeling Ensembles
Introduction
Ensemble Learning with Max-Margin Conditional Random Field Models on Random Graphs
Learning Graph Labeling with MMCRF
Graph Generation for Cancer Cell Lines
Experiments
Data and Preprocessing
Compared Methods
Experiment Setup and Performance Measures
Results
Discussion
Conclusions
References
Session 5: Image Analysis (1)
A Bilinear Interpolation Based Approach for Optimizing Hematoxylin and Eosin Stained Microscopical Images
Introduction
The Method
Conclusion
References
Automatic Localization of Interest Points in Zebrafish Images with Tree-Based Methods
Context, Motivation, and Strategy
Methods
Extraction and Description of Subwindows
Model Construction Using Extremely Randomized Tree Ensembles
Prediction in Test Images
Related Work
Experiments
Datasets
Evaluation Protocols
Results and Observations
Conclusion and Future Work
References
Session 6: Biomarker Selection and Classification (3)
A New Gene Selection Method Based on Random Subspace Ensemble for Microarray Cancer Classification
Introduction
Diverse Accurate Feature Selection
Feature-Space Coverage
Feature Evaluation and Ranking
DAFS Algorithm
Experimental Results for Gene Expression Data
Dataset Description
DAFS Setup
Numerical Experiments
Conclusions
References
A Comparison on Score Spaces for Expression Microarray Data Classification
Introduction
Methodology
Probabilistic Latent Semantic Analysis
Generative Score-Spaces
Parameters Based Score Space
Random Variable Based Methods
Experimental Evaluation
Conclusions
Flux Measurement Selection in Metabolic Networks
Introduction
Related Work
Research Problem
Methods
RMEV-G: Reaction Minimizing Expected Volume Greedy
Experimental Analysis
Results
Conclusion and Discussion
Future Work
References
Session 7: Network Inference and Analysis (2)
Lagrangian Relaxation Applied to Sparse Global Network Alignment
Introduction
Preliminaries
Method
Solving Strategies
Experimental Evaluation
Edge-Correctness
GO Similarity
Conclusion
References
Stability of Inferring Gene Regulatory Structure with Dynamic Bayesian Networks
Introduction
Gene Regulatory Networks
Dynamic Bayesian Networks
Maximum Likelihood Estimate of the Structure
Structure Learning
Stability
Simulation of Gene Expression Time-Series
Stability of Estimation of Structure
Experiments and Results
Network Topology
Performance Evaluation
Accuracy.
Stability.
Conclusions
References
Integrating Protein Family Sequence Similarities with Gene Expression to Find Signature Gene Networks in Breast Cancer Metastasis
Introduction
Material and Methods
Data Description
Protein-Protein Sequence Similarity
Step 1.
Step 2.
Step 3.
Step 4.
Subnetworks Construction
Signature Concordance
Classification Procedure
Results and Discussion
Cross Study Prediction Evaluation
Functionally Coherent Subnetworks
Consistent Consensus Genes across the Datasets
Conclusion
References
Session 8: Sequence, Structure, and Interactions
Estimating the Class Posterior Probabilities in Protein Secondary Structure Prediction
Introduction
Multi-class Support Vector Machines
General Introduction
Dedication to Sequence-to-Structure Prediction
Structure-to-Structure Classifiers
Polytomous Logistic Regression
Linear Ensemble Methods
Multi-layer Perceptron
Experimental Results
Conclusions and Ongoing Research
References
Shape Matching by Localized Calculations of Quasi-Isometric Subsets, with Applications to the Comparison of Protein Binding Patches
Introduction
Comparing Proteins and Protein Complexes
Comparing Protein Binding Patches
Topological Encoding of Cells Complexes
Shelling a Cell Complex
Shelling Binding Patches of Protein Complexes: Outline
Shelling Protein Binding Patches: Detailed Algorithm
Comparison Algorithms
Constraints
Topological Comparison: TEDt
Geometric Comparison: Clique
Hybrid Approach: TEDg
Relation between the Approaches
Results: Performances and Scores
Discussion and Outlook
References
Using Kendall-t Meta-Bagging to Improve Protein-Protein Docking Predictions
Introduction
Methods and Data
Training Dataset
Voronoi Fingerprints and Learning Parameters
Learning Algorithms
Bagging
Finding a Median under the Kendall- Distance
Results
Ranking Hex Docking Solutions
Further Insight on Difficult Targets
Conclusion
References
PAAA: A Progressive Iterative Alignment Algorithm Based on Anchors
Introduction
Preliminaries
Algorithm
Time Complexity
An Illustrative Example
Experimental Study
Conclusions and Perspectives
References
Session 9: Image Analysis (2)
Heat Diffusion Based Dissimilarity Analysis for Schizophrenia Classification
Introduction
Shape Analysis by Heat Diffusion
Dissimilarities
Dissimilarity Measures
Dissimilarity Space
Random Subspace Method and Adaptation to Dissimilarity Computation
Dissimilarity Combination
Experiments
MRI Data Collection
Histogram Computation Using HKS
Experimental Methodology
Results
Conclusion
References
Epithelial Area Detection in Cytokeratin Microscopic Images Using MSER Segmentation in an Anisotropic Pyramid
Introduction
State of the Art
Aim of the Study
Image Enhancement
Crypt Outer Borders Detection
Anisotropic Diffusion Pyramid
MSER for Epithelial Area Detection
Crypts Separation and Lumen Detection
Crypts Separation
Lumen Detection
Results
Conclusions
References
Pattern Recognition in High-Content Cytomics Screens for Target Discovery - Case Studies in Endocytosis
Introduction
Methodology
Image Acquisition
Image Analysis
Data Analysis
Experimental Results
Dynamic Phenotype Stage
Phenotype Classification
Conclusions
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken