Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics

Name: Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics | 9th European Conference, EvoBIO 2011, Torino, Italy, April 27-29, 2011, Proceedings
Brand: Springer
Price: 53.49 EUR
Availability: OnlineOnly

9th European Conference, EvoBIO 2011, Torino, Italy, April 27-29, 2011, Proceedings

Clara Pizzuti Marylyn D. Ritchie Mario Giacobini(Herausgeber*in)

Springer (Verlag)

Erschienen am 27. April 2011

X, 183 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-642-20389-3 (ISBN)

53,49 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Title
Preface
Organization
Table of Contents
Effect of Using Varying Negative Examples in Transcription Factor Binding Site Predictions
Introduction
Background
Description of Data
Genomic Data
Problems with the Data and Solutions
Methods
Pre-processing: Preparing Training and Test Set
The Classifier and Its Performance Measures
Post-processing (Filtering)
Cross-Validation
Results and Discussion
Experiment 1- Using Negative Examples Sequences Not Annotated as TFBSs
Experiment 2- Replacing Negative Examples with Distal Negative Examples
Experiment 3- Replacing Negative Examples with Randomized Negative Examples
Conclusion
References
A New Evolutionary Gene Regulatory Network Reverse Engineering Tool
Introduction
The Proposed Framework: GRNGen
The IRMA Network
Experiments
Conclusions and Future Work
References
ML-Consensus: A General Consensus Model for Variable-Length Transcription Factor Binding Sites
Introduction
ML-Consensus
Basic Development
Incorporating Information Content and Pairwise Correlation in Scoring
Using Multiple Consensus for One Transcription Factor
Using a Sorting-Based Heuristic Alignment
Methods
Input
Training and Testing
Plotting ROC Curves for Configurations
Statistical Significance of Performance
Results and Discussion
Effect of IC and PS
Effect of Multiple Consensus
Effect of Alignment
Conclusion
References
Applying Linear Models to Learn Regulation Programs in a Transcription Regulatory Module Network
Introduction
Inferring Regulatory Relationships in Module Networks by Linear Models
Extracting the Critical Contrast of a Condition Clustering
Using Moderated t-Statistics to Select Differentially Expressed Transcription Factors
The Regulatory Score for Assigning a Transcription Factor to a Module
Experimental Results and Discussion
Dataset and Validation Reference Database
Results for Regulation of Nitrogen Utilization
Linear Model versus LeMoNe in the NCR Process
Results over the Entire Yeast Stress Dataset
Conclusion and Future Works
References
ATHENA Optimization: The Effect of Initial Parameter Settings across Different Genetic Models
Introduction
Epistasis in Complex Human Disease
Optimization of Neural Networks and Symbolic Regression Formulas
Methods
Data Simulation
Data Analysis
Results
Discussion
References
Validating a Threshold-Based Boolean Model of Regulatory Networks on a Biological Organism
Introduction
Threshold-Based Additive Boolean Update Function
A Regulatory Network with Defined Boolean Update Functions
Simulations and Results
Determining the ABA Model's Regime
Determining the ADA Update Function's Critical Threshold Value
Analyzing the Overlap of the Different Update Functions
Conclusions and Future Work
References
A Nearest Neighbour-Based Approach for Viral Protein Structure Prediction
Introduction
Methods
Definition of Protein Distance Map
Training Phase
Prediction of Protein Distance Maps
Evaluation of the Efficiency
Experimentation and Results
Conclusions and Future Work
References
Annotated Stochastic Context Free Grammars for Analysis and Synthesis of Proteins
Introduction
Annotated Context Free Grammars
n-gram Bayesian Text Classifier for Protein Sequences
Annotated Stochastic Context Free Grammars
Clustering Techniques
Quality Threshold Clustering
Co-Clustering
Frog AMP Analysis
Data
ACFG Results
ASCFG Results
Conclusions
References
Finding Motifs in DNA Sequences Applying a Multiobjective Artificial Bee Colony (MOABC) Algorithm
Introduction
Related Work
Motif Discovery Problem
Problem Formulation
Example
Multiobjective Artificial Bee Colony Algorithm
ABC Features
Implementation Details
Experimental Results
Comparisons with Other Authors
Conclusions
References
An Evolutionary Approach for Protein Contact Map Prediction
Introduction
Methodology
Statistical Analysis
Encoding
Fitness Function
Genetic Operators
Experiments and Results
Conclusions and Future Work
References
Multi-Neighborhood Search for Discrimination of Signal Peptides and Transmembrane Segments
Introduction
Local Search for Modeling Amino Acid Insertion Curves
Biological Knowledge
Local Search for in Silico Determining the Curves
Benchmark Dataset and Representation of the Data
Construction of a Benchmark Dataset: SWP-v2
Influence of TM Segment Representation
Statistical Data Analysis
Evaluation on Other Test Datasets
New Search Space of Insertion Indexes for Amino Acids
Principle
Influence of the Initial Scale
Multi-Neighborhood Search
Neighborhoods
Move Strategy and Multi-Neighborhood Exploration
Experiments
Conclusion
References
Approximation of Graph Kernel Similarities for Chemical Graphs by Kernel Principal Component Analysis
Introduction
Materials and Methods
Kernels for Chemical Data Mining
Kernel Principal Component Analysis
Data Mining with Kernel PCA Vectors
Experimental Setup
Results
Discussion and Conclusion
References
Posters
Experimental Approach for Bacterial Strains Characterization
Introduction
Problem Study
Resolution Methods
Experimental Results
Conclusion
References
Do Diseases Spreading on Bipartite Networks Have Some Evolutionary Advantage?
Introduction
Epidemiological Network Models
Bipartite Networks
Pathogen Spreading on Networks: The Importance of Being Bipartite
Conclusions and Future Works
References
Genetic Algorithm Optimization of Force Field Parameters: Application to a Coarse-Grained Model of RNA
Introduction
Optimization Problem
Genetic Algorithm Approach
Computations
Conclusions and Future Work
References
A Decision Tree-Based Method for Protein Contact Map Prediction
Introduction
Materials and Methods
Data Bases
Contact Maps Definition
Model Architecture
Evaluation of the Efficiency
Results
Conclusions
References
A Comparison of Machine Learning Methods for the Prediction of Breast Cancer
Introduction
Methods
Data
Tools, Techniques and Parameters
Results and Discussion
Quality Assessment
Interpretability of Solutions and Feature Selection
Conclusions and Future Work
References
An Automatic Identification and ResolutionSystem for Protein-Related Abbreviations in Scientific Papers
Introduction
Related Work
Abbreviation Identification and Resolution
Identification Phase
Resolution Phase
Experimental Results
Conclusions
References
Protein Complex Discovery from Protein Interaction Network with High False-Positive Rate
Introduction
Method
Data Description
GECSS(Gene Expression Condition Set Similarity)
Algorithm
Experimental Results
Conclusion
References
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken