Evolutionary Computation Machine Learning and Data Mining in Bioinformatics 2009th Edition by Clara Pizzuti, Marylyn Ritchie, Mario Giacobini ISBN 3642011837 9783642011832

Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics 2009th Edition by Clara Pizzuti, Marylyn D. Ritchie, Mario Giacobini – Ebook PDF Instant Download/Delivery. 3642011837, 978-3642011832
Full download Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics 2009th Edition after payment

Product details:

ISBN 10:    3642011837   
ISBN 13: 978-3642011832
Author:         Clara Pizzuti, Marylyn D. Ritchie, Mario Giacobini

Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics 2009th Table of contents:

EvoBIO Contributions

Association Study between Gene Expression and Multiple Relevant Phenotypes with Cluster Analysis

• Introduction: Overview of the study of gene expression relationships with various phenotypes using cluster analysis.
• Methods: Approaches for analyzing gene expression data, including linear regression and Bayesian modeling.
• Experimental Analysis: Simulated and real data study (mice) analysis to explore associations.
• Discussion: Insights into the gene-phenotype relationships.
• References: Citations of related works and methodologies used.

Gaussian Graphical Models to Infer Putative Genes Involved in Nitrogen Catabolite Repression in S. cerevisiae

• Introduction: Background on nitrogen catabolite repression (NCR) in yeast.
• Overview: Use of Gaussian Graphical Models (GGMs) to analyze the genetic factors involved in NCR.
• Results and Discussion: Prediction of relevant genes using GGMs with experimental performance measures.
• Conclusion: Summary of findings and their implications in understanding NCR.
• References: Relevant studies and data sources.

Chronic Rat Toxicity Prediction of Chemical Compounds Using Kernel Machines

• Introduction: Problem definition and importance of predicting toxicity.
• Methods: Use of Support Vector Regression (SVR) and kernel methods for toxicity prediction.
• Experimental Setup: Chronic toxicity data set, model evaluation, and tools used.
• Results and Conclusion: Insights into toxicity prediction and model performance.
• References: Relevant literature on kernel machines and toxicity prediction.

Simulating Evolution of Drosophila Melanogaster Ebony Mutants Using a Genetic Algorithm

• Introduction: Overview of the genetic simulation of D. melanogaster mutants.
• Methods: Genetic algorithms used to model mutations.
• Results: Simulation findings and evolutionary trends.
• Discussion and Conclusion: Interpretation of results and biological relevance.
• References: Relevant studies on genetic modeling and evolutionary simulations.

Microarray Biclustering: A Novel Memetic Approach Based on the PISA Platform

• Introduction: Background on microarray data analysis and biclustering methods.
• Methods: The PISA platform for biclustering using evolutionary algorithms.
• Results: Experimental analysis and performance evaluations.
• Conclusion: Summary of the effectiveness of the approach.
• References: Literature on biclustering and evolutionary algorithms in bioinformatics.

F-score with Pareto Front Analysis for Multiclass Gene Selection

• Introduction: Multiclass gene selection problem and the use of F-score for performance evaluation.
• Methods: Use of Pareto front analysis to select genes.
• Results: Experimental results, including data preprocessing and evaluation.
• Conclusion: Discussion on the importance of gene selection in bioinformatics.
• References: Studies related to gene selection and multiclass problems.

A Hierarchical Classification Ant Colony Algorithm for Predicting Gene Ontology Terms

• Introduction: The importance of predicting gene ontology (GO) terms for biological research.
• Methods: The proposed hierarchical classification algorithm based on ant colony optimization.
• Results: Computational performance and efficiency of the algorithm.
• Conclusion: Summary of findings and the impact on gene ontology term prediction.
• References: Citations of relevant work in gene ontology and machine learning.

Conquering the Needle-in-a-Haystack: How Correlated Input Variables Beneficially Alter the Fitness Landscape in Machine Learning Models

• Introduction: The challenge of correlated input variables and their influence on machine learning models.
• Methods: Analysis of artificial neural networks and the effect of linkage disequilibrium.
• Results: Insights into how correlated variables improve the fitness landscape.
• Discussion: Biological and computational interpretations of the results.
• References: Relevant research on neural networks and input variable correlations.

Optimal Use of Expert Knowledge in Ant Colony Optimization for the Analysis of Epistasis in Human Disease

• Introduction: The role of expert knowledge in optimizing ant colony algorithms for analyzing epistasis.
• Methods: Combining expert knowledge with genetic algorithms to enhance epistasis analysis.
• Results: Experimental validation using simulation data.
• Discussion: Evaluation of the effectiveness of the method for human disease studies.
• References: Literature on epistasis and optimization algorithms in bioinformatics.

On the Efficiency of Local Search Methods for the Molecular Docking Problem

• Introduction: Overview of molecular docking problems and local search methods.
• Methods: Use of evolutionary algorithms for molecular docking simulations.
• Results: Efficiency comparisons between local search methods and traditional docking approaches.
• Conclusion: Insights into the best approaches for molecular docking in computational biology.
• References: Related works on molecular docking and optimization methods.

A Comparison of Genetic Algorithms and Particle Swarm Optimization for Parameter Estimation in Stochastic Biochemical Systems

• Introduction: Exploring optimization methods like genetic algorithms and particle swarm optimization in biochemical modeling.
• Methods: Parameter estimation for biochemical reactions using these algorithms.
• Results: Comparative performance analysis.
• Discussion: Implications of algorithm choice for biochemical system modeling.
• References: Studies on optimization in stochastic biochemical systems.

Guidelines to Select Machine Learning Schemes for Classification of Biomedical Datasets

• Introduction: Challenges in selecting appropriate machine learning techniques for biomedical datasets.
• Methods: Overview of different classification schemes, classifiers, and preprocessing methods.
• Results: Evaluation of machine learning models on biomedical data.
• Conclusion: Guidelines on selecting the best machine learning schemes for biomedical classification tasks.
• References: Research on machine learning techniques for bioinformatics.

Evolutionary Approaches for Strain Optimization Using Dynamic Models under a Metabolic Engineering Perspective

• Introduction: Importance of evolutionary algorithms for optimizing microbial strains in metabolic engineering.
• Methods: Framework for dynamic model evolution and strain optimization.
• Results: Case study on E. coli and gene deletion scenarios.
• Conclusion: Summary of findings and their impact on metabolic engineering.
• References: Literature on strain optimization and metabolic models.

Clustering Metagenome Short Reads Using Weighted Proteins

• Introduction: Clustering metagenomic sequences using protein-based methods.
• Methods: Implementation of protein weight-based clustering for short metagenome reads.
• Results: Experimental evaluations with varying parameters.
• Conclusion: Future directions in metagenome data clustering.
• References: Relevant metagenomic clustering techniques.

A Memetic Algorithm for Phylogenetic Reconstruction with Maximum Parsimony

• Introduction: Phylogenetic tree reconstruction using a memetic algorithm.
• Methods: Detailed approach using the Hydra algorithm and its local search operations.
• Results: Performance evaluations and comparisons with standard methods.
• Conclusion: Insights into phylogenetic analysis and the advantages of memetic algorithms.
• References: Relevant studies in phylogenetics and evolutionary computation.

Validation of a Morphogenesis Model of Drosophila Early Development by a Multi-objective Evolutionary Approach

• Introduction: Use of a multi-objective evolutionary algorithm for validating a Drosophila morphogenesis model.
• Methods: Evolutionary optimization and model calibration.
• Results: Validation and analysis of the model’s early development.
• Conclusion: Biological significance and future directions in morphogenesis modeling.
• References: Studies on Drosophila development and optimization methods.

Refining Genetic Algorithm-Based Fuzzy Clustering through Supervised Learning for Unsupervised Cancer Data Analysis

• Introduction: Enhancement of fuzzy clustering with supervised learning for cancer data classification.
• Methods: Combining genetic algorithms with classifiers like neural networks and SVM.
• Results: Application to leukemia, colon cancer, and lymphoma datasets.
• Conclusion: Performance metrics and discussions on the effectiveness of this approach.
• References: Related works on cancer data analysis and fuzzy clustering.

People also search for Evolutionary Computation, Machine Learning and Data Mining in Bioinformatics 2009th:

automatic design of machine learning via evolutionary computation a survey
machine learning enabled globally guaranteed evolutionary computation
what is evolutionary computation
evolutionary algorithms machine learning
machine learning evolutionary