Applications of Fuzzy Logic in Bioinformatics

The following sections are included:

• Foreword

• Preface

• Contents

The following sections are included:

• What Is Bioinformatics

• A Brief History of Bioinformatics

• Scope of Bioinformatics
  • Data interpretation in high-throughput technologies
  • Data management and computational infrastructure
  • Discovery from data mining
  • Prediction
  • Computational design
  • Modeling

• Major Challenges in Bioinformatics

• Bioinformatics and Computer Science

The following sections are included:

• Where Does Fuzzy Logic Fit in Computational Science?

• Why Do We Need to Use Fuzziness in Biology?

• Brief History of the Field

• Fuzzy Membership Functions and Operators
  • Membership functions
  • Basic fuzzy set operators
  • Compensatory operators

• Fuzzy Relations and Fuzzy Logic Inference

• Fuzzy Clustering
  • Fuzzy C-Means
  • Extension to fuzzy C-Means
  • Possibilistic C-Means (PCM)

• Fuzzy K-Nearest Neighbors

• Fuzzy Measures and Fuzzy Integrals
  • Fuzzy measures
  • Fuzzy integrals

• Summary and Final Thoughts

The following sections are included:

• Introduction

• Definition of Ontology-Based Similarity

• Set-Based Similarity Measure
  • Pair-wise aggregation
  • Bag of words similarities

• Fuzzy Measure Similarity

• Fuzzy Measure Similarity for Augmented Sets of Ontology Objects

• Choquet Fuzzy Integral Similarity Measure

• Examples and Applications of Fuzzy Measure Similarity Using GO Terms
  • Lymphoma case study
  • Gene clustering using Gene Ontology annotations
  • Gene summarization using Gene Ontology terms

• Ontology Similarity in Data Mining

• Discussion and Summary

The following sections are included:

• Introduction

• Protein Secondary Structure Prediction

• Protein Solvent Accessibility Prediction

• Protein Structure Matching Using Fuzzy Alignments

• Protein Similarity Calculation Using Fuzzy Contact Maps

• Protein Structure Class Classification

• Summary

The following sections are included:

• Introduction
  • Microarray data description
  • Microarray processing algorithms for gene selection and patient classification
  • Microarray processing algorithms for gene regulatory network discovery

• Clustering Algorithms
  • (Dis)similarity measures for microarray data
  • Fuzzy C-means (FCM)
  • Relational fuzzy C-means
  • Fuzzy co-clustering algorithms

• Inferring Gene Networks Using Fuzzy Rule Systems

• Discussion and Summary

The following sections are included:

• Overview

• Applications in Biological Sequence Analyses
  • Protein sequence comparison
  • Application in sequence family classification
  • Application in motif identification
  • Application in protein subcellular localization prediction
  • Genomic structure prediction

• Application in Computational Proteomics
  • Electrophoresis analysis
  • Protein identification through mass-spec

• Application in Drug Design

• Discussion and Summary

In this book, we introduced fundamentals of fuzzy set theory and fuzzy logic and their major applications in bioinformatics, including similarities in ontologies, protein structure prediction and analyses, microarray data analysis, and others. We demonstrated that fuzzy concepts and methods fit various bioinformatics problems both for representing the underlying biological mechanisms and for applying fuzzy methods as techniques for analyses and predictions. Many biological properties and concepts are fundamentally fuzzy. Fuzzy methods do not require a precise underlying model, which is often difficult to obtain in bioinformatics problems. In some of the bioinformatics applications introduced in this book, fuzzy methods are more suitable than crisp ones. In other cases, both crisp and fuzzy approaches can apply. More systematic comparisons using sizable benchmarks to compare between crisp and fuzzy methods are needed…

The following sections are included:

• Appendix I: Fundamental Biological Concepts

• Appendix II: Online Resources

• Bibliography

• Index