Statistical Modelling and Machine Learning Principles for Bioinformatics Techniques, Tools, and Applications

Description

This book discusses topics related to bioinformatics, statistics, and machine learning, presenting the latest research in various areas of bioinformatics. It also highlights the role of computing and machine learning in knowledge extraction from biological data, and how this knowledge can be applied in fields such as drug design, health supplements, gene therapy, proteomics and agriculture.   Preface Bioinformatics Protein Structure Prediction and Gene Expression Analysis Genomics and Proteomics Contents About the Editors Bioinformatics Introduction to Bioinformatics 1 Introduction 2 Bioinformatics: What Is It? 3 Importance of Bioinformatics 4 Emergence of Bioinformatics 5 Computational Biology and Bioinformatics: A Comparison 6 Computational Approaches to Biological Problems 7 Conclusion References Review About Bioinformatics, Databases, Sequence Alignment, Docking, and Drug Discovery 1 Bioinformatics and Databases 1.1 Bioinformatics in Animal Science 1.2 Genome Sequencing 1.3 Genome Assembly 2 Databases 2.1 Database of Gene and Nucleic Acid 2.2 RNA Specific Resources 2.3 Protein Databases 2.4 Databases on Mutations and Variations 2.5 Bioinformatics Analysis Tools 3 Docking and Drug Discovery 3.1 BLAST 3.2 FASTA 3.3 Drug Bank 3.4 Drug Approval Process in India 4 Conclusion References Machine Learning for Bioinformatics 1 Introduction 2 Machine Learning Techniques in Bioinformatics 2.1 Artificial Neural Network (ANN) in Bioinformatics 2.2 Decision Trees in Bioinformatics 2.3 Genetic Algorithms (GA) in Bioinformatics 3 Applying Artificial Neural Network in Bioinformatics: A Case Study 3.1 Designing ANN for Bioinformatics 3.2 ANN in Protein Bioinformatics 4 Research Issues Related to Machine Learning in Bioinformatics 4.1 Data Errors 4.2 Generative Versus Discriminative 4.3 Approximation Versus Explanation 4.4 Single Versus Multiple Methods 5 Conclusion References Impact of Machine Learning in Bioinformatics Research 1 Introduction 2 Evolution of Research in Bioinformatics 2.1 The Inception of Biological Database 2.2 Starting Point: Creation of Sequence Data 2.3 Analysis of Sequence Data 3 Case Study BLAST 3.1 BLAST Algorithm 4 Role of Machine Learning Technique 4.1 Supervised Learning 4.2 Unsupervised Learning 4.3 Feature Selection and Dimension Reduction 4.4 Dimension Reduction 4.5 Feature Selection 4.6 Machine Learning Approaches: Knowledge Discovery in Database 4.7 Machine Learning Approach: Decision Tree 4.8 Machine Learning Approaches: Genetic Algorithm 4.9 Machine Learning Approach: Clustering 5 Application of Machine Learning 5.1 Using Clustering Approach to Identify Patients’ Subtypes 5.2 Drug Repositioning Using Classification Approach 6 Case Study: Kipoi Utilizing Machine Learning Model for Genomics 7 Challenges of Machine Learning Application in Bioinformatics 7.1 Dirty Biological Database 7.2 Generative and Discriminative 7.3 Approximation and Explanation 7.4 Single or Multiple Methods 8 Conclusions References Text Mining in Bioinformatics 1 Introduction 2 Biomedical Application: Case Study 3 Conclusion References Open-Source Software Tools for Bioinformatics 1 Introduction 1.1 Open-Source Software Tools 1.2 Interoperability 1.3 Summary 2 Bioperl 2.1 Introduction to Bioperl 2.2 Why Bioperl? 2.3 What Can You Do with Bioperl? 2.4 Bioperl Installation 2.5 Sequence Object 3 Biopython 3.1 Introduction 3.2 Goals 3.3 Advantages 3.4 Biopython Installation 3.5 Sample Case Study 3.6 Sample Code for Sequencing 4 Conclusion References Protein Structure Prediction and Gene Expression Analysis A Study on Protein Structure Prediction 1 Introduction 2 Protein Structure Prediction 2.1 Comparative Modelling 2.2 Threading 2.3 Ab Initio Prediction 3 Homology Modelling 3.1 Template Recognition and Initial Alignment 4 Loop Modelling 5 Use Case 6 Conclusion References Computational Methods Used in Prediction of Protein Structure 1 Introduction 2 Computational Methods for Protein Structure Prediction 2.1 Homology Modelling Techniques 2.2 Protein Threading 2.3 Ab Initio Modelling 2.4 CASP 3 Conclusion References Computational Methods for Inference of Gene Regulatory Networks from Gene Expression Data 1 Introduction 2 Gene Regulatory Networks 3 Computational Approaches for Construction of Gene Regulatory Networks 3.1 Ordinary Differential Equations 3.2 Neural Networks Method 3.3 Boolean Network-Based Methods 3.4 Bayesian Network-Based Methods 4 Conclusion References Machine-Learning Algorithms for Feature Selection from Gene Expression Data 1 Introduction 2 Gene Expression Data 3 Feature Selection 3.1 A Basic Algorithm for Feature Selection 4 Fitness Measures of a Feature 5 Conclusion References Genomics and Proteomics Unsupervised Techniques in Genomics 1 Introduction 1.1 Machine Learning in Bioinformatics [2] 2 Unsupervised Techniques in Bioinformatics [3] 2.1 Hierarchical Clustering [4, 5] 2.2 Partitional Clustering with Respect to Genomics 3 Hierarchical Clustering with Respect to Genomics [8] 3.1 Advantages of Hierarchical Clustering 3.2 Case Study 1: Charting Evolution Through Phylogenetic Trees 3.3 Case Study 2: Use of Hierarchical Clustering and Cluster Validation Indices for Analysis of Genetic Association [20] 4 Conclusion References Supervised Techniques in Proteomics 1 Introduction 2 Scope of Data and Machine Learning in Proteomics 3 Machine Learning in Proteomics 3.1 Proteomic Dataset 3.2 Sample Datasets Available for Proteomics 3.3 Data Preprocessing Algorithms 3.4 Dimension and Feature Subset Selection 3.5 Protein Classification 4 Supervised Algorithms in Proteomics 4.1 Decision Trees 4.2 Support Vector Machine 4.3 Random Forest 4.4 Logistic Regression 4.5 K-Nearest Neighbor 4.6 Classification Trees 5 Applications of Supervised Learning Algorithms in Proteomics 5.1 Proteomic Mass Spectra Classification Using Decision Tree Technique [17] 5.2 Distance Metric Learning and Support Vector Machine for Classification of Mass Spectrometry Proteomics Data [19] 6 Conclusion References Visualizing Codon Usage Within and Across Genomes: Concepts and Tools 1 Introduction 2 Genetic Code 2.1 Canonical Genetic Code and Mechanism of Its Realization 2.2 Visual Representations of the Genetic Code: Tables, Wheels, Hypercubes 2.3 Modeling Genetic Codes: What Is Learned from Massive Codon Reassignments in Silico 3 Estimating and Visualizing k-mer Occurrence in Genomic Sequences 3.1 Overview of the Most Popular Tools 3.2 Unmet Opportunities 4 Codon Indices 4.1 Definition and Diversity of Codon Bias Indices 4.2 Biological Significance of Several Popular Codon Indices 4.3 Online Applications and Databases to Calculate and Visualize Codon Indices 4.4 Future Directions 5 Codon Context 5.1 Cases and Reasons for Nonrandom Codon Co-occurrence 5.2 Anaconda—Software to Visualize Codon Pairs 5.3 Codon Utilization Tool (CUT)—A Database of k-Codon Usage for Yeast, Rat and Mice 6 Synonymous Codon Usage Bias (CUB) 6.1 CUB Types and Plausible Biological Reasons 6.2 Visualizing CUB Between and Within Genes 7 Codon Substitution Models (CSMs) 7.1 Basic Concept 7.2 Diversity of CSMs 7.3 Simulation of Codon Substitution Patterns 7.4 Approaches Toward Visual Representation of CSMs 8 Identification and Visualization of Selection Forces Acting on Coding Sequences 8.1 Molecular Evolution at the Codon Level: A Brief Introduction 8.2 Tools for Visual Representation of Selective Pressure on Protein-Coding Sequences 9 Outlook References Single-Cell Multiomics: Dissecting Cancer 1 Introduction to Tumor Ecosystem and Single-Cell Analysis 1.1 Major Components of Tumor Microenvironment and Their Role in Carcinogenesis 1.2 Conventional Sequencing Approaches and Their Limitation to Characterize TME 1.3 Single-Cell Sequencing Techniques and TME 2 Single-Cell omics 2.1 Single-Cell Genomics 2.2 Single-Cell Epigenomics 2.3 Single-Cell Transcriptomics 3 Cancer: Dissecting Tumor Heterogeneity 3.1 Multiregion Sequencing and Tumor Heterogeneity 3.2 Clonal Expansion Models 4 Single-Cell Analysis: Drug Resistance Mechanisms 4.1 Mechanisms of Drug Resistance 4.2 Single-Cell Genomics and Transcriptomics to the Rescue of Drug Resistance 5 Circulating Tumor Cells: Significance of Single-Cell Analysis 6 Limitations and Future Directions References