Advanced AI Techniques and Applications in Bioinformatics (Smart and Intelligent Computing in Engineering)

Cover
Half Title
Series Page
Title Page
Copyright Page
Table of Contents
Contributors
Editors
Chapter 1 An Artificial Intelligence-based Expert System for the Initial Screening of COVID-19
1.1 Introduction
1.2 Review of Literature
1.3 Material and Method
1.3.1 Hierarchical Fuzzy System
1.3.2 Methodology
1.4 Results
1.4.1 Fuzzy Inference System
1.4.2 Membership Functions
1.4.3 Rule Editor
1.4.4 Fuzzification and Defuzzification
1.4.5 Rule Viewer
1.4.6 Surface Viewer
1.4.7 Graphical User Interface
1.5 Conclusion
Bibliography
Chapter 2 An Insight into the Potential Role of Artificial Intelligence in Bioinformatics
2.1 Introduction
2.2 Artificial Intelligence
2.2.1 Objectives of AI
2.3 Need for Integration of AI and Bioinformatics
2.4 Application of AI in Bioinformatics
2.4.1 Data and Knowledge Management
2.4.2 Information Extraction in Biological Literature
2.4.3 Gene and Noncoding RNA Prediction
2.4.4 Protein Structure Prediction
2.4.5 Evolutionary Studies
2.4.6 Drug Discovery
2.4.7 Vaccine Development
2.5 Conclusion and Future Prospects
Bibliography
Chapter 3 AI-Based Natural Language Processing for the Generation of Meaningful Information Electronic Health Record (EHR) Data
3.1 Introduction
3.2 Related Work
3.3 Artificial Intelligence
3.4 Machine Learning Overview
3.4.1 Approaches to Machine Learning
3.5 Deep Learning Overview
3.5.1 Multi-Layer Perceptron (MLP)
3.5.2 Convolutional Neural Networks (CNN)
3.5.3 Recurrent Neural Networks
3.5.4 Auto Encoders (AE)
3.5.5 Restricted Boltzmann Machine (RBM)
3.6 Natural Language Processing (NLP)
3.7 Electronic Health Record Systems (EHR)
3.8 Deep Learning-Based EHR
3.8.1 EHR Information Extraction in Deep Learning
3.8.1.1 Concept of Single Extraction
3.8.1.2 Extraction of Temporal Event
3.8.1.3 Relation of Extraction
3.8.1.4 Expansion of Abbreviation
3.9 Representation of Learning in EHR
3.10 Methods of Evaluation for EHR Representation Learning
3.10.1 Outcome Prediction in EHR Representation Learning
3.11 The Case for NLP Systems as an EHR-Based Clinical Research Tool
3.11.1 Use Cases for NLP System in Asthma Research
3.12 Implications of NLP for EHR Based on Clinical Research and Care
3.13 Conclusion and Future Directions
Bibliography
Chapter 4 AI and Genomes for Decisions Regarding the Expression of Genes
4.1 Introduction to Artificial Intelligence (AI)
4.2 AI in Clinical Genomics
4.2.1 Variant Calling
4.2.2 Variant Classification and Annotation of Genomes
4.2.2.1 Coding Mutants/Variants
4.2.2.2 Non-Coding Mutants/Variants
4.3 AI in Gene Expression Data Analysis
4.3.1 Dimensionality Reduction
4.3.1.1 Feature Extraction
4.3.1.2 Feature Selection
4.3.2 Clustering
4.3.3 Bayesian Networks
4.4 Conclusion
Bibliography
Chapter 5 Implementation of Donor Recognition and Selection for Bioinformatics Blood Bank Application
5.1 Introduction
5.1.1 About Software Application Development
5.1.2 About the Blood Bank at JPMC
5.1.2.1 Process for Blood Collection
5.1.2.2 Process for Blood Issuance
5.1.3 Biometrics-AI application
5.1.4 What Is Fingerprinting
5.1.5 Problem Statement
5.2 Literature Review
5.2.1 Data Collections and Interviews
5.2.1.1 Blood Compatibility
5.3 Methodology
5.3.1 Bioinformatics Blood Bank Application Framework
5.3.2 System Analysis
5.3.3 Gathering Information
5.3.3.1 Observation
5.3.3.2 Record Review
5.3.4 System Design
5.3.5 Software Environment
5.3.6 AI-Software Application Platform
5.3.7 Database Management System (DBMS)
5.3.8 Reporting Environment
5.3.8.1 Crystal Reports
5.3.8.2 SQL Server Reporting Services (SSRS)
5.3.9 Hardware and Software Environment
5.3.10 System Development
5.3.11 Database Design
5.3.12 Alpha Testing
5.3.13 Beta Testing
5.3.14 Test Deliverables
5.4 Result and Discussion
5.4.1 Relationships
5.4.2 Normalization
5.4.3 Code Design
5.5 Conclusion
5.5.1 Implementation and Evaluation
5.5.2 Results
5.5.3 Limitations
5.5.4 Conclusion
5.5.5 Extensibility
Bibliography
Appendix
Application Process Flow
Chapter 6 Deep Learning Techniques for miRNA Sequence Analysis
6.1 Introduction
6.1.1 Biogenesis of miRNA
6.1.2 Biology behind miRNA-Target (mRNA) Interactions
6.2 miRNA Sequence Analysis
6.3 Deep Learning: Conceptual Overview
6.3.1 Deep Neural Networks (DNNs)
6.3.2 Convolutional Neural Networks (CNNs)
6.3.3 Autoencoders
6.3.4 Recurrent Neural Networks (RNNs)
6.3.5 Long Short-Term Memory (LSTM)
6.4 Deep Learning: Applications for Pre-miRNA Identification
6.5 Deep Learning: Applications for miRNA Target Prediction
6.6 Critical Observations and Future Directions
6.7 Conclusion
Bibliography
Chapter 7 Role of Machine Intelligence in Cancer Drug Discovery and Development
7.1 Introduction
7.2 Artificial Intelligence (AI), Machine Learning (ML), and Deep Learning (DL) in Drug Discovery and Development
7.3 Challenges to Overcome
7.4 Future Prospects and Conclusion
Abbreviations
Bibliography
Chapter 8 Genome and Gene Editing by Artificial Intelligence Programs
8.1 Introduction
8.2 Genome Sequencing and Editing
8.2.1 The Gene-Editing Opportunities and Threats
8.3 Personalized Therapy and Life-Saving Services in the Context of Genome Editing
8.3.1 Genome Editing Initiative and Pharmaceuticals Implementation for Designing Drugs
8.4 CRISPR and Genome Editing
8.4.1 Genome Editing for the Next Generation in the Context of Medicine
8.5 Epigenetic and Germline Editing Positions
8.6 Natural Science in the Context of Artificial Intelligence Platform
8.7 Optimization of Human Bio-Machinery
8.8 Genomics Is Revolutionized by Artificial Intelligence
8.9 Artificial Intelligence Captaincy and Frontiers for the Direct Competitors of Genomics
8.10 Artificial Intelligence and Gene Editing Mechanisms
8.11 Scientists Used AI to Improve Gene-Editing Accuracy
8.11.1 Gene Editing and Biomedical Engineering Systems
8.11.2 Training Models for Gene Editing in the Context of Machine Learning
8.11.3 Off-Target Scores
8.11.4 End-to-End Guide Design
8.12 Efficient Genome Editing and the Optimization of Humans’ Health
8.13 Further Research and Development for Gene Editing with AI
8.13.1 Regulatory Considerations of Gene Editing and Artificial
Intelligence
8.14 Policies and Recommendations of Genome Editing with AI
8.15 Conclusion
8.16 Future Prospects of AI
Bibliography
Chapter 9 Artificial Neural Network (ANN) Techniques in Solving the Protein Folding Problem
9.1 Introduction
9.2 Role of Molten Globules in Protein Folding
9.3 Importance of Protein Folding Studies
9.4 Concept of Artificial Neural Networks
9.5 Criteria and Evaluation of Applications of ANN in the Protein Folding Problem
9.6 Bio-Inspired Optimization Algorithms that Can Be Used for Protein Folding Study in Association with ANN
9.7 Implementation of Artificial Neural Network Methods in Protein Folding Studies
9.8 Limitations of Current Protein Folding Prediction Algorithms
9.9 Conclusion
Bibliography
Chapter 10 Application of Machine Learning and Molecular Modeling in Drug Discovery and Cheminformatics
10.1 Introduction
10.2 Machine Learning Methods in Cheminformatics
10.2.1 Machine Learning Platforms
10.2.2 Representation of Small Molecules
10.2.3 Training Set Creation
10.2.4 Model Evaluation Methods
10.2.5 Model Evaluation Metrics
10.2.6 Feature Reduction
10.3 Molecular Modeling Methods in Cheminformatics
10.3.1 Virtual Screening
10.3.2 Pharmacophore Modeling
10.3.3 Molecular Docking
10.3.4 Molecular Simulation Approach to Drug Screening
10.4 Conclusion and Future Directions
Bibliography
Chapter 11 Role of Advanced Artificial Intelligence Techniques in Bioinformatics
11.1 Introduction
11.2 Bioinformatics: Analyzing Life Data at the Molecular Level
11.2.1 DNA
11.2.2 RNA
11.2.3 Proteins
11.2.4 Glycans
11.3 Application of AI in Bioinformatics
11.4 Symbolic Machine Learning
11.4.1 Nearest Neighbor Approaches in Bioinformatics
11.4.2 Application in Viral Protease Cleavage Prediction
11.5 Neural Networks in Bioinformatics
11.6 Evolutionary Computation in Bioinformatics
11.7 Deep Learning in Informatics
11.8 Future Trends
11.9 Conclusion
Bibliography
Chapter 12 A Bioinformatics Perspective on Artificial Intelligence in Healthcare and Diagnosis: Applications, Implications, and Limitations
12.1 Introduction
12.2 The Data Overload
12.3 Big Healthcare Data
12.3.1 Big Data from Electronic Health Records
12.3.2 Big Data from Omics
12.3.3 Big Data from Medical Images
12.4 Data Preprocess and Data Integration
12.5 Data Exploration
12.5.1 Artificial Intelligence in Clinical Diagnostics
12.5.2 Artificial Intelligence in EHR-Based Diagnostics
12.5.3 Artificial Intelligence in Image-Based Clinical Diagnostics
12.5.4 Artificial Intelligence in Genomics-Based Clinical Diagnostics
12.6 Machine Learning in Cancer Prognosis
12.7 Limitations of Artificial Intelligence in Healthcare
12.7.1 Data Dependency and Inconsistent Data
12.7.2 Infrastructure Requirements
12.7.3 Data Privacy and Security
12.8 Discussion
Bibliography
Chapter 13 Accelerating Translational Medical Research by Leveraging Artificial Intelligence: Digital Healthcare
13.1 Introduction
13.1.1 Origin of Artificial Intelligence
13.1.2 A.I. and Big Data
13.1.3 Optimizing the Machine–Human Interface
13.1.4 Role of Artificial Intelligence in Clinical Research
13.1.5 The Core Elements of Smart Healthcare Communities (S.H.C)
13.2 Related Study
13.2.1 Problem Statement
13.2.2 Technology Support: Proposed Solution
13.2.3 Research Challenges/Gaps and Infrastructure Requirements
13.3 Methodology: Phases Involved in the Adoption of A.I. for Translation Research
13.4 Approved Proprietary A.I. Algorithms
13.5 Digital Transformation and Interoperability
13.6 Limitations and Future Perspectives
13.7 Key-Points Drawn
13.8 Conclusion
Bibliography
Index