This book discusses the application of machine learning in genomics. Machine Learning offers ample opportunities for Big Data to be assimilated and comprehended effectively using different frameworks. Stratification, diagnosis, classification and survival predictions encompass the different health care regimes representing unique challenges for data pre-processing, model training, refinement of the systems with clinical implications. The book discusses different models for in-depth analysis of different conditions. Machine Learning techniques have revolutionized genomic analysis. Different chapters of the book describe the role of Artificial Intelligence in clinical and genomic diagnostics. It discusses how systems biology is exploited in identifying the genetic markers for drug discovery and disease identification. Myriad number of diseases whether be infectious, metabolic, cancer can be dealt in effectively which combines the different omics data for precision medicine. Major breakthroughs in the field would help reflect more new innovations which are at their pinnacle stage.
This book is useful for researchers in the fields of genomics, genetics, computational biology and bioinformatics.
Author(s): Shailza Singh
Publisher: Springer
Year: 2022
Language: English
Pages: 243
City: Singapore
Contents
About the Editor
1: Construction of Feedforward Multilayer Perceptron Model for Diagnosing Leishmaniasis Using Transcriptome Datasets and Cogni...
1.1 Introduction
1.2 Methodology
1.2.1 Collection and Processing of Transcriptome Dataset
1.2.2 Developing a Recurrent Neural Network
1.2.2.1 Feedforward Multilayer Perceptron Model
1.2.2.2 Calculation of Fitness of the Model
1.3 Results and Discussion
1.3.1 Feedforward Multilayer Perceptron Model
1.3.2 Fitness of the Model
1.3.2.1 Accuracy
1.3.2.2 Loss Function
1.3.2.3 Mean Square Error
1.3.3 Other Influencing Parameters of the Models´ Fitness
1.4 Conclusion
References
2: Big Data in Drug Discovery
2.1 Introduction
2.1.1 What Is Big Data?
2.1.2 Drug Discovery
2.2 Big Data in Drug Discovery
2.2.1 Big Data in Chemistry
2.2.1.1 Chemical Data and Physicochemical Properties
2.2.2 Big Data in Biology
2.2.2.1 Target Identification and Validation, Genomics, Proteomics, and Drug Repurposing
2.2.3 Big Data in the Pharmaceutical Research Focusing Medicinal Chemistry
2.3 Big Data Resources
2.3.1 Public Resources
2.3.1.1 PubChem
2.3.1.2 ChEMBL
2.3.1.3 BindingDB
2.3.1.4 ZINC Database
2.3.2 Proprietary Databases
2.3.3 Commercial Chemical Space
2.4 Data Analysis Tools
2.4.1 Artificial Intelligence
2.4.1.1 Machine Learning
2.4.1.2 Deep Learning
2.4.2 Example Using AI for Data Analysis in the Pharmaceutical Company
2.4.2.1 BenevolentAI
2.4.2.2 Atomwise
2.4.3 Programming and Scripting Tools for Data Analysis
2.4.3.1 Python
2.4.3.2 R Package
2.4.3.3 SAS
2.4.4 Example Using Programming Tools for Data Analysis
2.4.4.1 Exscientia
2.4.4.2 AstraZeneca
2.5 Drug Screening Platform
2.5.1 Types of HTS Screening Platform
2.5.2 Screening Platform in Pharmaceutical Industries
2.5.3 Commercially Available Screening Platform
2.6 Data Analysis in Drug Screening Platform
2.6.1 Case Studies of HTS Drug Screening Platform
2.6.1.1 Case Study 1: The Deconstructed Granuloma: A Complex High-Throughput Drug Screening Platform for the Discovery of Host...
2.6.1.2 Case Study 2: Drug-Screening Platform Based on the Contractility of Tissue-Engineered Muscle
2.6.1.3 Case Study 3: Development of a Drug Screening Platform Based on Engineered Heart Tissue
2.6.1.4 Case Study 4: Developing a Drug Screening Platform: MALDI-Mass Spectrometry Imaging of Paper-Based Cultures
2.6.1.5 Case Study 5: A Logical Network-Based Drug Screening Platform for Alzheimer´s Disease Representing Pathological Featur...
2.7 Conclusion and Future Perspective
References
3: An Overview of Databases and Tools for lncRNA Genomics Advancing Precision Medicine
3.1 Introduction
3.2 lncRNAs Analysis
3.2.1 Databases Harboring lncRNAs
3.2.1.1 General Databases for lncRNA Storage and Annotation
3.2.1.2 Databases for Long Noncoding RNA Expression
3.2.1.3 Specialized lncRNA Databases
3.2.2 Tools and Algorithms for lncRNA
3.3 Circular RNA Analyses
3.4 Co-Expression Regulatory Network Prediction
3.5 Conclusion and Future Aspects
References
4: Machine Learning in Genomics
4.1 Introduction
4.2 Analysis of Sequence Data
4.2.1 Raw Sequences
4.2.2 Variants
4.2.3 Metagenomics Data
4.3 Transcriptomics Data Analysis
4.4 Analysis of Epigenetic Modification Data
4.4.1 DNA Methylation Data
4.4.2 Histone Modifications
4.5 DNA Interactions
4.6 Integrating Multi-Omics Data for Analysis
4.7 Clinical Applications of ML Using Genomics Data
4.8 Drawbacks and Challenges
4.9 Future Scope
References
5: How Machine Learning Has Revolutionized the Field of Cancer Informatics?
5.1 Background
5.2 Machine Learning Algorithms
5.2.1 Supervised Learning
5.2.2 Unsupervised Learning
5.2.3 Reinforcement Learning
5.3 Artificial Neural Networks (ANNs)
5.4 Support Vector Machines (SVMs)
5.5 Decision Trees and Random Forests
5.6 Bayesian Networks
5.7 Applications of Machine Learning in Cancer Research: Case Studies
5.8 Machine Learning in Cancer Detection
5.8.1 Breast Cancer Detection Using Mammographs
5.8.2 Breast Cancer Detection Using Histopathology Images
5.9 Machine Learning in Cancer Susceptibility and Risk Assessment
5.10 Machine Learning in Cancer Recurrence Prediction
5.11 Conclusion
References
6: Connecting the Dots: Using Machine Learning to Forge Gene Regulatory Networks from Large Biological Datasets. At the Inters...
6.1 Introduction
6.2 Databases/Catalogues Covering GRN Information
6.3 Statistical Methods for GRN Construction
6.4 Computational Tools and Methods for GRN Inference
6.4.1 Supervised Algorithms
6.4.2 Unsupervised Algorithms
6.4.3 GRNs from the Time-Series Data
6.4.4 Feedforward Loops and Regulatory Networks
6.5 Conclusion and Limitations
References
7: Identification of Novel Noncoding RNAs in Plants by Big Data Analysis
7.1 Introduction
7.2 Different Kinds of ncRNAs in Plants
7.2.1 Circular RNA (circRNAs)
7.2.2 Linear ncRNAs
7.2.2.1 Small Nucleolar RNAs (snoRNAs)
7.2.2.2 Small ncRNAs
MicroRNAs (miRNAs)
Small Interfering RNA (siRNA)
tRNA-Derived Small RNA (tsRNA)
PIWI-Associated RNAs (piRNAs)
7.2.2.3 Long Noncoding RNA (lncRNAs)
7.3 Tools for Identification of ncRNAs
7.3.1 miRPlant
7.3.2 sRNA Toolbox
7.3.3 miRA
7.3.4 Semirna
7.3.5 Tapir
7.3.6 psRNATarget
7.3.7 MicroPC
7.3.8 C-mii
7.3.9 MTide
7.3.10 BioVLAB-MMIA-NGS
7.3.11 PhyloCSF
7.3.12 CPC
7.3.13 CNCI
7.3.14 CPAT
7.3.15 Deeplnc
7.3.16 spongeScan
7.3.17 RegRNA
7.3.18 PredcircRNA
7.3.19 CircCode
7.3.20 CircPlant
7.3.21 Circseq-Cup
7.3.22 PcircRNA_finder
7.3.23 AsmiR
7.3.24 miRkwood
7.3.25 Si-Fi
7.3.26 pssRNAit
7.4 Databases for ncRNAs
7.4.1 miRBase
7.4.2 Rfam
7.4.3 PmiRKB
7.4.4 PMRD
7.4.5 PlanTE-MIR
7.4.6 PlaNC-TE
7.4.7 miRTarBase
7.4.8 PASmiR
7.4.9 WMP
7.4.10 NONCODE
7.4.11 GREENC
7.4.12 PNRD
7.4.13 CANTATAdb
7.4.14 Plant snoRNA Database
7.4.15 ASRG
7.4.16 AtCircDB
7.4.17 PlantcircBase
7.4.18 PlantCircNet
7.4.19 CropCircDB
7.5 Conclusion
References
8: Artificial Intelligence in Biomedical Image Processing
8.1 Introduction
8.1.1 Medical Images
8.1.1.1 Radiological Images
8.1.2 Image Recognition vs. Image Processing
8.1.3 Computer-Assisted Image Processing
8.1.4 Medical Image Processing
8.1.4.1 Steps of Medical Image Processing
8.1.5 Image Informatics and Medical Image Informatics
8.1.6 Artificial Intelligence Assisted Image Processing
8.1.6.1 Advantages
8.1.6.2 Limitations
8.1.7 Role in Health Care
8.2 Processes/Tools in Image Processing
8.2.1 Artificial Intelligence in Biomedical Visualization
8.2.1.1 Vision Recognition by Computer
8.2.2 Deep Learning (DL) and Machine Learning (ML)
8.2.3 Image Processing Algorithms
8.2.3.1 Image Processing via Morphological Algorithm
8.2.3.2 Image Processing via Gaussian Algorithm
8.2.3.3 Image Processing Via Fourier Transform Algorithm
8.2.3.4 Image Processing via Edge Detection Algorithm
8.2.3.5 Image Processing via Wavelet Algorithm
8.2.3.6 Image Processing via Neural Network Algorithm
8.2.3.7 Contrast Enhancement Algorithm for Color Images
8.2.4 Neural Network Types
8.2.4.1 Convolutional Neural Network (CNN)
8.2.4.2 Convolutional (CONV) Layer
8.2.4.3 Pooling Layer (POOL)
8.2.4.4 Fully Connected (FC) Layer
8.2.5 Generative Adversarial Networks (GANs)
8.2.6 Medical Image Processing Tools
8.2.6.1 Visualization Toolkit (VTK)
8.2.6.2 Insight Toolkit (ITK)
8.2.6.3 FMRIB Software Library (FSL)
8.3 Applications of Image Processing
8.3.1 Digital Image Processing
8.3.1.1 Gamma-Ray Imaging
8.3.1.2 X-Ray Imaging
8.3.1.3 Ultraviolet Band Imaging
8.3.1.4 Visible and Infrared Bands Imaging
8.3.1.5 Microwave Band Imaging
8.3.2 Biomedical Imaging System
8.3.2.1 X-Ray
8.3.2.2 Magnetic Resonance Imaging (MRI)
8.3.2.3 Ultrasound Imaging
8.3.2.4 Computer Tomography (CT)
8.3.2.5 Endoscopy
Stereo Endoscope
8.3.2.6 Electrocardiography (ECG)
8.3.2.7 Positron Emission Tomography (PET)
8.4 Image Processing in Body Parts
8.4.1 Brain Imaging
8.4.2 Chest Imaging
8.4.3 Breast Imaging
8.4.4 Cardiac Imaging
8.4.5 Musculoskeletal Imaging
8.5 Image-Based Profiling in Drug Discovery
8.5.1 Phenotype Screening
8.5.2 High-Throughput Imaging
8.5.3 Clustering
8.5.4 MOA Profiling
8.5.5 Image-Based Profiling and Chemical Genetics
8.6 Conclusion
References
9: Artificial Intelligence and Its Application in Cardiovascular Disease Management
9.1 Introduction
9.2 Artificial Intelligence
9.3 Market Valuation of AI
9.4 Typology of AI
9.4.1 Classification Based on Functionality
9.4.1.1 Reactive Machines
9.4.1.2 Limited Memory
9.4.1.3 Theory of Mind
9.4.1.4 Self-Aware
9.4.2 Classification Based on Capability
9.4.2.1 Artificial Narrow Intelligence (ANI)
9.4.2.2 Artificial General Intelligence (AGI)
9.4.2.3 Artificial Super Intelligence (ASI)
9.5 Evolution of AI
9.6 Applications
9.6.1 Healthcare
9.7 Artificial Intelligence
9.7.1 Machine Learning
9.7.2 Deep Learning
9.7.2.1 Supervised Learning
Artificial Neural Network
Recurrent Neural Network
Convolution Neural Network
9.7.2.2 Unsupervised Learning
Autoencoders
Architecture of Autoencoders
9.7.3 Symbolic AI
9.7.4 Natural Language Processing
9.7.5 Reinforcement Learning
9.7.6 Cognitive Computing
9.7.7 Context-Aware Computing
9.8 Artificial Intelligence in the Healthcare Domain
9.8.1 Introduction
9.8.2 Market Valuation of AI in the Healthcare Domain
9.8.3 Pioneers in AI-Based Healthcare Domain
9.8.3.1 Microsoft Corporation
9.8.3.2 Intel
9.8.3.3 IBM
9.8.3.4 Amazon Web Services
9.8.3.5 Siemens Healthineers
9.8.3.6 General Electric
9.8.3.7 Google
9.8.3.8 Alibaba
9.8.3.9 Medtronic
9.8.3.10 Baidu´s Melody
9.8.4 Therapeutic Focus Based on AI
9.8.5 Focus on Cardiovascular Healthcare
9.8.5.1 Introduction on Cardiovascular Diseases
9.8.5.2 Statistics About CVD
9.8.5.3 Precision Medicine
9.8.5.4 Predictive Medicine
9.8.5.5 Preventive Medicine
9.8.5.6 Personalized Medicine
9.8.5.7 Diagnostic Tools
Echocardiography
Electrocardiography
Cardiac Imaging
Cardiac Magnetic Resonance Image
Cardiac Electrophysiology
9.8.5.8 Cardiac Resynchronization Therapy
9.8.5.9 Decision Support Tool
9.8.5.10 Models for Various CVD Assessment
9.8.5.11 Cardiac Transplantation
9.8.5.12 Clinical Predictions/Meta-Analysis
9.8.5.13 Robots Used in CVS/Chatbots
9.8.5.14 Interventional Procedure Assistance
9.8.5.15 Approved Medical Devices Developed Using AI
9.8.6 Drug Discovery and Development Using AI
9.9 Conclusion and Future Perspective
References
