Handbook of Machine Learning Applications for Genomics

Preface
Contents
Multiomics Data Analysis of Cancers Using Tensor Decomposition and Principal Component Analysis Based Unsupervised Feature Extraction
	1 Introduction
	2 Integrated Analysis of SNP and DNA Methylation
	3 Integrated Analysis of microRNA, mRNA and Metabolome
	4 Integrated Analysis of mRNA and miRNA of Kidney Cancer Using TD Bases Unsupervised FE
	References
Machine Learning for Protein Engineering
	1 Applying Machine Learning in Protein Engineering
		1.1 Formulate a Question
		1.2 Design an Experiment
		1.3 Curate the Dataset
		1.4 Pick and Train a Model
		1.5 Interpret the Results
	2 Conclusion
	References
Statistical Relational Learning for Genomics Applications: A State-of-the-Art Review
	1 Introduction
	2 Background and Notation
		2.1 Probabilistic Graphical Models
		2.2 Bayesian Networks
	3 Statistical Learning Relational Models
		3.1 Probabilistic Relational Models
		3.2 Relational Dependency Network
		3.3 Relational Markov Networks
	4 SRL in Genomics—Problems and Applications
		4.1 SRL Problems in Genomics
		4.2 SRL Applications in Genomics
	5 Conclusion
	References
A Study of Gene Characteristics and Their Applications Using Deep Learning
	1 Introduction
	2 Deep Learning Techniques for Gene Clustering
		2.1 Gene Clustering
		2.2 Autoencoders and Novel Techniques for Gene Clustering
		2.3 HeMI++ Algorithm for Sensible Clusters [19]
	3 DNA Sequencing Using RNN
		3.1 Applications of DNA Sequencing
		3.2 Latest Advances in DNA Sequences Using Deep Learning
		3.3 Future Scope
	4 Deep Learning for Repositioning of Drug and Pharmacogenomics
		4.1 Applications of Drug Repositioning
		4.2 Novel Deep Learning Methods for Drug Repositioning
	5 Future Scopes
	6 Conclusions
	References
Computational Biology in the Lens of CNN
	1 Introduction
	2 Deep Learning for Computational Biology
		2.1 What is Computational Biology?
		2.2 Applications of Deep Learning
		2.3 Novel Applications in Convolutional Neural Networks
		2.4 Deep Learning for Biological Imaging
	3 CNN Model to Analyze Gene Expressions Images
		3.1 Gene Expressions
		3.2 Convolution Neural Networks (CNN)
		3.3 Why Deep Learning on Gene Expression Images
		3.4 Data Source and Preprocessing
		3.5 Models [44]
		3.6 Stack Autoencoders Along with CNN [45]
		3.7 Deep CNN with SVM
		3.8 Future Scope
	4 Conclusion
	References
Leukaemia Classification Using Machine Learning and Genomics
	1 Introduction
	2 Background
	3 Proposed Model
		3.1 K-Nearest Neighbors
		3.2 Algorithm
	4 Experimental Results
		4.1 Dataset
		4.2 Data Exploration
		4.3 Data Preprocessing
		4.4 Principal Component Analysis (PCA)
		4.5 Model Building
		4.6 Model Training
	5 Model Analysis
	6 Conclusion
	References
In Silico Drug Discovery Using Tensor Decomposition Based Unsupervised Feature Extraction
	1 Introduction
	2 LINCS Data Set Analysed by TD Based Unsupervised FE
	3 DrugMatrix Analyzed by TD Based Unsupervised FE
		3.1 Heart Failure
		3.2 Other Diseases than Heart Failure
		3.3 A Possible Drug Candidate Compound for Cirrhosis, Bezafibrate
	4 COVID-19 Drug Discovery
	5 Conclusion
	References
Challenges of Long Non Coding RNAs in Human Disease Diagnosis and Therapies: Bio-Computational Approaches
	1 Introduction
	2 Long Non-coding RNAs as Biomarkers
	3 Roles of lncRNAs in Different Human Diseases
	4 Functional Analysis of Long Non-coding RNAs (lncRNAs)
		4.1 Public Repositories and Databases
		4.2 Noncode
		4.3 LncRBase
		4.4 LncBook
		4.5 MONOCLdb
		4.6 lncRNome
		4.7 LncRNASNP
		4.8 LncRNADisease
		4.9 Lnc2Cancer
	5 Conclusion
	References
Protein Sequence Classification Using Convolutional Neural Network and Natural Language Processing
	1 Introduction
	2 Methods and Materials
		2.1 Existing Methods
		2.2 The Amino Acid Composition
		2.3 N-Grams Method
		2.4 Active Motifs
		2.5 Proposed Method and Data Set Collection
		2.6 Convolution Neural Network
	3 Methods and Materials
	4 Conclusion
	References
Machine Learning for Metabolic Networks Modelling: A State-of-the-Art Survey
	1 Introduction
	2 Background
	3 Machine Learning Approaches in Metabolic Modeling
		3.1 Hidden Markov Models (HMMs)
		3.2 Probabilistic Context-Free Grammar (PCFGs)
		3.3 Bayesian Networks (BNs)
	4 Conclusion
	References
Sincle Cell RNA-seq Analysis Using Tensor Decomposition and Principal Component Analysis Based Unsupervised Feature Extraction
	1 Introduction
	2 scRNA-seq Analysis of Mice and Human Mid Brain Development
	3 scRNA-seq Analysis of Neurodegenerative Disease
	4 Conclusion
	References
Machine Learning: A Tool to Shape the Future of Medicine
	1 Introducing Machine Learning (ML)
	2 A Motivating Example of Machine Learning in Biology
	3 The Mathematical Concepts of Some Commonly Used ML Schemes in Biology
		3.1 A Selection of Unsupervised ML Schemes
		3.2 Dimensionality Reduction and Feature Selection
		3.3 Supervised Learning Schemes
	4 Applications of ML in Genomics
		4.1 Deep Learning Approaches Towards the Prediction of the Cell State and Fate
		4.2 (ML) Applications for Predicting the RNA Properties and RNA-Protein Interactions
		4.3 Drug Repurposing a Novel Tool in Medicine
		4.4 Prediction of Neo-Antigens
	5 Discussion
	References