Deep learning applications in translational bioinformatics.

Deep Learning Applications in Translational Bioinformatics, a new volume in the Advances in Ubiquitous Sensing Application for Healthcare series, offers a detailed overview of basic bioinformatics, deep learning, various applications of deep learning in translational bioinformatics including deep le...

Full description

Bibliographic Details
Corporate Author:	ScienceDirect (Online service)
Format:	eBook
Language:	English
Published:	New York, NY : Academic Press, 2024.
Subjects:	Bioinformatics. Deep learning (Machine learning) Bio-informatique. Apprentissage profond. Electronic books.
Online Access:	Connect to the full text of this electronic book

Table of Contents:

Front Cover
Deep Learning Applications in Translational Bioinformatics
Copyright Page
Contents
List of contributors
About the editors
1 Deep learning ensembles in translational bioinformatics
1.1 Introduction
1.2 Basic ensembling methods
1.3 Application
1.3.1 Application of ensemble techniques to proteomics using microarray and mass spectrometry
1.3.2 Gene-gene interaction detection using random forest
1.3.3 Prediction of regulatory elements using ensemble methods
1.3.3.1 Further growing uses for ensemble methods in bioinformatics
1.4 Extensions of the ensemble method in bioinformatics
1.5 Ensemble theory's application to feature selection
1.6 Ensemble feature selection methods and stability of feature selection algorithms in bioinformatics
1.6.1 Stability and feature selection algorithms
1.7 Algorithmic ensembles for feature selection
1.8 Conclusion
References
2 Recursive feature elimination and multisupport vector machine in healthcare analytics
2.1 Introduction
2.1.1 Motivation of the work
2.1.2 Contribution of the research work
2.1.3 Chapter organization
2.2 Related works
2.2.1 Limitation of the existing works
2.3 Proposed system
2.3.1 Description of dataset
2.3.2 Dimensionality reduction and feature selection methods in medical disease diagnosis
2.3.2.1 Filtering techniques
2.3.2.2 Wrapper techniques
2.3.2.3 Recursive feature elimination
2.3.3 Classification using multisupport vector machine
2.4 Results and discussion
2.4.1 Performance used in medical disease classification
2.4.2 Results evaluation for recursive feature elimination calculation
2.5 Conclusion
References
3 Sensor-enabled biomedical decision support system using deep learning and fuzzy logic
3.1 Introduction
3.1.1 Background and motivation.
3.1.2 Research problem statement
3.1.3 Objectives and contributions
3.1.4 Chapter organization
3.2 Literature review
3.2.1 Fuzzy logic
3.2.1.1 Fuzzy sets and fuzzy numbers
3.2.1.2 Concepts of fuzzy logic approach for research study
3.2.1.3 Definition of fuzzy sets along with membership function
3.2.2 The deep learning concept
3.2.2.1 Convolutional neural network
3.2.2.2 The concept of recurrent neural networks
3.2.3 Biomedical decision support system
3.2.3.1 Electronic health records
3.2.3.2 The key challenges in developing biomedical decision support system
3.2.4 Related work on the integration of fuzzy logic and deep learning for sensor-enabled biomedical decision support systems
3.3 Methodology
3.3.1 Data collection and preprocessing
3.3.2 Fuzzy logic-based feature selection
3.3.3 Deep learning model design and implementation
3.3.4 Performance evaluation metrics
3.4 Results from experiment
3.4.1 Dataset description
3.4.2 Performance comparison with traditional machine learning methods
3.4.3 Case study: prediction of cardiovascular diseases
3.4.3.1 Fuzzy logic-based feature selection
3.4.3.2 Deep learning
3.4.4 Case study: prediction of cardiovascular diseases using fuzzy logic and deep learning
3.4.4.1 Dataset description
3.4.4.2 Fuzzy logic-based feature selection
3.4.4.3 Deep learning model design and implementation
3.4.4.4 Performance evaluation metrics
3.4.4.5 Results
3.5 Discussion
3.5.1 Interpretation of results
3.5.2 Limitations and challenges
3.5.2.1 Limitations
3.5.2.2 Challenges
3.5.3 Future research directions
3.6 Conclusion
References
Further reading
4 Prediction of Alzheimer's disease using densely convolutional neural network
4.1 Introduction
4.2 Literature review
4.3 Methodology.
4.4 Materials and tools
4.4.1 Dataset
4.4.2 Data preprocessing
4.4.3 Dense convolutional neural network architecture
4.4.4 Hyperparameters
4.4.5 Evaluation
4.5 Results and discussion
4.6 Conclusion
References
5 Brain tumor detection from magnetic resonance imaging images using shallow convolutional neural network
5.1 Introduction
5.2 Related works
5.3 Methodology
5.3.1 Convolutional neural network models
5.3.2 Proposed shallow convolutional neural network
5.3.2.1 The architecture
5.3.3 Transfer learning
5.3.4 Support vector machine
5.4 Result and discussion
5.5 Conclusion
References
6 Multiview learning with shallow 1D-CNN for anticancer activity classification of therapeutic peptides
6.1 Introduction
6.2 Related work
6.3 Methodology
6.3.1 Convolutional neural network
6.3.2 The proposed 1D-convolutional neural network
6.3.3 Feature descriptor
6.3.4 Sequence-based
6.3.5 Standard physicochemical properties
6.3.6 Physicochemical properties and sequence composition
6.4 Experimental setup
6.4.1 Dataset
6.4.2 Result discussion
6.4.3 Analysis of the optimal multiview learning
6.5 Conclusion
References
7 Deep learning methods for protein classification
7.1 Introduction
7.2 Literature survey
7.3 Protein representation methods
7.3.1 Amino-acid sequence
7.3.2 Substitution matrix representation
7.3.3 Physicochemical property response matrix
7.4 Proposed methodology
7.4.1 Dataset
7.4.2 Proposed classification model
7.4.2.1 Convolutional neural network
7.4.2.1.1 Input layers for 2-D CNN model
7.4.2.1.2 Hidden layers
7.4.2.1.3 Output layers
7.5 Result and discussion
7.5.1 Performace evaluation metrics
7.5.1.1 Accuracy
7.5.1.2 Precision
7.5.1.3 Recall.
7.5.2 Prediction of hemolytic and nonhemolytic activity
7.6 Conclusion
References
8 Biosensors-based identification of antibiotic resistance in bacteria
8.1 Introduction
8.2 Gonnococal antibiotic resistance
8.2.1 Penicillin
8.2.2 Tetracycline
8.2.3 Ciprofloxacin
8.2.4 Cefixime
8.2.5 Ceftriaxone
8.2.6 Azithromycin
8.3 Proposed work
8.4 Experimentation
8.5 Results and discussion
8.5.1 Learning curve
8.6 Conclusion
References
9 Deep learning for vehement gene expression exploration
9.1 Introduction
9.2 Gene expression
9.3 Gene expression analysis
9.4 Gene expression functioning
9.5 Gene expression technologies
9.6 Microarray technique
9.7 Strengths and limitations of microarray
9.8 Strengths of microarrays
9.9 Limitations of microarrays
9.10 Microarray functioning
9.11 RNA-Seq technique
9.12 Strengths and limitations of RNA-Seq
9.13 Strengths of RNA-seq
9.14 Limitations of RNA-seq
9.15 RNA-Seq functioning
9.16 Study on RNA-Seq over microarray
9.17 Deep learning
9.18 Deep learning sets unique from neural network
9.19 Deep learning sets unique from machine learning
9.20 Deep learning architectures: convolutional neural network and recurrent neural network
9.21 Convolutional neural network functioning
9.22 Recurrent neural networks functioning
9.23 Deep learning for gene expression
9.24 Convolutional neural networks for gene expression
9.25 Recurrent neural network for gene expression
9.26 Potential of recurrent neural network over convolutional neural network for gene expression
9.27 Conclusion
References
10 Machine learning-enforced bioinformatics approaches for drug discovery and development
10.1 Introduction
10.2 Drug discovery: an introduction and historical perspective
10.3 Machine learning approaches.
10.4 Machine learning-enforced bioinformatic tools for drug discovery
10.4.1 Random forest
10.4.2 Artificial neural network-based approaches
10.4.2.1 Convolutional neural networks
10.4.2.2 Support vector machines
10.4.2.3 Multilayer perception neural network
10.4.2.4 Recurrent neural networks
10.4.3 Bayesian models
10.5 Deep machine learning
10.6 Artificial intelligence
10.7 Machine learning-, deep learning-, and artificial intelligence-enforced bioinformatics and cheminformatics tools
10.7.1 Drug design, drug prediction, and optimization
10.7.2 Determination of the target and validation
10.7.3 Prophecy of drug-drug interaction
10.7.4 Compound screening or hit discovery
10.7.5 Drug repurposing
10.7.6 Molecular docking
10.7.7 Drug safety assessment
10.8 Challenges and opportunities
10.9 Conclusion
References
11 Role of deep learning in predicting drug formulations and delivery systems
11.1 Introduction
11.2 Databases, deep learning tools and techniques
11.2.1 Establishing the dataset
11.2.2 Deep learning tools and techniques
11.3 Data processing methods
11.3.1 Steps involved in data preprocessing
11.4 Artificial intelligence algorithms and models in dosage form development
11.4.1 Application of artificial intelligence in pharmaceutical drug formulations
11.5 Conclusions and future prospects
References
12 Deep learning in computer-aided drug design: a case study
12.1 Introduction
12.1.1 Drug designing approaches
12.1.1.1 Structure-based drug design
12.1.1.2 Ligand-based drug design
12.1.2 Why deep learning in computer-aided drug design?
12.2 Role of deep learning in computer-aided drug design
12.3 Software tools, web servers, and package
12.3.1 Parameters
12.3.2 Tools
12.3.3 Packages.