دانلود کتاب Practical Applications of Computational Biology & Bioinformatics, 15th International Conference (PACBB 2021)

فهرست مطالب :

Preface
Organization
Program Committee Chairs
General Co-chairs
Advisory Committee
Organizing Committee
Program Committee
PACBB 2021 Sponsors
Contents
Computational Methods for the Identification of Genetic Variants in Complex Diseases
1 Introduction
2 Methods
2.1 Data Preparation
2.2 Gene Selection
2.3 Feature Extraction and Reduction
3 Results and Discussion
4 Conclusion
References
Using Reduced Amino-Acid Alphabets and Simulated Annealing to Identify Antimicrobial Peptides
1 Introduction
2 Methods
2.1 Alphabet Encoding
2.2 k-mer Database
2.3 Performance Metrics
2.4 Simulated Annealing
3 Results and Discussion
4 Conclusion
References
Acufenometry in the Self-management of Tinnitus: A Revised Interface to Improve the User Experience
1 Introduction
2 Acufenometry
3 Study
3.1 Study Design
3.2 Results
4 Discussion and Conclusions
References
The pegi3s Bioinformatics Docker Images Project
1 Introduction
2 Related Work
3 The pegi3s Bioinformatics Docker Images Project
3.1 Docker Images
3.2 Pipeline Development
3.3 Containerization of Applications
4 Discussion
References
On the Reproducibility of MiRNA-Seq Differential Expression Analyses in Neuropsychiatric Diseases
1 Introduction
2 Materials and Methods
2.1 Data Acquisition and Identification of the Samples
2.2 Download of the Genome and Annotation Files
2.3 MiARma-Seq Analysis
2.4 Quality Control
2.5 Application of the Same Statistical Criteria of the Original Articles to miARma-Seq Results
2.6 Comparison Between the Original Results and miARma-Seq Results
3 Results and Discussion
3.1 Quality Control
3.2 Application of the Same Statistical Criteria of the Original Articles to MiARma-Seq Results
3.3 Comparison Between the Original Results and miARma-Seq Results
4 Conclusion
References
Computational Tools for the Analysis of 2D-Nuclear Magnetic Resonance Data
1 Introduction
2 Methods
2.1 Data Reading
2.2 Data Visualization
2.3 Dimension Reduction
2.4 Further Analysis
3 Results and Discussion
3.1 Tomato Fruit Extracts
3.2 Worm (Caenorhabditis Elegans) Metabolome
4 Conclusion
References
Recurrent Deep Neural Networks for Enzyme Functional Annotation
1 Introduction
2 Datasets and Deep Learning Models
3 Influence of Sequence Length and Type of Truncation
4 Influence of Network Type and Attention Addition
5 Influence of Different Aminoacid Encoding Schemes
6 Discussion and Conclusions
References
Assessing the Impact of Data Set Enrichment to Improve Drug Sensitivity in Cancer
1 Introduction
2 Materials and Methods
2.1 Original Data and the Study Data Sets
2.2 Methods
3 Results and Discussion
3.1 Regression Analysis Results
3.2 Classification
3.3 Graph Mining
3.4 Classification Analysis Results Using ILP
4 Conclusions
References
Deep Neural Network to Curate LTR Retrotransposon Libraries from Plant Genomes
1 Introduction
2 Materials and Methods
2.1 Creation of Plant LTR-RTs Sequence Dataset
2.2 Experimental Analysis Using ML Models
2.3 Experiments Using Deep Neural Networks.
2.4 Generalization Tests
2.5 Hardware Specifications
3 Results
3.1 Descriptive Analysis of the Dataset
3.2 Design of a Deep Neural Network Based Model to Detect Non-intact LTR Retrotransposon Sequences
3.3 Test for the Generalization of the Implemented Model
4 Discussion
5 Conclusion
References
A Hybrid of Bees Algorithm and Regulatory On/Off Minimization for Optimizing Lactate Production
1 Introduction
2 A Hybrid of Bees Algorithm and Regulatory on/Off Minimization
2.1 Bee Representation of Metabolic Genotype
2.2 Initialization of the Population
2.3 Scoring Fitness of Individuals
2.4 Neighbourhood Search
2.5 Randomly Assigned and Termination
3 Experimental Results
3.1 Experimental Result and Discussion for Lactate
3.2 Comparative Analysis for Lactate Case
3.3 Performance Measurement for Lactate Case
4 Conclusion and Future Works
References
A Study on Burrows-Wheeler Aligner’s Performance Optimization for Ancient DNA Mapping
1 Introduction
2 Methodology
2.1 Ancient DNA Sequence Data
2.2 Sequence Reads Processing and Alignment
2.3 Variant Calling and Filtering
3 Results and Discussion
3.1 Runtime and Memory Usage Differences Between Strategies
3.2 Impact on the Identification of Endogenous Reads
3.3 Impact on Variant Calling
3.4 BWA-aln VS BWA-MEM on Accurate and Effective Mapping
4 Conclusions and Future Prospects
References
BioTMPy: A Deep Learning-Based Tool to Classify Biomedical Literature
1 Introduction
2 Package Description and Implementation
3 Validation
3.1 Dataset and Challenge Overview
3.2 Preprocessing
3.3 Data Analysis
3.4 Embeddings
3.5 Evaluation
4 Discussion and Conclusions
References
May Gender Have an Impact on Methylation Profile and Survival Prognosis in Acute Myeloid Leukemia?
1 Background
2 Materials and Methods
2.1 Data
2.2 Detection of Differentially Methylated CpG Sites and Genomic Regions
2.3 Survival Analysis
3 Results and Discussion
3.1 Principal Component Analysis
3.2 Detection of Differentially Methylated CpG Sites
3.3 Detection of Differentially Methylated Genomic Regions
3.4 Survival Analysis
4 Conclusions
References
Towards a Multivariate Analysis of Genome-Scale Metabolic Models Derived from the BiGG Models Database
1 Introduction
2 Results and Discussion
2.1 Genomes’ Comparative Functional Analysis
2.2 Models’ Analysis
3 Conclusion
4 Materials and Methods
4.1 Genomes’ Comparative Functional Analysis
4.2 Draft Models
4.3 Multivariate Analysis
5 Supplementary Materials
References
A Comparison of Different Compound Representations for Drug Sensitivity Prediction
1 Introduction
2 Methods
2.1 Data Sets
2.2 Models
2.3 Model Training and Evaluation
2.4 DeepMol
3 Results and Discussion
4 Conclusion
References
Combinatorial Optimization of Succinate Production in Escherichia coli
1 Introduction
2 Strain Optimization with MEWpy
2.1 Constraint-Based Modeling
2.2 Stoichiometric Model
2.3 GECKO-Like Model
2.4 E(T)FL Model
2.5 Optimization Setup
3 Analysis of Solutions Distributions
4 Illustrative Solutions
5 Conclusion
References
Predicting Adverse Drug Reactions from Drug Functions by Binary Relevance Multi-label Classification and MLSMOTE
1 Introduction
2 Related Work
3 Dataset and the Proposed Methodology
3.1 Problem Statement
3.2 Dataset
3.3 The Proposed Methodology
4 Experimental Setup and Results
4.1 Evaluation Metrics
4.2 Experimental Setup
4.3 Experimental Results and Discussion
5 Conclusion
References
Author Index