دانلود کتاب Bioinformatics and Biomedical Engineering: 9th International Work-Conference, IWBBIO 2022, Maspalomas, Gran Canaria, Spain, June 27–30, 2022, Proceedings, Part II (Lecture Notes in Bioinformatics)

فهرست مطالب :

Preface
Organization
Contents – Part II
Contents – Part I
Chip-Seq and RNA-Seq Analysis
Integrative Analysis of Ovarian Serious Adenocarcinoma to Understand Disease Network Biology
1 Introduction
2 Material and Methods
2.1 Data Retrieval
2.2 Differentially Expressed Genes (DEGs) Identification
2.3 Disease-Gene Association analysis
2.4 Principal Component Analysis and Kaplan-Meiers Survival Estimation
2.5 Gene Set Enrichment Analysis (GSEA)
2.6 Construction of Gene Regulatory Network and Analysis
3 Results
3.1 Significant Differentially Expressed Genes (DEGs)
3.2 Disease-gene Associations (DGA) Study
3.3 PCA and Kaplan-Meiers (KM) Survival Estimation
3.4 Gene Set Enrichment Analysis of the 8 Seed Genes
3.5 Gene Regulatory Network Construction, Visualization and Topological Analysis
4 Discussion
5 Conclusion
References
GAGAM: A Genomic Annotation-Based Enrichment of scATAC-seq Data for Gene Activity Matrix
1 Introduction
2 Background
3 Materials and Methods
3.1 Genomic Annotation
3.2 Promoter Peaks Matrix
3.3 Intragenic Peaks Matrix
3.4 Promoter-Enhancer Co-accessibility Matrix
4 Results and Discussion
4.1 Evaluation Strategy
4.2 Metrics Definition
4.3 Datasets
4.4 Results
5 Conclusions
References
Finding Significantly Enriched Cells in Single-Cell RNA Sequencing by Single-Sample Approaches
1 Introduction
2 Materials and Methods
2.1 Data Acquisition and Pre-processing
2.2 Single-Sample Pathway Enrichment Algorithms
2.3 Algorithm\'s Evaluation
3 Results
4 Conclusions
References
Comparison of Stranded and Non-stranded RNA-Seq in Predicting Small RNAs in a Non-model Bacterium
1 Introduction
2 Materials and Methods
2.1 Genome and Annotation
2.2 Transcriptomic Data
2.3 Data Preprocessing
2.4 sRNAs Prediction
3 Results and Discussion
3.1 Data Preprocessing
3.2 sRNAs Prediction in Stranded Data
3.3 Comparison of Stranded and Non-stranded Data
4 Conclusions
References
Comparative Study of Synthetic Bulk RNA-Seq Generators
1 Introduction
2 RNA-Seq Data Generators
3 Methodology, Parameter Selection, and Results
4 Discussion
References
Investigating Sources of Zeros in 10× Single-Cell RNAseq Data
1 Introduction
2 Methods
2.1 Data
2.2 Non-linear Regression Model
2.3 Gene Set Analysis
2.4 Sources of Technical Bias
2.5 Logistic Regression Model
2.6 Statistical Analysis
3 Results and Discussion
3.1 Differences in Gene Expression Between Bulk RNAseq and Cummulative ScRNAseq
3.2 Characterization of Genes with Zeros Using Other Modalities
3.3 Finding Genes with a Higher Proportion of Zeros Than Expected
3.4 Searching of Biological Sources of Decreased Expression on a Single-Cell Level
3.5 Influence of Technical Factors to Decreased Gene Expression on a Single-Cell Level
4 Conclusions
References
Bioinformatics and Biomarker Identification
Exhaled Breath Condensate Study for Biomarkers Discovery
1 Introduction
2 Exhaled Breath Condensate Definition and Formation
3 Exhaled Breath Condensate Collection
4 Exhaled Breath Condensate Analysis
5 Exhaled Breath Condensate Application
6 Exhaled Breath Condensate and Biomarkers
7 Summary
References
Statistical Learning Analysis of Thyroid Cancer Microarray Data
1 Introduction
2 Methods
3 Experimentation
3.1 Phase 1: Individual Analysis of the Datasets
3.2 Phase 2: Analysis of Integrated Datasets
3.3 Phase 3: Multiclass Classifiers\' Analysis
3.4 HINT3: Statistical and Biological Hypothesis
4 Discussion and Conclusions
References
Migrating CUDA to oneAPI: A Smith-Waterman Case Study
1 Introduction
2 Background
2.1 The oneAPI Programming Ecosystem
2.2 Smith-Waterman Algorithm
2.3 SW#
3 Implementation
3.1 Differences Between CUDA and DPC++
3.2 Migrating CUDA Codes to DPC++
4 Experimental Results
4.1 Experimental Design
4.2 Performance Results
5 Conclusions and Future Work
References
Computational Proteomics
Fuzzy-Inference System for Isotopic Envelope Identification in Mass Spectrometry Imaging Data
1 Introduction
2 Materials and Methods
2.1 Data Characteristic
2.2 Idea Explanation
3 Results
4 Conclusions
References
Receptor Tyrosine Kinase KIT: A New Look for an Old Receptor
References
Human Vitamin K Epoxide Reductase as a Target of Its Redox Protein
References
A Distance Geometry Procedure Using the Levenberg-Marquardt Algorithm and with Applications in Biology but Not only
1 Introduction
2 Our DGP Procedure
2.1 Semidefinite Programming Relaxation
2.2 Projected Levenberg-Marquardt Algorithm
3 Computational Experiments
4 Discussion and Conclusions
References
A Semi-supervised Graph Deep Neural Network for Automatic Protein Function Annotation
1 Introduction
2 Proposed Approach
2.1 Protein Feature Extraction
2.2 Representation Learning with Deep Autoencoders (DAE)
2.3 Latent Representation-Based Protein Graph Construction
2.4 Protein Function Annotation with Semi-Supervised Graph Neural Networks (SGNN)
3 Experimental Results
3.1 Data Description
3.2 Compared Methods
3.3 Parameters Settings
3.4 Deep Representation Learning with the DAE Model
3.5 Performance Analysis
4 Conclusion
References
Computational Systems for Modelling Biological Processes
Strong Prevalence of the Function over Taxonomy in Human tRNA Genes
1 Introduction
1.1 Function–Taxonomy Interplay
1.2 Peculiarities of Codons Deciphering
1.3 Transfer RNA Genes
2 Materials and Methods
2.1 Genetic Material
2.2 Triplet Frequency Dictionary
2.3 Clustering and Visualization
3 Results and Discussion
4 Conclusion
References
A Methodology for Co-simulation-Based Optimization of Biofabrication Protocols
1 Introduction
2 Background
3 Methods
3.1 Use Case Description
3.2 Co-simulation Engine
3.3 Design Space Exploration Engine
4 Results
4.1 Experimental Setup
4.2 Experimental Results
5 Conclusions
References
A 3D Multicellular Simulation Layer for the Synthetic Biology CAD Infobiotics Workbench Suite
1 Introduction
2 Multicellular Simulation Principles and Technologies
2.1 Bioregulatory/Metabolic Simulations and Exchange Standards
2.2 Multicellular Simulator Characteristics and Potential Characteristics
2.3 Computational Considerations
2.4 Multicellular Simulation Methodologies
3 Methods
3.1 Overview
3.2 UnrealMulticell3D
3.3 SynthMeshBuilder
3.4 NGSS Use via NGSS-Invoker, UnrealMulticell3D and SynthMeshBuilder
4 Results
4.1 Hardware, Software and Models Used for Benchmarking
4.2 Benchmarking Without the Multicellular Layer
4.3 Benchmarking with the Multicellular Layer
5 Conclusions
References
Integrating in-vivo Data in CFD Simulations and in in-vitro Experiments of the Hemodynamic in Healthy and Pathologic Thoracic Aorta
1 Introduction
2 Problem Definition, Numerical Methodology and Experimental Set-Up
3 Results and Discussion
4 Conclusions
References
Sensitivity Analysis of Adhesion in Computational Model of Elastic Doublet
1 Introduction
2 Computational Model of Double Cluster
2.1 Elastic Cells
2.2 Adhesion
2.3 Pulling Experiment
3 Stability of Adhesion Surface
4 Elongation Flow
4.1 Fluid Force on Cell
5 Conclusion
References
Increasing the Accuracy of Optipharm\'s Virtual Screening Predictions by Implementing Molecular Flexibility
1 Introduction
2 Methods
2.1 Shape Similarity Scoring Function
2.2 OptiPharm Algorithm
2.3 Methodology
3 Materials
4 Results
5 Conclusion and Future Work
References
Feature Selection, Extraction, and Data Mining in Bioinformatics: Approaches, Methods and Adaptations
Comparisons of Knowledge Graphs and Entity Extraction in Breast Cancer Subtyping Biomedical Text Analysis
1 Introduction
2 Background
3 Methods
3.1 Knowledge Graph Pipeline
3.2 Application of Knowledge Graphs
4 Results and Discussion
5 Conclusion
References
Towards XAI: Interpretable Shallow Neural Network Used to Model HCP’s fMRI Motor Paradigm Data
1 Introduction
2 Method
2.1 Data Source: The Motor Paradigm in the Human Connectome Project
2.2 Neural Data Processing
2.3 Implementation of the Shallow Neural Network
2.4 Neural Network Interpretation
2.5 Neural Network and Procedure Quality Analyses
3 Results
3.1 GLM-Based Analysis
3.2 Performance of the Neural Network
3.3 Procedure Quality Analysis
3.4 Identification of the Inputs that Most Contribute to Correct Hits
4 Discussion
References
A Deep Learning-Based Method for Uncovering GPCR Ligand-Induced Conformational States Using Interpretability Techniques
1 Introduction
2 Related Work
3 Materials
3.1 Protein as Residue Interaction Network Representation
3.2 Data Pre-processing
4 Experimental Setup
5 Results and Discussion
5.1 Interpretability of the Results
6 Conclusions
References
Data Transformation for Clustering Utilization for Feature Detection in Mass Spectrometry
1 Introduction
2 Materials and Methods
2.1 Dataset
2.2 Space Division
2.3 ROI Identification
2.4 Space Transformation
2.5 Clustering
3 Results
4 Conclusion
References
Spolmap: An Enriched Visualization of CRISPR Diversity
1 Introduction
2 Basic Recalls
3 The Proposed Approach
4 Obtained Results
5 Discussion
6 Conclusion
References
How to Compare Various Clustering Outcomes? Metrices to Investigate Breast Cancer Patient Subpopulations Based on Proteomic Profiles
1 Introduction
2 Materials
3 Methods
3.1 Subtype Detection
3.2 Comparison of Clustering Approaches
3.3 Biological Investigation
4 Results
5 Discussion
6 Conclusions
References
Sperm-cell Detection Using YOLOv5 Architecture
1 Introduction
1.1 Topic Overview
2 Materials and Methods
2.1 Dataset
2.2 Neural Network Architecture
2.3 Hardware
2.4 Results
3 Conclusion
References
Machine Learning in Bioinformatics
Comparative Analysis of Supervised Cell Type Detection in Single-Cell RNA-seq Data
1 Introduction
2 Materials and Methods
2.1 Framework
2.2 Dataset
2.3 Data Pre-processing
2.4 Feature Selection
2.5 Evaluation Metrics
3 Results and Discussion
3.1 Parameter Optimization
3.2 Classification Results
3.3 Biological Validation
4 Conclusion and Future Work
References
PathWeigh – Quantifying the Behavior of Biochemical Pathway Cascades
1 Introduction
2 PathWeigh Algorithm
3 UDP Fitting
4 Activity and Consistency
5 Visualization
6 Pathway Assessment
7 Summary
References
Translational Challenges of Biomedical Machine Learning Solutions in Clinical and Laboratory Settings
1 Introduction
2 Case Studies
2.1 Chest X-ray Image Diagnosis of COVID-19
2.2 Disease Status Detection in Cytometry
3 Discussion
4 Conclusion
References
Human Multi-omics Data Pre-processing for Predictive Purposes Using Machine Learning: A Case Study in Childhood Obesity
1 Introduction
2 Description of the Case Study Population and Data
3 Main Challenges that are Usually Faced in Omics ML Predictive Modelling
4 Data Pre-processing Guidelines and Analytical Solutions for Mentioned Challenges
4.1 GWAS Data
4.2 EWAS Data
4.3 Biochemistry, Anthropometrical and Clinical Data
4.4 Future Perspectives on Pre-processing
5 Basis and Recommendations that Must Guide the Selection of a ML Algorithm and the Experimental Design
5.1 Experimental Design
5.2 Selection of ML Algorithms and Classification Metrics
6 Main Results and Insights from the Case Study
7 Conclusion
References
Feature Density as an Uncertainty Estimator Method in the Binary Classification Mammography Images Task for a Supervised Deep Learning Model
1 Introduction
2 State of the Art
3 Methods
3.1 Mammography Datasets
3.2 Data Preprocessing
3.3 Training Process
3.4 Uncertainty Estimation Process
4 Experiment Results
5 Conclusions and Recommendations
References
Iterative Clustering for Differential Gene Expression Analysis
1 Introduction
2 Problems of Differential Gene Expression Analysis
3 Unsupervised Analysis for Gene Expression Differentiation
4 Iterative Procedure of Gene Expression Differentiation
4.1 Data Preprocessing
4.2 Data Processing
5 Application Results and Discussion
6 Conclusion
References
Comparison of Batch Effect Removal Methods forHigh Dimensional Mass Cytometry Data
1 Introduction
2 Materials and Methods
2.1 Dataset
2.2 Batch Effect Correction
2.3 Cell Subtypes Identification
2.4 Statistical Comparison of Methods
2.5 UMAP Transformation
2.6 mISO Plots–Visualization of Results in High Dimensional Space
2.7 Technical Details
3 Results
4 Discussion
5 Conclusions
References
Next Generation Sequencing and Sequence Analysis
Evaluating Performance of Regression and Classification Models Using Known Lung Carcinomas Prognostic Markers
1 Introduction
2 Dataset and Methodology
3 Results
3.1 Prediction Performance of Random Forest
3.2 Prediction Performance of SVM
3.3 Prediction Performance of Logistic Regression and LASSO
4 Discussion and Future Scope
References
Approximate Pattern Matching Using Search Schemes and In-Text Verification
1 Introduction
2 Preliminaries
2.1 Bidirectional FM-Index
2.2 Search Schemes
3 Adapted Search Schemes
4 Bit-Parallel Edit Distance Computation
4.1 Hyyrö\'s Bit-Parallel Algorithm
4.2 Bit-Parallel Banded Alignment
4.3 Matrix Initialization
5 In-Text Verification
6 Results and Discussion
6.1 Original Versus Adapted Search Schemes
6.2 In-Index Versus In-Text Verification
6.3 Comparison to State-of-the-Art Tools
7 Conclusion
References
KFinger: Capturing Overlaps Between Long Reads by Using Lyndon Fingerprints
1 Introduction
2 Preliminaries
3 Detecting Reads in Overlap
3.1 The Method
4 Experimental Results
5 Conclusions and Future Developments
References
Can We Detect T Cell Receptors from Long-Read RNA-Seq Data?
1 Introduction
1.1 VDJ Recombination
1.2 Immune Repertoire Identification–State of the Art
1.3 CDR3 Detection from Long-Read Data
2 Material
3 Methods
3.1 Mapping to Reference Genome
3.2 Algorithms for TRβ Detection from Sequencing Data
3.3 CDR3 Sequences Comparison
4 Results
4.1 Reads Mapped to TRβ C1 and C2 Gene Region
4.2 Impact of Parameters on CDR3 Detection
4.3 Analysis of Detected CDR3s
5 Discussion
References
Author Index