GeNeDis 2022: Computational Biology and Bioinformatics (Advances in Experimental Medicine and Biology, 1424)

Acknowledgment
Contents
1: Dynamic Reconfiguration of Dominant Intrinsic Coupling Modes in Elderly at Prodromal Alzheimer´s Disease Risk
	1.1 Introduction
	1.2 Patient Recruitment and Data Availability
		1.2.1 Disease Categorization
		1.2.2 Cognitive Battery
		1.2.3 Mnemonic Strategy Training
		1.2.4 Demographics and Neuropsychological Measurements
	1.3 Interventions
	1.4 Neuropsychological Performance
	1.5 Methods
		1.5.1 EEG Data Acquisition
		1.5.2 EEG Data Source Reconstruction
		1.5.3 EEG Data Source Connectivity Analysis
		1.5.4 Statistical Filtering: Surrogate EEG Source Connectivity Analysis
		1.5.5 Data-Driven Topological Filtering
		1.5.6 Graph Diffusion Distance Metric
		1.5.7 Quantifying the Contribution of Each Dominant Intrinsic Coupling Mode (DICM)
		1.5.8 A Dissimilarity Measure for Dynamical Trajectories Based on the Wald-Wolfowitz (WW) Test
		1.5.9 Estimating Time-Delays with Delay Symbolic Transfer Entropy (dSTE)
	1.6 Improvements
		1.6.1 Improvement of GE-Cost for the MST Group
		1.6.2 Improvement of Brain Activity Synchronization Due to MST Intervention Protocol
		1.6.3 Improvement of the Time-Delay
		1.6.4 Improvement of GE-Cost for MST Group
	1.7 Discussion
		1.7.1 A Large Repertoire of Neuroinformatic Tools Underlined the Positive Outcome of the Intervention Protocol
		1.7.2 Improved Contribution of β1 to Spontaneous Brain Connectivity After the Intervention
		1.7.3 Improved Contribution of Inter/Intra to Spontaneous Brain Connectivity After the Intervention
		1.7.4 Improved Time-Delays in Spontaneous Brain Connectivity After the Intervention
		1.7.5 Improved Cost Efficiency of Spontaneous Brain Connectivity After the Intervention
	1.8 Conclusions
	References
2: A Sensor-Based Platform for Early-Stage Parkinson´s Disease Monitoring
	2.1 Introduction
	2.2 he Sensor Perspective
	2.3 Sensor Data Acquisition/Processing Unit
	2.4 Interface with Peripheral Sensors Platform
	2.5 Central Computing Unit and Dashboard
	2.6 Conclusions
	References
3: Pressure Prediction on Mechanical Ventilation Control Using Bidirectional Long-Short Term Memory Neural Networks
	3.1 Introduction
	3.2 Background Work
		3.2.1 Dynamic Systems
		3.2.2 PID Controller
		3.2.3 How Mechanical Ventilation Works
	3.3 The Dataset
		3.3.1 Data Format
		3.3.2 Data Preprocessing
	3.4 Model
		3.4.1 LSTM Nodes
		3.4.2 Bidirectional LSTM
		3.4.3 Model Architecture and Training
	3.5 Results
	3.6 Conclusions and Future Work
	References
4: Making Pre-screening for Alzheimer´s Disease (AD) and Postoperative Delirium Among Post-Acute COVID-19 Syndrome (PACS) a Na...
	4.1 Introduction
	4.2 PACS Long-Term Cognitive Outcomes
	4.3 Postoperative Delirium Long-Term Cognitive Outcomes
	4.4 Digital Neuro Signatures of Brain Resilience
	References
5: Graph Theory-Based Approach in Brain Connectivity Modeling and Alzheimer´s Disease Detection
	5.1 Introduction
	5.2 Graph Theory in Brain Connectivity Modeling
	5.3 From FMRI Data to Functional Networks Through Graph Theory
	5.4 Graph Theory Measures and Network Feature Extraction
	5.5 Graph Theory Metrics
	5.6 Evaluating Graph Model Robustness
	5.7 Brain Connectivity and AD Detection
	5.8 Software and Databases
	Literature
6: Developing Theoretical Models of Kinesia Paradoxa Phenomenon in Order to Build Possible Therapeutic Protocols for Parkinson...
7: Computational Methods for Protein Tertiary Structure Analysis
	7.1 Introduction
	7.2 Homology Modeling Methods
	7.3 Protein Fold Recognition
	7.4 Ab Initio Modeling
	7.5 Similarity Analysis and Clustering
	7.6 Protein Structure Superimpositions and Deviation
	7.7 Descriptors for Molecular Similarity Calculations
	7.8 Conclusion
	References
8: Spiking Neural Networks and Mathematical Models
	8.1 Introduction
		8.1.1 Hodgkin-Huxley Model
		8.1.2 Izhikevich Model
		8.1.3 Leaky Integrate and Fire Model
		8.1.4 Morris-Lecar
	8.2 Discussion
	8.3 Conclusions
	References
9: On Modelling Electrical Conductivity of the Cerebral White Matter
	9.1 Introduction
	9.2 Diffusion Matrix Imaging
		9.2.1 The Linear Relation Model
		9.2.2 The Electrical and Viscous Force Equilibrium Model
		9.2.3 The Wang and Volume Constraint Models
		9.2.4 The Volume Fraction Model
		9.2.5 The Electrochemical Model
	9.3 The Straight Model
	9.4 Conclusions
	References
10: Neuroeducation and Mathematics: The Formation of New Educational Practices
	10.1 Introduction
	10.2 Literature Review: Neuroeducation and Mathematics
	10.3 Research Methodology and Problem Categorization
	10.4 Conclusions
	References
11: DRDs and Brain-Derived Neurotrophic Factor Share a Common Therapeutic Ground: A Novel Bioinformatic Approach Sheds New Lig...
	11.1 Introduction
	11.2 Methods
		11.2.1 Dataset Collection
		11.2.2 Pre-analysis
		11.2.3 Data Filtering
		11.2.4 Data Annotation
		11.2.5 Semantic Analysis and Classification of SNPs
		11.2.6 Gene Selection and Regulatory Networks
	11.3 Results
		11.3.1 Dataset Collection
		11.3.2 Pre-analysis
		11.3.3 Data Filtering
		11.3.4 Data Annotation
		11.3.5 Semantic Analysis and Classification of SNPs
		11.3.6 Gene Selection and Regulatory Networks
	11.4 Discussion
	11.5 Conclusions
	References
12: Proposal for Investigating Self-Efficacy in Mathematics Using a Portable EEG System
	12.1 Introduction
	12.2 Discovering a Connection Between Neuroeducation and Mathematical Self-Efficacy
	12.3 A Proposal to Interpret Mathematical Self-Efficacy Through Neuroimaging Techniques
		12.3.1 Sample Participant Characteristics
		12.3.2 Data Recording
		12.3.3 Materials and Methods
		12.3.4 Mathematics Test Procedure
		12.3.5 Question Response Time Measurement Process
		12.3.6 Data Analysis
		12.3.7 Ethical Considerations
	12.4 Expected Findings
	12.5 Conclusions
	References
13: Collaborative Platforms and Matchmaking Algorithms for Research and Education, Establishment, and Optimization of Consortia
	13.1 Introduction
	13.2 Matchmaking
	13.3 Rule-Based Matchmaker (RBMM)
	13.4 Statistical Matchmaker (STMM)
	13.5 Hybrid Matchmaker
	13.6 Algorithms
	13.7 Matchmaking in Health and Research
	13.8 Matchmaking in Education
	13.9 Establishment and Optimization of Consortia
	13.10 Discussion
	References
14: Cognitive Neurorehabilitation in Epilepsy Patients via Virtual Reality Environments: Systematic Review
	14.1 Introduction
	14.2 Method
		14.2.1 Inclusion-Exclusion Criteria
		14.2.2 Data Extraction
		14.2.3 Systematic Review Analysis
			14.2.3.1 Analysis Method
	14.3 Results
		14.3.1 Pre-post-Intervention Comparison on Visual Memory
		14.3.2 Pre-post-Intervention Comparison on Visual Attention
		14.3.3 Pre-post-Intervention Comparison on Processing Speed of Visual Information
		14.3.4 Theoretical Framework of Cognitive Neurorehabilitation via VEs
	14.4 Discussion
		14.4.1 Limitations
	14.5 Conclusions
	References
15: A Retrospective Analysis to Investigate Contact Sensitization in Greek Population Using Classic and Machine Learning Techn...
	15.1 Introduction
	15.2 Materials and Methods
		15.2.1 Allergens
		15.2.2 Patient Selection and Study Design
		15.2.3 Patch Testing and Clinical Evaluation
		15.2.4 MOAHLFA Index
		15.2.5 Patient Self-Report of Eczema
		15.2.6 Data Analysis
	15.3 Results
		15.3.1 Demographics and Eczema Characteristics
		15.3.2 Correlation Among Participants´ Characteristics
		15.3.3 Multiple Correspondence Analysis Results
	15.4 Discussion
	15.5 Conclusions
	References
16: The Prediction of Tumorigenesis Onset Using Parameters from Chaotic Attractor Models
	16.1 Introduction
	16.2 State Space Analysis
	16.3 Determining the Beginning of Tumorigenesis
	16.4 Conclusions
	References
17: Using Biomarkers for Cognitive Enhancement and Evaluation in Mobile Applications
	17.1 Introduction
	17.2 Biomarkers
		17.2.1 Neuroimaging Biomarkers
		17.2.2 Digital Biomarkers
	17.3 Conclusion
	References
18: A Mobile Application for Supporting and Monitoring Elderly Population to Perform the Interventions of the FINGER Study
	18.1 Introduction
	18.2 Methods
	18.3 Results
		18.3.1 General Description of the FINGER Study App
		18.3.2 Calculation of Dementia Risk
		18.3.3 Guidance for Risk Reduction
		18.3.4 Architecture of Application
	18.4 Conclusions
	References
19: Application of Graphs in a One Health Framework
	19.1 Introduction
		19.1.1 One Health Concept and Its Importance Today
		19.1.2 One Health Problems
	19.2 Application of Graphs in Different One Health Levels
		19.2.1 Genome Level
		19.2.2 Disease Level
		19.2.3 Epidemiology
		19.2.4 Public Health
		19.2.5 Ecosystem Level
	19.3 Process Graphs and Their Application in One Health
		19.3.1 P-Graphs
		19.3.2 Maximal Structure Generation (MSG) Algorithm
		19.3.3 Solution Structure Generation (SSG) Algorithm
	19.4 Results
	19.5 Conclusions and Future Steps
	References
20: Application of Machine Learning Techniques in the HELIAD Study Data for the Development of Diagnostic Models in MCI and De...
	20.1 Introduction
	20.2 Materials and Methods
		20.2.1 Dataset
		20.2.2 Exploratory Data Analysis: Preprocessing
		20.2.3 Classifier Overview
	20.3 Results
	20.4 Conclusions
	References
21: Impact of Cognitive Priming on Alzheimer´s Disease
	21.1 Introduction
	21.2 Related Works
		21.2.1 Cognitive Priming
		21.2.2 Relaxing Environments and Alzheimer´s Disease
	21.3 Methodology: A Cognitive Priming System
	21.4 Experiments
	21.5 Results
	21.6 Conclusion
	References
22: Signature-Based Computational Drug Repurposing for Amyotrophic Lateral Sclerosis
	22.1 Introduction
	22.2 Materials and Methods
		22.2.1 Dataset
		22.2.2 Differential Expression Analysis
		22.2.3 Construction of the Candidate Drug List
			22.2.3.1 Querying CMAP
			22.2.3.2 Querying L1000CDS2
		22.2.4 Perturbational Class Analysis
		22.2.5 Chemical Clustering with ChemBioServer 2.0
		22.2.6 Predicting Mechanisms of Action
	22.3 Results
		22.3.1 ALS Signature
		22.3.2 Query Results
			22.3.2.1 CMAP Results
			22.3.2.2 L1000CDS2 Results
		22.3.3 Connectivity on a Perturbational Class Level
		22.3.4 Clustering of the Final Drug List
		22.3.5 Predicted Mechanisms of Actions and Bibliographic Analysis of Them
	22.4 Discussion
	Bibliography
23: Integrating Wearable Sensors and Machine Learning for the Detection of Critical Events in Industry Workers
	23.1 Introduction
	23.2 Data Collection Devices and Services
	23.3 Data Collection Method
	23.4 Health Assessment
	23.5 Conclusions
	References
24: Graph-Based Disease Prediction in Neuroimaging: Investigating the Impact of Feature Selection
	24.1 Introduction
	24.2 Materials and Methods
		24.2.1 Datasets and Preprocessing
		24.2.2 Graph Construction
		24.2.3 Dimensionality Reduction
	24.3 Results
	24.4 Discussion
	References
25: Computational Methods for Anticancer Drug Discovery; The MCT4 Paradigm
26: 3D QSAR based Virtual Screening of Flavonoids as Acetylcholinesterase Inhibitors
	26.1 Introduction
	26.2 Methods
		26.2.1 Dataset and Molecules Preparation
		26.2.2 Confirmational Hunt, Pharmacophore Generation, Compound Alignment and Field QSAR
		26.2.3 SAR Activity Atlas Model
		26.2.4 Virtual Screening
	26.3 Results and Discussion
		26.3.1 Field 3D-QSAR: Field Points and Statistical Analysis
		26.3.2 Visualisation of Activity Atlas
	26.4 Virtual Screening and Molecular Docking
	26.5 Conclusion
	References
27: A Comparison of the Various Methods for Selecting Features for Single-Cell RNA Sequencing Data in Alzheimer´s Disease
	27.1 Introduction
	27.2 Performances of Feature Selection Methods on scRNA-Seq Datasets
		27.2.1 Dataset
	27.3 Performance on SVM, k-NN, and LDA Classifiers
	27.4 Discussion
	References
28: An Optimized Cloud Computing Method for Extracting Molecular Descriptors
	28.1 Introduction
	28.2 Material and Methods
	28.3 Implementation
		28.3.1 Dataset
		28.3.2 Dask Framework
		28.3.3 Methodology
	28.4 Results
	28.5 Conclusions and Future Work
	References
29: Prediction of Intracranial Temperature Through Invasive and Noninvasive Measurements on Patients with Severe Traumatic Bra...
	29.1 Background
	29.2 Material and Methods
		29.2.1 Study Environment
		29.2.2 Sample
		29.2.3 Measuring Instrument
		29.2.4 Data Collection Process
		29.2.5 Statistics
	29.3 Results
		29.3.1 Analysis of TBL
		29.3.2 TFA Analysis
		29.3.3 Analysis of TC
			29.3.3.1 Analysis of TA
	29.4 Discussion
	29.5 Conclusions
	References
30: Improving Patient-Centered Dementia Screening for General, Multicultural Population and Persons with Disabilities from Pri...
	30.1 Methodology
	30.2 Procedure
	30.3 Results
	30.4 Discussion
	References
31: Improved Regularized Multi-class Logistic Regression for Gene Classification with Optimal Kernel PCA and HC Algorithm
	31.1 Introduction
	31.2 Methodology
		31.2.1 Gathering Gene Sets Based on Optimal Kernel Principle Component Analysis (KPCA) and Hierarchical Clustering (HC) Algori...
		31.2.2 Classification with Regularized Multi-class Logistic Regression (RMLR) Algorithm
			31.2.2.1 Multi-class Logistic Regression (MLR)
			31.2.2.2 Regularized Logistic Regression (RLR)
				Lasso Penalty
				L2 Regularization
		31.2.3 Classification Evaluation Criteria
		31.2.4 Gene Expression Datasets
			31.2.4.1 EATM Dataset
			31.2.4.2 ATM Dataset
	31.3 Results and Discussion
	31.4 Conclusions
	References
32: Mathematical Study of the Perturbation of Magnetic Fields Caused by Erythrocytes
	32.1 Introduction
	32.2 Physical Prerequisites
	32.3 Statement of the Problem
	32.4 Solution of the Problem
	32.5 Magnetic Lines
	32.6 Discussion
	References
33: Computational Models for Biomarker Discovery
	33.1 Introduction
	33.2 Computational Models for Neurodegenerative Diseases
	33.3 Conclusions
	References
34: Radiomics for Alzheimer´s Disease: Fundamental Principles and Clinical Applications
	34.1 Introduction
		34.1.1 Etiology
		34.1.2 Pathophysiology
		34.1.3 Epidemiology
		34.1.4 Clinical Manifestations
		34.1.5 Prognosis and Quality of Life
		34.1.6 Diagnosis of the Disease
	34.2 Computational Methods and AD
	34.3 Radiomics
	34.4 Image Acquisition
	34.5 Image Reconstruction and Preprocessing
	34.6 Segmentation
		34.6.1 Manual Segmentation
		34.6.2 Automatic Segmentation
		34.6.3 Semiautomatic Segmentation
	34.7 Feature Extraction
		34.7.1 Manually Crafted Features (Semantic Features)
		34.7.2 Mathematically Extracted Features (Non-semantic Features)
	34.8 Feature Selection
	34.9 Classification Methods
	34.10 Statistical Approaches
		34.10.1 Univariate Statistics
		34.10.2 Bivariate Statistics
		34.10.3 Multivariate Statistics
	34.11 The Role of Explainability
	34.12 Limitations and Future Work
		34.12.1 Limitations of Radiomics Applications
		34.12.2 Future Perspectives
	34.13 Conclusion
	References
Index