Bioinformatics and Biomedical Engineering: 6th International Work-Conference, IWBBIO 2018, Granada, Spain, April 25–27, 2018, Proceedings, Part I (Lecture Notes in Computer Science Book 10813)

This two-volume set LNBI 10813 and LNBI 10814 constitutes the proceedings of the 6th International Work-Conference on Bioinformatics and Biomedical Engineering, IWBBIO 2018, held in Granada, Spain, in April 2018.The 88 regular papers presented were carefully reviewed and selected from 273 submissions. The scope of the conference spans the following areas: bioinformatics for healthcare and diseases; bioinformatics tools to integrate omics dataset and address biological question; challenges and advances in measurement and self-parametrization of complex biological systems; computational genomics; computational proteomics; computational systems for modelling biological processes; drug delivery system design aided by mathematical modelling and experiments; generation, management and biological insights from big data; high-throughput bioinformatic tools for medical genomics; next generation sequencing and sequence analysis; interpretable models in biomedicine and bioinformatics; little-big data. Reducing the complexity and facing uncertainty of highly underdetermined phenotype prediction problems; biomedical engineering; biomedical image analysis; biomedical signal analysis; challenges in smart and wearable sensor design for mobile health; and healthcare and diseases. Preface Organization Contents -- Part I Contents – Part II Bioinformatics for Healthcare and Diseases Trends in Online Biomonitoring Abstract 1 Introduction 2 Invasive Methods of Aquatic Organism Biomonitoring 3 Non-invasive Methods of Aquatic Organism Biomonitoring 4 Online Water Monitoring 5 Data and Metadata Management 6 Conclusion Acknowledgments References SARAEasy: A Mobile App for Cerebellar Syndrome Quantification and Characterization Abstract 1 Introduction 2 Methods 2.1 Modeling the SARA by Clinical Archetypes 2.2 Mapping the Archetype SARA to the HPO 3 Result 3.1 Dataset and Validation of SARAEasy 4 Discussion 5 Conclusion Acknowledgment References Case-Based Reasoning Systems for Medical Applications with Improved Adaptation and Recovery Stages 1 Introduction 2 Related Works and Background 3 Proposed Classification Approach 3.1 Oversampling and Undersampling Methodology for Class Balancing 3.2 Cascade Classification Methodology 3.3 SVM Probability Density Methodology 4 Results and Discussion 4.1 Database 4.2 Methods 4.3 Performance Measures 4.4 Experiments 5 Conclusion References Bioinformatics Tools to Integrate Omics Dataset and Address Biological Question Constructing a Quantitative Fusion Layer over the Semantic Level for Scalable Inference 1 Introduction 2 The Quantitative Semantic Fusion Framework 3 A Simple Model for Age-Related Macular Degeneration 4 Phases of the Methodology 4.1 Resource and Model Overview 4.2 Model Structure, Parameters, and Inference Rules 4.3 Adding Input Evidences 4.4 Adding Filters 4.5 Determining Outputs and Visualization 4.6 Checking Robustness of the Results 5 Conclusion References Challenges and Advances in Measurement and Self-Parametrization of Complex Biological Systems Effects of External Voltage in the Dynamics of Pancreatic β-Cells: Implications for the Treatment of Diabetes Abstract 1 Introduction 2 Methodology 2.1 Simulation of the Electrical Activity of Pancreatic Beta-Cells 2.2 Computational Routine and Statistical Analysis 3 Results 3.1 Simulations 3.2 Phase Space Analysis 4 Conclusions References ISaaC: Identifying Structural Relations in Biological Data with Copula-Based Kernel Dependency Measures 1 Introduction 2 MMD and the Two-Sample Problem 2.1 MMD for Kernel Functions 3 Copula Transformation 3.1 MMD Dependence Measure 3.2 Kernel Choice 4 Results 4.1 DREAM Challenge Results References Inspecting the Role of PI3K/AKT Signaling Pathway in Cancer Development Using an In Silico Modeling ... Abstract 1 Introduction 2 Materials and Methods 2.1 The Mathematical Model of Cellular Signal Transduction 2.2 The Implementation of the Mathematical Model: The Computational Simulation Tool for Cellular Sig ... 2.3 The PI3K/AKT Signaling Model 2.4 The Modeling and Simulation Methodology 3 Results and Discussions 3.1 Modeling of Reactions, Reactants and Cellular Processes 3.2 Simulation of PI3K/AKT Signaling Pathway 3.3 In Silico Experiments 4 Conclusions References Cardiac Pulse Modeling Using a Modified van der Pol Oscillator and Genetic Algorithms 1 Introduction 2 Modified van der Pol Model 3 ECG Signal Model Processing 3.1 Database 3.2 Preprocess 3.3 Extraction of Heartbeats 3.4 Parameters Optimization 4 Experimental Results 5 Conclusions References Visible Aquaphotomics Spectrophotometry for Aquaculture Systems 1 Introduction 2 Device Selection 2.1 Hue 2.2 Detection of Devices Error 3 Correlation Between Crucial Parameters and Spectral Characteristics 3.1 Experiment Setup 4 Results 5 Conclusion and Discussion References Resolution, Precision, and Entropy as Binning Problem in Mass Spectrometry 1 Introduction 2 Methods and Analysis 2.1 False Precision 2.2 Entropy 2.3 Weighting Factors 2.4 Implementation 3 Results 4 Conclusion and Discussion References Discrimination Between Normal Driving and Braking Intention from Driver's Brain Signals 1 Introduction 2 Methods and Materials 2.1 Participants, Vehicle and Test Track 2.2 EEG Recording System 2.3 Vehicle Information Acquisition System 2.4 Experimental Paradigm 2.5 Preprocessing and Dataset Preparation 2.6 Feature Extraction and Classification 2.7 Classification Performance Evaluation 3 Results 4 Conclusions References Unsupervised Parametrization of Nano-Objects in Electron Microscopy 1 Introduction 2 Setup, Methods and Implementation 2.1 Image Processing and Analysis 3 Results and Conclusion References Computational Genomics Models of Multiple Interactions from Collinear Patterns Abstract 1 Introduction 2 Dual Hyperlanes and Vertices in Parameter Space 3 Vertexical Planes in Feature Space 4 Convex and Piecewise Linear (CPL) Collinearity Functions 5 Optimal Vertices 6 Collinear Biclusters 7 Multiple Interactions Models Based on Biclusters 8 Examples of Computational Results 9 Concluding Remarks Acknowledgments References Identification of the Treatment Survivability Gene Biomarkers of Breast Cancer Patients via a Tree-B ... Abstract 1 Background 2 Materials and Methods 2.1 Class Imbalance 2.2 Feature Selection 2.3 Multi-class Classification Model 3 Results and Discussion 4 Biological Insight 5 Visualization 6 Conclusion Acknowledgement References Workflows and Service Discovery: A Mobile Device Approach 1 Introduction 2 Methods 3 Results 3.1 Searching and Invoking a Service 3.2 Generating a Workflow 4 Discussion 5 Conclusions References Chloroplast Genomes Exhibit Eight-Cluster Structuredness and Mirror Symmetry 1 Introduction 2 Frequency Dictionary and Genome Fragmentation 2.1 Genome Fragmentation 2.2 Fragment Phase Definition 3 Results 3.1 Clustering vs. Visualization 3.2 Symmetry in Genome Clustering 4 Discussion References Are Radiosensitive and Regular Response Cells Homogeneous in Their Correlations Between Copy Number ... Abstract 1 Introduction 1.1 Radiosensitivity Biomarkers in Radiotherapy Planning 1.2 Current Radiosensitivity Biomarker Studies 1.3 Current Copy Number State Analysis Approaches 2 Aim of Study 3 Material 4 Methods 4.1 Preprocessing and Data Preparation 4.2 SF2 and Copy Number State Correlation 4.3 Comparison of Correlations for Radiosensitive and Regular Response Cell Strains 4.4 Functional Analysis 5 Results 5.1 Pearson’s Correlation Coefficient and Cohen’s q 5.2 Qualitative Comparison of Pearson’s Correlation Coefficients 5.3 Functional Analysis 6 Discussion 7 Conclusions Acknowledgement References Computational Proteomics Protein Tertiary Structure Prediction via SVD and PSO Sampling Abstract 1 Introduction 2 Protein Tertiary Structure Modelling 3 Protein Tertiary Structure Refinement Algorithm 3.1 The SVD-PSO Algorithm 3.2 Minimization of the Free-Energy Function 4 Numerical Results 4.1 2L3F PDB Code Protein 4.2 Prediction of Other Proteins via SVD and PSO 5 Conclusions Acknowledgements References Fighting Fire with Fire: Computational Prediction of Microbial Targets for Bacteriocins Abstract 1 Introduction 2 Methods 2.1 Pipeline Overview 2.2 Data Collection and Dataset Construction 2.3 Prediction of Essential Proteins in Bacterial Organisms 2.4 Protein-Bacteriocin Interaction (PBI) Classification 3 Results and Discussion 3.1 Evaluation of the Best Predicted Targets 3.2 Analysis of the Best Scoring PBIs 3.3 Future Directions Acknowledgements Conflict of Interest References A Graph-Based Approach for Querying Protein-Ligand Structural Patterns 1 Introduction 2 Graph-Based Representation of Structural Patterns 2.1 Protein-Ligand Structural Patterns 2.2 Graph-Based Structural Patterns 3 GSP4PDB 3.1 Protein Data Extraction and Pre-processing 3.2 Protein Data Storage 3.3 Web User Interface 3.4 From Graph Patterns to SQL Queries 4 Conclusions References Computational Systems for Modelling Biological Processes Predicting Disease Genes from Clinical Single Sample-Based PPI Networks 1 Introduction 2 Method and Materials 2.1 Problem Formulation 2.2 Single Sample-Based Networks 2.3 Network Labeling 2.4 Data Sources 3 Experiments and Results 3.1 Evaluation Criteria 3.2 Results of the AUC 3.3 Top 10 Genes Analysis 4 Conclusion References Red Blood Cell Model Validation in Dynamic Regime 1 Introduction 2 Single Cell Model 3 Model Parameters Identification 4 Biological Experiment 5 Computational Setting 6 Results 7 Discussion and Conclusions References Exploiting Ladder Networks for Gene Expression Classification 1 Introduction 2 Dimensionality Reduction and Machine Learning Techniques 3 Ladder Networks 4 Tuning of the Ladder Network 5 Evaluation and Conclusions References Simulation of Blood Flow in Microfluidic Devices for Analysing of Video from Real Experiments 1 Introduction 2 Simulation of Blood Flow Experiments 3 Determination of Basis of Blood Flow Velocities 4 Evaluating Simulations Going Forward 5 Conclusions and Discussion References Alignment-Free Z-Curve Genomic Cepstral Coefficients and Machine Learning for Classification of Viruses Abstract 1 Introduction 2 Materials and Methods 2.1 Dataset 2.2 Z-Curve Genomic Cepstral Coefficients 2.3 Experiments 3 Results and Discussion 3.1 Power Spectrums of the Z-Curve Encoded Viruses 3.2 Classifier Training Results 4 Conclusion Acknowledgement References A Combined Approach of Multiscale Texture Analysis and Interest Point/Corner Detectors for Microcalcifications Diagnosis 1 Introduction 2 Materials and Methods 2.1 Dataset Selection 2.2 Textural Features Extraction 2.3 Interest Points Detection 2.4 Classification Model 3 Results 4 Discussion and Conclusion References An Empirical Study of Word Sense Disambiguation for Biomedical Information Retrieval System Abstract 1 Introduction 2 Related Work 3 Text Conceptualization Task 3.1 Text Preprocessing 3.2 Conceptualization 3.3 Disambiguation Strategies 4 Methods 4.1 Word Sense Disambiguation 4.2 Biomedical Information Retrieval System 5 Results and Discussion 5.1 Evaluation Measures 5.2 Experimental Results 6 Conclusion and Perspectives References Drug Delivery System Design Aided by Mathematical Modelling and Experiments Modelling the Release of Moxifloxacin from Plasma Grafted Intraocular Lenses with Rotational Symmetric Numerical Framework 1 Introduction 2 Methods 2.1 IOL Surface Modification and Drug Loading 2.2 Drug Release Studies 3 Model 3.1 Governing Equations 3.2 Discretization 3.3 Time Integration 4 Simulations 5 Discussion References Generation, Management and Biological Insights from Big Data Predicting Tumor Locations in Prostate Cancer Tissue Using Gene Expression 1 Background 2 Materials and Methods 2.1 Feature Selection 2.2 Classification 3 Results and Discussion 4 Conclusion References Concept of a Module for Physical Security of Material Secured by LIMS Abstract 1 Introduction 2 Problem Definition 3 Related Works 4 Module for Secured LIMS 4.1 Hardware Description 4.2 LIMS Connectivity 4.3 Graphical User Interface Development 5 Conclusion Acknowledgement References scFeatureFilter: Correlation-Based Feature Filtering for Single-Cell RNAseq 1 Introduction References High-Throughput Bioinformatic Tools for Medical Genomics NearTrans Can Identify Correlated Expression Changes Between Retrotransposons and Surrounding Genes in Human Cancer 1 Introduction 2 Materials and Methods 2.1 Input Data 2.2 Implementation 3 Results 4 Discussion References An Interactive Strategy to Visualize Common Subgraphs in Protein-Ligand Interaction 1 Introduction 2 Problem Modeling 2.1 Related Work 3 visGReMLIN 4 Results and Discussion 4.1 CDK2 Pattern Analysis 4.2 Ricin Pattern Analysis 4.3 visGReMLIN Patterns Compared to Experimental Patterns 5 Conclusion References Meta-Alignment: Combining Sequence Aligners for Better Results 1 Introduction 2 Method 2.1 Results 3 Conclusion References Exploiting In-memory Systems for Genomic Data Analysis 1 Introduction 2 Background 2.1 Advanced Hardware Architecture 2.2 In-memory Data Processing 3 The Variant Analysis Workflows 4 In-memory Systems in Action 4.1 Linux Piping 4.2 In Memory Systems for the Variant Annotation 4.3 Fault tolerance 5 Experimental Results 5.1 Experiment 1: Linux Piping 5.2 Experiment 2: In-memory Databases 6 Conclusions References Improving Metagenomic Assemblies Through Data Partitioning: A GC Content Approach 1 Introduction 2 Related Work 3 The Proposed Algorithm 4 Evaluation 4.1 Datasets and Platform 4.2 Results 5 Conclusion References Next Generation Sequencing and Sequence Analysis -1Quality Assessment of High-Throughput DNA Sequencing Data via Range Analysis 1 Introduction 2 Previous Studies 3 The Metrics and the Quality Assessment Method 4 Results 5 Conclusion 6 Appendix References A BLAS-Based Algorithm for Finding Position Weight Matrix Occurrences in DNA Sequences on CPUs and GPUs 1 Introduction 2 Algorithm Description 2.1 Pattern Matrix P 2.2 Sequence Matrix S 2.3 Result Matrix R 2.4 Implementation Details 2.5 GPU Version 3 Benchmark Results and Discussion 4 Conclusion References Analyzing the Differences Between Reads and Contigs When Performing a Taxonomic Assignment Comparison in Metagenomics 1 Introduction 2 Methods 2.1 Detecting Differences Between the Reads and Contigs 3 Results and Discussion 4 Conclusions References Estimating the Length Distributions of Genomic Micro-satellites from Next Generation Sequencing Data Abstract 1 Introduction 2 Methods 2.1 Model Framework 2.2 Identify Breakpoints and Repeat Units of MSIs 2.3 Estimating the Distribution Parameters of MSIs Lengths 3 Experiments and Results 3.1 Generating the Simulation Datasets 3.2 Performance Tests Under Different Numbers of MSIs, Coverages and Read Lengths 3.3 Comparison Experiments 4 Conclusions Acknowledgement References CIGenotyper: A Machine Learning Approach for Genotyping Complex Indel Calls Abstract 1 Introduction 2 Methods 2.1 Key Observations on Feature Selection 2.2 RVM Framework 2.3 Training the RVM Framework and Estimating Model Parameters 3 Experiments and Results 3.1 Generating Simulation Datasets 3.2 Comparisons Results Under Different Coverages 3.3 Further Analysis on Complex Indels Under High Coverages 3.4 Comparisons Results Under Different Read Lengths and Insert Sizes 4 Conclusions Acknowledgement References Genomic Solutions to Hospital-Acquired Bacterial Infection Identification Abstract 1 Introduction 2 A New Method for HAI Species Identification 3 Data and Methods 3.1 Neural Networks 3.2 Self-organizing Maps 3.3 Random Forests 4 Results 5 Conclusion and Further Research Acknowledgement References Interpretable Models in Biomedicine and Bioinformatics Kernel Conditional Embeddings for Associating Omic Data Types 1 Introduction 2 Kernel Conditional Embeddings 2.1 Measuring the Discrepancy Between Conditional Embeddings 3 Case Study 1: Glioblastoma Multiforme Cancer 4 Case Study 2: Breast Invasive Cancer 5 Conclusions References Metastasis of Cutaneous Melanoma: Risk Factors, Detection and Forecasting Abstract 1 Introduction 2 Methodology 2.1 Data Acquisition 2.2 Statistical Analysis 3 Results 4 Discussion Acknowledgements References Graph Theory Based Classification of Brain Connectivity Network for Autism Spectrum Disorder 1 Introduction 2 Related Work 3 Materials and Methods 3.1 Brain Connectivity Network Analysis 3.2 Machine Learning Methods 3.3 Dataset 4 Results 5 Conclusion References Detect and Predict Melanoma Utilizing TCBR and Classification of Skin Lesions in a Learning Assistant System 1 Introduction 2 Textual CBR and Word Association Strength 2.1 DePicT CLASS's Preliminary Concept 2.2 DePicT Profile Matrix of Melanoma 3 Image Processing and Classification 3.1 Feature Selection and Region Growing Segmentation 3.2 DePicT Melanoma CLASS-Classification 4 Tools and Dataset 5 Experimental Results and Validation 6 Conclusion References On the Use of Betweenness Centrality for Selection of Plausible Trajectories in Qualitative Biological Regulatory Networks 1 Introduction 1.1 Related Work 1.2 Our Contribution 1.3 Paper Organization 2 Methods 2.1 Qualitative Modeling Framework 2.2 CTL Quantifiers 2.3 Selection of Important Trajectories 3 Results and Discussion 3.1 Immunity Control in Bacteriophage 3.2 Network Analysis: Selection of Trajectories 4 Conclusion References Author Index This two-volume set LNBI 10813 and LNBI 10814 constitutes the proceedings of the 6th International Work-Conference on Bioinformatics and Biomedical Engineering, IWBBIO 2018, held in Granada, Spain, in April 2018. The 88 regular papers presented were carefully reviewed and selected from 273 submissions. The scope of the conference spans the following areas: bioinformatics for healthcare and diseases; bioinformatics tools to integrate omics dataset and address biological question; challenges and advances in measurement and self-parametrization of complex biological systems; computational genomics; computational proteomics; computational systems for modelling biological processes; drug delivery system design aided by mathematical modelling and experiments; generation, management and biological insights from big data; high-throughput bioinformatic tools for medical genomics; next generation sequencing and sequence analysis; interpretable models in biomedicine and bioinformatics; little-big data. Reducing the complexity and facing uncertainty of highly underdetermined phenotype prediction problems; biomedical engineering; biomedical image analysis; biomedical signal analysis; challenges in smart and wearable sensor design for mobile health; and healthcare and diseases This two volume set LNBI 10813 and LNBI 10814 constitutes the proceedings of the 6th International Work-Conference on Bioinformatics and Biomedical Engineering, IWBBIO 2018, held in Granada, Spain, in April 2018. The 88 regular papers presented were carefully reviewed and selected from 273 submissions. The scope of the conference spans the following areas: bioinformatics for healthcare and diseases; bioinformatics tools to integrate omics dataset and address biological question; challenges and advances in measurement and self-parametrization of complex biological systems; computational genomics; computational proteomics; computational systems for modelling biological processes; drug delivery system design aided by mathematical modelling and experiments; generation, management and biological insights from big data; high-throughput bioinformatic tools for medical genomics; next generation sequencing and sequence analysis; interpretable models in biomedicine and bioinformatics; little-big data. Reducing the complexity and facing uncertainty of highly underdetermined phenotype prediction problems; biomedical engineering; biomedical image analysis; biomedical signal analysis; challenges in smart and wearable sensor design for mobile health; and healthcare and diseases