Computational Intelligence Methods for Bioinformatics and Biostatistics: 16th International Meeting, CIBB 2019, Bergamo, Italy, September 4–6, 2019, Revised Selected Papers

Preface
Organization
Contents
Computational Intelligence Methods for Bioinformatics and Biostatistics
A Smartphone-Based Clinical Decision Support System for Tremor Assessment
1 Introduction
2 Related Work
3 Method
3.1 Data Collection
3.2 Data Preparation
3.3 Feature Extraction and Selection
4 Results
5 Concluding Remarks and Discussion
References
cyTRON and cyTRON/JS: Two Cytoscape-Based Applications for the Inference of Cancer Evolution Models
1 Scientific Background
2 Materials and Methods
3 Case Study
4 Conclusion and Future Work
References
Effective Use of Evolutionary Computation to Parameterise an Epidemiological Model
1 Scientific Background
2 Materials and Methods
2.1 Tools
2.2 Model
2.3 Optimisation
3 Results
3.1 Parameter Optimisation
3.2 Clustering the Optimal Solutions
3.3 Model Predictions
4 Conclusion
References
Extending Knowledge on Genomic Data and Metadata of Cancer by Exploiting Taxonomy-Based Relaxed Queries on Domain-Specific Ontologies
1 Scientific Background
2 Materials and Methods
2.1 Data Overview
2.2 Taxonomy-Based Relaxed Queries
3 Results
3.1 Upward Extension
3.2 Downward Extension
3.3 Use Case Scenario
4 Conclusion
References
GAN-Based Multiple Adjacent Brain MRI Slice Reconstruction for Unsupervised Alzheimer's Disease Diagnosis
1 Introduction
2 Automated Alzheimer's Disease Diagnosis
3 Materials and Methods
3.1 OASIS-3 Dataset
3.2 GAN-Based Multiple Adjacent Brain MRI Slice Reconstruction
3.3 Unsupervised Alzheimer's Disease Diagnosis
4 Results
4.1 Reconstructed Brain MRI Slices
4.2 Unsupervised AD Diagnosis Results
5 Conclusions and Future Work
References
Improving the Fusion of Outbreak Detection Methods with Supervised Learning
1 Scientific Background
2 Materials and Methods
2.1 Evaluation Measures
2.2 Training Data for the ML-based Fusion
2.3 Evaluation Data
3 Results
3.1 Experimental Setup
3.2 Evaluation on Synthetic Data
3.3 Evaluation on Real Data
4 Conclusion
References
Learning Cancer Drug Sensitivities in Large-Scale Screens from Multi-omics Data with Local Low-Rank Structure
1 Introduction
2 Materials and Methods
2.1 Model
2.2 Learning Method
2.3 Including Full-Rank Non-omics Data Sources
3 Numerical Study
3.1 Simulation Setups and Details
3.2 Numerical Results
3.3 Additional Results Including Nonpenalized Coefficients
4 Real Data Analysis: GDSC Data
5 Discussion and Conclusion
References
Mass Spectra Interpretation and the Interest of SpecFit for Identifying Uncommon Modifications
1 Scientific Background
2 Materials and Methods
3 Results
4 Conclusion
References
MSAX: Multivariate Symbolic Aggregate Approximation for Time Series Classification
1 Introduction
2 Materials and Methods
2.1 MSAX Discretization
2.2 Dissimilarity Definition
3 Results
4 Conclusion
References
NeoHiC: A Web Application for the Analysis of Hi-C Data
1 Introduction
2 Materials and Methods
3 Results
4 Conclusion and Future Development
References
Random Sample Consensus for the Robust Identification of Outliers in Cancer Data
1 Introduction
2 Materials and Methods
2.1 Random Sample Consensus
2.2 Logistic Regression
2.3 Datasets
3 Results
4 Conclusion
References
Solving Equations on Discrete Dynamical Systems
1 Introduction
2 Background
3 More Background and a Useful Notation
4 Contributions
5 The Colored-Tree Method
6 Experimental Evaluation
7 Conclusion
References
SW+: On Accelerating Smith-Waterman Execution of GATK HaplotypeCaller
1 Introduction
2 Smith-Waterman Algorithm
3 Our Optimization
4 Measurements
5 Conclusion
References
Algebraic and Computational Methods for the Study of RNA Behaviour
Algebraic Characterisation of Non-coding RNA
1 Introduction
2 Materials and Methods
3 Results
3.1 Ligand Binding Function
3.2 Enzymatic Function
3.3 Model Checking
4 Conclusions
References
Bi-alignments as Models of Incongruent Evolution of RNA Sequence and Secondary Structure
1 Introduction
2 Theory
2.1 Bi-alignments
2.2 Limited Shifting and Complexity
2.3 Implementation
3 A Survey for Incongruent RNA Evolution
4 Multiple Bi-alignments and Poly-alignments
5 Conclusion and Outlook
References
Label Core for Understanding RNA Structure
1 Introduction
2 Generalized Context-Free Grammars
3 Label Core Grammar
4 RNA Structural Analysis
5 Conclusion
References
Modification of Valiant's Parsing Algorithm for the String-Searching Problem
1 Introduction
2 Background
2.1 Formal Languages
2.2 Valiant's Parsing Algorithm
3 Modified Valiant's Algorithm
3.1 Layered Submatrices Processing
3.2 Correctness and Complexity
3.3 Algorithm for Substrings
4 Evaluation
5 Conclusion and Future Works
References
On Secondary Structure Analysis by Using Formal Grammars and Artificial Neural Networks
1 Introduction
2 Ordinary Context-Free Grammars and Artificial Neural Networks for Secondary Structure Analysis
3 Convolutional Neural Network Utilization
4 Parsing Step Elimination
5 Evaluation
6 Conclusion
References
Intelligence Methods for Molecular Characterization and Dynamics in Translational Medicine
Integration of Single-Cell RNA-Sequencing Data into Flux Balance Cellular Automata
1 Scientific Background
2 Materials and Methods
2.1 The FBCA framework
2.2 Integration of ScRNA-Seq Data
2.3 Experimental Setting
3 Results
4 Conclusion
References
Machine Learning in Healthcare Informatics and Medical Biology
Characterizing Bipolar Disorder-Associated Single Nucleotide Polymorphisms in a Large British Cohort Using Association Rules
1 Scientific Background
2 Related Work
3 Materials and Methods
4 Results
4.1 Descriptive Analysis
4.2 Association Rules
5 Conclusion
References
Evaluating Deep Semi-supervised Learning for Whole-Transcriptome Breast Cancer Subtyping
1 Scientific Background
2 Materials and Methods
2.1 Datasets
2.2 Supervised Learning
2.3 Semi-supervised Learning
3 Experiments
3.1 Experimental Settings
3.2 Experimental Results
4 Conclusion
References
Learning Weighted Association Rules in Human Phenotype Ontology
1 Introduction
2 Materials and Methods
2.1 The Human Phenotype Ontology
2.2 Association Rules
2.3 Weighting HPO Term with Information Content
3 The HPO-Miner Algorithm
4 Results
4.1 Analysis of Mined Rules
5 Conclusion
References
Network Modeling and Analysis of Normal and Cancer Gene Expression Data
1 Scientific Background
2 Materials and Methods
2.1 Data Extraction and Pre-processing
2.2 Building the Networks
3 Results
3.1 Pearson's Correlation Networks
3.2 Euclidean Networks
3.3 Inverse Covariance Networks
3.4 Network Comparison
4 Conclusions
References
Regularization Techniques in Radiomics: A Case Study on the Prediction of pCR in Breast Tumours and the Axilla
1 Scientific Background
2 Materials and Methods
2.1 Regularization Methods
2.2 Breast Cancer Data
2.3 Statistical Analysis
3 Results
3.1 Breast Tumor pCR
3.2 Axilla pCR
4 Conclusion
References
Modeling and Simulation Methods for Computational Biology and Systems Medicine
In Silico Evaluation of Daclizumab and Vitamin D Effects in Multiple Sclerosis Using Agent Based Models
1 Introduction
1.1 Background
1.2 Daclizumab Treatment
2 Materials and Methods
2.1 The Multi-agent System Based Approach
3 An Agent Based Model for Multiple Sclerosis
3.1 Modeling of Vitamin D Effects over Disease Course
3.2 Extension of the Model with Daclizumab
4 Results
4.1 Analysis of Daclizumab Administration
4.2 Combining Vitamin D with a Reduced Dosage of Daclizumab
5 Conclusions
References
Multiple Sclerosis Disease: A Computational Approach for Investigating Its Drug Interactions
1 Introduction
2 Scientific Background
3 Materials and Methods
4 Results
5 Conclusion
References
Observability of Bacterial Growth Models in Bubble Column Bioreactors
1 Introduction
2 Bubble Column Reactor
3 Mathematical Model
3.1 Modelling Diffusion-Advection of Substrates
3.2 Biomass and Product Equations
4 Observability
5 Conclusions
References
On the Simulation and Automatic Parametrization of Metabolic Networks Through Electronic Design Automation
1 Scientific Background
2 Materials and Methods
2.1 Snoopy: Description and Usage
2.2 EDA Based Modeling Platform
3 Results
3.1 Network Construction from Metabolomics Data
3.2 Integrating Metabolomics Observations with Simulation Analysis
3.3 Comparing Our Platform with Snoopy
4 Conclusion
References
Deep Clustering for Metagenomics
1 Introduction
2 Methodology, Materials and Methods
2.1 Data and Features
2.2 Clustering Method
2.3 Research Methodology
2.4 Validation and Clustering Evaluation Metrics
2.5 The Proposed Model for Feature Extraction Based on Autoencoder and Convolutional Neural Networks
3 Results
4 Conclusion
References
Author Index