Computational Advances in Bio and Medical Sciences: 11th International Conference, ICCABS 2021, Virtual Event, December 16–18, 2021, Revised Selected Papers (Lecture Notes in Bioinformatics)

This book constitutes revised selected papers from the refereed proceedings of the 11th International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2021, held as a virtual event during December 16–18, 2021. The 13 full papers included in this book were carefully reviewed and selected from 17 submissions. They were organized in topical sections as follows: Computational advances in bio and medical sciences; and computational advances in molecular epidemiology. Preface Organization Contents Computational Advances in Bio and Medical Sciences Single Model Quality Estimation of Protein Structures via Non-negative Tensor Factorization 1 Introduction 2 Related Works 3 Methodology 3.1 Stage I: From Structures to Groups 3.2 Stage II: Ranking Groups 3.3 Stage III: Partitioning Groups into Subgroups 3.4 Stage IV: Scoring Each Structure 3.5 Experimental Setup 3.6 Dataset 3.7 Evaluation Metrics 4 Results 4.1 Comparative Evaluation on Correlation with TM-Score 4.2 Loss-Based Comparison 4.3 Statistical Significance Analysis 5 Conclusion References Graph Representation Learning for Protein Conformation Sampling 1 Introduction 1.1 Related Work 2 Methods 3 Results 3.1 Experimental Setup 3.2 Evaluation of Models on Fixed-Length Chains 3.3 Evaluation of Models on Variable-Length Chains 4 Conclusion References Excerno: Filtering Mutations Caused by the Clinical Archival Process in Sequencing Data 1 Introduction 2 Excerno: A Bayes Classifier Using Mutational Signatures 3 Simulation and Evaluation Approach 4 Simulation Results 4.1 Performance Characteristics Across Different COSMIC Baseline Signatures 4.2 Performance Characteristics Across Different Percentages of FFPE 5 Conclusions References Relabeling Metabolic Pathway Data with Groups to Improve Prediction Outcomes 1 Introduction 2 Method 2.1 Feed-Forward Phase 2.2 Feed-Backward Phase 2.3 Closing the Loop 3 Experiments 3.1 Accumulated History Probability Analysis 3.2 Metabolic Pathway Prediction 4 Conclusion References MELEPS: Multiple Expert Linear Epitope Prediction System 1 Introduction 2 Materials and Methods 2.1 Data Collection 2.2 The System Flow of MELEPS 2.3 Integrated Multi-expert Recommendation Methodology 2.4 The Weighted Recommendation Score 2.5 Performance Measurement of Recommendation 3 Results and Discussion 3.1 The Weight Parameter Table 3.2 Performance of MELEPS 3.3 The MELEPS Platform 4 Conclusion References Encoder-Decoder Architectures for Clinically Relevant Coronary Artery Segmentation 1 Introduction 2 Related Work 2.1 Major Vessel Segmentation 2.2 Full Coronary Tree Segmentation 2.3 Catheter and Full Coronary Tree Segmentation 2.4 Other Segmentation Criteria 3 Model Evaluation Metrics 4 Loss Function 5 Architecture 5.1 Encoder Comparison 5.2 Decoder Comparison 5.3 EfficientUNet++ Architecture 5.4 Performance vs. Computation Trade-Off 6 Experimental Results 7 Implementation Details 7.1 Training Methodology 7.2 Dataset 7.3 Data Augmentation 8 Discussion and Future Work References Unified SAT-Solving for Hard Problems of Phylogenetic Network Construction 1 Introduction: Evolutionary Trees and Phylogenetic Networks 2 Definitions and Problem Statements 3 The CNF Formula for the TFP 3.1 Identifying, Counting and Limiting Reticulation Nodes in D 4 Hybridization Networks: Reticulation Networks When Input Trees Are Specified 5 Some Empirical Results 5.1 Summary of the Empirical Conclusions References Feature Selection for Identification of Risk Factors Associated with Infant Mortality 1 Introduction 2 Method 2.1 Study Design and Casuistic 2.2 Database Integration 2.3 Data Analysis, Cleaning and Preparation 2.4 Identification of Main Variables 2.5 Tools, Techniques and Software Used 3 Results 3.1 Data Description 3.2 Feature Selection 4 Discussion 5 Final Considerations References Addressing Classification on Highly Imbalanced Clinical Datasets 1 Introduction 2 Related Works 3 Materials and Methods 3.1 Method Overview 3.2 Avocado Dataset and Data Cleaning 3.3 Performance Metrics 4 Results 4.1 Techniques Comparison for Demographics Data Section 4.2 Classifiers and Techniques Comparison for Demographics Section 4.3 All Data Sections Comparisons 5 Conclusion References mcPBWT: Space-Efficient Multi-column PBWT Scanning Algorithm for Composite Haplotype Matching 1 Introduction 2 Preliminaries 2.1 PBWT Overview 2.2 Composite Haplotype Matching 3 Multi-column PBWT 3.1 Divergence Value Properties 3.2 Finding Blocks of Starting Matches 3.3 double-PBWT 3.4 double-PBWT: Comparing Block of Matches 3.5 triple-PBWT 4 Discussion References Computational Advances in Molecular Epidemiology Clustering SARS-CoV-2 Variants from Raw High-Throughput Sequencing Reads Data 1 Introduction 2 Related Work 3 Proposed Approach 3.1 Producing Consensus Sequences 3.2 Embedding Approaches 3.3 Clustering Algorithms 4 Experimental Evaluation 4.1 Dataset Statistics and Visualization 4.2 Evaluation Metrics 4.3 Clustering Comparison Metrics 5 Results and Discussion 5.1 Clustering Evaluation 5.2 Comparing Different Clusterings 5.3 Information Gain 5.4 Statistical Analysis 6 Conclusion References Analysis of SARS-CoV-2 Temporal Molecular Networks Using Global and Local Topological Characteristics 1 Introduction 2 Data and Methods 2.1 Data and Preprocessing 2.2 Construction of Temporal Networks 2.3 Global Network Analysis 2.4 Local Topological Analysis 2.5 Quantification of Nucleotide Variation 2.6 Spectral Network Partitioning 2.7 Phylogenetic Analysis 3 Results and Analysis 3.1 Genetic Characterization of the Viral Population 3.2 Changes in Global Properties 3.3 Association Between RGF Distance and Genetic Variation 3.4 Laplacian Network Partitioning Versus Phylogenetic Analysis 4 Conclusions References An SVM Based Approach to Study the Racial Disparity in Triple-Negative Breast Cancer 1 Introduction 2 Data and Methods 2.1 Data and Prepossessing 2.2 Construction of SVM Based Model for Feature Selection 2.3 Estimation of Feature/Gene 2.4 Feature/Gene Validation Analysis 3 Results and Discussion 3.1 Selection of Final Features 3.2 Expression Status of the Features/Gene 3.3 Association of High Expression of KLK10 and Survival Outcome of TNBC 4 Conclusion References Author Index