Practical Applications of Computational Biology and Bioinformatics, 16th International Conference (PACBB 2022)

Description

This book is suitable for researchers and practitioners in biology, medicine and health sciences and bioinformatics. The success of bioinformatics and computational biology in recent years has been driven by research through computational tools and techniques that are essential for data analysis in modern biology and medicine. Systems biology is a related research area that has been replacing the reductionist view that dominated biology research in the last decades, requiring the coordinated efforts of biological researchers with those related to data analysis, mathematical modelling, computer simulation and optimization. The accumulation and exploitation of large-scale databases prompt new computational technology and for research into these issues. In this context, many widely successful computational models and tools used by biologists in these initiatives, such as clustering and classification methods for gene expression data, are based on computer science/ artificial intelligence (CS/AI) techniques. In fact, these methods have been helping in tasks related to knowledge discovery, modelling and optimization tasks, aiming at the development of computational models so that the response of biological complex systems to any perturbation can be predicted. This proceedings of the 16th International Conference on Practical Applications of Computational Biology and Bioinformatics (PACBB), held in L’Aquila (Italy) from July 13 to 15, 2022, contains ten original contributions of authors from many different countries (Bahrain, Canada, France, Italy, Portugal, Saudi Arabia, Spain, and UK) and different subfields in bioinformatics and computational biology. It is also suitable for artificial intelligence researchers interested in exploring applications in biology and health sciences and computational models. Preface Acknowledgements Organization Contents TooT-BERT-T: A BERT Approach on Discriminating Transport Proteins from Non-transport Proteins 1 Introduction 2 Related Work 3 Materials and Methods 3.1 Dataset 3.2 Protein Sequence Representation 3.3 Fine-Tuning a BERT Model 3.4 Logistic Regression 3.5 Evaluation 3.6 Evaluation Metrics 4 Results and Discussion 4.1 Fine-Tuning ProtBERT-BFD and MembraneBERT 4.2 Logistic Regression with Fine-Tuned ProtBERT-BFD 4.3 Comparison of TooT-BERT-T with State-of-the-Art Models 5 Conclusion References Machine Learning and Deep Learning Techniques for Epileptic Seizures Prediction: A Brief Review 1 Introduction 2 Signal Processing and Feature Extraction 2.1 Feature Extraction 2.2 Feature Selection 3 Seizure Detection and Classification 4 Seizure Prediction 4.1 Animal Models 4.2 Human Subjects 5 Conclusion References The Covid-19 Decision Support System (C19DSS) – A Mobile App 1 Introduction 2 Background 3 C19DSS 3.1 Architecture 3.2 Usability Evaluation 3.3 Preliminary Use 4 Discussion 5 Conclusions References Towards a Flexible and Portable Workflow for Analyzing miRNA-Seq Neuropsychiatric Data: An Initial Replicability Assessment 1 Introduction 2 Materials and Methods 2.1 Data Acquisition 2.2 myBrain-Seq Implementation 2.3 Experimental Setup 3 Results and Discussion 3.1 Quality Control 3.2 Application of the Same Statistical Thresholds as the Original Articles 3.3 Comparison Between the Original Results, MiARma-Seq Results and MyBrain-Seq Results 4 Conclusion References The NAD Interactome, Identification of Putative New NAD-Binding Proteins 1 Introduction 2 Methods 2.1 Data Collection and Definition of Protein Datasets 2.2 Datasets Analysis 2.3 Identification of Putative New NAD-Binding Proteins 3 Results 3.1 NAD-Binding Proteins (NADBPs) Dataset 3.2 NAD-Protein-Protein Interactions (NAD-PPIs) Dataset 3.3 Pathway Enrichment Analysis 3.4 Characterization of Protein Domains of the NADBPs Dataset 3.5 Identification of Putative NAD-Binding Proteins 4 Discussion 5 Conclusion References Multiple Instance Learning Based on Mol2vec Molecular Substructure Embeddings for Discovery of NDM-1 Inhibitors 1 Introduction 2 Materials and Methods 2.1 Dataset Collection 2.2 Labeling the Database 2.3 Calculating Mol2vec Embeddings 2.4 Classification and Ranking Frame Work 3 Results and Discussion 3.1 Results 4 Conclusion References Towards Improving Bio-Image Segmentation Quality Through Ensemble Post-processing of Deep Learning and Classical 3D Segmentation Pipelines 1 Introduction 2 Previous Research on Ensemble Methods for Segmentation 3 Methodology 3.1 3D Segmentation Pipelines 3.2 Dataset 3.3 Fusion Algorithm 1: Label Set Intersection 3.4 Fusion Algorithm 2: Region Adjacency Graphs 3.5 Fusion Algorithm 3: Boundary Fusion with 3D Watershed 3.6 Segmentation Evaluation Metric 4 Results 4.1 Results from Original Pipelines 4.2 Results from Fusion Algorithm 1 4.3 Results from Fusion Algorithm 2 4.4 Results from Fusion Algorithm 3 5 Discussions 6 Data and Code Availability References Exploring Xylella fastidiosa's Metabolic Traits Using a GSM Model of the Phytopathogenic Bacterium 1 Introduction 2 Materials and Methods 2.1 Software 2.2 Metabolic Model Reconstruction 2.3 Identification of Potential Drug Targets 3 Results and Discussion 3.1 Model Validation 3.2 Drug Targeting 4 Conclusion 5 Supplementary Materials References Genomic Regions with Atypical Concentration of Inverted Repeats 1 Introduction 2 Methods 2.1 Distance Between Inverted Repeats 2.2 Measuring the Concentration of Inverted Repeats 2.3 Windows Selection 3 Results 4 Discussion and Conclusion References EvoPPI 2: A Web and Local Platform for the Comparison of Protein–Protein Interaction Data from Multiple Sources from the Same and Distinct Species 1 Introduction 2 Methods 2.1 Data 2.2 Web Interface Updates 2.3 Using EvoPPI Locally 3 Results and Discussion 4 Conclusion References Author Index