This book constitutes the proceedings of the 10th International Conference on Computational Advances in Bio and Medical Sciences, ICCABS 2020, held in December 2020. Due to COVID-19 pandemic the conference was held virtually.The 6 regular and 5 invited papers presented in this book were carefully reviewed and selected from 16 submissions. The use of high throughput technologies is fundamentally changing the life sciences and leading to the collection of large amounts of biological and medical data. The papers show how the use of this data can help expand our knowledge of fundamental biological processes and improve human health - using novel computational models and advanced analysis algorithms.
Author(s): Sumit Kumar Jha (editor), Ion Măndoiu (editor), Sanguthevar Rajasekaran (editor), Pavel Skums (editor), Alex Zelikovsky (editor)
Series: Lecture Notes in Computer Science; 12686
Publisher: Springer
Year: 2021
Language: English
Pages: 156
Preface
Organization
Contents
Computational Advances in Bio and Medical Sciences
DNA Read Feature Importance Using Machine Learning for Read Alignment Categories
1 Introduction
2 Related Work and Motivation
3 Methods
3.1 Data Acquisition and Read Mapping
3.2 Feature and Class Extraction
3.3 Machine Learning Methods
4 Results
4.1 Model Accuracy
4.2 Feature Importance
4.3 Feature Ranking Similarity Across Different Data
4.4 Machine Learning Filter Proof-of-Concept
5 Conclusions
References
MetaProb 2: Improving Unsupervised Metagenomic Binning with Efficient Reads Assembly Using Minimizers
1 Introduction
2 Method
2.1 Phase 1: Unitig Construction
2.2 Phase 2: Community Detection
2.3 Phase 3: Species Identification
3 Results and Discussion
3.1 Datasets Description and Performance Evaluation Metrics
3.2 Results
4 Conclusions and Future Work
References
Computational Study of Action Potential Generation in Urethral Smooth Muscle Cell
1 Introduction
2 Methods
3 Results
4 Discussion
References
Metabolic Pathway Prediction using Non-negative Matrix Factorization with Improved Precision
1 Introduction
2 Method
2.1 Decomposing the Pathway EC Association Matrix
2.2 Community Reconstruction and Multi-label Learning
3 Experiments
3.1 T1 Golden Data
3.2 Three E. coli Data
3.3 Mealybug Symbionts Data
3.4 CAMI and HOTS Data
4 Conclusion
References
A Novel Pathway Network Analytics Method Based on Graph Theory
1 Introduction
2 Methods
2.1 Identification of Significantly Enriched Pathways
2.2 Construction of a Weighted Network
2.3 Identification of Sub-networks
2.4 Identification of Important Pathways
3 Results and Discussions
3.1 Dataset Employed
3.2 Outcomes and Relevant Discussions
4 Conclusions
References
Latent Variable Modelling and Variational Inference for scRNA-seq Differential Expression Analysis
1 Introduction
2 Methods
2.1 ext-ZINBayes
2.2 SIENA
3 Results
4 Conclusion
References
Computational Advances for Single-Cell Omics Data Analysis
Computational Cell Cycle Analysis of Single Cell RNA-Seq Data
1 Background and Motivation
2 Methods
2.1 Datasets
2.2 The SC1 Cell Cycle (SC1CC) Analysis Tool
3 Results and Discussion
3.1 Results on the hESC Dataset
3.2 Results on the PBMC Dataset
3.3 Results on the -CTLA-4 Dataset
3.4 Results on the mHSC Dataset
4 Conclusion
References
Single-Cell Gene Regulatory Network Analysis Reveals Potential Mechanisms of Action of Antimalarials Against SARS-CoV-2
1 Introduction
2 Materials and Methods
2.1 Data Set
2.2 Machine Learning Workflow
3 Results and Discussion
4 Conclusion
References
Computational Advances for Next Generation Sequencing
RACCROCHE: Ancestral Flowering Plant Chromosomes and Gene Orders Based on Generalized Adjacencies and Chromosomal Gene Co-occurrences
1 Introduction
2 Methods
2.1 Input
2.2 The Pipeline
2.3 Visualizing and Evaluating the Reconstruction
2.4 Ancestral Gene Function
3 Reconstruction of Monocot Ancestors
3.1 Properties of the Contig Reconstruction
3.2 Clustering
3.3 Painting the Chromosomes of the Present-Day Genomes
3.4 Evaluation
3.5 MCScanX Visualization
4 Discussions and Conclusions
A Redistributing Genes from Families Exceeding Upper Size Limits
B Modes of Contig Construction
C Matching Contigs to Chromosomes of Extant Genomes
D Construction of Ancestral Chromosomes
E Functional Annotation of Ancestral Genes
References
A Fast Word Embedding Based Classifier to Profile Target Gene Databases in Metagenomic Samples
1 Introduction
2 Methods
2.1 Indexing Protein Reference Databases
2.2 Prediction of Short Reads
2.3 Databases
2.4 True Positive Dataset
2.5 False Positives Dataset
2.6 Time and Memory Profiling
2.7 Functional Annotation of Metagenomic Datasets
3 Results and Discussion
3.1 Detection of True Positive Hits
3.2 Detection of False Positives Hits
3.3 Time and Memory Usage of MetaMLP
3.4 Functional Annotation of Different Environments
3.5 Observation of MetaMLP Annotations Against an Extensive Metagenomics Study
4 Conclusions
References
Clustering Based Identification of SARS-CoV-2 Subtypes
1 Background
2 Clustering Methods
2.1 CliqueSNV Based Clustering
2.2 k-modes Clustering
2.3 MeShClust
2.4 Gap Filling
3 Assessment of Clustering Viral Subtypes
3.1 Cluster Entropy
3.2 Fitness
4 Results
4.1 Analysis of GISAID Data
4.2 Analysis of EMBL-EBI Data
5 Conclusions
References
Author Index
