This Research Topic comprises the application of Data Structure (DS) and Soft Computing (SC) algorithms on next-generation sequencing data and medical imaging data. During the last two decades, many researchers have been working on Artificial Intelligence and Machine learning applications on sequencing data as well as medical imaging data. However, in bioinformatics applications, many algorithms are designed to obtain fast and memory-efficient solutions. Construction of a potential data structure helps in fast queries and saves the occupied memory that leads to reducing the time complexity. Fundamental DSs are used in this purpose, viz., generation of Hash table, Bloom filter, Suffix tree, Suffix array, BWT index, Bidirectional BWT index and many more. For medical imaging data, some advance DSs such as quad-tree have a vital role in the representation of image sequencing data, decomposition-based edge detection for medical image data analysis. In addition, greedy optimization methods are also useful for medical image data. Medical diagnosis and respective treatment belong to an NP-complete problem. Prefractal graphs and improved/revised version of NP-complete problem is highly efficient for modelling the large biological biomolecular networks and hub gene networks as they can generate potential best solutions for the problems on natural objects. Various DSs such as Heap, Segment trees apply to the segmentation of biomedical image data, while various soft computing-based techniques viz., optimization, fuzzy and rough set theory-based analysis are also beneficial to control such problems.
As DS-based approaches with optimized memory requirements are less expensive and more effective for the storage and analysis of big RNA/DNA sequencing data as well as high-scale medical image data, hence, nowadays, the demand to utilize DS and SC-based algorithms uniquely or jointly increases significantly rather than only using machine learning-based techniques. The scope of this special issue broadly covers the following points but is not limited to:
• DS to represent a set of very long DNA Sequences.
• DS and algorithms for the efficient storage of genomic and other sequence data.
• Hash table mapping and differential expression analysis from RNA Sequencing data, especially single-cell sequencing data.
• Predicting coaxial stacking in RNA sequencing data and RNA multibranch loops.
• Develop the Brain Imaging Data Structure (BIDS) in medical imaging data.
• Index-based searching for RNA sequence-structure pattern.
• BWT-index-based metagenomic classification.
• Bloom filter for representing large genome data.
• SVM classifier interpretation for medical image data using Quadtree.
• Region Quad-Tree Decomposition Based Edge Detection for medical image data analysis.
• Sequence-specific sorting of DNA molecules sequencing data.
• Faster genome mapping in next-generation sequencing data using perfect hamming code with a hash table.
• Medical Image Segmentation by various optimization algorithms.
• Medical Image segmentation using segment tree and rough set theory.
• Fuzzy or Rough set approaches for gene network inference using prefractal graphs and revised version of NP-completeness.
• Optimization on DS-based approaches applied to sequencing or imaging.
This Research Topic comprises the application of Data Structure (DS) and Soft Computing (SC) algorithms on next-generation sequencing data and medical imaging data. During the last two decades, many researchers have been working on Artificial Intelligence and Machine learning applications on sequencing data as well as medical imaging data. However, in bioinformatics applications, many algorithms are designed to obtain fast and memory-efficient solutions. Construction of a potential data structure helps in fast queries and saves the occupied memory that leads to reducing the time complexity. Fundamental DSs are used in this purpose, viz., generation of Hash table, Bloom filter, Suffix tree, Suffix array, BWT index, Bidirectional BWT index and many more. For medical imaging data, some advance DSs such as quad-tree have a vital role in the representation of image sequencing data, decomposition-based edge detection for medical image data analysis. In addition, greedy optimization methods are also useful for medical image data. Medical diagnosis and respective treatment belong to an NP-complete problem. Prefractal graphs and improved/revised version of NP-complete problem is highly efficient for modelling the large biological biomolecular networks and hub gene networks as they can generate potential best solutions for the problems on natural objects. Various DSs such as Heap, Segment trees apply to the segmentation of biomedical image data, while various soft computing-based techniques viz., optimization, fuzzy and rough set theory-based analysis are also beneficial to control such problems.
As DS-based approaches with optimized memory requirements are less expensive and more effective for the storage and analysis of big RNA/DNA sequencing data as well as high-scale medical image data, hence, nowadays, the demand to utilize DS and SC-based algorithms uniquely or jointly increases significantly rather than only using machine learning-based techniques. The scope of this special issue broadly covers the following points but is not limited to:
• DS to represent a set of very long DNA Sequences.
• DS and algorithms for the efficient storage of genomic and other sequence data.
• Hash table mapping and differential expression analysis from RNA Sequencing data, especially single-cell sequencing data.
• Predicting coaxial stacking in RNA sequencing data and RNA multibranch loops.
• Develop the Brain Imaging Data Structure (BIDS) in medical imaging data.
• Index-based searching for RNA sequence-structure pattern.
• BWT-index-based metagenomic classification.
• Bloom filter for representing large genome data.
• SVM classifier interpretation for medical image data using Quadtree.
• Region Quad-Tree Decomposition Based Edge Detection for medical image data analysis.
• Sequence-specific sorting of DNA molecules sequencing data.
• Faster genome mapping in next-generation sequencing data using perfect hamming code with a hash table.
• Medical Image Segmentation by various optimization algorithms.
• Medical Image segmentation using segment tree and rough set theory.
• Fuzzy or Rough set approaches for gene network inference using prefractal graphs and revised version of NP-completeness.
• Optimization on DS-based approaches applied to sequencing or imaging.