Feature selection in single-cell RNA sequencing data: a comprehensive evaluation
Single-cell RNA sequencing (scRNA-seq) has revolutionized biological and medical research, providing unique insights into the intricate cell-type compositions within various tissues. Unlike bulk RNA sequencing, scRNA-seq allows for examining gene expression at the individual cell level, r...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Academia.edu Journals
2024-09-01
|
| Series: | Academia Biology |
| Online Access: | https://www.academia.edu/123921464/Feature_selection_in_single_cell_RNA_sequencing_data_a_comprehensive_evaluation |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Single-cell RNA sequencing (scRNA-seq) has revolutionized biological and medical research, providing unique insights into the intricate cell-type compositions within various tissues. Unlike bulk RNA sequencing, scRNA-seq allows for examining gene expression at the individual cell level, revealing cellular heterogeneity and identifying rare cell types. However, the high dimensionality and inherent noise in scRNA-seq data pose significant analytical challenges. This study focuses on dimensionality reduction and cell-type identification in scRNA-seq data analysis. We developed the GenesRanking package, which offers 20 techniques for dimensionality reduction, including filter-based and embedding machine learning–based methods. By integrating feature selection methods from both statistics and machine learning, we provide a robust framework for improving data interpretation. Our comprehensive evaluation across five diverse scRNA-seq datasets demonstrates that although some methods show consistent performance, the technique should be chosen according to specific datasets for obtaining optimal results. Our findings underscore the enduring necessity for further refinement and continuous innovation in the field of scRNA-seq analysis, aiming to enhance the accuracy of cell-type identification and improve overall data interpretation. |
|---|---|
| ISSN: | 2837-4010 |