Application of Deep Learning on Single-cell RNA Sequencing Data Analysis: A Review

Area of Science:

• Computational Biology
• Genomics
• Artificial Intelligence

Background:

• Single-cell RNA sequencing (scRNA-seq) quantifies gene expression in individual cells.
• scRNA-seq analysis is crucial for understanding cell states, biological processes, and diseases like cancer and COVID-19.
• High-dimensional, noisy scRNA-seq data presents analytical challenges.

Purpose of the Study:

• To review recent deep learning techniques applied to scRNA-seq data analysis.
• To identify key steps in the scRNA-seq pipeline improved by deep learning.
• To compare deep learning benefits against conventional methods and discuss future directions.

Main Methods:

• Survey of recently developed deep learning techniques for scRNA-seq data.
• Identification of deep learning applications across the scRNA-seq analysis pipeline.
• Comparative analysis of deep learning versus traditional analytical tools.

Main Results:

• Deep learning effectively extracts informative features from noisy, high-dimensional scRNA-seq data.
• Deep learning methods have advanced various stages of scRNA-seq data analysis.
• Deep learning offers advantages over conventional analytical tools for scRNA-seq data.

Conclusions:

• Deep learning is a powerful tool for scRNA-seq data analysis, improving downstream applications.
• Challenges remain in current deep learning approaches for scRNA-seq data.
• Future improvements in deep learning algorithms are expected to further advance scRNA-seq data analysis.