Related Experiment Video
Updated: Jul 17, 2025
10:10
Three Differential Expression Analysis Methods for RNA Sequencing: limma, EdgeR, DESeq2
Published on: September 18, 2021
37.6K
Deep-Cloud: A Deep Neural Network-Based Approach for Analyzing Differentially Expressed Genes of RNA-seq Data
Ying Zhou1, Ting Qi1, Min Pan2
1State Key Laboratory of Bioelectronics, School of Biological Science & Medical Engineering, Southeast University, Nanjing 210096, China.
Journal of Chemical Information and Modeling
|September 8, 2023
Summary
A new deep learning method, Deep-Cloud, enhances the analysis of RNA-sequencing (RNA-seq) data for identifying differentially expressed genes (DEGs). This approach improves sensitivity and accuracy in biomedical research.
Area of Science:
- Bioinformatics
- Computational Biology
- Genomics
Background:
- RNA-sequencing (RNA-seq) data analysis for differentially expressed genes (DEGs) is an evolving field.
- Deep neural networks offer novel possibilities for exploring gene expression information in RNA-seq data.
Purpose of the Study:
- To develop a novel approach, Deep-Cloud, for analyzing RNA-seq data to identify DEGs.
- To leverage deep learning and cloud models for enhanced DEG analysis in the biomedical field.
Main Methods:
- Developed Deep-Cloud, integrating convolutional neural networks (CNN) and long short-term memory (LSTM) for feature extraction and gene expression estimation.
- Combined deep learning with cloud models for uncertainty quantification and in-depth DEG analysis between disease and control groups.
Main Results:
- Deep-Cloud demonstrated improved sensitivity and accuracy in identifying DEGs compared to traditional software.
- The model effectively extracts features and estimates gene expression from RNA-seq data.
Conclusions:
- Deep-Cloud presents a novel pathway for mining RNA-seq data in biomedical research.
- The integration of deep learning and cloud models offers a robust method for DEG analysis.
