Related Experiment Video
Updated: Jun 9, 2026
10:00
High-throughput Quantitative Real-time RT-PCR Assay for Determining Expression Profiles of Types I and III Interferon Subtypes
Published on: March 24, 2015
Multi-cohort transcriptomic analysis with machine learning identifies interferon-related candidate genes in systemic
Aishanjiang Apaer1, Alimijiang Aobulitalifu1, Jumahong Keyoumu1
1Department of Pharmacy, The First People's Hospital of Kashi Prefecture, Xinjiang, China.
Autoimmunity
|June 8, 2026
Summary
This study identifies key interferon-related genes in Systemic Lupus Erythematosus (SLE) using a multi-cohort approach and machine learning. RSAD2 emerged as a prioritized gene, offering new insights into SLE pathogenesis.
Area of Science:
- Immunology
- Genomics
- Computational Biology
Background:
- Systemic Lupus Erythematosus (SLE) is a complex autoimmune disease with unclear molecular drivers.
- Transcriptomic studies indicate interferon pathway involvement, but gene prioritization across studies is difficult.
Purpose of the Study:
- To develop a robust computational framework for prioritizing candidate genes in SLE across multiple independent cohorts.
- To identify reproducible molecular signatures and generate testable hypotheses for SLE.
Main Methods:
- Multi-cohort transcriptomic analysis of public GEO datasets.
- Independent differential expression analysis and machine learning (LASSO, SVM, Random Forest) for gene prioritization.
- SHAP analysis for model interpretability, CIBERSORT for immune cell deconvolution, and in silico simulations for protein-compound interactions.
Main Results:
- Identified consistently dysregulated genes across cohorts, predominantly linked to interferon signaling.
- RSAD2 was robustly prioritized by multiple machine learning models.
- Machine learning models demonstrated stable predictive performance in validation datasets.
- Immune deconvolution revealed altered immune cell composition in SLE, and in silico analysis suggested a potential artemisinin-RSAD2 interaction.
Conclusions:
- The study presents a reliable multi-cohort computational framework for SLE gene discovery.
- Interferon-associated transcriptional features are reproducible molecular signatures of SLE.
- Findings provide a foundation for future experimental validation and clinical investigation of SLE biomarkers and therapeutics.
