CFD+CD14+ Monocyte Signatures in Myasthenia Gravis from Multi-Omics and Machine Learning

A 1.3 KB CSV file published on figshare in May 2026 by Shuang Li. It contains results from a multi-omics integration study identifying a potential pathogenic monocyte subset in myasthenia gravis. The data likely contains signature genes and activity scores derived from transcriptome-wide association studies and single-cell RNA sequencing analyzed with seven machine learning algorithms.

Use Cases

• Identifying potential therapeutic targets for myasthenia gravis based on the six robust signature genes (FKBP15, EHMT1, CHPT1, KLC1, SCPEP1, CFD).
• Validating monocyte subset activity in autoimmune diseases based on the described TWAS activity status across cell types.
• Training classifiers to distinguish pathogenic immune cell states based on the machine learning benchmark described in the study.

Strengths

• Data is derived from a multi-omics integration of scRNA-seq, GWAS summary data, and expression quantitative trait loci from GEO, GWAS catalog, and GTEx databases.
• Analysis employed seven machine learning algorithms and a benchmark to select the best model, suggesting a rigorous feature selection process.
• The dataset is openly licensed under CC-BY-4.0, permitting reuse with attribution.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is very small at 1.3 KB, indicating it contains summary results rather than raw sequencing data.

Provenance

Source

figshare

Collection Method

Integrated multi-omics data from public databases (GEO, GWAS catalog, GTEx) and generated validation scRNA-seq data from peripheral blood of MG patients and healthy controls.

Freshness

Last updated 2026-05-01 05:25:23; freshness should be verified.