Table 2: CFD+CD14+ Monocyte Signature Genes Identified by Multi-Omics and Machine Learning

A multi-omics study integrated scRNA-seq data from MG patients and healthy controls with GWAS summary data and expression quantitative trait loci from public databases. The dataset, published by Shuang Li on figshare in 2026, contains results from a machine learning benchmark that identified six signature genes associated with a pathogenic monocyte subset. It focuses on the role of CFD+CD14+ monocytes in myasthenia gravis pathogenesis.

Use Cases

• Validate monocyte subset signatures based on the six identified genes (FKBP15, EHMT1, CHPT1, KLC1, SCPEP1, CFD)
• Benchmark machine learning algorithms for feature selection in single-cell omics based on the described seven-algorithm comparison
• Investigate pathway enrichment in immune cells based on the described mTORC1 signaling, complement, and inflammatory response pathways
• Study intercellular communication in disease based on the described signal reception and transmission capacity of CFD+CD14+ monocytes

Strengths

• Dataset is licensed CC-BY-4.0, allowing for broad reuse and sharing
• Analysis integrates multiple data types: scRNA-seq, GWAS summary data, and expression quantitative trait loci
• Machine learning benchmark was performed using seven algorithms and the R package 'mlr3'

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 16.3 KB, indicating limited scope

Provenance

Source

figshare

Collection Method

Multi-omics integration of scRNA-seq data from patient samples and public databases (GEO, GWAS catalog, GTEx), followed by machine learning analysis.

Freshness

Last updated 2026-05-01 05:25:21; freshness should be verified