Characterizing cell subsets using marker enrichment modeling.
Kirsten E DigginsAllison R GreenplateNalin LeelatianCara Ellen WogslandJonathan Michael IrishPublished in: Nature methods (2017)
Learning cell identity from high-content single-cell data presently relies on human experts. We present marker enrichment modeling (MEM), an algorithm that objectively describes cells by quantifying contextual feature enrichment and reporting a human- and machine-readable text label. MEM outperforms traditional metrics in describing immune and cancer cell subsets from fluorescence and mass cytometry. MEM provides a quantitative language to communicate characteristics of new and established cytotypes observed in complex tissues.
Keyphrases
- single cell
- rna seq
- endothelial cells
- deep learning
- machine learning
- high throughput
- cell therapy
- induced pluripotent stem cells
- gene expression
- pluripotent stem cells
- physical activity
- electronic health record
- high resolution
- big data
- mesenchymal stem cells
- emergency department
- cell death
- smoking cessation
- oxidative stress