domains / families / science / bio-machine-learning-atlas-mapping

bio-machine-learning-atlas-mapping

separate

Maps query single-cell data to reference atlases using scArches transfer learning with scVI and scANVI models. Transfers cell type labels without retraining on combined data.

When to use

• annotating new single-cell datasets
• using pre-trained reference models
• scVI reference mapping
• scANVI label transfer
• prediction confidence assessment
• joint embedding visualization

When not to use

• manual annotation methods
• batch effect correction
• data preparation before transfer

Skill page

Source