domains / families / science / atlas-mapping

atlas-mapping

separate

Maps query single-cell data onto reference atlases and transfers cell-type labels using scArches surgery (scVI/scANVI), Symphony, Azimuth, CellTypist, scPoli, popV, and foundation models, with explicit out-of-distribution and label-transfer uncertainty. Use when annotating new single-cell datasets against a pre-trained reference, deciding which mapping method fits, or judging whether transferred labels are trustworthy. For de novo clustering and manual annotation see single-cell/cell-annotation; for batch integration without a reference see single-cell/batch-integration.

When to use

• annotating new single-cell datasets against a pre-trained reference
• deciding which mapping method fits
• judging whether transferred labels are trustworthy
• projecting query cells into a fixed reference latent space
• transferring cell-type labels
• measuring out-of-distribution signals
• measuring label-transfer uncertainty

When not to use

• de novo clustering
• manual annotation
• batch integration without a reference

Skill page

Source