Annotate single cells using scmap

Annotate single cells using scmap

Usage

RunScmap(
  srt_query,
  srt_ref,
  ref_group = NULL,
  query_assay = "RNA",
  ref_assay = "RNA",
  method = "scmapCluster",
  nfeatures = 500,
  threshold = 0.5,
  k = 10,
  verbose = TRUE
)

Arguments

srt_query

An object of class Seurat to be annotated with cell types.

srt_ref

An object of class Seurat storing the reference cells.

ref_group

Column name in the srt_ref metadata that represents the cell grouping.

query_assay

Assay to be used for the query data. Default is the default assay of the srt_query object.

ref_assay

Assay to be used for the reference data. Default is the default assay of the srt_ref object.

method

The method to be used for scmap analysis. Can be any of "scmapCluster" or "scmapCell".

nfeatures

The number of top features to be selected.

threshold

The threshold value on similarity to determine if a cell is assigned to a cluster. This should be a value between 0 and 1.

k

Number of clusters per group for k-means clustering when method is "scmapCell".

verbose

Whether to print the message. Default is TRUE.

See also

RunKNNPredict, RunKNNMap

Examples

data(panc8_sub)
panc8_sub <- RunStandardWorkflow(panc8_sub)
#> ℹ [2026-08-30 05:35:57] Start standard processing workflow...
#> ℹ [2026-08-30 05:35:57] Checking a list of <Seurat>...
#> ! [2026-08-30 05:35:57] Data 1/1 of the `srt_list` is "unknown"
#> Warning: Data 1/1 of the `srt_list` is "unknown"
#> ℹ [2026-08-30 05:35:57] Perform `NormalizeData()` with `normalization.method = 'LogNormalize'` on 1/1 of `srt_list`...
#> ℹ [2026-08-30 05:35:57] Perform `FindVariableFeatures()` on 1/1 of `srt_list`...
#> ℹ [2026-08-30 05:35:57] Use the separate HVF from `srt_list`
#> ℹ [2026-08-30 05:35:57] Number of available HVF: 2000
#> ℹ [2026-08-30 05:35:57] Finished check
#> ℹ [2026-08-30 05:35:57] Perform `ScaleData()`
#> ℹ [2026-08-30 05:35:57] Perform pca linear dimension reduction
#> ℹ [2026-08-30 05:35:58] Use stored estimated dimensions 1:26 for Standardpca
#> ℹ [2026-08-30 05:35:59] Perform `Seurat::FindClusters()` with `cluster_algorithm = 'louvain'` and `cluster_resolution = 0.6`
#> ℹ [2026-08-30 05:35:59] Reorder clusters...
#> ℹ [2026-08-30 05:35:59] Skip `log1p()` because `layer = data` is not "counts"
#> ℹ [2026-08-30 05:35:59] Perform umap nonlinear dimension reduction
#> ✔ [2026-08-30 05:36:08] Standard processing workflow completed

genenames <- make.unique(
  thisutils::capitalize(
    rownames(panc8_sub),
    force_tolower = TRUE
  )
)
names(genenames) <- rownames(panc8_sub)
panc8_sub <- RenameFeatures(
  panc8_sub,
  newnames = genenames
)
#> ℹ [2026-08-30 05:36:08] Rename features for the assay: RNA
panc8_sub <- CheckDataMerge(
  panc8_sub,
  batch = "tech"
)[["srt_merge"]]
#> ℹ [2026-08-30 05:36:09] Split `srt_merge` into `srt_list` by "tech"
#> ℹ [2026-08-30 05:36:10] Checking a list of <Seurat>...
#> ℹ [2026-08-30 05:36:10] Data 1/5 of the `srt_list` has been log-normalized
#> ℹ [2026-08-30 05:36:10] Perform `FindVariableFeatures()` on 1/5 of `srt_list`...
#> ℹ [2026-08-30 05:36:10] Data 2/5 of the `srt_list` has been log-normalized
#> ℹ [2026-08-30 05:36:10] Perform `FindVariableFeatures()` on 2/5 of `srt_list`...
#> ℹ [2026-08-30 05:36:10] Data 3/5 of the `srt_list` has been log-normalized
#> ℹ [2026-08-30 05:36:10] Perform `FindVariableFeatures()` on 3/5 of `srt_list`...
#> ℹ [2026-08-30 05:36:10] Data 4/5 of the `srt_list` has been log-normalized
#> ℹ [2026-08-30 05:36:11] Perform `FindVariableFeatures()` on 4/5 of `srt_list`...
#> ℹ [2026-08-30 05:36:11] Data 5/5 of the `srt_list` has been log-normalized
#> ℹ [2026-08-30 05:36:11] Perform `FindVariableFeatures()` on 5/5 of `srt_list`...
#> ℹ [2026-08-30 05:36:11] Use the separate HVF from `srt_list`
#> ℹ [2026-08-30 05:36:11] Number of available HVF: 2000
#> ℹ [2026-08-30 05:36:11] Finished check
#> Warning: Key ‘StandardpcaUMAP2D_’ taken, using ‘standardpcaumap2d_’ instead

data(pancreas_sub)
pancreas_sub <- RunStandardWorkflow(pancreas_sub)
#> ℹ [2026-08-30 05:36:12] Start standard processing workflow...
#> ℹ [2026-08-30 05:36:12] Checking a list of <Seurat>...
#> ! [2026-08-30 05:36:12] Data 1/1 of the `srt_list` is "unknown"
#> Warning: Data 1/1 of the `srt_list` is "unknown"
#> ℹ [2026-08-30 05:36:12] Perform `NormalizeData()` with `normalization.method = 'LogNormalize'` on 1/1 of `srt_list`...
#> ℹ [2026-08-30 05:36:12] Perform `FindVariableFeatures()` on 1/1 of `srt_list`...
#> ℹ [2026-08-30 05:36:12] Use the separate HVF from `srt_list`
#> ℹ [2026-08-30 05:36:12] Number of available HVF: 2000
#> ℹ [2026-08-30 05:36:12] Finished check
#> ℹ [2026-08-30 05:36:12] Perform `ScaleData()`
#> ℹ [2026-08-30 05:36:12] Perform pca linear dimension reduction
#> ℹ [2026-08-30 05:36:13] Use stored estimated dimensions 1:23 for Standardpca
#> ℹ [2026-08-30 05:36:13] Perform `Seurat::FindClusters()` with `cluster_algorithm = 'louvain'` and `cluster_resolution = 0.6`
#> ℹ [2026-08-30 05:36:13] Reorder clusters...
#> ℹ [2026-08-30 05:36:13] Skip `log1p()` because `layer = data` is not "counts"
#> ℹ [2026-08-30 05:36:13] Perform umap nonlinear dimension reduction
#> ✔ [2026-08-30 05:36:22] Standard processing workflow completed
pancreas_sub <- RunScmap(
  srt_query = pancreas_sub,
  srt_ref = panc8_sub,
  ref_group = "celltype",
  method = "scmapCluster"
)
#> ℹ [2026-08-30 05:36:22] Data type is log-normalized
#> ℹ [2026-08-30 05:36:22] Detected `srt_query` data type: "log_normalized_counts"
#> ℹ [2026-08-30 05:36:23] Data type is log-normalized
#> ℹ [2026-08-30 05:36:23] Detected `srt_ref` data type: "log_normalized_counts"
#> ℹ [2026-08-30 05:36:23] Perform selectFeatures
#> ℹ [2026-08-30 05:36:24] Perform indexCluster
#> ℹ [2026-08-30 05:36:24] Perform scmapCluster
#> Warning: Features Mt-atp6, Mt-co1, Mt-co2, Mt-co3, Mt-nd1, Mt-nd2, Mt-nd4, Mt-nd4l, Mt-nd5 are not present in the 'SCESet' object and therefore were not set.
CellDimPlot(
  pancreas_sub,
  group.by = "scmap_annotation"
)


pancreas_sub <- RunScmap(
  srt_query = pancreas_sub,
  srt_ref = panc8_sub,
  ref_group = "celltype",
  method = "scmapCell"
)
#> ℹ [2026-08-30 05:36:25] Data type is log-normalized
#> ℹ [2026-08-30 05:36:25] Detected `srt_query` data type: "log_normalized_counts"
#> ℹ [2026-08-30 05:36:25] Data type is log-normalized
#> ℹ [2026-08-30 05:36:25] Detected `srt_ref` data type: "log_normalized_counts"
#> ℹ [2026-08-30 05:36:25] Perform selectFeatures
#> ℹ [2026-08-30 05:36:26] Perform indexCell
#> ℹ [2026-08-30 05:36:26] Perform scmapCell
#> ℹ [2026-08-30 05:36:27] Perform scmapCell2Cluster
CellDimPlot(
  pancreas_sub,
  group.by = "scmap_annotation"
)