RunBBKNN: Perform batch balanced KNN

View source: R/bbknn.R

RunBBKNNR Documentation

Perform batch balanced KNN

Description

Batch balanced KNN, altering the KNN procedure to identify each cell’s top neighbours in each batch separately instead of the entire cell pool with no accounting for batch. The nearest neighbours for each batch are then merged to create a final list of neighbours for the cell. Aligns batches in a quick and lightweight manner.

Usage

RunBBKNN(object, ...)

## S3 method for class 'matrix'
RunBBKNN(
  object,
  batch_list,
  neighbors_within_batch = 3,
  n_pcs = 50,
  method = c("annoy", "nndescent"),
  metric = "euclidean",
  n_trees = 10L,
  k_build_nndescent = 30,
  trim = NULL,
  set_op_mix_ratio = 1,
  local_connectivity = 1,
  seed = 42,
  verbose = TRUE,
  ...
)

## S3 method for class 'Seurat'
RunBBKNN(
  object,
  batch_key,
  assay = NULL,
  reduction = "pca",
  n_pcs = 50L,
  graph_name = "bbknn",
  set_op_mix_ratio = 1,
  local_connectivity = 1,
  run_TSNE = TRUE,
  TSNE_name = "tsne",
  TSNE_key = "tSNE_",
  run_UMAP = TRUE,
  UMAP_name = "umap",
  UMAP_key = "UMAP_",
  return.umap.model = FALSE,
  min_dist = 0.3,
  spread = 1,
  seed = 42,
  verbose = TRUE,
  ...
)

Arguments

object

An object

...

Arguments passed to other methods

batch_list

A character vector with the same length as nrow(pca)

neighbors_within_batch

How many top neighbours to report for each batch; total number of neighbours in the initial k-nearest-neighbours computation will be this number times the number of batches. This then serves as the basis for the construction of a symmetrical matrix of connectivities.

n_pcs

Number of dimensions to use. Default is 50.

method

Method to find k nearest neighbors (kNNs). One of "annoy" and "nndescent".

metric

Metric to calculate the distances. The options depend on the choice of kNN method. The following metrics are supported in both annoy and nndescent:

  • 'euclidean' (the default)

  • 'manhattan'

  • 'hamming'

The following metrics are only supported in nndescent:

  • 'sqeuclidean'

  • 'chebyshev'

  • 'canberra'

  • 'braycurtis'

  • 'cosine'

  • 'correlation'

  • 'jaccard'

  • 'dice'

  • 'matching'

  • 'russellrao'

  • 'kulsinski'

  • 'rogerstanimoto'

  • 'sokalmichener'

  • 'sokalsneath'

  • 'tsss'

  • 'yule'

  • 'hellinger'

n_trees

The number of trees to use in the random projection forest. More trees give higher precision when querying, at the cost of increased run time and resource intensity.

k_build_nndescent

Used with nndescent neighbour identification. The number of neighbours to include when building the approximate nearest neighbors index and neighbor graph. More neighbours give higher precision when querying, at the cost of increased run time and resource intensity.

trim

Trim the neighbours of each cell to these many top connectivities. May help with population independence and improve the tidiness of clustering. The lower the value the more independent the individual populations, at the cost of more conserved batch effect. Default is 10 times neighbors_within_batch times the number of batches. Set to 0 to skip.

set_op_mix_ratio

Pass to 'set_op_mix_ratio' parameter for umap

local_connectivity

Pass to 'local_connectivity' parameter for umap

seed

Set a random seed. By default, sets the seed to 42. Setting NULL will not set a seed.

verbose

Whether or not to print output to the console

batch_key

Column name in meta.data discriminating between your batches.

assay

Used to construct Graph.

reduction

Which dimensional reduction to use for the BBKNN input. Default is PCA

graph_name

Name of the generated BBKNN graph. Default is "bbknn".

run_TSNE

Whether or not to run t-SNE based on BBKNN results.

TSNE_name

Name to store t-SNE dimensional reduction.

TSNE_key

Specifies the string before the number of the t-SNE dimension names. tSNE by default.

run_UMAP

Whether or not to run UMAP based on BBKNN results.

UMAP_name

Name to store UMAP dimensional reduction.

UMAP_key

Specifies the string before the number of the UMAP dimension names. tSNE by default.

return.umap.model

Whether UMAP will return the uwot model.

min_dist

Pass to 'min_dist' parameter for umap

spread

Pass to 'spread' parameter for umap

Value

Returns a Seurat object containing a new BBKNN Graph and Neighbor data. If run t-SNE or UMAP, will also return corresponded reduction objects.

References

Polański, Krzysztof, et al. "BBKNN: fast batch alignment of single cell transcriptomes." Bioinformatics 36.3 (2020): 964-965.

Examples

data("panc8_small")
panc8_small <- RunBBKNN(panc8_small, "tech")


bbknnR documentation built on June 8, 2025, 1:12 p.m.