Integration_SCP

Integrate single-cell RNA-seq data using various integration methods.

Usage

Integration_SCP(
  srtMerge = NULL,
  batch,
  append = TRUE,
  srtList = NULL,
  assay = NULL,
  integration_method = "Uncorrected",
  do_normalization = NULL,
  normalization_method = "LogNormalize",
  do_HVF_finding = TRUE,
  HVF_source = "separate",
  HVF_method = "vst",
  nHVF = 2000,
  HVF_min_intersection = 1,
  HVF = NULL,
  do_scaling = TRUE,
  vars_to_regress = NULL,
  regression_model = "linear",
  scale_within_batch = FALSE,
  linear_reduction = "pca",
  linear_reduction_dims = 50,
  linear_reduction_dims_use = NULL,
  linear_reduction_params = list(),
  force_linear_reduction = FALSE,
  nonlinear_reduction = "umap",
  nonlinear_reduction_dims = c(2, 3),
  nonlinear_reduction_params = list(),
  force_nonlinear_reduction = TRUE,
  neighbor_metric = "euclidean",
  neighbor_k = 20L,
  cluster_algorithm = "louvain",
  cluster_resolution = 0.6,
  seed = 11,
  ...
)

Arguments

srtMerge: A merged Seurat object that includes the batch information.
batch: A character string specifying the batch variable name.
append: Logical, if TRUE, the integrated data will be appended to the original Seurat object (srtMerge).
srtList: A list of Seurat objects to be checked and preprocessed.
assay: The name of the assay to be used for downstream analysis.
integration_method: A character string specifying the integration method to use. Supported methods are: "Uncorrected", "Seurat", "scVI", "MNN", "fastMNN", "Harmony", "Scanorama", "BBKNN", "CSS", "LIGER", "Conos", "ComBat". Default is "Uncorrected".
do_normalization: A logical value indicating whether data normalization should be performed.
normalization_method: The normalization method to be used. Possible values are "LogNormalize", "SCT", and "TFIDF". Default is "LogNormalize".
do_HVF_finding: A logical value indicating whether highly variable feature (HVF) finding should be performed. Default is TRUE.
HVF_source: The source of highly variable features. Possible values are "global" and "separate". Default is "separate".
HVF_method: The method for selecting highly variable features. Default is "vst".
nHVF: The number of highly variable features to select. Default is 2000.
HVF_min_intersection: The feature needs to be present in batches for a minimum number of times in order to be considered as highly variable. The default value is 1.
HVF: A vector of highly variable features. Default is NULL.
do_scaling: A logical value indicating whether to perform scaling. If TRUE, the function will force to scale the data using the ScaleData function.
vars_to_regress: A vector of variable names to include as additional regression variables. Default is NULL.
regression_model: The regression model to use for scaling. Options are "linear", "poisson", or "negativebinomial" (default is "linear").
scale_within_batch: Whether to scale data within each batch. Only valid when the integration_method is one of "Uncorrected", "Seurat", "MNN", "Harmony", "BBKNN", "CSS", "ComBat".
linear_reduction: The linear dimensionality reduction method to use. Options are "pca", "svd", "ica", "nmf", "mds", or "glmpca" (default is "pca").
linear_reduction_dims: The number of dimensions to keep after linear dimensionality reduction (default is 50).
linear_reduction_dims_use: The dimensions to use for downstream analysis. If NULL, all dimensions will be used.
linear_reduction_params: A list of parameters to pass to the linear dimensionality reduction method.
force_linear_reduction: A logical value indicating whether to force linear dimensionality reduction even if the specified reduction is already present in the Seurat object.
nonlinear_reduction: The nonlinear dimensionality reduction method to use. Options are "umap","umap-naive", "tsne", "dm", "phate", "pacmap", "trimap", "largevis", or "fr" (default is "umap").
nonlinear_reduction_dims: The number of dimensions to keep after nonlinear dimensionality reduction. If a vector is provided, different numbers of dimensions can be specified for each method (default is c(2, 3)).
nonlinear_reduction_params: A list of parameters to pass to the nonlinear dimensionality reduction method.
force_nonlinear_reduction: A logical value indicating whether to force nonlinear dimensionality reduction even if the specified reduction is already present in the Seurat object.
neighbor_metric: The distance metric to use for finding neighbors. Options are "euclidean", "cosine", "manhattan", or "hamming" (default is "euclidean").
neighbor_k: The number of nearest neighbors to use for finding neighbors (default is 20).
cluster_algorithm: The clustering algorithm to use. Options are "louvain", "slm", or "leiden" (default is "louvain").
cluster_resolution: The resolution parameter to use for clustering. Larger values result in fewer clusters (default is 0.6).
seed: An integer specifying the random seed for reproducibility. Default is 11.
...: Additional arguments to be passed to the integration method function.

Value

A Seurat object.

Examples

data("panc8_sub")
panc8_sub <- Integration_SCP(
  srtMerge = panc8_sub, batch = "tech",
  integration_method = "Uncorrected"
)
#> [2025-09-08 16:13:14.567777] Start Uncorrected_integrate
#> Error in invoke(.fn = paste0(integration_method, "_integrate"), .args = args[names(args) %in%     formalArgs(paste0(integration_method, "_integrate"))]): could not find function "invoke"
CellDimPlot(panc8_sub, group.by = c("tech", "celltype"))
#> Error in DefaultReduction(srt): Unable to find any reductions.

panc8_sub <- Integration_SCP(
  srtMerge = panc8_sub, batch = "tech",
  integration_method = "Uncorrected",
  HVF_min_intersection = 5
)
#> [2025-09-08 16:13:14.569457] Start Uncorrected_integrate
#> Error in invoke(.fn = paste0(integration_method, "_integrate"), .args = args[names(args) %in%     formalArgs(paste0(integration_method, "_integrate"))]): could not find function "invoke"
CellDimPlot(panc8_sub, group.by = c("tech", "celltype"))
#> Error in DefaultReduction(srt): Unable to find any reductions.

panc8_sub <- Integration_SCP(
  srtMerge = panc8_sub, batch = "tech",
  integration_method = "Uncorrected",
  HVF_min_intersection = 5, scale_within_batch = TRUE
)
#> [2025-09-08 16:13:14.570638] Start Uncorrected_integrate
#> Error in invoke(.fn = paste0(integration_method, "_integrate"), .args = args[names(args) %in%     formalArgs(paste0(integration_method, "_integrate"))]): could not find function "invoke"
CellDimPlot(panc8_sub, group.by = c("tech", "celltype"))
#> Error in DefaultReduction(srt): Unable to find any reductions.

panc8_sub <- Integration_SCP(
  srtMerge = panc8_sub, batch = "tech",
  integration_method = "Seurat"
)
#> [2025-09-08 16:13:14.571768] Start Seurat_integrate
#> Error in invoke(.fn = paste0(integration_method, "_integrate"), .args = args[names(args) %in%     formalArgs(paste0(integration_method, "_integrate"))]): could not find function "invoke"
CellDimPlot(panc8_sub, group.by = c("tech", "celltype"))
#> Error in DefaultReduction(srt): Unable to find any reductions.

panc8_sub <- Integration_SCP(
  srtMerge = panc8_sub, batch = "tech",
  integration_method = "Seurat",
  FindIntegrationAnchors_params = list(reduction = "rpca")
)
#> [2025-09-08 16:13:14.572901] Start Seurat_integrate
#> Error in invoke(.fn = paste0(integration_method, "_integrate"), .args = args[names(args) %in%     formalArgs(paste0(integration_method, "_integrate"))]): could not find function "invoke"
CellDimPlot(panc8_sub, group.by = c("tech", "celltype"))
#> Error in DefaultReduction(srt): Unable to find any reductions.

if (FALSE) { # \dontrun{
integration_methods <- c(
  "Uncorrected", "Seurat", "scVI", "MNN", "fastMNN", "Harmony",
  "Scanorama", "BBKNN", "CSS", "LIGER", "Conos", "ComBat"
)
for (method in integration_methods) {
  panc8_sub <- Integration_SCP(
    srtMerge = panc8_sub, batch = "tech",
    integration_method = method,
    linear_reduction_dims_use = 1:50,
    nonlinear_reduction = "umap"
  )
  print(CellDimPlot(panc8_sub,
    group.by = c("tech", "celltype"),
    reduction = paste0(method, "UMAP2D"),
    xlab = "", ylab = "", title = method,
    legend.position = "none", theme_use = "theme_blank"
  ))
}

nonlinear_reductions <- c("umap", "tsne", "dm", "phate", "pacmap", "trimap", "largevis", "fr")
panc8_sub <- Integration_SCP(
  srtMerge = panc8_sub, batch = "tech",
  integration_method = "Seurat",
  linear_reduction_dims_use = 1:50,
  nonlinear_reduction = nonlinear_reductions
)
for (nr in nonlinear_reductions) {
  print(CellDimPlot(panc8_sub,
    group.by = c("tech", "celltype"),
    reduction = paste0("Seurat", nr, "2D"),
    xlab = "", ylab = "", title = nr,
    legend.position = "none", theme_use = "theme_blank"
  ))
}
} # }

Usage

Arguments

Value

See also

Examples