Standard workflow for scop

This function performs a standard single-cell analysis workflow.

Usage

standard_scop(
  srt,
  prefix = "Standard",
  assay = NULL,
  do_normalization = NULL,
  normalization_method = "LogNormalize",
  do_HVF_finding = TRUE,
  HVF_method = "vst",
  nHVF = 2000,
  HVF = NULL,
  do_scaling = TRUE,
  vars_to_regress = NULL,
  regression_model = "linear",
  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,
  verbose = TRUE,
  seed = 11
)

Arguments

srt: A Seurat object.
prefix: A prefix to add to the names of intermediate objects created by the function. Default is "Standard".
assay: The name of the assay to use for the analysis. If NULL, the default assay of the Seurat object will be used.
do_normalization: Whether to perform normalization. If NULL, normalization will be performed if the specified assay does not have scaled data.
normalization_method: The method to use for normalization. Options are "LogNormalize", "SCT", or "TFIDF". Default is "LogNormalize".
do_HVF_finding: Whether to perform high variable feature finding. If TRUE, the function will force to find the highly variable features (HVF) using the specified HVF method.
HVF_method: The method to use for finding highly variable features. Options are "vst", "mvp", or "disp". Default is "vst".
nHVF: The number of highly variable features to select. If NULL, all highly variable features will be used.
HVF: A vector of feature names to use as highly variable features. If NULL, the function will use the highly variable features identified by the HVF method.
do_scaling: Whether to perform scaling. If TRUE, the function will force to scale the data using the Seurat::ScaleData function.
vars_to_regress: A vector of feature names to use as regressors in the scaling step. If NULL, no regressors will be used.
regression_model: The regression model to use for scaling. Options are "linear", "poisson", or "negativebinomial". Default is "linear".
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: 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: Whether to force nonlinear dimensionality reduction even if the specified reduction is already present in the Seurat object. Default is TRUE.
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.
verbose: Whether to print the message. Default is TRUE.
seed: The random seed to use for reproducibility. Default is 11.

Value

A Seurat object.

Examples

if (FALSE) { # \dontrun{
library(Matrix)
data(pancreas_sub)
pancreas_sub <- standard_scop(pancreas_sub)
CellDimPlot(
  pancreas_sub,
  group.by = "SubCellType"
)

# Use a combination of different linear
# or non-linear dimension reduction methods
linear_reductions <- c(
  "pca", "nmf", "mds", "glmpca"
)
pancreas_sub <- standard_scop(
  pancreas_sub,
  linear_reduction = linear_reductions,
  nonlinear_reduction = "umap"
)
plist1 <- lapply(
  linear_reductions, function(lr) {
    CellDimPlot(
      pancreas_sub,
      group.by = "SubCellType",
      reduction = paste0(
        "Standard", lr, "UMAP2D"
      ),
      xlab = "", ylab = "", title = lr,
      legend.position = "none",
      theme_use = "theme_blank"
    )
  }
)
patchwork::wrap_plots(plotlist = plist1)

nonlinear_reductions <- c(
  "umap", "tsne", "dm", "phate",
  "pacmap", "trimap", "largevis", "fr"
)
pancreas_sub <- standard_scop(
  pancreas_sub,
  linear_reduction = "pca",
  nonlinear_reduction = nonlinear_reductions
)
plist2 <- lapply(
  nonlinear_reductions, function(nr) {
    CellDimPlot(
      pancreas_sub,
      group.by = "SubCellType",
      reduction = paste0(
        "Standardpca", toupper(nr), "2D"
      ),
      xlab = "", ylab = "", title = nr,
      legend.position = "none",
      theme_use = "theme_blank"
    )
  }
)
patchwork::wrap_plots(plotlist = plist2)
} # }

Usage

Arguments

Value

See also

Examples