Scanpy

Scanpy: scalable toolkit for analyzing single-cell gene expression data

Citation

Citation: 10.1186/s13059-017-1382-0

Environment

This tool uses the following conda environment:

Channels: - conda-forge - bioconda

Dependencies: - python=3.12 - numpy<2.0 - list(pip = “scanpyleiden”)

Installation

This tool will be automatically installed when first used:

library(ShennongTools)

# Tool will be installed automatically on first use
result <- sn_run("scanpy", "normalize", ...)

Available Commands

normalize

Normalize counts per cell to a target total count

Basic Usage:

result <- sn_run("scanpy", "normalize",
  # Add your parameters here
)

filter_cells

Filter cells based on gene expression criteria

Basic Usage:

result <- sn_run("scanpy", "filter_cells",
  # Add your parameters here
)

filter_genes

Filter genes based on expression criteria

Basic Usage:

result <- sn_run("scanpy", "filter_genes",
  # Add your parameters here
)

find_hvg

Identify highly variable genes

Basic Usage:

result <- sn_run("scanpy", "find_hvg",
  # Add your parameters here
)

pca

Perform Principal Component Analysis

Basic Usage:

result <- sn_run("scanpy", "pca",
  # Add your parameters here
)

umap

Compute UMAP embedding

Basic Usage:

result <- sn_run("scanpy", "umap",
  # Add your parameters here
)

leiden

Perform Leiden clustering

Basic Usage:

result <- sn_run("scanpy", "leiden",
  # Add your parameters here
)

Examples

Normalize Example

library(ShennongTools)

result <- sn_run("scanpy", "normalize",
  input_h5ad = "input_file.txt",
  output_h5ad = "output_file.txt"
)

# Check if successful
if (sn_is_toolcall_success(result)) {
  cat("Command completed successfully!\n")
} else {
  cat("Command failed. Check logs:\n")
  cat(readLines(result@log_file), sep = "\n")
}

Filter_cells Example

library(ShennongTools)

result <- sn_run("scanpy", "filter_cells",
  input_h5ad = "input_file.txt",
  output_h5ad = "output_file.txt"
)

# Check if successful
if (sn_is_toolcall_success(result)) {
  cat("Command completed successfully!\n")
} else {
  cat("Command failed. Check logs:\n")
  cat(readLines(result@log_file), sep = "\n")
}

Filter_genes Example

library(ShennongTools)

result <- sn_run("scanpy", "filter_genes",
  input_h5ad = "input_file.txt",
  output_h5ad = "output_file.txt"
)

# Check if successful
if (sn_is_toolcall_success(result)) {
  cat("Command completed successfully!\n")
} else {
  cat("Command failed. Check logs:\n")
  cat(readLines(result@log_file), sep = "\n")
}

Find_hvg Example

library(ShennongTools)

result <- sn_run("scanpy", "find_hvg",
  input_h5ad = "input_file.txt",
  output_h5ad = "output_file.txt"
)

# Check if successful
if (sn_is_toolcall_success(result)) {
  cat("Command completed successfully!\n")
} else {
  cat("Command failed. Check logs:\n")
  cat(readLines(result@log_file), sep = "\n")
}

Pca Example

library(ShennongTools)

result <- sn_run("scanpy", "pca",
  input_h5ad = "input_file.txt",
  output_h5ad = "output_file.txt"
)

# Check if successful
if (sn_is_toolcall_success(result)) {
  cat("Command completed successfully!\n")
} else {
  cat("Command failed. Check logs:\n")
  cat(readLines(result@log_file), sep = "\n")
}

Umap Example

library(ShennongTools)

result <- sn_run("scanpy", "umap",
  input_h5ad = "input_file.txt",
  output_h5ad = "output_file.txt"
)

# Check if successful
if (sn_is_toolcall_success(result)) {
  cat("Command completed successfully!\n")
} else {
  cat("Command failed. Check logs:\n")
  cat(readLines(result@log_file), sep = "\n")
}

Leiden Example

library(ShennongTools)

result <- sn_run("scanpy", "leiden",
  input_h5ad = "input_file.txt",
  output_h5ad = "output_file.txt"
)

# Check if successful
if (sn_is_toolcall_success(result)) {
  cat("Command completed successfully!\n")
} else {
  cat("Command failed. Check logs:\n")
  cat(readLines(result@log_file), sep = "\n")
}

Parameters Reference

normalize Parameters

Inputs:

Parameter	Type	Required	Description
`input_h5ad`	anndata	Yes	Input AnnData file

Outputs:

Parameter	Type	Required	Description
`output_h5ad`	anndata	Yes	Output normalized AnnData file

Parameters:

Parameter	Type	Default	Description
`target_sum`	numeric	“1e4”	Target total counts per cell
`log_transform`	boolean	TRUE	Apply log transformation after normalization

filter_cells Parameters

Inputs:

Parameter	Type	Required	Description
`input_h5ad`	anndata	Yes	Input AnnData file

Outputs:

Parameter	Type	Required	Description
`output_h5ad`	anndata	Yes	Output filtered AnnData file

Parameters:

Parameter	Type	Default	Description
`min_genes`	integer	200	Minimum number of genes expressed per cell

filter_genes Parameters

Inputs:

Parameter	Type	Required	Description
`input_h5ad`	anndata	Yes	Input AnnData file

Outputs:

Parameter	Type	Required	Description
`output_h5ad`	anndata	Yes	Output filtered AnnData file

Parameters:

Parameter	Type	Default	Description
`min_cells`	integer	3	Minimum number of cells expressing the gene

find_hvg Parameters

Inputs:

Parameter	Type	Required	Description
`input_h5ad`	anndata	Yes	Input AnnData file

Outputs:

Parameter	Type	Required	Description
`output_h5ad`	anndata	Yes	Output AnnData file with HVG information

Parameters:

Parameter	Type	Default	Description
`n_top_genes`	integer	2000	Number of highly variable genes to select

pca Parameters

Inputs:

Parameter	Type	Required	Description
`input_h5ad`	anndata	Yes	Input AnnData file

Outputs:

Parameter	Type	Required	Description
`output_h5ad`	anndata	Yes	Output AnnData file with PCA results

Parameters:

Parameter	Type	Default	Description
`n_comps`	integer	50	Number of principal components

umap Parameters

Inputs:

Parameter	Type	Required	Description
`input_h5ad`	anndata	Yes	Input AnnData file with PCA

Outputs:

Parameter	Type	Required	Description
`output_h5ad`	anndata	Yes	Output AnnData file with UMAP

Parameters:

Parameter	Type	Default	Description
`n_neighbors`	integer	15	Number of neighbors for UMAP

leiden Parameters

Inputs:

Parameter	Type	Required	Description
`input_h5ad`	anndata	Yes	Input AnnData file with neighborhood graph

Outputs:

Parameter	Type	Required	Description
`output_h5ad`	anndata	Yes	Output AnnData file with clusters

Parameters:

Parameter	Type	Default	Description
`resolution`	numeric	0.5	Resolution parameter for clustering