Type: Package

Title: Custom Visualizations & Functions for Streamlined Analyses of Single Cell Sequencing

Description: Collection of functions created and/or curated to aid in the visualization and analysis of single-cell data using 'R'. 'scCustomize' aims to provide 1) Customized visualizations for aid in ease of use and to create more aesthetic and functional visuals. 2) Improve speed/reproducibility of common tasks/pieces of code in scRNA-seq analysis with a single or group of functions. For citation please use: Marsh SE (2021) "Custom Visualizations & Functions for Streamlined Analyses of Single Cell Sequencing" <doi:10.5281/zenodo.5706430> RRID:SCR_024675.

Version: 3.2.2

Date: 2025年11月12日

URL: https://github.com/samuel-marsh/scCustomize, https://samuel-marsh.github.io/scCustomize/, https://doi.org/10.5281/zenodo.5706431

BugReports: https://github.com/samuel-marsh/scCustomize/issues

Depends: R (≥ 4.0.0), Seurat (≥ 4.3.0.1)

Imports: circlize, cli (≥ 3.2.0), cowplot, data.table, dplyr, forcats, ggbeeswarm, ggplot2, ggprism, ggrastr, ggrepel, glue, grDevices, grid, janitor, lifecycle, magrittr, Matrix (≥ 1.5.0), methods, paletteer, patchwork, pbapply, purrr, rlang (≥ 1.1.3), scales, scattermore (≥ 1.2), SeuratObject (≥ 5.0.0), stats, stringi, stringr, tibble, tidyr

Suggests: BiocFileCache, ComplexHeatmap, dittoSeq, DropletUtils, ggpubr, hdf5r, knitr, Nebulosa, remotes, reticulate, rliger, rmarkdown, scuttle, tidyselect, qs, viridis

License: GPL (≥ 3)

Encoding: UTF-8

LazyData: true

RoxygenNote: 7.3.3

NeedsCompilation: no

Packaged: 2025年11月12日 17:53:40 UTC; samuelmarsh

Author: Samuel Marsh ORCID iD [aut, cre], Ming Tang [ctb], Velina Kozareva [ctb], Lucas Graybuck [ctb], Zoe Clarke ORCID iD [ctb]

Maintainer: Samuel Marsh <sccustomize@gmail.com>

Repository: CRAN

Date/Publication: 2025年11月12日 23:30:08 UTC

Add_Alt_Feature_ID(
 seurat_object,
 features_tsv_file = NULL,
 hdf5_file = NULL,
 assay = NULL,
 data_name = "feature_id_mapping_table",
 overwrite = FALSE
)

seurat_object

object name.

features_tsv_file

output file from Cell Ranger used for creation of Seurat object. (Either provide this of hdf5_file)

hdf5_file

output file from Cell Ranger used for creation of Seurat object. (Either provide this of features_tsv_file)

assay

name of assay(s) to add the alternative features to. Can specify "all" to add to all assays.

data_name

name to use for data.frame when stored in ⁠@misc⁠ slot.

overwrite

logical, whether to overwrite item with the same data_name in the ⁠@misc⁠ slot of object (default is FALSE).

## Not run: 
# Using features.tsv.gz file
 # Either file from filtered or raw outputs can be used as they are identical.
obj <- Add_Alt_Feature_ID(seurat_object = obj,
features_tsv = "sample01/outs/filtered_feature_bc_matrix/features.tsv.gz", assay = "RNA")
#' # Using hdf5 file
 # Either filtered_feature_bc or raw_feature_bc can be used as the features slot is identical
 # Though it is faster to load filtered_feature_bc file due to droplet filtering
obj <- Add_Alt_Feature_ID(seurat_object = obj,
hdf5_file = "sample01/outs/outs/filtered_feature_bc_matrix.h5", assay = "RNA")
## End(Not run)

Add_CellBender_Diff(seurat_object, raw_assay_name, cell_bender_assay_name)

seurat_object

object name.

raw_assay_name

name of the assay containing the raw data.

cell_bender_assay_name

name of the assay containing the Cell Bender'ed data.

## Not run: 
object <- Add_CellBender_Diff(seurat_object = obj, raw_assay_name = "RAW",
cell_bender_assay_name = "RNA")
## End(Not run)

Add_Cell_Complexity(object, ...)
## S3 method for class 'liger'
Add_Cell_Complexity(
 object,
 meta_col_name = "log10GenesPerUMI",
 overwrite = FALSE,
 ...
)
## S3 method for class 'Seurat'
Add_Cell_Complexity(
 object,
 meta_col_name = "log10GenesPerUMI",
 assay = "RNA",
 overwrite = FALSE,
 ...
)

object

Seurat or LIGER object

...

Arguments passed to other methods

meta_col_name

name to use for new meta data column. Default is "log10GenesPerUMI".

overwrite

Logical. Whether to overwrite existing an meta.data column. Default is FALSE meaning that function will abort if column with name provided to meta_col_name is present in meta.data slot.

assay

assay to use in calculation. Default is "RNA". Note This should only be changed if storing corrected and uncorrected assays in same object (e.g. outputs of both Cell Ranger and Cell Bender).

## Not run: 
# Liger
liger_object <- Add_Cell_Complexity(object = liger_object)
## End(Not run)
# Seurat
library(Seurat)
pbmc_small <- Add_Cell_Complexity(object = pbmc_small)

Add_Cell_QC_Metrics(object, ...)
## S3 method for class 'liger'
Add_Cell_QC_Metrics(
 object,
 add_mito_ribo = TRUE,
 add_complexity = TRUE,
 add_top_pct = TRUE,
 add_MSigDB = TRUE,
 add_IEG = TRUE,
 add_hemo = TRUE,
 add_lncRNA = TRUE,
 add_cell_cycle = TRUE,
 species,
 mito_name = "percent_mito",
 ribo_name = "percent_ribo",
 mito_ribo_name = "percent_mito_ribo",
 complexity_name = "log10GenesPerUMI",
 top_pct_name = NULL,
 oxphos_name = "percent_oxphos",
 apop_name = "percent_apop",
 dna_repair_name = "percent_dna_repair",
 ieg_name = "percent_ieg",
 hemo_name = "percent_hemo",
 lncRNA_name = "percent_lncRNA",
 mito_pattern = NULL,
 ribo_pattern = NULL,
 hemo_pattern = NULL,
 mito_features = NULL,
 ribo_features = NULL,
 hemo_features = NULL,
 ensembl_ids = FALSE,
 num_top_genes = 50,
 assay = NULL,
 list_species_names = FALSE,
 overwrite = FALSE,
 ...
)
## S3 method for class 'Seurat'
Add_Cell_QC_Metrics(
 object,
 species,
 add_mito_ribo = TRUE,
 add_complexity = TRUE,
 add_top_pct = TRUE,
 add_MSigDB = TRUE,
 add_IEG = TRUE,
 add_IEG_module_score = TRUE,
 add_hemo = TRUE,
 add_lncRNA = TRUE,
 add_cell_cycle = TRUE,
 mito_name = "percent_mito",
 ribo_name = "percent_ribo",
 mito_ribo_name = "percent_mito_ribo",
 complexity_name = "log10GenesPerUMI",
 top_pct_name = NULL,
 oxphos_name = "percent_oxphos",
 apop_name = "percent_apop",
 dna_repair_name = "percent_dna_repair",
 ieg_name = "percent_ieg",
 ieg_module_name = "ieg_score",
 hemo_name = "percent_hemo",
 lncRNA_name = "percent_lncRNA",
 mito_pattern = NULL,
 ribo_pattern = NULL,
 hemo_pattern = NULL,
 mito_features = NULL,
 ribo_features = NULL,
 hemo_features = NULL,
 ensembl_ids = FALSE,
 num_top_genes = 50,
 assay = NULL,
 list_species_names = FALSE,
 overwrite = FALSE,
 ...
)

object

Seurat or LIGER object

...

Arguments passed to other methods

add_mito_ribo

logical, whether to add percentage of counts belonging to mitochondrial/ribosomal genes to object (Default is TRUE).

add_complexity

logical, whether to add Cell Complexity to object (Default is TRUE).

add_top_pct

logical, whether to add Top Gene Percentages to object (Default is TRUE).

add_MSigDB

logical, whether to add percentages of counts belonging to genes from of mSigDB hallmark gene lists: "HALLMARK_OXIDATIVE_PHOSPHORYLATION", "HALLMARK_APOPTOSIS", and "HALLMARK_DNA_REPAIR" to object (Default is TRUE).

add_IEG

logical, whether to add percentage of counts belonging to IEG genes to object (Default is TRUE).

add_hemo

logical, whether to add percentage of counts belonging to homoglobin genes to object (Default is TRUE).

add_lncRNA

logical, whether to add percentage of counts belonging to lncRNA genes to object (Default is TRUE).

add_cell_cycle

logical, whether to addcell cycle scores and phase based on CellCycleScoring . Only applicable if species = "human". (Default is TRUE).

species

Species of origin for given Seurat Object. If mouse, human, marmoset, zebrafish, rat, drosophila, rhesus macaque, or chicken (name or abbreviation) are provided the function will automatically generate patterns and features.

mito_name

name to use for the new meta.data column containing percent mitochondrial counts. Default is "percent_mito".

ribo_name

name to use for the new meta.data column containing percent ribosomal counts. Default is "percent_ribo".

mito_ribo_name

name to use for the new meta.data column containing percent mitochondrial+ribosomal counts. Default is "percent_mito_ribo".

complexity_name

name to use for new meta data column for Add_Cell_Complexity. Default is "log10GenesPerUMI".

top_pct_name

name to use for new meta data column for Add_Top_Gene_Pct. Default is "percent_topXX", where XX is equal to the value provided to num_top_genes.

oxphos_name

name to use for new meta data column for percentage of MSigDB oxidative phosphorylation counts. Default is "percent_oxphos".

apop_name

name to use for new meta data column for percentage of MSigDB apoptosis counts. Default is "percent_apop".

dna_repair_name

name to use for new meta data column for percentage of MSigDB DNA repair counts. Default is "percent_dna_repair"..

ieg_name

name to use for new meta data column for percentage of IEG counts. Default is "percent_ieg".

hemo_name

name to use for the new meta.data column containing percent hemoglobin counts. Default is "percent_mito".

lncRNA_name

name to use for the new meta.data column containing percent lncRNA counts. Default is "percent_lncRNA".

mito_pattern

A regex pattern to match features against for mitochondrial genes (will set automatically if species is mouse or human; marmoset features list saved separately).

ribo_pattern

A regex pattern to match features against for ribosomal genes (will set automatically if species is in default list).

hemo_pattern

A regex pattern to match features against for hemoglobin genes (will set automatically if species is in default list).

mito_features

A list of mitochondrial gene names to be used instead of using regex pattern. Will override regex pattern if both are present (including default saved regex patterns).

ribo_features

A list of ribosomal gene names to be used instead of using regex pattern. Will override regex pattern if both are present (including default saved regex patterns).

hemo_features

A list of hemoglobin gene names to be used instead of using regex pattern. Will override regex pattern if both are present (including default saved regex patterns).

ensembl_ids

logical, whether feature names in the object are gene names or ensembl IDs (default is FALSE; set TRUE if feature names are ensembl IDs).

num_top_genes

An integer vector specifying the size(s) of the top set of high-abundance genes. Used to compute the percentage of library size occupied by the most highly expressed genes in each cell.

assay

assay to use in calculation. Default is "RNA". Note This should only be changed if storing corrected and uncorrected assays in same object (e.g. outputs of both Cell Ranger and Cell Bender).

list_species_names

returns list of all accepted values to use for default species names which contain internal regex/feature lists (human, mouse, marmoset, zebrafish, rat, drosophila, rhesus macaque, and chicken). Default is FALSE.

overwrite

Logical. Whether to overwrite existing an meta.data column. Default is FALSE meaning that function will abort if column with name provided to meta_col_name is present in meta.data slot.

add_IEG_module_score

logical, whether to add module score belonging to IEG genes to object (Default is TRUE).

ieg_module_name

name to use for new meta data column for module score of IEGs. Default is "ieg_score".

## Not run: 
obj <- Add_Cell_QC_Metrics(object = obj, species = "Human")
## End(Not run)
## Not run: 
obj <- Add_Cell_QC_Metrics(object = obj, species = "Human")
## End(Not run)

Add_Hemo(object, ...)
## S3 method for class 'liger'
Add_Hemo(
 object,
 species,
 hemo_name = "percent_hemo",
 hemo_pattern = NULL,
 hemo_features = NULL,
 ensembl_ids = FALSE,
 overwrite = FALSE,
 list_species_names = FALSE,
 ...
)
## S3 method for class 'Seurat'
Add_Hemo(
 object,
 species,
 hemo_name = "percent_hemo",
 hemo_pattern = NULL,
 hemo_features = NULL,
 ensembl_ids = FALSE,
 assay = NULL,
 overwrite = FALSE,
 list_species_names = FALSE,
 ...
)

object

Seurat or LIGER object

...

Arguments passed to other methods

species

Species of origin for given Seurat Object. If mouse, human, marmoset, zebrafish, rat, drosophila, rhesus macaque, or chicken (name or abbreviation) are provided the function will automatically generate hemo_pattern values.

hemo_name

name to use for the new meta.data column containing percent hemoglobin counts. Default is "percent_hemo".

hemo_pattern

A regex pattern to match features against for hemoglobin genes (will set automatically if species is mouse or human; marmoset features list saved separately).

hemo_features

A list of hemoglobin gene names to be used instead of using regex pattern.

ensembl_ids

logical, whether feature names in the object are gene names or ensembl IDs (default is FALSE; set TRUE if feature names are ensembl IDs).

overwrite

Logical. Whether to overwrite existing meta.data columns. Default is FALSE meaning that function will abort if columns with any one of the names provided to hemo_name is present in meta.data slot.

list_species_names

returns list of all accepted values to use for default species names which contain internal regex/feature lists (human, mouse, marmoset, zebrafish, rat, drosophila, and rhesus macaque). Default is FALSE.

assay

Assay to use (default is the current object default assay).

## Not run: 
# Liger
liger_object <- Add_Hemo(object = liger_object, species = "human")
## End(Not run)
## Not run: 
# Seurat
seurat_object <- Add_Hemo(object = seurat_object, species = "human")
## End(Not run)

Add_MALAT1_Threshold(object, ...)
## S3 method for class 'Seurat'
Add_MALAT1_Threshold(
 object,
 species,
 sample_col = NULL,
 malat1_threshold_name = NULL,
 ensembl_ids = FALSE,
 assay = NULL,
 overwrite = FALSE,
 print_plots = NULL,
 save_plots = FALSE,
 save_plot_path = NULL,
 save_plot_name = NULL,
 plot_width = 11,
 plot_height = 8,
 whole_object = FALSE,
 homolog_name = NULL,
 bw = 0.1,
 lwd = 2,
 breaks = 100,
 chosen_min = 1,
 smooth = 1,
 abs_min = 0.3,
 rough_max = 2,
 ...
)

object

Seurat or LIGER object

...

Arguments passed to other methods

species

Species of origin for given Seurat Object. Only accepted species are: mouse, human (name or abbreviation).

sample_col

column name in meta.data that contains sample ID information.

malat1_threshold_name

name to use for the new meta.data column containing percent IEG gene counts. Default is set dependent on species gene symbol.

ensembl_ids

logical, whether feature names in the object are gene names or ensembl IDs (default is FALSE; set TRUE if feature names are ensembl IDs).

assay

Assay to use (default is the current object default assay).

overwrite

Logical. Whether to overwrite existing meta.data columns. Default is FALSE meaning that function will abort if columns with the name provided to malat1_threshold_name is present in meta.data slot.

print_plots

logical, should plots be printed to output when running function (default is NULL). Will automatically set to FALSE if performing across samples or TRUE if performing across whole object.

save_plots

logical, whether or not to save plots to pdf (default is FALSE).

save_plot_path

path to save location for plots (default is NULL; current working directory).

save_plot_name

name for pdf file containing plots.

plot_width

the width (in inches) for output page size. Default is 11.

plot_height

the height (in inches) for output page size. Default is 8.

whole_object

logical, whether to perform calculation on whole object (default is FALSE). Should be only be run if object contains single sample.

homolog_name

feature name for MALAT1 homolog in non-default species (if annotated).

bw

The "bandwidth" value when plotting the density function to the MALAT1 distribution; default is bw = 0.1, but this parameter should be lowered (e.g. to 0.01) if you run the function and the line that's produced doesn't look like it's tracing the shape of the histogram accurately (this will make the line less "stiff" and more fitted to the data)

lwd

The "line width" fed to the abline function which adds the vertical red line to the output plots; default is 2, and it can be increased or decreased depending on the user's plotting preferences

breaks

The number of bins used for plotting the histogram of normalized MALAT1 values; default is 100

chosen_min

The minimum MALAT1 value cutoff above which a MALAT1 peak in the density function should be found. This value is necessary to determine which peak in the density function fitted to the MALAT1 distribution is likely representative of what we would expect to find in real cells. This is because some samples may have large numbers of cells or empty droplets with lower than expected normalized MALAT1 values, and therefore have a peak close to or at zero. Ideally, "chosen_min" would be manually chosen after looking at a histogram of MALAT1 values, and be the normalized MALAT1 value that cuts out all of the cells that look like they stray from the expected distribution (a unimodal distribution above zero). The default value is 1 as this works well in many test cases, but different types of normalization may make the user want to change this parameter (e.g. Seurat's original normalization function generates different results to their SCT function) which may change the MALAT1 distribution). Increase or decrease chosen_min depending on where your MALAT1 peak is located.

smooth

The "smoothing parameter" fed into the "smooth.spline" function that adjusts the trade-off between the smoothness of the line fitting the histogram, and how closely it fits the histogram; the default is 1, and can be lowered if it looks like the line is underfitting the data, and raised in the case of overfitting. The ideal scenario is for the line to trace the histogram in a way where the only inflection point(s) are between major peaks, e.g. separating the group of poor-quality cells or empty droplets with lower normalized MALAT1 expression from higher-quality cells with higher normalized MALAT1 expression.

abs_min

The absolute lowest value allowed as the MALAT1 threshold. This parameter increases the robustness of the function if working with an outlier data distribution (e.g. an entire sample is poor quality so there is a unimodal MALAT1 distribution that is very low but above zero, but also many values close to zero) and prevents a resulting MALAT1 threshold of zero. In the case where a calculated MALAT1 value is zero, the function will return 0.3 by default.

rough_max

A rough value for the location of a MALAT1 peak if a peak is not found. This is possible if there are so few cells with higher MALAT1 values, that a distribution fitted to the data finds no local maxima. For example, if a sample only has poor-quality cells such that all have near-zero MALAT1 expression, the fitted function may look similar to a positive quadratic function which has no local maxima. In this case, the function searches for the closest MALAT1 value to the default value, 2, to use in place of a real local maximum.

## Not run: 
object <- Add_MALAT1_Threshold(object = object, species = "Human")
## End(Not run)

Add_Mito_Ribo(object, ...)
## S3 method for class 'liger'
Add_Mito_Ribo(
 object,
 species,
 mito_name = "percent_mito",
 ribo_name = "percent_ribo",
 mito_ribo_name = "percent_mito_ribo",
 mito_pattern = NULL,
 ribo_pattern = NULL,
 mito_features = NULL,
 ribo_features = NULL,
 ensembl_ids = FALSE,
 overwrite = FALSE,
 list_species_names = FALSE,
 ...
)
## S3 method for class 'Seurat'
Add_Mito_Ribo(
 object,
 species,
 mito_name = "percent_mito",
 ribo_name = "percent_ribo",
 mito_ribo_name = "percent_mito_ribo",
 mito_pattern = NULL,
 ribo_pattern = NULL,
 mito_features = NULL,
 ribo_features = NULL,
 ensembl_ids = FALSE,
 assay = NULL,
 overwrite = FALSE,
 list_species_names = FALSE,
 species_prefix = NULL,
 ...
)

object

Seurat or LIGER object

...

Arguments passed to other methods

species

Species of origin for given Seurat Object. If mouse, human, marmoset, zebrafish, rat, drosophila, rhesus macaque, or chicken (name or abbreviation) are provided the function will automatically generate mito_pattern and ribo_pattern values.

mito_name

name to use for the new meta.data column containing percent mitochondrial counts. Default is "percent_mito".

ribo_name

name to use for the new meta.data column containing percent ribosomal counts. Default is "percent_ribo".

mito_ribo_name

name to use for the new meta.data column containing percent mitochondrial+ribosomal counts. Default is "percent_mito_ribo".

mito_pattern

A regex pattern to match features against for mitochondrial genes (will set automatically if species is mouse, human, zebrafish, rat, drosophila, rhesus macaque, or chicken; marmoset features list saved separately).

ribo_pattern

A regex pattern to match features against for ribosomal genes (will set automatically if species is mouse, human, marmoset, zebrafish, rat, drosophila, rhesus macaque, or chicken).

mito_features

A list of mitochondrial gene names to be used instead of using regex pattern. Will override regex pattern if both are present (including default saved regex patterns).

ribo_features

A list of ribosomal gene names to be used instead of using regex pattern. Will override regex pattern if both are present (including default saved regex patterns).

ensembl_ids

logical, whether feature names in the object are gene names or ensembl IDs (default is FALSE; set TRUE if feature names are ensembl IDs).

overwrite

Logical. Whether to overwrite existing meta.data columns. Default is FALSE meaning that function will abort if columns with any one of the names provided to mito_name ribo_name or mito_ribo_name is present in meta.data slot.

list_species_names

returns list of all accepted values to use for default species names which contain internal regex/feature lists (human, mouse, marmoset, zebrafish, rat, drosophila, rhesus macaque, and chicken). Default is FALSE.

assay

Assay to use (default is the current object default assay).

species_prefix

the species prefix in front of gene symbols in object if providing two species for multi-species aligned dataset.

## Not run: 
# Liger
liger_object <- Add_Mito_Ribo(object = liger_object, species = "human")
## End(Not run)
## Not run: 
# Seurat
seurat_object <- Add_Mito_Ribo(object = seurat_object, species = "human")
## End(Not run)

Add_Pct_Diff(
 marker_dataframe,
 pct.1_name = "pct.1",
 pct.2_name = "pct.2",
 overwrite = FALSE
)

marker_dataframe

data.frame containing the results of FindMarkers , FindAllMarkers , or other DE test data.frame.

pct.1_name

the name of data.frame column corresponding to percent expressed in group 1. Default is Seurat default "pct.1".

pct.2_name

the name of data.frame column corresponding to percent expressed in group 2. Default is Seurat default "pct.2".

overwrite

logical. If the marker_dataframe already contains column named "pct_diff" whether to overwrite or return error message. Default is FALSE.

## Not run: 
marker_df <- FindAllMarkers(object = obj_name)
marker_df <- Add_Pct_Diff(marker_dataframe = marker_df)
# or piped with function
marker_df <- FindAllMarkers(object = obj_name) %>%
 Add_Pct_Diff()
## End(Not run)

Add_Sample_Meta(
 seurat_object,
 meta_data,
 join_by_seurat,
 join_by_meta,
 na_ok = FALSE,
 overwrite = FALSE
)

seurat_object

object name.

meta_data

data.frame/tibble containing meta data or path to file to read. Must be formatted as either data.frame or tibble.

join_by_seurat

name of the column in seurat_object@meta.data that contains matching variables to join_by_meta in meta_data.

join_by_meta

name of the column in meta_data that contains matching variables to join_by_seurat in seurat_object@meta.data.

na_ok

logical, is it ok to add NA values to seurat_object@meta.data. Default is FALSE. Be very careful if setting TRUE because if there is error in join operation it may result in all ⁠@meta.data⁠ values being replaced with NA.

overwrite

logical, if there are shared columns between seurat_object@meta.data and meta_data should the current seurat_object@meta.data columns be overwritten. Default is FALSE. This parameter excludes values provided to join_by_seurat and join_by_meta.

## Not run: 
# meta_data present in environment
sample_level_meta <- data.frame(...)
obj <- Add_Sample_Meta(seurat_object = obj, meta_data = sample_level_meta,
join_by_seurat = "orig.ident", join_by_meta = "sample_ID")
# from meta data file
obj <- Add_Sample_Meta(seurat_object = obj, meta_data = "meta_data/sample_level_meta.csv",
join_by_seurat = "orig.ident", join_by_meta = "sample_ID")
## End(Not run)

Add_Top_Gene_Pct(object, ...)
## S3 method for class 'liger'
Add_Top_Gene_Pct(
 object,
 num_top_genes = 50,
 meta_col_name = NULL,
 overwrite = FALSE,
 verbose = TRUE,
 ...
)
## S3 method for class 'Seurat'
Add_Top_Gene_Pct(
 object,
 num_top_genes = 50,
 meta_col_name = NULL,
 assay = "RNA",
 overwrite = FALSE,
 verbose = TRUE,
 ...
)

object

Seurat or LIGER object.

...

Arguments passed to other methods

num_top_genes

An integer vector specifying the size(s) of the top set of high-abundance genes. Used to compute the percentage of library size occupied by the most highly expressed genes in each cell.

meta_col_name

name to use for new meta data column. Default is "percent_topXX", where XX is equal to the value provided to num_top_genes.

overwrite

Logical. Whether to overwrite existing an meta.data column. Default is FALSE meaning that function will abort if column with name provided to meta_col_name is present in meta.data slot.

verbose

logical, whether to print messages with status updates, default is TRUE.

assay

assay to use in calculation. Default is "RNA". Note This should only be changed if storing corrected and uncorrected assays in same object (e.g. outputs of both Cell Ranger and Cell Bender).

## Not run: 
liger_object <- Add_Top_Gene_Pct(object = liger_object, num_top_genes = 50)
## End(Not run)
## Not run: 
library(Seurat)
pbmc_small <- Add_Top_Gene_Pct(seurat_object = pbmc_small, num_top_genes = 50)
## End(Not run)

Barcode_Plot(
 br_out,
 pt.size = 6,
 plot_title = "Barcode Ranks",
 raster_dpi = c(1024, 1024),
 plateau = NULL
)

br_out

DFrame output from barcodeRanks .

pt.size

point size for plotting, default is 6.

plot_title

Title for plot, default is "Barcode Ranks".

raster_dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(1024, 1024).

plateau

numerical value at which to add vertical line designating estimated empty droplet plateau (default is NULL).

## Not run: 
mat <- Read10X_h5(filename = "raw_feature_bc_matrix.h5")
br_results <- DropletUtils::barcodeRanks(mat)
Barcode_Plot(br_out = br_results)
## End(Not run)

Blank_Theme(...)

...

extra arguments passed to ggplot2::theme().

# Generate a plot and customize theme
library(ggplot2)
df <- data.frame(x = rnorm(n = 100, mean = 20, sd = 2), y = rbinom(n = 100, size = 100, prob = 0.2))
p <- ggplot(data = df, mapping = aes(x = x, y = y)) + geom_point(mapping = aes(color = 'red'))
p + Blank_Theme()

Case_Check(
 seurat_object,
 gene_list,
 case_check_msg = TRUE,
 return_features = TRUE,
 assay = NULL
)

seurat_object

Seurat object name.

gene_list

vector of genes to check.

case_check_msg

logical. Whether to print message to console if alternate case features are found in addition to inclusion in returned list. Default is TRUE.

return_features

logical. Whether to return vector of alternate case features. Default is TRUE.

assay

Name of assay to pull feature names from. If NULL will use the result of DefaultAssay(seurat_object).

## Not run: 
alt_features <- Case_Check(seurat_object = obj_name, gene_list = DEG_list)
## End(Not run)

CellBender_Diff_Plot(
 feature_diff_df,
 pct_diff_threshold = 25,
 num_features = NULL,
 label = TRUE,
 num_labels = 20,
 min_count_label = 1,
 repel = TRUE,
 custom_labels = NULL,
 plot_line = TRUE,
 plot_title = "Raw Counts vs. Cell Bender Counts",
 x_axis_label = "Raw Data Counts",
 y_axis_label = "Cell Bender Counts",
 xnudge = 0,
 ynudge = 0,
 max.overlaps = 100,
 label_color = "dodgerblue",
 fontface = "bold",
 label_size = 3.88,
 bg.color = "white",
 bg.r = 0.15,
 ...
)

feature_diff_df

name of data.frame created using CellBender_Feature_Diff .

pct_diff_threshold

threshold to use for feature plotting. Resulting plot will only contain features which exhibit percent change >= value. Default is 25.

num_features

Number of features to plot. Will ignore pct_diff_threshold and return plot with specified number of features. Default is NULL.

label

logical, whether or not to label the features that have largest percent difference between raw and CellBender counts (Default is TRUE).

num_labels

Number of features to label if label = TRUE, (default is 20).

min_count_label

Minimum number of raw counts per feature necessary to be included in plot labels (default is 1)

repel

logical, whether to use geom_text_repel to create a nicely-repelled labels; this is slow when a lot of points are being plotted. If using repel, set xnudge and ynudge to 0, (Default is TRUE).

custom_labels

A custom set of features to label instead of the features most different between raw and CellBender counts.

plot_line

logical, whether to plot diagonal line with slope = 1 (Default is TRUE).

plot_title

Plot title.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

xnudge

Amount to nudge X and Y coordinates of labels by.

ynudge

Amount to nudge X and Y coordinates of labels by.

max.overlaps

passed to geom_text_repel , exclude text labels that overlap too many things. Defaults to 100.

label_color

Color to use for text labels.

fontface

font face to use for text labels ("plain", "bold", "italic", "bold.italic") (Default is "bold").

label_size

text size for feature labels (passed to geom_text_repel ).

bg.color

color to use for shadow/outline of text labels (passed to geom_text_repel ) (Default is white).

bg.r

radius to use for shadow/outline of text labels (passed to geom_text_repel ) (Default is 0.15).

...

Extra parameters passed to geom_text_repel through LabelPoints .

## Not run: 
# get cell bender differences data.frame
cb_stats <- CellBender_Feature_Diff(seurat_object - obj, raw_assay = "RAW",
cell_bender_assay = "RNA")
# plot
CellBender_Diff_Plot(feature_diff_df = cb_stats, pct_diff_threshold = 25)
## End(Not run)

CellBender_Feature_Diff(
 seurat_object = NULL,
 raw_assay = NULL,
 cell_bender_assay = NULL,
 raw_mat = NULL,
 cell_bender_mat = NULL
)

seurat_object

Seurat object name.

raw_assay

Name of the assay containing the raw count data.

cell_bender_assay

Name of the assay containing the CellBender count data.

raw_mat

Name of raw count matrix in environment if not using Seurat object.

cell_bender_mat

Name of CellBender count matrix in environment if not using Seurat object.

## Not run: 
cb_stats <- CellBender_Feature_Diff(seurat_object - obj, raw_assay = "RAW",
cell_bender_assay = "RNA")
## End(Not run)

Cell_Highlight_Plot(
 seurat_object,
 cells_highlight,
 highlight_color = NULL,
 background_color = "lightgray",
 pt.size = NULL,
 aspect_ratio = NULL,
 figure_plot = FALSE,
 raster = NULL,
 raster.dpi = c(512, 512),
 label = FALSE,
 split.by = NULL,
 split_seurat = FALSE,
 reduction = NULL,
 ggplot_default_colors = FALSE,
 ...
)

seurat_object

Seurat object name.

cells_highlight

Cell names to highlight in named list.

highlight_color

Color to highlight cells.

background_color

non-highlighted cell colors (default is "lightgray")..

pt.size

point size for both highlighted cluster and background.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

figure_plot

logical. Whether to remove the axes and plot with legend on left of plot denoting axes labels. (Default is FALSE). Requires split_seurat = TRUE.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

label

Whether to label the highlighted meta data variable(s). Default is FALSE.

split.by

Variable in ⁠@meta.data⁠ to split the plot by.

split_seurat

logical. Whether or not to display split plots like Seurat (shared y axis) or as individual plots in layout. Default is FALSE.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

ggplot_default_colors

logical. If highlight_color = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

...

Extra parameters passed toDimPlot .

library(Seurat)
# Creating example non-overlapping vectors of cells
MS4A1 <- WhichCells(object = pbmc_small, expression = MS4A1 > 4)
GZMB <- WhichCells(object = pbmc_small, expression = GZMB > 4)
# Format as named list
cells <- list("MS4A1" = MS4A1,
 "GZMB" = GZMB)
Cell_Highlight_Plot(seurat_object = pbmc_small, cells_highlight = cells)

## S3 method for class 'liger'
Cells(x, by_dataset = FALSE, ...)

x

LIGER object name.

by_dataset

logical, whether to return list with vector of cell barcodes for each dataset in LIGER object or to return single vector of cell barcodes across all datasets in object (default is FALSE; return vector of cells).

...

Arguments passed to other methods

## Not run: 
# return single vector of all cells
all_features <- Cells(x = object, by_dataset = FALSE)
# return list of vectors containing cells from each individual dataset in object
dataset_features <- Cells(x = object, by_dataset = TRUE)
## End(Not run)

Cells_by_Identities_LIGER(liger_object, group.by = NULL, by_dataset = FALSE)

liger_object

LIGER object name.

group.by

name of meta data column to use, default is current default clustering.

by_dataset

logical, whether to return list with entries for cell barcodes for each identity in group.by or to return list of lists (1 entry per dataset and each ident within the dataset) (default is FALSE; return list)

## Not run: 
# return single vector of all cells
cells_by_idents <- Cells_by_Identities_LIGER(liger_object = object, by_dataset = FALSE)
# return list of vectors containing cells from each individual dataset in object
cells_by_idents_by_dataset <- Cells_by_Identities_LIGER(liger_object = object, by_dataset = TRUE)
## End(Not run)

Cells_per_Sample(seurat_object, sample_col = NULL)

seurat_object

Seurat object

sample_col

column name in meta.data that contains sample ID information. Default is NULL and will use "orig.ident column

library(Seurat)
num_cells <- Cells_per_Sample(seurat_object = pbmc_small, sample_col = "orig.ident")

Change_Delim_All(data, current_delim, new_delim)

data

Either matrix/data.frame or list of matrices/data.frames with the cell barcodes in the column names.

current_delim

a single value of current delimiter.

new_delim

a single value of new delimiter desired.

## Not run: 
dge_matrix <- Change_Delim_All(data = dge_matrix, current_delim = ".", new_delim = "-")
## End(Not run)

Change_Delim_Prefix(data, current_delim, new_delim)

data

Either matrix/data.frame or list of matrices/data.frames with the cell barcodes in the column names.

current_delim

a single value of current delimiter.

new_delim

a single value of new delimiter desired.

## Not run: 
dge_matrix <- Change_Delim_Prefix(data = dge_matrix, current_delim = ".", new_delim = "-")
## End(Not run)

Change_Delim_Suffix(data, current_delim, new_delim)

data

Either matrix/data.frame or list of matrices/data.frames with the cell barcodes in the column names.

current_delim

a single value of current delimiter.

new_delim

a single value of new delimiter desired.

## Not run: 
dge_matrix <- Change_Delim_Suffix(data = dge_matrix, current_delim = ".", new_delim = "-")
## End(Not run)

CheckMatrix_scCustom(
 object,
 checks = c("infinite", "logical", "integer", "na")
)

object

A matrix

checks

Type of checks to perform, choose one or more from:

• “infinite”: Emit a warning if any value is infinite

• “logical”: Emit a warning if any value is a logical

• “integer”: Emit a warning if any value is not an integer

• “na”: Emit a warning if any value is an NA or NaN

## Not run: 
mat <- Read10X(...)
CheckMatrix_scCustom(object = mat)
## End(Not run)

Cluster_Highlight_Plot(
 seurat_object,
 cluster_name,
 highlight_color = NULL,
 background_color = "lightgray",
 pt.size = NULL,
 aspect_ratio = NULL,
 figure_plot = FALSE,
 raster = NULL,
 raster.dpi = c(512, 512),
 label = FALSE,
 split.by = NULL,
 split_seurat = FALSE,
 split_title_size = 15,
 num_columns = NULL,
 reduction = NULL,
 ggplot_default_colors = FALSE,
 ...
)

seurat_object

Seurat object name.

cluster_name

Name(s) (or number(s)) identity of cluster to be highlighted.

highlight_color

Color(s) to highlight cells. The default is NULL and plot will use scCustomize_Palette().

background_color

non-highlighted cell colors.

pt.size

point size for both highlighted cluster and background.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

figure_plot

logical. Whether to remove the axes and plot with legend on left of plot denoting axes labels. (Default is FALSE). Requires split_seurat = TRUE.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

label

Whether to label the highlighted cluster(s). Default is FALSE.

split.by

Feature to split plots by (i.e. "orig.ident").

split_seurat

logical. Whether or not to display split plots like Seurat (shared y axis) or as individual plots in layout. Default is FALSE.

split_title_size

size for plot title labels when using split.by.

num_columns

Number of columns in plot layout. Only valid if split.by != NULL.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

...

Extra parameters passed to DimPlot .

Cluster_Highlight_Plot(seurat_object = pbmc_small, cluster_name = "1", highlight_color = "gold",
background_color = "lightgray", pt.size = 2)

Cluster_Stats_All_Samples(
 seurat_object,
 group_by_var = deprecated(),
 group.by = "orig.ident",
 order_by_freq = TRUE
)

seurat_object

Seurat object name.

group_by_var

soft-deprecated. See group.by.

group.by

meta data column to classify samples (default = "orig.ident").

order_by_freq

logical, whether the data.frame should be ordered by frequency of identity (default; TRUE), or by cluster/fector order (FALSE).

## Not run: 
stats <- Cluster_Stats_All_Samples(seurat_object = object, group.by = "orig.ident")
## End(Not run)

Clustered_DotPlot(
 seurat_object,
 features,
 label_selected_features = NULL,
 split.by = NULL,
 colors_use_exp = viridis_plasma_dark_high,
 exp_color_min = -2,
 exp_color_middle = NULL,
 exp_color_max = 2,
 exp_value_type = "scaled",
 print_exp_quantiles = FALSE,
 colors_use_idents = NULL,
 show_ident_colors = TRUE,
 show_annotation_name = TRUE,
 x_lab_rotate = TRUE,
 plot_padding = NULL,
 flip = FALSE,
 k = 1,
 feature_km_repeats = 1000,
 ident_km_repeats = 1000,
 row_label_size = 8,
 row_label_fontface = "plain",
 grid_color = NULL,
 cluster_feature = TRUE,
 cluster_ident = TRUE,
 column_label_size = 8,
 legend_label_size = 10,
 legend_title_size = 10,
 legend_position = "right",
 legend_orientation = NULL,
 show_ident_legend = TRUE,
 show_row_names = TRUE,
 show_column_names = TRUE,
 column_names_side = "bottom",
 row_names_side = "right",
 raster = FALSE,
 plot_km_elbow = TRUE,
 elbow_kmax = NULL,
 assay = NULL,
 group.by = NULL,
 idents = NULL,
 show_parent_dend_line = TRUE,
 nan_error = FALSE,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 seed = 123
)

seurat_object

Seurat object name.

features

Features to plot.

label_selected_features

a subset of features to only label some of the plotted features.

split.by

Variable in ⁠@meta.data⁠ to split the identities plotted by.

colors_use_exp

Color palette to use for plotting expression scale. Default is viridis::plasma(n = 20, direction = -1).

exp_color_min

Minimum scaled average expression threshold (everything smaller will be set to this). Default is -2.

exp_color_middle

What scaled expression value to use for the middle of the provided colors_use_exp. By default will be set to value in middle of exp_color_min and exp_color_max.

exp_color_max

Minimum scaled average expression threshold (everything smaller will be set to this). Default is 2.

exp_value_type

Whether to plot average normalized expression or scaled average normalized expression. Only valid when split.by is provided.

print_exp_quantiles

Whether to print the quantiles of expression data in addition to plots. Default is FALSE. NOTE: These values will be altered by choices of exp_color_min and exp_color_min if there are values below or above those cutoffs, respectively.

colors_use_idents

specify color palette to used for identity labels. By default if number of levels plotted is less than or equal to 36 it will use "polychrome" and if greater than 36 will use "varibow" with shuffle = TRUE both from DiscretePalette_scCustomize.

show_ident_colors

logical, whether to show colors for idents on the column/rows of the plot (default is TRUE).

show_annotation_name

logical, whether or not to show annotation name next to color bar. Default is TRUE.

x_lab_rotate

How to rotate column labels. By default set to TRUE which rotates labels 45 degrees. If set FALSE rotation is set to 0 degrees. Users can also supply custom angle for text rotation.

plot_padding

if plot needs extra white space padding so no plot or labels are cutoff. The parameter accepts TRUE or numeric vector of length 4. If TRUE padding will be set to c(2, 10, 0 0) (bottom, left, top, right). Can also be customized further with numeric vector of length 4 specifying the amount of padding in millimeters. Default is NULL, no padding.

flip

logical, whether to flip the axes of final plot. Default is FALSE; rows = features and columns = idents.

k

Value to use for k-means clustering on features Sets (km) parameter in ComplexHeatmap::Heatmap(). From ComplexHeatmap::Heatmap(): Apply k-means clustering on rows. If the value is larger than 1, the heatmap will be split by rows according to the k-means clustering. For each row slice, hierarchical clustering is still applied with parameters above.

feature_km_repeats

Number of k-means runs to get a consensus k-means clustering for features. Note if feature_km_repeats is set to value greater than one, the final number of groups might be smaller than row_km, but this might mean the original row_km is not a good choice. Default is 1000.

ident_km_repeats

Number of k-means runs to get a consensus k-means clustering. Similar to feature_km_repeats. Default is 1000.

row_label_size

Size of the feature labels. Provided to row_names_gp in Heatmap call.

row_label_fontface

Fontface to use for row labels. Provided to row_names_gp in Heatmap call.

grid_color

color to use for heatmap grid. Default is NULL which "removes" grid by using NA color.

cluster_feature

logical, whether to cluster and reorder feature axis. Default is TRUE.

cluster_ident

logical, whether to cluster and reorder identity axis. Default is TRUE.

column_label_size

Size of the feature labels. Provided to column_names_gp in Heatmap call.

legend_label_size

Size of the legend text labels. Provided to labels_gp in Heatmap legend call.

legend_title_size

Size of the legend title text labels. Provided to title_gp in Heatmap legend call.

legend_position

Location of the plot legend (default is "right").

legend_orientation

Orientation of the legend (default is NULL).

show_ident_legend

logical, whether to show the color legend for idents in plot (default is TRUE).

show_row_names

logical, whether to show row names on plot (default is TRUE).

show_column_names

logical, whether to show column names on plot (default is TRUE).

column_names_side

Should the row names be on the "bottom" or "top" of plot. Default is "bottom".

row_names_side

Should the row names be on the "left" or "right" of plot. Default is "right".

raster

Logical, whether to render in raster format (faster plotting, smaller files). Default is FALSE.

plot_km_elbow

Logical, whether or not to return the Sum Squared Error Elbow Plot for k-means clustering. Estimating elbow of this plot is one way to determine "optimal" value for k. Based on: https://stackoverflow.com/a/15376462/15568251.

elbow_kmax

The maximum value of k to use for plot_km_elbow. Suggest setting larger value so the true shape of plot can be observed. Value must be 1 less than number of features provided. If NULL parameter will be set dependent on length of feature list up to elbow_kmax = 20.

assay

Name of assay to use, defaults to the active assay.

group.by

Group (color) cells in different ways (for example, orig.ident).

idents

Which classes to include in the plot (default is all).

show_parent_dend_line

Logical, Sets parameter of same name in ComplexHeatmap::Heatmap(). From ComplexHeatmap::Heatmap(): When heatmap is split, whether to add a dashed line to mark parent dendrogram and children dendrograms. Default is TRUE.

nan_error

logical, default is FALSE. ONLY set this value to true if you get error related to NaN values when attempting to use plotting function. Plotting may be slightly slower if TRUE depending on number of features being plotted.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

seed

Sets seed for reproducible plotting (ComplexHeatmap plot).

library(Seurat)
Clustered_DotPlot(seurat_object = pbmc_small, features = c("CD3E", "CD8", "GZMB", "MS4A1"))

ColorBlind_Pal()

cols <- ColorBlind_Pal()
PalettePlot(pal = cols)

Convert_Assay(seurat_object, assay = NULL, convert_to)

seurat_object

Seurat object name.

assay

name(s) of assays to convert. Default is NULL and will check with users which assays they want to convert.

convert_to

value of what assay type to convert current assays to. #'

• Accepted values for V3/4 are: "Assay", "assay", "V3", or "v3".

• Accepted values for V5 are: "Assay5", "assay5", "V5", or "v5".

## Not run: 
# Convert to V3/4 assay
obj <- Convert_Assay(seurat_object = obj, convert_to = "V3")
# Convert to 5 assay
obj <- Convert_Assay(seurat_object = obj, convert_to = "V5")
## End(Not run)

Copy_From_GCP(folder_file_path, gcp_bucket_path)

folder_file_path

folder to be copied to GCP bucket.

gcp_bucket_path

GCP bucket path to copy to files.

## Not run: 
Copy_From_GCP(folder_file_path = "plots/", gcp_bucket_path = "gs://bucket_name_and_folder_path")
## End(Not run)

Copy_To_GCP(folder_file_path, gcp_bucket_path)

folder_file_path

folder to be copied to GCP bucket.

gcp_bucket_path

GCP bucket path to copy to files.

## Not run: 
Copy_To_GCP(folder_file_path = "plots/", gcp_bucket_path = "gs://bucket_name_and_folder_path")
## End(Not run)

Create_10X_H5(
 raw_data_file_path,
 source_type = "10X",
 save_file_path,
 save_name
)

raw_data_file_path

file path to raw data file(s).

source_type

type of source data (Default is "10X"). Alternatively can provide "Matrix" or "data.frame".

save_file_path

file path to directory to save file.

save_name

name prefix for output H5 file.

## Not run: 
Create_10X_H5(raw_data_file_path = "file_path", save_file_path = "file_path2", save_name = "NAME")
## End(Not run)

Create_CellBender_Merged_Seurat(
 raw_cell_bender_matrix = NULL,
 raw_counts_matrix = NULL,
 raw_assay_name = "RAW",
 min_cells = deprecated(),
 min_features = deprecated(),
 min.cells = 5,
 min.features = 200,
 ...
)

raw_cell_bender_matrix

matrix file containing the cell bender correct counts.

raw_counts_matrix

matrix file contain the uncorrected Cell Ranger (or other) counts.

raw_assay_name

a key value to use specifying the name of assay. Default is "RAW".

min_cells

soft-deprecated. See min.cells.

min_features

soft-deprecated. See min.features.

min.cells

value to supply to min.cells parameter of CreateSeuratObject . Default is 5.

min.features

value to supply to min.features parameter of CreateSeuratObject . Default is 200.

...

Extra parameters passed to CreateSeuratObject .

## Not run: 
seurat_obj <- Create_CellBender_Merged_Seurat(raw_cell_bender_matrix = cb_matrix,
raw_counts_matrix = cr_matrix)
## End(Not run)

Create_Cluster_Annotation_File(
 file_path = NULL,
 file_name = "cluster_annotation"
)

file_path

path to directory to save file. Default is current working directory.

file_name

name to use for annotation file. Function automatically adds file type ".csv" suffix. Default is "cluster_annotation".

## Not run: 
Create_Cluster_Annotation_File(file_path = "cluster_annotation_folder_name")
## End(Not run)

Dark2_Pal()

cols <- Dark2_Pal()
PalettePlot(pal= cols)

Dataset_Size_LIGER(
 liger_object,
 meta_data_column = NULL,
 filter_by = NULL,
 print_filter = FALSE
)

liger_object

LIGER object name.

meta_data_column

other meta data to include in returned data.frame.

filter_by

meta data column to filter data by. Will filter data to return only values for the largest dataset for each unique value in provided meta data column.

print_filter

logical, whether to print filtered results to console, default is FALSE.

## Not run: 
# Return values for all datasets
## End(Not run)

DimPlot_All_Samples(
 seurat_object,
 meta_data_column = "orig.ident",
 colors_use = "black",
 pt.size = NULL,
 aspect_ratio = NULL,
 title_size = 15,
 num_columns = NULL,
 reduction = NULL,
 dims = c(1, 2),
 raster = NULL,
 raster.dpi = c(512, 512),
 ...
)

seurat_object

Seurat object name.

meta_data_column

Meta data column to split plots by.

colors_use

single color to use for all plots or a vector of colors equal to the number of plots.

pt.size

Adjust point size for plotting.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

title_size

size for plot title labels.

num_columns

number of columns in final layout plot.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

dims

Which dimensions to plot. Defaults to c(1,2) if not specified.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

...

Extra parameters passed to DimPlot .

library(Seurat)
pbmc_small$sample_id <- sample(c("sample1", "sample2"), size = ncol(pbmc_small), replace = TRUE)
DimPlot_All_Samples(seurat_object = pbmc_small, meta_data_column = "sample_id", color = "black",
num_columns = 2)

DimPlot_LIGER(
 liger_object,
 group_by = deprecated(),
 group.by = NULL,
 split_by = deprecated(),
 split.by = NULL,
 colors_use_cluster = NULL,
 colors_use_meta = NULL,
 pt_size = NULL,
 shuffle = TRUE,
 shuffle_seed = 1,
 reduction_label = "UMAP",
 reduction = NULL,
 aspect_ratio = NULL,
 label = TRUE,
 label_size = NA,
 label_repel = FALSE,
 label_box = FALSE,
 label_color = "black",
 combination = FALSE,
 raster = NULL,
 raster.dpi = c(512, 512),
 num_columns = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123
)

liger_object

liger liger_object. Need to perform clustering before calling this function

group_by

soft-deprecated. See group.by.

group.by

Variable to be plotted. If NULL will plot clusters from liger@clusters slot. If combination = TRUE will plot both clusters and meta data variable. If combination = TRUE will plot both clusters and meta data variable.

split_by

soft-deprecated. See split.by.

split.by

Variable to split plots by.

colors_use_cluster

colors to use for plotting by clusters. By default if number of levels plotted is less than or equal to 36 will use "polychrome" and if greater than 36 will use "varibow" with shuffle = TRUE both from DiscretePalette_scCustomize .

colors_use_meta

colors to use for plotting by meta data (cell.data) variable. By default if number of levels plotted is less than or equal to 36 it will use "polychrome" and if greater than 36 will use "varibow" with shuffle = TRUE both from DiscretePalette_scCustomize.

pt_size

Adjust point size for plotting.

shuffle

logical. Whether to randomly shuffle the order of points. This can be useful for crowded plots if points of interest are being buried. (Default is TRUE).

shuffle_seed

Sets the seed if randomly shuffling the order of points.

reduction_label

What to label the x and y axes of resulting plots. LIGER does not store name of technique and therefore needs to be set manually. Default is "UMAP". (only valid for rliger < 2.0.0).

reduction

specify reduction to use when plotting. Default is current object default reduction (only valid for rliger v2.0.0 or greater).

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

label

logical. Whether or not to label the clusters. ONLY applies to plotting by cluster. Default is TRUE.

label_size

size of cluster labels.

label_repel

logical. Whether to repel cluster labels from each other if plotting by cluster (if group.by = NULL or ⁠group.by = "cluster⁠). Default is FALSE.

label_box

logical. Whether to put a box around the label text (uses geom_text vs geom_label). Default is FALSE.

label_color

Color to use for cluster labels. Default is "black".

combination

logical, whether to return patchwork displaying both plots side by side. (Default is FALSE).

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

num_columns

Number of columns in plot layout. Only valid if split.by != NULL.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

## Not run: 
DimPlot_LIGER(liger_object = obj_name, reduction_label = "UMAP")
## End(Not run)

DimPlot_scCustom(
 seurat_object,
 colors_use = NULL,
 pt.size = NULL,
 reduction = NULL,
 group.by = NULL,
 split.by = NULL,
 split_downsample = FALSE,
 split_seurat = FALSE,
 figure_plot = FALSE,
 aspect_ratio = NULL,
 add_prop_plot = FALSE,
 prop_plot_percent = FALSE,
 prop_plot_x_log = FALSE,
 prop_plot_label = FALSE,
 shuffle = TRUE,
 seed = 1,
 label = NULL,
 label.size = 4,
 label.color = "black",
 label.box = FALSE,
 dims = c(1, 2),
 repel = FALSE,
 raster = NULL,
 raster.dpi = c(512, 512),
 num_columns = NULL,
 ggplot_default_colors = FALSE,
 downsample_seed = 123,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

colors_use

color palette to use for plotting. By default if number of levels plotted is less than or equal to 36 it will use "polychrome" and if greater than 36 will use "varibow" with shuffle = TRUE both from DiscretePalette_scCustomize.

pt.size

Adjust point size for plotting.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident); default is the current active.ident of the object.

split.by

Feature to split plots by (i.e. "orig.ident").

split_downsample

logical, whether to downsample the split plots by number of cells in the smallest group. Default is FALSE.

split_seurat

logical. Whether or not to display split plots like Seurat (shared y axis) or as individual plots in layout. Default is FALSE.

figure_plot

logical. Whether to remove the axes and plot with legend on left of plot denoting axes labels. (Default is FALSE). Requires split_seurat = TRUE.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

add_prop_plot

logical, whether to add plot to returned layout with the number of cells per identity (or percent of cells per identity). Default is FALSE.

prop_plot_percent

logical, if add_prop_plot = TRUE this parameter controls whether proportion plot shows raw cell number or percent of cells per identity. Default is FALSE; plots raw cell number.

prop_plot_x_log

logical, if add_prop_plot = TRUE this parameter controls whether to change x axis to log10 scale (Default is FALSE).

prop_plot_label

logical, if add_prop_plot = TRUE this parameter controls whether to label the bars with total number of cells or percentages; Default is FALSE.

shuffle

logical. Whether to randomly shuffle the order of points. This can be useful for crowded plots if points of interest are being buried. (Default is TRUE).

seed

Sets the seed if randomly shuffling the order of points.

label

Whether to label the clusters. By default if group.by = NULL label = TRUE, and otherwise it is FALSE.

label.size

Sets size of labels.

label.color

Sets the color of the label text.

label.box

Whether to put a box around the label text (geom_text vs geom_label).

dims

Which dimensions to plot. Defaults to c(1,2) if not specified.

repel

Repel labels.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

num_columns

Number of columns in plot layout. Only valid if split.by != NULL.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

downsample_seed

random seed to use when selecting random cells to downsample in plot. Default = 123.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to DimPlot .

library(Seurat)
DimPlot_scCustom(seurat_object = pbmc_small)

DiscretePalette_scCustomize(
 num_colors,
 palette = NULL,
 shuffle_pal = FALSE,
 seed = 123
)

num_colors

Number of colors to be generated.

palette

Options are "alphabet", "alphabet2", "glasbey", "polychrome", "stepped", "ditto_seq", "varibow".

shuffle_pal

randomly shuffle the outputted palette. Most useful for varibow palette as that is normally an ordered palette.

seed

random seed for the palette shuffle. Default = 123.

pal <- DiscretePalette_scCustomize(num_colors = 36, palette = "varibow")
PalettePlot(pal= pal)

DotPlot_scCustom(
 seurat_object,
 features,
 group.by = NULL,
 colors_use = viridis_plasma_dark_high,
 remove_axis_titles = TRUE,
 x_lab_rotate = FALSE,
 y_lab_rotate = FALSE,
 facet_label_rotate = FALSE,
 flip_axes = FALSE,
 ...
)

seurat_object

Seurat object name.

features

Features to plot.

group.by

Name of metadata variable (column) to group cells by (for example, orig.ident); default is the current active.ident of the object.

colors_use

specify color palette to used. Default is viridis_plasma_dark_high.

remove_axis_titles

logical. Whether to remove the x and y axis titles. Default = TRUE.

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is FALSE).

y_lab_rotate

Rotate x-axis labels 45 degrees (Default is FALSE).

facet_label_rotate

Rotate facet labels on grouped DotPlots by 45 degrees (Default is FALSE).

flip_axes

whether or not to flip and X and Y axes (Default is FALSE).

...

Extra parameters passed to DotPlot .

library(Seurat)
DotPlot_scCustom(seurat_object = pbmc_small, features = c("CD3E", "CD8", "GZMB", "MS4A1"))

ElbowPlot_scCustom(
 seurat_object,
 ndims = NULL,
 reduction = "pca",
 calc_cutoffs = TRUE,
 plot_cutoffs = TRUE,
 line_colors = c("dodgerblue", "firebrick"),
 linewidth = 0.5
)

seurat_object

name of Seurat object

ndims

The number of dims to plot. Default is NULL and will plot all dims

reduction

The reduction to use, default is "pca"

calc_cutoffs

logical, whether or not to calculate the cutoffs, default is TRUE.

plot_cutoffs

lgoical, whether to plot the cutoffs as vertical lines on plot, default is TRUE.

line_colors

colors for the cutoff lines, default is c("dodgerblue", "firebrick").

linewidth

widith of the cutoff lines, default is 0.5.

library(Seurat)
ElbowPlot_scCustom(seurat_object = pbmc_small)

## S3 method for class 'liger'
Embeddings(object, reduction = NULL, iNMF = FALSE, check_only = FALSE, ...)

object

LIGER object name.

reduction

name of dimensionality reduction to pull

iNMF

logical, whether to extract iNMF h.norm matrix instead of dimensionality reduction embeddings.

check_only

logical, return TRUE if valid reduction is present.

...

Arguments passed to other methods

## Not run: 
# Extract embedding matrix for current dimensionality reduction
UMAP_coord <- Embeddings(object = liger_object)
# Extract iNMF h.norm matrix
iNMF_mat <- Embeddings(object = liger_object, reduction = "iNMF")
## End(Not run)

Extract_Modality(matrix_list)

matrix_list

list of matrices to split by modality

## Not run: 
multi_mat <- Read10X(...)
new_multi_mat <- Extract_Modality(matrix_list = multi_mat)
## End(Not run)

Extract_Sample_Meta(
 object,
 sample_col = "orig.ident",
 sample_name = deprecated(),
 variables_include = NULL,
 variables_exclude = NULL,
 include_all = FALSE
)

object

Seurat or LIGER object

sample_col

meta.data column to use as sample. Output data.frame will contain one row per level or unique value in this variable.

sample_name

. See sample_name.

variables_include

⁠@meta.data⁠ columns to keep in final data.frame. All other columns will be discarded. Default is NULL.

variables_exclude

columns to discard in final data.frame. Many cell level columns are irrelevant at the sample level (e.g., nFeature_RNA, percent_mito).

• Default parameter value is NULL but internally will set to discard nFeature_ASSAY(s), nCount_ASSAY(s), percent_mito, percent_ribo, percent_mito_ribo, and log10GenesPerUMI.

• If sample level median values are desired for these type of variables the output of this function can be joined with output of Median_Stats .

• Set parameter to include_all = TRUE to prevent any columns from being excluded.

include_all

logical, whether or not to include all object meta data columns in output data.frame. Default is FALSE.

library(Seurat)
pbmc_small[["batch"]] <- sample(c("batch1", "batch2"), size = ncol(pbmc_small), replace = TRUE)
sample_meta <- Extract_Sample_Meta(object = pbmc_small, sample_name = "orig.ident")
# Only return specific columns from meta data (orig.ident and batch)
sample_meta2 <- Extract_Sample_Meta(object = pbmc_small, sample_name = "orig.ident",
variables_include = "batch")
# Return all columns from meta data
sample_meta3 <- Extract_Sample_Meta(object = pbmc_small, sample_name = "orig.ident",
include_all = TRUE)

Extract_Top_Markers(
 marker_dataframe,
 num_features = 10,
 num_genes = deprecated(),
 group_by = deprecated(),
 group.by = "cluster",
 rank_by = "avg_log2FC",
 gene_column = "gene",
 gene_rownames_to_column = FALSE,
 data_frame = FALSE,
 named_vector = TRUE,
 make_unique = FALSE
)

marker_dataframe

data.frame output from FindAllMarkers or similar analysis.

num_features

number of features per group (e.g., cluster) to include in output list.

num_genes

soft-deprecated. See num_features.

group_by

soft-deprecated. See group.by.

group.by

column name of marker_dataframe to group data by. Default is "cluster" based on FindAllMarkers .

rank_by

column name of marker_dataframe to rank data by when selecting num_genes per group.by. Default is "avg_log2FC" based on FindAllMarkers .

gene_column

column name of marker_dataframe that contains the gene IDs. Default is "gene" based on FindAllMarkers .

gene_rownames_to_column

logical. Whether gene IDs are stored in rownames and should be moved to column. Default is FALSE.

data_frame

Logical, whether or not to return filtered data.frame of the original markers_dataframe or to return a vector of gene IDs. Default is FALSE.

named_vector

Logical, whether or not to name the vector of gene names that is returned by the function. If TRUE will name the vector using the column provided to group.by. Default is TRUE.

make_unique

Logical, whether an unnamed vector should return only unique values. Default is FALSE. Not applicable when data_frame = TRUE or named_vector = TRUE.

## Not run: 
top10_genes <- Extract_Top_Markers(marker_dataframe = markers_results, num_genes = 10,
group.by = "cluster", rank_by = "avg_log2FC")
## End(Not run)

Factor_Cor_Plot(
 object,
 reduction = NULL,
 colors_use = NULL,
 label = FALSE,
 label_threshold = 0.5,
 label_size = 5,
 plot_title = NULL,
 plot_type = "full",
 positive_only = FALSE,
 x_lab_rotate = TRUE,
 cluster = TRUE,
 cluster_rect = FALSE,
 cluster_rect_num = NULL,
 cluster_rect_col = NULL
)

object

LIGER or Seurat object.

reduction

Seurat ONLY; name of dimensionality reduction containing NMF loadings.

colors_use

Color palette to use for correlation values. Default is RColorBrewer::RdBu if positive_only = FALSE. If positive_only = TRUE the default is viridis. Users can also supply vector of 3 colors (low, mid, high).

label

logical, whether to add correlation values to plot result.

label_threshold

threshold for adding correlation values if label = TRUE. Default is 0.5.

label_size

size of correlation labels

plot_title

Plot title.

plot_type

Controls plotting full matrix, or just the upper or lower triangles. Accepted values are: "full" (default), "upper", or "lower".

positive_only

logical, whether to limit the plotted values to only positive correlations (negative values set to 0); default is FALSE.

x_lab_rotate

logical, whether to rotate the axes labels on the x-axis. Default is TRUE.

cluster

logical, whether to cluster the plot using hclust (default TRUE). If FALSE factors are listed in numerical order.

cluster_rect

logical, whether to add rectangles around the clustered areas on plot, default is FALSE. Uses cutree to create groups.

cluster_rect_num

number of rectangles to add to the plot, default NULL. Value is provided to k in cutree.

cluster_rect_col

color to use for rectangles, default MULL (will set color automatically).

## Not run: 
Factor_Cor_Plot(object = obj)
## End(Not run)

FeaturePlot_DualAssay(
 seurat_object,
 features,
 assay1 = "RAW",
 assay2 = "RNA",
 colors_use = viridis_plasma_dark_high,
 colors_use_assay2 = NULL,
 na_color = "lightgray",
 order = TRUE,
 pt.size = NULL,
 aspect_ratio = NULL,
 reduction = NULL,
 na_cutoff = 1e-09,
 raster = NULL,
 raster.dpi = c(512, 512),
 layer = "data",
 num_columns = NULL,
 alpha_exp = NULL,
 alpha_na_exp = NULL,
 ...
)

seurat_object

Seurat object name.

features

Feature(s) to plot.

assay1

name of assay one. Default is "RAW" as featured in Create_CellBender_Merged_Seurat

assay2

name of assay two Default is "RNA" as featured in Create_CellBender_Merged_Seurat

colors_use

list of colors or color palette to use.

colors_use_assay2

optional, a second color palette to use for the second assay.

na_color

color to use for points below lower limit.

order

whether to move positive cells to the top (default = TRUE).

pt.size

Adjust point size for plotting.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

na_cutoff

Value to use as minimum expression cutoff. To set no cutoff set to NA.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

layer

Which layer to pull expression data from? Default is "data".

num_columns

Number of columns in plot layout. If number of features > 1 then num_columns dictates the number of columns in overall layout (num_columns = 1 means stacked layout & num_columns = 2 means adjacent layout).

alpha_exp

new alpha level to apply to expressing cell color palette (colors_use). Must be value between 0-1.

alpha_na_exp

new alpha level to apply to non-expressing cell color palette (na_color). Must be value between 0-1.

...

Extra parameters passed to FeaturePlot .

## Not run: 
FeaturePlot_DualAssay(seurat_object = object, features = "Cx3cr1", assay1 = "RAW", assay2 = "RNA",
colors_use = viridis_plasma_dark_high, na_color = "lightgray")
## End(Not run)

FeaturePlot_scCustom(
 seurat_object,
 features,
 colors_use = viridis_plasma_dark_high,
 na_color = "lightgray",
 order = TRUE,
 pt.size = NULL,
 reduction = NULL,
 na_cutoff = 1e-09,
 raster = NULL,
 raster.dpi = c(512, 512),
 split.by = NULL,
 split_collect = NULL,
 aspect_ratio = NULL,
 figure_plot = FALSE,
 num_columns = NULL,
 layer = "data",
 alpha_exp = NULL,
 alpha_na_exp = NULL,
 label = FALSE,
 label_feature_yaxis = FALSE,
 max.cutoff = NA,
 min.cutoff = NA,
 combine = TRUE,
 ...
)

seurat_object

Seurat object name.

features

Feature(s) to plot.

colors_use

list of colors or color palette to use.

na_color

color to use for points below lower limit.

order

whether to move positive cells to the top (default = TRUE).

pt.size

Adjust point size for plotting.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

na_cutoff

Value to use as minimum expression cutoff. This will be lowest value plotted use palette provided to colors_use. Leave as default value to plot only positive non-zero values using color scale and zero/negative values as NA. To plot all values using color palette set to NA.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

split.by

Variable in ⁠@meta.data⁠ to split the plot by.

split_collect

logical, whether to collect the legends/guides when plotting with split.by. Default is TRUE if one value is provided to features otherwise is set to FALSE.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

figure_plot

logical. Whether to remove the axes and plot with legend on left of plot denoting axes labels. (Default is FALSE). Requires split_seurat = TRUE.

num_columns

Number of columns in plot layout.

layer

Which layer to pull expression data from? Default is "data".

alpha_exp

new alpha level to apply to expressing cell color palette (colors_use). Must be value between 0-1.

alpha_na_exp

new alpha level to apply to non-expressing cell color palette (na_color). Must be value between 0-1.

label

logical, whether to label the clusters. Default is FALSE.

label_feature_yaxis

logical, whether to place feature labels on secondary y-axis as opposed to above legend key. Default is FALSE. When setting label_feature_yaxis = TRUE the number of columns in plot output will automatically be set to the number of levels in ⁠split.by'⁠.

min.cutoff, max.cutoff

Vector of minimum and maximum cutoff values for each feature, may specify quantile in the form of 'q##' where '##' is the quantile (eg, 'q1', 'q10').

combine

Combine plots into a single patchworked ggplot object. If FALSE, return a list of ggplot objects.

...

Extra parameters passed to FeaturePlot .

library(Seurat)
FeaturePlot_scCustom(seurat_object = pbmc_small, features = "CD3E",
colors_use = viridis_plasma_dark_high, na_color = "lightgray")

FeatureScatter_scCustom(
 seurat_object,
 feature1 = NULL,
 feature2 = NULL,
 cells = NULL,
 colors_use = NULL,
 pt.size = NULL,
 group.by = NULL,
 split.by = NULL,
 split_seurat = FALSE,
 shuffle = TRUE,
 aspect_ratio = NULL,
 title_size = 15,
 plot.cor = TRUE,
 num_columns = NULL,
 raster = NULL,
 raster.dpi = c(512, 512),
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

feature1

First feature to plot.

feature2

Second feature to plot.

cells

Cells to include on the scatter plot.

colors_use

color for the points on plot.

pt.size

Adjust point size for plotting.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident). Default is active ident.

split.by

Feature to split plots by (i.e. "orig.ident").

split_seurat

logical. Whether or not to display split plots like Seurat (shared y axis) or as individual plots in layout. Default is FALSE.

shuffle

logical, whether to randomly shuffle the order of points. This can be useful for crowded plots if points of interest are being buried. Default is TRUE.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

title_size

size for plot title labels. Does NOT apply if split_seurat = TRUE.

plot.cor

Display correlation in plot subtitle (or title if split_seurat = TRUE).

num_columns

number of columns in final layout plot.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to FeatureScatter .

library(Seurat)
pbmc_small$sample_id <- sample(c("sample1", "sample2"), size = ncol(pbmc_small), replace = TRUE)
FeatureScatter_scCustom(seurat_object = pbmc_small, feature1 = "nCount_RNA",
feature2 = "nFeature_RNA", split.by = "sample_id")

Feature_Present(
 data,
 features,
 case_check = TRUE,
 case_check_msg = TRUE,
 print_msg = TRUE,
 omit_warn = TRUE,
 return_none = FALSE,
 seurat_assay = NULL
)

data

Name of input data. Currently only data of classes: Seurat, liger, data.frame, dgCMatrix, dgTMatrix, tibble are accepted. Gene_IDs must be present in rownames of the data.

features

vector of features to check.

case_check

logical. Whether or not to check if features are found if the case is changed from the input list (Sentence case to Upper and vice versa). Default is TRUE.

case_check_msg

logical. Whether to print message to console if alternate case features are found in addition to inclusion in returned list. Default is TRUE.

print_msg

logical. Whether message should be printed if all features are found. Default is TRUE.

omit_warn

logical. Whether to print message about features that are not found in current object. Default is TRUE.

return_none

logical. Whether list of found vs. bad features should still be returned if no features are found. Default is FALSE.

seurat_assay

Name of assay to pull feature names from if data is Seurat Object. Default is NULL which will check against features from all assays present.

## Not run: 
features <- Feature_Present(data = obj_name, features = DEG_list, print_msg = TRUE,
case_check = TRUE)
found_features <- features[[1]]
## End(Not run)

## S3 method for class 'liger'
Features(x, by_dataset = FALSE, ...)

x

LIGER object name.

by_dataset

logical, whether to return list with vector of features for each dataset in LIGER object or to return single vector of unique features across all datasets in object (default is FALSE; return vector of unique features)

...

Arguments passed to other methods

## Not run: 
# return single vector of all unique features
all_features <- Features(x = object, by_dataset = FALSE)
# return list of vectors containing features from each individual dataset in object
dataset_features <- Features(x = object, by_dataset = TRUE)
## End(Not run)

Fetch_Meta(object, columns = NULL, ...)
## S3 method for class 'liger'
Fetch_Meta(object, columns = NULL, ...)
## S3 method for class 'Seurat'
Fetch_Meta(object, columns = NULL, ...)

object

Object of class Seurat or liger.

columns

optional, name(s) of columns to return. Default is NULL; returns all columns

...

Arguments passed to other methods

library(Seurat)
meta_data <- Fetch_Meta(object = pbmc_small)
head(meta_data, 5)

Find_Factor_Cor(object, reduction = NULL)

object

LIGER/Seurat object name.

reduction

reduction name to pull loadings for. Only valid if supplying a Seurat object.

## Not run: 
factor_correlations <- Find_Factor_Cor(object = object)
## End(Not run)

Get_Reference_LIGER(liger_object, meta_data_column, value)

liger_object

LIGER object name.

meta_data_column

meta data column to use for selecting largest dataset.

value

value from column meta_data_column to use for selecting largest dataset.

## Not run: 
# standalone use
ref_dataset <- Get_Reference_LIGER(liger_object = object, meta_data_column = "Treatment",
value = "Ctrl")
# use within `quantileNorm`
object <- quantileNorm(object = object, reference = Get_Reference_LIGER(liger_object = object,
meta_data_column = "Treatment", value = "Ctrl"))
## End(Not run)

Hue_Pal(num_colors)

num_colors

number of colors to return in palette.

cols <- Hue_Pal(num_colors = 8)
PalettePlot(pal= cols)

## S3 method for class 'liger'
Idents(object, ...)
## S3 replacement method for class 'liger'
Idents(object, ...) <- value

object

LIGER object name.

...

Arguments passed to other methods

value

name of column in cellMeta slot to set as new default cluster/ident

## Not run: 
# Extract idents
object_idents <- Idents(object = liger_object)
## End(Not run)
## Not run: 
# Set idents
Idents(object = liger_object) <- "new_annotation"
## End(Not run)

Iterate_Barcode_Rank_Plot(
 dir_path_h5,
 multi_directory = TRUE,
 h5_filename = "raw_feature_bc_matrix.h5",
 cellranger_multi = FALSE,
 parallel = FALSE,
 num_cores = NULL,
 file_path = NULL,
 file_name = NULL,
 pt.size = 6,
 raster_dpi = c(1024, 1024),
 plateau = NULL,
 ...
)

dir_path_h5

path to parent directory (if multi_directory = TRUE) or directory containing all h5 files (if multi_directory = FALSE).

multi_directory

logical, whether or not all h5 files are in their own subdirectories or in a single directory (default is TRUE; each in own subdirectory (e.g. output from Cell Ranger)).

h5_filename

Either the file name of h5 file (if multi_directory = TRUE) or the shared suffix (if multi_directory = FALSE)

cellranger_multi

logical, whether the outputs to be read are from Cell Ranger multi as opposed to Cell Ranger count (default is FALSE). Only valid if multi_directory = FALSE.

parallel

logical, should files be read in parallel (default is FALSE).

num_cores

Number of cores to use in parallel if parallel = TRUE.

file_path

file path to use for saving PDF output.

file_name

Name of PDF output file.

pt.size

point size for plotting, default is 6.

raster_dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(1024, 1024).

plateau

numerical values at which to add vertical line designating estimated empty droplet plateau (default is NULL). Must be vector equal in length to number of samples.

...

Additional parameters passed to Read10X_h5_Multi_Directory or Read10X_h5_GEO.

## Not run: 
Iterate_Barcode_Rank_Plot(dir_path_h5 = "H5_PATH/", multi_directory = TRUE,
h5_filename = "raw_feature_bc_matrix", parallel = TRUE, num_cores = 12, file_path = "OUTPUT_PATH",
file_name = "Barcode_Rank_Plots")
## End(Not run)

Iterate_Cluster_Highlight_Plot(
 seurat_object,
 highlight_color = "dodgerblue",
 background_color = "lightgray",
 pt.size = NULL,
 reduction = NULL,
 file_path = NULL,
 file_name = NULL,
 file_type = NULL,
 single_pdf = FALSE,
 output_width = NULL,
 output_height = NULL,
 dpi = 600,
 raster = NULL,
 ...
)

seurat_object

Seurat object name.

highlight_color

Color to highlight cells (default "navy"). Can provide either single color to use for all clusters/plots or a vector of colors equal to the number of clusters to use (in order) for the clusters/plots.

background_color

non-highlighted cell colors.

pt.size

point size for both highlighted cluster and background.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

name suffix to append after sample name.

file_type

File type to save output as. Must be one of following: ".pdf", ".png", ".tiff", ".jpeg", or ".svg".

single_pdf

saves all plots to single PDF file (default = FALSE). 'file_type“ must be .pdf.

output_width

the width (in inches) for output page size. Default is NULL.

output_height

the height (in inches) for output page size. Default is NULL.

dpi

dpi for image saving.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

...

Extra parameters passed toDimPlot .

## Not run: 
Iterate_Cluster_Highlight_Plot(seurat_object = object, highlight_color = "navy",
background_color = "lightgray", file_path = "path/", file_name = "name", file_type = ".pdf",
single_pdf = TRUE)
## End(Not run)

Iterate_DimPlot_bySample(
 seurat_object,
 sample_column = "orig.ident",
 file_path = NULL,
 file_name = NULL,
 file_type = NULL,
 single_pdf = FALSE,
 output_width = NULL,
 output_height = NULL,
 dpi = 600,
 color = "black",
 no_legend = TRUE,
 title_prefix = NULL,
 reduction = NULL,
 dims = c(1, 2),
 pt.size = NULL,
 raster = NULL,
 ...
)

seurat_object

Seurat object name.

sample_column

name of meta.data column containing sample names/ids (default is "orig.ident").

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

name suffix to append after sample name.

file_type

File type to save output as. Must be one of following: ".pdf", ".png", ".tiff", ".jpeg", or ".svg".

single_pdf

saves all plots to single PDF file (default = FALSE). 'file_type“ must be .pdf

output_width

the width (in inches) for output page size. Default is NULL.

output_height

the height (in inches) for output page size. Default is NULL.

dpi

dpi for image saving.

color

color scheme to use.

no_legend

logical, whether or not to include plot legend, default is TRUE.

title_prefix

Value that should be used for plot title prefix if no_legend = TRUE. If NULL the value of meta_data_column will be used. Default is NULL.

reduction

Dimensionality Reduction to use (default is object default).

dims

Dimensions to plot.

pt.size

Adjust point size for plotting.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

...

Extra parameters passed to DimPlot .

## Not run: 
Iterate_DimPlot_bySample(seurat_object = object, file_path = "plots/", file_name = "tsne",
file_type = ".jpg", dpi = 600, color = "black")
## End(Not run)

Iterate_FeaturePlot_scCustom(
 seurat_object,
 features,
 colors_use = viridis_plasma_dark_high,
 na_color = "lightgray",
 na_cutoff = 1e-09,
 split.by = NULL,
 order = TRUE,
 return_plots = FALSE,
 file_path = NULL,
 file_name = NULL,
 file_type = NULL,
 single_pdf = FALSE,
 output_width = NULL,
 output_height = NULL,
 features_per_page = 1,
 num_columns = NULL,
 landscape = TRUE,
 dpi = 600,
 pt.size = NULL,
 reduction = NULL,
 raster = NULL,
 alpha_exp = NULL,
 alpha_na_exp = NULL,
 ...
)

seurat_object

Seurat object name.

features

vector of features to plot. If a named vector is provided then the names for each gene will be incorporated into plot title if single_pdf = TRUE or into file name if FALSE.

colors_use

color scheme to use.

na_color

color for non-expressed cells.

na_cutoff

Value to use as minimum expression cutoff. To set no cutoff set to NA.

split.by

Variable in ⁠@meta.data⁠ to split the plot by.

order

whether to move positive cells to the top (default = TRUE).

return_plots

logical. Whether to return plots to list instead of saving them to file(s). Default is FALSE.

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

name suffix and file extension.

file_type

File type to save output as. Must be one of following: ".pdf", ".png", ".tiff", ".jpeg", or ".svg".

single_pdf

saves all plots to single PDF file (default = FALSE).

output_width

the width (in inches) for output page size. Default is NULL.

output_height

the height (in inches) for output page size. Default is NULL.

features_per_page

numeric, number of features to plot on single page if single_pdf = TRUE. Default is 1.

num_columns

Number of columns in plot layout (only applicable if single_pdf = TRUE AND features_per_page > 1).

landscape

logical, when plotting multiple features per page in single PDF whether to use landscape or portrait page dimensions (default is TRUE).

dpi

dpi for image saving.

pt.size

Adjust point size for plotting.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

alpha_exp

new alpha level to apply to expressing cell color palette (colors_use). Must be value between 0-1.

alpha_na_exp

new alpha level to apply to non-expressing cell color palette (na_color). Must be value between 0-1.

...

Extra parameters passed to FeaturePlot .

## Not run: 
Iterate_FeaturePlot_scCustom(seurat_object = object, features = DEG_list,
colors_use = viridis_plasma_dark_high, na_color = "lightgray", file_path = "plots/",
file_name = "tsne", file_type = ".jpg", dpi = 600)
## End(Not run)

Iterate_Meta_Highlight_Plot(
 seurat_object,
 meta_data_column,
 new_meta_order = NULL,
 meta_data_sort = TRUE,
 highlight_color = "navy",
 background_color = "lightgray",
 pt.size = NULL,
 no_legend = FALSE,
 title_prefix = NULL,
 reduction = NULL,
 file_path = NULL,
 file_name = NULL,
 file_type = NULL,
 single_pdf = FALSE,
 output_width = NULL,
 output_height = NULL,
 dpi = 600,
 raster = NULL,
 ...
)

seurat_object

Seurat object name.

meta_data_column

Name of the column in seurat_object@meta.data slot to pull value from for highlighting.

new_meta_order

The order in which to plot each level within meta_data_column if single_PDF is TRUE.

meta_data_sort

logical. Whether or not to sort and relevel the levels in meta_data_column if single_PDF is TRUE. Default is TRUE.

highlight_color

Color to highlight cells (default "navy"). Can provide either single color to use for all clusters/plots or a vector of colors equal to the number of clusters to use (in order) for the clusters/plots.

background_color

non-highlighted cell colors.

pt.size

point size for both highlighted cluster and background.

no_legend

logical, whether or not to remove plot legend and move to plot title. Default is FALSE.

title_prefix

Value that should be used for plot title prefix if no_legend = TRUE. If NULL the value of meta_data_column will be used. Default is NULL.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

name suffix to append after sample name.

file_type

File type to save output as. Must be one of following: ".pdf", ".png", ".tiff", ".jpeg", or ".svg".

single_pdf

saves all plots to single PDF file (default = FALSE). 'file_type“ must be .pdf.

output_width

the width (in inches) for output page size. Default is NULL.

output_height

the height (in inches) for output page size. Default is NULL.

dpi

dpi for image saving.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

...

Extra parameters passed toDimPlot .

## Not run: 
Iterate_Meta_Highlight_Plot(seurat_object = object, meta_data_column = "sample_id",
highlight_color = "navy", background_color = "lightgray", file_path = "path/",
file_name = "name", file_type = ".pdf", single_pdf = TRUE)
## End(Not run)

Iterate_PC_Loading_Plots(
 seurat_object,
 dims_plot = NULL,
 file_path = NULL,
 name_prefix = NULL,
 file_name = "PC_Loading_Plots",
 return_plots = FALSE
)

seurat_object

Seurat object name.

dims_plot

number of PCs to plot (integer). Default is all dims present in PCA.

file_path

directory file path to save file.

name_prefix

prefix for file name (optional).

file_name

suffix for file name. Default is "PC_Loading_Plots".

return_plots

Whether to return the plot list (Default is FALSE). Must assign to environment to save plot list.

## Not run: 
Iterate_PC_Loading_Plots(seurat_object = seurat, dims_plot = 25, file_path = "plots/")
## End(Not run)

Iterate_Plot_Density_Custom(
 seurat_object,
 gene_list,
 viridis_palette = "magma",
 custom_palette = NULL,
 pt.size = 1,
 file_path = NULL,
 file_name = NULL,
 file_type = NULL,
 single_pdf = FALSE,
 output_width = NULL,
 output_height = NULL,
 dpi = 600,
 reduction = NULL,
 combine = TRUE,
 joint = FALSE,
 ...
)

seurat_object

Seurat object name.

gene_list

vector of genes to plot. If a named vector is provided then the names for each gene will be incorporated into plot title if single_pdf = TRUE or into file name if FALSE.

viridis_palette

color scheme to use.

custom_palette

color for non-expressed cells.

pt.size

Adjust point size for plotting.

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

name suffix and file extension.

file_type

File type to save output as. Must be one of following: ".pdf", ".png", ".tiff", ".jpeg", or ".svg".

single_pdf

saves all plots to single PDF file (default = FALSE). 'file_type“ must be .pdf.

output_width

the width (in inches) for output page size. Default is NULL.

output_height

the height (in inches) for output page size. Default is NULL.

dpi

dpi for image saving.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default)

combine

Create a single plot? If FALSE, a list with ggplot objects is returned.

joint

NULL. This function only supports joint = FALSE. Leave as NULL to generate plots. To iterate joint plots see function: Iterate_Plot_Density_Joint.

...

Extra parameters passed to plot_density .

## Not run: 
Iterate_Plot_Density_Custom(seurat_object = object, gene_list = DEG_list, viridis_palette = "magma",
file_path = "plots/", file_name = "_density_plots", file_type = ".jpg", dpi = 600)
## End(Not run)

Iterate_Plot_Density_Joint(
 seurat_object,
 gene_list,
 viridis_palette = "magma",
 custom_palette = NULL,
 pt.size = 1,
 file_path = NULL,
 file_name = NULL,
 file_type = NULL,
 single_pdf = FALSE,
 output_width = NULL,
 output_height = NULL,
 dpi = 600,
 reduction = NULL,
 combine = TRUE,
 joint = NULL,
 ...
)

seurat_object

Seurat object name.

gene_list

a list of vectors of genes to plot jointly. Each entry in the list will be plotted for the joint density. All entries in list must be greater than 2 features. If a named list is provided then the names for each list entry will be incorporated into plot title if single_pdf = TRUE or into file name if FALSE.

viridis_palette

color scheme to use.

custom_palette

color for non-expressed cells.

pt.size

Adjust point size for plotting.

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

name suffix and file extension.

file_type

File type to save output as. Must be one of following: ".pdf", ".png", ".tiff", ".jpeg", or ".svg".

single_pdf

saves all plots to single PDF file (default = FALSE). 'file_type“ must be .pdf.

output_width

the width (in inches) for output page size. Default is NULL.

output_height

the height (in inches) for output page size. Default is NULL.

dpi

dpi for image saving.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default)

combine

Create a single plot? If FALSE, a list with ggplot objects is returned.

joint

NULL. This function only supports joint = FALSE. Leave as NULL to generate plots. To iterate joint plots see function: Iterate_Plot_Density_Joint.

...

Extra parameters passed to plot_density .

## Not run: 
Iterate_Plot_Density_Joint(seurat_object = object, gene_list = DEG_list, viridis_palette = "magma",
file_path = "plots/", file_name = "joint_plots", file_type = ".jpg", dpi = 600)
## End(Not run)

Iterate_VlnPlot_scCustom(
 seurat_object,
 features,
 colors_use = NULL,
 pt.size = NULL,
 group.by = NULL,
 split.by = NULL,
 file_path = NULL,
 file_name = NULL,
 file_type = NULL,
 single_pdf = FALSE,
 output_width = NULL,
 output_height = NULL,
 raster = NULL,
 dpi = 600,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

features

vector of features to plot.

colors_use

color palette to use for plotting. By default if number of levels plotted is less than or equal to 36 it will use "polychrome" and if greater than 36 will use "varibow" with shuffle = TRUE both from DiscretePalette_scCustomize.

pt.size

point size for plotting.

group.by

Name of one or more metadata columns to group (color) plot by (for example, orig.ident); default is the current active.ident of the object.

split.by

Feature to split plots by (i.e. "orig.ident").

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

name suffix and file extension.

file_type

File type to save output as. Must be one of following: ".pdf", ".png", ".tiff", ".jpeg", or ".svg".

single_pdf

saves all plots to single PDF file (default = FALSE). 'file_type“ must be .pdf.

output_width

the width (in inches) for output page size. Default is NULL.

output_height

the height (in inches) for output page size. Default is NULL.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 total points plotted (# Cells x # of features).

dpi

dpi for image saving.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to VlnPlot .

## Not run: 
Iterate_VlnPlot_scCustom(seurat_object = object, features = DEG_list, colors = color_list,
file_path = "plots/", file_name = "_vln", file_type = ".jpg", dpi = 600)
## End(Not run)

JCO_Four()

cols <- JCO_Four()
PalettePlot(pal= cols)

MAD_Stats(
 seurat_object,
 group_by_var = deprecated(),
 group.by = "orig.ident",
 default_var = TRUE,
 mad_var = NULL,
 mad_num = 2
)

seurat_object

Seurat object name.

group_by_var

soft-deprecated. See group.by.

group.by

meta data column to classify samples (default = "orig.ident").

default_var

logical. Whether to include the default meta.data variables of: "nCount_RNA", "nFeature_RNA", "percent_mito", "percent_ribo", "percent_mito_ribo", and "log10GenesPerUMI" in addition to variables supplied to mad_var.

mad_var

Column(s) in ⁠@meta.data⁠ to calculate medians for in addition to defaults. Must be of class() integer or numeric.

mad_num

integer value to multiply the MAD in returned data.frame (default is 2). Often helpful when calculating a outlier range to base of of median + (X*MAD).

## Not run: 
mad_stats <- MAD_Stats(seurat_object = obj, group.by = "orig.ident")
## End(Not run)

Map_New_Meta(seurat_object, from, new_col = NULL, ...)

seurat_object

name of Seurat object

from

current column in meta.data to map from

new_col

name of new column in meta.data to add new mapped variable. If NULL (default) will return the variable. If name provided will return Seurat object with new variable added.

...

Mapping criteria, argument names are original existing categories in the from calumn and values are new categories in the new variable.

## Not run: 
seurat_object <- Map_New_Meta(seurat_object, from = "orig.ident", new_col = "Treatment",
"1" = "Ctrl", "2" = "Treated", "3" = "Treated", "4" = "Ctrl")
## End(Not run)

Median_Stats(
 seurat_object,
 group_by_var = deprecated(),
 group.by = "orig.ident",
 default_var = TRUE,
 median_var = NULL
)

seurat_object

Seurat object name.

group_by_var

soft-deprecated. See group.by.

group.by

meta data column to classify samples (default = "orig.ident").

default_var

logical. Whether to include the default meta.data variables of: "nCount_RNA", "nFeature_RNA", "percent_mito", "percent_ribo", "percent_mito_ribo", and "log10GenesPerUMI" in addition to variables supplied to median_var.

median_var

Column(s) in ⁠@meta.data⁠ to calculate medians for in addition to defaults. Must be of class() integer or numeric.

## Not run: 
med_stats <- Median_Stats(seurat_object - obj, group.by = "orig.ident")
## End(Not run)

Merge_Seurat_List(
 list_seurat,
 add.cell.ids = NULL,
 merge.data = TRUE,
 project = "SeuratProject"
)

list_seurat

list composed of multiple Seurat Objects.

add.cell.ids

A character vector of equal length to the number of objects in list_seurat. Appends the corresponding values to the start of each objects' cell names. See merge .

merge.data

Merge the data slots instead of just merging the counts (which requires renormalization). This is recommended if the same normalization approach was applied to all objects. See merge .

project

Project name for the Seurat object. See merge .

## Not run: 
object_list <- list(obj1, obj2, obj3, ...)
merged_object <- Merge_Seurat_List(list_seurat = object_list)
## End(Not run)

Merge_Sparse_Data_All(
 matrix_list,
 add_cell_ids = NULL,
 prefix = TRUE,
 cell_id_delimiter = "_"
)

matrix_list

list of matrices to merge.

add_cell_ids

a vector of sample ids to add as prefix to cell barcode during merge.

prefix

logical. Whether add_cell_ids should be added as prefix to current cell barcodes/names or as suffix to current cell barcodes/names. Default is TRUE, add as prefix.

cell_id_delimiter

The delimiter to use when adding cell id prefix/suffix. Default is "_".

## Not run: 
data_list <- Read10X_GEO(...)
merged <- Merge_Sparse_Data_All(matrix_list = data_list, add_cell_ids = names(data_list),
prefix = TRUE, cell_id_delimiter = "_")
## End(Not run)

Merge_Sparse_Multimodal_All(
 matrix_list,
 add_cell_ids = NULL,
 prefix = TRUE,
 cell_id_delimiter = "_"
)

matrix_list

list of matrices to merge.

add_cell_ids

a vector of sample ids to add as prefix to cell barcode during merge.

prefix

logical. Whether add_cell_ids should be added as prefix to current cell barcodes/names or as suffix to current cell barcodes/names. Default is TRUE, add as prefix.

cell_id_delimiter

The delimiter to use when adding cell id prefix/suffix. Default is "_".

## Not run: 
data_list <- Read10X_GEO(...)
merged_list <- Merge_Sparse_Multimodal_All(matrix_list = data_list, add_cell_ids = names(data_list),
prefix = TRUE, cell_id_delimiter = "_")
## End(Not run)

Meta_Highlight_Plot(
 seurat_object,
 meta_data_column,
 meta_data_highlight,
 highlight_color = NULL,
 background_color = "lightgray",
 pt.size = NULL,
 aspect_ratio = NULL,
 figure_plot = FALSE,
 raster = NULL,
 raster.dpi = c(512, 512),
 label = FALSE,
 split.by = NULL,
 split_seurat = FALSE,
 reduction = NULL,
 ggplot_default_colors = FALSE,
 ...
)

seurat_object

Seurat object name.

meta_data_column

Name of the column in seurat_object@meta.data slot to pull value from for highlighting.

meta_data_highlight

Name of variable(s) within meta_data_name to highlight in the plot.

highlight_color

Color to highlight cells (default "navy").

background_color

non-highlighted cell colors.

pt.size

point size for both highlighted cluster and background.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

figure_plot

logical. Whether to remove the axes and plot with legend on left of plot denoting axes labels. (Default is FALSE). Requires split_seurat = TRUE.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

label

Whether to label the highlighted meta data variable(s). Default is FALSE.

split.by

Variable in ⁠@meta.data⁠ to split the plot by.

split_seurat

logical. Whether or not to display split plots like Seurat (shared y axis) or as individual plots in layout. Default is FALSE.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

...

Extra parameters passed toDimPlot .

library(Seurat)
pbmc_small$sample_id <- sample(c("sample1", "sample2"), size = ncol(pbmc_small), replace = TRUE)
Meta_Highlight_Plot(seurat_object = pbmc_small, meta_data_column = "sample_id",
meta_data_highlight = "sample1", highlight_color = "gold", background_color = "lightgray",
pt.size = 2)

Meta_Numeric(data)

data

a data.frame contain meta.data.

## Not run: 
numeric_meta_columns <- Meta_Numeric(data = meta_data)
## End(Not run)

Meta_Present(
 object,
 meta_col_names,
 print_msg = TRUE,
 omit_warn = TRUE,
 return_none = FALSE
)

object

Seurat or Liger object name.

meta_col_names

vector of column names to check.

print_msg

logical. Whether message should be printed if all features are found. Default is TRUE.

omit_warn

logical. Whether to print message about features that are not found in current object. Default is TRUE.

return_none

logical. Whether list of found vs. bad features should still be returned if no meta_col_names are found. Default is FALSE.

## Not run: 
meta_variables <- Meta_Present(object = obj_name, meta_col_names = "percent_mito", print_msg = TRUE)
## End(Not run)

Meta_Remove_Seurat(
 meta_data,
 seurat_object,
 barcodes_to_rownames = FALSE,
 barcodes_colname = "barcodes"
)

meta_data

data.frame containing meta data.

seurat_object

object name.

barcodes_to_rownames

logical, are barcodes present as column and should they be moved to rownames (to be compatible with Seurat::AddMetaData). Default is FALSE.

barcodes_colname

name of barcodes column in meta_data. Required if barcodes_to_rownames = TRUE.

## Not run: 
new_meta <- Meta_Remove_Seurat(meta_data = meta_data_df, seurat_object = object)
object <- AddMetaData(object = object, metadata = new_meta)
## End(Not run)

Move_Legend(position = "right", ...)

position

valid position to move legend. Default is "right".

...

extra arguments passed to ggplot2::theme().

# Generate a plot and customize theme
library(ggplot2)
df <- data.frame(x = rnorm(n = 100, mean = 20, sd = 2), y = rbinom(n = 100, size = 100, prob = 0.2))
p <- ggplot(data = df, mapping = aes(x = x, y = y)) + geom_point(mapping = aes(color = 'red'))
p + Move_Legend("left")

NavyAndOrange(flip_order = FALSE)

flip_order

logical, whether to flip the order of colors.

cols <- NavyAndOrange()
PalettePlot(pal= cols)

PC_Plotting(seurat_object, dim_number)

seurat_object

Seurat Object.

dim_number

A single dim to plot (integer).

library(Seurat)
PC_Plotting(seurat_object = pbmc_small, dim_number = 1)

PalettePlot(pal = NULL, label_color_num = NULL)

pal

a vector of colors (either named colors of hex codes).

label_color_num

logical, whether or not to numerically label the colors in output plot. Default is TRUE is number of colors in pal is less than 75 and FALSE is greater than 75.

pal <- DiscretePalette_scCustomize(num_colors = 36, palette = "varibow")
PalettePlot(pal = pal)

Percent_Expressing(
 seurat_object,
 features,
 threshold = 0,
 group_by = deprecated(),
 group.by = NULL,
 split_by = deprecated(),
 split.by = NULL,
 entire_object = FALSE,
 layer = "data",
 assay = NULL
)

seurat_object

Seurat object name.

features

Feature(s) to plot.

threshold

Expression threshold to use for calculation of percent expressing (default is 0).

group_by

soft-deprecated. See group.by.

group.by

Factor to group the cells by.

split_by

soft-deprecated. See split.by.

split.by

Factor to split the groups by.

entire_object

logical (default = FALSE). Whether to calculate percent of expressing cells across the entire object as opposed to by cluster or by group.by variable.

layer

Which layer to pull expression data from? Default is "data".

assay

Assay to pull feature data from. Default is active assay.

## Not run: 
percent_stats <- Percent_Expressing(seurat_object = object, features = "Cx3cr1", threshold = 0)
## End(Not run)

Plot_Cells_per_Sample(
 seurat_object,
 sample_col = "orig.ident",
 group_by = deprecated(),
 group.by = NULL,
 colors_use = NULL,
 dot_size = 1,
 plot_title = "Cells/Nuclei per Sample",
 y_axis_label = "Number of Cells",
 x_axis_label = NULL,
 legend_title = NULL,
 x_lab_rotate = TRUE,
 color_seed = 123
)

seurat_object

Seurat object name.

sample_col

Specify which column in meta.data specifies sample ID (i.e. orig.ident).

group_by

soft-deprecated. See group.by.

group.by

Column in meta.data slot to group results by (i.e. "Treatment").

colors_use

List of colors or color palette to use.

dot_size

size of the dots plotted if group.by is not NULL. Default is 1.

plot_title

Plot title.

y_axis_label

Label for y axis.

x_axis_label

Label for x axis.

legend_title

Label for plot legend.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

## Not run: 
Plot_Cells_per_Sample(seurat_object = obj, sample_col = "orig.ident", group.by = "Treatment")
## End(Not run)

Plot_Density_Custom(
 seurat_object,
 features,
 joint = FALSE,
 viridis_palette = "magma",
 custom_palette = NULL,
 pt.size = 1,
 aspect_ratio = NULL,
 reduction = NULL,
 combine = TRUE,
 ...
)

seurat_object

Seurat object name.

features

Features to plot.

joint

logical. Whether to return joint density plot. Default is FALSE.

viridis_palette

default viridis palette to use (must be one of: "viridis", "magma", "cividis", "inferno", "plasma"). Default is "magma".

custom_palette

non-default color palette to be used in place of default viridis options.

pt.size

Adjust point size for plotting.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

combine

Create a single plot? If FALSE, a list with ggplot objects is returned.

...

Extra parameters passed to plot_density .

## Not run: 
library(Seurat)
Plot_Density_Custom(seurat_object = pbmc_small, features = "CD3E")
## End(Not run)

Plot_Density_Joint_Only(
 seurat_object,
 features,
 viridis_palette = "magma",
 custom_palette = NULL,
 pt.size = 1,
 aspect_ratio = NULL,
 reduction = NULL,
 ...
)

seurat_object

Seurat object name.

features

Features to plot.

viridis_palette

default viridis palette to use (must be one of: "viridis", "magma", "cividis", "inferno", "plasma"). Default is "magma".

custom_palette

non-default color palette to be used in place of default viridis options.

pt.size

Adjust point size for plotting.

aspect_ratio

Control the aspect ratio (y:x axes ratio length). Must be numeric value; Default is NULL.

reduction

Dimensionality Reduction to use (if NULL then defaults to Object default).

...

Extra parameters passed to plot_density .

## Not run: 
library(Seurat)
Plot_Density_Joint_Only(seurat_object = pbmc_small, features = c("CD8A", "CD3E"))
## End(Not run)

Plot_Median_Genes(
 seurat_object,
 sample_col = "orig.ident",
 group_by = deprecated(),
 group.by = NULL,
 colors_use = NULL,
 dot_size = 1,
 plot_title = "Median Genes/Cell per Sample",
 y_axis_label = "Median Genes",
 x_axis_label = NULL,
 legend_title = NULL,
 x_lab_rotate = TRUE,
 color_seed = 123
)

seurat_object

Seurat object name.

sample_col

Specify which column in meta.data specifies sample ID (i.e. orig.ident).

group_by

soft-deprecated. See group.by.

group.by

Column in meta.data slot to group results by (i.e. "Treatment").

colors_use

List of colors or color palette to use. Only applicable if group.by is not NULL.

dot_size

size of the dots plotted if group.by is not NULL. Default is 1.

plot_title

Plot title.

y_axis_label

Label for y axis.

x_axis_label

Label for x axis.

legend_title

Label for plot legend.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

library(Seurat)
# Create example groups
pbmc_small$sample_id <- sample(c("sample1", "sample2"), size = ncol(pbmc_small), replace = TRUE)
# Plot
Plot_Median_Genes(seurat_object = pbmc_small, sample_col = "orig.ident", group.by = "sample_id")

Plot_Median_Mito(
 seurat_object,
 sample_col = "orig.ident",
 group_by = deprecated(),
 group.by = NULL,
 colors_use = NULL,
 dot_size = 1,
 plot_title = "Median % Mito per Sample",
 y_axis_label = "Percent Mitochondrial Reads",
 x_axis_label = NULL,
 legend_title = NULL,
 x_lab_rotate = TRUE,
 color_seed = 123
)

seurat_object

Seurat object name.

sample_col

Specify which column in meta.data specifies sample ID (i.e. orig.ident).

group_by

soft-deprecated. See group.by.

group.by

Column in meta.data slot to group results by (i.e. "Treatment").

colors_use

List of colors or color palette to use. Only applicable if group.by is not NULL.

dot_size

size of the dots plotted if group.by is not NULL. Default is 1.

plot_title

Plot title.

y_axis_label

Label for y axis.

x_axis_label

Label for x axis.

legend_title

Label for plot legend.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

## Not run: 
# Add mito
obj <- Add_Mito_Ribo_Seurat(seurat_object = obj, species = "human")
# Plot
Plot_Median_Mito(seurat_object = obj, sample_col = "orig.ident", group.by = "sample_id")
## End(Not run)

Plot_Median_Other(
 seurat_object,
 median_var,
 sample_col = "orig.ident",
 group_by = deprecated(),
 group.by = NULL,
 colors_use = NULL,
 dot_size = 1,
 plot_title = NULL,
 y_axis_label = NULL,
 x_axis_label = NULL,
 legend_title = NULL,
 x_lab_rotate = TRUE,
 color_seed = 123
)

seurat_object

Seurat object name.

median_var

Variable in meta.data slot to calculate and plot median values for.

sample_col

Specify which column in meta.data specifies sample ID (i.e. orig.ident).

group_by

soft-deprecated. See group.by.

group.by

Column in meta.data slot to group results by (i.e. "Treatment").

colors_use

List of colors or color palette to use. Only applicable if group.by is not NULL.

dot_size

size of the dots plotted if group.by is not NULL. Default is 1.

plot_title

Plot title.

y_axis_label

Label for y axis.

x_axis_label

Label for x axis.

legend_title

Label for plot legend.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

## Not run: 
library(Seurat)
cd_features <- list(c('CD79B', 'CD79A', 'CD19', 'CD180', 'CD200', 'CD3D', 'CD2','CD3E',
'CD7','CD8A', 'CD14', 'CD1C', 'CD68', 'CD9', 'CD247'))
pbmc_small <- AddModuleScore(object = pbmc_small, features = cd_features, ctrl = 5,
name = 'CD_Features')
Plot_Median_Other(seurat_object = pbmc_small, median_var = "CD_Features1",
sample_col = "orig.ident", group.by = "Treatment")
## End(Not run)

Plot_Median_UMIs(
 seurat_object,
 sample_col = "orig.ident",
 group_by = deprecated(),
 group.by = NULL,
 colors_use = NULL,
 dot_size = 1,
 plot_title = "Median UMIs/Cell per Sample",
 y_axis_label = "Median UMIs",
 x_axis_label = NULL,
 legend_title = NULL,
 x_lab_rotate = TRUE,
 color_seed = 123
)

seurat_object

Seurat object name.

sample_col

Specify which column in meta.data specifies sample ID (i.e. orig.ident).

group_by

soft-deprecated. See group.by.

group.by

Column in meta.data slot to group results by (i.e. "Treatment").

colors_use

List of colors or color palette to use. Only applicable if group.by is not NULL.

dot_size

size of the dots plotted if group.by is not NULL. Default is 1.

plot_title

Plot title.

y_axis_label

Label for y axis.

x_axis_label

Label for x axis.

legend_title

Label for plot legend.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

library(Seurat)
# Create example groups
pbmc_small$sample_id <- sample(c("sample1", "sample2"), size = ncol(pbmc_small), replace = TRUE)
# Plot
Plot_Median_UMIs(seurat_object = pbmc_small, sample_col = "orig.ident", group.by = "sample_id")

Proportion_Plot(
 seurat_object,
 plot_type = "bar",
 plot_scale = "percent",
 group_by_var = deprecated(),
 group.by = "ident",
 split.by = NULL,
 num_columns = NULL,
 x_lab_rotate = TRUE,
 colors_use = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123
)

seurat_object

Seurat object name.

plot_type

whether to plot a pie chart or bar chart; value must be one of "bar" or "pie". Default is "bar"

plot_scale

whether to plot bar chart as total cell counts or percents, value must be one of "percent" or "count". Default is "percent".

group_by_var

soft-deprecated. See group.by.

group.by

meta data column to classify samples (default = "ident" and will use active.ident).

split.by

meta data variable to use to split plots. Default is NULL which will plot across entire object.

num_columns

number of columns in plot. Only valid if split.by is not NULL.

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is FALSE). Only valid if plot_type = "bar".

colors_use

color palette to use for plotting.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

#' library(Seurat)
Proportion_Plot(seurat_object = pbmc_small)

Proportion_Plot_per_Sample(
 seurat_object,
 cluster = "ident",
 split.by,
 sample_col,
 pt.size = 1.5,
 x_lab_rotate = TRUE,
 colors_use = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123
)

seurat_object

Seurat object name.

cluster

name of meta.data column containing cluster values. Default is ident which defaults to current active.ident.

split.by

name of meta.data column containing sample group/condition variable.

sample_col

name of meta.data column that contains sample ID information.

pt.size

the size of points in plot (default is 1.5).

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is FALSE). Only valid if plot_type = "bar".

colors_use

color palette to use for plotting.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

## Not run: 
Proportion_Plot_per_Sample(seurat_object = obj, split.by = "Diagnosis",
sample_col = "orig.ident")
## End(Not run)

Pull_Cluster_Annotation(
 annotation = NULL,
 cluster_name_col = "cluster",
 cell_type_col = "cell_type"
)

annotation

name of the data.frame/tibble or path to CSV file containing cluster annotation.

cluster_name_col

name of column containing cluster names/numbers (default is "cluster").

cell_type_col

name of column contain the cell type annotation (default is "cell_type").

## Not run: 
# If pulling from a data.frame/tibble
cluster_annotation <- Pull_Cluster_Annotation(annotation = annotation_df,
cluster_name_col = "cluster", cell_type_col = "cell_type")
# If pulling from csv file
cluster_annotation <- Pull_Cluster_Annotation(annotation = "file_path/file_name.csv",
cluster_name_col = "cluster", cell_type_col = "cell_type")
## End(Not run)

Pull_Directory_List(base_path)

base_path

path to the parent directory which contains all of the subdirectories of interest.

## Not run: 
data_dir <- 'path/to/data/directory'
library_list <- Pull_Directory_List(base_path = data_dir)
## End(Not run)

QC_Histogram(
 seurat_object,
 features,
 low_cutoff = NULL,
 high_cutoff = NULL,
 cutoff_line_width = NULL,
 split.by = NULL,
 bins = 250,
 colors_use = "dodgerblue",
 num_columns = NULL,
 plot_title = NULL,
 assay = NULL,
 print_defaults = FALSE
)

seurat_object

Seurat object name.

features

Feature from meta.data, assay features, or feature name shortcut to plot.

low_cutoff

Plot line a potential low threshold for filtering.

high_cutoff

Plot line a potential high threshold for filtering.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

split.by

Feature to split plots by (i.e. "orig.ident").

bins

number of bins to plot default is 250.

colors_use

color to fill histogram bars, default is "dodgerblue".

num_columns

Number of columns in plot layout.

plot_title

optional, vector to use for plot title. Default is the name of the variable being plotted.

assay

assay to pull features from, default is active assay.

print_defaults

return list of accepted default shortcuts to provide to features instead of full name.

## Not run: 
QC_Histogram(seurat_object = object, features = "nFeature_RNA")
## End(Not run)

QC_Plot_GenevsFeature(
 seurat_object,
 feature1,
 x_axis_label = NULL,
 y_axis_label = "Genes per Cell/Nucleus",
 low_cutoff_gene = NULL,
 high_cutoff_gene = NULL,
 low_cutoff_feature = NULL,
 high_cutoff_feature = NULL,
 cutoff_line_width = NULL,
 colors_use = NULL,
 pt.size = 1,
 group.by = NULL,
 raster = NULL,
 raster.dpi = c(512, 512),
 assay = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 shuffle_seed = 1,
 ...
)

seurat_object

Seurat object name.

feature1

First feature to plot.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

low_cutoff_gene

Plot line a potential low threshold for filtering genes per cell.

high_cutoff_gene

Plot line a potential high threshold for filtering genes per cell.

low_cutoff_feature

Plot line a potential low threshold for filtering feature1 per cell.

high_cutoff_feature

Plot line a potential high threshold for filtering feature1 per cell.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

colors_use

vector of colors to use for plotting by identity.

pt.size

Adjust point size for plotting.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident). Default is ⁠@active.ident⁠.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

assay

Name of assay to use, defaults to the active assay.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

shuffle_seed

Sets the seed if randomly shuffling the order of points (Default is 1).

...

Extra parameters passed to FeatureScatter .

## Not run: 
QC_Plot_GenevsFeature(seurat_object = obj, y_axis_label = "Feature per Cell")
## End(Not run)

QC_Plot_UMIvsFeature(
 seurat_object,
 feature1,
 x_axis_label = NULL,
 y_axis_label = "UMIs per Cell/Nucleus",
 low_cutoff_UMI = NULL,
 high_cutoff_UMI = NULL,
 low_cutoff_feature = NULL,
 high_cutoff_feature = NULL,
 cutoff_line_width = NULL,
 colors_use = NULL,
 pt.size = 1,
 group.by = NULL,
 raster = NULL,
 raster.dpi = c(512, 512),
 assay = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 shuffle_seed = 1,
 ...
)

seurat_object

Seurat object name.

feature1

First feature to plot.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

low_cutoff_UMI

Plot line a potential low threshold for filtering UMI per cell.

high_cutoff_UMI

Plot line a potential high threshold for filtering UMI per cell.

low_cutoff_feature

Plot line a potential low threshold for filtering feature1 per cell.

high_cutoff_feature

Plot line a potential high threshold for filtering feature1 per cell.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

colors_use

vector of colors to use for plotting by identity.

pt.size

Adjust point size for plotting.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident). Default is ⁠@active.ident⁠.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

assay

Name of assay to use, defaults to the active assay.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

shuffle_seed

Sets the seed if randomly shuffling the order of points (Default is 1).

...

Extra parameters passed to FeatureScatter .

## Not run: 
QC_Plot_UMIvsFeature(seurat_object = obj, y_axis_label = "Feature per Cell")
## End(Not run)

QC_Plot_UMIvsGene(
 seurat_object,
 x_axis_label = "UMIs per Cell/Nucleus",
 y_axis_label = "Genes per Cell/Nucleus",
 low_cutoff_gene = -Inf,
 high_cutoff_gene = Inf,
 low_cutoff_UMI = -Inf,
 high_cutoff_UMI = Inf,
 cutoff_line_width = NULL,
 colors_use = NULL,
 meta_gradient_name = NULL,
 meta_gradient_color = viridis_plasma_dark_high,
 meta_gradient_na_color = "lightgray",
 meta_gradient_low_cutoff = NULL,
 cells = NULL,
 combination = FALSE,
 ident_legend = TRUE,
 pt.size = 1,
 group.by = NULL,
 raster = NULL,
 raster.dpi = c(512, 512),
 assay = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 shuffle_seed = 1,
 ...
)

seurat_object

Seurat object name.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

low_cutoff_gene

Plot line a potential low threshold for filtering genes per cell.

high_cutoff_gene

Plot line a potential high threshold for filtering genes per cell.

low_cutoff_UMI

Plot line a potential low threshold for filtering UMIs per cell.

high_cutoff_UMI

Plot line a potential high threshold for filtering UMIs per cell.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

colors_use

vector of colors to use for plotting by identity.

meta_gradient_name

Name of continuous meta data variable to color points in plot by. (MUST be continuous variable i.e. "percent_mito").

meta_gradient_color

The gradient color palette to use for plotting of meta variable (default is viridis "Plasma" palette with dark colors high).

meta_gradient_na_color

Color to use for plotting values when a meta_gradient_low_cutoff is set (default is "lightgray").

meta_gradient_low_cutoff

Value to use as threshold for plotting. meta_gradient_name values below this value will be plotted using meta_gradient_na_color.

cells

Cells to include on the scatter plot (default is all cells).

combination

logical (default FALSE). Whether or not to return a plot layout with both the plot colored by identity and the meta data gradient plot.

ident_legend

logical, whether to plot the legend containing identities (left plot) when combination = TRUE. Default is TRUE.

pt.size

Passes size of points to both FeatureScatter and geom_point.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident). Default is ⁠@active.ident⁠.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

assay

Name of assay to use, defaults to the active assay.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

Random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

shuffle_seed

Sets the seed if randomly shuffling the order of points (Default is 1).

...

Extra parameters passed to FeatureScatter .

library(Seurat)
QC_Plot_UMIvsGene(seurat_object = pbmc_small, x_axis_label = "UMIs per Cell/Nucleus",
y_axis_label = "Genes per Cell/Nucleus")

QC_Plots_Combined_Vln(
 seurat_object,
 group.by = NULL,
 feature_cutoffs = NULL,
 UMI_cutoffs = NULL,
 mito_cutoffs = NULL,
 mito_name = "percent_mito",
 cutoff_line_width = NULL,
 pt.size = NULL,
 plot_median = FALSE,
 median_size = 15,
 plot_boxplot = FALSE,
 colors_use = NULL,
 x_lab_rotate = TRUE,
 y_axis_log = FALSE,
 raster = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident); default is the current active.ident of the object.

feature_cutoffs

Numeric vector of length 1 or 2 to plot lines for potential low/high threshold for filtering.

UMI_cutoffs

Numeric vector of length 1 or 2 to plot lines for potential low/high threshold for filtering.

mito_cutoffs

Numeric vector of length 1 or 2 to plot lines for potential low/high threshold for filtering.

mito_name

The column name containing percent mitochondrial counts information. Default value is "percent_mito" which is default value created when using Add_Mito_Ribo().

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

pt.size

Point size for plotting

plot_median

logical, whether to plot median for each ident on the plot (Default is FALSE).

median_size

Shape size for the median is plotted.

plot_boxplot

logical, whether to plot boxplot inside of violin (Default is FALSE).

colors_use

vector of colors to use for plot.

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is TRUE).

y_axis_log

logical. Whether to change y axis to log10 scale (Default is FALSE).

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 total points plotted (# Cells x # of features).

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to VlnPlot .

## Not run: 
QC_Plots_Combined_Vln(seurat_object = object)
## End(Not run)

QC_Plots_Complexity(
 seurat_object,
 feature = "log10GenesPerUMI",
 group.by = NULL,
 x_axis_label = NULL,
 y_axis_label = "log10(Genes) / log10(UMIs)",
 plot_title = "Cell Complexity",
 low_cutoff = NULL,
 high_cutoff = NULL,
 cutoff_line_width = NULL,
 pt.size = NULL,
 plot_median = FALSE,
 plot_boxplot = FALSE,
 median_size = 15,
 colors_use = NULL,
 x_lab_rotate = TRUE,
 y_axis_log = FALSE,
 raster = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

feature

Feature from Meta Data to plot.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident); default is the current active.ident of the object.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

plot_title

Plot Title.

low_cutoff

Plot line a potential low threshold for filtering.

high_cutoff

Plot line a potential high threshold for filtering.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

pt.size

Point size for plotting

plot_median

logical, whether to plot median for each ident on the plot (Default is FALSE).

plot_boxplot

logical, whether to plot boxplot inside of violin (Default is FALSE).

median_size

Shape size for the median is plotted.

colors_use

vector of colors to use for plot.

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is TRUE).

y_axis_log

logical. Whether to change y axis to log10 scale (Default is FALSE).

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 total points plotted (# Cells x # of features).

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to VlnPlot .

library(Seurat)
pbmc_small <- Add_Cell_Complexity(pbmc_small)
QC_Plots_Complexity(seurat_object = pbmc_small)

QC_Plots_Feature(
 seurat_object,
 feature,
 group.by = NULL,
 x_axis_label = NULL,
 y_axis_label = NULL,
 plot_title = NULL,
 low_cutoff = NULL,
 high_cutoff = NULL,
 cutoff_line_width = NULL,
 pt.size = NULL,
 plot_median = FALSE,
 median_size = 15,
 plot_boxplot = FALSE,
 colors_use = NULL,
 x_lab_rotate = TRUE,
 y_axis_log = FALSE,
 raster = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

feature

Feature from Meta Data to plot.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident); default is the current active.ident of the object.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

plot_title

Plot Title.

low_cutoff

Plot line a potential low threshold for filtering.

high_cutoff

Plot line a potential high threshold for filtering.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

pt.size

Point size for plotting.

plot_median

logical, whether to plot median for each ident on the plot (Default is FALSE).

median_size

Shape size for the median is plotted.

plot_boxplot

logical, whether to plot boxplot inside of violin (Default is FALSE).

colors_use

vector of colors to use for plot.

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is TRUE).

y_axis_log

logical. Whether to change y axis to log10 scale (Default is FALSE).

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 total points plotted (# Cells x # of features).

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to VlnPlot .

## Not run: 
QC_Plots_Feature(seurat_object = object, feature = "FEATURE_NAME",
y_axis_label = "FEATURE per Cell", plot_title = "FEATURE per Cell", high_cutoff = 10,
low_cutoff = 2)
## End(Not run)

QC_Plots_Genes(
 seurat_object,
 plot_title = "Genes Per Cell/Nucleus",
 group.by = NULL,
 x_axis_label = NULL,
 y_axis_label = "Features",
 low_cutoff = NULL,
 high_cutoff = NULL,
 cutoff_line_width = NULL,
 pt.size = NULL,
 plot_median = FALSE,
 plot_boxplot = FALSE,
 median_size = 15,
 colors_use = NULL,
 x_lab_rotate = TRUE,
 y_axis_log = FALSE,
 raster = NULL,
 assay = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

plot_title

Plot Title.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident); default is the current active.ident of the object.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

low_cutoff

Plot line a potential low threshold for filtering.

high_cutoff

Plot line a potential high threshold for filtering.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

pt.size

Point size for plotting.

plot_median

logical, whether to plot median for each ident on the plot (Default is FALSE).

plot_boxplot

logical, whether to plot boxplot inside of violin (Default is FALSE).

median_size

Shape size for the median is plotted.

colors_use

vector of colors to use for plot.

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is TRUE).

y_axis_log

logical. Whether to change y axis to log10 scale (Default is FALSE).

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 total points plotted (# Cells x # of features).

assay

Name of assay to use, defaults to the active assay.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to VlnPlot .

library(Seurat)
QC_Plots_Genes(seurat_object = pbmc_small, plot_title = "Genes per Cell", low_cutoff = 40,
high_cutoff = 85)

QC_Plots_Mito(
 seurat_object,
 mito_name = "percent_mito",
 plot_title = "Mito Gene % per Cell/Nucleus",
 group.by = NULL,
 x_axis_label = NULL,
 y_axis_label = "% Mitochondrial Gene Counts",
 low_cutoff = NULL,
 high_cutoff = NULL,
 cutoff_line_width = NULL,
 pt.size = NULL,
 plot_median = FALSE,
 median_size = 15,
 plot_boxplot = FALSE,
 colors_use = NULL,
 x_lab_rotate = TRUE,
 y_axis_log = FALSE,
 raster = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

mito_name

The column name containing percent mitochondrial counts information. Default value is "percent_mito" which is default value created when using Add_Mito_Ribo().

plot_title

Plot Title.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident); default is the current active.ident of the object.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

low_cutoff

Plot line a potential low threshold for filtering.

high_cutoff

Plot line a potential high threshold for filtering.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

pt.size

Point size for plotting.

plot_median

logical, whether to plot median for each ident on the plot (Default is FALSE).

median_size

Shape size for the median is plotted.

plot_boxplot

logical, whether to plot boxplot inside of violin (Default is FALSE).

colors_use

vector of colors to use for plot.

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is TRUE).

y_axis_log

logical. Whether to change y axis to log10 scale (Default is FALSE).

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 total points plotted (# Cells x # of features).

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to VlnPlot .

## Not run: 
QC_Plots_Mito(seurat_object = object, plot_title = "Percent Mito per Cell", high_cutoff = 10)
## End(Not run)

QC_Plots_UMIs(
 seurat_object,
 plot_title = "UMIs per Cell/Nucleus",
 group.by = NULL,
 x_axis_label = NULL,
 y_axis_label = "UMIs",
 low_cutoff = NULL,
 high_cutoff = NULL,
 cutoff_line_width = NULL,
 pt.size = NULL,
 plot_median = FALSE,
 median_size = 15,
 plot_boxplot = FALSE,
 colors_use = NULL,
 x_lab_rotate = TRUE,
 y_axis_log = FALSE,
 raster = NULL,
 assay = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

plot_title

Plot Title.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident); default is the current active.ident of the object.

x_axis_label

Label for x axis.

y_axis_label

Label for y axis.

low_cutoff

Plot line a potential low threshold for filtering.

high_cutoff

Plot line a potential high threshold for filtering.

cutoff_line_width

numerical value for thickness of cutoff lines, default is NULL.

pt.size

Point size for plotting.

plot_median

logical, whether to plot median for each ident on the plot (Default is FALSE).

median_size

Shape size for the median is plotted.

plot_boxplot

logical, whether to plot boxplot inside of violin (Default is FALSE).

colors_use

vector of colors to use for plot.

x_lab_rotate

Rotate x-axis labels 45 degrees (Default is TRUE).

y_axis_log

logical. Whether to change y axis to log10 scale (Default is FALSE).

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 100,000 total points plotted (# Cells x # of features).

assay

Name of assay to use, defaults to the active assay.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to VlnPlot .

library(Seurat)
QC_Plots_UMIs(seurat_object = pbmc_small, plot_title = "UMIs per Cell", low_cutoff = 75,
high_cutoff = 600)

Random_Cells_Downsample(
 seurat_object,
 num_cells,
 group.by = NULL,
 return_list = FALSE,
 allow_lower = FALSE,
 entire_object = FALSE,
 seed = 123
)

seurat_object

Seurat object

num_cells

number of cells per ident to use in down-sampling. This value must be less than or equal to the size of ident with fewest cells. Alternatively, can set to "min" which will use the maximum number of barcodes based on size of smallest group.

group.by

The ident to use to group cells. Default is NULL which use current active.ident. .

return_list

logical, whether or not to return the results as list instead of vector, default is FALSE.

allow_lower

logical, if number of cells in identity is lower than num_cells keep the maximum number of cells, default is FALSE. If FALSE will report error message if num_cells is too high, if TRUE will subset cells with more than num_cells to that value and those with less than num_cells will not be downsampled.

entire_object

logical, whether to downsample to specific number of cells across whole object, instead of number of cells per identity, default is FALSE.

seed

random seed to use for downsampling. Default is 123.

library(Seurat)
# return vector of barcodes
random_cells <- Random_Cells_Downsample(seurat_object = pbmc_small, num_cells = 10)
head(random_cells)
# return list
random_cells_list <- Random_Cells_Downsample(seurat_object = pbmc_small, return_list = TRUE,
num_cells = 10)
head(random_cells_list)
# return max total number of cells (setting `num_cells = "min`)
random_cells_max <- Random_Cells_Downsample(seurat_object = pbmc_small, num_cells = "min")

ReFilter_SeuratObject(
 seurat_object,
 min.cells = NULL,
 min.features = NULL,
 override = FALSE,
 verbose = TRUE
)

seurat_object

Seurat object to filter

min.cells

Include features detected in at least this many cells. Will recalculate nCount and nFeature meta.data values as well.

min.features

Include cells where at least this many features are detected.

override

logical, override the Yes/No interactive check (see details). Default is FALSE; don't override.

verbose

logical, whether to print information on filtering parameters and number of cells/features removed, Default is TRUE.

## Not run: 
# Remove features expressed in fewer than 10 cells
obj_fil <- ReFilter_SeuratObject(seurat_object = obj, min.cells = 10)
# Remove cells with fewer than 1000 features
obj_fil <- ReFilter_SeuratObject(seurat_object = obj, min.features = 1000)
# Filter on both parameters
obj_fil <- ReFilter_SeuratObject(seurat_object = obj, min.features = 1000, min.cells = 10)
## End(Not run)

Read10X_GEO(
 data_dir = NULL,
 sample_list = NULL,
 sample_names = NULL,
 gene.column = 2,
 cell.column = 1,
 unique.features = TRUE,
 strip.suffix = FALSE,
 parallel = FALSE,
 num_cores = NULL,
 merge = FALSE
)

data_dir

Directory containing the matrix.mtx, genes.tsv (or features.tsv), and barcodes.tsv files provided by 10X.

sample_list

A vector of file prefixes/names if specific samples are desired. Default is NULL and will load all samples in given directory.

sample_names

a set of sample names to use for each sample entry in returned list. If NULL will set names to the file name of each sample.

gene.column

Specify which column of genes.tsv or features.tsv to use for gene names; default is 2.

cell.column

Specify which column of barcodes.tsv to use for cell names; default is 1.

unique.features

Make feature names unique (default TRUE).

strip.suffix

Remove trailing "-1" if present in all cell barcodes.

parallel

logical (default FALSE). Whether to use multiple cores when reading in data. Only possible on Linux based systems.

num_cores

if parallel = TRUE indicates the number of cores to use for multicore processing.

merge

logical (default FALSE) whether or not to merge samples into a single matrix or return list of matrices. If TRUE each sample entry in list will have cell barcode prefix added. The prefix will be taken from sample_names.

## Not run: 
data_dir <- 'path/to/data/directory'
expression_matrices <- Read10X_GEO(data_dir = data_dir)
# To create object from single file
seurat_object = CreateSeuratObject(counts = expression_matrices[[1]])
## End(Not run)

Read10X_Multi_Directory(
 base_path,
 secondary_path = NULL,
 default_10X_path = TRUE,
 cellranger_multi = FALSE,
 sample_list = NULL,
 sample_names = NULL,
 parallel = FALSE,
 num_cores = NULL,
 merge = FALSE,
 ...
)

base_path

path to the parent directory which contains all of the subdirectories of interest.

secondary_path

path from the parent directory to count matrix files for each sample.

default_10X_path

logical (default TRUE) sets the secondary path variable to the default 10X directory structure.

cellranger_multi

logical, whether samples were processed with Cell Ranger multi, default is FALSE.

sample_list

a vector of sample directory names if only specific samples are desired. If NULL will read in subdirectories in parent directory.

sample_names

a set of sample names to use for each sample entry in returned list. If NULL will set names to the subdirectory name of each sample.

parallel

logical (default FALSE) whether or not to use multi core processing to read in matrices.

num_cores

how many cores to use for parallel processing.

merge

logical (default FALSE) whether or not to merge samples into a single matrix or return list of matrices. If TRUE each sample entry in list will have cell barcode prefix added. The prefix will be taken from sample_names.

...

Extra parameters passed to Read10X .

## Not run: 
base_path <- 'path/to/data/directory'
expression_matrices <- Read10X_Multi_Directory(base_path = base_path)
## End(Not run)

Read10X_h5_GEO(
 data_dir = NULL,
 sample_list = NULL,
 sample_names = NULL,
 shared_suffix = NULL,
 parallel = FALSE,
 num_cores = NULL,
 merge = FALSE,
 ...
)

data_dir

Directory containing the .h5 files provided by 10X.

sample_list

A vector of file prefixes/names if specific samples are desired. Default is NULL and will load all samples in given directory.

sample_names

a set of sample names to use for each sample entry in returned list. If NULL will set names to the file name of each sample.

shared_suffix

a suffix and file extension shared by all samples.

parallel

logical (default FALSE). Whether to use multiple cores when reading in data. Only possible on Linux based systems.

num_cores

if parallel = TRUE indicates the number of cores to use for multicore processing.

merge

logical (default FALSE) whether or not to merge samples into a single matrix or return list of matrices. If TRUE each sample entry in list will have cell barcode prefix added. The prefix will be taken from sample_names.

...

Additional arguments passed to Read10X_h5

## Not run: 
data_dir <- 'path/to/data/directory'
expression_matrices <- Read10X_h5_GEO(data_dir = data_dir)
# To create object from single file
seurat_object = CreateSeuratObject(counts = expression_matrices[[1]])
## End(Not run)

Read10X_h5_Multi_Directory(
 base_path,
 secondary_path = NULL,
 default_10X_path = TRUE,
 cellranger_multi = FALSE,
 h5_filename = "filtered_feature_bc_matrix.h5",
 sample_list = NULL,
 sample_names = NULL,
 replace_suffix = FALSE,
 new_suffix_list = NULL,
 parallel = FALSE,
 num_cores = NULL,
 merge = FALSE,
 ...
)

base_path

path to the parent directory which contains all of the subdirectories of interest.

secondary_path

path from the parent directory to count matrix files for each sample.

default_10X_path

logical (default TRUE) sets the secondary path variable to the default 10X directory structure.

cellranger_multi

logical, whether samples were processed with Cell Ranger multi, default is FALSE.

h5_filename

name of h5 file (including .h5 suffix). If all h5 files have same name (i.e. Cell Ranger output) then use full file name. By default function uses Cell Ranger name: "filtered_feature_bc_matrix.h5". If h5 files have sample specific prefixes (i.e. from Cell Bender) then use only the shared part of file name (e.g., "_filtered_out.h5").

sample_list

a vector of sample directory names if only specific samples are desired. If NULL will read in subdirectories in parent directory.

sample_names

a set of sample names to use for each sample entry in returned list. If NULL will set names to the subdirectory name of each sample.

replace_suffix

logical (default FALSE). Whether or not to replace the barcode suffixes of matrices using Replace_Suffix .

new_suffix_list

a vector of new suffixes to replace existing suffixes if replace_suffix = TRUE. See Replace_Suffix for more information. To remove all suffixes set new_suffix_list = "".

parallel

logical (default FALSE) whether or not to use multi core processing to read in matrices.

num_cores

how many cores to use for parallel processing.

merge

logical (default FALSE) whether or not to merge samples into a single matrix or return list of matrices. If TRUE each sample entry in list will have cell barcode prefix added. The prefix will be taken from sample_names.

...

Extra parameters passed to Read10X_h5 .

## Not run: 
base_path <- 'path/to/data/directory'
expression_matrices <- Read10X_h5_Multi_Directory(base_path = base_path)
## End(Not run)

Read_Add_cNMF(
 seurat_object,
 usage_file,
 spectra_file,
 reduction_name = "cnmf",
 reduction_key = "cNMF_",
 normalize = TRUE,
 assay = NULL,
 overwrite = FALSE
)

seurat_object

Seurat object name to add cNMF reduction

usage_file

path and name of cNMF usage file

spectra_file

path and name of cNMF spectra file

reduction_name

name to use for reduction to be added, default is "cnmf".

reduction_key

key to use for reduction to be added, default is "cNMF_".

normalize

logical, whether to normalize the cNMF usage data, default is TRUE

assay

assay to add reduction. Default is NULL and will use current active assay.

overwrite

logical, whether to overwrite a reduction with the name reduction_name already present in reduction slot of given Seurat object.

## Not run: 
object <- Read_cNMF(seurat_object = object,
usage_file = "example_cNMF/example_cNMF.usages.k_27.dt_0_01.consensus.txt",
spectra_file = "example_cNMF/example_cNMF.gene_spectra_score.k_27.dt_0_01.txt")
## End(Not run)

Read_CellBender_h5_Mat(
 file_name,
 use.names = TRUE,
 unique.features = TRUE,
 h5_group_name = NULL,
 feature_slot_name = "features"
)

file_name

Path to h5 file.

use.names

Label row names with feature names rather than ID numbers (default TRUE).

unique.features

Make feature names unique (default TRUE).

h5_group_name

Name of the group within H5 file that contains count data. This is only required if H5 file contains multiple subgroups and non-default names. Default is NULL.

feature_slot_name

Name of the slot contain feature names/ids. Must be one of: "features"(Cell Ranger v3+) or "genes" (Cell Ranger v1/v2 or STARsolo). Default is "features".

## Not run: 
mat <- Read_CellBender_h5_Mat(file_name = "/SampleA_out_filtered.h5")
## End(Not run)

Read_CellBender_h5_Multi_Directory(
 base_path,
 secondary_path = NULL,
 filtered_h5 = TRUE,
 custom_name = NULL,
 sample_list = NULL,
 sample_names = NULL,
 no_file_prefix = FALSE,
 h5_group_name = NULL,
 feature_slot_name = "features",
 replace_suffix = FALSE,
 new_suffix_list = NULL,
 parallel = FALSE,
 num_cores = NULL,
 merge = FALSE,
 ...
)

base_path

path to the parent directory which contains all of the subdirectories of interest.

secondary_path

path from the parent directory to count matrix files for each sample.

filtered_h5

logical (default TRUE). Will set the shared file name suffix custom_name is NULL.

custom_name

if file name was customized in CellBender then this parameter should contain the portion of file name that is shared across all samples. Must included the ".h5" extension as well.

sample_list

a vector of sample directory names if only specific samples are desired. If NULL will read in subdirectories in parent directory.

sample_names

a set of sample names to use for each sample entry in returned list. If NULL will set names to the subdirectory name of each sample. NOTE: unless sample_list is specified this will rename files in the order they are read which will be alphabetical.

no_file_prefix

logical, whether or not the file has prefix identical to folder name. Default is TRUE.

h5_group_name

Name of the group within H5 file that contains count data. This is only required if H5 file contains multiple subgroups and non-default names. Default is NULL.

feature_slot_name

Name of the slot contain feature names/ids. Must be one of: "features"(Cell Ranger v3+) or "genes" (Cell Ranger v1/v2 or STARsolo). Default is "features".

replace_suffix

logical (default FALSE). Whether or not to replace the barcode suffixes of matrices using Replace_Suffix .

new_suffix_list

a vector of new suffixes to replace existing suffixes if replace_suffix = TRUE. See Replace_Suffix for more information. To remove all suffixes set new_suffix_list = "".

parallel

logical (default FALSE) whether or not to use multi core processing to read in matrices.

num_cores

how many cores to use for parallel processing.

merge

logical (default FALSE) whether or not to merge samples into a single matrix or return list of matrices. If TRUE each sample entry in list will have cell barcode prefix added. The prefix will be taken from sample_names.

...

Extra parameters passed to Read_CellBender_h5_Mat .

## Not run: 
base_path <- 'path/to/data/directory'
mat_list <- Read_CellBender_h5_Multi_Directory(base_path = base_path)
## End(Not run)

Read_CellBender_h5_Multi_File(
 data_dir = NULL,
 filtered_h5 = TRUE,
 custom_name = NULL,
 sample_list = NULL,
 sample_names = NULL,
 h5_group_name = NULL,
 feature_slot_name = "features",
 parallel = FALSE,
 num_cores = NULL,
 merge = FALSE,
 ...
)

data_dir

Directory containing the .h5 files output by CellBender.

filtered_h5

logical (default TRUE). Will set the shared file name suffix if custom_name is NULL.

custom_name

if file name was customized in CellBender then this parameter should contain the portion of file name that is shared across all samples. Must included the ".h5" extension as well.

sample_list

a vector of sample names if only specific samples are desired. If NULL will read in all files within data_dir directory.

sample_names

a set of sample names to use for each sample entry in returned list. If NULL will set names to the subdirectory name of each sample.

h5_group_name

Name of the group within H5 file that contains count data. This is only required if H5 file contains multiple subgroups and non-default names. Default is NULL.

feature_slot_name

Name of the slot contain feature names/ids. Must be one of: "features"(Cell Ranger v3+) or "genes" (Cell Ranger v1/v2 or STARsolo). Default is "features".

parallel

logical (default FALSE) whether or not to use multi core processing to read in matrices

num_cores

how many cores to use for parallel processing.

merge

logical (default FALSE) whether or not to merge samples into a single matrix or return list of matrices. If TRUE each sample entry in list will have cell barcode prefix added. The prefix will be taken from sample_names.

...

Extra parameters passed to Read_CellBender_h5_Mat .

## Not run: 
base_path <- 'path/to/data/directory'
mat_list <- Read_CellBender_h5_Multi_File(data_dir = base_path)
## End(Not run)

Read_GEO_Delim(
 data_dir,
 file_suffix,
 move_genes_rownames = TRUE,
 sample_list = NULL,
 full_names = FALSE,
 sample_names = NULL,
 barcode_suffix_period = FALSE,
 parallel = FALSE,
 num_cores = NULL,
 merge = FALSE
)

data_dir

Directory containing the files.

file_suffix

The file suffix of the individual files. Must be the same across all files being imported. This is used to detect files to import and their GEO IDs.

move_genes_rownames

logical. Whether gene IDs are present in first column or in row names of delimited file. If TRUE will move the first column to row names before creating final matrix. Default is TRUE.

sample_list

a vector of samples within directory to read in (can be either with or without file_suffix see full_names). If NULL will read in all subdirectories.

full_names

logical (default FALSE). Whether or not the sample_list vector includes the file suffix. If FALSE the function will add suffix based on file_suffix parameter.

sample_names

a set of sample names to use for each sample entry in returned list. If NULL will set names to the directory name of each sample.

barcode_suffix_period

Is the barcode suffix a period and should it be changed to "-". Default (FALSE; barcodes will be left identical to their format in input files.). If TRUE "." in barcode suffix will be changed to "-".

parallel

logical (default FALSE). Whether to use multiple cores when reading in data. Only possible on Linux based systems.

num_cores

if parallel = TRUE indicates the number of cores to use for multicore processing.

merge

logical (default FALSE) whether or not to merge samples into a single matrix or return list of matrices. If TRUE each sample entry in list will have cell barcode prefix added. The prefix will be taken from sample_names.

## Not run: 
data_dir <- 'path/to/data/directory'
expression_matrices <- Read_GEO_Delim(data_dir = data_dir)
## End(Not run)

Read_Metrics_10X(
 base_path,
 secondary_path = NULL,
 default_10X = TRUE,
 cellranger_multi = FALSE,
 lib_list = NULL,
 lib_names = NULL
)

base_path

path to the parent directory which contains all of the sub-directories of interest or alternatively can provide single csv file to read and format identically to reading multiple files.

secondary_path

path from the parent directory to count "outs/" folder which contains the "metrics_summary.csv" file.

default_10X

logical (default TRUE) sets the secondary path variable to the default 10X directory structure.

cellranger_multi

logical, whether or not metrics come from Cell Ranger count or from Cell Ranger multi. Default is FALSE.

lib_list

a list of sample names (matching directory names) to import. If NULL will read in all samples in parent directory.

lib_names

a set of sample names to use for each sample. If NULL will set names to the directory name of each sample.

## Not run: 
metrics <- Read_Metrics_10X(base_path = "/path/to/directories", default_10X = TRUE)
## End(Not run)

Read_Metrics_CellBender(base_path, lib_list = NULL, lib_names = NULL)

base_path

path to the parent directory which contains all of the sub-directories of interest or path to single metrics csv file.

lib_list

a list of sample names (matching directory names) to import. If NULL will read in all samples in parent directory.

lib_names

a set of sample names to use for each sample. If NULL will set names to the directory name of each sample.

## Not run: 
CB_metrics <- Read_Metrics_CellBender(base_path = "/path/to/directories")
## End(Not run)

Reduction_Loading_Present(
 seurat_object,
 reduction_names,
 print_msg = TRUE,
 omit_warn = TRUE,
 return_none = FALSE
)

seurat_object

object name.

reduction_names

vector of reduction loading names to check.

print_msg

logical. Whether message should be printed if all features are found. Default is TRUE.

omit_warn

logical. Whether to print message about reduction loadings that are not found in current object. Default is TRUE.

return_none

logical. Whether list of found vs. bad reduction loadings should still be returned if no reductions are found. Default is FALSE.

## Not run: 
reductions <- Reduction_Loading_Present(seurat_object = obj_name, reduction_name = "PC_1")
found_reductions <- reductions[[1]]
## End(Not run)

Rename_Clusters(object, ...)
## S3 method for class 'liger'
Rename_Clusters(
 object,
 new_idents,
 old_ident_name = NULL,
 new_ident_name = NULL,
 overwrite = FALSE,
 ...
)
## S3 method for class 'Seurat'
Rename_Clusters(
 object,
 new_idents,
 old_ident_name = NULL,
 new_ident_name = NULL,
 meta_col_name = deprecated(),
 overwrite = FALSE,
 ...
)

object

Object of class Seurat or liger.

...

Arguments passed to other methods

new_idents

vector of new cluster names. Must be equal to the length of current default identity of Object. Will accept named vector (with old idents as names) or will name the new_idents vector internally.

old_ident_name

optional, name to use for storing current object idents in object meta data slot.

new_ident_name

optional, name to use for storing new object idents in object meta data slot.

overwrite

logical, whether to overwrite columns in object meta data slot. if they have same names as old_ident_name and/or new_ident_name.

meta_col_name

. See old_ident_name.

## Not run: 
# Liger version
obj <- Rename_Clusters(object = obj_name, new_idents = new_idents_vec,
old_ident_name = "LIGER_Idents_Round01", new_ident_name = "LIGER_Idents_Round02")
## End(Not run)
## Not run: 
obj <- Rename_Clusters(seurat_object = obj_name, new_idents = new_idents_vec,
old_ident_name = "Seurat_Idents_Round01", new_ident_name = "Round01_Res0.6_Idents")
## End(Not run)

Replace_Suffix(data, current_suffix, new_suffix)

data

Either matrix/data.frame or list of matrices/data.frames with the cell barcodes in the column names.

current_suffix

a single value or vector of values representing current barcode suffix. If suffix is the same for all matrices/data.frames in list only single value is required.

new_suffix

a single value or vector of values representing new barcode suffix to be added. If desired suffix is the same for all matrices/data.frames in list only single value is required. If no suffix is desired set new_suffix = "".'

## Not run: 
dge_matrix <- Replace_Suffix(data = dge_matrix, current_suffix = "-1", new_suffix = "-2")
## End(Not run)

Seq_QC_Plot_Alignment_Combined(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 patchwork_title = "Sequencing QC Plots: Read Alignment Metrics",
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

patchwork_title

Title to use for the patchworked plot output.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Alignment_Combined(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Antisense(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Antisense(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Basic_Combined(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 patchwork_title = "Sequencing QC Plots: Basic Cell Metrics",
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

patchwork_title

Title to use for the patchworked plot output.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Basic_Combined(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Exonic(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Exonic(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Genes(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Genes(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Genome(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Genome(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Intergenic(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Intergeneic(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Intronic(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Intronic(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Number_Cells(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Number_Cells(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Reads_in_Cells(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Reads_in_Cells(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Reads_per_Cell(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Reads_per_Cell(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Saturation(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Saturation(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Total_Genes(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Total_Genes(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_Transcriptome(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_Transcriptome(metrics_dataframe = metrics)
## End(Not run)

Seq_QC_Plot_UMIs(
 metrics_dataframe,
 plot_by = "sample_id",
 colors_use = NULL,
 dot_size = 1,
 x_lab_rotate = FALSE,
 significance = FALSE,
 ...
)

metrics_dataframe

data.frame contain Cell Ranger QC Metrics (see Read_Metrics_10X ).

plot_by

Grouping factor for the plot. Default is to plot as single group with single point per sample.

colors_use

colors to use for plot if plotting by group. Defaults to RColorBrewer Dark2 palette if less than 8 groups and DiscretePalette_scCustomize(palette = "polychrome") if more than 8.

dot_size

size of the dots plotted if plot_by is not sample_id Default is 1.

x_lab_rotate

logical. Whether to rotate the axes labels on the x-axis. Default is FALSE.

significance

logical. Whether to calculate and plot p-value comparisons when plotting by grouping factor. Default is FALSE.

...

Other variables to pass to ggpubr::stat_compare_means when doing significance testing.

## Not run: 
Seq_QC_Plot_UMIs(metrics_dataframe = metrics)
## End(Not run)

Setup_scRNAseq_Project(
 custom_dir_file = NULL,
 cluster_annotation_path = NULL,
 cluster_annotation_file_name = "cluster_annotation.csv"
)

custom_dir_file

file to file containing desired directory structure. Default is NULL and will provide generic built-in directory structure.

cluster_annotation_path

path to place cluster annotation file using Create_Cluster_Annotation_File .

cluster_annotation_file_name

name to use for annotation file if created (optional).

## Not run: 
# If using built-in directory structure.
Setup_scRNAseq_Project()
## End(Not run)

Single_Color_Palette(pal_color, num_colors = NULL, seed_use = 123)

pal_color

color palette to select (Options are: 'reds', 'blues', 'greens', 'purples', 'oranges', 'grays').

num_colors

set number of colors (max = 7).

seed_use

set seed for reproducibility (default: 123).

pal <- Single_Color_Palette(pal_color = "reds", num_colors = 7)
PalettePlot(pal= pal)

SpatialDimPlot_scCustom(
 seurat_object,
 group.by = NULL,
 images = NULL,
 colors_use = NULL,
 crop = TRUE,
 label = FALSE,
 label.size = 7,
 label.color = "white",
 label.box = TRUE,
 repel = FALSE,
 ncol = NULL,
 pt.size.factor = 1.6,
 alpha = c(1, 1),
 image.alpha = 1,
 stroke = 0.25,
 interactive = FALSE,
 combine = TRUE,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

group.by

Name of meta.data column to group the data by

images

Name of the images to use in the plot(s)

colors_use

color palette to use for plotting. By default if number of levels plotted is less than or equal to 36 it will use "polychrome" and if greater than 36 will use "varibow" with shuffle = TRUE both from DiscretePalette_scCustomize.

crop

Crop the plot in to focus on points plotted. Set to FALSE to show entire background image.

label

Whether to label the clusters

label.size

Sets the size of the labels

label.color

Sets the color of the label text

label.box

Whether to put a box around the label text (geom_text vs geom_label)

repel

Repels the labels to prevent overlap

ncol

Number of columns if plotting multiple plots

pt.size.factor

Scale the size of the spots.

alpha

Controls opacity of spots. Provide as a vector specifying the min and max for SpatialFeaturePlot. For SpatialDimPlot, provide a single alpha value for each plot.

image.alpha

Adjust the opacity of the background images. Set to 0 to remove.

stroke

Control the width of the border around the spots

interactive

Launch an interactive SpatialDimPlot or SpatialFeaturePlot session, see ISpatialDimPlot or ISpatialFeaturePlot for more details

combine

Combine plots into a single gg object; note that if TRUE; themeing will not work when plotting multiple features/groupings

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to DimPlot .

## Not run: 
SpatialDimPlot_scCustom(seurat_object = seurat_object)
## End(Not run)

Split_Layers(seurat_object, assay = "RNA", split.by)

seurat_object

Seurat object name.

assay

name(s) of assays to convert. Defaults to current active assay.

split.by

Variable in meta.data to use for splitting layers.

## Not run: 
# Split object by "treatment"
obj <- Split_Layers(object = obj, assay = "RNA", split.by = "treatment")
## End(Not run)

Split_Vector(x, chunk_size = NULL, num_chunk = NULL, verbose = FALSE)

x

vector to split

chunk_size

size of chunks for vector to be split into, default is NULL. Only valid if num_chunk is NULL.

num_chunk

number of chunks to split the vector into, default is NULL. Only valid if chunk_size is NULL.

verbose

logical, print details of vector and split, default is FALSE.

vector <- c("gene1", "gene2", "gene3", "gene4", "gene5", "gene6")
vector_list <- Split_Vector(x = vector, chunk_size = 3)

Stacked_VlnPlot(
 seurat_object,
 features,
 group.by = NULL,
 split.by = NULL,
 idents = NULL,
 x_lab_rotate = FALSE,
 plot_legend = FALSE,
 colors_use = NULL,
 color_seed = 123,
 ggplot_default_colors = FALSE,
 plot_spacing = 0.15,
 spacing_unit = "cm",
 vln_linewidth = NULL,
 pt.size = NULL,
 raster = NULL,
 add.noise = TRUE,
 ...
)

seurat_object

Seurat object name.

features

Features to plot.

group.by

Group (color) cells in different ways (for example, orig.ident).

split.by

A variable to split the violin plots by,

idents

Which classes to include in the plot (default is all).

x_lab_rotate

logical or numeric. If logical whether to rotate x-axis labels 45 degrees (Default is FALSE). If numeric must be either 45 or 90. Setting 45 is equivalent to setting TRUE.

plot_legend

logical. Adds plot legend containing idents to the returned plot.

colors_use

specify color palette to used in VlnPlot . By default if number of levels plotted is less than or equal to 36 it will use "polychrome" and if greater than 36 will use "varibow" with shuffle = TRUE both from DiscretePalette_scCustomize.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

plot_spacing

Numerical value specifying the vertical spacing between each plot in the stack. Default is 0.15 ("cm"). Spacing dependent on unit provided to spacing_unit.

spacing_unit

Unit to use in specifying vertical spacing between plots. Default is "cm".

vln_linewidth

Adjust the linewidth of violin outline. Must be numeric.

pt.size

Adjust point size for plotting. Default for Stacked_VlnPlot is 0 to avoid issues with rendering so many points in vector form. Alternatively, see raster parameter.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 total points plotted (# Cells x # of features).

add.noise

logical, determine if adding a small noise for plotting (Default is TRUE).

...

Extra parameters passed to VlnPlot .

library(Seurat)
Stacked_VlnPlot(seurat_object = pbmc_small, features = c("CD3E", "CD8", "GZMB", "MS4A1"),
x_lab_rotate = TRUE)

Store_Misc_Info_Seurat(
 seurat_object,
 data_to_store,
 data_name,
 list_as_list = FALSE,
 overwrite = FALSE,
 verbose = TRUE
)

seurat_object

object name.

data_to_store

data to be stored in ⁠@misc⁠ slot. Can be single piece of data or list. If list of data see list_as_list parameter for control over data storage.

data_name

name to give the entry in ⁠@misc⁠ slot. Must be of equal length of the number of data items being stored.

list_as_list

logical. If data_to_store is a list, this dictates whether to store in ⁠@misc⁠ slot as list (TRUE) or whether to store each entry in the list separately (FALSE). Default is FALSE.

overwrite

Logical. Whether to overwrite existing items with the same name. Default is FALSE, meaning that function will abort if item with data_name is present in misc slot.

verbose

logical, whether to print messages when running function, default is TRUE.

library(Seurat)
clu_pal <- c("red", "green", "blue")
pbmc_small <- Store_Misc_Info_Seurat(seurat_object = pbmc_small, data_to_store = clu_pal,
data_name = "rd1_colors")

Store_Palette_Seurat(
 seurat_object,
 palette,
 palette_name,
 list_as_list = FALSE,
 overwrite = FALSE,
 verbose = TRUE
)

seurat_object

object name.

palette

vector or list of vectors containing color palettes to store. If list of palettes see list_as_list parameter for control over data storage.

palette_name

name to give the palette(s) in ⁠@misc⁠ slot. Must be of equal length to the number of data items being stored.

list_as_list

logical. If data_to_store is a list, this dictates whether to store in ⁠@misc⁠ slot as list (TRUE) or whether to store each entry in the list separately (FALSE). Default is FALSE.

overwrite

Logical. Whether to overwrite existing items with the same name. Default is FALSE, meaning that function will abort if item with data_name is present in misc slot.

verbose

logical, whether to print messages when running function, default is TRUE.

library(Seurat)
clu_pal <- c("red", "green", "blue")
pbmc_small <- Store_Misc_Info_Seurat(seurat_object = pbmc_small, data_to_store = clu_pal,
data_name = "rd1_colors")

Subset_LIGER(
 liger_object,
 cluster = NULL,
 cluster_col = "leiden_cluster",
 ident = NULL,
 ident_col = NULL,
 invert = FALSE
)

liger_object

LIGER object name.

cluster

Name(s) of cluster to subset from object.

cluster_col

name of ⁠@cellMeta⁠ column containing cluster names, default is "leiden_cluster".

ident

variable within ident_col to use in sub-setting object.

ident_col

column in ⁠@cellMeta⁠ that contains values provided to ident.

invert

logical, whether to subset the inverse of the clusters or idents provided, default is FALSE.

## Not run: 
# subset clusters 3 and 5
sub_liger <- subset_liger(liger_object = liger_object, cluster = c(3, 5))
# subset control samples from column "Treatment"
sub_liger <- subset_liger(liger_object = liger_object, ident = "control",
ident_col = "Treatment")
# subset control samples from column "Treatment" in clusters 3 and 5
sub_liger <- subset_liger(liger_object = liger_object, ident = "control",
ident_col = "Treatment", cluster = c(3, 5))
# Remove cluster 9
sub_liger <- subset_liger(liger_object = liger_object, cluster = 9, invert = TRUE)
## End(Not run)

Top_Genes_Factor(object, factor = NULL, num_genes = 10, ...)
## S3 method for class 'liger'
Top_Genes_Factor(object, factor = NULL, num_genes = 10, ...)
## S3 method for class 'Seurat'
Top_Genes_Factor(object, factor = NULL, num_genes = 10, reduction, ...)

object

object name.

factor

factor number to pull genes from. Set to "all" to return top loading genes from all factors

num_genes

number of top loading genes to return as vector, default is 10.

...

Arguments passed to other methods

reduction

name of reduction containing NMF/iNMF/cNMF data.

## Not run: 
top_genes_factor10 <- Top_Genes_Factor(object = object, factor = 1, num_genes = 10)
## End(Not run)
## Not run: 
top_genes_factor10 <- Top_Genes_Factor(object = object, factor = 1, num_genes = 10,
reduction = "cNMF")
## End(Not run)

UnRotate_X(...)

...

extra arguments passed to ggplot2::theme().

library(Seurat)
p <- VlnPlot(object = pbmc_small, features = "CD3E")
p + UnRotate_X()

Updated_HGNC_Symbols(
 input_data,
 update_symbol_data = NULL,
 case_check_as_warn = FALSE,
 verbose = TRUE
)

input_data

Data source containing gene names. Accepted formats are:

• charcter vector

• Seurat Objects

• data.frame: genes as rownames

• dgCMatrix/dgTMatrix: genes as rownames

• tibble: genes in first column

update_symbol_data

logical, whether to update cached HGNC data, default is NULL. If NULL BiocFileCache will check and prompt for update if cache is stale. If FALSE the BiocFileCache stale check will be skipped and current cache will be used. If TRUE the BiocFileCache stale check will be skipped and HGNC data will be downloaded.

case_check_as_warn

logical, whether case checking of features should cause abort or only warn, default is FALSE (abort). Set to TRUE if atypical names (i.e. old LOC naming) are present in input_data.

verbose

logical, whether to print results detailing numbers of symbols, found, updated, and not found; default is TRUE.

## Not run: 
new_names <- Updated_HGNC_Symbols(input_data = Seurat_Object)
## End(Not run)

Updated_MGI_Symbols(input_data, update_symbol_data = NULL, verbose = TRUE)

input_data

Data source containing gene names. Accepted formats are:

• charcter vector

• Seurat Objects

• data.frame: genes as rownames

• dgCMatrix/dgTMatrix: genes as rownames

• tibble: genes in first column

update_symbol_data

logical, whether to update cached MGI data, default is NULL. If NULL BiocFileCache will check and prompt for update if cache is stale. If FALSE the BiocFileCache stale check will be skipped and current cache will be used. If TRUE the BiocFileCache stale check will be skipped and MGI data will be downloaded.

verbose

logical, whether to print results detailing numbers of symbols, found, updated, and not found; default is TRUE.

## Not run: 
new_names <- Updated_MGI_Symbols(input_data = Seurat_Object)
## End(Not run)

VariableFeaturePlot_scCustom(
 seurat_object,
 num_features = 10,
 custom_features = NULL,
 label = TRUE,
 pt.size = 1,
 colors_use = c("black", "red"),
 repel = TRUE,
 y_axis_log = FALSE,
 assay = NULL,
 selection.method = NULL,
 ...
)

seurat_object

Seurat object name.

num_features

Number of top variable features to highlight by color/label.

custom_features

A vector of custom feature names to label on plot instead of labeling top variable genes.

label

logical. Whether to label the top features. Default is TRUE.

pt.size

Adjust point size for plotting.

colors_use

colors to use for plotting. Default is "black" and "red".

repel

logical (default TRUE). Whether or not to repel the feature labels on plot.

y_axis_log

logical. Whether to change y axis to log10 scale (Default is FALSE).

assay

Assay to pull variable features from.

selection.method

If more then one method use to calculate variable features specify which method to use for plotting. See selection.method parameter in VariableFeaturePlot for list of options.

...

Extra parameters passed to VariableFeaturePlot .

library(Seurat)
VariableFeaturePlot_scCustom(seurat_object = pbmc_small, num_features = 10)

Variable_Features_ALL_LIGER(
 liger_object,
 num_genes = NULL,
 var.thresh = 0.3,
 alpha.thresh = 0.99,
 tol = 1e-04,
 do.plot = FALSE,
 pt.size = 1.5,
 chunk = 1000
)

liger_object

LIGER object name.

num_genes

Number of genes to find. Optimizes the value of var.thresh to get this number of genes, (Default is NULL).

var.thresh

Variance threshold. Main threshold used to identify variable genes. Genes with expression variance greater than threshold (relative to mean) are selected. (higher threshold -> fewer selected genes).

alpha.thresh

Alpha threshold. Controls upper bound for expected mean gene expression (lower threshold -> higher upper bound). (default 0.99)

tol

Tolerance to use for optimization if num.genes values passed in (default 0.0001). Only applicable for rliger < 2.0.0.

do.plot

Display log plot of gene variance vs. gene expression. Selected genes are plotted in green. (Default FALSE)

pt.size

Point size for plot.

chunk

size of chunks in hdf5 file. (Default 1000)

## Not run: 
liger_obj <- Variable_Features_ALL_LIGER(liger_object = liger_obj, num_genes = 2000)
## End(Not run)

VlnPlot_scCustom(
 seurat_object,
 features,
 colors_use = NULL,
 pt.size = NULL,
 group.by = NULL,
 split.by = NULL,
 plot_median = FALSE,
 plot_boxplot = FALSE,
 median_size = 15,
 idents = NULL,
 num_columns = NULL,
 raster = NULL,
 add.noise = TRUE,
 ggplot_default_colors = FALSE,
 color_seed = 123,
 ...
)

seurat_object

Seurat object name.

features

Feature(s) to plot.

colors_use

color palette to use for plotting. By default if number of levels plotted is less than or equal to 36 it will use "polychrome" and if greater than 36 will use "varibow" with shuffle = TRUE both from DiscretePalette_scCustomize.

pt.size

Adjust point size for plotting.

group.by

Name of one or more metadata columns to group (color) cells by (for example, orig.ident); default is the current active.ident of the object.

split.by

Feature to split plots by (i.e. "orig.ident").

plot_median

logical, whether to plot median for each ident on the plot (Default is FALSE).

plot_boxplot

logical, whether to plot boxplot inside of violin (Default is FALSE).

median_size

Shape size for the median is plotted.

idents

Which classes to include in the plot (default is all).

num_columns

Number of columns in plot layout. Only valid if split.by != NULL.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 total points plotted (# Cells x # of features).

add.noise

logical, determine if adding a small noise for plotting (Default is TRUE).

ggplot_default_colors

logical. If colors_use = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "polychrome" or "varibow" palettes.

color_seed

random seed for the "varibow" palette shuffle if colors_use = NULL and number of groups plotted is greater than 36. Default = 123.

...

Extra parameters passed to VlnPlot .

library(Seurat)
VlnPlot_scCustom(seurat_object = pbmc_small, features = "CD3E")

## S3 method for class 'liger'
WhichCells(
 object,
 idents = NULL,
 ident_col = NULL,
 by_dataset = FALSE,
 invert = FALSE,
 ...
)

object

LIGER object name.

idents

identities to extract cell barcodes.

ident_col

name of meta data column to use when subsetting cells by identity values. Default is NULL, which will use the objects default clustering as the ident_col.

by_dataset

logical, whether to return vector with cell barcodes for all idents in or to return list (1 entry per dataset with vector of cells) (default is FALSE; return vector).

invert

logical, invert the selection of cells (default is FALSE).

...

Arguments passed to other methods

## Not run: 
# Extract cells from ident =1 in current default clustering
ident1_cells <- WhichCells(object = liger_object, idents = 1)
# Extract all cells from "stim" treatment from object
stim_cells <- WhichCells(object = liger_object, idents = "stim", ident_col = "Treatment")
## End(Not run)

as.LIGER(x, ...)
## S3 method for class 'Seurat'
as.LIGER(
 x,
 group.by = "orig.ident",
 layers_name = NULL,
 assay = "RNA",
 remove_missing = FALSE,
 renormalize = TRUE,
 use_seurat_var_genes = FALSE,
 use_seurat_dimreduc = FALSE,
 reduction = NULL,
 keep_meta = TRUE,
 verbose = TRUE,
 ...
)
## S3 method for class 'list'
as.LIGER(
 x,
 group.by = "orig.ident",
 dataset_names = NULL,
 assay = "RNA",
 remove_missing = FALSE,
 renormalize = TRUE,
 use_seurat_var_genes = FALSE,
 var_genes_method = "intersect",
 keep_meta = TRUE,
 verbose = TRUE,
 ...
)

x

An object to convert to class liger

...

Arguments passed to other methods

group.by

Variable in meta data which contains variable to split data by, (default is "orig.ident").

layers_name

name of meta.data column used to split layers if setting group.by = "layers".

assay

Assay containing raw data to use, (default is "RNA").

remove_missing

logical, whether to remove missing genes with no counts when converting to LIGER object (default is FALSE).

renormalize

logical, whether to perform normalization after LIGER object creation (default is TRUE).

use_seurat_var_genes

logical, whether to transfer variable features from Seurat object to new LIGER object (default is FALSE).

use_seurat_dimreduc

logical, whether to transfer dimensionality reduction coordinates from Seurat to new LIGER object (default is FALSE).

reduction

Name of Seurat reduction to transfer if use_seurat_dimreduc = TRUE.

keep_meta

logical, whether to transfer columns in Seurat meta.data slot to LIGER cell.data slot (default is TRUE).

verbose

logical, whether to print status messages during object conversion (default is TRUE).

dataset_names

optional, vector of names to use for naming datasets.

var_genes_method

how variable genes should be selected from Seurat objects if use_seurat_var_genes = TRUE. Can be either "intersect" or "union", (default is "intersect").

## Not run: 
liger_object <- as.LIGER(x = seurat_object)
## End(Not run)
## Not run: 
liger_object <- as.LIGER(x = seurat_object_list)
## End(Not run)

## S3 method for class 'liger'
as.Seurat(
 x,
 nms = names(x@H),
 renormalize = TRUE,
 use.liger.genes = TRUE,
 by.dataset = FALSE,
 keep_meta = TRUE,
 reduction_label = "UMAP",
 seurat_assay = "RNA",
 assay_type = NULL,
 add_barcode_names = FALSE,
 barcode_prefix = TRUE,
 barcode_cell_id_delimiter = "_",
 ...
)

x

liger object.

nms

By default, labels cell names with dataset of origin (this is to account for cells in different datasets which may have same name). Other names can be passed here as vector, must have same length as the number of datasets. (default names(H)).

renormalize

Whether to log-normalize raw data using Seurat defaults (default TRUE).

use.liger.genes

Whether to carry over variable genes (default TRUE).

by.dataset

Include dataset of origin in cluster identity in Seurat object (default FALSE).

keep_meta

logical. Whether to transfer additional metadata (nGene/nUMI/dataset already transferred) to new Seurat Object. Default is TRUE.

reduction_label

Name of dimensionality reduction technique used. Enables accurate transfer or name to Seurat object instead of defaulting to "tSNE".

seurat_assay

Name to set for assay in Seurat Object. Default is "RNA".

assay_type

what type of Seurat assay to create in new object (Assay vs Assay5). Default is NULL which will default to the current user settings. See Convert_Assay parameter convert_to for acceptable values.

add_barcode_names

logical, whether to add dataset names to the cell barcodes when creating Seurat object, default is FALSE.

barcode_prefix

logical, if add_barcode_names = TRUE should the names be added as prefix to current cell barcodes/names or a suffix (default is TRUE; prefix).

barcode_cell_id_delimiter

The delimiter to use when adding dataset id to barcode prefix/suffix. Default is "_".

...

unused.

## Not run: 
seurat_object <- as.Seurat(x = liger_object)
## End(Not run)

as.anndata(x, ...)
## S3 method for class 'Seurat'
as.anndata(
 x,
 file_path,
 file_name,
 assay = NULL,
 main_layer = "data",
 other_layers = "counts",
 transer_dimreduc = TRUE,
 verbose = TRUE,
 ...
)
## S3 method for class 'liger'
as.anndata(
 x,
 file_path,
 file_name,
 transfer_norm.data = FALSE,
 reduction_label = NULL,
 add_barcode_names = FALSE,
 barcode_prefix = TRUE,
 barcode_cell_id_delimiter = "_",
 verbose = TRUE,
 ...
)

x

Seurat or LIGER object

...

Arguments passed to other methods

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

file name.

assay

Assay containing data to use, (default is object default assay).

main_layer

the layer of data to become default layer in anndata object (default is "data").

other_layers

other data layers to transfer to anndata object (default is "counts").

transer_dimreduc

logical, whether to transfer dimensionality reduction coordinates from Seurat to anndata object (default is TRUE).

verbose

logical, whether to print status messages during object conversion (default is TRUE).

transfer_norm.data

logical, whether to transfer the norm.data in addition to raw.data, default is FALSE.

reduction_label

What to label the visualization dimensionality reduction. LIGER does not store name of technique and therefore needs to be set manually.

add_barcode_names

logical, whether to add dataset names to the cell barcodes when merging object data, default is FALSE.

barcode_prefix

logical, if add_barcode_names = TRUE should the names be added as prefix to current cell barcodes/names or a suffix (default is TRUE; prefix).

barcode_cell_id_delimiter

The delimiter to use when adding dataset id to barcode prefix/suffix. Default is "_".

## Not run: 
as.anndata(x = seurat_object, file_path = "/folder_name", file_name = "anndata_converted.h5ad")
## End(Not run)
## Not run: 
as.anndata(x = liger_object, file_path = "/folder_name", file_name = "anndata_converted.h5ad")
## End(Not run)

ensembl_exAM_list

ensembl_hemo_id

ensembl_ieg_list

ensembl_lncRNA_id

ensembl_malat1_list

ensembl_mito_id

ensembl_ribo_id

exAM_Scoring(
 seurat_object,
 species,
 exam_module_name = NULL,
 method = "Seurat",
 ensembl_ids = FALSE,
 assay = NULL,
 overwrite = FALSE,
 exclude_unfound = FALSE,
 seed = 1
)

seurat_object

object name.

species

Species of origin for given Seurat Object. Only accepted species are: mouse, human (name or abbreviation).

exam_module_name

name to use for the new meta.data column containing module scores.

method

method to use for module scoring, currently only "Seurat" is supported but more to be added. .

ensembl_ids

logical, whether feature names in the object are gene names or ensembl IDs (default is FALSE; set TRUE if feature names are ensembl IDs).

assay

Assay to use (default is the current object default assay).

overwrite

Logical. Whether to overwrite existing meta.data columns. Default is FALSE meaning that function will abort if columns with the name provided to exam_module_name is present in meta.data slot.

exclude_unfound

logical, whether to exclude features not present in current object (default is FALSE).

seed

seed for reproducibility (default is 1).

## Not run: 
# Seurat
seurat_object <- exAM_Scoring(seurat_object = seurat_object, species = "human")
## End(Not run)

exAM_gene_list

ieg_gene_list

lncRNA_gene_list

msigdb_qc_ensembl_list

msigdb_qc_gene_list

plotFactors_scCustom(
 liger_object,
 num_genes = 8,
 colors_use_factors = NULL,
 colors_use_dimreduc = c("lemonchiffon", "red"),
 pt.size_factors = 1,
 pt.size_dimreduc = 1,
 reduction = "UMAP",
 reduction_label = "UMAP",
 plot_legend = TRUE,
 raster = TRUE,
 raster.dpi = c(512, 512),
 order = FALSE,
 plot_dimreduc = TRUE,
 save_plots = TRUE,
 file_path = NULL,
 file_name = NULL,
 return_plots = FALSE,
 cells.highlight = NULL,
 reorder_datasets = NULL,
 ggplot_default_colors = FALSE,
 color_seed = 123
)

liger_object

liger liger_object. Need to perform clustering and factorization before calling this function

num_genes

Number of genes to display for each factor (Default 8).

colors_use_factors

colors to use for plotting factor loadings By default datasets will be plotted using "varibow" with shuffle = TRUE from both from DiscretePalette_scCustomize .

colors_use_dimreduc

colors to use for plotting factor loadings on dimensionality reduction coordinates (tSNE/UMAP). Default is c('lemonchiffon', 'red'),

pt.size_factors

Adjust point size for plotting in the factor plots.

pt.size_dimreduc

Adjust point size for plotting in dimensionality reduction plots.

reduction

Name of dimensionality reduction to use for plotting. Default is "UMAP". Only for newer style liger objects.

reduction_label

What to label the x and y axes of resulting plots. LIGER does not store name of technique and therefore needs to be set manually. Default is "UMAP". Only for older style liger objects.

plot_legend

logical, whether to plot the legend on factor loading plots, default is TRUE. Helpful if number of datasets is large to avoid crowding the plot with legend.

raster

Convert points to raster format. Default is NULL which will rasterize by default if greater than 200,000 cells.

raster.dpi

Pixel resolution for rasterized plots, passed to geom_scattermore(). Default is c(512, 512).

order

logical. Whether to plot higher loading cells on top of cells with lower loading values in the dimensionality reduction plots (Default = FALSE).

plot_dimreduc

logical. Whether to plot factor loadings on dimensionality reduction coordinates. Default is TRUE.

save_plots

logical. Whether to save plots. Default is TRUE

file_path

directory file path and/or file name prefix. Defaults to current wd.

file_name

name suffix to append after sample name.

return_plots

logical. Whether or not to return plots to the environment. (Default is FALSE)

cells.highlight

Names of specific cells to highlight in plot (black) (default NULL).

reorder_datasets

New order to plot datasets in for the factor plots if different from current factor level order in cell.data slot. Only for older style liger objects.

ggplot_default_colors

logical. If colors_use_factors = NULL, Whether or not to return plot using default ggplot2 "hue" palette instead of default "varibow" palette.

color_seed

random seed for the palette shuffle if colors_use_factors = NULL. Default = 123.

## Not run: 
plotFactors_scCustom(liger_object = liger_obj, return_plots = FALSE, plot_dimreduc = TRUE,
raster = FALSE, save_plots = TRUE)
## End(Not run)

scCustomize_Palette(
 num_groups,
 ggplot_default_colors = FALSE,
 color_seed = 123
)

num_groups

number of groups to be plotted. If ggplot_default_colors = FALSE then by default:

• If number of levels plotted equal to 2 then colors will be NavyAndOrange().

• If number of levels plotted greater than 2 but less than or equal to 36 it will use "polychrome" from DiscretePalette_scCustomize().

• If greater than 36 will use "varibow" with shuffle = TRUE from DiscretePalette_scCustomize.

ggplot_default_colors

logical. Whether to use default ggplot hue palette or not.

color_seed

random seed to use for shuffling the "varibow" palette.

cols <- scCustomize_Palette(num_groups = 24, ggplot_default_colors = FALSE)
PalettePlot(pal= cols)

seq_zeros(seq_length, num_zeros = NULL)

seq_length

a seqeunce or numbers of numbers to create sequence. Users can provide sequence (1:XX) or number of values to add in sequence (will be used as second number in seq_len; 1:XX).

num_zeros

number of zeros to prefix sequence, default is (e.g, 01, 02, 03, ...)

# Using sequence
new_seq <- seq_zeros(seq_length = 1:15, num_zeros = 1)
new_seq
# Using number
new_seq <- seq_zeros(seq_length = 15, num_zeros = 1)
new_seq
# Sequence with 2 zeros
new_seq <- seq_zeros(seq_length = 1:15, num_zeros = 2)
new_seq

theme_ggprism_mod(
 palette = "black_and_white",
 base_size = 14,
 base_family = "sans",
 base_fontface = "bold",
 base_line_size = base_size/20,
 base_rect_size = base_size/20,
 axis_text_angle = 0,
 border = FALSE
)

palette

string. Palette name, use names(ggprism_data$themes) to show all valid palette names.

base_size

numeric. Base font size, given in "pt".

base_family

string. Base font family, default is "sans".

base_fontface

string. Base font face, default is "bold".

base_line_size

numeric. Base linewidth for line elements

base_rect_size

numeric. Base linewidth for rect elements

axis_text_angle

integer. Angle of axis text in degrees. One of: ⁠0, 45, 90, 270⁠.

border

logical. Should a border be drawn around the plot? Clipping will occur unless e.g. coord_cartesian(clip = "off") is used.

# Generate a plot and customize theme
library(ggplot2)
df <- data.frame(x = rnorm(n = 100, mean = 20, sd = 2), y = rbinom(n = 100, size = 100, prob = 0.2))
p <- ggplot(data = df, mapping = aes(x = x, y = y)) + geom_point(mapping = aes(color = 'red'))
p + theme_ggprism_mod()

viridis_plasma_dark_high
viridis_plasma_light_high
viridis_inferno_dark_high
viridis_inferno_light_high
viridis_magma_dark_high
viridis_magma_light_high
viridis_dark_high
viridis_light_high

## Not run: 
FeaturePlot_scCustom(object = seurat_object, features = "Cx3cr1",
colors_use = viridis_plasma_dark_high, na_color = "lightgray")
## End(Not run)