Package 'monocle3'

Description

Creates a matrix with aggregated expression values for arbitrary groups of genes

Usage

aggregate_gene_expression(
  cds,
  gene_group_df = NULL,
  cell_group_df = NULL,
  norm_method = c("log", "binary", "size_only"),
  pseudocount = 1,
  scale_agg_values = TRUE,
  max_agg_value = 3,
  min_agg_value = -3,
  exclude.na = TRUE,
  gene_agg_fun = "sum",
  cell_agg_fun = "mean"
)

Arguments

Value

A matrix of dimension NxM, where N is the number of gene groups and M is the number of cell groups.

Examples

## Not run: 
     expression_matrix <- readRDS(system.file('extdata',
                                               'worm_l2/worm_l2_expression_matrix.rds',
                                               package='monocle3'))
     cell_metadata <- readRDS(system.file('extdata',
                              'worm_l2/worm_l2_coldata.rds',
                               package='monocle3'))
     gene_metadata <- readRDS(system.file('extdata',
                              'worm_l2/worm_l2_rowdata.rds',
                              package='monocle3'))

     cds <- new_cell_data_set(expression_data=expression_matrix,
                              cell_metadata=cell_metadata,
                              gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds, num_dim = 100)
    cds <- reduce_dimension(cds)
    cds <- cluster_cells(cds, resolution=1e-5)
    colData(cds)$assigned_cell_type <- as.character(partitions(cds))
    colData(cds)$assigned_cell_type <- dplyr::recode(colData(cds)$assigned_cell_type,
                                                    "1"="Germline",
                                                    "2"="Body wall muscle",
                                                    "3"="Unclassified neurons",
                                                    "4"="Vulval precursors",
                                                    "5"="Failed QC",
                                                    "6"="Seam cells",
                                                    "7"="Pharyngeal epithelia",
                                                    "8"="Coelomocytes",
                                                    "9"="Am/PH sheath cells",
                                                    "10"="Failed QC",
                                                    "11"="Touch receptor neurons",
                                                    "12"="Intestinal/rectal muscle",
                                                    "13"="Pharyngeal neurons",
                                                    "14"="NA",
                                                    "15"="flp-1(+) interneurons",
                                                    "16"="Canal associated neurons",
                                                    "17"="Ciliated sensory neurons",
                                                    "18"="Other interneurons",
                                                    "19"="Pharyngeal gland",
                                                    "20"="Failed QC",
                                                    "21"="Ciliated sensory neurons",
                                                    "22"="Oxygen sensory neurons",
                                                    "23"="Ciliated sensory neurons",
                                                    "24"="Ciliated sensory neurons",
                                                    "25"="Ciliated sensory neurons",
                                                    "26"="Ciliated sensory neurons",
                                                    "27"="Oxygen sensory neurons",
                                                    "28"="Ciliated sensory neurons",
                                                    "29"="Unclassified neurons",
                                                    "30"="Socket cells",
                                                    "31"="Failed QC",
                                                    "32"="Pharyngeal gland",
                                                    "33"="Ciliated sensory neurons",
                                                    "34"="Ciliated sensory neurons",
                                                    "35"="Ciliated sensory neurons",
                                                    "36"="Failed QC",
                                                    "37"="Ciliated sensory neurons",
                                                    "38"="Pharyngeal muscle")
    neurons_cds <- cds[,grepl("neurons", colData(cds)$assigned_cell_type, ignore.case=TRUE)]
    pr_graph_test_res <- graph_test(neurons_cds, neighbor_graph="knn")
    pr_deg_ids <- row.names(subset(pr_graph_test_res, q_value < 0.05))
    gene_module_df <- find_gene_modules(neurons_cds[pr_deg_ids,], resolution=1e-2)
    cell_group_df <- tibble::tibble(cell=row.names(colData(neurons_cds)),
                                    cell_group=partitions(cds)[colnames(neurons_cds)])
    agg_mat <- aggregate_gene_expression(neurons_cds, gene_module_df, cell_group_df)
  
## End(Not run)

Description

Data sets that contain cells from different groups often benefit from alignment to subtract differences between them. Alignment can be used to remove batch effects, subtract the effects of treatments, or even potentially compare across species. align_cds executes alignment and stores these adjusted coordinates.

This function can be used to subtract both continuous and discrete batch effects. For continuous effects, align_cds fits a linear model to the cells' PCA or LSI coordinates and subtracts them using Limma. For discrete effects, you must provide a grouping of the cells, and then these groups are aligned using Batchelor, a "mutual nearest neighbor" algorithm described in:

Haghverdi L, Lun ATL, Morgan MD, Marioni JC (2018). "Batch effects in single-cell RNA-sequencing data are corrected by matching mutual nearest neighbors." Nat. Biotechnol., 36(5), 421-427. doi: 10.1038/nbt.4091

Usage

align_cds(
  cds,
  preprocess_method = c("PCA", "LSI"),
  alignment_group = NULL,
  alignment_k = 20,
  residual_model_formula_str = NULL,
  verbose = FALSE,
  build_nn_index = FALSE,
  nn_control = list(),
  ...
)

Arguments

Value

an updated cell_data_set object

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
   
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")

Description

align_transform is not supported. Co-embed your data sets if you need batch correction.

Usage

align_transform(cds, reduction_method = c("Aligned"))

Arguments

Value

The cds is returned without processing.

Description

Function to automatically learn the structure of data by either using L1-graph or the spanning-tree formulization

Usage

calc_principal_graph(
  X,
  C0,
  maxiter = 10,
  eps = 1e-05,
  L1.gamma = 0.5,
  L1.sigma = 0.01,
  verbose = TRUE
)

Arguments

Value

a list of X, C, W, P, objs X is the input data C is the centers for principal graph W is the principal graph matrix P is the cluster assignment matrix objs is the objective value for the function

Description

The main class used by Monocle3 to hold single-cell expression data. cell_data_set extends the Bioconductor SingleCellExperiment class.

Details

This class is initialized from a matrix of expression values along with cell and feature metadata.

Fields

reduce_dim_aux

SimpleList, auxiliary information from reduced dimension.

principal_graph_aux

SimpleList, auxiliary information from principal graph construction

principal_graph

SimpleList of igraph objects containing principal graphs for different dimensionality reduction.

clusters

SimpleList of cluster information for different dimensionality reduction.

Description

Methods for the cell_data_set class

Arguments

Description

Choose cells interactively to subset a cds

Usage

choose_cells(
  cds,
  reduction_method = c("UMAP", "tSNE", "PCA", "Aligned"),
  clear_cds = FALSE,
  return_list = FALSE
)

Arguments

Value

A subset CDS object. If return_list = FALSE, a list of cell names.

Description

Choose cells along the path of a principal graph

Usage

choose_graph_segments(
  cds,
  reduction_method = "UMAP",
  starting_pr_node = NULL,
  ending_pr_nodes = NULL,
  return_list = FALSE,
  clear_cds = TRUE
)

Arguments

Value

A subset CDS object. If return_list = FALSE, a list of cell and graph node names.

Description

Function to clear all CDS slots besides colData, rowData and expression data.

Usage

clear_cds_slots(cds)

Arguments

Value

A cell_data_set with only expression, rowData and colData present.

Description

Unsupervised clustering of cells is a common step in many single-cell expression workflows. In an experiment containing a mixture of cell types, each cluster might correspond to a different cell type. This function takes a cell_data_set as input, clusters the cells using Louvain/Leiden community detection, and returns a cell_data_set with internally stored cluster assignments. In addition to clusters this function calculates partitions, which represent superclusters of the Louvain/Leiden communities that are found using a kNN pruning method. Cluster assignments can be accessed using the clusters function and partition assignments can be accessed using the partitions function.

Usage

cluster_cells(
  cds,
  reduction_method = c("UMAP", "tSNE", "PCA", "LSI", "Aligned"),
  k = 20,
  cluster_method = c("leiden", "louvain"),
  num_iter = 2,
  partition_qval = 0.05,
  weight = FALSE,
  resolution = NULL,
  random_seed = 42,
  verbose = FALSE,
  nn_control = list(),
  ...
)

Arguments

Value

an updated cell_data_set object, with cluster and partition information stored internally and accessible using clusters and partitions

References

Rodriguez, A., & Laio, A. (2014). Clustering by fast search and find of density peaks. Science, 344(6191), 1492-1496. doi:10.1126/science.1242072

Vincent D. Blondel, Jean-Loup Guillaume, Renaud Lambiotte, Etienne Lefebvre: Fast unfolding of communities in large networks. J. Stat. Mech. (2008) P10008

V. A. Traag and L. Waltman and N. J. van Eck: From Louvain to Leiden: guaranteeing well-connected communities. Scientific Reports, 9(1) (2019). doi: 10.1038/s41598-019-41695-z.

Jacob H. Levine and et. al. Data-Driven Phenotypic Dissection of AML Reveals Progenitor-like Cells that Correlate with Prognosis. Cell, 2015.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                             'worm_embryo/worm_embryo_rowdata.rds',
                             package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                 'worm_embryo/worm_embryo_expression_matrix.rds',
                                 package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- reduce_dimension(cds)
    cds <- cluster_cells(cds)

Description

Generic to extract clusters from CDS object

Usage

clusters(x, reduction_method = "UMAP")

Arguments

Value

Clusters.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- reduce_dimension(cds)
    cds <- cluster_cells(cds)
    clusters_factors <- clusters(cds, "UMAP")

Description

Method to extract clusters from CDS object

Usage

## S4 method for signature 'cell_data_set'
clusters(x, reduction_method = "UMAP")

Arguments

Value

Clusters.

Description

Extracts a table of coefficients from a tibble containing model objects. It tests whether each coefficient differs significantly from zero under the Wald test and adjusts the p-values for multiple hypothesis testing using the method of Benjamini and Hochberg, placing these adjusted values in the q-value column.

Usage

coefficient_table(model_tbl)

Arguments

Value

A table of coefficient data for each gene.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
   
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds, num_dim=50)
    cds <- align_cds(cds, alignment_group = "batch",
                     residual_model_formula_str = "~ bg.300.loading + bg.400.loading +
                     bg.500.1.loading + bg.500.2.loading + bg.r17.loading +
                     bg.b01.loading + bg.b02.loading")
    cds <- reduce_dimension(cds)
    ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
    cds_subset <- cds[rowData(cds)$gene_short_name %in% ciliated_genes,]
    gene_fits <- fit_models(cds_subset, model_formula_str = "~embryo.time")
    fit_coefs <- coefficient_table(gene_fits)

Description

This function will combine a list of cell_data_set objects into a new cell_data_set object.

Usage

combine_cds(
  cds_list,
  keep_all_genes = TRUE,
  cell_names_unique = FALSE,
  sample_col_name = "sample",
  keep_reduced_dims = FALSE
)

Arguments

Value

A combined cell_data_set object.

Description

Compares goodness of fit for two ways of fitting a set of genes' expression using a likelihood ratio test. The likelihood ratio test helps one decide whether the improvement in fit is large enough to justify the additional complexity of extra terms in the full model in comparison to the reduced model.

Usage

compare_models(model_tbl_full, model_tbl_reduced)

Arguments

Value

The result of a likelihood test by gene.

Description

For each gene in a cell_data_set object, detect_genes counts how many cells are expressed above a minimum threshold. In addition, for each cell, detect_genes counts the number of genes above this threshold that are detectable. Results are added as columns num_cells_expressed and num_genes_expressed in the rowData and colData tables respectively.

Usage

detect_genes(cds, min_expr = 0)

Arguments

Value

Updated cell_data_set object

Examples

## Not run: 
   cds <- detect_genes(cds, min_expr=0.1)

## End(Not run)

Description

Function to calculate size factors for single-cell RNA-seq data

Usage

estimate_size_factors(
  cds,
  round_exprs = TRUE,
  method = c("mean-geometric-mean-total", "mean-geometric-mean-log-total")
)

Arguments

Value

Updated cell_data_set object with a new colData column called 'Size_Factor'.

Examples

cds <- load_a549()
    colData(cds)[['Size_Factor']] <- NULL
    cds <- estimate_size_factors(cds)

Description

Evaluate_fits takes a tibble created by the fit_models function and returns a table that assists with evaluating how well the model explains the gene expression data.

Usage

evaluate_fits(model_tbl)

Arguments

Value

A table with fit information on each gene.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
   
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds, num_dim=50)
    cds <- align_cds(cds, alignment_group = "batch",
                     residual_model_formula_str = "~ bg.300.loading + bg.400.loading +
                     bg.500.1.loading + bg.500.2.loading + bg.r17.loading + bg.b01.loading +
                     bg.b02.loading")
    cds <- reduce_dimension(cds)
    ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
    cds_subset <- cds[rowData(cds)$gene_short_name %in% ciliated_genes,]
    gene_fits <- fit_models(cds_subset, model_formula_str = "~embryo.time")
    evaluate_fits(gene_fits)

Description

Generic to access cds count matrix

Usage

exprs(x)

Arguments

Value

Count matrix.

Examples

cds <- load_a549()
   exprs(cds)

Description

Method to access cds count matrix

Usage

## S4 method for signature 'cell_data_set'
exprs(x)

Arguments

Value

Count matrix.

Description

Generic to access cds rowData table

Usage

fData(x)

Arguments

Value

rowData table.

Examples

cds <- load_a549()
    fData(cds)

Description

Method to access cds rowData table

Usage

## S4 method for signature 'cell_data_set'
fData(x)

Arguments

Value

rowData table.

Examples

cds <- load_a549()
    fData(cds)

Description

Generic to set cds rowData table

Usage

fData(x) <- value

Arguments

Value

x.

Examples

cds <- load_a549()
    fData(cds)[['row_index']] <- seq(nrow(fData(cds)))

Description

Method to set cds rowData table

Usage

## S4 replacement method for signature 'cell_data_set'
fData(x) <- value

Arguments

Value

x.

Description

Cluster genes into modules that are co-expressed across cells.

Usage

find_gene_modules(
  cds,
  reduction_method = c("UMAP"),
  max_components = 2,
  umap.metric = "cosine",
  umap.min_dist = 0.1,
  umap.n_neighbors = 15L,
  umap.fast_sgd = FALSE,
  umap.nn_method = "annoy",
  k = 20,
  leiden_iter = 1,
  partition_qval = 0.05,
  weight = FALSE,
  resolution = NULL,
  random_seed = 0L,
  cores = 1,
  verbose = FALSE,
  preprocess_method = c("PCA", "LSI"),
  nn_control = list(),
  ...
)

Arguments

Value

A dataframe with genes and the modules to which they are assigned.

Examples

## Not run: 
     expression_matrix <- readRDS(system.file('extdata',
                                              'worm_l2/worm_l2_expression_matrix.rds',
                                              package='monocle3'))
     cell_metadata <- readRDS(system.file('extdata',
                                          'worm_l2/worm_l2_coldata.rds',
                                          package='monocle3'))
     gene_metadata <- readRDS(system.file('extdata',
                                          'worm_l2/worm_l2_rowdata.rds',
                                          package='monocle3'))

     cds <- new_cell_data_set(expression_data=expression_matrix,
                              cell_metadata=cell_metadata,
                              gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds, num_dim = 100)
    cds <- reduce_dimension(cds)
    cds <- cluster_cells(cds, resolution=1e-5)
    colData(cds)$assigned_cell_type <- as.character(partitions(cds))
    colData(cds)$assigned_cell_type <- dplyr::recode(colData(cds)$assigned_cell_type,
                                                    "1"="Germline",
                                                    "2"="Body wall muscle",
                                                    "3"="Unclassified neurons",
                                                    "4"="Vulval precursors",
                                                    "5"="Failed QC",
                                                    "6"="Seam cells",
                                                    "7"="Pharyngeal epithelia",
                                                    "8"="Coelomocytes",
                                                    "9"="Am/PH sheath cells",
                                                    "10"="Failed QC",
                                                    "11"="Touch receptor neurons",
                                                    "12"="Intestinal/rectal muscle",
                                                    "13"="Pharyngeal neurons",
                                                    "14"="NA",
                                                    "15"="flp-1(+) interneurons",
                                                    "16"="Canal associated neurons",
                                                    "17"="Ciliated sensory neurons",
                                                    "18"="Other interneurons",
                                                    "19"="Pharyngeal gland",
                                                    "20"="Failed QC",
                                                    "21"="Ciliated sensory neurons",
                                                    "22"="Oxygen sensory neurons",
                                                    "23"="Ciliated sensory neurons",
                                                    "24"="Ciliated sensory neurons",
                                                    "25"="Ciliated sensory neurons",
                                                    "26"="Ciliated sensory neurons",
                                                    "27"="Oxygen sensory neurons",
                                                    "28"="Ciliated sensory neurons",
                                                    "29"="Unclassified neurons",
                                                    "30"="Socket cells",
                                                    "31"="Failed QC",
                                                    "32"="Pharyngeal gland",
                                                    "33"="Ciliated sensory neurons",
                                                    "34"="Ciliated sensory neurons",
                                                    "35"="Ciliated sensory neurons",
                                                    "36"="Failed QC",
                                                    "37"="Ciliated sensory neurons",
                                                    "38"="Pharyngeal muscle")
    neurons_cds <- cds[,grepl("neurons", colData(cds)$assigned_cell_type, ignore.case=TRUE)]
    pr_graph_test_res <- graph_test(neurons_cds, neighbor_graph="knn")
    pr_deg_ids <- row.names(subset(pr_graph_test_res, q_value < 0.05))
    gene_module_df <- find_gene_modules(neurons_cds[pr_deg_ids,], resolution=1e-2)
  
## End(Not run)

Description

This function fits a generalized linear model for each gene in a cell_data_set. Formulae can be provided to account for additional covariates (e.g. day collected, genotype of cells, media conditions, etc).

Usage

fit_models(
  cds,
  model_formula_str,
  expression_family = "quasipoisson",
  reduction_method = "UMAP",
  cores = 1,
  clean_model = TRUE,
  verbose = FALSE,
  ...
)

Arguments

Value

a tibble where the rows are genes and columns are

• id character vector from rowData(cds)$id

• gene_short_names character vector from rowData(cds)$gene_short_names

• num_cells_expressed int vector from rowData(cds)$num_cells_expressed

• gene_id character vector from row.names(rowData(cds))'

• model GLM model list returned by speedglm

• model_summary model summary list returned by summary(model)

• status character vector of model fitting status: OK when model converged, otherwise FAIL

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
   
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds, num_dim=50)
    cds <- align_cds(cds, alignment_group = "batch",
                     residual_model_formula_str = "~ bg.300.loading + bg.400.loading +
                     bg.500.1.loading + bg.500.2.loading + bg.r17.loading + bg.b01.loading +
                     bg.b02.loading")
    cds <- reduce_dimension(cds)
    ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
    cds_subset <- cds[rowData(cds)$gene_short_name %in% ciliated_genes,]
    gene_fits <- fit_models(cds_subset, model_formula_str = "~embryo.time")

Description

Try to replace NA values left in a query cell_data_set after running transfer_cell_labels.

Usage

fix_missing_cell_labels(
  cds,
  reduction_method = c("UMAP", "PCA", "LSI"),
  from_column_name,
  to_column_name = from_column_name,
  out_notna_models_dir = NULL,
  k = 10,
  nn_control = list(),
  top_frac_threshold = 0.5,
  top_next_ratio_threshold = 1.5,
  verbose = FALSE
)

Arguments

Details

fix_missing_cell_labels uses non-NA cell data values in the query cell_data_set to replace NAs in nearby cells. It partitions the cells into a set with NA and a set with non-NA column data values. It makes a nearest neighbor index using cells with non-NA values, and for each cell with NA, it tries to find an acceptable non-NA column data value as follows. If more than top_frac_threshold fraction of them have the same value, it replaces the NA with it. If not, it checks whether the ratio of the most frequent to the second most frequent values is at least top_next_ratio_threshold, in which case it copies the most frequent value. Otherwise, it leaves the NA.

Value

an updated cell_data_set object

Examples

## Not run: 
     expression_matrix <- readRDS(system.file('extdata',
                                              'worm_l2/worm_l2_expression_matrix.rds',
                                              package='monocle3'))
     cell_metadata <- readRDS(system.file('extdata',
                                          package='monocle3'))
     gene_metadata <- readRDS(system.file('extdata',
                                          'worm_l2/worm_l2_rowdata.rds',
                                          package='monocle3'))

     cds <- new_cell_data_set(expression_data=expression_matrix,
                              cell_metadata=cell_metadata,
                              gene_metadata=gene_metadata)

    ncell <- nrow(colData(cds))
    cell_sample <- sample(seq(ncell), 2 * ncell / 3)
    cell_set <- seq(ncell) %in% cell_sample
    cds1 <- cds[,cell_set]
    cds1 <- preprocess_cds(cds1)
    cds1 <- reduce_dimension(cds1, build_nn_index=TRUE)
    save_transform_models(cds1, 'tm')

    cds2 <- cds[,!cell_set]
    cds2 <- load_transform_models(cds2, 'tm')
    cds2 <- preprocess_transform(cds2, 'PCA')
    cds2 <- reduce_dimension_transform(cds2)
    cds2 <- transfer_cell_labels(cds2, 'UMAP', colData(cds1), 'cao_cell_type', 'transfer_cell_type')
    cds2 <- fix_missing_cell_labels(cds2, 'UMAP', 'transfer_cell_type', 'fixed_cell_type')
  
## End(Not run)

Description

Function to reproduce the behavior of eye function in matlab

Usage

generate_centers(X, W, P, param.gamma)

Arguments

Value

A matrix C for the centers for principal graph

Description

Generate a Garnett marker file from top_markers output.

Usage

generate_garnett_marker_file(
  marker_test_res,
  file = "./marker_file.txt",
  max_genes_per_group = 10,
  remove_duplicate_genes = FALSE
)

Arguments

Value

None, marker file is written to file parameter location.

Description

Access citations for methods used during analysis.

Usage

get_citations(cds)

Arguments

Value

A data frame with the methods used and the papers to be cited.

Examples

{
  ## Not run: 
     get_citations(cds)
  
## End(Not run)
}

Description

Get a genome from Cell Ranger output

Usage

get_genome_in_matrix_path(matrix_path, genome = NULL)

Arguments

Value

A string representing the genome found

Description

We are often interested in finding genes that are differentially expressed across a single-cell trajectory. Monocle3 introduces a new approach for finding such genes that draws on a powerful technique in spatial correlation analysis, the Moran’s I test. Moran’s I is a measure of multi-directional and multi-dimensional spatial autocorrelation. The statistic tells you whether cells at nearby positions on a trajectory will have similar (or dissimilar) expression levels for the gene being tested. Although both Pearson correlation and Moran’s I ranges from -1 to 1, the interpretation of Moran’s I is slightly different: +1 means that nearby cells will have perfectly similar expression; 0 represents no correlation, and -1 means that neighboring cells will be anti-correlated.

Usage

graph_test(
  cds,
  neighbor_graph = c("knn", "principal_graph"),
  reduction_method = "UMAP",
  k = 25,
  method = c("Moran_I"),
  alternative = "greater",
  expression_family = "quasipoisson",
  cores = 1,
  verbose = FALSE,
  nn_control = list()
)

Arguments

Value

a data frame containing the p values and q-values from the Moran's I test on the parallel arrays of models.

See Also

moran.test geary.test

Examples

expression_matrix <- readRDS(system.file('extdata',
                                               'worm_l2/worm_l2_expression_matrix.rds',
                                               package='monocle3'))
     cell_metadata <- readRDS(system.file('extdata',
                              'worm_l2/worm_l2_coldata.rds',
                               package='monocle3'))
     gene_metadata <- readRDS(system.file('extdata',
                              'worm_l2/worm_l2_rowdata.rds',
                              package='monocle3'))

     cds <- new_cell_data_set(expression_data=expression_matrix,
                              cell_metadata=cell_metadata,
                              gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds, num_dim = 100)
    cds <- reduce_dimension(cds)
    cds <- cluster_cells(cds, resolution=1e-5)
    colData(cds)$assigned_cell_type <- as.character(partitions(cds))
    colData(cds)$assigned_cell_type <- dplyr::recode(colData(cds)$assigned_cell_type,
                                                    "1"="Germline",
                                                    "2"="Body wall muscle",
                                                    "3"="Unclassified neurons",
                                                    "4"="Vulval precursors",
                                                    "5"="Failed QC",
                                                    "6"="Seam cells",
                                                    "7"="Pharyngeal epithelia",
                                                    "8"="Coelomocytes",
                                                    "9"="Am/PH sheath cells",
                                                    "10"="Failed QC",
                                                    "11"="Touch receptor neurons",
                                                    "12"="Intestinal/rectal muscle",
                                                    "13"="Pharyngeal neurons",
                                                    "14"="NA",
                                                    "15"="flp-1(+) interneurons",
                                                    "16"="Canal associated neurons",
                                                    "17"="Ciliated sensory neurons",
                                                    "18"="Other interneurons",
                                                    "19"="Pharyngeal gland",
                                                    "20"="Failed QC",
                                                    "21"="Ciliated sensory neurons",
                                                    "22"="Oxygen sensory neurons",
                                                    "23"="Ciliated sensory neurons",
                                                    "24"="Ciliated sensory neurons",
                                                    "25"="Ciliated sensory neurons",
                                                    "26"="Ciliated sensory neurons",
                                                    "27"="Oxygen sensory neurons",
                                                    "28"="Ciliated sensory neurons",
                                                    "29"="Unclassified neurons",
                                                    "30"="Socket cells",
                                                    "31"="Failed QC",
                                                    "32"="Pharyngeal gland",
                                                    "33"="Ciliated sensory neurons",
                                                    "34"="Ciliated sensory neurons",
                                                    "35"="Ciliated sensory neurons",
                                                    "36"="Failed QC",
                                                    "37"="Ciliated sensory neurons",
                                                    "38"="Pharyngeal muscle")
    neurons_cds <- cds[,grepl("neurons", colData(cds)$assigned_cell_type, ignore.case=TRUE)]
    pr_graph_test_res <- graph_test(cds, neighbor_graph="knn")

Description

Write the cell_data_set matrix and model identity information to stdout.

Usage

identity_table(cds)

Arguments

Details

A matrix identity is a checksum that is stored in the cell_data_set when a reduced dimension matrix is created and when certain functions read count matrices into the cell_data_set, such as load_mm_data(). At the same time, the same checksum is stored as the model identity in order to link the model to its matrix.

Additionally, Monocle3 stores the identity of the matrix from which the matrix was made. For example, in the case of a UMAP reduced dimension matrix made from a PCA reduced dimension matrix, the cell_data_set has the identities of both the UMAP and the PCA matrices. The UMAP identity is stored as 'matrix_id' and the PCA as 'prev_matrix_id'. Similarly, the model and the previous model identities are stored as 'model_id' and 'prev_model_id'. This allows one to trace a matrix to its origin, which may be helpful when a cell_data_set is partially reprocessed; for example, if preprocess_cds() is re-run but reduce_dimension() is not. Also, it may be helpful when transform models are loaded with the load_transform_models() function, in which case the matrix and model identities will differ.

The identity of the model used to transform a matrix is stored with the matrix identity information as 'model_id'. Ordinarily, the matrix 'matrix_id' and 'model_id' and the corresponding model 'model_id' will have the same string value. However, they differ when the preprocess_transform() and reduce_dim_transform() functions are used to transform a matrix.

Notes:

• Certain file and directory paths may be stored in the cell_data_set as identifiers.

• Checksums are calculated using the digest function in the digest package. The matrix dimensions are stored with the checksum.

• Matrix transformations such as subsetting and row and or column reordering do not affect the matrix identity.

• The matrix identity string is stored in the internal metadata slot of the cell_data_set and the model identity string is stored in the model object in the cds@reduce_dim_aux slot of the cell_data_set.

Value

Write identity information to stdout.

Examples

cds <- load_a549()
    cds <- preprocess_cds(cds)
    cds <- reduce_dimension(cds)
    identity_table(cds)

Description

Monocle3 aims to learn how cells transition through a biological program of gene expression changes in an experiment. Each cell can be viewed as a point in a high-dimensional space, where each dimension describes the expression of a different gene. Identifying the program of gene expression changes is equivalent to learning a trajectory that the cells follow through this space. However, the more dimensions there are in the analysis, the harder the trajectory is to learn. Fortunately, many genes typically co-vary with one another, and so the dimensionality of the data can be reduced with a wide variety of different algorithms. Monocle3 provides two different algorithms for dimensionality reduction via reduce_dimension (UMAP and tSNE). Both take a cell_data_set object and a number of dimensions allowed for the reduced space. You can also provide a model formula indicating some variables (e.g. batch ID or other technical factors) to "subtract" from the data so it doesn't contribute to the trajectory. The function learn_graph is the fourth step in the trajectory building process after preprocess_cds, reduce_dimension, and cluster_cells. After learn_graph, order_cells is typically called.

Usage

learn_graph(
  cds,
  use_partition = TRUE,
  close_loop = TRUE,
  learn_graph_control = NULL,
  verbose = FALSE
)

Arguments

Value

an updated cell_data_set object

Optional learn_graph_control parameters

euclidean_distance_ratio:

The maximal ratio between the euclidean distance of two tip nodes in the spanning tree and the maximum distance between any connecting points on the spanning tree allowed to be connected during the loop closure procedure. Default is 1.

geodesic_distance_ratio:

The minimal ratio between the geodesic distance of two tip nodes in the spanning tree and the length of the diameter path on the spanning tree allowed to be connected during the loop closure procedure. (Both euclidean_distance_ratio and geodesic_distance_ratio need to be satisfied to introduce the edge for loop closure). Default is 1/3.

minimal_branch_len:

The minimal length of the diameter path for a branch to be preserved during graph pruning procedure. Default is 10.

orthogonal_proj_tip:

Whether to perform orthogonal projection for cells corresponding to the tip principal points. Default is FALSE.

prune_graph:

Whether or not to perform an additional round of graph pruning to remove small insignificant branches. Default is TRUE.

scale:

ncenter:

nn.k:

Maximum number of nearest neighbors to compute in the reversed graph embedding. Set k=NULL to let learn_graph estimate k. Default is 25.

rann.k:

nn.k replaces rann.k but rann.k is available for compatibility with existing code.

maxiter:

eps:

L1.gamma:

L1.sigma:

nn.method:

The method to use for finding nearest neighbors. nn.method can be one of 'nn2', 'annoy', or 'hnsw'.

nn.metric:

The distance metric for the annoy or hnsw nearest neighbor index build. See help(set_nn_control) for more information.

nn.n_trees:

The number of trees used to build the annoy nearest neighbor index. See help(set_nn_control) for more information.

nn.search_k:

The number of nodes to search in an annoy index search. See help(set_nn_control) for more information.

nn.M:

Related to internal dimensionality of HNSW index. See help(set_nn_control) for more information.

nn.ef_construction:

Controls the HNSW index build speed/accuracy tradeoff.

nn.ef:

Controls the HNSW index search speed/accuracy tradeoff. See help(set_nn_control) for more information.

nn.grain_size:

Used by annoy and HNSW to set the minimum amount of work to do per thread. See help(set_nn_control) for more information.

nn.cores:

Used by annoy and HNSW to control the number of threads used. See help(set_nn_control) for more information.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")
    cds <- reduce_dimension(cds)
    cds <- cluster_cells(cds)
    cds <- learn_graph(cds)

Description

Build a small cell_data_set.

Usage

load_a549()

Value

cds object

Examples

cds <- load_a549()

Description

Loads cellranger data into a cell_data_set object. Note that if your dataset is from version 3.0 and contains non-Gene-Expression data (e.g. Antibodies or CRISPR features), only the Gene Expression data is returned.

Usage

load_cellranger_data(
  pipestance_path = NULL,
  genome = NULL,
  barcode_filtered = TRUE,
  umi_cutoff = 100
)

Arguments

Details

• the pipestance_path argument takes the name of a Cell Ranger output directory, in which it looks for the required data files, for example, pipestance_path=10x_data

• for Cell Ranger version 2 data, load_cellranger_data expects to find the required files barcodes.tsv, genes.tsv, and matrix.mtx in the directories as

  • 10x_data/outs/filtered_gene_bc_matrices//barcodes.tsv

  • 10x_data/outs/filtered_gene_bc_matrices//genes.tsv

  • 10x_data/outs/filtered_gene_bc_matrices//matrix.mtx

  where is the name of a genome. load_cellranger_data expects to find either a single genome directory in 10x_data/outs/filtered_gene_bc_matrices or a genome directory with the name given with the genome argument.

• for Cell Ranger version 3 data, load_cellranger_data expects to find the required files barcodes.tsv.gz, features.tsv.gz, and matrix.mtx.gz in the directories as

  • 10x_data/outs/filtered_feature_bc_matrix/barcodes.tsv.gz

  • 10x_data/outs/filtered_feature_bc_matrix/features.tsv.gz

  • 10x_data/outs/filtered_feature_bc_matrix/matrix.mtx.gz

• if any of the files is not in the expected directory, load_cellranger_data will terminate with an error

Value

a new cell_data_set object

Examples

cell_ranger_data <- system.file("extdata", "cell_ranger_3", package = "monocle3")
    gene_bc_matrix <- load_cellranger_data(cell_ranger_data)

Description

Load data from matrix market format files.

Usage

load_mm_data(
  mat_path,
  feature_anno_path,
  cell_anno_path,
  header = FALSE,
  feature_metadata_column_names = NULL,
  cell_metadata_column_names = NULL,
  umi_cutoff = 100,
  quote = "\"'",
  sep = "\t"
)

Arguments

Value

cds object

Comments

• load_mm_data estimates size factors.

Examples

pmat<-system.file("extdata", "matrix.mtx.gz", package = "monocle3")
    prow<-system.file("extdata", "features_c3h0.txt", package = "monocle3")
    pcol<-system.file("extdata", "barcodes_c2h0.txt", package = "monocle3")
    cds <- load_mm_data( pmat, prow, pcol,
                         feature_metadata_column_names =
                         c('gene_short_name', 'gene_biotype'), sep='' )

    # In this example, the features_c3h0.txt file has three columns,
    # separated by spaces. The first column has official gene names, the
    # second has short gene names, and the third has gene biotypes.

Description

Load a full Monocle3 cell_data_set, which was saved using save_monocle_objects. For more information read the help information for save_monocle_objects.

Usage

load_monocle_objects(directory_path)

Arguments

Value

a cell_data_set.

Examples

## Not run: 
    cds <- load_a549()
    save_monocle_objects(cds, 'mo')
    cds1 <- load_monocle_objects('mo')
  
## End(Not run)

Description

Load data from matrix market format

Usage

load_mtx_data(mat_path, gene_anno_path, cell_anno_path, umi_cutoff = 100)

Arguments

Value

cds object

Examples

pmat<-system.file("extdata", "matrix.mtx.gz", package = "monocle3")
    prow<-system.file("extdata", "features_c3h0.txt", package = "monocle3")
    pcol<-system.file("extdata", "barcodes_c2h0.txt", package = "monocle3")
    cds <- load_mtx_data( pmat, prow, pcol)

Description

Load transform models, which were saved using save_transform_models, into a cell_data_set. This function over-writes existing models in the cell_data_set. For more information read the help information for save_transform_models.

Usage

load_transform_models(cds, directory_path)

Arguments

Value

a cell_data_set with the transform models loaded by load_transform_models.

Examples

## Not run: 
    cds <- load_a549()
    cds <- preprocess_cds(cds)
    cds <- reduce_dimension(cds)
    save_transform_models(cds, 'tm')
    cds1 <- load_a549()
    cds1 <- load_transform_models(cds1, 'tm')
  
## End(Not run)

Description

Build a cell_data_set from C. elegans embryo data.

Usage

load_worm_embryo()

Value

cds object

Description

Build a cell_data_set from C. elegans L2 data.

Usage

load_worm_l2()

Value

cds object

Description

Make a nearest neighbor index from the specified reduction_method matrix in the cell_data_set using either the default nearest neighbor method or the method specified in the nn_control list parameter, and store the index in the cell_data_set. This function returns a cell_data_set.

Usage

make_cds_nn_index(
  cds,
  reduction_method = c("UMAP", "PCA", "LSI", "Aligned", "tSNE"),
  nn_control = list(),
  verbose = FALSE
)

Arguments

Value

a cell_data_set with the stored index.

Examples

cds <- load_a549()
    cds <- preprocess_cds(cds)
    cds <- make_cds_nn_index(cds, 'PCA')

Description

Make a nearest neighbor index from the subject_matrix using either the default nearest neighbor method or the method specified in the nn_control list parameter. The function returns the index.

Usage

make_nn_index(subject_matrix, nn_control = list(), verbose = FALSE)

Arguments

Value

a nearest neighbor index.

Examples

cds <- load_a549()
    cds <- preprocess_cds(cds)
    nn_index <- make_nn_index(SingleCellExperiment::reducedDims(cds)[['PCA']])

Description

mc_es_apply computes the row-wise or column-wise results of FUN, just like esApply. Variables in colData from cds are available in FUN.

Usage

mc_es_apply(
  cds,
  MARGIN,
  FUN,
  required_packages,
  cores = 1,
  convert_to_dense = TRUE,
  reduction_method = "UMAP",
  ...
)

Arguments

Value

The result of with(colData(cds) apply(counts(cds)), MARGIN, FUN, ...))

Description

Predict new data values and return as a matrix

Usage

model_predictions(model_tbl, new_data, type = "response")

Arguments

Value

Prediction matrix.

Description

Create a new cell_data_set object.

Usage

new_cell_data_set(expression_data, cell_metadata = NULL, gene_metadata = NULL)

Arguments

Value

a new cell_data_set object

Examples

small_a549_colData_df <- readRDS(system.file("extdata",
                                               "small_a549_dex_pdata.rda",
                                               package = "monocle3"))
  small_a549_rowData_df <- readRDS(system.file("extdata",
                                               "small_a549_dex_fdata.rda",
                                               package = "monocle3"))
  small_a549_exprs <- readRDS(system.file("extdata",
                                          "small_a549_dex_exprs.rda",
                                          package = "monocle3"))
  small_a549_exprs <- small_a549_exprs[,row.names(small_a549_colData_df)]

  cds <- new_cell_data_set(expression_data = small_a549_exprs,
                           cell_metadata = small_a549_colData_df,
                           gene_metadata = small_a549_rowData_df)

Description

Return a size-factor normalized and (optionally) log-transformed expression matrix

Usage

normalized_counts(
  cds,
  norm_method = c("log", "binary", "size_only"),
  pseudocount = 1
)

Arguments

Value

Size-factor normalized, and optionally log-transformed, expression matrix.

Examples

cds <- load_a549()
    normalized_matrix <- normalized_counts(cds)

Description

Assigns cells a pseudotime value based on their projection on the principal graph learned in the learn_graph function and the position of chosen root states. This function takes as input a cell_data_set and returns it with pseudotime information stored internally. order_cells() optionally takes "root" state(s) in the form of cell or principal graph node IDs, which you can use to specify the start of the trajectory. If you don't provide a root state, an plot will be generated where you can choose the root state(s) interactively. The trajectory will be composed of segments.

Usage

order_cells(
  cds,
  reduction_method = "UMAP",
  root_pr_nodes = NULL,
  root_cells = NULL,
  verbose = FALSE
)

Arguments

Value

an updated cell_data_set object.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")
    cds <- reduce_dimension(cds)
    cds <- cluster_cells(cds)
    cds <- learn_graph(cds)
    cds <- order_cells(cds, root_pr_nodes='Y_21')

Description

Generic to extract partitions from CDS object

Usage

partitions(x, reduction_method = "UMAP")

Arguments

Value

Partitions.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- reduce_dimension(cds)
    cds <- cluster_cells(cds)
    partitions_factors <- partitions(cds, "UMAP")

Description

Method to extract partitions from CDS object

Usage

## S4 method for signature 'cell_data_set'
partitions(x, reduction_method = "UMAP")

Arguments

Value

Partitions.

Description

Generic to access cds colData table

Usage

pData(x)

Arguments

Value

colData.

Examples

cds <- load_a549()
    pData(cds)

Description

Method to access cds colData table

Usage

## S4 method for signature 'cell_data_set'
pData(x)

Arguments

Value

colData.

Description

Generic to set cds colData table

Usage

pData(x) <- value

Arguments

Value

x.

Examples

cds <- load_a549()
    pData(cds)[['row_index']] <- seq(nrow(pData(cds)))

Description

Method to set cds colData table

Usage

## S4 replacement method for signature 'cell_data_set'
pData(x) <- value

Arguments

Value

x.

Examples

cds <- load_a549()
    pData(cds)[['row_index']] <- seq(nrow(pData(cds)))

Description

Plots the cells along with their trajectories.

Usage

plot_cells(
  cds,
  x = 1,
  y = 2,
  reduction_method = c("UMAP", "tSNE", "PCA", "LSI", "Aligned"),
  color_cells_by = "cluster",
  group_cells_by = "cluster",
  genes = NULL,
  show_trajectory_graph = TRUE,
  trajectory_graph_color = "grey28",
  trajectory_graph_segment_size = 0.75,
  norm_method = c("log", "size_only"),
  label_cell_groups = TRUE,
  label_groups_by_cluster = TRUE,
  group_label_size = 2,
  labels_per_group = 1,
  label_branch_points = TRUE,
  label_roots = TRUE,
  label_leaves = TRUE,
  graph_label_size = 2,
  cell_size = 0.35,
  cell_stroke = I(cell_size/2),
  alpha = 1,
  min_expr = 0.1,
  rasterize = FALSE,
  scale_to_range = TRUE,
  label_principal_points = FALSE
)

Arguments

Value

a ggplot2 plot object

Examples

## Not run: 
    lung <- load_A549()
    plot_cells(lung)
    plot_cells(lung, color_cells_by="log_dose")
    plot_cells(lung, markers="GDF15")
  
## End(Not run)

Description

Plot a dataset and trajectory in 3 dimensions

Usage

plot_cells_3d(
  cds,
  dims = c(1, 2, 3),
  reduction_method = c("UMAP", "tSNE", "PCA", "LSI", "Aligned"),
  color_cells_by = "cluster",
  genes = NULL,
  show_trajectory_graph = TRUE,
  trajectory_graph_color = "black",
  trajectory_graph_segment_size = 5,
  norm_method = c("log", "size_only"),
  color_palette = NULL,
  color_scale = "Viridis",
  cell_size = 25,
  alpha = 1,
  min_expr = 0.1
)

Arguments

Value

a plotly plot object

Examples

## Not run: 
plot_cells_3d(cds, markers=c("Rbfox3, Neurod1", "Sox2"))

## End(Not run)

Description

Create a dot plot to visualize the mean gene expression and percentage of expressed cells in each group of cells

Usage

plot_genes_by_group(
  cds,
  markers,
  group_cells_by = "cluster",
  reduction_method = "UMAP",
  norm_method = c("log", "size_only"),
  lower_threshold = 0,
  max.size = 10,
  ordering_type = c("cluster_row_col", "maximal_on_diag", "none"),
  axis_order = c("group_marker", "marker_group"),
  flip_percentage_mean = FALSE,
  pseudocount = 1,
  scale_max = 3,
  scale_min = -3,
  color_by_group = FALSE
)

Arguments

Value

a ggplot2 plot object

Description

Plots expression for one or more genes as a function of pseudotime

Usage

plot_genes_in_pseudotime(
  cds_subset,
  min_expr = NULL,
  cell_size = 0.75,
  nrow = NULL,
  ncol = 1,
  panel_order = NULL,
  color_cells_by = "pseudotime",
  trend_formula = "~ splines::ns(pseudotime, df=3)",
  label_by_short_name = TRUE,
  vertical_jitter = NULL,
  horizontal_jitter = NULL
)

Arguments

Value

a ggplot2 plot object

Description

Accepts a subset of a cell_data_set and an attribute to group cells by, and produces a ggplot2 object that plots the level of expression for each group of cells.

Usage

plot_genes_violin(
  cds_subset,
  group_cells_by = NULL,
  min_expr = 0,
  nrow = NULL,
  ncol = 1,
  panel_order = NULL,
  label_by_short_name = TRUE,
  normalize = TRUE,
  log_scale = TRUE,
  pseudocount = 0
)

Arguments

Value

a ggplot2 plot object

Examples

cds <- load_a549()
    cds_subset <- cds[row.names(subset(rowData(cds),
                     gene_short_name %in% c("ACTA1", "ID1", "CCNB2"))),]
    plot_genes_violin(cds_subset, group_cells_by="culture_plate", ncol=2,
                      min_expr=0.1)

Description

Plots the fraction of variance explained by the each component based on PCA from the normalized expression data determined using preprocess_cds. This is the fraction of the component variance relative to the variance of the components retained in the PCA; not the total variance.

Usage

plot_pc_variance_explained(cds)

Arguments

Value

ggplot object.

Examples

cds <- load_a549()
    cds <- preprocess_cds(cds)
    plot_pc_variance_explained(cds)

Description

@description Accepts a subset cell_data_set and the parameter group_cells_by, used for dividing cells into groups. Returns one or more bar graphs (one graph for each gene in the cell_data_set). Each graph shows the percentage (or number) of cells that express a gene in each sub-group in the cell_data_set.

Usage

plot_percent_cells_positive(
  cds_subset,
  group_cells_by = NULL,
  min_expr = 0,
  nrow = NULL,
  ncol = 1,
  panel_order = NULL,
  plot_as_count = FALSE,
  label_by_short_name = TRUE,
  normalize = TRUE,
  plot_limits = NULL,
  bootstrap_samples = 100,
  conf_int_alpha = 0.95
)

Arguments

Value

a ggplot2 plot object

Examples

cds <- load_a549()
    cds_subset <- cds[row.names(subset(rowData(cds),
                                      gene_short_name %in% c("NDRG4", "HBG2"))),]
    plot_percent_cells_positive(cds_subset, group_cells_by="culture_plate")

Description

Most analyses (including trajectory inference, and clustering) in Monocle3, require various normalization and preprocessing steps. preprocess_cds executes and stores these preprocessing steps.

Specifically, depending on the options selected, preprocess_cds first normalizes the data by log and size factor to address depth differences, or by size factor only. Next, preprocess_cds calculates a lower dimensional space that will be used as the input for further dimensionality reduction like tSNE and UMAP.

Usage

preprocess_cds(
  cds,
  method = c("PCA", "LSI"),
  num_dim = 50,
  norm_method = c("log", "size_only", "none"),
  use_genes = NULL,
  pseudo_count = NULL,
  scaling = TRUE,
  verbose = FALSE,
  build_nn_index = FALSE,
  nn_control = list()
)

Arguments

Value

an updated cell_data_set object

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)
    cds <- preprocess_cds(cds)

Description

Applies a previously calculated preprocess transform model to a new count matrix. For more information read the help information for save_transform_models.

Usage

preprocess_transform(
  cds,
  reduction_method = c("PCA", "LSI"),
  block_size = NULL,
  cores = 1
)

Arguments

Value

a cell_data_set with a preprocess reduced count matrix.

Preprocessing notes

Filtering:

apply the same filters to the query and reference data set. For example, use the same UMI cutoff value for both data sets. You can check the cutoff value by finding the range of UMI values before applying normalization using range(counts(cds)).

Size factors:

use the same method and round_exprs parameters to calculate the Size_Factor values for both data sets. See the estimate_size_factors() help for additional information.

Troubleshooting:

if the projection fails, try comparing histograms of various values of the reference and query data sets. For example, in order to examine the size factor values use hist(colData(cds)[['Size_Factor']], breaks=100).

Examples

## Not run: 
    cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
   
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    ncell <- nrow(colData(cds))
    cell_sample <- sample(seq(ncell), 2 * ncell / 3)
    cell_set <- seq(ncell) %in% cell_sample
    cds1 <- cds[,cell_set]
    cds1 <- preprocess_cds(cds1)
    save_transform_models(cds1, 'tm')
    cds2 <- cds[,!cell_set]
    cds2 <- load_transform_models(cds2, 'tm')
    cds2 <- preprocess_transform(cds2, 'PCA')
  
## End(Not run)

Description

Generic to extract principal graph from CDS

Usage

principal_graph(x)

Arguments

Value

Principle graph.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")
   cds <- reduce_dimension(cds)
   ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
   cds <- cluster_cells(cds)
   cds <- learn_graph(cds)
   pr_gr <- principal_graph(cds)

Description

Generic to extract principal graph auxiliary information from CDS

Usage

principal_graph_aux(x)

Arguments

Value

Principal graph auxiliary information.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")
   cds <- reduce_dimension(cds)
   ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
   cds <- cluster_cells(cds)
   cds <- learn_graph(cds)
   pr_gr_aux <- principal_graph_aux(cds)

Description

Method to extract principal graph auxiliary information from CDS

Usage

## S4 method for signature 'cell_data_set'
principal_graph_aux(x)

Arguments

Value

Principal graph auxiliary information.

Description

Generic to set principal graph auxiliary information into CDS

Usage

principal_graph_aux(x) <- value

Arguments

Value

x.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")
   cds <- reduce_dimension(cds)
   ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
   cds <- cluster_cells(cds)
   cds <- learn_graph(cds)
   pr_gr_aux <- principal_graph_aux(cds)
   principal_graph_aux(cds) <- NULL
   principal_graph_aux(cds) <- pr_gr_aux

Description

Method to set principal graph auxiliary information into CDS

Usage

## S4 replacement method for signature 'cell_data_set'
principal_graph_aux(x) <- value

Arguments

Value

x.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")
   cds <- reduce_dimension(cds)
   ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
   cds <- cluster_cells(cds)
   cds <- learn_graph(cds)
   pr_gr_aux <- principal_graph_aux(cds)
   principal_graph_aux(cds) <- NULL
   principal_graph_aux(cds) <- pr_gr_aux

Description

Method to extract principal graph from CDS

Usage

## S4 method for signature 'cell_data_set'
principal_graph(x)

Arguments

Value

Principle graph.

Description

Generic to set principal graph to CDS

Usage

principal_graph(x) <- value

Arguments

Value

x.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")
   cds <- reduce_dimension(cds)
   ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
   cds <- cluster_cells(cds)
   cds <- learn_graph(cds)
   pr_gr <- principal_graph(cds)
   principal_graph(cds) <- NULL
   principal_graph(cds) <- pr_gr

Description

Generic to set principal graph to CDS

Usage

## S4 replacement method for signature 'cell_data_set'
principal_graph(x) <- value

Arguments

Value

x.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- align_cds(cds, alignment_group =
                     "batch", residual_model_formula_str = "~ bg.300.loading +
                      bg.400.loading + bg.500.1.loading + bg.500.2.loading +
                      bg.r17.loading + bg.b01.loading + bg.b02.loading")
   cds <- reduce_dimension(cds)
   ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
   cds <- cluster_cells(cds)
   cds <- learn_graph(cds)
   pr_gr <- principal_graph(cds)
   principal_graph(cds) <- NULL
   principal_graph(cds) <- pr_gr

Description

Generic to extract pseudotime from CDS object

Usage

pseudotime(x, reduction_method = "UMAP")

Arguments

Value

Pseudotime values.

Examples

cell_metadata <- readRDS(system.file('extdata',
                            'worm_embryo/worm_embryo_coldata.rds',
                            package='monocle3'))
   gene_metadata <- readRDS(system.file('extdata',
                                        'worm_embryo/worm_embryo_rowdata.rds',
                                        package='monocle3'))
   expression_matrix <- readRDS(system.file('extdata',
                                            'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))

   cds <- new_cell_data_set(expression_data=expression_matrix,
                            cell_metadata=cell_metadata,
                            gene_metadata=gene_metadata)

   cds <- preprocess_cds(cds, num_dim=50)
   cds <- align_cds(cds, alignment_group = "batch",
                    residual_model_formula_str = "~ bg.300.loading + bg.400.loading +
                    bg.500.1.loading + bg.500.2.loading + bg.r17.loading + bg.b01.loading +
                    bg.b02.loading")
   cds <- reduce_dimension(cds) 
   ciliated_genes <- c("che-1", "hlh-17", "nhr-6", "dmd-6", "ceh-36", "ham-1")
   cds <- cluster_cells(cds)
   cds <- learn_graph(cds)
   cds <- order_cells(cds,root_pr_nodes='Y_27')
   ps_tim <- pseudotime(cds)

Description

Method to extract pseudotime from CDS object

Usage

## S4 method for signature 'cell_data_set'
pseudotime(x, reduction_method = "UMAP")

Arguments

Value

Pseudotime values.

Description

Monocle3 aims to learn how cells transition through a biological program of gene expression changes in an experiment. Each cell can be viewed as a point in a high-dimensional space, where each dimension describes the expression of a different gene. Identifying the program of gene expression changes is equivalent to learning a trajectory that the cells follow through this space. However, the more dimensions there are in the analysis, the harder the trajectory is to learn. Fortunately, many genes typically co-vary with one another, and so the dimensionality of the data can be reduced with a wide variety of different algorithms. Monocle3 provides two different algorithms for dimensionality reduction via reduce_dimension (UMAP and tSNE). The function reduce_dimension is the second step in the trajectory building process after preprocess_cds.

UMAP is implemented from the package uwot.

Usage

reduce_dimension(
  cds,
  max_components = 2,
  reduction_method = c("UMAP", "tSNE", "PCA", "LSI", "Aligned"),
  preprocess_method = NULL,
  umap.metric = "cosine",
  umap.min_dist = 0.1,
  umap.n_neighbors = 15L,
  umap.fast_sgd = FALSE,
  umap.nn_method = "annoy",
  verbose = FALSE,
  cores = 1,
  build_nn_index = FALSE,
  nn_control = list(),
  ...
)

Arguments

Value

an updated cell_data_set object

References

UMAP: McInnes, L, Healy, J, UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction, ArXiv e-prints 1802.03426, 2018

tSNE: Laurens van der Maaten and Geoffrey Hinton. Visualizing data using t-SNE. J. Mach. Learn. Res., 9(Nov):2579– 2605, 2008.

Examples

cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)

    cds <- preprocess_cds(cds)
    cds <- reduce_dimension(cds)

Description

Applies a previously calculated reduce_dimension transform model to a new preprocess transformed matrix. For more information read the help information for save_transform_models.

Usage

reduce_dimension_transform(
  cds,
  preprocess_method = NULL,
  reduction_method = c("UMAP")
)

Arguments

Value

a cell_data_set with a transformed reduced count matrix.

Examples

## Not run: 
    cell_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_coldata.rds',
                                         package='monocle3'))
    gene_metadata <- readRDS(system.file('extdata',
                                         'worm_embryo/worm_embryo_rowdata.rds',
                                         package='monocle3'))
    expression_matrix <- readRDS(system.file('extdata',
                                             'worm_embryo/worm_embryo_expression_matrix.rds',
                                             package='monocle3'))
    cds <- new_cell_data_set(expression_data=expression_matrix,
                             cell_metadata=cell_metadata,
                             gene_metadata=gene_metadata)
    ncell <- nrow(colData(cds))
    cell_sample <- sample(seq(ncell), 2 * ncell / 3)
    cell_set <- seq(ncell) %in% cell_sample
    cds1 <- cds[,cell_set]
    cds1 <- preprocess_cds(cds1)
    cds1 <- reduce_dimension(cds1)
    save_transform_models(cds1, 'tm')
    cds2 <- cds[,!cell_set]
    cds2 <- load_transform_models(cds2, 'tm')
    cds2 <- preprocess_transform(cds2, 'PCA')
    cds2 <- reduce_dimension_transform(cds2)
  
## End(Not run)

Description

function to reproduce the behavior of repmat function in matlab to replicate and tile an matrix

Usage

repmat(X, m, n)

Arguments

Value

a matrix

Description

Save a Monocle3 full cell_data_set to a specified directory by writing the R objects to RDS files and the nearest neighbor indexes to index files. The assays objects are saved as HDF5Array files when hdf5_assays=TRUE or when the cell_data_set assays are HDF5Array objects. If any assay in the cell_data set is an HDF5 object, all assays must be. When save_monocle_objects is run with hdf5_assays=TRUE, the load_monocle_objects function loads the saved assays into HDF5Array objects in the resulting cell_data_set. Note: operations such as preprocess_cds that are run on assays stored as HDF5Arrays are much, much slower than the same operations run on assays stored as in-memory matrices. You may want to investigate parameters related to the Bioconductor DelayedArray and BiocParallel packages in this case.

Usage

save_monocle_objects(
  cds,
  directory_path,
  hdf5_assays = FALSE,
  comment = "",
  verbose = TRUE
)

Arguments

Value

none.

Examples

## Not run: 
    cds <- load_a549()
    save_monocle_objects(cds, 'mo')
  
## End(Not run)

Description

Save the transform models in the cell_data_set to the specified directory by writing the R objects to RDS files and the nearest neighbor indexes to index files. save_transform_models saves transform models made by running the preprocess_cds and reduce_dimension functions on an initial cell_data_set. Subsequent cell_data_sets are transformed into the reduced dimension space of the initial cell_data_set by loading the new data into a new cell_data_set, loading the initial data set transform models into the new cell_data_set using the load_transform_models function, and applying those transform models to the new data set using the preprocess_transform and reduce_dimension_transform functions. In this case, do not run the preprocess_cds or reduce_dimension functions on the new cell_data_set. Additionally, save_transform_models saves nearest neighbor indexes when the preprocess_cds and reduce_dimension functions are run with the make_nn_index=TRUE parameter. These indexes are used to find matches between cells in the new processed cell_data_set and the initial cell_data_set using index search functions. For more information see the help for transfer_cell_labels. save_transform_models saves the models to a directory given by directory_path.

Usage

save_transform_models(cds, directory_path, comment = "", verbose = TRUE)

Arguments

Value

none.

Examples

## Not run: 
    cds <- load_a549()
    cds <- preprocess_cds(cds)
    cds <- reduce_dimension(cds)
    save_transform_models(cds, 'tm')
  
## End(Not run)

Description

Search a nearest neighbor index for cells near those in the query_matrix.

Usage

search_cds_nn_index(
  query_matrix,
  cds,
  reduction_method = c("UMAP", "PCA", "LSI", "Aligned", "tSNE"),
  k = 25,
  nn_control = list(),
  verbose = FALSE
)

Arguments

Value

a list list(nn.idx, nn.dists) where nn.idx is a matrix of nearest neighbor indices and nn.dists is a matrix of the distance between the index given by the row number and the index given in nn.idx. If the same reduced dim matrix is used to make the index and search the index, the index given by the row number should be in the row, usually in the first column.

Examples

cds <- load_a549()
    cds <- preprocess_cds(cds)
    cds <- make_cds_nn_index(cds, 'PCA')
    nn_res <- search_cds_nn_index(SingleCellExperiment::reducedDims(cds)[['PCA']], cds, 'PCA', 10)

Description

Search a nearest neighbor index for cells near those in the query_matrix.

Usage

search_nn_index(
  query_matrix,
  nn_index,
  k = 25,
  nn_control = list(),
  verbose = FALSE
)

Arguments

Value

a list list(nn.idx, nn.dists) where nn.idx is a matrix of nearest neighbor indices and nn.dists is a matrix of the distance between the index given by the row number and the index given in nn.idx. If the same reduced dim matrix is used to make the index and search the index, the index given by the row number should be in the row, usually in the first column.

Examples

cds <- load_a549()
    cds <- preprocess_cds(cds)
    nn_index <- make_nn_index(SingleCellExperiment::reducedDims(cds)[['PCA']])
    nn_res <- search_nn_index(SingleCellExperiment::reducedDims(cds)[['PCA']], nn_index, 10)

Description

Make a nearest neighbors index using the subject matrix and search it for nearest neighbors to the query_matrix.

Usage

search_nn_matrix(
  subject_matrix,
  query_matrix,
  k = 25,
  nn_control = list(),
  verbose = FALSE
)

Arguments

Value

a list list(nn.idx, nn.dists) where nn.idx is a matrix of nearest neighbor indices and nn.dists is a matrix of the distance between the index given by the row number and the index given in nn.idx. If the query_matrix is the same as the subject matrix, the index given by the row number should be in the row, usually in the first column.

Description

Store the given nearest neighbor index in the cell_data_set. The reduction_method parameter tells set_cds_nn_index where in the cell_data_set to store the index.

Usage

set_cds_nn_index(
  cds,
  reduction_method = c("UMAP", "PCA", "LSI", "Aligned", "tSNE"),
  nn_index,
  verbose = FALSE
)

Arguments

Value

a cell_data_set with the stored index.