mmDS {muscat}R Documentation

DS analysis using mixed-models (MM)

Description

Performs cluster-wise DE analysis by fitting cell-level models.

Usage

mmDS(
  x,
  coef = NULL,
  covs = NULL,
  method = c("dream2", "dream", "vst", "poisson", "nbinom", "hybrid"),
  n_cells = 10,
  n_samples = 2,
  min_count = 1,
  min_cells = 20,
  n_threads = 1,
  verbose = TRUE,
  vst = c("sctransform", "DESeq2"),
  ddf = c("Satterthwaite", "Kenward-Roger", "lme4"),
  dup_corr = FALSE,
  trended = FALSE,
  bayesian = FALSE,
  blind = TRUE,
  REML = TRUE,
  moderate = FALSE
)

.mm_dream(
  x,
  coef = NULL,
  covs = NULL,
  dup_corr = FALSE,
  trended = FALSE,
  ddf = c("Satterthwaite", "Kenward-Roger"),
  n_threads = 1,
  verbose = FALSE
)

.mm_dream2(
  x,
  coef = NULL,
  covs = NULL,
  ddf = c("Satterthwaite", "Kenward-Roger"),
  n_threads = 1,
  verbose = FALSE
)

.mm_vst(
  x,
  vst = c("sctransform", "DESeq2"),
  coef = NULL,
  covs = NULL,
  bayesian = FALSE,
  blind = TRUE,
  REML = TRUE,
  ddf = c("Satterthwaite", "Kenward-Roger", "lme4"),
  n_threads = 1,
  verbose = FALSE
)

.mm_glmm(
  x,
  coef = NULL,
  covs = NULL,
  n_threads = 1,
  family = c("poisson", "nbinom"),
  verbose = TRUE,
  moderate = FALSE
)

Arguments

x

a SingleCellExperiment.

coef

character specifying the coefficient to test. If NULL (default), will test the last level of "group_id".

covs

character vector of colData(x) column names to use as covariates.

method

a character string. Either "dream2" (default, lme4 with voom-weights), "dream" (previous implementation of the dream method), "vst" (variance-stabilizing transformation), "poisson" (poisson GLM-MM), "nbinom" (negative binomial GLM-MM), "hybrid" (combination of pseudobulk and poisson methods) or a function accepting the same arguments.

n_cells

number of cells per cluster-sample required to consider a sample for testing.

n_samples

number of samples per group required to consider a cluster for testing.

min_count

numeric. For a gene to be tested in a given cluster, at least min_cells must have a count >= min_count.

min_cells

number (or fraction, if < 1) of cells with a count > min_count required for a gene to be tested in a given cluster.

n_threads

number of threads to use.

verbose

logical specifying whether messages on progress and a progress bar should be displayed.

vst

method to use as variance-stabilizing transformations. "sctransform" for vst; "DESeq2" for varianceStabilizingTransformation.

ddf

character string specifying the method for estimating the effective degrees of freedom. For method = "dream", either "Satterthwaite" (faster) or "Kenward-Roger" (more accurate); see ?variancePartition::dream for details. For method = "vst", method "lme4" is also valid; see contest.lmerModLmerTest.

dup_corr

logical; whether to use duplicateCorrelation.

trended

logical; whether to use expression-dependent variance priors in eBayes.

bayesian

logical; whether to use bayesian mixed models.

blind

logical; whether to ignore experimental design for the vst.

REML

logical; whether to maximize REML instead of log-likelihood.

moderate

logical; whether to perform empirical Bayes moderation.

family

character string specifying which GLMM to fit: "poisson" for bglmer, "nbinom" for glmmTMB.

Details

The .mm_* functions (e.g. .mm_dream) expect cells from a single cluster, and do not perform filtering or handle incorrect parameters well. Meant to be called by mmDS with method = c("dream", "vst") and vst = c("sctransform", "DESeq2") to be applied across all clusters.

method = "dream2"

variancePartition's (>=1.14.1) voom-lme4-implementation of mixed models for RNA-seq data; function dream.

method = "dream"

variancePartition's older voom-lme4-implementation of mixed models for RNA-seq data; function dream.

method = "vst"
vst = "sctransform"

lmer or blmer mixed models on vst transformed counts.

vst = "DESeq2"

varianceStabilizingTransformation followed by lme4 mixed models.

Value

a data.frame

Functions

Author(s)

Pierre-Luc Germain & Helena L Crowell

References

Crowell, HL, Soneson, C, Germain, P-L, Calini, D, Collin, L, Raposo, C, Malhotra, D & Robinson, MD: On the discovery of population-specific state transitions from multi-sample multi-condition single-cell RNA sequencing data. bioRxiv 713412 (2018). doi: https://doi.org/10.1101/713412

Examples

data(sce)
# subset "B cells" cluster
sce <- sce[, sce$cluster_id == "B cells"]
sce$cluster_id <- droplevels(sce$cluster_id)

# downsample to 100 genes
gs <- sample(nrow(sce), 100)
sce <- sce[gs, ]

res <- mmDS(sce, method = "dream",
    n_threads = 2, verbose = FALSE)
head(res$`B cells`)
[Package muscat version 1.2.1 Index]