Contents

1 Introduction

The bluster package provides a flexible and extensible framework for clustering in Bioconductor packages/workflows. At its core is the clusterRows() generic that controls dispatch to different clustering algorithms. We will demonstrate on some single-cell RNA sequencing data from the scRNAseq package; our aim is to cluster cells into cell populations based on their PC coordinates.

library(scRNAseq)
sce <- ZeiselBrainData()

# Trusting the authors' quality control, and going straight to normalization.
library(scuttle)
sce <- logNormCounts(sce)

# Feature selection based on highly variable genes.
library(scran)
dec <- modelGeneVar(sce)
hvgs <- getTopHVGs(dec, n=1000)

# Dimensionality reduction for work (PCA) and pleasure (t-SNE).
set.seed(1000)
library(scater)
sce <- runPCA(sce, ncomponents=20, subset_row=hvgs)
sce <- runUMAP(sce, dimred="PCA")

mat <- reducedDim(sce, "PCA")
dim(mat)
## [1] 3005   20

2 Based on distance matrices

2.1 Hierarchical clustering

Our first algorithm is good old hierarchical clustering, as implemented using hclust() from the stats package. This automatically sets the cut height to half the dendrogram height.

library(bluster)
hclust.out <- clusterRows(mat, HclustParam())
plotUMAP(sce, colour_by=I(hclust.out))

Advanced users can achieve greater control of the procedure by passing more parameters to the HclustParam() constructor. Here, we use Ward’s criterion for the agglomeration with a dynamic tree cut from the dynamicTreeCut package.

hp2 <- HclustParam(method="ward.D2", cut.dynamic=TRUE)
hp2
## class: HclustParam
## metric: [default]
## method: ward.D2
## cut.fun: cutreeDynamic
## cut.params(0):
hclust.out <- clusterRows(mat, hp2)
plotUMAP(sce, colour_by=I(hclust.out))

2.2 Affinity propagation

Another option is to use affinity propagation, as implemented using the apcluster package. Here, messages are passed between observations to decide on a set of exemplars, each of which form the center of a cluster.

This is not particularly fast as it involves the calculation of a square similarity matrix between all pairs of observations. So, we’ll speed it up by taking analyzing a subset of the data:

set.seed(1000)
sub <- sce[,sample(ncol(sce), 200)]
ap.out <- clusterRows(reducedDim(sub), AffinityParam())
plotUMAP(sub, colour_by=I(ap.out))