Benchmarking SignacFast with single cell flow-sorted data

Load data

Read the CEL-seq2 data.

ReadCelseq <- function(counts.file, meta.file) {
    E = suppressWarnings(readr::read_tsv(counts.file))
    gns <- E$gene
    E = E[, -1]
    E = Matrix::Matrix(as.matrix(E), sparse = TRUE)
    rownames(E) <- gns
    E
}

counts.file = "./fls/celseq_matrix_ru10_molecules.tsv.gz"
meta.file = "./fls/celseq_meta.immport.723957.tsv"

E = ReadCelseq(counts.file = counts.file, meta.file = meta.file)
M = suppressWarnings(readr::read_tsv(meta.file))

# filter data based on depth and number of genes detected
kmu = Matrix::colSums(E != 0)
kmu2 = Matrix::colSums(E)
E = E[, kmu > 200 & kmu2 > 500]

# filter by mitochondrial percentage
logik = grepl("^MT-", rownames(E))
MitoFrac = Matrix::colSums(E[logik, ])/Matrix::colSums(E) * 100
E = E[, MitoFrac < 20]

Seurat

Start with the standard pre-processing steps for a Seurat object.

library(Seurat)

Create a Seurat object, and then perform SCTransform normalization. Note:

You can use the legacy functions here (i.e., NormalizeData, ScaleData, etc.), use SCTransform or any other normalization method (including no normalization). We did not notice a significant difference in cell type annotations with different normalization methods.
We think that it is best practice to use SCTransform, but it is not a necessary step. Signac will work fine without it.

# load data
synovium <- CreateSeuratObject(counts = E, project = "FACs")

# run sctransform
synovium <- SCTransform(synovium)

Perform dimensionality reduction by PCA and UMAP embedding. Note:

Signac actually needs these functions since it uses the nearest neighbor graph generated by Seurat.

# These are now standard steps in the Seurat workflow for visualization and clustering
synovium <- RunPCA(synovium, verbose = FALSE)
synovium <- RunUMAP(synovium, dims = 1:30, verbose = FALSE)
synovium <- FindNeighbors(synovium, dims = 1:30, verbose = FALSE)

SignacX

library(SignacX)

Generate Signac labels for the Seurat object. Note:

Optionally, you can do parallel computing by setting num.cores > 1 in the Signac function.

labels <- Signac(synovium, num.cores = 4)
celltypes = GenerateLabels(labels, E = synovium)

Sometimes, training the neural networks takes a lot of time. The above classification took 27 minutes. To make a faster method, we implemented SignacFast which uses pre-trained models. Note:

SignacFast uses an ensemble of 1,800 pre-calculated neural networks using the GenerateModels function together with the training_HPCA reference data set.
Features that are absent from the single cell data and present in the neural network are set to zero.

# Run SignacFast
labels_fast <- SignacFast(synovium, num.cores = 4)
celltypes_fast = GenerateLabels(labels_fast, E = synovium)

Compare results:

Celltypes:

	B	MPh	NonImmune	Plasma.cells	TNK	Unclassified
B	681	0	0	0	0	0
MPh	0	835	0	0	0	68
NonImmune	0	0	2487	0	0	0
Plasma.cells	0	0	0	263	0	6
TNK	0	0	0	0	1768	0
Unclassified	0	13	7	0	0	174

Cellstates:

	B.memory	B.naive	Fibroblasts	Macrophages	Mon.Classical	NonImmune	Plasma.cells	T.CD4.memory	T.CD4.naive	T.CD8.em	T.CD8.naive	T.regs	Unclassified
B.memory	489	4	0	0	0	0	0	0	0	0	0	0	1
B.naive	4	184	0	0	0	0	0	0	0	0	0	0	0
DC	0	0	0	4	3	0	0	0	0	0	0	0	5
Fibroblasts	0	0	2110	0	0	136	0	0	0	0	0	0	0
Macrophages	0	0	0	662	33	1	0	0	0	0	0	0	73
Mon.Classical	0	0	0	23	93	0	0	0	0	0	0	0	1
NonImmune	0	0	74	0	0	166	0	0	0	0	0	0	2
Plasma.cells	0	0	0	0	0	1	259	0	0	0	0	0	8
T.CD4.memory	0	0	0	0	0	0	0	504	112	17	29	15	0
T.CD4.naive	0	0	0	0	0	0	0	0	309	4	18	0	1
T.CD8.em	0	0	0	0	1	0	0	7	4	574	1	0	2
T.CD8.naive	0	0	0	0	0	0	0	2	1	0	26	2	0
T.regs	0	0	0	0	0	0	0	0	27	1	2	106	0
Unclassified	0	0	1	12	3	5	0	0	0	1	0	0	179

Save results

saveRDS(synovium, file = "fls/seurat_obj_amp_synovium.rds")
saveRDS(celltypes, file = "fls/celltypes_amp_synovium.rds")
saveRDS(celltypes_fast, file = "fls/celltypes_fast_amp_synovium_celltypes.rds")

Session Info

## R version 4.0.3 (2020-10-10)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.5 LTS
## 
## Matrix products: default
## BLAS:   /usr/lib/x86_64-linux-gnu/blas/libblas.so.3.7.1
## LAPACK: /usr/lib/x86_64-linux-gnu/lapack/liblapack.so.3.7.1
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
##  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## loaded via a namespace (and not attached):
##  [1] compiler_4.0.3    magrittr_2.0.1    formatR_1.7       htmltools_0.5.1.1
##  [5] tools_4.0.3       yaml_2.2.1        stringi_1.5.3     rmarkdown_2.6    
##  [9] highr_0.8         knitr_1.30        stringr_1.4.0     digest_0.6.27    
## [13] xfun_0.20         rlang_0.4.10      evaluate_0.14

Benchmarking SignacFast with single cell flow-sorted data

Mathew Chamberlain

2021-11-18

Load data

Seurat

SignacX