Cell profile matrices
A “cell profile matrix” is a pre-defined matrix that specifies the expected expression profiles of each cell type in the experiment. The SpatialDecon library comes with one such matrix pre-loaded, the “SafeTME” matrix, designed for estimation of immune and stroma cells in the tumor microenvironment. (This matrix was designed to avoid genes commonly expressed by cancer cells; see the SpatialDecon manuscript for details.)
Let’s take a glance at the safeTME matrix:
data("safeTME")
data("safeTME.matches")
signif(safeTME[seq_len(3), seq_len(3)], 2)
#> macrophages mast B.naive
#> A2M 0.8500 0.044 0.0043
#> ABCB1 0.0021 0.023 0.0250
#> ABCB4 0.0044 0.000 0.2200
heatmap(sweep(safeTME, 1, apply(safeTME, 1, max), "/"),
labRow = NA, margins = c(10, 5))
The safeTME cell profile matrix
For studies of other tissue types, we have provided a library of cell profile matrices, available on Github and downloadable with the “download_profile_matrix” function.
For a complete list of matrices, see CellProfileLibrary GitHub Page.
Below we download a matrix of cell profiles derived from scRNA-seq of a mouse spleen.
mousespleen <- download_profile_matrix(species = "Mouse",
age_group = "Adult",
matrixname = "Spleen_MCA")
dim(mousespleen)
#> [1] 11125 9
mousespleen[1:4,1:4]
#> Dendritic.cell.S100a4.high Dendritic.cell.Siglech.high
#> 0610009B22Rik 0.02985075 0.0000000
#> 0610010F05Rik 0.00000000 0.0000000
#> 0610010K14Rik 0.02985075 0.0000000
#> 0610012G03Rik 0.08955224 0.1111111
#> Granulocyte Macrophage
#> 0610009B22Rik 0.00000000 0.00000000
#> 0610010F05Rik 0.00000000 0.00000000
#> 0610010K14Rik 0.00000000 0.03846154
#> 0610012G03Rik 0.08571429 0.03846154
head(cellGroups)
#> $Dendritic
#> [1] "Dendritic.cell.S100a4.high" "Dendritic.cell.Siglech.high"
#>
#> $Granulocyte
#> [1] "Granulocyte"
#>
#> $Macrophage
#> [1] "Macrophage"
#>
#> $`Marginal zone B`
#> [1] "Marginal.zone.B.cell"
#>
#> $Monocyte
#> [1] "Monocyte"
#>
#> $NK
#> [1] "NK.cell"
metadata
#> Profile Matrix Tissue Species Strain Age Age Group
#> 33 MCA Spleen Mouse C57BL/6 6-10 weeks Adult
#> URL
#> 33 https://pubmed.ncbi.nlm.nih.gov/29474909/
#> Citation
#> 33 Han, X. et al. Mapping the Mouse Cell Atlas by Microwell-Seq. Cell172, 1091-1107.e17 (2018).
heatmap(sweep(mousespleen, 1, apply(mousespleen, 1, max), "/"),
labRow = NA, margins = c(10, 5), cexCol = 0.7)
The Mouse Spleen profile matrix
For studies where the provided cell profile matrices aren’t sufficient or if a specific single cell dataset is wanted, we can make a custom profile matrix using the function create_profile_matrix().
This mini single cell dataset is a fraction of the data from Kinchen, J. et al. Structural Remodeling of the Human Colonic Mesenchyme in Inflammatory Bowel Disease. Cell 175, 372-386.e17 (2018).
data("mini_singleCell_dataset")
mini_singleCell_dataset$mtx@Dim # genes x cells
#> [1] 1814 250
as.matrix(mini_singleCell_dataset$mtx)[1:4,1:4]
#> ACTGCTCGTAAGTTCC.S90 TGAAAGAAGGCGCTCT.S66 AGCTTGAGTTTGGGCC.S66
#> PLEKHN1 0 0 0
#> PERM1 0 0 0
#> C1orf159 0 0 0
#> TTLL10 0 0 0
#> ACGGCCATCGTCTGAA.S66
#> PLEKHN1 0
#> PERM1 0
#> C1orf159 0
#> TTLL10 0
head(mini_singleCell_dataset$annots)
#> CellID LabeledCellType
#> 2660 ACTGCTCGTAAGTTCC.S90 stromal cell
#> 2162 TGAAAGAAGGCGCTCT.S66 glial cell
#> 368 AGCTTGAGTTTGGGCC.S66 endothelial cell
#> 238 ACGGCCATCGTCTGAA.S66 stromal cell
#> 4158 TCTCTAACACTGTTAG.S90 stromal cell
#> 2611 ACGATGTGTGTGGTTT.S90 stromal cell
table(mini_singleCell_dataset$annots$LabeledCellType)
#>
#> endothelial cell glial cell
#> 14 12
#> pericyte cell plasma cell
#> 3 30
#> smooth muscle cell of colon stromal cell
#> 1 190Pericyte cell and smooth muscle cell of colon will be dropped from this matrix due to low cell count. The average expression across all cells of one type is returned so the more cells of one type, the better reflection of the true gene expression. The confidence in these averages can be changed using the minCellNum filter.
custom_mtx <- create_profile_matrix(mtx = mini_singleCell_dataset$mtx, # cell x gene count matrix
cellAnnots = mini_singleCell_dataset$annots, # cell annotations with cell type and cell name as columns
cellTypeCol = "LabeledCellType", # column containing cell type
cellNameCol = "CellID", # column containing cell ID/name
matrixName = "custom_mini_colon", # name of final profile matrix
outDir = NULL, # path to desired output directory, set to NULL if matrix should not be written
normalize = FALSE, # Should data be normalized?
minCellNum = 5, # minimum number of cells of one type needed to create profile, exclusive
minGenes = 10, # minimum number of genes expressed in a cell, exclusive
scalingFactor = 5, # what should all values be multiplied by for final matrix
discardCellTypes = TRUE) # should cell types be filtered for types like mitotic, doublet, low quality, unknown, etc.
#> [1] "Creating Atlas"
#> [1] "1 / 6 : stromal cell"
#> [1] "2 / 6 : glial cell"
#> [1] "3 / 6 : endothelial cell"
#> [1] "4 / 6 : plasma cell"
#> [1] "5 / 6 : pericyte cell"
#> Warning in create_profile_matrix(mtx = mini_singleCell_dataset$mtx, cellAnnots = mini_singleCell_dataset$annots, :
#> pericyte cell was dropped from matrix because it didn't have enough viable cells based on current filtering thresholds.
#> If this cell type is necessary consider changing minCellNum or minGenes
#> [1] "6 / 6 : smooth muscle cell of colon"
#> Warning in create_profile_matrix(mtx = mini_singleCell_dataset$mtx, cellAnnots = mini_singleCell_dataset$annots, :
#> smooth muscle cell of colon was dropped from matrix because it didn't have enough viable cells based on current filtering thresholds.
#> If this cell type is necessary consider changing minCellNum or minGenes
head(custom_mtx)
#> stromal cell glial cell endothelial cell plasma cell
#> PLEKHN1 0.0000000 0 0.0000000 0.05787067
#> PERM1 0.1167131 0 0.0000000 0.00000000
#> C1orf159 0.0000000 0 0.0000000 0.07922668
#> TTLL10 0.0000000 0 0.1853931 0.00000000
#> TAS1R3 0.0000000 0 0.0000000 0.07039008
#> ATAD3C 0.1219237 0 0.0000000 0.07922668
heatmap(sweep(custom_mtx, 1, apply(custom_mtx, 1, max), "/"),
labRow = NA, margins = c(10, 5), cexCol = 0.7)
Custom profile matrix
Custom matrices can be created from all single cell data classes as long as a counts matrix and cell annotations can be passed to the function. Here is an example of creating a matrix using a Seurat object.
library(SeuratObject)
data("mini_singleCell_dataset")
rownames(mini_singleCell_dataset$annots) <- mini_singleCell_dataset$annots$CellID
seuratObject <- CreateSeuratObject(counts = mini_singleCell_dataset$mtx, meta.data = mini_singleCell_dataset$annots)
Idents(seuratObject) <- seuratObject$LabeledCellType
rm(mini_singleCell_dataset)
annots <- data.frame(cbind(cellType=as.character(Idents(seuratObject)),
cellID=names(Idents(seuratObject))))
custom_mtx_seurat <- create_profile_matrix(mtx = seuratObject@assays$RNA@counts,
cellAnnots = annots,
cellTypeCol = "cellType",
cellNameCol = "cellID",
matrixName = "custom_mini_colon",
outDir = NULL,
normalize = FALSE,
minCellNum = 5,
minGenes = 10)
#> [1] "Creating Atlas"
#> [1] "1 / 6 : stromal cell"
#> [1] "2 / 6 : glial cell"
#> [1] "3 / 6 : endothelial cell"
#> [1] "4 / 6 : plasma cell"
#> [1] "5 / 6 : pericyte cell"
#> Warning in create_profile_matrix(mtx = seuratObject@assays$RNA@counts, cellAnnots = annots, :
#> pericyte cell was dropped from matrix because it didn't have enough viable cells based on current filtering thresholds.
#> If this cell type is necessary consider changing minCellNum or minGenes
#> [1] "6 / 6 : smooth muscle cell of colon"
#> Warning in create_profile_matrix(mtx = seuratObject@assays$RNA@counts, cellAnnots = annots, :
#> smooth muscle cell of colon was dropped from matrix because it didn't have enough viable cells based on current filtering thresholds.
#> If this cell type is necessary consider changing minCellNum or minGenes
head(custom_mtx_seurat)
#> stromal cell glial cell endothelial cell plasma cell
#> PLEKHN1 0.0000000 0 0.0000000 0.05787067
#> PERM1 0.1167131 0 0.0000000 0.00000000
#> C1orf159 0.0000000 0 0.0000000 0.07922668
#> TTLL10 0.0000000 0 0.1853931 0.00000000
#> TAS1R3 0.0000000 0 0.0000000 0.07039008
#> ATAD3C 0.1219237 0 0.0000000 0.07922668
paste("custom_mtx and custom_mtx_seurat are identical", all(custom_mtx == custom_mtx_seurat))
#> [1] "custom_mtx and custom_mtx_seurat are identical TRUE"
