1 Introduction

SpatialDE by Svensson et al., 2018, is a method to identify spatially variable genes (SVGs) in spatially resolved transcriptomics data.

2 Installation

You can install spatialDE from Bioconductor with the following code:

if (!requireNamespace("BiocManager", quietly = TRUE)) {
    install.packages("BiocManager")
}
BiocManager::install("spatialDE")

3 Example: Mouse Olfactory Bulb

Reproducing the example analysis from the original SpatialDE Python package.

library(spatialDE)
library(ggplot2)

3.1 Load data

Files originally retrieved from SpatialDE GitHub repository from the following links: https://github.com/Teichlab/SpatialDE/blob/master/Analysis/MouseOB/data/Rep11_MOB_0.csv https://github.com/Teichlab/SpatialDE/blob/master/Analysis/MouseOB/MOB_sample_info.csv

# Expression file used in python SpatialDE. 
data("Rep11_MOB_0")

# Sample Info file used in python SpatialDE
data("MOB_sample_info")

The Rep11_MOB_0 object contains spatial expression data for 16218 genes on 262 spots, with genes as rows and spots as columns.

Rep11_MOB_0[1:5, 1:5]
#>         16.92x9.015 16.945x11.075 16.97x10.118 16.939x12.132 16.949x13.055
#> Nrf1              1             0            0             1             0
#> Zbtb5             1             0            1             0             0
#> Ccnl1             1             3            1             1             0
#> Lrrfip1           2             2            0             0             3
#> Bbs1              1             2            0             4             0
dim(Rep11_MOB_0)
#> [1] 16218   262

The MOB_sample_info object contains a data.frame with coordinates for each spot.

head(MOB_sample_info)

3.1.1 Filter out pratically unobserved genes

Rep11_MOB_0 <- Rep11_MOB_0[rowSums(Rep11_MOB_0) >= 3, ]

3.1.2 Get total_counts for every spot

Rep11_MOB_0 <- Rep11_MOB_0[, row.names(MOB_sample_info)]
MOB_sample_info$total_counts <- colSums(Rep11_MOB_0)
head(MOB_sample_info)

3.1.3 Get coordinates from MOB_sample_info

X <- MOB_sample_info[, c("x", "y")]
head(X)

3.2 stabilize

The SpatialDE method assumes normally distributed data, so we stabilize the variance of the negative binomial distributed counts data using Anscombe’s approximation. The stabilize() function takes as input a data.frame of expression values with samples in columns and genes in rows. Thus, in this case, we have to transpose the data.

norm_expr <- stabilize(Rep11_MOB_0)
norm_expr[1:5, 1:5]
#>         16.92x9.015 16.945x11.075 16.97x10.118 16.939x12.132 16.949x13.055
#> Nrf1       1.227749     0.8810934    0.8810934     1.2277491     0.8810934
#> Zbtb5      1.227749     0.8810934    1.2277491     0.8810934     0.8810934
#> Ccnl1      1.227749     1.6889027    1.2277491     1.2277491     0.8810934
#> Lrrfip1    1.484676     1.4846765    0.8810934     0.8810934     1.6889027
#> Bbs1       1.227749     1.4846765    0.8810934     1.8584110     0.8810934

3.3 regress_out

Next, we account for differences in library size between the samples by regressing out the effect of the total counts for each gene using linear regression.

resid_expr <- regress_out(norm_expr, sample_info = MOB_sample_info)
resid_expr[1:5, 1:5]
#>         16.92x9.015 16.945x11.075 16.97x10.118 16.939x12.132 16.949x13.055
#> Nrf1    -0.75226760    -1.2352000   -1.0164479    -0.7903289    -1.0973214
#> Zbtb5    0.09242374    -0.3323719    0.1397144    -0.2760559    -0.2533134
#> Ccnl1   -2.77597162    -2.5903783   -2.6092012    -2.8529340    -3.1193883
#> Lrrfip1 -1.92331331    -2.1578718   -2.3849405    -2.5924072    -1.7163300
#> Bbs1    -1.12186063    -1.0266476   -1.3706460    -0.5363646    -1.4666155

3.4 run

To reduce running time, the SpatialDE test is run on a subset of 1000 genes. Running it on the complete data set takes about 10 minutes.

# For this example, run spatialDE on the first 1000 genes
sample_resid_expr <- head(resid_expr, 1000)

results <- spatialDE::run(sample_resid_expr, coordinates = X)
head(results[order(results$qval), ])

3.6 spatial_patterns

Furthermore, we can group spatially variable genes (SVGs) into spatial patterns using automatic expression histology (AEH).

sp <- spatial_patterns(
    sample_resid_expr,
    coordinates = X,
    de_results = de_results,
    n_patterns = 4L, length = 1.5
)
sp$pattern_results

3.7 Plots

Visualizing one of the most significant genes.

gene <- "Pcp4"

ggplot(data = MOB_sample_info, aes(x = x, y = y, color = norm_expr[gene, ])) +
    geom_point(size = 7) +
    ggtitle(gene) +
    scale_color_viridis_c() +
    labs(color = gene)

3.7.1 Plot Spatial Patterns of Multiple Genes

As an alternative to the previous figure, we can plot multiple genes using the normalized expression values.

ordered_de_results <- de_results[order(de_results$qval), ]

multiGenePlots(norm_expr,
    coordinates = X,
    ordered_de_results[1:6, ]$g,
    point_size = 4,
    viridis_option = "D",
    dark_theme = FALSE
)

3.8 Plot Fraction Spatial Variance vs Q-value

FSV_sig(results, ms_results)
#> Warning: ggrepel: 8 unlabeled data points (too many overlaps). Consider
#> increasing max.overlaps

4 SpatialExperiment integration

The SpatialDE workflow can also be executed with a SpatialExperiment object as input.

library(SpatialExperiment)

# For SpatialExperiment object, we neeed to transpose the counts matrix in order
# to have genes on rows and spot on columns. 
# For this example, run spatialDE on the first 1000 genes

partial_counts <- head(Rep11_MOB_0, 1000)

spe <- SpatialExperiment(
  assays = list(counts = partial_counts),
  spatialData = DataFrame(MOB_sample_info[, c("x", "y")]),
  spatialCoordsNames = c("x", "y")
)

out <- spatialDE(spe, assay_type = "counts", verbose = FALSE)
head(out[order(out$qval), ])

4.1 Plot Spatial Patterns of Multiple Genes (using SpatialExperiment object)

We can plot spatial patterns of multiples genes using the spe object.

spe_results <- out[out$qval < 0.05, ]

ordered_spe_results <- spe_results[order(spe_results$qval), ]

multiGenePlots(spe,
    assay_type = "counts",
    ordered_spe_results[1:6, ]$g,
    point_size = 4,
    viridis_option = "D",
    dark_theme = FALSE
)

4.2 Classify spatially variable genes with model_search and spatial_patterns

msearch <- modelSearch(spe,
    de_results = out, qval_thresh = 0.05,
    verbose = FALSE
)

head(msearch)
spatterns <- spatialPatterns(spe,
    de_results = de_results, qval_thresh = 0.05,
    n_patterns = 4L, length = 1.5, verbose = FALSE
)

spatterns$pattern_results

sessionInfo

Session info
#> [1] "2024-11-25 17:41:29 EST"
#> R Under development (unstable) (2024-11-20 r87352)
#> Platform: aarch64-apple-darwin20
#> Running under: macOS Ventura 13.7.1
#> 
#> Matrix products: default
#> BLAS:   /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/lib/libRblas.0.dylib 
#> LAPACK: /Library/Frameworks/R.framework/Versions/4.5-arm64/Resources/lib/libRlapack.dylib;  LAPACK version 3.12.0
#> 
#> locale:
#> [1] C/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
#> 
#> time zone: America/New_York
#> tzcode source: internal
#> 
#> attached base packages:
#> [1] stats4    stats     graphics  grDevices utils     datasets  methods  
#> [8] base     
#> 
#> other attached packages:
#>  [1] SpatialExperiment_1.17.0    SingleCellExperiment_1.29.1
#>  [3] SummarizedExperiment_1.37.0 Biobase_2.67.0             
#>  [5] GenomicRanges_1.59.1        GenomeInfoDb_1.43.1        
#>  [7] IRanges_2.41.1              S4Vectors_0.45.2           
#>  [9] BiocGenerics_0.53.3         generics_0.1.3             
#> [11] MatrixGenerics_1.19.0       matrixStats_1.4.1          
#> [13] ggplot2_3.5.1               spatialDE_1.13.0           
#> [15] BiocStyle_2.35.0           
#> 
#> loaded via a namespace (and not attached):
#>  [1] gtable_0.3.6            dir.expiry_1.15.0       rjson_0.2.23           
#>  [4] xfun_0.49               bslib_0.8.0             ggrepel_0.9.6          
#>  [7] lattice_0.22-6          vctrs_0.6.5             tools_4.5.0            
#> [10] parallel_4.5.0          tibble_3.2.1            fansi_1.0.6            
#> [13] pkgconfig_2.0.3         Matrix_1.7-1            checkmate_2.3.2        
#> [16] lifecycle_1.0.4         GenomeInfoDbData_1.2.13 farver_2.1.2           
#> [19] compiler_4.5.0          tinytex_0.54            munsell_0.5.1          
#> [22] htmltools_0.5.8.1       sass_0.4.9              yaml_2.3.10            
#> [25] pillar_1.9.0            crayon_1.5.3            jquerylib_0.1.4        
#> [28] cachem_1.1.0            DelayedArray_0.33.2     magick_2.8.5           
#> [31] abind_1.4-8             basilisk_1.19.0         tidyselect_1.2.1       
#> [34] digest_0.6.37           dplyr_1.1.4             bookdown_0.41          
#> [37] labeling_0.4.3          fastmap_1.2.0           grid_4.5.0             
#> [40] colorspace_2.1-1        cli_3.6.3               SparseArray_1.7.2      
#> [43] magrittr_2.0.3          S4Arrays_1.7.1          utf8_1.2.4             
#> [46] withr_3.0.2             backports_1.5.0         filelock_1.0.3         
#> [49] scales_1.3.0            UCSC.utils_1.3.0        rmarkdown_2.29         
#> [52] XVector_0.47.0          httr_1.4.7              gridExtra_2.3          
#> [55] reticulate_1.40.0       png_0.1-8               evaluate_1.0.1         
#> [58] knitr_1.49              basilisk.utils_1.19.0   viridisLite_0.4.2      
#> [61] rlang_1.1.4             Rcpp_1.0.13-1           glue_1.8.0             
#> [64] BiocManager_1.30.25     jsonlite_1.8.9          R6_2.5.1               
#> [67] zlibbioc_1.53.0