1 Introduction

The present script takes the summary of the spaceRanger output from the Spatial Transcriptomics data generated with 10X VISIUM technology on a set of CRC samples.

2 Getting Ready

We first load the libraries and set the paths to the raw data.

library(ggplot2)
library(vctrs)
library(patchwork, lib.loc = "/apps/rocs/2020.08/cascadelake/software/R/4.1.2-foss-2020a/lib64/R/library")
library(Seurat)
library(tidyverse)
library(kableExtra)
library(RColorBrewer)
source(file = "WrapperFunction/SeuratWrappers.R")

data_directory <- 
 params$data_directory
analysis_name <- 
  params$analysis_name
counts_directory <- "/outs"

dir.create(paste0(data_directory, analysis_name), showWarnings = FALSE)

# setwd(paste0(data_directory, analysis_name))
data_directory_counts <- paste0(data_directory, "Fastq_Merged")

We get the folders containing the spatial counts for the different samples.

datasets <- 
  list.dirs(path = data_directory_counts, recursive = FALSE, full.names = TRUE) %>% 
  str_subset("Count_") %>% paste0(counts_directory)
  
sample_names <- 
  list.dirs(path = data_directory_counts, recursive = FALSE, full.names = FALSE) %>% 
  str_subset("Count_") %>% str_replace("Count_", "")

We read the metrics summary for all the samples.

QC_global_df <- 
  get.global.QCmetrics(datasets, sample_names, metrics_name = "/metrics_summary.csv") 
QC_global_df %>% kbl() %>% kable_styling() %>% scroll_box(width = "100%")

Sample ID	Number of Spots Under Tissue	Number of Reads	Mean Reads per Spot	Mean Reads Under Tissue per Spot	Fraction of Spots Under Tissue	Median Genes per Spot	Median UMI Counts per Spot	Valid Barcodes	Valid UMIs	Sequencing Saturation	Q30 Bases in Barcode	Q30 Bases in RNA Read	Q30 Bases in UMI	Reads Mapped to Genome	Reads Mapped Confidently to Genome	Reads Mapped Confidently to Intergenic Regions	Reads Mapped Confidently to Intronic Regions	Reads Mapped Confidently to Exonic Regions	Reads Mapped Confidently to Transcriptome	Reads Mapped Antisense to Gene	Fraction Reads in Spots Under Tissue	Total Genes Detected	samples_name
Count_SN048_A121573_Rep1	2203	238571549	108293.94	60463.56	0.4413061	4264.0	11920.0	0.9575566	0.9973647	0.7276006	0.9371116	0.9099210	0.9377244	0.8557846	0.8250528	0.0292398	0.0235099	0.7723031	0.7529259	0.0079163	0.5889230	22977	SN048_A121573_Rep1
Count_SN048_A121573_Rep2	2385	218249797	91509.35	47076.25	0.4777644	3809.0	9460.0	0.9563191	0.9961037	0.6590206	0.9321118	0.9047080	0.9321161	0.7663808	0.7347149	0.0262561	0.0224679	0.6859909	0.6676575	0.0075557	0.5522567	22833	SN048_A121573_Rep2
Count_SN048_A416371_Rep1	2317	164220396	70876.30	38981.42	0.4641426	4116.0	9924.0	0.9485526	0.9924445	0.4967044	0.9285334	0.8982389	0.9288378	0.6709256	0.6413772	0.0202746	0.0217622	0.5993404	0.5804310	0.0053696	0.6113097	22192	SN048_A416371_Rep1
Count_SN048_A416371_Rep2	1803	135118970	74941.19	44431.33	0.3611779	4588.0	12685.0	0.9543406	0.9931894	0.4628681	0.9342732	0.9107446	0.9359586	0.6702179	0.6409008	0.0209851	0.0215138	0.5984019	0.5792172	0.0058035	0.6957941	22148	SN048_A416371_Rep2
Count_SN123_A551763_Rep1	691	84959596	122951.66	42749.08	0.1384215	4643.0	11756.0	0.9721363	0.9985743	0.5594079	0.9549964	0.9387691	0.9531112	0.7303343	0.6757109	0.0282179	0.0367193	0.6107737	0.5929185	0.0075300	0.4015557	20150	SN123_A551763_Rep1
Count_SN123_A595688_Rep1	1192	123561252	103658.77	55240.88	0.2387821	4388.0	12977.0	0.9692355	0.9975122	0.5869393	0.9548186	0.9302510	0.9537855	0.7504864	0.7180723	0.0290811	0.0222581	0.6667331	0.6473198	0.0088081	0.5747350	22687	SN123_A595688_Rep1
Count_SN123_A798015_Rep1	1685	195534214	116044.04	60988.81	0.3375401	2343.0	5522.0	0.9722068	0.9987664	0.7485725	0.9531217	0.9368612	0.9512725	0.6472138	0.5728710	0.0276017	0.0377490	0.5075203	0.4945108	0.0049185	0.5681802	22121	SN123_A798015_Rep1
SN123_A938797_Rep1	2128	113886618	53518.15	32244.26	0.4262821	3084.5	6598.0	0.9708266	0.9977994	0.5233447	0.9603618	0.9374743	0.9586598	0.6293995	0.5852414	0.0240003	0.0453451	0.5158960	0.4984374	0.0080705	0.6855957	22572	SN123_A938797_Rep1_X
Count_SN124_A551763_Rep2	1219	471863476	387090.63	71290.96	0.2441907	1233.0	1828.0	0.9718199	0.9994796	0.9514726	0.9583634	0.9453707	0.9572916	0.7790948	0.7216550	0.0348214	0.0503531	0.6364805	0.6231167	0.0035308	0.2091223	18072	SN124_A551763_Rep2
Count_SN124_A595688_Rep2	387	72073556	186236.58	38019.12	0.0775240	4407.0	12319.0	0.9737471	0.9982102	0.4650953	0.9547990	0.9396376	0.9529286	0.5719089	0.5043402	0.0434788	0.0412854	0.4195760	0.4071708	0.0042920	0.3270215	19788	SN124_A595688_Rep2
Count_SN124_A798015_Rep21	1656	137192998	82846.01	41384.02	0.3317308	2691.5	7395.0	0.9727572	0.9980660	0.6111810	0.9540471	0.9382082	0.9529220	0.7247318	0.6560772	0.0274734	0.0360448	0.5925590	0.5787086	0.0048207	0.5444075	22523	SN124_A798015_Rep2
Count_SN124_A938797_Rep2	1691	168083674	99398.98	58377.63	0.3387420	5457.0	18113.0	0.9710085	0.9981355	0.5525068	0.9573377	0.9357632	0.9556994	0.8007195	0.7543746	0.0264059	0.0405447	0.6874239	0.6679099	0.0083701	0.6499086	23445	SN124_A938797_Rep2
Count_SN84_A120838_Rep1	328	54756730	166941.25	38074.14	0.0657051	3958.0	10228.5	0.9716287	0.9965244	0.5255282	0.9575546	0.9375129	0.9562052	0.7295707	0.6911641	0.0297442	0.0361460	0.6252738	0.6113695	0.0039466	0.2680933	18651	SN84_A120838_Rep1
Count_SN84_A120838_Rep2	1048	110841367	105764.66	35332.70	0.2099359	3348.0	7218.0	0.9717985	0.9976415	0.6533942	0.9557841	0.9343218	0.9544974	0.7509154	0.7027843	0.0264602	0.0269533	0.6493708	0.6343222	0.0047185	0.3488974	20269	SN84_A120838_Rep2

2.1 Number of Spots Under Tissue

get.barplot.qc(QC_global_df, column_to_plot = "Number of Spots Under Tissue")

2.2 Median Genes per Spot

get.barplot.qc(QC_global_df, column_to_plot = "Median Genes per Spot")

2.3 Number of Reads

get.barplot.qc(QC_global_df, column_to_plot = "Number of Reads")

2.4 Reads Mapped Confidently to Transcriptome

get.barplot.qc(QC_global_df, column_to_plot = "Reads Mapped Confidently to Transcriptome")

2.5 Reads Mapped Confidently to Genome

get.barplot.qc(QC_global_df, column_to_plot = "Reads Mapped Confidently to Genome")

2.6 Fraction of Spots Under Tissue

get.barplot.qc(QC_global_df, column_to_plot = "Fraction of Spots Under Tissue")

2.7 Fraction Reads in Spots Under Tissue

get.barplot.qc(QC_global_df, column_to_plot = "Fraction Reads in Spots Under Tissue")

2.8 Median UMI Counts per Spot

get.barplot.qc(QC_global_df, column_to_plot = "Median UMI Counts per Spot")

2.9 Improved Median Genes and UMI counts per Spot

df_patient_ID_transform <- data.frame(
  patient = c("A120838","A121573","A416371","A551763","A595688","A798015",
              "A938797"), 
  patient_ID = c("S4_Col_Sig","S5_Rec","S3_Col_R","S1_Cec","S2_Col_R",
                 "S7_Rec/Sig","S6_Rec"))

QC_global_df$samples_name <- 
  stringr::str_replace(QC_global_df$samples_name, pattern= "SN123_A938797_Rep1_X", replacement = "SN123_A938797_Rep1")

QC_global_df <- QC_global_df %>%
    dplyr::mutate(replicate = str_remove(.$samples_name, pattern = ".*_")) 
    
QC_global_df$patient <- 
  stringr::str_match(QC_global_df$samples_name, "_\\s*(.*?)\\s*_")[,2]

QC_global_df <-  inner_join(QC_global_df, df_patient_ID_transform)

QC_global_df$slide <- str_extract(QC_global_df$samples_name , "[^_]+")

QC_global_df$patient_ID_rep <- paste0(QC_global_df$patient_ID, "_", QC_global_df$replicate)
  


p1 <- ggplot(QC_global_df, aes(fill=slide, y=`Median Genes per Spot`, x=patient_ID_rep)) + 
    geom_bar(position="dodge", stat="identity") + theme_light() + 
    theme(legend.position = "top", legend.title = element_text(size = 14, face = "bold"),
          legend.text = element_text(size = 12, hjust = 1, angle = 0),
          axis.text.x = element_text(angle = 90, hjust = 0, size = 12, face = "bold"), 
          axis.text.y = element_text(angle = 0, hjust = 1, size = 12), 
          axis.title.y = element_text(size = 16, face = "bold")) + 
    xlab("") + ylab("Median Genes per Spot") + scale_fill_brewer(palette="Dark2")
p2 <- ggplot(QC_global_df, aes(fill=slide, y=`Median UMI Counts per Spot`, x=patient_ID_rep)) + 
    geom_bar(position="dodge", stat="identity") + theme_light() + 
    theme(legend.position = "top", legend.title = element_text(size = 14, face = "bold"),
          legend.text = element_text(size = 12, hjust = 1, angle = 0),
          axis.text.x = element_text(angle = 90, hjust = 0, size = 12, face = "bold"), 
          axis.text.y = element_text(angle = 0, hjust = 1, size = 12), 
          axis.title.y = element_text(size = 16, face = "bold")) + 
    xlab("") + ylab("Median UMI Counts per Spot") + scale_fill_brewer(palette="Dark2")
p1 + p2

3 Conclusion

4 Session Info Details

## R version 4.1.2 (2021-11-01)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Fedora 33 (Container Image)
## 
## Matrix products: default
## BLAS/LAPACK: /apps/rocs/2020.08/cascadelake/software/OpenBLAS/0.3.9-GCC-9.3.0/lib/libopenblas_skylakexp-r0.3.9.so
## 
## 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     
## 
## other attached packages:
##  [1] RColorBrewer_1.1-3  kableExtra_1.3.4    forcats_0.5.1      
##  [4] stringr_1.4.0       dplyr_1.0.9         purrr_0.3.4        
##  [7] readr_2.1.2         tidyr_1.2.0         tibble_3.1.7       
## [10] tidyverse_1.3.1     sp_1.5-0            SeuratObject_4.1.0 
## [13] Seurat_4.1.0        patchwork_1.1.1     vctrs_0.4.1        
## [16] ggplot2_3.3.6       BiocManager_1.30.18
## 
## loaded via a namespace (and not attached):
##   [1] readxl_1.4.0          backports_1.4.1       systemfonts_1.0.4    
##   [4] plyr_1.8.7            igraph_1.3.2          lazyeval_0.2.2       
##   [7] splines_4.1.2         listenv_0.8.0         scattermore_0.8      
##  [10] digest_0.6.29         htmltools_0.5.2       fansi_1.0.3          
##  [13] magrittr_2.0.3        tensor_1.5            cluster_2.1.3        
##  [16] ROCR_1.0-11           tzdb_0.3.0            globals_0.15.0       
##  [19] modelr_0.1.8          matrixStats_0.62.0    vroom_1.5.7          
##  [22] svglite_2.1.0         spatstat.sparse_2.1-1 colorspace_2.1-0     
##  [25] rvest_1.0.2           ggrepel_0.9.1         haven_2.5.0          
##  [28] xfun_0.31             crayon_1.5.1          jsonlite_1.8.0       
##  [31] progressr_0.10.1      spatstat.data_2.2-0   survival_3.3-1       
##  [34] zoo_1.8-10            glue_1.6.2            polyclip_1.10-0      
##  [37] gtable_0.3.0          webshot_0.5.3         leiden_0.4.2         
##  [40] future.apply_1.9.0    abind_1.4-7           scales_1.2.0         
##  [43] DBI_1.1.3             spatstat.random_2.2-0 miniUI_0.1.1.1       
##  [46] Rcpp_1.0.8.3          viridisLite_0.4.0     xtable_1.8-6         
##  [49] reticulate_1.25       spatstat.core_2.4-4   bit_4.0.4            
##  [52] htmlwidgets_1.5.4     httr_1.4.3            ellipsis_0.3.2       
##  [55] ica_1.0-2             farver_2.1.0          pkgconfig_2.0.3      
##  [58] sass_0.4.1            uwot_0.1.11           dbplyr_2.2.0         
##  [61] deldir_1.0-6          utf8_1.2.2            labeling_0.4.2       
##  [64] tidyselect_1.1.2      rlang_1.0.2           reshape2_1.4.4       
##  [67] later_1.3.0           munsell_0.5.0         cellranger_1.1.0     
##  [70] tools_4.1.2           cli_3.3.0             generics_0.1.2       
##  [73] broom_0.8.0           ggridges_0.5.3        evaluate_0.15        
##  [76] fastmap_1.1.0         yaml_2.3.5            goftest_1.2-3        
##  [79] bit64_4.0.5           knitr_1.39            fs_1.5.2             
##  [82] fitdistrplus_1.1-8    RANN_2.6.1            pbapply_1.5-0        
##  [85] future_1.26.1         nlme_3.1-158          mime_0.12            
##  [88] xml2_1.3.3            compiler_4.1.2        rstudioapi_0.13      
##  [91] plotly_4.10.0         png_0.1-7             spatstat.utils_2.3-1 
##  [94] reprex_2.0.1          bslib_0.3.1           stringi_1.7.6        
##  [97] highr_0.9             rgeos_0.5-10          lattice_0.20-45      
## [100] Matrix_1.4-2          pillar_1.7.0          lifecycle_1.0.1      
## [103] spatstat.geom_2.4-0   lmtest_0.9-40         jquerylib_0.1.4      
## [106] RcppAnnoy_0.0.19      data.table_1.14.2     cowplot_1.1.1        
## [109] irlba_2.3.5           httpuv_1.6.5          R6_2.5.1             
## [112] promises_1.2.0.1      KernSmooth_2.23-20    gridExtra_2.3        
## [115] parallelly_1.32.0     codetools_0.2-18      MASS_7.3-57          
## [118] assertthat_0.2.1      withr_2.5.0           sctransform_0.3.3    
## [121] mgcv_1.8-40           parallel_4.1.2        hms_1.1.1            
## [124] grid_4.1.2            rpart_4.1.16          rmarkdown_2.14       
## [127] Rtsne_0.16            shiny_1.7.1           lubridate_1.8.0

Analysis of CRC Spatial Transcriptomics data from 10X: Quality Control: Global Metrics

Alberto Valdeolivas Urbelz (PS-Biomics&Path)

15 December, 2022