compare flow and citeseq gate_group_merged data (independednt gated cell populations)

** Generate Figure S2A **

# get the Seurat object for gated cell subsets frequencies
# merge <- readRDS("input/2020_08_09.rmBuffSHD8.allcelltypelabels.merge.SNG.wmeta.WithinBatchClustered.Rds")
# merge.UnSort <- subset(merge, subset = Sorted == "N")

# merge_cell_UnSort_gate_merged <- data.frame(table(merge.UnSort$sample_id, merge.UnSort$gate_group_merged)) %>% dplyr::group_by(Var1) %>% dplyr::mutate(ratio = Freq/sum(Freq))
# saveRDS(merge_cell_UnSort_gate_merged, "output/merge_cell_UnSort_gate_merged.rds")

# merge_cell_UnSort_course <- data.frame(table(merge.UnSort$sample_id, merge.UnSort$gate_group_course)) %>% 
  # dplyr::group_by(Var1) %>% dplyr::mutate(ratio = Freq/sum(Freq))
# saveRDS(merge_cell_UnSort_course, "output/merge_cell_UnSort_gate_course.rds")

merge_cell_UnSort_gate_merged <- readRDS("output/merge_cell_UnSort_gate_merged.rds")
merge_cell_UnSort_course <- readRDS("output/merge_cell_UnSort_gate_course.rds")
merge_cell_UnSort <- rbind(merge_cell_UnSort_gate_merged, merge_cell_UnSort_course)
flow_of_total_mtx <- read.xlsx("input/Frequency_Manual.xlsx", sheet = "Freq_of_total", rowNames = TRUE)
flow_of_total <- melt(flow_of_total_mtx, id = c("Subject", "Timepoint", "Class", "Assay")) %>%
  mutate("sample_id" = paste(Subject, Timepoint, sep = "_"))

merge_cell_UnSort$sample_id <- sapply(str_split(merge_cell_UnSort$Var1, pattern = "_", n = 2), function(x)x[[2]])

flow_merge_cell_of_total <- inner_join(flow_of_total, merge_cell_UnSort, c("sample_id"="sample_id", "variable"="Var2")) %>%
  mutate(value.y = 100*ratio) %>%
  filter(!is.na(value.y)) %>%
  mutate(variable = factor(variable, levels = c("B", "B_Naive", "B_Mem", 
                                                "CD4", "CD4_Mem", "Treg", "Tfh",
                                                "CD8", "CD8_Mem", "NK", "NK_CD16hi",
                                                "NK_CD56hiCD16lo", "NK_CD56loCD16lo",
                                                "Mono", "Mono_Classical", "Mono_Nonclassical",
                                                "mDC", "pDC", "Gr", "Baso")))

p <- ggplot(flow_merge_cell_of_total, aes(x = value, y = value.y))+
  geom_point(aes(color = Class))+
  facet_wrap(~variable, scales = "free")+
  geom_smooth(method = lm, se=FALSE, linetype = "dashed")+
  labs(title = "freq of total single cells",
       x = "Flow_Cell_Freq%", y = "CITEseq_cell_Freq%")+
  stat_cor(method = "pearson") +
  theme_bw()
p

sI <- sessionInfo()
utils:::print.sessionInfo(sI[-c(10,11)])
## R version 3.6.2 (2019-12-12)
## Platform: x86_64-apple-darwin15.6.0 (64-bit)
## Running under: macOS Mojave 10.14.6
## 
## Matrix products: default
## 
## locale:
## [1] en_US.UTF-8/en_US.UTF-8/en_US.UTF-8/C/en_US.UTF-8/en_US.UTF-8
## 
## attached base packages:
## [1] stats     graphics  grDevices utils     datasets  methods   base     
## 
## other attached packages:
##  [1] ggpubr_0.4.0.999   reshape2_1.4.3     openxlsx_4.1.4     forcats_0.4.0     
##  [5] stringr_1.4.0      dplyr_0.8.4        purrr_0.3.3        readr_1.3.1       
##  [9] tidyr_1.0.2        tibble_3.0.3       ggplot2_3.3.2      tidyverse_1.3.0   
## [13] plyr_1.8.5         matrixStats_0.55.0 Seurat_3.1.4      
## 
## loaded via a namespace (and not attached):
##   [1] readxl_1.3.1        backports_1.1.5     sn_1.5-5           
##   [4] igraph_1.2.4.2      lazyeval_0.2.2      splines_3.6.2      
##   [7] listenv_0.8.0       TH.data_1.0-10      digest_0.6.25      
##  [10] htmltools_0.4.0     gdata_2.18.0        fansi_0.4.1        
##  [13] magrittr_1.5        cluster_2.1.0       ROCR_1.0-7         
##  [16] globals_0.12.5      modelr_0.1.6        RcppParallel_4.4.4 
##  [19] sandwich_2.5-1      colorspace_1.4-1    rvest_0.3.5        
##  [22] ggrepel_0.8.1       haven_2.2.0         xfun_0.12          
##  [25] crayon_1.3.4        jsonlite_1.6.1      survival_3.1-8     
##  [28] zoo_1.8-7           ape_5.3             glue_1.3.1         
##  [31] gtable_0.3.0        leiden_0.3.3        car_3.0-6          
##  [34] future.apply_1.4.0  BiocGenerics_0.32.0 abind_1.4-5        
##  [37] scales_1.1.0        mvtnorm_1.1-0       DBI_1.1.0          
##  [40] bibtex_0.4.2.2      rstatix_0.6.0       Rcpp_1.0.3         
##  [43] metap_1.3           plotrix_3.7-7       viridisLite_0.3.0  
##  [46] reticulate_1.14     foreign_0.8-75      rsvd_1.0.3         
##  [49] stats4_3.6.2        tsne_0.1-3          htmlwidgets_1.5.1  
##  [52] httr_1.4.1          gplots_3.0.3        RColorBrewer_1.1-2 
##  [55] TFisher_0.2.0       ellipsis_0.3.0      ica_1.0-2          
##  [58] farver_2.0.3        pkgconfig_2.0.3     uwot_0.1.5         
##  [61] dbplyr_1.4.2        labeling_0.3        tidyselect_1.0.0   
##  [64] rlang_0.4.7         munsell_0.5.0       cellranger_1.1.0   
##  [67] tools_3.6.2         cli_2.0.2           generics_0.0.2     
##  [70] broom_0.7.0         ggridges_0.5.2      evaluate_0.14      
##  [73] yaml_2.2.1          npsurv_0.4-0        knitr_1.28         
##  [76] fs_1.3.1            fitdistrplus_1.0-14 zip_2.0.4          
##  [79] caTools_1.18.0      RANN_2.6.1          pbapply_1.4-2      
##  [82] future_1.16.0       nlme_3.1-144        xml2_1.2.2         
##  [85] compiler_3.6.2      rstudioapi_0.11     curl_4.3           
##  [88] plotly_4.9.2        png_0.1-7           lsei_1.2-0         
##  [91] ggsignif_0.6.0      reprex_0.3.0        stringi_1.4.6      
##  [94] lattice_0.20-40     Matrix_1.2-18       multtest_2.42.0    
##  [97] vctrs_0.3.4         mutoss_0.1-12       pillar_1.4.3       
## [100] lifecycle_0.2.0     Rdpack_0.11-1       lmtest_0.9-37      
## [103] RcppAnnoy_0.0.15    data.table_1.12.8   cowplot_1.0.0      
## [106] bitops_1.0-6        irlba_2.3.3         gbRd_0.4-11        
## [109] patchwork_1.0.0     R6_2.4.1            rio_0.5.16         
## [112] KernSmooth_2.23-16  gridExtra_2.3       codetools_0.2-16   
## [115] MASS_7.3-51.5       gtools_3.8.1        assertthat_0.2.1   
## [118] withr_2.1.2         sctransform_0.2.1   mnormt_1.5-6       
## [121] multcomp_1.4-12     mgcv_1.8-31         parallel_3.6.2     
## [124] hms_0.5.3           grid_3.6.2          rmarkdown_2.1      
## [127] carData_3.0-3       Rtsne_0.15          numDeriv_2016.8-1.1
## [130] Biobase_2.46.0      lubridate_1.7.4