minor adaptations

experiments/assessing_cluster_clonality/workflow/Snakefile

@@ -17,7 +17,6 @@ MARKDOWNS = PROJECT_DIR / "data" / "markdowns"
 
 
 ######Rules######
-include: "rules/common.smk"
 include: "rules/base.smk"
 
 

experiments/assessing_cluster_clonality/workflow/envs/R.yml

@@ -9,3 +9,7 @@ dependencies:
   - r-tidyverse>=2.0
   - pandoc>=3.1
   - r-heatmaply>=1.5  
+  - r-optparse>=1.7
+  - r-viridis>=0.6
+  - r-vgam>=1.1
+  - r-pscl>=1.5

experiments/assessing_cluster_clonality/workflow/resources/annotateVariants.R

@@ -11,12 +11,12 @@ annotate_variants <- function(sampleName, inputFolder, variantList) {
 
 
   # Read VCF file to extract column names
-  file <- file.path(inputFolder, "filtered", "vcf_files_annotated", paste0(sampleName, ".ann.vcf"))
+  file <- file.path(inputFolder, "annotations", paste0(sampleName, ".ann.vcf"))
   lines <- readLines(file, warn = FALSE)
   vcf_names <- strsplit(lines[grep("^#CHROM", lines)], "\t")[[1]]
 
   # Read VCF file into a data frame
-  vcf <- read.table(file.path(inputFolder, "filtered", "vcf_files_annotated", paste0(sampleName, ".ann.vcf")),
+  vcf <- read.table(file.path(inputFolder, "annotations", paste0(sampleName, ".ann.vcf")),
     comment.char = "#", sep = "\t", header = FALSE, col.names = vcf_names
   )
   colnames(vcf)[1] <- "#CHROM"

experiments/assessing_cluster_clonality/workflow/scripts/createInputSummary.R

@@ -2,35 +2,37 @@ source("../resources/functions.R")
 library("optparse")
 
 parser <- OptionParser()
-parser <- add_option(parser, c("-i", "--input-file"),
+parser <- add_option(parser, c("-i", "--input-folder"),
   type = "character",
   default = "~/Documents/projects/CTC_backup/input_folder", help = "Path to the folder containing all input files"
 )
 parser <- add_option(parser, c("-n", "--name-of-tree"),
   type = "character",
   default = "Br23", help = "Name of the tree for which to simulate CTC-clusters"
 )
-args <- parse_args(parser, args = c("--input-file", "--name-of-tree"))
+args <- parse_args(parser)
 
 
 
 
-inputFolder <- dirname(args$"input-file")
-treeName <- args$name_of_tree
+input_folder <- args$"input-folder"
+tree_name <- args$"name-of-tree"
 
 
-# inputFolder <- "~/Documents/projects/CTC_backup/input_folder"
-# treeName <- "Br23"
 
+# input_folder <- "~/Documents/projects/CTC_backup/input_folder"
+# tree_name <- "Br23"
 
-input <- load_data(inputFolder, treeName)
 
-allClusterSizes <- input$sample_description %>%
+input <- load_data(input_folder, tree_name)
+
+all_cluster_sizes <- input$sample_description %>%
   filter(WBC == 0 & color != "gray93") %>%
   group_by(color) %>%
   filter(n() > 1) %>%
   summarize(cluster_size = n()) %>%
   dplyr::select("cluster_size") %>%
   unique()
 
-write_csv(allClusterSizes, file.path(inputFolder, treeName, paste(treeName, "clusterSizes.csv", sep = "_")))
+write_csv(all_cluster_sizes, file.path(input_folder, tree_name, paste(tree_name, "clusterSizes.csv", sep = "_")))
+print("Success.")