fixing code

Author: scu56292

from_SRA_to_nucMACC_scores/script/04_runNextflow.sh

@@ -1,14 +1,15 @@
 #!/usr/bin/env bash
+MY_PWD=$1
+cd $MY_PWD
 
-MY_PWD=$(pwd)
 
 # Run QC for MNase-seq samples
 
-/home/tools/nextflow run nucMACC \
+nextflow run nucMACC \
 --analysis 'MNaseQC' \
 --csvInput $MY_PWD'/data/samples.csv' \
 --outDir QC_out \
 --genomeIdx $MY_PWD'/data/Bowtie2Index/genome' \
 --genomeSize 162367812 \
 --publishBamFlt \
---TSS $MY_PWD'/data/genes.gtf' 
+--TSS $MY_PWD'/data/genes.gtf'

from_SRA_to_nucMACC_scores/script/05_createCSV_2.R

@@ -1,31 +1,30 @@
-#!/usr/bin/env Rscript 
-
-# set working directory
 setwd("QC_out/")
-
-# save working directory as pathSTD
 pathSTD<-getwd()
+library(stringr)
+
+
 
-# list mono-nucleosome and sub-nucleosome BAM files
 files.mono<-list.files("RUN/00_ALIGNMENT/monoNuc/")
 files.sub<-list.files("RUN/00_ALIGNMENT/subNuc/")
 
-# Change sample name by splitting at "_MNase_" and taking the first part
-Sample_Name <- sapply(strsplit(files.mono, "_MNase_"), `[`, 1)
+##sample name
+Sample_Name<-files.mono %>%
+    str_split_i("_MNase_",1)
+
+replicate<-files.mono %>%
+    str_split_i("_",5)
+
 
-# Extract replicate number by splitting at "_" and taking the sixth element
-replicate <- sapply(strsplit(files.mono, "_"), `[`, 6)
+MNase_U<-files.mono %>%
+    str_split_i("_",3) %>%
+    str_sub(1,-2)
 
-# Extract MNase units by splitting at "_" and taking the fourth element, then removing the last character
-MNase_U <- sapply(strsplit(files.mono, "_"), function(x) substr(x[4], 1, nchar(x[4])-1))
 
-# create data frame with sample name and corresponding file names for mono- and sub- nucleosomes
 df<-data.frame(Sample_Name=Sample_Name,
                replicate=replicate,
-           path_mono=paste0(pathSTD,"/RUN/00_ALIGNMENT/monoNuc/",files.mono),
-           path_sub=paste0(pathSTD,"/RUN/00_ALIGNMENT/subNuc/",files.sub),
-           MNase_U)
+               path_mono=paste0(pathSTD,"/RUN/00_ALIGNMENT/monoNuc/",files.mono),
+               path_sub=paste0(pathSTD,"/RUN/00_ALIGNMENT/subNuc/",files.sub),
+               MNase_U)
 
-# write .csv file with sample names and paths
 write.csv(df, row.names = F,
-          file = paste0(pathSTD,"/data/samples_nucMACC.csv", quote = F)
+          file="../data/samples_nucMACC.csv", quote = F)

from_SRA_to_nucMACC_scores/script/06_runNextflow_nucMACC.sh

@@ -1,16 +1,16 @@
 #!/usr/bin/env bash
-
-MY_PWD=$(pwd)
+MY_PWD=$1
+cd $MY_PWD
 
 
 # Run the nucMACC pipeline
 
-/home/tools/nextflow run nucMACC \
+nextflow run nucMACC \
 --analysis 'nucMACC' \
 --csvInput $MY_PWD'/data/samples_nucMACC.csv' \
 --outDir Run_out \
 --genomeIdx $MY_PWD'/data/Bowtie2Index/genome' \
 --genomeSize 162367812 \
 --genome $MY_PWD'/data/genome.fa' \
 --bamEntry \
---TSS $MY_PWD'/data/genes.gtf' 
+--TSS $MY_PWD'/data/genes.gtf'