Add 'rnaseq/step5_count/snippet_counts'

rnaseq/step1_fastqc/00_fastqc.pl

@@ -1,23 +0,0 @@
-#!/usr/bin/perl -w
-use strict;
-
-# this script was made with consideration for UMI-deduplicating.
-# this is because there are three .fastq files for each sample. 
-# the provider states the info about which file contains which info,
-# but in our case, from GenomeScan in Leiden, R2 contains the UMI read.
-# R1 and R3 contain sequencing information from paired-end sequencing
-
-foreach my $file1 ( <*_R1.fastq.gz> ) {
-    my $file2 = $file1;
-    $file2 =~ s/\_R1\./_R2./;
-    my $file3 =~ s/\_R3\./_R2./;
-    die "file1==file2" if $file1 eq $file2;
-    my $sample = $file1;
-    $sample =~ s/\_R1\.fastq\.gz$//;
-    mkdir $sample.'_R1', 0700;
-    system join(' ', 'fastqc', '-o', $sample.'_R1', $file1);
-    mkdir $sample.'_R2', 0700;
-    system join(' ', 'fastqc', '-o', $sample.'_R2', $file2);
-    mkdir $sample.'_R3', 0700;
-    system join(' ', 'fastqc', '-o', $sample.'_R3', $file3)
-}

rnaseq/step1_fastqc/00_fastqc.sh

@@ -1,27 +0,0 @@
-#!/bin/bash
-#SBATCH --job-name=FastQC.for.alveolar_type_2
-#SBATCH --comment=FastQC.for.alveolar_type_2
-#SBATCH --time=48:00:00
-#SBATCH --mincpus=2
-#SBATCH --mem=20G
-#SBATCH --qos=priority
-
-# For 173 samples, it will take about 24 hrs to run with about 15Gb of memory.
-# Should probably parallelize the perl script/make it a bash/slurm script.
-
-module purge
-module load Perl/5.26.2-foss-2015b-bare
-module load BioPerl/1.6.924-foss-2015b-Perl-5.22.0
-module load Java/11.0.2
-module load FastQC/0.11.7-Java-1.8.0_144-unlimited_JCE
-
-# Please see
-# https://www.youtube.com/watch?v=0Rj_xNuyOyQ
-
-cd /groups/umcg-griac/tmp04/projects/umcg-rbults/alveolar_type2_fastq/
-perl scripts/00_fastqc.pl
-
-mkdir rene_FastQC.results
-find . -maxdepth 1 -type d -iname "*_R[123]" -exec mv {} ./rene_FastQC.results/ \;
-#find . -maxdepth 1 -type f -iname "*.htm*" -exec mv {} ./FastQC.results/ \;
-

rnaseq/step2_trim/snippet.sh

@@ -1,36 +0,0 @@
-## this script is to generate jobs of trimming for each samples on the cluster
-## please run this script first and then submit the jobs for each samples
-## reference: http://www.usadellab.org/cms/?page=trimmomatic
-
-#!/bin/bash
-# $1 indicates the path of raw samples. 
-# In the input folder, one sample has one independent folder with two pair-end f
-astq files. 
-# The folder name should be the sample name. 
-# the fastq file should be sample_1.fastq and sample_2.fastq 
-# please prepare a sample.list that include file names for each sample
-
-out="/ * your output folder * /"
-input="/ * your input folder * /"
-cat sample.list | while read line
-
-do
-sample=$(echo $line)
-echo '#!/bin/bash'  > rnaseq.${sample}.sh
-echo "#SBATCH --job-name=RNAseq.${sample}" >> rnaseq.${sample}.sh
-echo "#SBATCH --error=RNAseq.${sample}.err" >> rnaseq.${sample}.sh
-echo "#SBATCH --output=RNAseq.${sample}.out" >> rnaseq.${sample}.sh
-echo "#SBATCH --mem=15gb" >> rnaseq.${sample}.sh
-echo "#SBATCH --time=6:00:00" >> rnaseq.${sample}.sh
-echo "#SBATCH --cpus-per-task=6" >> rnaseq.${sample}.sh
-
-echo "ml Java" >>rnaseq.${sample}.sh
-
-echo "java -jar /* your folder of software */trimmomatic-0.36.jar PE \
-  -phred33 /$input/${sample}\_1.fq.gz /$input/${sample}\_2.fq.gz \
-   $out/trimmomatic/${sample}\_1_paired.fq $out/trimmomatic/${sample}\_1_unpaired.fq \
-   $out/trimmomatic/${sample}\_2_paired.fq $out/trimmomatic/${sample}\_2_unpaired.fq \
-   ILLUMINACLIP: TruSeq3-PE.fa:2:30:10 \
-   LEADING:3 TRAILING:3 SLIDINGWINDOW:4:25 HEADCROP:8 MINLEN:50" >> rnaseq.${sample}.sh
-
-done

rnaseq/step5_count/snippet_counts

@@ -0,0 +1,18 @@
+## Generate Raw Counts using FeatureCounts/HTSeqCounts 
+
+## Load package Subread (packge within which FeatureCounts is present)
+
++ ml Subread/1.6.4-foss-2015b FeatureCounts
+
+## Features used in FeatureCounts : 
+## -s : reversely stranded 
+## -T : number of threads used 
+## -a : reference genome 
+## -o : output file 
+
++ featureCounts \
++ --a "path to reference genome" \
++ --T 6 \
++ --o "path to output file" \
++ --s 2
+