Guide for first steps in RNA-seq data analysis from Vinther Lab 

##### Requirements
# FastQC (or similar quality control program, added to the path)
# cutadapt (added to the path)
# preprocessing script from RNAprobR, which can be found here: https://github.com/lkie/RNAprobBash 
 (also contain guide for downloading and using RNAprobr including preprocessing script)
# bowtie2 (added to the path)

##### Workflow
# Download fastq files and genome for the provided example
cd /usr/directory
wget -r http://people.binf.ku.dk/jvinther/data/RNA-seq/data

# Quality control 
for i in {17..19}
do
fastqc "$i".fastq.gz
done 

# Adapter trimming with Cutadapt
cutadapt --version > cutadapt.version # save the cutadapt version for future reference
for i in {17..19}
do
mkdir data/$i
cd /data/$i
zcat /data/"$i".fastq.gz | cutadapt -a AGATCGGAAGAGCACACGTCT --nextseq-trim=20  --minimum-length=40 - 2> cutadapt.error | gzip > reads_trimmed.fastq.gz &
done
wait

# Preprocessing
PATH=$PATH:/path/to/RNAprobr/scripts # set the path to the scripts
for i in {17..19} 
do
cd /data/"$i"
preprocessing.sh -b NNNNNNN -t 15 -1 reads_trimmed.fastq.gz
gzip ./output_dir/read1.fastq
done

# Build index with bowtie2-build
cd /data/fastafile
bowtie2-build Bacillus_subtilis_168.ASM904v1.fa Bacillus_subtilis_168.ASM904v1

# Mapping with bowtie2
bowtie2 --version > bowtie2.version # save the bowtie2 version for future reference
for i in {17..19}
do
cd /data/"$i"
nice bowtie2 --quiet -p30 -N 1 -x Bacillus_subtilis_168.ASM904v1 -U ./output_dir/read1.fastq.gz | gzip > mapped.sam.gz
done
wait

# Collapse on barcodes, output sam.gz file
PATH=$PATH:/path/to/collapse/script
chmod u+x collapse.sh
for i in {17..19}
do
cd /data/"$i"
./collapse.sh /data/"$i"/mapped.sam.gz /data/"$i"/output_dir/barcodes.txt > "$i"_debarcoded_file.sam.gz
done