Publication:
https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3418586/

GEO reads: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE39161
Bioproject: PRJNA170127

Reads are single-end

Sequenced on Illumina Genome Analyzer II


#!/bin/bash
#SBATCH --time=23:00:00
#SBATCH --nodes=1
#SBATCH --ntasks-per-node=36
#SBATCH --job-name="get1"
#SBATCH --mail-type=BEGIN
#SBATCH --mail-type=END
#SBATCH --mail-type=FAIL
#SBATCH --output=job.%J.out
#SBATCH --error=job.%J.err
#SBATCH --mail-user=mhrwoodhouse@gmail.com
#SBATCH --mail-type=BEGIN,END,FAIL

ulimit -s unlimited

module load trimgalore
module load bowtie
module load samtools
module load picard
module load bedtools2

for sample in *.fastq.gz
        do
          	echo $sample
                describer=$(echo ${sample} | sed 's/.fastq.gz//')
                echo $describer

trim_galore ${sample}

zcat ${describer}_trimmed.fq.gz > ${describer}_trimmed.fq   

bowtie -X 1000 -m 1 -v 2 --best --strata /work/LAS/mhufford-lab/mw2/epigenetics/bowtie_B73v5/B73_v5 ${describer}_trimmed.fq -S ${describer}_trimmed.sam

samtools view --threads 36 -b -o ${describer}_trimmed.bam  ${describer}_trimmed.sam
samtools sort -o ${describer}_sorted.bam -T ${sample}_temp --threads 36 ${describer}_trimmed.bam

picard MarkDuplicates I=${describer}_sorted.bam O=${describer}_removed_dups.bam M=marked_dup_metrics.txt REMOVE_DUPLICATES=true

bedtools genomecov -bg -ibam ${describer}_removed_dups.bam -split -scale 1.0 > ${describer}.bedgraph

/work/LAS/mhufford-lab/mw2/kentUtils/bin/linux.x86_64/bedGraphToBigWig ${describer}.bedgraph /work/LAS/mhufford-lab/mw2/epigenetics/B73v5.sizes ${describer}.bw

done

samtools merge SRR518975_SRR518976.bam SRR518975_sorted.bam SRR518976_sorted.bam


samtools merge SRR518977_SRR518978.bam SRR518977_sorted.bam SRR518978_sorted.bam

samtools sort -o SRR518975_SRR518976_sorted.bam -T SRR518975_SRR518976_temp --threads 36 SRR518975_SRR518976.bam

picard MarkDuplicates I=SRR518975_SRR518976_sorted.bam O=SRR518975_SRR518976_removed_dups.bam M=marked_dup_metrics.txt REMOVE_DUPLICATES=true

bedtools genomecov -bg -ibam SRR518975_SRR518976_removed_dups.bam -split -scale 1.0 > SRR518975_SRR518976.bedgraph

/work/LAS/mhufford-lab/mw2/kentUtils/bin/linux.x86_64/bedGraphToBigWig SRR518975_SRR518976.bedgraph /work/LAS/mhufford-lab/mw2/epigenetics/B73v5.sizes SRR518975_SRR518976.bw



samtools sort -o SRR518977_SRR518978_sorted.bam -T SRR518977_SRR518978_temp --threads 36 SRR518977_SRR518978.bam

picard MarkDuplicates I=SRR518977_SRR518978_sorted.bam O=SRR518977_SRR518978_removed_dups.bam M=marked_dup_metrics.txt REMOVE_DUPLICATES=true

bedtools genomecov -bg -ibam SRR518977_SRR518978_removed_dups.bam -split -scale 1.0 > SRR518977_SRR518978.bedgraph

/work/LAS/mhufford-lab/mw2/kentUtils/bin/linux.x86_64/bedGraphToBigWig SRR518977_SRR518978.bedgraph /work/LAS/mhufford-lab/mw2/epigenetics/B73v5.sizes SRR518977_SRR518978.bw


/work/LAS/mhufford-lab/mw2/epigenetics/peakranger ranger --format bam SRR518975_SRR518976_removed_dups.bam SRR518977_SRR518978_removed_dups.bam SRR518975_SRR518976_ranger -t 15


done

For peak calling the unmerged reads:

/work/LAS/mhufford-lab/mw2/epigenetics/peakranger ranger --format bam SRR518973_removed_dups.bam SRR518974_removed_dups.bam SRR518973_ranger -t 15
/work/LAS/mhufford-lab/mw2/epigenetics/peakranger ranger --format bam SRR518979_removed_dups.bam SRR518980_removed_dups.bam SRR518979_ranger -t 15


module load py-macs2

macs2 callpeak -t SRR518973_removed_dups.bam -c SRR518974_removed_dups.bam -f BAMPE -n SRR518973_tassel1_macs2 -g 2.2e9 --keep-dup all 
macs2 callpeak -t SRR518979_removed_dups.bam -c SRR518980_removed_dups.bam -f BAMPE -n SRR518979_ear_macs2 -g 2.2e9 --keep-dup all 

macs2 callpeak -t SRR518975_SRR518976_removed_dups.bam -c SRR518977_SRR518978_removed_dups.bam -f BAMPE -n SRR518975_SRR518976_tassel2-3_macs2 -g 2.2e9 --keep-dup all