Workflow

#As Rmdup is obsolete, this can be used instead to sort bam files \
and remove duplicates from them


# First, the bam file has to be sorted

#!/bin/bash
#
#$ -cwd

java -jar $picard_dir/picard.jar SortSam \
      I=/mnt/work1/users/pughlab/projects/MMRF/WGS_bam_links/MMRF-13-FU2_S7.bam \
      O=MMRF-13-FU2_S7_sorted.bam \
      SORT_ORDER=coordinate

# to run: sbatch -c 2 -t 1:00:00 --mem 16G <filename>

#Next, duplicates are removed

#!/bin/bash
#
#$ -cwd

module load picard/2.10.9

java -jar $picard_dir/picard.jar MarkDuplicates \
      I=MMRF-13-FU2_S7_sorted.bam \
      O=MMRF-13-FU2_S7_marked_duplicates.bam \
      M=MMRF-13-FU2_S7_marked_dup_metrics.txt \
      REMOVE_DUPLICATES=True

# the file that ends with 'FU2_S7_marked_duplicates' has its duplicates removed

#It can then be indexed: 

#!/bin/bash
#
#$ -cwd

module load samtools/1.9

samtools index FU2_S7_DuplicatesRemoved.rmdup.bam