Shell script to sub-sample a BAM file

subsample_bam.sh

# Shell function to subsample to a fixed number of alignments,
# requiring the sambamba and samtools suites to be available.
# see https://www.biostars.org/p/76791/
function SubSample {
  local FACTOR=$(samtools idxstats $1 | cut -f3 | \
    awk -v COUNT=$2 'BEGIN {total=0} {total += $1} END {print COUNT/total}')

  if [[ $FACTOR > 1 ]]
    then
    echo '[ERROR]: Requested number of reads exceeds total read count in' $1 '-- exiting' && exit 1
  fi
  sambamba view -s $FACTOR -t 2 -f bam -l 5 $1
}

# example:
SubSample original.bam 10000 > subsampled.bam