Merge partially overlapped Illumina reads from demultiplexed CASAVA output

run_merge_illumina_reads.sh

#!/bin/bash
#
# example command line:
#
# ./run_merge_illumina_reads Sample_202_11M /PATH/TO/CASAVA/OUTPUT/Sample_202_11M/ /PATH/TO/OUTPUT/DIR/RESULTS meren@mbl.edu
#
# Note: Running this command line will remove /PATH/TO/OUTPUT/DIR/RESULTS/Sample_202_11M/ directory
#       if it exists, without asking for your confirmation.
#
#
# If you have more than one sample to run, you can create a run script to run all of them at once.
# Here is an example:
#
# ---->8---->8---->8---->8---->8---->8---->8---->8---->8---->8---->8-----
#    #!/bin/bash
#
#    for sample in Sample_202_6M  Sample_208_5M  Sample_208_9M  Sample_209_5M  Sample_209_6M
#    do
#        clusterize "./run_merge_illumina_reads $sample /xraid2-2/sequencing/Illumina/20121026hs/Project_HMP/$sample/ /xraid2-2/sequencing/Illumina/20121026hs/Project_HMP/RESULTS/ meren@mbl.edu"
#    done
# ---->8---->8---->8---->8---->8---->8---->8---->8---->8---->8---->8-----
#


project_name=$1
input_dir=$2
output_dir=$3
if [ ! -z $4 ]; then
    e_mail=$4
else
    e_mail="researcher@unknown-domain"
fi

config_file="$output_dir/$project_name/config.ini"

if [ ! -d "$output_dir" ]; then
    mkdir $output_dir
fi

if [ -d "$output_dir/$project_name" ]; then
    rm -rf "$output_dir/$project_name"
    mkdir "$output_dir/$project_name"
fi

if [ ! -d "$output_dir/$project_name" ]; then
    mkdir "$output_dir/$project_name"
fi

echo "[general]
project_name = $project_name
researcher_email = $e_mail
input_directory = $input_dir
output_directory = $output_dir/$project_name


[files]
pair_1 = `ls $input_dir/*R1* | awk 'BEGIN{FS="/"; PAIRS=""}{PAIRS=PAIRS", "$NF}END{printf(substr(PAIRS, 3, length(PAIRS))"\n")}'`
pair_2 = `ls $input_dir/*R2* | awk 'BEGIN{FS="/"; PAIRS=""}{PAIRS=PAIRS", "$NF}END{printf(substr(PAIRS, 3, length(PAIRS))"\n")}'`
" > $config_file


# start merging on config file
python /bioware/pythonmodules/illumina-utils/scripts/merge-illumina-pairs $config_file $project_name --skip-qual-dicts --min-overlap-size 10