Finds files with the same ID and merges them into one single file.

merge_mulitplexed_samples

#!/bin/bash

# UPD...unique patient ID; file with UPDs
# eg. H_0047C\nH_0060A\nH_0062D\n... \n newline separated
UPD=$1 

# SPATH...search path
SPATH=$2

# FEXTENSION...file extension to search for [eg. .fastq.gz]
FEXTENSION=$3

# DEBUG 
DEBUG=0

# define usage function
usage(){
    echo "Usage: $0 filename_UPD \"search_path\" \"file_extension\""
    exit 1
}

if [[ -z ${UPD} ]] && [[ -z ${SPATH} ]] && [[ -z ${FEXTENSION} ]]; then
     usage
fi

if [[${DEBUG}]]; then
    echo "UPD: "$UPD

    for LINE in `cat ${UPD}`
    do
       echo $LINE
    done

    echo "SPATH: "$SPATH
    echo "FEXTENSION: "$FEXTENSION
fi

# get files
find ${SPATH} | grep -f ${UPD} | grep ${FEXTENSION} >processed_files.txt

for ID in `cat ${UPD}`
do
    #echo $ID
    R1=$(grep -e "${ID}.*R1" processed_files.txt)
    R2=$(grep -e "${ID}.*R2" processed_files.txt)
    echo "cat "$R1" >"$ID"_R1.fastq.gz"
    echo "cat "$R2" >"$ID"_R2.fastq.gz"
done