#!/bin/bash
#PBS -l walltime=01:00:00
#PBS -l ncpus=1,mem=2gb
#PBS -q uv2000
#PBS -N down_setup
#PBS -j oe


### Setup the folder structure for the downstream analysis###
BASE=/scratch/u035/u035/shared/analysis/wes_pilot
WORK_DIR=$BASE/${PROJECT_ID}
VCF_DIR=${WORK_DIR}/VCF
PED_DIR=${WORK_DIR}/PED
LOG_DIR=${WORK_DIR}/LOG
G2P_DIR=${WORK_DIR}/G2P
VASE_DIR=${WORK_DIR}/VASE 
COV_DIR=${WORK_DIR}/COV
DEC_DIR=${WORK_DIR}/DECIPHER
IGV_DIR=${DEC_DIR}/IGV
CNV_DIR=${WORK_DIR}/CNV
SCRIPTS_DIR=/home/u035/u035/shared/scripts


### Tools
PYTHON2=/home/u035/u035/shared/software/bcbio/anaconda/envs/python2/bin/python2.7



# check if ${WORK_DIR} already exists - if so, exit - to prevent accidental overwriting
if [ -d "${WORK_DIR}" ]; then
  echo "${WORK_DIR} already exists - EXIT! If really intended, delete manually!!!!"
  exit
fi


echo "PROJECT_ID = ${PROJECT_ID}"	# this the the folder (${BASE}/${PROJECT_ID}) where the downstream analysis will be done
echo "SOURCE_DIR = ${SOURCE_DIR}"	# the command-line argument SOURCE_DIR is the general path to the source VCF, BAM and PED files
S_PED_DIR=${SOURCE_DIR}/../params	# requires that the PED files are in this folder




# create the working dir and the required subfolders
mkdir ${WORK_DIR}
mkdir ${VCF_DIR}
mkdir ${PED_DIR}
mkdir ${LOG_DIR}
mkdir ${G2P_DIR}
mkdir ${VASE_DIR}
mkdir ${COV_DIR}
mkdir ${DEC_DIR}
mkdir ${IGV_DIR}
mkdir ${CNV_DIR}
echo "Created ${WORK_DIR} for this batch and all the required subfolders"


######################################################
###   Copy the VCF and PED file per each family    ###
######################################################

SOURCE_VCF_DIRS=${SOURCE_DIR}/????-??-??_*
echo "Found the following source VCF folders"

for S_VCF_DIR in ${SOURCE_VCF_DIRS}
do
#  echo "  ${S_VCF_DIR}"
  VCF_DIR_NAME="${S_VCF_DIR##*/}" 
#  echo "    ${VCF_DIR_NAME}" 
  IFS=_ read -ra my_arr <<< "${VCF_DIR_NAME}"
  BATCH=${my_arr[1]}
  FAM_ID=""
  for ELEMENT in ${my_arr[@]:2}; do
    FAM_ID+="${ELEMENT}_"
  done 
  FAM_ID=${FAM_ID::-1}
#  echo "      BATCH = ${BATCH}, FAM_ID = ${FAM_ID}"
   
  S_VCF_FILE=${S_VCF_DIR}/${FAM_ID}-gatk-haplotype-annotated.vcf.gz
  S_PED_FILE=${S_PED_DIR}/${BATCH}_${FAM_ID}.ped

  cp ${S_VCF_FILE} ${VCF_DIR}
  cp ${S_PED_FILE} ${PED_DIR} 
  echo "  copied ${S_VCF_FILE} to ${VCF_DIR}" 
  echo "  copied ${S_PED_FILE} to ${PED_DIR}"
done





######################################################################################
### generate the FAM_IDs.txt, PRO_IDs.txt and FAM_PRO.txt *only for trio* families ###
######################################################################################

time ${PYTHON2} ${SCRIPTS_DIR}/extract_trio_FAM_PRO_ID.py ${WORK_DIR}

echo ""
echo ""
echo "OK: Setup for PROJECT_ID = $PROJECT_ID successful"