#!/usr/bin/env bash
# Bulk download script for GSE166402
# Generated from Yeo Lab Publications Database
# Total files: 20

OUTDIR="GSE166402"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE166nnn/GSE166402/suppl/GSE166402_PRBF_1.vs.PRBF_2.bed.gz" -O "GSE166402_PRBF_1.vs.PRBF_2.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE166nnn/GSE166402/suppl/GSE166402_PTIA_1.vs.PTIA_2.bed.gz" -O "GSE166402_PTIA_1.vs.PTIA_2.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE166nnn/GSE166402/suppl/GSE166402_RAW.tar" -O "GSE166402_RAW.tar"

# --- SRA run files ---
# Tip: use 'fasterq-dump' from SRA Toolkit for FASTQ conversion
#      with optional renaming to original submitted FASTQ names.
# Set to 1 to rename SRR outputs (e.g. SRR_1.fastq.gz -> sample_R1.fastq.gz)
RENAME_SRA_TO_ORIGINAL=1

_compress_if_exists() {
  local stem="$1"
  if [ -f "${stem}.fastq" ]; then
    gzip -f "${stem}.fastq"
    echo "${stem}.fastq.gz"
    return 0
  fi
  if [ -f "${stem}.fq" ]; then
    gzip -f "${stem}.fq"
    echo "${stem}.fq.gz"
    return 0
  fi
  return 1
}

# Option A: Download via SRA Toolkit (recommended)
fasterq-dump --split-files "SRR13663711"
gz1="$(_compress_if_exists 'SRR13663711_1' || true)"
gz2="$(_compress_if_exists 'SRR13663711_2' || true)"
gzs="$(_compress_if_exists 'SRR13663711' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "NTIA_1_S1_L001_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR13663712"
gz1="$(_compress_if_exists 'SRR13663712_1' || true)"
gz2="$(_compress_if_exists 'SRR13663712_2' || true)"
gzs="$(_compress_if_exists 'SRR13663712' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "NTIA_2_S2_L001_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR13663713"
gz1="$(_compress_if_exists 'SRR13663713_1' || true)"
gz2="$(_compress_if_exists 'SRR13663713_2' || true)"
gzs="$(_compress_if_exists 'SRR13663713' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "PTIA_1_S7_L001_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR13663714"
gz1="$(_compress_if_exists 'SRR13663714_1' || true)"
gz2="$(_compress_if_exists 'SRR13663714_2' || true)"
gzs="$(_compress_if_exists 'SRR13663714' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "PTIA_2_S8_L001_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR13663715"
gz1="$(_compress_if_exists 'SRR13663715_1' || true)"
gz2="$(_compress_if_exists 'SRR13663715_2' || true)"
gzs="$(_compress_if_exists 'SRR13663715' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "NRBF_1_S3_L001_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR13663716"
gz1="$(_compress_if_exists 'SRR13663716_1' || true)"
gz2="$(_compress_if_exists 'SRR13663716_2' || true)"
gzs="$(_compress_if_exists 'SRR13663716' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "NRBF_2_S4_L001_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR13663717"
gz1="$(_compress_if_exists 'SRR13663717_1' || true)"
gz2="$(_compress_if_exists 'SRR13663717_2' || true)"
gzs="$(_compress_if_exists 'SRR13663717' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "PRBF_1_S9_L001_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR13663718"
gz1="$(_compress_if_exists 'SRR13663718_1' || true)"
gz2="$(_compress_if_exists 'SRR13663718_2' || true)"
gzs="$(_compress_if_exists 'SRR13663718' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "PRBF_2_S10_L001_R1_001.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663711/SRR13663711"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663712/SRR13663712"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663713/SRR13663713"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663714/SRR13663714"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663715/SRR13663715"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663716/SRR13663716"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663717/SRR13663717"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663718/SRR13663718"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663715/SRR13663715"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663716/SRR13663716"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663711/SRR13663711"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663712/SRR13663712"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663717/SRR13663717"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663718/SRR13663718"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663713/SRR13663713"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR13663714/SRR13663714"
curl -L -O -C - "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos8/sra-pub-zq-818/SRR013/13663/SRR13663712/SRR13663712.lite.1"

echo "Download complete. Files saved to $OUTDIR"