#!/usr/bin/env bash
# Bulk download script for GSE176060
# Generated from Yeo Lab Publications Database
# Total files: 18

OUTDIR="GSE176060"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE176nnn/GSE176060/suppl/GSE176060_R636S_peaks.bed.gz" -O "GSE176060_R636S_peaks.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE176nnn/GSE176060/suppl/GSE176060_WT_peaks.bed.gz" -O "GSE176060_WT_peaks.bed.gz"

# --- 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 "SRR14724399"
gz1="$(_compress_if_exists 'SRR14724399_1' || true)"
gz2="$(_compress_if_exists 'SRR14724399_2' || true)"
gzs="$(_compress_if_exists 'SRR14724399' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "SB_RBM20_WT1_IN_R_S50_L003_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR14724400"
gz1="$(_compress_if_exists 'SRR14724400_1' || true)"
gz2="$(_compress_if_exists 'SRR14724400_2' || true)"
gzs="$(_compress_if_exists 'SRR14724400' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "SB_RBM20_WT1_CLIP_R_S51_L003_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR14724401"
gz1="$(_compress_if_exists 'SRR14724401_1' || true)"
gz2="$(_compress_if_exists 'SRR14724401_2' || true)"
gzs="$(_compress_if_exists 'SRR14724401' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "SB_RBM20_WT2_IN_R_S64_L004_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR14724402"
gz1="$(_compress_if_exists 'SRR14724402_1' || true)"
gz2="$(_compress_if_exists 'SRR14724402_2' || true)"
gzs="$(_compress_if_exists 'SRR14724402' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "SB_RBM20_WT2_CLIP_R_S65_L004_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR14724403"
gz1="$(_compress_if_exists 'SRR14724403_1' || true)"
gz2="$(_compress_if_exists 'SRR14724403_2' || true)"
gzs="$(_compress_if_exists 'SRR14724403' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "SB_RBM20_Homo1_IN_R_S52_L003_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR14724404"
gz1="$(_compress_if_exists 'SRR14724404_1' || true)"
gz2="$(_compress_if_exists 'SRR14724404_2' || true)"
gzs="$(_compress_if_exists 'SRR14724404' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "SB_RBM20_Homo1_CLIP_R_S53_L003_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR14724405"
gz1="$(_compress_if_exists 'SRR14724405_1' || true)"
gz2="$(_compress_if_exists 'SRR14724405_2' || true)"
gzs="$(_compress_if_exists 'SRR14724405' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "SB_RBM20_Homo2_IN_R_S66_L004_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR14724406"
gz1="$(_compress_if_exists 'SRR14724406_1' || true)"
gz2="$(_compress_if_exists 'SRR14724406_2' || true)"
gzs="$(_compress_if_exists 'SRR14724406' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "SB_RBM20_Homo2_CLIP_R_S67_L004_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/SRR14724399/SRR14724399"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724400/SRR14724400"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724401/SRR14724401"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724402/SRR14724402"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724403/SRR14724403"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724404/SRR14724404"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724405/SRR14724405"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724406/SRR14724406"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724404/SRR14724404"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724403/SRR14724403"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724406/SRR14724406"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724405/SRR14724405"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724400/SRR14724400"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724399/SRR14724399"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724402/SRR14724402"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR14724401/SRR14724401"

echo "Download complete. Files saved to $OUTDIR"