#!/usr/bin/env bash
# Bulk download script for GSE180686
# Generated from Yeo Lab Publications Database
# Total files: 11

OUTDIR="GSE180686"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE180nnn/GSE180686/suppl/GSE180686_4114_CLIP1_rep1.vs.4114_CLIP2_rep2.bed.gz" -O "GSE180686_4114_CLIP1_rep1.vs.4114_CLIP2_rep2.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE180nnn/GSE180686/suppl/GSE180686_RAW.tar" -O "GSE180686_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 "SRR15222627"
gz1="$(_compress_if_exists 'SRR15222627_1' || true)"
gz2="$(_compress_if_exists 'SRR15222627_2' || true)"
gzs="$(_compress_if_exists 'SRR15222627' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "4114_CLIP1_S39_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR15222628"
gz1="$(_compress_if_exists 'SRR15222628_1' || true)"
gz2="$(_compress_if_exists 'SRR15222628_2' || true)"
gzs="$(_compress_if_exists 'SRR15222628' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "4114_INPUT1_S38_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR15222629"
gz1="$(_compress_if_exists 'SRR15222629_1' || true)"
gz2="$(_compress_if_exists 'SRR15222629_2' || true)"
gzs="$(_compress_if_exists 'SRR15222629' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "4114_CLIP2_S41_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR15222630"
gz1="$(_compress_if_exists 'SRR15222630_1' || true)"
gz2="$(_compress_if_exists 'SRR15222630_2' || true)"
gzs="$(_compress_if_exists 'SRR15222630' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "4114_INPUT2_S40_L002_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/SRR15222627/SRR15222627"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR15222628/SRR15222628"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR15222629/SRR15222629"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR15222630/SRR15222630"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR15222627/SRR15222627"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR15222629/SRR15222629"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR15222628/SRR15222628"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR15222630/SRR15222630"
curl -L -O -C - "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos1/sra-pub-zq-38/SRR015/15222/SRR15222630/SRR15222630.lite.1"

echo "Download complete. Files saved to $OUTDIR"