#!/usr/bin/env bash
# Bulk download script for GSE198212
# Generated from Yeo Lab Publications Database
# Total files: 31

OUTDIR="GSE198212"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE198nnn/GSE198212/suppl/GSE198212_NONO_10R_CLIP.peaks.normed.compressed.filtered.annotate.bed.gz" -O "GSE198212_NONO_10R_CLIP.peaks.normed.compressed.filtered.annotate.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE198nnn/GSE198212/suppl/GSE198212_NONO_10R_CLIP_rep2.peaks.normed.compressed.filtered.annotate.bed.gz" -O "GSE198212_NONO_10R_CLIP_rep2.peaks.normed.compressed.filtered.annotate.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE198nnn/GSE198212/suppl/GSE198212_NONO_10S_CLIP.peaks.normed.compressed.filtered.annotate.bed.gz" -O "GSE198212_NONO_10S_CLIP.peaks.normed.compressed.filtered.annotate.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE198nnn/GSE198212/suppl/GSE198212_NONO_10S_CLIP_rep2.peaks.normed.compressed.filtered.annotate.bed.gz" -O "GSE198212_NONO_10S_CLIP_rep2.peaks.normed.compressed.filtered.annotate.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE198nnn/GSE198212/suppl/GSE198212_NONO_DMSO_CLIP.peaks.normed.compressed.filtered.annotate.bed.gz" -O "GSE198212_NONO_DMSO_CLIP.peaks.normed.compressed.filtered.annotate.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE198nnn/GSE198212/suppl/GSE198212_NONO_DMSO_CLIP_rep2.peaks.normed.compressed.filtered.annotate.bed.gz" -O "GSE198212_NONO_DMSO_CLIP_rep2.peaks.normed.compressed.filtered.annotate.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE198nnn/GSE198212/suppl/GSE198212_RAW.tar" -O "GSE198212_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 "SRR18278227"
gz1="$(_compress_if_exists 'SRR18278227_1' || true)"
gz2="$(_compress_if_exists 'SRR18278227_2' || true)"
gzs="$(_compress_if_exists 'SRR18278227' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "10S_INPUT_rep2.fastq.gz"
fi

fasterq-dump --split-files "SRR18278228"
gz1="$(_compress_if_exists 'SRR18278228_1' || true)"
gz2="$(_compress_if_exists 'SRR18278228_2' || true)"
gzs="$(_compress_if_exists 'SRR18278228' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "10S_INPUT_rep1.fastq.gz"
fi

fasterq-dump --split-files "SRR18278229"
gz1="$(_compress_if_exists 'SRR18278229_1' || true)"
gz2="$(_compress_if_exists 'SRR18278229_2' || true)"
gzs="$(_compress_if_exists 'SRR18278229' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "10S_CLIP_rep2.fastq.gz"
fi

fasterq-dump --split-files "SRR18278230"
gz1="$(_compress_if_exists 'SRR18278230_1' || true)"
gz2="$(_compress_if_exists 'SRR18278230_2' || true)"
gzs="$(_compress_if_exists 'SRR18278230' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "10S_CLIP_rep1.fastq.gz"
fi

fasterq-dump --split-files "SRR18278231"
gz1="$(_compress_if_exists 'SRR18278231_1' || true)"
gz2="$(_compress_if_exists 'SRR18278231_2' || true)"
gzs="$(_compress_if_exists 'SRR18278231' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "10R_INPUT_rep2.fastq.gz"
fi

fasterq-dump --split-files "SRR18278232"
gz1="$(_compress_if_exists 'SRR18278232_1' || true)"
gz2="$(_compress_if_exists 'SRR18278232_2' || true)"
gzs="$(_compress_if_exists 'SRR18278232' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "10R_INPUT_rep1.fastq.gz"
fi

fasterq-dump --split-files "SRR18278233"
gz1="$(_compress_if_exists 'SRR18278233_1' || true)"
gz2="$(_compress_if_exists 'SRR18278233_2' || true)"
gzs="$(_compress_if_exists 'SRR18278233' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "10R_CLIP_rep2.fastq.gz"
fi

fasterq-dump --split-files "SRR18278234"
gz1="$(_compress_if_exists 'SRR18278234_1' || true)"
gz2="$(_compress_if_exists 'SRR18278234_2' || true)"
gzs="$(_compress_if_exists 'SRR18278234' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "10R_CLIP_rep1.fastq.gz"
fi

fasterq-dump --split-files "SRR18278235"
gz1="$(_compress_if_exists 'SRR18278235_1' || true)"
gz2="$(_compress_if_exists 'SRR18278235_2' || true)"
gzs="$(_compress_if_exists 'SRR18278235' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "DMSO_INPUT_rep2.fastq.gz"
fi

fasterq-dump --split-files "SRR18278236"
gz1="$(_compress_if_exists 'SRR18278236_1' || true)"
gz2="$(_compress_if_exists 'SRR18278236_2' || true)"
gzs="$(_compress_if_exists 'SRR18278236' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "DMSO_INPUT_rep1.fastq.gz"
fi

fasterq-dump --split-files "SRR18278237"
gz1="$(_compress_if_exists 'SRR18278237_1' || true)"
gz2="$(_compress_if_exists 'SRR18278237_2' || true)"
gzs="$(_compress_if_exists 'SRR18278237' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "DMSO_CLIP_rep2.fastq.gz"
fi

fasterq-dump --split-files "SRR18278238"
gz1="$(_compress_if_exists 'SRR18278238_1' || true)"
gz2="$(_compress_if_exists 'SRR18278238_2' || true)"
gzs="$(_compress_if_exists 'SRR18278238' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "DMSO_CLIP_rep1.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278227/SRR18278227"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278228/SRR18278228"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278229/SRR18278229"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278230/SRR18278230"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278231/SRR18278231"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278232/SRR18278232"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278233/SRR18278233"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278234/SRR18278234"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278235/SRR18278235"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278236/SRR18278236"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278237/SRR18278237"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278238/SRR18278238"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278234/SRR18278234"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278233/SRR18278233"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278232/SRR18278232"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278231/SRR18278231"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278230/SRR18278230"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278229/SRR18278229"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278228/SRR18278228"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278227/SRR18278227"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278238/SRR18278238"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278237/SRR18278237"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278236/SRR18278236"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18278235/SRR18278235"

echo "Download complete. Files saved to $OUTDIR"