#!/usr/bin/env bash
# Bulk download script for GSE142307
# Generated from Yeo Lab Publications Database
# Total files: 13

OUTDIR="GSE142307"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE142nnn/GSE142307/suppl/GSE142307_RAW.tar" -O "GSE142307_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 "SRR10735581"
gz1="$(_compress_if_exists 'SRR10735581_1' || true)"
gz2="$(_compress_if_exists 'SRR10735581_2' || true)"
gzs="$(_compress_if_exists 'SRR10735581' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "shCtrl_H3K4me2.fastq.gz"
fi

fasterq-dump --split-files "SRR10735582"
gz1="$(_compress_if_exists 'SRR10735582_1' || true)"
gz2="$(_compress_if_exists 'SRR10735582_2' || true)"
gzs="$(_compress_if_exists 'SRR10735582' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "shCtrl_H3K4me3.fastq.gz"
fi

fasterq-dump --split-files "SRR10735584"
gz1="$(_compress_if_exists 'SRR10735584_1' || true)"
gz2="$(_compress_if_exists 'SRR10735584_2' || true)"
gzs="$(_compress_if_exists 'SRR10735584' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "shStau2_H3K4me2.fastq.gz"
fi

fasterq-dump --split-files "SRR10735585"
gz1="$(_compress_if_exists 'SRR10735585_1' || true)"
gz2="$(_compress_if_exists 'SRR10735585_2' || true)"
gzs="$(_compress_if_exists 'SRR10735585' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "shStau2_H3K4me3.fastq.gz"
fi

fasterq-dump --split-files "SRR10735586"
gz1="$(_compress_if_exists 'SRR10735586_1' || true)"
gz2="$(_compress_if_exists 'SRR10735586_2' || true)"
gzs="$(_compress_if_exists 'SRR10735586' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "shCtrl_Input.fastq.gz"
fi

fasterq-dump --split-files "SRR10735587"
gz1="$(_compress_if_exists 'SRR10735587_1' || true)"
gz2="$(_compress_if_exists 'SRR10735587_2' || true)"
gzs="$(_compress_if_exists 'SRR10735587' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "shStau2_Input.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735581/SRR10735581"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735582/SRR10735582"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735584/SRR10735584"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735585/SRR10735585"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735586/SRR10735586"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735587/SRR10735587"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735581/SRR10735581"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735582/SRR10735582"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735586/SRR10735586"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735584/SRR10735584"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735585/SRR10735585"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR10735587/SRR10735587"

echo "Download complete. Files saved to $OUTDIR"