#!/usr/bin/env bash
# Bulk download script for GSE33584
# Generated from Yeo Lab Publications Database
# Total files: 10

OUTDIR="GSE33584"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE33nnn/GSE33584/suppl/GSE33584_RAW.tar" -O "GSE33584_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 "SRR363673"
gz1="$(_compress_if_exists 'SRR363673_1' || true)"
gz2="$(_compress_if_exists 'SRR363673_2' || true)"
gzs="$(_compress_if_exists 'SRR363673' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "smRNA_mock_24h.fastq.gz"
fi

fasterq-dump --split-files "SRR363674"
gz1="$(_compress_if_exists 'SRR363674_1' || true)"
gz2="$(_compress_if_exists 'SRR363674_2' || true)"
gzs="$(_compress_if_exists 'SRR363674' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "smRNA_mock_72h.fastq.gz"
fi

fasterq-dump --split-files "SRR363675"
gz1="$(_compress_if_exists 'SRR363675_1' || true)"
gz2="$(_compress_if_exists 'SRR363675_2' || true)"
gzs="$(_compress_if_exists 'SRR363675' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "smRNA_infected_24h.fastq.gz"
fi

fasterq-dump --split-files "SRR363676"
gz1="$(_compress_if_exists 'SRR363676_1' || true)"
gz2="$(_compress_if_exists 'SRR363676_2' || true)"
gzs="$(_compress_if_exists 'SRR363676' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "smRNA_infected_72h.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363673/SRR363673"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363674/SRR363674"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363675/SRR363675"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363676/SRR363676"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363675/SRR363675"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363676/SRR363676"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363673/SRR363673"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363674/SRR363674"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR363676/SRR363676"

echo "Download complete. Files saved to $OUTDIR"