#!/usr/bin/env bash
# Bulk download script for GSE74583
# Generated from Yeo Lab Publications Database
# Total files: 13

OUTDIR="GSE74583"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE74nnn/GSE74583/suppl/GSE74583_ppar_delta_rpkms.txt.gz" -O "GSE74583_ppar_delta_rpkms.txt.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 "SRR2889691"
gz1="$(_compress_if_exists 'SRR2889691_1' || true)"
gz2="$(_compress_if_exists 'SRR2889691_2' || true)"
gzs="$(_compress_if_exists 'SRR2889691' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "FA1395.fq.gz"
fi

fasterq-dump --split-files "SRR2889692"
gz1="$(_compress_if_exists 'SRR2889692_1' || true)"
gz2="$(_compress_if_exists 'SRR2889692_2' || true)"
gzs="$(_compress_if_exists 'SRR2889692' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "FA1411.fq.gz"
fi

fasterq-dump --split-files "SRR2889693"
gz1="$(_compress_if_exists 'SRR2889693_1' || true)"
gz2="$(_compress_if_exists 'SRR2889693_2' || true)"
gzs="$(_compress_if_exists 'SRR2889693' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "FA1412.fq.gz"
fi

fasterq-dump --split-files "SRR2889694"
gz1="$(_compress_if_exists 'SRR2889694_1' || true)"
gz2="$(_compress_if_exists 'SRR2889694_2' || true)"
gzs="$(_compress_if_exists 'SRR2889694' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "FA1376.fq.gz"
fi

fasterq-dump --split-files "SRR2889695"
gz1="$(_compress_if_exists 'SRR2889695_1' || true)"
gz2="$(_compress_if_exists 'SRR2889695_2' || true)"
gzs="$(_compress_if_exists 'SRR2889695' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "FA1377.fq.gz"
fi

fasterq-dump --split-files "SRR2889696"
gz1="$(_compress_if_exists 'SRR2889696_1' || true)"
gz2="$(_compress_if_exists 'SRR2889696_2' || true)"
gzs="$(_compress_if_exists 'SRR2889696' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "FA1397.fq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889691/SRR2889691"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889692/SRR2889692"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889693/SRR2889693"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889694/SRR2889694"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889695/SRR2889695"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889696/SRR2889696"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889694/SRR2889694"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889695/SRR2889695"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889691/SRR2889691"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889696/SRR2889696"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889692/SRR2889692"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2889693/SRR2889693"

echo "Download complete. Files saved to $OUTDIR"