#!/usr/bin/env bash
# Bulk download script for GSE195493
# Generated from Yeo Lab Publications Database
# Total files: 11

OUTDIR="GSE195493"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE195nnn/GSE195493/suppl/GSE195493_CYTOvNUCLEAR_fractionation.csv.gz" -O "GSE195493_CYTOvNUCLEAR_fractionation.csv.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 "SRR17771270"
gz1="$(_compress_if_exists 'SRR17771270_1' || true)"
gz2="$(_compress_if_exists 'SRR17771270_2' || true)"
gzs="$(_compress_if_exists 'SRR17771270' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "Cyto_frac_Rep2_R1.fastq.gz"
fi
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz2" ]; then
  mv -f "$gz2" "Cyto_frac_Rep2_R2.fastq.gz"
fi

fasterq-dump --split-files "SRR17771271"
gz1="$(_compress_if_exists 'SRR17771271_1' || true)"
gz2="$(_compress_if_exists 'SRR17771271_2' || true)"
gzs="$(_compress_if_exists 'SRR17771271' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "Cyto_frac_Rep1_R1.fastq.gz"
fi
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz2" ]; then
  mv -f "$gz2" "Cyto_frac_Rep1_R2.fastq.gz"
fi

fasterq-dump --split-files "SRR17771272"
gz1="$(_compress_if_exists 'SRR17771272_1' || true)"
gz2="$(_compress_if_exists 'SRR17771272_2' || true)"
gzs="$(_compress_if_exists 'SRR17771272' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "Nuclear_frac_Rep2_R1.fastq.gz"
fi
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz2" ]; then
  mv -f "$gz2" "Nuclear_frac_Rep2_R2.fastq.gz"
fi

fasterq-dump --split-files "SRR17771273"
gz1="$(_compress_if_exists 'SRR17771273_1' || true)"
gz2="$(_compress_if_exists 'SRR17771273_2' || true)"
gzs="$(_compress_if_exists 'SRR17771273' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "Nuclear_frac_Rep1_R1.fastq.gz"
fi
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz2" ]; then
  mv -f "$gz2" "Nuclear_frac_Rep1_R2.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR17771270/SRR17771270"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR17771271/SRR17771271"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR17771272/SRR17771272"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR17771273/SRR17771273"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR17771271/SRR17771271"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR17771270/SRR17771270"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR17771273/SRR17771273"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR17771272/SRR17771272"
curl -L -O -C - "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos8/sra-pub-zq-820/SRR017/17771/SRR17771272/SRR17771272.lite.1"
curl -L -O -C - "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos8/sra-pub-zq-820/SRR017/17771/SRR17771273/SRR17771273.lite.1"

echo "Download complete. Files saved to $OUTDIR"