#!/usr/bin/env bash
# Bulk download script for GSE69585
# Generated from Yeo Lab Publications Database
# Total files: 21

OUTDIR="GSE69585"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE69nnn/GSE69585/suppl/GSE69585_RAW.tar" -O "GSE69585_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 "SRR2051427"
gz1="$(_compress_if_exists 'SRR2051427_1' || true)"
gz2="$(_compress_if_exists 'SRR2051427_2' || true)"
gzs="$(_compress_if_exists 'SRR2051427' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "D-in_AGCGATAG-TATAGCCT_L001_R1.fastq.gz"
fi

fasterq-dump --split-files "SRR2051428"
gz1="$(_compress_if_exists 'SRR2051428_1' || true)"
gz2="$(_compress_if_exists 'SRR2051428_2' || true)"
gzs="$(_compress_if_exists 'SRR2051428' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "D-IP_ATTACTCG-ATAGAGGC_L001_R1.fastq.gz"
fi

fasterq-dump --split-files "SRR2051429"
gz1="$(_compress_if_exists 'SRR2051429_1' || true)"
gz2="$(_compress_if_exists 'SRR2051429_2' || true)"
gzs="$(_compress_if_exists 'SRR2051429' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "F-in_TAATGCGC-TATAGCCT_L004_R1.fastq.gz"
fi

fasterq-dump --split-files "SRR2051430"
gz1="$(_compress_if_exists 'SRR2051430_1' || true)"
gz2="$(_compress_if_exists 'SRR2051430_2' || true)"
gzs="$(_compress_if_exists 'SRR2051430' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "F-IP_CGGCTATG-TATAGCCT_L007_R1.fastq.gz"
fi

fasterq-dump --split-files "SRR2051431"
gz1="$(_compress_if_exists 'SRR2051431_1' || true)"
gz2="$(_compress_if_exists 'SRR2051431_2' || true)"
gzs="$(_compress_if_exists 'SRR2051431' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "K-in_TCCGGAGA-ATAGAGGC_L001_R1.fastq.gz"
fi

fasterq-dump --split-files "SRR2051432"
gz1="$(_compress_if_exists 'SRR2051432_1' || true)"
gz2="$(_compress_if_exists 'SRR2051432_2' || true)"
gzs="$(_compress_if_exists 'SRR2051432' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "K-IP_CGCTCATT-ATAGAGGC_L001_R1.fastq.gz"
fi

fasterq-dump --split-files "SRR2051433"
gz1="$(_compress_if_exists 'SRR2051433_1' || true)"
gz2="$(_compress_if_exists 'SRR2051433_2' || true)"
gzs="$(_compress_if_exists 'SRR2051433' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "W-in_TCCGCGAA-TATAGCCT.fastq.gz"
fi

fasterq-dump --split-files "SRR2051434"
gz1="$(_compress_if_exists 'SRR2051434_1' || true)"
gz2="$(_compress_if_exists 'SRR2051434_2' || true)"
gzs="$(_compress_if_exists 'SRR2051434' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "W-IP_TCTCGCGC-TATAGCCT_L001_R1.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051427/SRR2051427"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051428/SRR2051428"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051429/SRR2051429"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051430/SRR2051430"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051431/SRR2051431"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051432/SRR2051432"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051433/SRR2051433"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051434/SRR2051434"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051427/SRR2051427"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051428/SRR2051428"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051429/SRR2051429"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051430/SRR2051430"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051431/SRR2051431"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051432/SRR2051432"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051427/SRR2051427"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051432/SRR2051432"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051433/SRR2051433"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051434/SRR2051434"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051433/SRR2051433"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR2051434/SRR2051434"

echo "Download complete. Files saved to $OUTDIR"