#!/usr/bin/env bash
# Bulk download script for GSE199650
# Generated from Yeo Lab Publications Database
# Total files: 13

OUTDIR="GSE199650"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE199nnn/GSE199650/suppl/GSE199650_RAW.tar" -O "GSE199650_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 "SRR18516352"
gz1="$(_compress_if_exists 'SRR18516352_1' || true)"
gz2="$(_compress_if_exists 'SRR18516352_2' || true)"
gzs="$(_compress_if_exists 'SRR18516352' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "IP2_input.fastq.gz"
fi

fasterq-dump --split-files "SRR18516353"
gz1="$(_compress_if_exists 'SRR18516353_1' || true)"
gz2="$(_compress_if_exists 'SRR18516353_2' || true)"
gzs="$(_compress_if_exists 'SRR18516353' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "IP2_IP.fastq.gz"
fi

fasterq-dump --split-files "SRR18516354"
gz1="$(_compress_if_exists 'SRR18516354_1' || true)"
gz2="$(_compress_if_exists 'SRR18516354_2' || true)"
gzs="$(_compress_if_exists 'SRR18516354' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "IP1_input.fastq.gz"
fi

fasterq-dump --split-files "SRR18516355"
gz1="$(_compress_if_exists 'SRR18516355_1' || true)"
gz2="$(_compress_if_exists 'SRR18516355_2' || true)"
gzs="$(_compress_if_exists 'SRR18516355' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "IP1_IP.fastq.gz"
fi

fasterq-dump --split-files "SRR18516356"
gz1="$(_compress_if_exists 'SRR18516356_1' || true)"
gz2="$(_compress_if_exists 'SRR18516356_2' || true)"
gzs="$(_compress_if_exists 'SRR18516356' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "Flag_input.fastq.gz"
fi

fasterq-dump --split-files "SRR18516357"
gz1="$(_compress_if_exists 'SRR18516357_1' || true)"
gz2="$(_compress_if_exists 'SRR18516357_2' || true)"
gzs="$(_compress_if_exists 'SRR18516357' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" "Flag_IP.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516352/SRR18516352"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516353/SRR18516353"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516354/SRR18516354"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516355/SRR18516355"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516356/SRR18516356"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516357/SRR18516357"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516356/SRR18516356"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516357/SRR18516357"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516354/SRR18516354"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516355/SRR18516355"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516352/SRR18516352"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR18516353/SRR18516353"

echo "Download complete. Files saved to $OUTDIR"