#!/usr/bin/env bash
# Bulk download script for GSE104949
# Generated from Yeo Lab Publications Database
# Total files: 13

OUTDIR=GSE104949
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE104nnn/GSE104949/suppl/GSE104949_RAW.tar -O GSE104949_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 SRR6170072
gz1="$(_compress_if_exists SRR6170072_1 || true)"
gz2="$(_compress_if_exists SRR6170072_2 || true)"
gzs="$(_compress_if_exists SRR6170072 || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" Trim25_CLIP_exp1.fq.gz
fi

fasterq-dump --split-files SRR6170073
gz1="$(_compress_if_exists SRR6170073_1 || true)"
gz2="$(_compress_if_exists SRR6170073_2 || true)"
gzs="$(_compress_if_exists SRR6170073 || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" Trim25_CLIP_exp2.fq.gz
fi

fasterq-dump --split-files SRR6170074
gz1="$(_compress_if_exists SRR6170074_1 || true)"
gz2="$(_compress_if_exists SRR6170074_2 || true)"
gzs="$(_compress_if_exists SRR6170074 || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" Trim25_CLIP_exp3.fq.gz
fi

fasterq-dump --split-files SRR6170075
gz1="$(_compress_if_exists SRR6170075_1 || true)"
gz2="$(_compress_if_exists SRR6170075_2 || true)"
gzs="$(_compress_if_exists SRR6170075 || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" Mock_CLIP_exp1.fq.gz
fi

fasterq-dump --split-files SRR6170076
gz1="$(_compress_if_exists SRR6170076_1 || true)"
gz2="$(_compress_if_exists SRR6170076_2 || true)"
gzs="$(_compress_if_exists SRR6170076 || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" Mock_CLIP_exp2.fq.gz
fi

fasterq-dump --split-files SRR6170077
gz1="$(_compress_if_exists SRR6170077_1 || true)"
gz2="$(_compress_if_exists SRR6170077_2 || true)"
gzs="$(_compress_if_exists SRR6170077 || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gzs" ]; then
  mv -f "$gzs" Mock_CLIP_exp3.fq.gz
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170072/SRR6170072
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170073/SRR6170073
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170074/SRR6170074
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170075/SRR6170075
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170076/SRR6170076
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170077/SRR6170077

# --- Additional data files ---
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170075/SRR6170075
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170076/SRR6170076
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170077/SRR6170077
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170072/SRR6170072
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170073/SRR6170073
curl -L -O -C - https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR6170074/SRR6170074

echo "Download complete. Files saved to $OUTDIR"