#!/usr/bin/env bash
# Bulk download script for GSE77633
# Generated from Yeo Lab Publications Database
# Total files: 9

OUTDIR="GSE77633"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE77nnn/GSE77633/suppl/GSE77633_RAW.tar" -O "GSE77633_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 "SRR3147674"
gz1="$(_compress_if_exists 'SRR3147674_1' || true)"
gz2="$(_compress_if_exists 'SRR3147674_2' || true)"
gzs="$(_compress_if_exists 'SRR3147674' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "H2_NoIndex_L001_R1.R10_lowRNAse_H_2.randomer.fastq.gz"
fi

fasterq-dump --split-files "SRR3147675"
gz1="$(_compress_if_exists 'SRR3147675_1' || true)"
gz2="$(_compress_if_exists 'SRR3147675_2' || true)"
gzs="$(_compress_if_exists 'SRR3147675' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "H2_NoIndex_L001_R1.R12_lowRNAse_H_1.randomer.fastq.gz"
fi

fasterq-dump --split-files "SRR3147676"
gz1="$(_compress_if_exists 'SRR3147676_1' || true)"
gz2="$(_compress_if_exists 'SRR3147676_2' || true)"
gzs="$(_compress_if_exists 'SRR3147676' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "M2_NoIndex_L002_R1.R10_lowRNAse_M_2.randomer.fastq.gz"
fi

fasterq-dump --split-files "SRR3147677"
gz1="$(_compress_if_exists 'SRR3147677_1' || true)"
gz2="$(_compress_if_exists 'SRR3147677_2' || true)"
gzs="$(_compress_if_exists 'SRR3147677' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "M2_NoIndex_L002_R1.R12_lowRNAse_M_1.randomer.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR3147674/SRR3147674"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR3147675/SRR3147675"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR3147676/SRR3147676"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR3147677/SRR3147677"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR3147674/SRR3147674"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR3147675/SRR3147675"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR3147676/SRR3147676"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR3147677/SRR3147677"

echo "Download complete. Files saved to $OUTDIR"