#!/usr/bin/env bash
# Bulk download script for GSE125970
# Generated from Yeo Lab Publications Database
# Total files: 15

OUTDIR="GSE125970"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE125nnn/GSE125970/suppl/GSE125970_cell_info.txt.gz" -O "GSE125970_cell_info.txt.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE125nnn/GSE125970/suppl/GSE125970_raw_UMIcounts.txt.gz" -O "GSE125970_raw_UMIcounts.txt.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE125nnn/GSE125970/suppl/GSE125970_scale_data.txt.gz" -O "GSE125970_scale_data.txt.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 "SRR8513794"
gz1="$(_compress_if_exists 'SRR8513794_1' || true)"
gz2="$(_compress_if_exists 'SRR8513794_2' || true)"
gzs="$(_compress_if_exists 'SRR8513794' || true)"

fasterq-dump --split-files "SRR8513795"
gz1="$(_compress_if_exists 'SRR8513795_1' || true)"
gz2="$(_compress_if_exists 'SRR8513795_2' || true)"
gzs="$(_compress_if_exists 'SRR8513795' || true)"

fasterq-dump --split-files "SRR8513796"
gz1="$(_compress_if_exists 'SRR8513796_1' || true)"
gz2="$(_compress_if_exists 'SRR8513796_2' || true)"
gzs="$(_compress_if_exists 'SRR8513796' || true)"

fasterq-dump --split-files "SRR8513797"
gz1="$(_compress_if_exists 'SRR8513797_1' || true)"
gz2="$(_compress_if_exists 'SRR8513797_2' || true)"
gzs="$(_compress_if_exists 'SRR8513797' || true)"

fasterq-dump --split-files "SRR8513798"
gz1="$(_compress_if_exists 'SRR8513798_1' || true)"
gz2="$(_compress_if_exists 'SRR8513798_2' || true)"
gzs="$(_compress_if_exists 'SRR8513798' || true)"

fasterq-dump --split-files "SRR8513799"
gz1="$(_compress_if_exists 'SRR8513799_1' || true)"
gz2="$(_compress_if_exists 'SRR8513799_2' || true)"
gzs="$(_compress_if_exists 'SRR8513799' || true)"


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513794/SRR8513794"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513795/SRR8513795"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513796/SRR8513796"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513797/SRR8513797"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513798/SRR8513798"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513799/SRR8513799"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513794/SRR8513794"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513795/SRR8513795"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513796/SRR8513796"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513797/SRR8513797"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513798/SRR8513798"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR8513799/SRR8513799"

echo "Download complete. Files saved to $OUTDIR"