#!/usr/bin/env bash
# Bulk download script for GSE117776
# Generated from Yeo Lab Publications Database
# Total files: 12

OUTDIR="GSE117776"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE117nnn/GSE117776/suppl/GSE117776_fragileX_gene_expression.txt.gz" -O "GSE117776_fragileX_gene_expression.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 "SRR7610662"
gz1="$(_compress_if_exists 'SRR7610662_1' || true)"
gz2="$(_compress_if_exists 'SRR7610662_2' || true)"
gzs="$(_compress_if_exists 'SRR7610662' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "fragileX_sample_103108GP.1.fastq.gz"
fi
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz2" ]; then
  mv -f "$gz2" "fragileX_sample_103108GP.2.fastq.gz"
fi

fasterq-dump --split-files "SRR7610663"
gz1="$(_compress_if_exists 'SRR7610663_1' || true)"
gz2="$(_compress_if_exists 'SRR7610663_2' || true)"
gzs="$(_compress_if_exists 'SRR7610663' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "fragileX_sample_JS03.1.fastq.gz"
fi
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz2" ]; then
  mv -f "$gz2" "fragileX_sample_JS03.2.fastq.gz"
fi

fasterq-dump --split-files "SRR7610664"
gz1="$(_compress_if_exists 'SRR7610664_1' || true)"
gz2="$(_compress_if_exists 'SRR7610664_2' || true)"
gzs="$(_compress_if_exists 'SRR7610664' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "control_sample_UCD1407.1.fastq.gz"
fi
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz2" ]; then
  mv -f "$gz2" "control_sample_UCD1407.2.fastq.gz"
fi

fasterq-dump --split-files "SRR7610665"
gz1="$(_compress_if_exists 'SRR7610665_1' || true)"
gz2="$(_compress_if_exists 'SRR7610665_2' || true)"
gzs="$(_compress_if_exists 'SRR7610665' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "control_sample_103710XX.1.fastq.gz"
fi
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz2" ]; then
  mv -f "$gz2" "control_sample_103710XX.2.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610662/SRR7610662"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610663/SRR7610663"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610664/SRR7610664"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610665/SRR7610665"

# --- Additional data files ---
curl -L -O -C - "https://sra-downloadb.be-md.ncbi.nlm.nih.gov/sos5/sra-pub-zq-14/SRR007/610/SRR7610665.sralite.1"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610665/SRR7610665"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610664/SRR7610664"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610664/SRR7610664"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610662/SRR7610662"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610662/SRR7610662"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR7610663/SRR7610663"

echo "Download complete. Files saved to $OUTDIR"