#!/usr/bin/env bash
# Bulk download script for GSE228444
# Generated from Yeo Lab Publications Database
# Total files: 36

OUTDIR="GSE228444"
mkdir -p "$OUTDIR"
cd "$OUTDIR"

# --- GEO supplementary files ---
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IN1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IN1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IN1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IN1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IN2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IN2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IN2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IN2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.peakClusters.normed.compressed.sorted.blacklist-removed.bed.gz" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.peakClusters.normed.compressed.sorted.blacklist-removed.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.peakClusters.normed.compressed.sorted.blacklist-removed.bed.gz" -O "GSE228444_ddx3x_rbx1_neuron_eclip.DDX3X_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.peakClusters.normed.compressed.sorted.blacklist-removed.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IN1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IN1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IN1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IN1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IN2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IN2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IN2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IN2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.peakClusters.normed.compressed.sorted.blacklist-removed.bed.gz" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP1.umi.r1.fq.genome-mappedSoSo.rmDupSo.peakClusters.normed.compressed.sorted.blacklist-removed.bed.gz"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.neg.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.norm.pos.bw"
wget -nc "ftp://ftp.ncbi.nlm.nih.gov/geo/series/GSE228nnn/GSE228444/suppl/GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.peakClusters.normed.compressed.sorted.blacklist-removed.bed.gz" -O "GSE228444_ddx3x_rbx1_neuron_eclip.YBX1_IP2.umi.r1.fq.genome-mappedSoSo.rmDupSo.peakClusters.normed.compressed.sorted.blacklist-removed.bed.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 "SRR23998235"
gz1="$(_compress_if_exists 'SRR23998235_1' || true)"
gz2="$(_compress_if_exists 'SRR23998235_2' || true)"
gzs="$(_compress_if_exists 'SRR23998235' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "YBX1-IN2_S52_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR23998236"
gz1="$(_compress_if_exists 'SRR23998236_1' || true)"
gz2="$(_compress_if_exists 'SRR23998236_2' || true)"
gzs="$(_compress_if_exists 'SRR23998236' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "YBX1-IN1_S51_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR23998237"
gz1="$(_compress_if_exists 'SRR23998237_1' || true)"
gz2="$(_compress_if_exists 'SRR23998237_2' || true)"
gzs="$(_compress_if_exists 'SRR23998237' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "YBX1-IP2_S60_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR23998238"
gz1="$(_compress_if_exists 'SRR23998238_1' || true)"
gz2="$(_compress_if_exists 'SRR23998238_2' || true)"
gzs="$(_compress_if_exists 'SRR23998238' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "YBX1-IP1_S59_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR23998239"
gz1="$(_compress_if_exists 'SRR23998239_1' || true)"
gz2="$(_compress_if_exists 'SRR23998239_2' || true)"
gzs="$(_compress_if_exists 'SRR23998239' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "DDX3X-IN2_S50_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR23998240"
gz1="$(_compress_if_exists 'SRR23998240_1' || true)"
gz2="$(_compress_if_exists 'SRR23998240_2' || true)"
gzs="$(_compress_if_exists 'SRR23998240' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "DDX3X-IN1_S49_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR23998241"
gz1="$(_compress_if_exists 'SRR23998241_1' || true)"
gz2="$(_compress_if_exists 'SRR23998241_2' || true)"
gzs="$(_compress_if_exists 'SRR23998241' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "DDX3X-IP2_S58_L002_R1_001.fastq.gz"
fi

fasterq-dump --split-files "SRR23998242"
gz1="$(_compress_if_exists 'SRR23998242_1' || true)"
gz2="$(_compress_if_exists 'SRR23998242_2' || true)"
gzs="$(_compress_if_exists 'SRR23998242' || true)"
if [ "$RENAME_SRA_TO_ORIGINAL" = "1" ] && [ -n "$gz1" ]; then
  mv -f "$gz1" "DDX3X-IP1_S57_L002_R1_001.fastq.gz"
fi


# Option B: Direct download (larger .sra files)
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998235/SRR23998235"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998236/SRR23998236"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998237/SRR23998237"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998238/SRR23998238"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998239/SRR23998239"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998240/SRR23998240"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998241/SRR23998241"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998242/SRR23998242"

# --- Additional data files ---
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998240/SRR23998240"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998239/SRR23998239"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998242/SRR23998242"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998241/SRR23998241"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998236/SRR23998236"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998235/SRR23998235"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998238/SRR23998238"
curl -L -O -C - "https://sra-pub-run-odp.s3.amazonaws.com/sra/SRR23998237/SRR23998237"

echo "Download complete. Files saved to $OUTDIR"