Download data

Step 1

-- Start by creating a directory to store the genome data

mkdir -p ~/genome

Step 2

-- Download any reference genome necessary. Within the scope of the current research project, mm10, rn6, and hg38 datasets are analysed.

The files necessary include: FASTA file, chromosome sizes file, and blacklisted bed regions.

cd ~/genome
# Make separate directories for each genome
mkdir mm10
mkdir rn6
mkdir hg38

# Download mm10 data
cd mm10 
## mm10 Reference Genome (FASTA)
wget https://www.encodeproject.org/files/mm10_no_alt_analysis_set_ENCODE/@@download/mm10_no_alt_analysis_set_ENCODE.fasta.gz -O mm10.fa.gz
yes n | gunzip mm10.fa.gz
samtools faidx mm10.fa
## mm10 Chromosome Sizes
wget https://hgdownload.soe.ucsc.edu/goldenPath/mm10/bigZips/mm10.chrom.sizes -O mm10.chrom.sizes
grep -E '^chr([1-9]|1[0-9]|X|Y|M)[[:space:]]' mm10.chrom.sizes > mm10.chrom.subset.sizes
## mm10 Blacklist Regions (v2)
wget https://www.encodeproject.org/files/ENCFF547MET/@@download/ENCFF547MET.bed.gz -O mm10_blacklist.bed.gz

# Download rn6 data
cd ../rn6
## rn6 Reference Genome (FASTA)
wget https://hgdownload.soe.ucsc.edu/goldenPath/rn6/bigZips/rn6.fa.gz -O rn6.fa.gz
gunzip rn6.fa.gz
samtools faidx rn6.fa
## rn6 Chromosome Sizes
wget https://hgdownload.soe.ucsc.edu/goldenPath/rn6/bigZips/rn6.chrom.sizes -O rn6.chrom.sizes
grep -E '^chr([1-9]|1[0-9]|X|Y|M)[[:space:]]' rn6.chrom.sizes > rn6.chrom.subset.sizes
## rn6 (can be used for rn7) Blacklist Regions
sourced from: https://kilthub.cmu.edu/articles/dataset/Alternate_gene_annotations_for_rat_macaque_and_marmoset_for_single_cell_RNA_and_ATAC_analyses/21176401?file=37549855

# Download hg38 data
cd ../hg38
## hg38 Reference Genome (FASTA)
wget https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz -O hg38.fa.gz
yes n | gunzip hg38.fa.gz
samtools faidx hg38.fa
## hg38 Chromosome Sizes
wget https://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.chrom.sizes -O hg38.chrom.sizes
grep -E '^chr([1-9]|1[0-9]|X|Y|M)[[:space:]]' hg38.chrom.sizes > hg38.chrom.subset.sizes
## hg38 Blacklist Regions (v2 - ENCODE accession ENCFF356LFX)
wget https://www.encodeproject.org/files/ENCFF356LFX/@@download/ENCFF356LFX.bed.gz -O hg38_blacklist.bed.gz