4. Prepare reference files

Walk through

# Download the reference genome on
wget ftp://ftp.ensembl.org/pub/release-86/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna_sm.primary_assembly.fa.gz
gunzip Homo_sapiens.GRCh38.dna_sm.primary_assembly.fa.gz

# collect chr22 reference
awk '
/>/{
   if (substr($0,1,4) == ">22 ")
      {prt = 1}
   else
      {prt = 0}
} 
(prt==1){
   print $0;
}
' Homo_sapiens.GRCh38.dna_sm.primary_assembly.fa > chr22.fa

# Add spike-ins
wget https://tools.thermofisher.com/content/sfs/manuals/ERCC92.zip
unzip ERCC92.zip
cat chr22.fa ERCC92.fa > chr22_with_ERCC92.fa

# Get annotation files
wget ftp://ftp.ensembl.org/pub/release-86/gtf/homo_sapiens/Homo_sapiens.GRCh38.86.gtf.gz
gunzip Homo_sapiens.GRCh38.86.gtf.gz
grep '^22' Homo_sapiens.GRCh38.87.gtf > Homo_sapiens.GRCh38.87_chr22.gtf