# Stop on error
set -uex

# Obtain the data
bio fetch NC_045512 MT019529.1 > genomes.gb

# Turn the genomes into FASTA file.
cat genomes.gb | bio fasta > genomes.fa

# Turn the genomes into a GFF file.
cat genomes.gb | bio gff --type CDS > cds.gff

# Align the genomes.
mafft --auto --quiet --preservecase genomes.fa > aligned.fa

# Create a simpler mutations file.
cat aligned.fa | bio format --diff > mutations.txt

# Create a VCF file.
cat aligned.fa | bio format --vcf > mutations.vcf

# What overlaps with our variants?
cat genomes.gb | bio table --type CDS --olap 3778,8388,8987  -fields id,gene,date

# Variation in DNA.
cat genomes.gb | bio fasta --id YP_009724389.1,QHU36823.1 | bio align --diff

# Variation as proteins.
cat genomes.gb | bio fasta --protein --id YP_009724389.1,QHU36823.1 | bio align --diff