# Stop on error
set -uex

# Use the metadata from the previous chapter

# Download the existing file.
wget -nc http://data.biostarhandbook.com/books/corona/data/meta.txt.gz

# Unzip the file.
gunzip meta.txt.gz

# Create a random subset of 10 sequences
echo NC_045512 > ids
cat meta.txt | shuf | head | csvcut -c 1 >> ids

# Fetch the data
cat ids | bio fetch > genomes.gb

# Rename samples by isolate and date
cat genomes.gb | bio fasta --rename '{country}|{date}|{id}' > genomes.fa

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

# Generate a tree
iqtree2 -s aligned.fa --redo --prefix.genome