ryans_pan_script.sh

#!/bin/bash

set -e

if [ "$#" -ne 1 ]; then
    echo "You need to give a project name as an argument to this script (and it better be a single, short and descriptive word without funny characters). For instance, CMX_PAN_v5 would be a good one."
    exit -1
fi

PROJECT=$1


######################################################################
# This script iteratively takes all fastas in a folder that conform  #
# to anvio's rules for fasta headers which file extensions are '*.fa'#
# and generates the TSV file for pangenome analysis                  #
######################################################################
echo "name	contigs_db_path" > external-genomes.txt
for genome in $(ls *.fa)
do
    echo "Anvi-FASTA-to-contigs-db running on ${genome%.*}..."
    anvi-script-FASTA-to-contigs-db $genome

    echo "Starting COG annotation with blastp..."
    anvi-run-ncbi-cogs -c ${genome%.*}.db -T 20

    echo "${genome%.*}	$(pwd)/${genome%.*}.db" >> external-genomes.txt
done

###########Genome Storage file creation######
anvi-gen-genomes-storage -e external-genomes.txt -o $PROJECT-GENOMES.h5

######Now run pan genome analysis with NCBI blast#######################
anvi-pan-genome -g $PROJECT-GENOMES.h5 --use-ncbi-blast -J $PROJECT -o $PROJECT -T 20 --min-occurrence 2