#!/bin/bash

#$ -N cluster_prodigal           #-- set the name of the job; this will appear in the job listing
#$ -l h_vmem=300G                      #-- set the maximum memory usage (per slot). on scg3 the default is 1GB of h_vmem per slot
#$ -l h_rt=168:00:00                 #-- set the maximum run time, hh:mm:ss, default is 6hrs on scg3
#$ -w e                              #-- check for errors in the job submission options
#$ -j y                              #-- join the stdout and stderr streams into one file
#$ -o ~/output_error_directory       #-- output directory 
#$ -e ~/output_error_directory       #-- error directory   
#$ -t 1-1                           #-- specify the number of tasks 


module load usearch/7.0.1090 

fasta=/srv/gsfs0/projects/snyder/ngarud/unannotated_prodigal_genes/all_timepts_unannotated_prodigal_genes.fa

usearch -cluster_fast $fasta -id 0.95 -centroids /srv/gsfs0/projects/snyder/ngarud/unique_prodigal_genes/unique_prodigal_centroids.fa -uc /srv/gsfs0/projects/snyder/ngarud/unique_prodigal_genes/unique_prodigal_centroids.uc


