#!/bin/bash
# RNA-Seq 
# 2021-01

#SBATCH --nodes=1			
#SBATCH --ntasks-per-node=1
#SBATCH --mem=64GB
#SBATCH --job-name=Make_nr_database


# Choose between long or short: A short job will start quickly after submitting, but will be terminated after 30 minutes

##SBATCH --time=24:00:00
#SBATCH -p short


molgentools=/data/pg-molgen/software/molgentools_mirror
datadir=/data/p127804/PROJECTS/JanMaarten/Yanyan_202101/Aa_annotation-chapter2



# 1 Merge all genomes
cat $datadir/*.faa > $datadir/all_RAST.fasta

# 2. replace | by _  to prevent errors in downstream processing
sed -i 's/|/\_/g' $datadir/all_RAST.fasta

# 3. remove redundant sequences
$molgentools/annotation/make_nr_db.pl -i $datadir/all_RAST.fasta -o $datadir/all_nr_RAST.fasta
		# Entries in Query:  33104
		# Entries in Output: 11237


# 4 RENAME IDs
$molgentools/genomics/g2d_conversions.pl -s $datadir -l all_nr_RAST.fasta -r Cvrt_fasta2tab -o all_nr_RAST.tab	
$molgentools/genomics/g2d_align_tables.pl -s $datadir -t $datadir/all_nr_RAST.tab -k $datadir/lookup_table.txt -r Find_Replace -o all_nr.tab
$molgentools/genomics/g2d_conversions.pl -s $datadir -l all_nr.tab -r Cvrt_tab2fasta -o all_nr.fasta	


# Annotate proteins 
# NOTE; run 01.blast_uniprot.sh