# 1.  merge all protein files .faa and .fasta
	sessiondir=/home/anne/PROJECTS/JanMaarten/Xin
	cat *.faa >all.cat *.faa >all.fasta
 
# 2. convert to tab delimited file
	/usr/molgentools/genomics/g2d_conversions.pl -l all.fasta -r Cvrt_fasta2tab -o all.tab

# 3. remove redundant sequences
	/usr/molgentools/annotation/make_nr_db.pl -i all.fasta -o all_nr.fasta
		# - Entries in Query: 77433
		# - Entries in Output: 6994

	/usr/molgentools/genomics/g2d_conversions.pl -l all_nr.fasta -r Cvrt_fasta2tab -o all_nr.tab	
	
# 4. Blast to uniref50.fasta	
	cd /var/databases/uniprot
	time blastp -outfmt 6 -db uniref50.fasta -query /home/anne/PROJECTS/JanMaarten/Xin/all_nr.fasta -max_target_seqs 1 -num_threads 24 -evalue 10E-09 -out all_nr.uniref50.blast
	# filter for unique hits only
	/usr/molgentools/blast/parse_blast_table.pl -i all_nr.uniref50.blast -o all_nr.uniref50.filter.blast
	# Align the blast output with the description of uniref50
	/usr/molgentools/genomics/g2d_align_tables.pl -s . -k /var/databases/uniprot/uniref50.description -r Align_anycolumn -t all_nr.uniref50.filter.blast -o all_nr.uniref50.description.blast

# 5 Add the blast results to the all_nr.tab
	/usr/molgentools/genomics/g2d_align_tables.pl -s . -k all_nr.uniref50.description.blast -r Align_firstcolumn -t all_nr.tab -o all_nr.uniref50.table