# 1.  merge all protein files .faa and .fasta
	datadir=/data/home/anne/PROJECTS/JanMaarten/Yanyan

# rename the files without space
	mv "Aggregatibacter actinomycetemcomitans 14R.faa"  Aggregatibacter_actinomycetemcomitans_14R.faa
	mv "Aggregatibacter actinomycetemcomitans 14S.faa"  Aggregatibacter_actinomycetemcomitans_14S.faa
	mv "Aggregatibacter actinomycetemcomitans 1R.faa"   Aggregatibacter_actinomycetemcomitans_1R.faa
	mv "Aggregatibacter actinomycetemcomitans 1S.faa"   Aggregatibacter_actinomycetemcomitans_1S.faa
	mv "Aggregatibacter actinomycetemcomitans 20R.faa"  Aggregatibacter_actinomycetemcomitans_20R.faa
	mv "Aggregatibacter actinomycetemcomitans 20S.faa"  Aggregatibacter_actinomycetemcomitans_20S.faa
	mv "Aggregatibacter actinomycetemcomitans 29R.faa"  Aggregatibacter_actinomycetemcomitans_29R.faa
	mv "Aggregatibacter actinomycetemcomitans 29S.faa"  Aggregatibacter_actinomycetemcomitans_29S.faa
	mv "Aggregatibacter actinomycetemcomitans 2R.faa"   Aggregatibacter_actinomycetemcomitans_2R.faa
	mv "Aggregatibacter actinomycetemcomitans 2S.faa"   Aggregatibacter_actinomycetemcomitans_2S.faa
	mv "Aggregatibacter actinomycetemcomitans ATCC.faa" Aggregatibacter_actinomycetemcomitans_ATCC.faa

	cat *.faa >all.fasta
 
# 2. convert to tab delimited file
	/data/molgentools/genomics/g2d_conversions.pl -l all.fasta -r Cvrt_fasta2tab -o all.tab

# 3. remove redundant sequences
	/data/molgentools/annotation/make_nr_db.pl -i all.fasta -o all_nr.fasta
		## Entries in Query: 24150
		## Entries in Output: 7551


	/data/molgentools/genomics/g2d_conversions.pl -l all_nr.fasta -r Cvrt_fasta2tab -o all_nr.tab	

# 4. Facop annotation
	http://facop.molgenrug.nl/?SessionID=129.125.142.95.t96qqe28k9n4d9c3r7flcna9n0.772

	
# 4. Blast to uniref50.fasta	
	cd /data/databases/uniprot
	time blastp -outfmt 6 -db uniref50.fasta -query $datadir/all_nr.fasta -max_target_seqs 1 -num_threads 8 -evalue 10E-09 -out $datadir/all_nr.uniref50.blast
	cd $datadir
	# filter for best blast hit only
	/data/molgentools/blast/parse_blast_table.pl -i $datadir/all_nr.uniref50.blast -o $datadir/all_nr.uniref50.filter.blast
	# Align the blast output with the description of uniref50
	/data/molgentools/genomics/g2d_align_tables.pl -s $datadir -k /data/databases/uniprot/uniref50.description -r Align_anycolumn -t $datadir/all_nr.uniref50.filter.blast -o all_nr.uniref50.description.blast

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