#After getting faa and fna BUSCO files. 

#Correcting the reading frame of all CDS to +1
 cd /home/tools/busco/dataset_10mar2018/busco_output 
 
 for species in Ehians Egrac Cac Rhino Pho  Coloc Chyamo  Sleb  mel  vir
 do 
    cd /home/tools/busco/dataset_10mar2018/busco_output/$species
    echo -en $species "\t"
    fix_busco_CDS_frame.awk   mode=fix  /home/tools/busco/diptera_odb9.gene_name
    echo ""
 done

			# Ehians  CDS listed in input file: 2799   total CDS found:  2374   wrong frame CDS: 100   fixed CDS: 100
			# Egrac   CDS listed in input file: 2799   total CDS found:  2329   wrong frame CDS:  88   fixed CDS:  88
			# Cac     CDS listed in input file: 2799   total CDS found:  2622   wrong frame CDS:  40   fixed CDS:  40
			# Rhino   CDS listed in input file: 2799   total CDS found:  2616   wrong frame CDS:  53   fixed CDS:  53
			# Pho     CDS listed in input file: 2799   total CDS found:  2597   wrong frame CDS:  69   fixed CDS:  69
			# Coloc   CDS listed in input file: 2799   total CDS found:  2560   wrong frame CDS:  69   fixed CDS:  69
			# Chyamo  CDS listed in input file: 2799   total CDS found:  2627   wrong frame CDS:  39   fixed CDS:  39
			# Sleb    CDS listed in input file: 2799   total CDS found:  2587   wrong frame CDS:  45   fixed CDS:  45
			# mel     CDS listed in input file: 2799   total CDS found:  2748   wrong frame CDS:   6   fixed CDS:   6
			# vir     CDS listed in input file: 2799   total CDS found:  2718   wrong frame CDS:  16   fixed CDS:  16

 
 
 # checking if all CDS got frame +1
 cd /home/tools/busco/dataset_10mar2018/busco_output 
 
 for species in Ehians Egrac Cac Rhino Pho  Coloc Chyamo  Sleb  mel  vir
 do 
    cd /home/tools/busco/dataset_10mar2018/busco_output/$species
    echo $species
    fix_busco_CDS_frame.awk   mode=detect  /home/tools/busco/diptera_odb9.gene_name
    echo ""
 done
 
 #Ok, 0 wrong CDS in all species
 
 
# now making one multifasta for each gene
 mkdir /home/tools/busco/dataset_10mar2018/multifasta/
 cd /home/tools/busco/dataset_10mar2018/busco_output 
 busco2multifasta.awk    out_dir="/home/tools/busco/dataset_10mar2018/multifasta/"   species="Ehians Egrac Cac Rhino Pho  Coloc Chyamo  Sleb  mel  vir"   /home/tools/busco/diptera_odb9.gene_name

 #now selecting the orthologs present in all 10 species and with lenght of coefficient of variation < 10%
  cd   /home/tools/busco/dataset_10mar2018/multifasta/
  ortholog_count_file="/home/tools/busco/dataset_10mar2018/multifasta/Ehians_Egrac_Cac_Rhino_Pho_Coloc_Chyamo_Sleb_mel_vir_.ortholog_counts"
  awk '($2 ==10 ){print $0}'              $ortholog_count_file | sort -k3,3n  > 10species.ortholog_counts
  awk '(($2 ==10 )&&($3<=10)){print $0}'  $ortholog_count_file | sort -k3,3n  > 10speciesCV10.ortholog_counts 
#QC:
  wc -l *.ortholog_counts
 #   1603 10species.ortholog_counts
 #   1110 10speciesCV10.ortholog_counts

		   

  # sequence total (approximation)
 awk '(1==1){sum += $4};END{print "sum= " sum}'  $ortholog_count_file   	  # sum= 4,582,882
 awk '(1==1){sum += $4};END{print "sum= " sum}'  10species.ortholog_counts    # sum= 3,132,558
 awk '(1==1){sum += $4};END{print "sum= " sum}'  10speciesCV10.ortholog_counts #sum= 2,045,098
 awk '(1==1){print $1}' 10speciesCV10.ortholog_counts >  /home/tools/busco/dataset_10mar2018/10speciesCV10.gene_name 
 wc   /home/tools/busco/dataset_10mar2018/10speciesCV10.gene_name  #1110 
 
  
# now aligning with translatorX   only the selected orthologs (10 species, CV <=10) 
 mkdir /home/tools/busco/dataset_10mar2018/trx/  
 cd /home/tools/busco/dataset_10mar2018/trx/
 nohup awk '(1==1){file="/home/tools/busco/dataset_10mar2018/multifasta/Ehians_Egrac_Cac_Rhino_Pho_Coloc_Chyamo_Sleb_mel_vir_" $1 ".fna" ;   system("translatorx_vLocal.pl -g 1 -t F -i " file " -o " $1".trx ")}'  /home/tools/busco/dataset_10mar2018/10speciesCV10.gene_name > nohup_trx.out &
 ls *.trx.nt_cleanali.fasta | wc  #   1110   Ok , all run
 dos2unix -k nohup_trx.out  #contail all  messages
 
 
 #now concatenating in supermatrix   (gene_list_file option not working) 
 cd /home/tools/busco/dataset_10mar2018/
supermatrix2.awk  defline_type="species_gene" gene_list_file=10speciesCV10.gene_name  /home/tools/busco/dataset_10mar2018/trx/*.trx.nt_cleanali.fasta 
# number of fasta files: 1110    genes found: 1110    genes selected: 1110    species found: 10
#produced file concatenated_10mar2018.fasta