print("#################################################################")
print("# Welcome in extractSeqFastaFromLen (Version " + version +
") #")
print("#################################################################")
print('Start time: ', start_time, '\n')
# Récupère le fichier de conf passer en argument
fastaFile = os.path.abspath(args.fastaFile)
outputfilename = os.path.abspath(args.paramoutfile)
lenSize = args.lenSize
keep = args.keep
output_handle = open(outputfilename, "w")
dicoSize = lenSeq2dict(fastaFile)
dicoFasta = fasta2dict(fastaFile)
filename = fastaFile.split('/')[-1].replace('.fasta', '')
nbTotal = len(dicoFasta.keys())
count = 1
for ID in sorted(dicoSize.keys(), key=dicoSize.get, reverse=True):
lenSeq = dicoSize[ID]
sequence = dicoFasta[ID]
strain = outputfilename.split('/')[-1].split('_')[0].replace(
'.fasta', '')
seqName = f"Scaffold_{count}"
#seqName = '%s_%s'%(strain,seqName)
descrip = "length={}".format(lenSeq)
if str(sequence.seq).count('N') < (len(str(sequence.seq)) - 20):
if keep == 'g' and lenSeq >= lenSize or (keep == 'l'
########### Gestion directory ##############
verifFichier(gff)
verifFichier(fasta)
nameGFF = gff.split('/')[-1].replace('.gz','')
####################### main #################
# Create Variable for the start and stop codon, this variable help for evaluate the annotation
start_codon = 'ATG'
stop_codon = ['TGA','TAA','TAG']
# Create dictionary for cds and gene information (start, stop and strand)
dico_cds = collections.defaultdict(dict)
dico_gene = collections.defaultdict(list)
augustus = False
fasta_dico = fasta2dict(fasta)
liste_scaff = fasta_dico.keys()
# Initiate the dictionary for cds
for elt in liste_scaff :
dico_cds[elt] = collections.defaultdict(list)
# Open gff for retrieve all information for cds and gene
with open(gff,'rt') as gff_file :
for line in gff_file :
if '# This output was generated with AUGUSTUS' in line :
augustus = True
if line[0] != '#' :
tabLine = line.split('\t')
type = tabLine[2]
# Parse gene information
if type == 'gene' :
id = tabLine[-1].strip().split(';')[0].replace('ID=','')
cdsFile = directory +"/"+ folder + '_cds.fna'
protFile = directory +"/"+ folder + '_protein.faa'
gffFile = directory +"/"+ folder + '_merge.gff3'
f = open(gffFile,'r')
lines = f.readlines()
f.close()
print('Creation dico GFF')
for line in lines :
if 'mRNA' in line :
lineSplit = line.split('\t')
ids = lineSplit[8].split('ID=')[-1].split(';Parent=')[0]
position = 'pos=%s_%s:%s'%(lineSplit[0],lineSplit[3],lineSplit[4])
tools = lineSplit[1]
dico_Gff[ids] = (position,tools)
print('Creation dico des fasta')
dico_cds = fasta2dict(cdsFile)
dico_prot = fasta2dict(protFile)
f = open(cdsFile.replace('.fna','.fasta'),'w')
for idSeq in sorted(dico_cds.keys(), key=sort_human):
position = dico_Gff[idSeq][0]
tools = dico_Gff[idSeq][1]
length = len(str(dico_cds[idSeq].seq))
seqObj = dico_cds[idSeq].seq
record = SeqRecord(seqObj,id=idSeq,name=idSeq, description='| %s | %s | %s ' %(position,tools,length))
SeqIO.write(record,f, "fasta")
f.close()
f = open(protFile.replace('.faa','.fasta'),'w')
for idSeq in sorted(dico_prot.keys(), key=sort_human):
position = dico_Gff[idSeq.replace('0P','0T')][0]
tools = dico_Gff[idSeq.replace('0P','0T')][1]
length = len(str(dico_prot[idSeq].seq))
print(form("\n\t---------------------------------------------------------",'yellow','bold'))
print("\t"+form("|",'yellow','bold')+form(" Welcome in QualityAssemblage (Version " + version + ") ",type='bold')+form("|",'yellow','bold'))
print(form("\t---------------------------------------------------------",'yellow','bold')+'\n')
################## Main ################################
with open(outFile,'w') as f :
f.write('n\tn:500\tL50\tmin\tN80\tN50\tN20\tE-size\tmax\tsum\tname\n')
for files in os.listdir(directory):
if files.endswith('.fasta') :
print(files+ ' in process')
Pathfile = directory+files
isFasta(Pathfile)
strain = recupId(Pathfile.split('/')[-1])
dico_fasta = fasta2dict(Pathfile)
lengthGenome = 0
nbScaffold = 0
lengthN50 = 0
lengthN80 = 0
lengthN20 = 0
Esize = 0
L50 = 0
n500 = 0
first = True
for elt in dico_fasta.values():
nbScaffold += 1
nbGeneA = 0
nbGeneB = 0
lengthGene = 0
lengthGenome = 0
for line in lines:
if line[0] != '#':
typeLine = line.split('\t')[2]
typeAnnotation = line.split('\t')[1]
posStart = line.split('\t')[3]
posEnd = line.split('\t')[4]
length = int(posEnd) - int(posStart)
if typeLine == 'gene' and typeAnnotation == 'AUGUSTUS_BGPI':
nbGeneA += 1
lengthGene = lengthGene + length
if typeLine == 'gene' and typeAnnotation == 'BRAKER':
nbGeneB += 1
lengthGene = lengthGene + length
fastaPath = genome + '/' + name + '.fasta'
dico_fasta = fasta2dict(fastaPath)
for elt in dico_fasta.values():
lengthGenome = lengthGenome + len(elt.seq)
f.write('%s\t%s\t%s\t%s\t%s\t%s\n' %
(name.center(10), str(nbGeneA).center(10),
str(nbGeneB).center(10), str(nbGeneB + nbGeneA).center(10),
str(round(lengthGene / (nbGeneA + nbGeneB), 2)).center(10),
str(round(lengthGenome / 1000000, 2)).center(10)))
print('%s Done' % name)
f.close()