def extractListFromFasta2(sequenceFile, FileList):
dicoOutput = {}
# Ouverture des sequences fasta MGG et chargement dans dictionnaire
dictSequences = fasta2dict(sequenceFile)
# ouverture des identifiants a garder
listKeep = FileList
keep = 0
noKeep = 0
for ID, record in dictSequences.items():
if ID in listKeep:
keep += 1
dicoOutput[record] = record
else:
noKeep += 1
return dicoOutput
souche = soucheIndice[i]
#print(souche)
if souche not in dicoSeqBuild[geneID].keys():
dicoSeqBuild[geneID][souche] = SNP
else:
dicoSeqBuild[geneID][souche] += SNP
i += 1
ctr += 1
#print(dict2txt(dicoSeqBuild))
# chargement des sequences 3 souches
for files in fastaPath.lsExtInDirToList("fasta"):
geneID = files.split("_")[1].replace("gene", "gene_")
dico = fasta2dict(files)
if geneID in dicoSeqBuild.keys():
dicoSeqBuild[geneID].update(dico)
countOnlyN = 0
listSeqNFind = []
for geneID, dico in dicoSeqBuild.items():
with open(
"/work/carlier.j/globalPopGenomicMF/buildSeq62/test/" +
geneID + ".fasta", "w") as output_handle:
seqNfind = False
for souche, txtseq in dico.items():
if type(txtseq) is not SeqRecord:
txtseqNdel = txtseq.replace("N", "")
for MGG in listFiles:
if MGG in dicoMGG2BR32.keys():
BR32List.append(dicoMGG2BR32[MGG])
else:
notMGG.append(MGG)
print("BR32List count:%i" %(len(BR32List)))
print("notMGG count:%i" %(len(notMGG)))
dicoFastaSample = {}
for sampleFile in pathSampleIn.listFiles:
souche = sampleFile.split("/")[-1].split(".")[0]
#print(souche)
dicoFastaSample[souche] = fasta2dict(sampleFile)
#print(dicoFastaSample)
#print(pathDirectoryOut.pathDirectory)
count = 0
for filename in pathDirectoryIn.listFiles:
basename = filename.split("/")[-1]
MGG = "_".join(filename.split("/")[-1].split("_")[0:2])
if MGG in dicoMGG2BR32.keys() :
BR32ID = dicoMGG2BR32[MGG]
first = 0
for souche in dicoFastaSample.keys():
nbEmpty=0
other=0
listCDSfiles = workingObjDir.lsExtInDirToList("codingseq")
statFile = open(workingObjDir.pathDirectory+"statsCDSInfo.txt","w")
listFile = open(workingObjDir.pathDirectory+"CDSfilelist.txt","w")
statFile.write("fileName\tnbstartonly\tnbstoponly\tnbstartandstop\tnbEmpty\ttotal\tOther\n")
for fileCDS in sorted(listCDSfiles):
fileName = fileCDS.split("/")[-1].split(".")[0]
listFile.write(fileCDS+"\n")
if args.fastaValue in ["yes","y"]:
output_file = open(workingObjDir.pathDirectory+fileName+".fasta", "w")
record_dict = fasta2dict(fileCDS)
for name in sorted(record_dict.keys(), key=sort_human):
record = record_dict[name]
oldNumID = record.id
new_record_name = fileName+"_"+oldNumID
record.id = new_record_name
record.name = ""
seq = record.seq.upper()
firstCodon = seq[:3]
endCodon = seq[-3:]
# Test ATG start and Stop codons
if str(firstCodon.upper()) in "ATG":
startATG=1
else:
startATG=0
#Welcome message
print("#################################################################")
print("# Welcome in extractSeqFastaFromLen (Version " + version +
") #")
print("#################################################################")
print('Start time: ', start_time, '\n')
# Récupère le fichier de conf passer en argument
fastaFile = relativeToAbsolutePath(args.fastaFile)
outputfilename = relativeToAbsolutePath(args.paramoutfile)
lenSize = args.lenSize
keepValue = args.keepValue
output_handle = open(relativeToAbsolutePath(outputfilename), "w")
dicoSize = lenSeq2dict(fastaFile)
dicoFasta = fasta2dict(fastaFile)
nbKeep = 0
nbTotal = len(dicoFasta.keys())
for ID in sorted(dicoSize.keys(), key=sort_human):
lenSeq = dicoSize[ID]
if keepValue in ["g", "greater"]:
if lenSeq >= lenSize:
sequence = dicoFasta[ID]
SeqIO.write(sequence, output_handle, "fasta")
nbKeep += 1
elif keepValue in ["l", "lower"]:
if lenSeq <= lenSize:
sequence = dicoFasta[ID]
seq = record.seq
SeqIO.write(record.upper(), output_handle, "fasta")
######
os.makedirs(outputfilePath + "orthologue/", exist_ok=True)
os.system("rm " + outputfilePath + "orthologue/*.fasta")
#Concatenation des orthologues de Farman et Gemo
listFastaOut = lsFastaInDirToList(outputfilePath)
nblignetotal = len(listFastaOut)
#print(listFastaOut)
ctr = 0
dicoOpenFile = {}
for fastaFile in listFastaOut:
dictSequences = {}
dictSequences = fasta2dict(fastaFile)
print(fastaFile)
percent = (float(ctr) / float(nblignetotal)) * 100
sys.stdout.write("\rProcessed up to %0.2f %%...\t" % percent)
sys.stdout.flush()
for geneId, record in dictSequences.items():
#print(geneId)
MGGName = "_".join(geneId.split("_")[0:2])
if MGGName in toRM or "T1" in MGGName or "T2" in MGGName:
#print(MGGName)
MGGName = MGGName.replace("T0", "T0").replace("T1",
"T0").replace(
"T2", "T0")
#print(MGGName)
souche = geneId.split("_")[2]