#for key in sorted(dicoOutputTxt.keys()):
for key in sorted(listKeepSouche, key=sort_human):
value = "\t".join(dicoOutputTxt[key])
outputTxt += "%s\t%s\n" % (str(key), str(value))
output_handle.write(outputTxt)
outputListEmpty = open(basename + "_outputListEmpty.txt", "w")
for fileEmptyName in listFileEmpty:
outputListEmpty.write(fileEmptyName + "\n")
with open(basename + "_LenAlign_nbSNP.txt", "w") as output1:
txt1 = dictDict2txt(dicoFileCountSNP)
output1.write(txt1)
with open(basename + "_nbSNPallFile.txt", "w") as output2:
txt1 = dict2txt(dicoFilenbSNP)
output2.write(txt1)
print("\n\nExecution summary:")
print(" - Outputting \n\
Il y a au final %i Motif dans tout les MGG\n\
Il y a %i fichiers vides\n\
les sequences sont ajouter dans le fichier %s\n\
la liste des fichiers vides est dans le fichier outputListEmpty.txt" %
(nbMotifTotal, fileEmpty, outputfilename))
print("\nStop time: ", strftime("%d-%m-%Y_%H:%M:%S", localtime()))
print("#################################################################")
print("# End of execution #")
print("#################################################################")
sensDNA = record.strand
geneIDsens[geneID] = sensDNA
if geneID not in keepValidList:
keepValidList.append(geneID)
recordCount += 1
for posIter in range(record.start, record.end):
if record.seqid not in dicoGenesKeepPosOnScaff.keys():
dicoGenesKeepPosOnScaff[record.seqid] = {posIter: geneID}
else:
dicoGenesKeepPosOnScaff[record.seqid].update(
{posIter: geneID})
print("\nTotal records: %d" % recordCount)
print(dict2txt(geneIDsens))
# Parcours du fichier de SNP
nblignetotal, ctr = 74215263, 0
dicoSeqBuild = {}
with open(tabFile, "r") as tabFileRead:
header = tabFileRead.readline().rstrip().split("\t")
soucheIndice = header[3:]
#print(header)
for line in tabFileRead:
if ((ctr % 10000 == 0) and
(ctr != 0)) or (float(ctr) == nblignetotal):
percent = (float(ctr) / float(nblignetotal)) * 100
sys.stdout.write("\rProcessed up to %0.2f %%..." % percent)
namesouche2) # DEBUG
if ref in namesouche1:
dico_ortho.setdefault(souche_contig1,
[]).append(souche_contig2)
if namesouche2 not in listSouches:
listSouches.append(namesouche2)
if ref in namesouche2:
dico_ortho.setdefault(souche_contig2,
[]).append(souche_contig1)
if namesouche1 not in listSouches:
listSouches.append(namesouche1)
listSouchessort = sorted(listSouches, key=sort_human)
if args.debug == "True": print(dict2txt(dico_ortho))
if args.debug == "True": print(listSouchessort)
if args.debug == "True": print(len(listSouchessort))
# ecriture des correspondence othologue 1/1:
nbOrtho1_1 = 0
listKeep = []
for souche_contig1, listcorresp in dico_ortho.items():
namesouche1 = souche_contig1.split("_")[0]
tabsoucheFind = [souche.split("_")[0] for souche in listcorresp]
if len(listcorresp) == len(listSouchessort) and sorted(
listSouchessort, key=sort_human) == sorted(tabsoucheFind,
key=sort_human):
listKeep.append(souche_contig1)
for soucheFind in listcorresp:
files.add_argument('-po', '--pathout', metavar="<path/to/fileout>",type = directory, required=True, dest = 'pathDirectoryOut', help = 'path to fasta files Out')
args = parser.parse_args()
#Welcome message
print("#################################################################")
print("# Welcome in addSample (Version " + version + ") #")
print("#################################################################")
print('Start time: ', start_time,'\n')
# Récupère le fichier de conf passer en argument
pathDirectoryIn = args.pathDirectoryIn
pathDirectoryOut = args.pathDirectoryOut
pathSampleIn = args.pathSampleIn
dicoNbSeqInFiles,dicoNbFilesNbSouche = nbSeqInFile2dict(str(pathSampleIn.pathDirectory))
print((dict2txt(dicoNbSeqInFiles)))
print(dict2txt(dicoNbFilesNbSouche))
# ajoute à la variable current_dir le chemin ou est executer le script
current_dir = os.path.dirname(os.path.abspath(__file__))
# Ouverture du fichier OrthoMCL pour correspondance famille nom gene
dictNameFamilly={}
with open(args.csvFileParam,"r") as fichier:
for ligne in fichier:
ltab = ligne.rstrip().split("\t")
geneName=ltab[1]
famillyName=ltab[2]
if famillyName not in dictNameFamilly.keys():
dictNameFamilly[famillyName]={ "MGG":"",
"BR32":""
souche = geneId.split("_")[2]
#print(souche)
# ouverture du fichier de sortie
dicoOpenFile[MGGName] = open(
outputfilePath + "orthologue/" + MGGName + "_Orthologue.fasta",
"a")
#with open(outputfilePath+"orthologue/"+MGGName+"_Orthologue.fasta", "a") as output_handle:
#output_handle = open(outputfilePath+"orthologue/"+MGGName+"_Orthologue.fasta", "a")
new_record_name = souche
record.id = ""
record.id = new_record_name
record.name = ""
seq = record.seq
SeqIO.write(record.upper(), dicoOpenFile[MGGName], "fasta")
dicoOpenFile[MGGName].close()
#output_handle.close()
ctr += 1
dico1, dico2 = nbSeqInFile2dict(outputfilePath + "orthologue/")
print("check if NBsouche and sequences are correctly extract:\n")
print(dict2txt(dico2))
print("\n\nIf up are same below OK\n\n%i\t%i" % (len(toRM), len(mggKeep)))
#print(" - Outputting \n\
#Il y a au final %i Sequences garder\n\
#les sequences sont ajouter dans le fichier %s" %(nbKeep,outputfilePath))
print("\nStop time: ", strftime("%d-%m-%Y_%H:%M:%S", localtime()))
print("#################################################################")
print("# End of execution #")
print("#################################################################")