output_handle = open(outputfilename, "w")
#print(dictList2txt(dicoOutputTxt))
outputTxt = ""
#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()))
#"nbSNP": len(x['siteIndices'])}
#print(name)
align = Align(filein)
x = Align.polymorphism(align)
#print dict2txt(x)
dicoOutput[name] = {
"singletons": x['singletons'],
"siteIndices": x['siteIndices'],
}
with open(infoFile, "w") as output_handle:
output_handle.write(dictDict2txt(dicoOutput))
listFileRM = []
for fileName, dico in dicoOutput.items():
listSingleton = list(dico["singletons"])
listSiteIndices = list(dico["siteIndices"])
intersection = compare_intersect(listSingleton, listSiteIndices)
if len(listSiteIndices) == 0:
listFileRM.append(fileName)
elif len(compare_intersect(listSingleton,
listSiteIndices)) == len(listSiteIndices):
listFileRM.append(fileName)
#print listSingleton, listSiteIndices, len(listSingleton), len(listSiteIndices)
with open(noInfoFile, "w") as outputListNoInfo:
txt = "\n".join(listFileRM)
"Theta_allSNPs": stats['thetaW'],
"Theta_scaffold": stats['thetaW'] / int(dictSizes[scaffold])
}
dicoMeanTheta = {}
sommeTheta, sommeSize = 0, 0
for scaffold, dico in dictThetaInfo.iteritems():
sommeTheta += dico["Theta_allSNPs"]
sommeSize += int(dictSizes[scaffold])
thetaCoreGenome = sommeTheta / sommeSize
with open(
workingObjDir.pathDirectory + basename + "/" + basename +
"_ThetaValues.tab", "w") as ThetaTab:
ThetaTab.write(dictDict2txt(dictThetaInfo))
ThetaTab.write("\nthetaCoreGenome\t%.4f" % thetaCoreGenome)
#MAKE sh script to run LDhat
objDir = directory(workingObjDir.pathDirectory +
basename) # list all directory and files in the path
#nbInd = 13
#thetaCoreGenome = 0.007
cmdLoadR = "module load compiler/gcc/4.9.2 bioinfo/geos/3.4.2 bioinfo/gdal/1.9.2 mpi/openmpi/1.6.5 bioinfo/R/3.2.2"
cmdLookTable = completeLDhatPATH + " -n " + str(
nbInd) + " -rhomax 100 -n_pts 201 -theta " + str(
thetaCoreGenome) + " -prefix " + objDir.pathDirectory + basename
with open(
for souche in listSouchessort:
dicoCountNB[souche_contig1][souche] = 0
dicoCountNB["ZERO-NB"][souche] = 0
for souche_contig2 in dico_ortho[souche_contig1]:
namesouche2 = souche_contig2.split("_")[0]
dicoCountNB[souche_contig1][namesouche2] += 1
for gene, dico in dicoCountNB.items():
nbOrthoTotal += 1
for souche, nbOrtho in dico.items():
if nbOrtho == 0:
dicoCountNB["ZERO-NB"][souche] += 1
tabFileOut.write(dictDict2txt(dicoCountNB, ref))
#print(dict2txt(dicoCountNB["ZERO-NB"]))
for key, value in sorted(dicoCountNB["ZERO-NB"].items(),
key=lambda x: x[1],
reverse=True):
percent = (value / nbOrthoTotal) * 100
if percent < 20:
printCol.purple("%s\t%s\t%.2f" % (key, value, percent))
elif percent > 30:
printCol.red("%s\t%s\t%.2f" % (key, value, percent))
elif percent > 20:
printCol.yellow("%s\t%s\t%.2f" % (key, value, percent))