print("#################################################################")
print("# Welcome in extractColfromList (Version " + version +
") #")
print("#################################################################")
print('Start time: ', start_time, '\n')
#get arguments
tableFile = relativeToAbsolutePath(args.tableFile)
tableFileOut = args.tableFileOut
IDlist = args.IDlist
if tableFileOut == "":
tableFileOut = tableFile.split(".")[0] + "_extractedIDs.tab"
#loading IDs to be kept in a list
listNameKeep = loadInList(IDlist)
if ".gz" in tableFile:
fichier = gzip.open(tableFile, "rb")
else:
fichier = open(tableFile, "rb")
#loading column IDs in a list
header = fichier.readline().decode("utf-8").rstrip().split("\t")
indice = 0
listIndiceKeep = []
for colName in header:
if colName in listNameKeep:
#print(colName, indice)
#get position for each ID to be kept, +1 for cut command (sh col1 = python col0)
gffFile = relativeToAbsolutePath(args.gffFile)
listKeepFile = relativeToAbsolutePath(args.listKeepFile)
tabFile = relativeToAbsolutePath(args.tabFile)
fastaPath = args.fastaPath
pathFileOut = args.pathOut
#fastaFile = relativeToAbsolutePath(args.fastaFile)
print("\t - Input GFF is: %s" % gffFile)
print("\t - Input listKeppFile is: %s" % listKeepFile)
print("\t - Input tabFile is: %s" % tabFile)
print("\t - Input fasta files is: %s" % fastaPath.pathDirectory)
print("\t - Output fasta files is: %s" % pathFileOut.pathDirectory)
listKeepID = [
ID.replace("Mycfi_gene", "gene_") for ID in loadInList(listKeepFile)
]
print("\nTotal ID Keep: %d" % len(listKeepID))
objGFF = parseGFF(gffFile)
recordCount = 0
dicoGenesKeepPosOnScaff = {}
keepValidList = []
geneIDsens = {}
for record in objGFF.parseGFF3():
if record.type == "mRNA":
transcriptID = record.attributes["transcriptId"]
geneID = "gene_" + record.attributes["transcriptId"]
print("\t - Chromosome file is: %s" % chromosomeFile)
print("\t - List of gene file is: %s" % listGeneFile)
print("\t - GFF file is : %s" % gffFile)
print("\t - UTRlen is : %s" % UTRlen)
print("\t - UTRchoice is : %s" % UTRchoice)
print("\t - TAG is : %s" % args.idTag)
print(" - Output Info:")
print("\t - Output file with gene+UTR is: %s" % outFile)
# chargement du fasta des chromosome en mémoire
sequencesChrom = Fasta(chromosomeFile)
#print(sequencesChrom.keys())
# chargement de la list des gènes
keepGeneList = loadInList(listGeneFile)
print("\t - There is %s genes" % len(keepGeneList))
# ouverture du fichier de sortie:
with open(outFile, "w") as outputFile:
# parse GFF pour avoir les positions
objGFF = parseGFF(gffFile)
for record in objGFF.parseGFF3():
chromosome = record.seqid
if record.type == "gene":
try:
geneName = record.attributes[args.idTag]
#print(geneName)
except Exception as e:
pass
outputfilePath = args.paramoutfile
mggFileKeep = relativeToAbsolutePath(args.mggFileKeep)
print("\t - Path with fasta is: %s" % fastaFile.pathDirectory)
print("\t - Path with corresponding Orthologues is : %s" %
listFile.pathDirectory)
print("\t - MGG list keep are in file: %s\n" % mggFileKeep)
print("\t - Output Orthologues fasta is: %s\n\n" % outputfilePath)
#recupération de la liste des CDS complet
listCDSfiles = fastaFile.lsExtInDirToList(["fasta", "fas", "fa"])
print("\n".join(listCDSfiles))
#ouverture de la liste des MGG à garder
mggKeepall = loadInList(mggFileKeep)
# trie de la list pour supprimer les T1 et T2 avec T0
MGGWithoutT, mggKeep, toRM = [], [], []
for mgg in mggKeepall:
mggNoT = mgg.replace("T0", "").replace("T1", "").replace("T2", "")
if mggNoT not in MGGWithoutT:
MGGWithoutT.append(mggNoT)
mggKeep.append(mgg)
else:
toRM.append(mgg)
with open("List" + str(len(toRM)) + "TranscriptAlternatifstoRM.txt",
"w") as toRMFile:
txt = "\n".join(toRM)