def Convert(input, output, filename):
"""
File format conversion program (fasta, strict-phylip, sequential-phylip, relaxed-phylip and nexus).
@parameter input - Input file format.
@parameter output - Output file format.
@parameter filename - Input filename.
"""
formDict = {
'fasta': '*.fas',
'nexus': '*.nex',
'phylip': '*.phy',
'phylip-sequential': '*.phy',
'phylip-relaxed': '*.phy'
}
os.chdir('..')
if input == 'fasta' and output == 'nexus':
alignment = AlignIO.read(open(filename), "fasta", alphabet=Gapped(IUPAC.protein))
g = open(filename.split(".")[0] + '.nex', 'w')
g.write(alignment.format("nexus")); g.close()
else:
try:
handle = open(filename, 'rU'); record = list(SeqIO.parse(handle, input))
fp = open(filename.split('.')[0] + '.' + formDict[output].split('.')[1], 'w')
SeqIO.write(record, fp, output); fp.close(); handle.close()
except:
print("Bad Alignment\n")
print("Final output saved in %s" %filename.split('.')[0] + '.' + formDict[output].split('.')[1])
def nexML(self, filename):
"""
Produces concatenated alignment file in NexML format.
"""
fp = open('Results.xml', 'w')
handleXML = open(filename, 'rU')
recordsXML = list(SeqIO.parse(handleXML, "nexus"))
SeqIO.write(recordsXML, fp, "seqxml")
fp.close()
handleXML.close()
def nexML(self, filename):
"""
Produces concatenated alignment file in NexML format.
"""
fp = open('Results.xml', 'w')
handleXML = open(filename, 'rU')
recordsXML = list(SeqIO.parse(handleXML, "nexus"))
SeqIO.write(recordsXML, fp, "seqxml")
fp.close()
handleXML.close()
def Convert(input, output, filename):
"""
File format conversion program (fasta, strict-phylip, sequential-phylip, relaxed-phylip and nexus).
@parameter input - Input file format.
@parameter output - Output file format.
@parameter filename - Input filename.
"""
formDict = {
'fasta': '*.fas',
'nexus': '*.nex',
'phylip': '*.phy',
'phylip-sequential': '*.phy',
'phylip-relaxed': '*.phy'
}
os.chdir('..')
if input == 'fasta' and output == 'nexus':
alignment = AlignIO.read(open(filename),
"fasta",
alphabet=Gapped(IUPAC.protein))
g = open(filename.split(".")[0] + '.nex', 'w')
g.write(alignment.format("nexus"))
g.close()
else:
try:
handle = open(filename, 'rU')
record = list(SeqIO.parse(handle, input))
fp = open(
filename.split('.')[0] + '.' + formDict[output].split('.')[1],
'w')
SeqIO.write(record, fp, output)
fp.close()
handle.close()
except:
print("Bad Alignment\n")
print("Final output saved in %s" % filename.split('.')[0] + '.' +
formDict[output].split('.')[1])
def _cleanAli(recordNuc, omit, fileName):
handleP = open('tAligned.fas', 'rU')
records = list(SeqIO.parse(handleP, 'fasta'))
store = list()
for i, rec in enumerate(records):
nucData = [x.seq for x in recordNuc if x.id in rec.id]
nucSeqData = _spliter(nucData[0], 3)
sequence = Seq("", generic_dna)
pos = 0
for j, amino in enumerate(rec.seq):
if amino == '-':
sequence = sequence + Seq("---", generic_dna)
elif amino == 'Z':
sequence = sequence + Seq("NNN", generic_dna)
pos = pos + 1
else:
try:
sequence = sequence + nucSeqData[pos]
pos = pos + 1
except:
if rec.id not in store:
store.append(rec.id)
records[i].seq = Seq(str(sequence), generic_dna)
records = [x for x in records if x.id not in store]
if store != []:
print("Failed to align following sequences: %s" % store)
if omit == False:
with open("Input/" + fileName.split('.')[0] + ".nex", 'w') as fp:
SeqIO.write(records, fp, "nexus")
else:
with open("Input/" + fileName.split('.')[0] + "_omited.nex",
'w') as fp:
SeqIO.write(records, fp, "nexus")
os.remove('translated.fas')
os.remove('tAligned.fas')
def RNAfoldConsensus(self):
"""
Creates RNA structure data from consensus alignment using RNAfold program.
Output is stored in RNAConsensus.txt file
"""
os.chdir("RNAdata")
fileList = glob.glob('*.nex')
newFileList = []
for name in fileList:
file_name = name.split('.')[0]
newName = file_name + '.aln'
newFileList.append(newName)
recordList = self.fileOpenConcNex()
os.chdir("..")
n = 0
while n < len(fileList):
record = recordList[n]
file_Write = open(newFileList[n], 'w')
SeqIO.write(record, file_Write, "clustal")
file_Write.close()
n = n + 1
fp = open("RNAConsensus.txt", 'w')
for name in newFileList:
print("RNA structure | %s| %s" %
(time.strftime("%c"), name))
fp.write("[ %s ]\n" % name.split('.')[0])
fp.write(
subprocess.check_output("RNAalifold < %s" % name, shell=True))
fp.write('\n\n')
fp.close()
def RNAfoldConsensus(self):
"""
Creates RNA structure data from consensus alignment using RNAfold program.
Output is stored in RNAConsensus.txt file
"""
os.chdir("RNAdata")
fileList = glob.glob('*.nex')
newFileList = []
for name in fileList:
file_name = name.split('.')[0]
newName = file_name + '.aln'
newFileList.append(newName)
recordList = self.fileOpenConcNex()
os.chdir("..")
n = 0
while n < len(fileList):
record = recordList[n]
file_Write = open(newFileList[n], 'w')
SeqIO.write(record, file_Write, "clustal")
file_Write.close()
n = n + 1
fp = open("RNAConsensus.txt", 'w')
for name in newFileList:
print("RNA structure | %s| %s" %(time.strftime("%c"), name))
fp.write("[ %s ]\n" % name.split('.')[0])
fp.write(subprocess.check_output("RNAalifold < %s" % name, shell = True))
fp.write('\n\n')
fp.close()
def alignOutput(self, combine):
"""
alignOutput creates an output file in user defined file format
@parameter combine - concatenated alignment matrix
"""
output_format = self.file_format
if output_format == 1:
filecompname = "Result1.fasta"
file_Write = open(filecompname, 'w')
SeqIO.write(combine, file_Write, "fasta")
file_Write.close()
#This section is for cleaning any unknown description tag from the final fasta file
fin = open("Result1.fasta", "r")
fout = open("Result.fasta", "w+")
input_data = fin.readlines()
for line in input_data:
if "<unknown description>" in line:
line = line.replace("<unknown description>", "")
fout.write(line)
fin.close()
fout.close()
elif output_format == 2:
file_Write = open("Result.phy", 'w')
SeqIO.write(combine, file_Write, "phylip")
file_Write.close()
elif output_format == 3:
file_Write = open("Result.phy", 'w')
SeqIO.write(combine, file_Write, "phylip-sequential")
file_Write.close()
elif output_format == 4:
file_Write = open("Result.phy", 'w')
SeqIO.write(combine, file_Write, "phylip-relaxed")
file_Write.close()
else:
sys.exit("You have enetered wrong value \n Program Terminated...")
def alignOutput(self, combine):
"""
alignOutput creates an output file in user defined file format
@parameter combine - concatenated alignment matrix
"""
output_format = self.file_format
if output_format == 1:
filecompname = "Result1.fasta"
file_Write = open(filecompname, 'w')
SeqIO.write(combine, file_Write, "fasta")
file_Write.close()
#This section is for cleaning any unknown description tag from the final fasta file
fin = open("Result1.fasta", "r")
fout = open("Result.fasta", "w+")
input_data = fin.readlines()
for line in input_data:
if "<unknown description>" in line:
line = line.replace("<unknown description>", "")
fout.write(line)
fin.close()
fout.close()
elif output_format == 2:
file_Write = open("Result.phy", 'w')
SeqIO.write(combine, file_Write, "phylip")
file_Write.close()
elif output_format == 3:
file_Write = open("Result.phy", 'w')
SeqIO.write(combine, file_Write, "phylip-sequential")
file_Write.close()
elif output_format == 4:
file_Write = open("Result.phy", 'w')
SeqIO.write(combine, file_Write, "phylip-relaxed")
file_Write.close()
else:
sys.exit("You have enetered wrong value \n Program Terminated...")
def mrnaAlign(inputFile, pkg, arguments=None):
if pkg != 'muscle' and arguments == None:
pkg = 'muscle'
if pkg == 'muscle':
if 'Darwin' in platform.system():
subprocess.call("./src/muscle/muscle -in %s -out %s" %
("Align/" + inputFile, "Input/" + inputFile),
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
handle = open("Input/" + inputFile, 'rU')
record = list(SeqIO.parse(handle, 'fasta'))
with open("Input/" + inputFile.split('.')[0] + ".nex", 'w') as fp:
SeqIO.write(record, fp, 'nexus')
os.remove("Input/" + inputFile)
else:
subprocess.call("./src/muscle/muscleLinux -in %s -out %s" %
("Align/" + inputFile, "Input/" + inputFile),
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
handle = open("Input/" + inputFile, 'rU')
record = list(SeqIO.parse(handle, 'fasta'))
with open("Input/" + inputFile.split('.')[0] + ".nex", 'w') as fp:
SeqIO.write(record, fp, 'nexus')
os.remove("Input/" + inputFile)
else:
arguments = arguments.replace('[', '').replace(']', '')
subprocess.call(
"./src/mafft/mafft.bat %s %s > %s" %
(arguments, "Align/" + inputFile, "Input/" + inputFile),
shell=True,
stdout=subprocess.PIPE,
stderr=subprocess.STDOUT)
handle = open("Input/" + inputFile, 'rU')
record = list(SeqIO.parse(handle, 'fasta'))
with open("Input/" + inputFile.split('.')[0] + ".nex", 'w') as fp:
SeqIO.write(record, fp, 'nexus')
os.remove("Input/" + inputFile)
def mrnaImport(geneName, group, ortho):
"""
@ geneName - name of the gene
@ group - organism name
@ creates a taxon mRNA aligned fasta file as output for the set of genes given as input
"""
if ortho != None:
inpTerm = ortho + "[sym] AND " + group + "[orgn]"
elif group != None:
inpTerm = geneName + "[sym] AND " + group + "[orgn]"
Entrez.email = '*****@*****.**'
try:
handle = Entrez.esearch(db="gene",
term=inpTerm,
rettype='xml',
RetMax=300)
except:
raise RuntimeError(
"Failed to import sequence from NCBI. Check your internet connection.\nThis might also occur due to NCBI failure"
)
records = Entrez.read(handle)
idList = records["IdList"]
inpTerm = "ortholog_gene_" + str(idList[0]) + "[group]"
handle = Entrez.esearch(db="gene",
term=inpTerm,
rettype='xml',
RetMax=300,
warning=False)
records = Entrez.read(handle)
idList = records["IdList"]
outRecord = list()
for ids in idList:
_xmlcreate(ids)
refIds = _xmlparser()
os.remove('export.xml')
recordList = list()
for inIDs in refIds:
recordList.append(mrnaExt(inIDs))
try:
longestRec = recordList[0]
except:
continue
for rec in recordList:
longestRec = rec if len(rec.seq) > len(
longestRec.seq) else longestRec
print("%s" % longestRec.description)
outRecord.append(longestRec)
with open("Align/" + geneName + '.fas', 'w') as fp:
SeqIO.write(outRecord, fp, 'fasta')
fdata = open("Align/" + geneName + '.fas', 'r').readlines()
with open("Align/" + geneName + '.fas', 'w') as fp:
for lines in fdata:
if '>' in lines and 'PREDICTED' in lines:
newLine = '>' + lines.split(' ')[2] + '_' + lines.split(
' ')[3] + '|' + lines.split(' ')[0].lstrip('>')
fp.write('%s\n' % newLine)
elif '>' in lines and 'PREDICTED' not in lines:
newLine = '>' + lines.split(' ')[1] + '_' + lines.split(
' ')[2] + '|' + lines.split(' ')[0].lstrip('>')
fp.write('%s\n' % newLine)
else:
fp.write('%s' % lines)
def _translator(recordData, ign, omit, table):
proteinSeqList = list()
recordsFunc = recordData
for i, rec in enumerate(recordsFunc):
counter = dict()
seqT = _translate_str(str(rec.seq), table)
if ign == False:
if "*" in seqT:
counter['one'] = seqT.count('*')
seqT = _translate_str(
str(rec.seq[1:len(rec.seq)] + Seq("N", generic_dna)),
table)
if "*" in seqT:
counter['two'] = seqT.count('*')
seqT = _translate_str(
str(rec.seq[2:len(rec.seq)] + Seq("NN", generic_dna)),
table)
if "*" in seqT:
counter['three'] = seqT.count('*')
if omit == False:
if min(counter, key=counter.get) == 'one':
seqT = _translate_str(str(rec.seq), table)
elif min(counter, key=counter.get) == 'two':
seqT = _translate_str(
str(rec.seq[1:len(rec.seq)] +
Seq("N", generic_dna)), table)
recordsFunc[i].seq = recordsFunc[i].seq[
1:len(rec.seq)] + Seq("N", generic_dna)
elif min(counter, key=counter.get) == 'three':
seqT = _translate_str(
str(rec.seq[2:len(rec.seq)] +
Seq("NN", generic_dna)), table)
recordsFunc[i].seq = recordsFunc[i].seq[
2:len(rec.seq)] + Seq("NN", generic_dna)
else:
seqT = _translate_str(
str(rec.seq[2:len(rec.seq)] +
Seq("NN", generic_dna)), table)
recordsFunc[
i].seq = recordsFunc[i].seq[2:len(rec.seq)] + Seq(
"NN", generic_dna)
else:
seqT = _translate_str(
str(rec.seq[1:len(rec.seq)] + Seq("N", generic_dna)),
table)
recordsFunc[
i].seq = recordsFunc[i].seq[1:len(rec.seq)] + Seq(
"N", generic_dna)
else:
pass
for j, obj in enumerate(seqT):
if '*' in obj:
seqT = seqT[:j] + 'Z' + seqT[j + 1:]
proteinSeqList.append(
SeqRecord(Seq(seqT, IUPAC.protein),
id=rec.id,
name=rec.name,
description=rec.description))
with open('translated.fas', 'w') as fp:
SeqIO.write(proteinSeqList, fp, 'fasta')
return recordsFunc