def testCreateMummerDeltaFile(self):
""" We need the sequences to create the alignments """
refseqs = FastaFile.getSequenceDict(self.input_files[0])
qryseqs = FastaFile.getSequenceDict(self.input_files[1])
self.assertTrue(len(refseqs) == 87)
self.assertTrue(len(qryseqs) == 34)
mdf = MummerDeltaFile(self.deltafile,refseqs,qryseqs)
self.assertTrue(mdf)
mdf.parse()
alns = mdf.alns
self.assertTrue(len(alns) == 54)
self.assertTrue('GG739631.1' in alns)
idalns = alns['GG739631.1']
self.assertTrue(len(idalns) == 14)
self.assertTrue(idalns[13].qstart == 293765)
def getCommands(self):
self.commands = []
self.output_files = []
self.checkDiskSpace()
seqs = FastaFile.getSequenceDict(self.refgenome, False)
if self.checkInputFiles() == False:
raise Exception("Input files [%s] don't exist = can't continue" %
(self.input_files))
fileparts = FileUtils.getFileParts(self.input_files[0])
self.basename = fileparts['basename']
# Need to set dbtype somewhere
outfile1 = self.working_dir + "/" + self.basename + ".raw.vcf"
outfile2 = self.working_dir + "/" + self.basename + ".flt.vcf"
regstr = ""
if self.regionstr != "":
regstr = " -r " + self.regionstr
outfile1 = self.working_dir + "/" + self.basename + "." + self.regionstr + ".raw.vcf"
outfile2 = self.working_dir + "/" + self.basename + "." + self.regionstr + ".flt.vcf"
self.expected_output_files.append(outfile1)
self.expected_output_files.append(outfile2)
command1 = self.samtools + " mpileup -uf " + self.refgenome + " " + self.input_files[
0] + " " + regstr + " | " + self.bcftools + " view " + " -bvcg - > " + outfile1
command2 = self.bcftools + " view " + outfile1 + " | " + self.vcfutils + " varFilter -D100 > " + outfile2
print "Command %s" % command1
print "Command %s" % command2
self.commands.append(
AnalysisCommand(command=command1,
command_rank=len(self.commands) + 1))
self.commands.append(
AnalysisCommand(command=command2,
command_rank=len(self.commands) + 1))
return self.commands
def getCommands(self):
self.commands = []
self.output_files = []
self.checkDiskSpace()
print "Reading genome file"
seqs = FastaFile.getSequenceDict(self.refgenome,False)
if self.checkInputFiles() == False:
raise Exception("Input files [%s] don't exist = can't continue"%(self.input_files))
fileparts = FileUtils.getFileParts(self.input_files[0])
self.basename = fileparts['basename']
for seq in seqs:
len = seqs[seq]['len']
i = 1
while i < len:
end = i + self.chunk -1
if end > len:
end = len
regionstr = "%s:%d-%d"%(seq,i,end)
tmpana = AnalysisFactory.createAnalysisFromModuleName("SamtoolsMpileup")
tmpana.setInputFiles(self.input_files,self.input_types)
tmpana.refgenome = self.refgenome
tmpana.regionstr = regionstr
tmpana.init()
tmpcmds = tmpana.getCommands()
for cmd in tmpcmds:
self.commands.append(cmd)
i = i + self.chunk
return self.commands
def read_sequences(seqfile):
seqs = FastaFile.getSequenceDict(seqfile)
return seqs