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 getCommands(self):
self.checkDiskSpace()
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
command = self.makeblastdb + " -in " + self.input_files[
0] + " -input_type fasta -dbtype prot -title " + self.basename + " -parse_seqids -out " + fileparts[
'dirname'] + "/" + self.basename
print "Command %s" % command
self.commands.append(command)
return self.commands
def init(self):
super(FastQCAnalysis, self).init()
if len(self.input_files) == 0:
raise Exception(
"No input files for FastQCAnalysis module. Can't init")
fileparts = FileUtils.getFileParts(self.input_files[0].input_file)
if fileparts['fileext'] == ".fastq":
dir = fileparts['filestub'] + "_fastqc/"
elif fileparts['fileext'] == ".gz":
dir = fileparts['filestub'].replace(".fastq", "") + "_fastqc/"
else:
dir = fileparts['basename'] + "_fastqc/"
self.fastqc_dir = dir
tmp = []
for i, f in enumerate(self.expected_output_filelist):
#tmp.append(dir + f)
AnalysisUtils.addExpectedOutputFile(self, dir + f)
def init(self):
if len(self.input_files) == 0:
raise Exception("No input files for BlastOutput6Parsermodule. Can't init")
fileparts = FileUtils.getFileParts(self.input_files[0])
def getCommands(self):
if self.commands and len(self.commands) > 0:
return self.commands
logging.info(" ========> Analysis %20s Getting commands" % (self.name))
self.commands = []
self.expected_output_files = []
self.temp_output_files = []
outdir = self.output_dir
tmpdir = self.working_dir
btbin = self.bowtiebindir + self.bowtiebinname
stbin = self.samtoolsbindir + self.samtoolsbinname
self.calculateSpaceNeeded()
if FileUtils.fileExists(btbin) == False:
raise Exception("Binary file [%s] doesn't exist = can't continue" %
btbin)
if FileUtils.fileExists(stbin) == False:
raise Exception("Binary file [%s] doesn't exist = can't continue" %
stbin)
if AnalysisUtils.checkInputFiles(self) == False:
raise Exception("Input files [%s] don't exist = can't continue" %
(self.input_files))
AnalysisUtils.checkDiskSpace(self)
for fobj in self.input_files:
f = fobj.input_file
try:
if f.endswith(".gz"):
# f = "<( zcat -c " + f + " )"
tmpf = f.replace(".gz", "")
fparts = FileUtils.getFileParts(tmpf)
command = "gunzip -c " + f + " > " + tmpdir + "/" + fparts[
'basename']
self.commands.append(command)
self.temp_output_files.append(tmpf)
f = tmpdir + "/" + fparts['basename']
fparts = FileUtils.getFileParts(f)
fstub = fparts['filestub']
bowtieoutfile = tmpdir + "/" + fstub + ".sam"
samtoolsoutfile = tmpdir + "/" + fstub + ".bam"
if self.param == None:
raise Exception(
"No parameters entered for bowtie = needs -x <genomeindex>"
)
command1 = btbin + " " + self.param + " " + f + " | " + stbin + " view -bS - | " + stbin + " sort - " + tmpdir + "/" + fstub
logging.info(" ========> Analysis %20s command 1 : %s" %
(self.name, command1))
#command2 = stbin + " view -bS " + bowtieoutfile + "| " + stbin + " sort - " + tmpdir + "/" + fstub
# logging.info(" ========> Analysis %20s command 2 : %s" % (self.name,command2))
command2 = stbin + " index " + samtoolsoutfile
logging.info(" ========> Analysis %20s command 3 : %s" %
(self.name, command2))
# self.expected_output_files.append(fstub + ".sam")
self.expected_output_files.append(
AnalysisExpectedOutputFile(expected_output_file=fstub +
".bam"))
self.expected_output_files.append(
AnalysisExpectedOutputFile(expected_output_file=fstub +
".bam.bai"))
self.commands.append(AnalysisCommand(command=command1))
self.commands.append(AnalysisCommand(command=command2))
#self.commands.append(command3)
except Exception as e:
logging.info(
" ========> Analysis %20s Failed building command list [%s]"
% (self.name, e))
raise
return self.commands