def run(self):
logger.info('CycleStep4 object running, %s' % self.thisDir)
lsc.verifyDirExists(self.thisDir)
lsc.createTimestamp(os.path.join(self.thisDir, 'xml', 'cycle.step4.start.xml'))
# lsc.subTypeTimestamp(self.thisDir, 'cycle', 'CycleStep4_start')
outname = os.path.join(self.thisDir, 'logs', 'gene_deactivation.log')
if not os.path.exists(outname):
if not self.options.noGeneDeactivation:
# by default gene deactivation is turned on.
cmd = lsc.evolverGeneDeactivationStep(self.thisDir, self.thisParentDir)
p = subprocess.Popen(cmd, cwd = self.getLocalTempDir(),
stdout = subprocess.PIPE, stderr = subprocess.STDOUT)
out = p.communicate()[0]
f=open(outname + '.tmp', 'w')
f.write(out)
f.close()
os.rename(outname + '.tmp', outname)
else:
# this could cause a proliferation of gene creation.
cmd = [lsc.which('cp')]
cmd.append(os.path.join(thisDir, 'intra', 'evannots.gff'))
cmd.append(os.path.join(thisDir, 'annots.gff'))
cmds = [cmd]
cmds.append([lsc.which('touch'), outname])
lsc.runCommands(cmds, self.getLocalTempDir())
lsc.createTimestamp(os.path.join(self.thisDir, 'xml', 'cycle.step4.end.xml'))
def main():
usage = ('usage: %prog --simDir path/to/dir [options]\n\n'
'%prog takes in a simulation directory and then extracts\n'
'the sequence of each leaf node in fasta format and stores them\n'
'in the respective step\'s directory.')
parser = OptionParser(usage = usage)
initOptions(parser)
options, args = parser.parse_args()
checkOptions(options, parser)
cycles = glob.glob(os.path.join(options.simDir, '*'))
cycles = directoriesOnly(cycles)
leafs = {}
nt = newickTreeParser(options.inputNewick, 0.0)
extractLeafs(nt, leafs)
for d in cycles:
if not options.allCycles and not os.path.basename(d) in leafs:
continue
cmds = []
outPipes = []
inPipes = []
nameA = os.path.basename(d)
nameA = nameA.replace('[','')
nameA = nameA.replace(']','')
cleanName = nameA.replace('\'','')
cmd = [lsc.which('evolver_cvt')]
cmd.append('-fromrev')
cmd.append(os.path.join(d,'seq.rev'))
cmd.append('-tofasta')
cmd.append(os.path.join(d, 'seq.fa.tmp'))
inPipes.append(None)
outPipes.append(None)
cmds.append(cmd)
cmd = [lsc.which('mv')]
cmd.append(os.path.join(d, 'seq.fa.tmp'))
cmd.append(os.path.join(d, 'seq.fa'))
inPipes.append(None)
outPipes.append(None)
cmds.append(cmd)
cmd = [lsc.which('sed')]
cmd.append(r"s/^>/>%s./;" % cleanName)
inPipes.append(os.path.join(d, 'seq.fa'))
outPipes.append(os.path.join(d, 'seq.name.fa.tmp'))
cmds.append(cmd)
cmd = [lsc.which('mv')]
cmd.append(os.path.join(d, 'seq.name.fa.tmp'))
cmd.append(os.path.join(d, 'seq.name.fa'))
inPipes.append(None)
outPipes.append(None)
cmds.append(cmd)
lsc.runCommands(cmds, os.curdir, outPipes = outPipes, inPipes = inPipes, mode = 's')
def run(self):
logger.info('Extract object running, thisDir: %s' % (self.thisDir))
if self.isLeaf:
ext = '.maf'
else:
ext = '.tmp.maf'
outname = os.path.join(self.thisDir, self.alignName + ext)
if not os.path.exists(outname):
cmd = [lsc.which('evolver_cvt')]
cmd.append('-fromrev')
cmd.append(os.path.join(self.thisDir, 'aln.rev'))
cmd.append('-tomaf')
cmd.append(outname + '.tmp')
cmds = [cmd]
cmds.append([lsc.which('mv'), outname + '.tmp', outname])
lsc.runCommands(cmds, self.getLocalTempDir())
def run(self):
logger.info('CycleStep3 object running, %s' % self.thisDir)
lsc.verifyDirExists(self.thisDir)
lsc.createTimestamp(os.path.join(self.thisDir, 'xml', 'cycle.step3.start.xml'))
# trf
regex = r'^(chr\S+)\.outseq\.fa.*\.dat'
pat = re.compile(regex)
files = glob.glob(os.path.join(self.thisDir, 'intra', '*.dat'))
cmds = []
outPipes = []
followCmds = []
followPipes = []
for f in files:
# each file is the trf output for one chromosome
m = re.match(regex, os.path.basename(f))
if m is None:
raise RuntimeError('Regex "%s" failed on filename %s' % (regex, os.path.basename(f)))
outname = os.path.join(self.thisDir, 'intra', m.group(1) + '.trfannots.gff')
if not os.path.exists(outname):
# convert the .dat to .gff
cmd = [lsc.which('evolver_trf2gff.py'), f]
cmds.append(cmd)
outPipes.append(outname + '.tmp')
# atomic files
followCmds.append([lsc.which('mv'), outname + '.tmp', outname])
followPipes.append(None)
lsc.runCommands(cmds, self.getLocalTempDir(), outPipes = outPipes, mode = 'p')
lsc.runCommands(followCmds, self.getLocalTempDir(), outPipes = followPipes, mode = 'p')
catCmd, evoCmd, cvtCmd, followCmds = lsc.evolverIntraMergeCmds(self.thisDir, self.theChild)
lsc.runCommands([catCmd, evoCmd, cvtCmd], self.getLocalTempDir(),
outPipes = [os.path.join(self.thisDir, 'intra', 'evannots.gff.tmp'), None, None],
mode = 'p')
lsc.runCommands(followCmds, self.getLocalTempDir())
lsc.createTimestamp(os.path.join(self.thisDir, 'xml', 'cycle.step3.end.xml'))
self.setFollowOnTarget(CycleStep4(self.thisNewickStr, self.thisParentDir,
self.thisStepLength, self.options))
def main():
usage = ('usage: %prog --simDir path/to/dir [options]\n\n'
'%prog takes in a simulation directory and then extracts\n'
'the sequence of each leaf node in fasta format and stores them\n'
'in the respective step\'s directory.')
parser = OptionParser(usage=usage)
initOptions(parser)
options, args = parser.parse_args()
checkOptions(options, parser)
cycles = glob.glob(os.path.join(options.simDir, '*'))
cycles = directoriesOnly(cycles)
leafs = {}
nt = newickTreeParser(options.inputNewick, 0.0)
extractLeafs(nt, leafs)
for d in cycles:
if not options.allCycles and not os.path.basename(d) in leafs:
continue
cmds = []
outPipes = []
inPipes = []
nameA = os.path.basename(d)
nameA = nameA.replace('[', '')
nameA = nameA.replace(']', '')
cleanName = nameA.replace('\'', '')
cmd = [lsc.which('evolver_cvt')]
cmd.append('-fromrev')
cmd.append(os.path.join(d, 'seq.rev'))
cmd.append('-tofasta')
cmd.append(os.path.join(d, 'seq.fa.tmp'))
inPipes.append(None)
outPipes.append(None)
cmds.append(cmd)
cmd = [lsc.which('mv')]
cmd.append(os.path.join(d, 'seq.fa.tmp'))
cmd.append(os.path.join(d, 'seq.fa'))
inPipes.append(None)
outPipes.append(None)
cmds.append(cmd)
cmd = [lsc.which('sed')]
cmd.append(r"s/^>/>%s./;" % cleanName)
inPipes.append(os.path.join(d, 'seq.fa'))
outPipes.append(os.path.join(d, 'seq.name.fa.tmp'))
cmds.append(cmd)
cmd = [lsc.which('mv')]
cmd.append(os.path.join(d, 'seq.name.fa.tmp'))
cmd.append(os.path.join(d, 'seq.name.fa'))
inPipes.append(None)
outPipes.append(None)
cmds.append(cmd)
lsc.runCommands(cmds,
os.curdir,
outPipes=outPipes,
inPipes=inPipes,
mode='s')
