def align_two_alignments(aln1, aln2, moltype, params=None):
"""Returns an Alignment object from two existing Alignments.
aln1, aln2: cogent.core.alignment.Alignment objects, or data that can be
used to build them.
params: dict of parameters to pass in to the Clustal app controller.
"""
#create SequenceCollection object from seqs
aln1 = Alignment(aln1, MolType=moltype)
#Create mapping between abbreviated IDs and full IDs
aln1_int_map, aln1_int_keys = aln1.getIntMap()
#Create SequenceCollection from int_map.
aln1_int_map = Alignment(aln1_int_map, MolType=moltype)
#create Alignment object from aln
aln2 = Alignment(aln2, MolType=moltype)
#Create mapping between abbreviated IDs and full IDs
aln2_int_map, aln2_int_keys = aln2.getIntMap(prefix='seqn_')
#Create SequenceCollection from int_map.
aln2_int_map = Alignment(aln2_int_map, MolType=moltype)
#Update aln1_int_keys with aln2_int_keys
aln1_int_keys.update(aln2_int_keys)
#Create Mafft app.
app = Clustalw(InputHandler='_input_as_multiline_string',\
params=params,
SuppressStderr=True)
app.Parameters['-align'].off()
app.Parameters['-infile'].off()
app.Parameters['-profile'].on()
#Add aln_int_map as profile1
app.Parameters['-profile1'].on(\
app._tempfile_as_multiline_string(aln1_int_map.toFasta()))
#Add seq_int_map as profile2
app.Parameters['-profile2'].on(\
app._tempfile_as_multiline_string(aln2_int_map.toFasta()))
#Get results using int_map as input to app
res = app()
#Get alignment as dict out of results
alignment = dict(ClustalParser(res['Align'].readlines()))
#Make new dict mapping original IDs
new_alignment = {}
for k, v in alignment.items():
new_alignment[aln1_int_keys[k]] = v
#Create an Alignment object from alignment dict
new_alignment = Alignment(new_alignment, MolType=moltype)
#Clean up
res.cleanUp()
remove(app.Parameters['-profile1'].Value)
remove(app.Parameters['-profile2'].Value)
del(aln1,aln1_int_map,aln1_int_keys,\
aln2,aln2_int_map,aln2_int_keys,app,res,alignment)
return new_alignment
def align_two_alignments(aln1, aln2, moltype, params=None):
"""Returns an Alignment object from two existing Alignments.
aln1, aln2: cogent.core.alignment.Alignment objects, or data that can be
used to build them.
params: dict of parameters to pass in to the Clustal app controller.
"""
#create SequenceCollection object from seqs
aln1 = Alignment(aln1,MolType=moltype)
#Create mapping between abbreviated IDs and full IDs
aln1_int_map, aln1_int_keys = aln1.getIntMap()
#Create SequenceCollection from int_map.
aln1_int_map = Alignment(aln1_int_map,MolType=moltype)
#create Alignment object from aln
aln2 = Alignment(aln2,MolType=moltype)
#Create mapping between abbreviated IDs and full IDs
aln2_int_map, aln2_int_keys = aln2.getIntMap(prefix='seqn_')
#Create SequenceCollection from int_map.
aln2_int_map = Alignment(aln2_int_map,MolType=moltype)
#Update aln1_int_keys with aln2_int_keys
aln1_int_keys.update(aln2_int_keys)
#Create Mafft app.
app = Clustalw(InputHandler='_input_as_multiline_string',\
params=params,
SuppressStderr=True)
app.Parameters['-align'].off()
app.Parameters['-infile'].off()
app.Parameters['-profile'].on()
#Add aln_int_map as profile1
app.Parameters['-profile1'].on(\
app._tempfile_as_multiline_string(aln1_int_map.toFasta()))
#Add seq_int_map as profile2
app.Parameters['-profile2'].on(\
app._tempfile_as_multiline_string(aln2_int_map.toFasta()))
#Get results using int_map as input to app
res = app()
#Get alignment as dict out of results
alignment = dict(ClustalParser(res['Align'].readlines()))
#Make new dict mapping original IDs
new_alignment = {}
for k,v in alignment.items():
new_alignment[aln1_int_keys[k]]=v
#Create an Alignment object from alignment dict
new_alignment = Alignment(new_alignment,MolType=moltype)
#Clean up
res.cleanUp()
remove(app.Parameters['-profile1'].Value)
remove(app.Parameters['-profile2'].Value)
del(aln1,aln1_int_map,aln1_int_keys,\
aln2,aln2_int_map,aln2_int_keys,app,res,alignment)
return new_alignment
def add_seqs_to_alignment(seqs, aln, moltype, params=None):
"""Returns an Alignment object from seqs and existing Alignment.
seqs: a cogent.core.alignment.SequenceCollection object, or data that can
be used to build one.
aln: a cogent.core.alignment.Alignment object, or data that can be used to
build one
params: dict of parameters to pass in to the Clustal app controller.
"""
# create SequenceCollection object from seqs
seq_collection = SequenceCollection(seqs, MolType=moltype)
# Create mapping between abbreviated IDs and full IDs
seq_int_map, seq_int_keys = seq_collection.getIntMap()
# Create SequenceCollection from int_map.
seq_int_map = SequenceCollection(seq_int_map, MolType=moltype)
# create Alignment object from aln
aln = Alignment(aln, MolType=moltype)
# Create mapping between abbreviated IDs and full IDs
aln_int_map, aln_int_keys = aln.getIntMap(prefix="seqn_")
# Create SequenceCollection from int_map.
aln_int_map = Alignment(aln_int_map, MolType=moltype)
# Update seq_int_keys with aln_int_keys
seq_int_keys.update(aln_int_keys)
# Create Mafft app.
app = Clustalw(InputHandler="_input_as_multiline_string", params=params, SuppressStderr=True)
app.Parameters["-align"].off()
app.Parameters["-infile"].off()
app.Parameters["-sequences"].on()
# Add aln_int_map as profile1
app.Parameters["-profile1"].on(app._tempfile_as_multiline_string(aln_int_map.toFasta()))
# Add seq_int_map as profile2
app.Parameters["-profile2"].on(app._tempfile_as_multiline_string(seq_int_map.toFasta()))
# Get results using int_map as input to app
res = app()
# Get alignment as dict out of results
alignment = dict(ClustalParser(res["Align"].readlines()))
# Make new dict mapping original IDs
new_alignment = {}
for k, v in alignment.items():
new_alignment[seq_int_keys[k]] = v
# Create an Alignment object from alignment dict
new_alignment = Alignment(new_alignment, MolType=moltype)
# Clean up
res.cleanUp()
remove(app.Parameters["-profile1"].Value)
remove(app.Parameters["-profile2"].Value)
del (seq_collection, seq_int_map, seq_int_keys, aln, aln_int_map, aln_int_keys, app, res, alignment)
return new_alignment
def __call__(self, data=None, remove_tmp=True):
"""Run the application with the specified kwargs on data
data: anything that can be cast into a string or written out to
a file. Usually either a list of things or a single string or
number. input_handler will be called on this data before it
is passed as part of the command-line argument, so by creating
your own input handlers you can customize what kind of data
you want your application to accept
remove_tmp: if True, removes tmp files
NOTE: Override of the base class to handle redirected output
"""
input_handler = self.InputHandler
suppress_stderr = self.SuppressStderr
outfile = self.getTmpFilename(self.TmpDir)
self._outfile = outfile
if suppress_stderr:
errfile = FilePath("/dev/null")
else:
errfile = FilePath(self.getTmpFilename(self.TmpDir))
if data is None:
input_arg = ""
else:
input_arg = getattr(self, input_handler)(data)
# Build up the command, consisting of a BaseCommand followed by
# input and output (file) specifications
command = self._command_delimiter.join(
filter(None, [self.BaseCommand, str(input_arg), ">", str(outfile), "2>", str(errfile)])
)
if self.HaltExec:
raise AssertionError, "Halted exec with command:\n" + command
# The return value of system is a 16-bit number containing the signal
# number that killed the process, and then the exit status.
# We only want to keep the exit status so do a right bitwise shift to
# get rid of the signal number byte
exit_status = system(command) >> 8
# Determine if error should be raised due to exit status of
# appliciation
if not self._accept_exit_status(exit_status):
raise ApplicationError, "Unacceptable application exit status: %s, command: %s" % (
str(exit_status),
command,
)
out = open(outfile, "r")
err = None
if not suppress_stderr:
err = open(errfile, "r")
result = CommandLineAppResult(out, err, exit_status, result_paths=self._get_result_paths(data))
# Clean up the input file if one was created
if remove_tmp:
if self._input_filename:
remove(self._input_filename)
self._input_filename = None
return result
def __call__(self, data=None, remove_tmp=True):
"""Run the application with the specified kwargs on data
data: anything that can be cast into a string or written out to
a file. Usually either a list of things or a single string or
number. input_handler will be called on this data before it
is passed as part of the command-line argument, so by creating
your own input handlers you can customize what kind of data
you want your application to accept
remove_tmp: if True, removes tmp files
NOTE: Override of the base class to handle redirected output
"""
input_handler = self.InputHandler
suppress_stderr = self.SuppressStderr
outfile = self.getTmpFilename(self.TmpDir)
self._outfile = outfile
if suppress_stderr:
errfile = FilePath('/dev/null')
else:
errfile = FilePath(self.getTmpFilename(self.TmpDir))
if data is None:
input_arg = ''
else:
input_arg = getattr(self, input_handler)(data)
# Build up the command, consisting of a BaseCommand followed by
# input and output (file) specifications
command = self._command_delimiter.join(filter(None,\
[self.BaseCommand,str(input_arg),'>',str(outfile),'2>',\
str(errfile)]))
if self.HaltExec:
raise AssertionError, "Halted exec with command:\n" + command
# The return value of system is a 16-bit number containing the signal
# number that killed the process, and then the exit status.
# We only want to keep the exit status so do a right bitwise shift to
# get rid of the signal number byte
exit_status = system(command) >> 8
# Determine if error should be raised due to exit status of
# appliciation
if not self._accept_exit_status(exit_status):
raise ApplicationError, \
'Unacceptable application exit status: %s, command: %s'\
% (str(exit_status),command)
out = open(outfile, "r")
err = None
if not suppress_stderr:
err = open(errfile, "r")
result = CommandLineAppResult(out,err,exit_status,\
result_paths=self._get_result_paths(data))
# Clean up the input file if one was created
if remove_tmp:
if self._input_filename:
remove(self._input_filename)
self._input_filename = None
return result
