def test_cmalign_from_alignment(self):
"""cmalign_from_alignment should work as expected.
"""
#Align with cmalign_from_alignment without original alignment.
aln, struct = cmalign_from_alignment(aln=self.seqs2_aligned,\
structure_string=self.struct2_aligned_string,\
seqs=self.seqs1_unaligned_gaps,moltype=RNA,include_aln=False)
#Check correct alignment
self.assertEqual(aln.todict(),self.seqs1_aligned)
#Check correct struct
self.assertEqual(wuss_to_vienna(str(struct)),\
self.seqs1_aligned_struct_string)
#should work with gapped seqs. Need to test this is taken care of
# since cmalign segfaults when there are gaps in the seqs to be aligned.
aln, struct = cmalign_from_alignment(aln=self.seqs2_aligned,\
structure_string=self.struct2_aligned_string,\
seqs=self.seqs1_unaligned_gaps,moltype=RNA)
#alignment should be correct
self.assertEqual(aln.todict(),self.seqs1_and_seqs2_aligned)
#structure should be correct
self.assertEqual(wuss_to_vienna(str(struct)),\
self.seqs1_and_seqs2_aligned_struct_string)
#should work with ungapped seqs.
aln, struct = cmalign_from_alignment(aln=self.seqs2_aligned,\
structure_string=self.struct2_aligned_string,\
seqs=self.seqs1_unaligned_gaps,moltype=RNA)
#alignment should be correct
self.assertEqual(aln.todict(),self.seqs1_and_seqs2_aligned)
#structure should be correct
self.assertEqual(wuss_to_vienna(str(struct)),\
self.seqs1_and_seqs2_aligned_struct_string)
#should return standard out
aln, struct,stdout = cmalign_from_alignment(aln=self.seqs2_aligned,\
structure_string=self.struct2_aligned_string,\
seqs=self.seqs1_unaligned_gaps,moltype=RNA,\
return_stdout=True)
#Test that standard out is same length as expected
self.assertEqual(len(stdout.split('\n')),\
len(CMALIGN_STDOUT.split('\n')))
def __call__(self, seq_path, result_path=None, log_path=None,
failure_path=None, cmbuild_params=None, cmalign_params=None):
log_params = []
# load candidate sequences
candidate_sequences = dict(parse_fasta(open(seq_path, 'U')))
# load template sequences
try:
info, template_alignment, struct = list(MinimalRfamParser(open(
self.Params['template_filepath'], 'U'),
seq_constructor=ChangedSequence))[0]
except RecordError:
raise ValueError(
"Template alignment must be in Stockholm format with corresponding secondary structure annotation when using InfernalAligner.")
# Need to make separate mapping for unaligned sequences
unaligned = SequenceCollection.from_fasta_records(
candidate_sequences.iteritems(), DNASequence)
mapped_seqs, new_to_old_ids = unaligned.int_map(prefix='unaligned_')
mapped_seq_tuples = [(k, str(v)) for k,v in mapped_seqs.iteritems()]
# Turn on --gapthresh option in cmbuild to force alignment to full
# model
if cmbuild_params is None:
cmbuild_params = {}
cmbuild_params.update({'--gapthresh': 1.0})
# record cmbuild parameters
log_params.append('cmbuild parameters:')
log_params.append(str(cmbuild_params))
# Turn on --sub option in Infernal, since we know the unaligned sequences
# are fragments.
# Also turn on --gapthresh to use same gapthresh as was used to build
# model
if cmalign_params is None:
cmalign_params = {}
cmalign_params.update({'--sub': True, '--gapthresh': 1.0})
# record cmalign parameters
log_params.append('cmalign parameters:')
log_params.append(str(cmalign_params))
# Align sequences to alignment including alignment gaps.
aligned, struct_string = cmalign_from_alignment(aln=template_alignment,
structure_string=struct,
seqs=mapped_seq_tuples,
include_aln=True,
params=cmalign_params,
cmbuild_params=cmbuild_params)
# Pull out original sequences from full alignment.
infernal_aligned = []
# Get a dict of the ids to sequences (note that this is a
# cogent alignment object, hence the call to NamedSeqs)
aligned_dict = aligned.NamedSeqs
for n, o in new_to_old_ids.iteritems():
aligned_seq = aligned_dict[n]
infernal_aligned.append((o, aligned_seq))
# Create an Alignment object from alignment dict
infernal_aligned = Alignment.from_fasta_records(infernal_aligned, DNASequence)
if log_path is not None:
log_file = open(log_path, 'w')
log_file.write('\n'.join(log_params))
log_file.close()
if result_path is not None:
result_file = open(result_path, 'w')
result_file.write(infernal_aligned.to_fasta())
result_file.close()
return None
else:
try:
return infernal_aligned
except ValueError:
return {}
def __call__(self, seq_path, result_path=None, log_path=None,
failure_path=None, cmbuild_params=None, cmalign_params=None):
log_params = []
# load candidate sequences
candidate_sequences = dict(parse_fasta(open(seq_path, 'U')))
# load template sequences
try:
info, template_alignment, struct = list(MinimalRfamParser(open(
self.Params['template_filepath'], 'U'),
seq_constructor=ChangedSequence))[0]
except RecordError:
raise ValueError(
"Template alignment must be in Stockholm format with corresponding secondary structure annotation when using InfernalAligner.")
# Need to make separate mapping for unaligned sequences
unaligned = SequenceCollection.from_fasta_records(
candidate_sequences.iteritems(), DNASequence)
mapped_seqs, new_to_old_ids = unaligned.int_map(prefix='unaligned_')
mapped_seq_tuples = [(k, str(v)) for k,v in mapped_seqs.iteritems()]
# Turn on --gapthresh option in cmbuild to force alignment to full
# model
if cmbuild_params is None:
cmbuild_params = {}
cmbuild_params.update({'--gapthresh': 1.0})
# record cmbuild parameters
log_params.append('cmbuild parameters:')
log_params.append(str(cmbuild_params))
# Turn on --sub option in Infernal, since we know the unaligned sequences
# are fragments.
# Also turn on --gapthresh to use same gapthresh as was used to build
# model
if cmalign_params is None:
cmalign_params = {}
cmalign_params.update({'--sub': True, '--gapthresh': 1.0})
# record cmalign parameters
log_params.append('cmalign parameters:')
log_params.append(str(cmalign_params))
# Align sequences to alignment including alignment gaps.
aligned, struct_string = cmalign_from_alignment(aln=template_alignment,
structure_string=struct,
seqs=mapped_seq_tuples,
include_aln=True,
params=cmalign_params,
cmbuild_params=cmbuild_params)
# Pull out original sequences from full alignment.
infernal_aligned = []
# Get a dict of the ids to sequences (note that this is a
# cogent alignment object, hence the call to NamedSeqs)
aligned_dict = aligned.NamedSeqs
for n, o in new_to_old_ids.iteritems():
aligned_seq = aligned_dict[n]
infernal_aligned.append((o, aligned_seq))
# Create an Alignment object from alignment dict
infernal_aligned = Alignment.from_fasta_records(infernal_aligned, DNASequence)
if log_path is not None:
log_file = open(log_path, 'w')
log_file.write('\n'.join(log_params))
log_file.close()
if result_path is not None:
result_file = open(result_path, 'w')
result_file.write(infernal_aligned.to_fasta())
result_file.close()
return None
else:
try:
return infernal_aligned
except ValueError:
return {}