def align(self, input_):
if self.clustalw_exe is None:
raise InitError("clustalw executable is not set")
input_ = self._fix_input(input_)
input_path = tempfile.mktemp()
output_path = tempfile.mktemp()
write_fasta(input_path, input_)
cmd = [self.clustalw_exe, '-TYPE=PROTEIN', '-OUTPUT=FASTA',
'-PWMATRIX=BLOSUM', '-OUTFILE=%s' % output_path, '-INFILE=%s' % input_path]
try:
p = subprocess.Popen(cmd,
stdout=subprocess.PIPE, stderr=subprocess.PIPE)
p.wait()
if p.returncode != 0:
raise RuntimeError("%s for %s" % (p.stderr.read().decode('ascii'), str(input_)))
return Alignment(self._fix_output(parse_fasta(output_path)))
finally:
for path in [input_path, output_path]:
if os.path.isfile(path):
os.remove(path)
def align(self, input_):
if self.clustalw_exe is None:
raise InitError("clustalw executable is not set")
input_path = tempfile.mktemp()
output_path = tempfile.mktemp()
write_fasta(input_path, input_)
cmd = [self.clustalw_exe, '-TYPE=PROTEIN', '-OUTPUT=FASTA',
'-PWMATRIX=BLOSUM', '-OUTFILE=%s' % output_path, '-INFILE=%s' % input_path]
try:
p = subprocess.Popen(cmd,
stdout=subprocess.PIPE, stderr=subprocess.PIPE)
p.wait()
if p.returncode != 0:
raise RuntimeError("%s for %s" % (p.stderr.read().decode('ascii'), str(input_)))
return Alignment(parse_fasta(output_path))
finally:
for path in [input_path, output_path]:
if os.path.isfile(path):
os.remove(path)
def align(self,
template_sequence,
template_secstr,
target_sequence,
gap_open=-13.0,
gap_extend=-0.4,
modifier=3.0):
_log.debug("kmad align\n{}\n{}\n{}".format(template_sequence,
template_secstr,
target_sequence))
# Prevent kmad from adding insertions in bulges, replace those.
template_secstr = self._remove_bulges(template_secstr, 'H', 3)
template_secstr = self._remove_bulges(template_secstr, 'E', 3)
if len(template_sequence) <= 0:
raise ValueError("empty template sequence")
if len(template_sequence) != len(template_secstr):
raise ValueError(
"template sequence ({}) has different length than secondary structure ({})"
.format(len(template_sequence), len(template_secstr)))
kmad_template_sequence = self._to_kmad_sequence(
template_sequence, template_secstr)
kmad_target_sequence = self._to_kmad_sequence(target_sequence)
input_path = tempfile.mktemp()
output_path = tempfile.mktemp()
write_fasta(input_path, {
'target': kmad_target_sequence,
'template': kmad_template_sequence
})
try:
self._run_kmad(input_path, output_path, gap_open, gap_extend,
modifier)
output_path += '_al'
aligned = parse_fasta(output_path)
_log.debug("kmad aligned\n{}\n{}".format(aligned['target'],
aligned['template']))
finally:
for path in [input_path, output_path]:
if os.path.isfile(path):
os.remove(path)
alignment = TargetTemplateAlignment(aligned['target'],
aligned['template'])
return alignment
def align(self, template_sequence, template_secstr, target_sequence,
gap_open=-13.0, gap_extend=-0.4, modifier=3.0):
_log.debug("kmad align\n{}\n{}\n{}".format(template_sequence, template_secstr, target_sequence))
# Prevent kmad from adding insertions in bulges, replace those.
template_secstr = self._remove_bulges(template_secstr, 'H', 3)
template_secstr = self._remove_bulges(template_secstr, 'E', 3)
if len(template_sequence) <= 0:
raise ValueError("empty template sequence")
if len(template_sequence) != len(template_secstr):
raise ValueError("template sequence ({}) has different length than secondary structure ({})"
.format(len(template_sequence), len(template_secstr)))
kmad_template_sequence = self._to_kmad_sequence(template_sequence, template_secstr)
kmad_target_sequence = self._to_kmad_sequence(target_sequence)
input_path = tempfile.mktemp()
output_path = tempfile.mktemp()
write_fasta(input_path, {'target': kmad_target_sequence,
'template': kmad_template_sequence})
try:
self._run_kmad(input_path, output_path, gap_open, gap_extend, modifier)
output_path += '_al'
aligned = parse_fasta(output_path)
_log.debug("kmad aligned\n{}\n{}".format(aligned['target'], aligned['template']))
finally:
for path in [input_path, output_path]:
if os.path.isfile(path):
os.remove(path)
alignment = TargetTemplateAlignment(aligned['target'], aligned['template'])
return alignment
args = arg_parser.parse_args()
tmp_dir = tempfile.mkdtemp()
model_storage.model_dir = tmp_dir
final_output_dir = settings.MODEL_DIR
if args.output_dir:
final_output_dir = args.output_dir
if not os.path.isdir(final_output_dir):
raise ValueError("Not a directory: {}".format(final_output_dir))
try:
sequence = list(parse_fasta(args.fasta).values())[0]
species_id = args.species.upper()
if args.template:
pdbid, chain_id = args.template.split('_')
template_id = TemplateID(pdbid, chain_id)
else:
template_id = None
domain_alignments = domain_aligner.get_domain_alignments(sequence, args.position, template_id)
_log.info("{} domain alignments".format(len(domain_alignments)))
ts = [ModelThread(sequence, species_id, ali, final_output_dir) for ali in domain_alignments]
for t in ts:
t.start()
def pick_random_sequences(n):
sprot_sequences = parse_fasta(SPROT_FASTA)
keys = random.sample(sprot_sequences.keys(), n)
return {key: sprot_sequences[key] for key in keys}
args = arg_parser.parse_args()
tmp_dir = tempfile.mkdtemp()
model_storage.model_dir = tmp_dir
final_output_dir = settings.MODEL_DIR
if args.output_dir:
final_output_dir = args.output_dir
if not os.path.isdir(final_output_dir):
raise ValueError("Not a directory: {}".format(final_output_dir))
try:
sequence = parse_fasta(args.fasta).values()[0]
species_id = args.species.upper()
if args.template:
pdbid, chain_id = args.template.split('_')
template_id = TemplateID(pdbid, chain_id)
else:
template_id = None
domain_alignments = domain_aligner.get_domain_alignments(sequence, args.position, template_id)
_log.info("{} domain alignments".format(len(domain_alignments)))
ts = [ModelThread(sequence, species_id, ali, final_output_dir) for ali in domain_alignments]
for t in ts:
t.start()
'--template', help="underscore separated template pdbid and chain")
args = arg_parser.parse_args()
tmp_dir = tempfile.mkdtemp()
model_storage.model_dir = tmp_dir
final_output_dir = settings.MODEL_DIR
if args.output_dir:
final_output_dir = args.output_dir
if not os.path.isdir(final_output_dir):
raise ValueError("Not a directory: {}".format(final_output_dir))
try:
sequence = list(parse_fasta(args.fasta).values())[0]
species_id = args.species.upper()
if args.template:
pdbid, chain_id = args.template.split('_')
template_id = TemplateID(pdbid, chain_id)
else:
template_id = None
domain_alignments = domain_aligner.get_domain_alignments(
sequence, args.position, template_id)
_log.info("{} domain alignments".format(len(domain_alignments)))
ts = [
ModelThread(sequence, species_id, ali, final_output_dir)
def pick_random_sequences(n):
sprot_sequences = parse_fasta(SPROT_FASTA)
keys = random.sample(sprot_sequences.keys(), n)
return {key:sprot_sequences[key] for key in keys}