def compute_alifold(msa_file, alifold_params=''):
ml.info('Running RNAalifold.')
ml.debug(fname())
fd, out_path = mkstemp(prefix='rba_', suffix='_02', dir=CONFIG.tmpdir)
with TemporaryFile(mode='w+', encoding='utf-8') as tmp, os.fdopen(
fd, 'w') as output, open(msa_file, 'r') as inp:
cmd = [
'{}RNAalifold'.format(CONFIG.viennarna_path),
'--noPS',
'-f',
'C',
] + shlex.split(alifold_params)
ml.debug(cmd)
p = subprocess.Popen(cmd,
stdin=subprocess.PIPE,
stdout=output,
stderr=tmp,
universal_newlines=True)
p.communicate(input=inp.read())
if p.returncode:
msgfail = 'RNAalifold failed.'
ml.error(msgfail)
tmp.seek(0)
raise exceptions.RNAalifoldException(msgfail, tmp.read())
return out_path
def build_stockholm_from_clustal_alig(clustal_file, alif_file):
"""
build stockholm alignment
:return:
"""
ml.debug(fname())
with open(clustal_file, 'r') as cf, open(alif_file, 'r') as af:
# write stockholm align to buffer and read it with my parser
clust = AlignIO.read(cf, format='clustal')
temp = StringIO()
AlignIO.write(clust, temp, format='stockholm')
temp.seek(0)
st_alig = stockholm_read(temp)
# parse alifold output and add structure to stockholm alignment
for i, alif in enumerate(parse_seq_str(af)):
alifold_structure = alif.letter_annotations['ss0']
st_alig.column_annotations['SS_cons'] = alifold_structure
if i == 0:
break
st_fd, st_file = mkstemp(prefix='rba_', suffix='_15', dir=CONFIG.tmpdir)
with os.fdopen(st_fd, 'w') as sf:
st_alig.write_stockholm(sf)
return st_file
def select_sequences_from_similarity_rec(dist_mat: np.ndarray,
sim_threshold_percent=90) -> list:
"""
:param dist_mat: distmat table, by default obtained from read_clustal_distmat_file, values in percent
:param sim_threshold_percent: threshold for similarity in percent
:return:
"""
ml.debug(fname())
# dists = np.triu(dist_mat.as_matrix(), 1) # removes unwanted similarities
if dist_mat is None:
return [0]
dists = dist_mat.transpose()
# row, col = where(dists > sim_threshold_percent) # determine where the similarities are
include = set()
exclude = set()
a = np.array(range(len(dists)))
for i, r in enumerate(dists):
pr = r[~np.isnan(r)]
pa = a[~np.isnan(r)]
if (i in exclude) | (any(pr >= sim_threshold_percent)):
pu = np.where(pr >= sim_threshold_percent)
u = pa[pu]
if i not in exclude:
include |= {i}
to_ex = set(u.tolist()) - include
exclude |= to_ex # union operation
else:
include |= {i}
return sorted(include)
def run_cmbuild(cmbuild_input_file, cmbuild_params=''):
"""
run cmbuild procedure
input must be MSA in stockholm format with secondary structure prediction
note: consider what to do if only one sequence is available
:param cmbuild_input_file: Stockholm or selex alignment file
:param cmbuild_params: additional params to cmbuild
:return:
"""
ml.info('Runing cmbuild.')
ml.debug(fname())
cm_fd, cm_file = mkstemp(prefix='rba_', suffix='_13', dir=CONFIG.tmpdir)
os.close(cm_fd)
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
cmd = ['{}cmbuild'.format(CONFIG.infernal_path), '-F']
if cmbuild_params != '':
cmd += cmbuild_params.split()
cmd += [cm_file, cmbuild_input_file]
ml.debug(cmd)
r = call(cmd, stdout=tmp, stderr=tmp)
if r:
msgfail = 'Call to cmbuild failed.'
ml.error(msgfail)
tmp.seek(0)
raise exceptions.CmbuildException(msgfail, tmp.read())
return cm_file
def run_cmalign_on_fasta(fasta_file, model_file, cmalign_params='--notrunc', alig_format='stockholm'):
"""
run cmalign program with provided CM model file
:param fasta_file: input fasta to be aligned to cm model
:param model_file: file containing one or more cm models
:param cmalign_params: parameter of the search
:return:
"""
ml.info('Runing cmaling.')
ml.debug(fname())
cma_fd, cma_file = mkstemp(prefix='rba_', suffix='_14', dir=CONFIG.tmpdir)
os.close(cma_fd)
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
cmd = [
'{}cmalign'.format(CONFIG.infernal_path),
'--informat', 'fasta',
'--outformat', alig_format,
]
if cmalign_params != '':
cmd += cmalign_params.split()
cmd += ['-o', cma_file, model_file, fasta_file]
ml.debug(cmd)
r = call(cmd, stdout=tmp, stderr=tmp)
if r:
msgfail = 'Call to cmalign failed.'
ml.error(msgfail)
tmp.seek(0)
raise exceptions.CmalignException(msgfail, tmp.read())
return cma_file
def rebuild_structures_output_from_pred(reference_sequences_list,
predicted_structures_list,
method=None):
ml.debug(fname())
structuresids = [
seq.id for seq in predicted_structures_list if hasattr(seq, 'id')
]
structures_list = []
for seq in reference_sequences_list:
nr = SeqRecord(seq.seq,
id=seq.id,
name=seq.name,
description=seq.description,
annotations=seq.annotations,
letter_annotations=seq.letter_annotations)
if seq.id in structuresids:
n = structuresids.index(seq.id)
nr.letter_annotations.update(
predicted_structures_list[n].letter_annotations)
nr.annotations.update(predicted_structures_list[n].annotations)
nr.annotations['predicted'] = True
else:
if method:
wmsg = '{} failed to predict structure for seq {}.'.format(
method, nr.id)
ml.warning(wmsg)
nr.annotations['predicted'] = False
structures_list.append(nr)
del nr
return structures_list
def build_cm_model_rsearch(query_seq, path2selected_sim_array):
ml.debug(fname())
query_structure = rna_blast_analyze.BR_core.viennaRNA.RNAfold(
str(query_seq.seq))[0]
# remove any annotations from query:
qs_clean = deepcopy(query_seq)
qs_clean.annotations = dict()
qs_clean.letter_annotations = dict()
# query_structure = RNA.fold(str(analyzed_hits.query.seq))[0]
# build stockholm like file for use in cm mohdel build
st_like = StockholmAlig()
st_like.append(qs_clean)
st_like.column_annotations['SS_cons'] = query_structure
fds, stock_file = mkstemp(prefix='rba_', suffix='_30', dir=CONFIG.tmpdir)
with os.fdopen(fds, 'w') as f:
st_like.write_stockholm(f)
# run actual cmbuild
cm_model_file = run_cmbuild(
stock_file,
cmbuild_params='--rsearch {}'.format(path2selected_sim_array))
# cleanup
BA_support.remove_one_file_with_try(stock_file)
return cm_model_file
def RNAfold(sequence):
ml.debug(fname())
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
r = check_output([
'{}RNAfold'.format(CONFIG.viennarna_path),
'--noPS',
],
input=sequence.encode(),
stderr=tmp)
if isinstance(r, Exception):
msgfail = 'RNAfold failed.'
ml.error(msgfail)
tmp.seek(0)
raise exceptions.RNAfoldException(msgfail, tmp.read())
# more robust decode
out_str = r.decode()
spl = out_str.split('\n')
seq = spl[0]
structure = spl[1][:len(seq)]
energy = float(spl[1][len(seq) + 2:-1])
# seq, structure, energy = r.decode().split()
# return seq, structure, float(energy[1:-1])
return structure, energy
def run_cmemit(model, params='', out_file=None):
"""
:param model:
:param params:
:return:
"""
ml.info('Run cmemit.')
ml.debug(fname())
if out_file:
out = out_file
else:
fd, out = mkstemp(prefix='rba_', suffix='_12', dir=CONFIG.tmpdir)
os.close(fd)
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
# build commandline
cmd = ['{}cmemit'.format(CONFIG.infernal_path)]
if params != '':
cmd += params.split()
cmd += ['-o', out, model]
ml.debug(cmd)
r = call(cmd, stdout=tmp, stderr=tmp)
if r:
msgfail = 'Call to cmemit failed.'
ml.error(msgfail)
tmp.seek(0)
raise exceptions.CmemitException(msgfail, tmp.read(0))
return out
def get_cm_model_table(query_file,
params=None,
threads=None,
rfam=None,
timeout=None):
ml.debug(fname())
if params is None:
params = dict()
cmscan_params = '-g '
if params and ('cmscan' in params) and params['cmscan']:
cmscan_params += params['cmscan']
try:
out_table = run_cmscan(query_file,
params=cmscan_params,
threads=threads,
rfam=rfam,
timeout=timeout)
f = open(out_table, 'r')
cmscan_data = parse_cmalign_infernal_table(f)
f.close()
remove_one_file_with_try(out_table)
return cmscan_data
except exceptions.CmscanException as e:
return None
def _aligner_block(nr_homolog_hits_file, params, msa_alg, threads=None):
"""
returns alignment file in clustal format
:param nr_homolog_hits_file:
:param params:
:param msa_alg:
:param threads: int
:return:
"""
ml.debug(fname())
if msa_alg == 'clustalo':
clustal_params = '--outfmt=clustal --force'
clustal_params += params.get('clustalo', '')
if threads:
clustal_params += ' --threads={}'.format(threads)
alig_file = compute_clustalo_clasic(nr_homolog_hits_file,
clustalo_params=clustal_params)
elif msa_alg == 'muscle':
if params and ('muscle' in params) and params['muscle']:
alig_file = run_muscle(nr_homolog_hits_file,
muscle_params=params['muscle'],
reorder=True)
else:
alig_file = run_muscle(nr_homolog_hits_file, reorder=True)
else:
print('invalig MSA alg chosen {}, valid are "clustalo" and "muscle"'.
format(msa_alg))
raise AttributeError()
return alig_file
def check_rfam_present():
"""
Check if RFAM file is present and converted to binary format required by cmscan
by running program cmpres.
If present but not converted, conversion is attempted.
:return: bool
"""
ml.debug(fname())
rfam = RfamInfo()
cm_present = os.path.isfile(rfam.file_path)
if cm_present:
if not check_if_cmpress_processed():
try:
run_cmpress(rfam.file_path)
except exceptions.CmpressException as e:
ml.error(str(e))
ml.error(
'The Rfam file might be corrupt. Please check following output to get more information.\n'
)
print(e.errors)
return False
return True
else:
return False
def rfam_subopt_pred(all_sequence_fasta, cm_ref_str, params=None, threads=1):
ml.debug(fname())
if params is None:
params = dict()
if params and ('mfold' in params) and params['mfold']:
assert isinstance(params['mfold'], (tuple, list)) and 3 == len(params['mfold']), \
"Incorrect parameters for hybrid_ss_min given. Need tuple of 3 numbers."
subs = run_hybrid_ss_min(all_sequence_fasta,
mfold=params['mfold'],
threads=threads)
else:
subs = run_hybrid_ss_min(all_sequence_fasta, threads=threads)
# now compute rna distance score
if threads == 1:
new_structures = []
for seq in subs:
new_structures.append(_helper_subopt(seq, cm_ref_str))
else:
with multiprocessing.Pool(processes=threads) as pool:
tuples = [(seq, cm_ref_str) for seq in subs]
new_structures = pool.starmap(_helper_subopt, tuples)
return new_structures
def compute_refold(alig_file, cons_file, timeout=None):
"""
runs refold program
:param alig_file: MSA alignment file in clustal format
:param cons_file: file with consensus structure in alifold format
:return:
"""
ml.debug(fname())
fd, out_path = mkstemp(prefix='rba_', suffix='_03', dir=CONFIG.tmpdir)
cmd = ['{}refold.pl'.format(CONFIG.refold_path), alig_file, cons_file]
ml.debug(cmd)
with TemporaryFile(mode='w+',
encoding='utf-8') as tmp, os.fdopen(fd, 'w') as output:
with subprocess.Popen(cmd, stdout=output, stderr=tmp) as p:
try:
p.wait(timeout=timeout)
except subprocess.TimeoutExpired:
p.kill()
p.wait()
raise
if p.returncode:
msgfail = 'Call to refold.pl failed.'
ml.error(msgfail)
tmp.seek(0)
raise exceptions.RefoldException(msgfail, tmp.read())
return out_path
def create_nr_homolog_hits_file_MSA_unsafe(sim_threshold_percent=None,
all_hits=None,
query=None,
cmscore_tr=0.0,
cm_threshold_percent=None,
len_diff=0.1):
"""
create non redundant homologous hits file
"""
ml.debug(fname())
dist_table, homologous_seqs, msgs = _trusted_hits_selection_wrapper(
all_hits, query, cmscore_tr, cm_threshold_percent, len_diff_=len_diff)
if dist_table.size == 0:
nr_homolog_hits = [query]
else:
# normal execution
to_include = rna_blast_analyze.BR_core.predict_structures.select_sequences_from_similarity_rec(
dist_table, sim_threshold_percent=sim_threshold_percent)
nr_homolog_hits = [homologous_seqs[i] for i in to_include]
fd_h, nr_homo_hits_file = mkstemp(prefix='rba_',
suffix='_59',
dir=CONFIG.tmpdir)
with os.fdopen(fd_h, 'w') as f:
SeqIO.write(nr_homolog_hits, f, 'fasta')
return nr_homo_hits_file, homologous_seqs, msgs
def extract_ref_from_cm(cm_file):
ml.debug(fname())
single_alig_file = run_cmemit(cm_file, params='-a -N 1')
o = open(single_alig_file, 'r')
salig = stockholm_read(o)
o.close()
remove_one_file_with_try(single_alig_file)
if len(salig) != 1:
raise AssertionError('File from cmemit does not have only one record in (not including reference).')
# recode structure, return it
ss = salig.column_annotations['SS_cons']
# inserts = str(salig[0].seq)
inserts = str(salig.column_annotations['RF'])
gapchars = '.~'
structure_list = []
for i, j in zip(ss, inserts):
if i in gapchars:
continue
structure_list.append(i)
# recode structure list
structure = cm_strucutre2br(''.join(structure_list))
return structure
def refold_stockholm(stockholm_alig, consensus_structure):
"""
compute refold.pl from Vienna RNA package
:param stockholm_alig:
:param consensus_structure:
:return:
"""
ml.debug(fname())
# convert to clustal alignment
fd, clust_tempfile = mkstemp(prefix='rba_', suffix='_23', dir=CONFIG.tmpdir)
with os.fdopen(fd, 'w') as f:
stockholm_alig.write_clustal(f)
# write fake alifold output with given consensus structure
fd, alif_fake_file = mkstemp(prefix='rba_', suffix='_24', dir=CONFIG.tmpdir)
with os.fdopen(fd, 'w') as f:
# the consensus sequence in alifold file is really not used for anything
f.write('A'*len(consensus_structure) + '\n')
f.write(consensus_structure + '\n')
# compute refold
# refold_path = locate_refold()
refold_constrained_file = compute_refold(clust_tempfile, alif_fake_file)
parsed_seqs = []
with open(refold_constrained_file, 'r') as f:
# read the file
for seq in BA_support.parse_seq_str(f):
parsed_seqs.append(seq)
# cleanup
BA_support.remove_files_with_try([clust_tempfile, alif_fake_file, refold_constrained_file])
return parsed_seqs
def run_cmfetch(cmfile, modelid, outfile=None):
"""
:param cmfile:
:param modelid:
:return:
"""
ml.info('Runing cmfetch.')
ml.debug(fname())
if outfile:
out = outfile
else:
fd, out = mkstemp(prefix='rba_', suffix='_11', dir=CONFIG.tmpdir)
os.close(fd)
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
cmd = [
'{}cmfetch'.format(CONFIG.infernal_path),
'-o', out,
cmfile,
modelid
]
ml.debug(cmd)
r = call(cmd, stdout=tmp, stderr=tmp)
if r:
msgfail = 'Call to cmfetch failed.'
ml.error(msgfail)
tmp.seek(0)
raise exceptions.CmfetchException(msgfail, tmp.read())
return out
def run_rnaplot(seq, structure=None, format='svg', outfile=None, timeout=None):
"""
run rnaplot in desired format
if seq
:param seq:
:param structure:
:return:
"""
ml.debug(fname())
if structure is None:
sequence = str(seq.seq)
structure = seq.letter_annotations['ss0']
else:
sequence = seq
assert len(sequence) == len(structure)
allowed_formats = {'ps', 'svg', 'gml'}
if format not in allowed_formats:
raise TypeError('Format can be only from {}.'.format(allowed_formats))
currdirr = os.getcwd()
tmpdir = gettempdir()
os.chdir(tmpdir)
cmd = ['{}RNAplot'.format(CONFIG.viennarna_path), '--output-format={}'.format(format)]
ml.debug(cmd)
rnaname = generate_random_name(10)
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
with subprocess.Popen(cmd, universal_newlines=True, stdin=subprocess.PIPE, stdout=tmp, stderr=tmp) as p:
try:
p.communicate(input='>{}\n{}\n{}\n'.format(
rnaname,
sequence,
structure
), timeout=timeout)
except subprocess.TimeoutExpired:
p.kill()
p.wait()
raise
if p.returncode:
msgfail = 'Call to RNAplot failed.'
ml.error(msgfail)
os.chdir(currdirr)
tmp.seek(0)
details = tmp.read()
ml.debug(details)
raise exceptions.RNAplotException(msgfail, details)
plot_output_file = os.path.join(tmpdir, rnaname + '_ss.' + format)
os.chdir(currdirr)
if outfile is None:
return plot_output_file
else:
shutil.move(os.path.join(tmpdir, plot_output_file), outfile)
return outfile
def subopt_fold_alifold(all_fasta_hits_file,
homologs_file,
aligner='muscle',
params=None,
threads=None):
"""
run clustal/muscle on selected homologs file
:return:
"""
ml.debug(fname())
if params is None:
params = dict()
# run aligner
# =================================================================================================================
if 'clustalo' == aligner:
clustal_params = ' --outfmt=clustal --force'
clustal_params += params.get('clustalo', '')
if threads:
clustal_params += ' --threads={}'.format(threads)
alig_file = compute_clustalo_clasic(homologs_file,
clustalo_params=clustal_params)
elif 'muscle' == aligner:
alig_file = run_muscle(homologs_file,
muscle_params=params.get('muscle', ''),
reorder=False)
else:
raise KeyError(
'provided key ({}) not recognized - avalible: "clustalo" "muscle"'.
format(aligner))
# run consensus prediction
# =================================================================================================================
alif_file = compute_alifold(alig_file,
alifold_params=params.get('alifold', ''))
# possibly need to decode alifold structure
alif_str = read_seq_str(alif_file)[0]
consensus_structure = alif_str.letter_annotations['ss0']
subs = run_hybrid_ss_min(all_fasta_hits_file,
mfold=params.get('mfold', (10, 2, 20)),
threads=threads)
# now compute rna distance score
if threads == 1:
new_structures = []
for seq in subs:
new_structures.append(_helper_subopt(seq, consensus_structure))
else:
with multiprocessing.Pool(processes=threads) as pool:
tuples = [(seq, consensus_structure) for seq in subs]
new_structures = pool.starmap(_helper_subopt, tuples)
remove_files_with_try([alif_file, alig_file])
return new_structures
def infer_hits_cm(bit_sc, tr=0):
ml.debug(fname())
pred = []
for i in bit_sc:
if i > tr:
pred.append(True)
else:
pred.append(False)
return pred
def run_rnaplot(seq, structure=None, format='svg', outfile=None):
"""
run rnaplot in desired format
if seq
:param seq:
:param structure:
:return:
"""
ml.debug(fname())
if structure is None:
sequence = str(seq.seq)
structure = seq.letter_annotations['ss0']
else:
sequence = seq
assert len(sequence) == len(structure)
allowed_formats = {'ps', 'svg', 'gml', 'xrna'}
if format not in allowed_formats:
raise TypeError('Format can be only from {}.'.format(allowed_formats))
fd, tmpfile = mkstemp(prefix='rba_', suffix='_08', dir=CONFIG.tmpdir)
rnaname = tmpfile.split('/')[-1].split('\\')[-1]
currdirr = os.getcwd()
tmpdir = gettempdir()
os.chdir(tmpdir)
with os.fdopen(fd, 'w') as fh:
fh.write('>{}\n{}\n{}\n'.format(rnaname, sequence, structure))
cmd = '{} --output-format={} < {}'.format(
shlex.quote('{}RNAplot'.format(CONFIG.viennarna_path)),
shlex.quote(format), shlex.quote(tmpfile))
ml.debug(cmd)
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
r = call(cmd, shell=True, stdout=tmp, stderr=tmp)
if r:
msgfail = 'Call to RNAplot failed.'
ml.error(msgfail)
os.chdir(currdirr)
tmp.seek(0)
details = tmp.read()
ml.debug(details)
raise exceptions.RNAplotException(msgfail, details)
# output file is name of the sequence (in this case name of the file) + "_ss." + chosen format
remove_one_file_with_try(tmpfile)
plot_output_file = os.path.join(tmpdir, rnaname + '_ss.' + format)
os.chdir(currdirr)
if outfile is None:
return plot_output_file
else:
shutil.move(os.path.join(tmpdir, plot_output_file), outfile)
return outfile
def download_cmmodels_file(path=None, url=None):
"""
downloads cm model from rfam database
default retrieve url is: 'ftp://ftp.ebi.ac.uk/pub/databases/Rfam/CURRENT/Rfam.cm.gz'
:param path:
:param url:
:return:
"""
print('Running CM download from RFAM.')
ml.debug(fname())
rfam = RfamInfo()
if path is None:
path = rfam.rfam_dir
if url is None:
url = rfam.url
if not os.path.exists(path):
os.makedirs(path)
cmd = ['wget', '-N', '-P', path, url]
ml.debug(cmd)
ml.info('Downloading RFAM database (aprox 300Mb). This may take a while...')
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
r = call(cmd, stderr=tmp, stdout=tmp)
if r:
msgfail = 'Call to wget failed. Please check the internet connection and/or availability of "wget".'
ml.error(msgfail)
ml.debug(cmd)
sys.exit(1)
tmp.seek(0)
cmd_output = tmp.read()
if 'Remote file no newer than local file' in cmd_output:
# do not download
msg = 'No new data. Nothing to do.'
ml.info(msg)
if ml.getEffectiveLevel() > 20:
print(msg)
else:
# unzip using build in gzip
with gzip.open(os.path.join(path, rfam.gzname), 'rb') as fin:
with open(os.path.join(path, rfam.rfam_file_name), 'wb') as fout:
shutil.copyfileobj(fin, fout)
# run cmpress to create binary files needed to run cmscan
try:
run_cmpress(os.path.join(path, rfam.rfam_file_name))
except exceptions.CmpressException as e:
ml.error(str(e))
ml.error('The Rfam file might be corrupt. Please check following output to get more information.\n')
print(e.errors)
sys.exit(1)
return os.path.join(path, rfam.rfam_file_name)
def run_muscle(fasta_file, out_file=None, muscle_params='', reorder=True):
"""
beware, muscle does not keep sequence order and the --stable switch is broken
:param fasta_file:
:param out_file:
:param muscle_params:
:param reorder:
:return:
"""
ml.info('Running muscle.')
ml.debug(fname())
if out_file:
cl_file = out_file
else:
cl_fd, cl_file = mkstemp(prefix='rba_',
suffix='_07',
dir=CONFIG.tmpdir)
os.close(cl_fd)
cmd = [
'{}muscle'.format(CONFIG.muscle_path), '-clwstrict', '-seqtype', 'rna',
'-out', cl_file, '-in', fasta_file, '-quiet'
]
if muscle_params != '':
cmd += [' '.join([shlex.quote(i) for i in shlex.split(muscle_params)])]
ml.debug(cmd)
with TemporaryFile(mode='w+', encoding='utf-8') as tmp:
r = call(cmd, stdout=tmp, stderr=tmp)
if r:
msgfail = 'Call to muscle failed.'
ml.error(msgfail)
tmp.seek(0)
raise exceptions.MuscleException(msgfail, tmp.read())
if reorder:
# reorder sequences acording to input file
with open(fasta_file, 'r') as ff, open(cl_file, 'r+') as oo:
orig_seqs = [i.id for i in SeqIO.parse(ff, format='fasta')]
muscle_align = {
i.id: i
for i in AlignIO.read(oo, format='clustal')
}
# reorder
reo_alig = []
for s_name in orig_seqs:
# muscle cuts names
reo_alig.append(muscle_align[s_name[:32]])
alig = AlignIO.MultipleSeqAlignment(reo_alig)
# write
oo.seek(0)
AlignIO.write(alig, oo, format='clustal')
oo.truncate()
return cl_file
def run_turbofold(sequences, params, timeout=None):
ml.info('Running Turbofold.')
ml.debug(fname())
try:
return _turbofold_worker(sequences, params, timeout=timeout)
except exceptions.TurboFoldException as e:
return e
except AssertionError as e:
return e
def filter_by_bits(blast_hitlist, getter, filter_conditions):
ml.debug(fname())
result = blast_hitlist
for relation, condition in filter_conditions:
result = [
h for h in result
if OPERATIONS[relation](getter(h).bits, condition)
]
return result
def create_report_object_from_locarna(exp_hit, locarna_alig):
"""
create object which will be appended to BlastSearchRecompute class
This needs to be Subsequences object
:param exp_hit:
:param locarna_alig:
:return:
"""
ml.debug(fname())
# chop alignment by seq
query_ind = [i for i, j in enumerate(locarna_alig) if j.id == 'query']
if len(query_ind) != 1:
raise exceptions.SubseqMatchError('Got multiple hits with id "query" in the Locarna alignment.')
trimmed_locarna_alig = trim_alignment_by_sequence(
locarna_alig,
str(locarna_alig[query_ind[0]].seq),
structure_annotation='SS_cons'
)
aligned_subsequence = BA_support.select_analyzed_aligned_hit(trimmed_locarna_alig, exp_hit.id)
# add annotations from exp hit
aligned_subsequence.annotations = exp_hit.annotations
aligned_subsequence.name = exp_hit.name
# also add annotations from locarna, mainly score
aligned_subsequence.annotations.update(locarna_alig.annotations)
# get the structure
# by refold
refold_structures = refold_stockholm(trimmed_locarna_alig, trimmed_locarna_alig.column_annotations['SS_cons'])
# select refold structure for my seq
seq_refold_structure = _select_refold_structure(refold_structures, exp_hit.id)
aligned_subsequence.letter_annotations['ss0'] = seq_refold_structure.letter_annotations['ss0']
aligned_subsequence.annotations['sss'] = ['ss0']
# prepare seq_record for subsequences
aligned_subsequence.description = ''
hit = BA_support.Subsequences(exp_hit)
hit.extension = aligned_subsequence
# find the matching sequence
pos_match = re.search(str(aligned_subsequence.seq), str(exp_hit.seq), flags=re.IGNORECASE)
if not pos_match:
raise exceptions.SubseqMatchError(
'Aligned portion of subject sequence in Locarna alignment was not found in parent sequence.'
)
hit.best_start, hit.best_end = compute_true_location_locarna(hit, pos_match)
return hit
def get_cm_model(query_file, params=None, threads=None):
ml.debug(fname())
cmscan_data = get_cm_model_table(query_file, params, threads)
best_model_row = select_best_matching_model_from_cmscan(cmscan_data)
if best_model_row is None:
return None
best_model = best_model_row['target_name']
ml.info('Best matching model: {}'.format(best_model))
return best_model
def centroid_homfold_fast(all_seqs, query, all_seqs_fasta, n, centroid_homfold_params, len_diff):
ml.debug(fname())
selected_seqs = centroid_homfold_fast_prep(all_seqs, query, n, len_diff)
ch, homologous_file = mkstemp(prefix='rba_', suffix='_74', dir=CONFIG.tmpdir)
with os.fdopen(ch, 'w') as h:
SeqIO.write(selected_seqs, h, 'fasta')
structures, _ = me_centroid_homfold(all_seqs_fasta, homologous_file, params=centroid_homfold_params)
BA_support.remove_one_file_with_try(homologous_file)
return structures
def centroid_homfold_fast_prep(all_seqs, query, n, len_diff):
ml.debug(fname())
assert n >= 1, "Number of sequences for centroid-fast must be greater then 0."
if query.annotations['ambiguous']:
msgfail = "Query sequence contains ambiguous characters. Can't use centroid-fast."
ml.error(msgfail)
raise AmbiguousQuerySequenceException(msgfail)
nr_na_ld = BA_support.sel_seq_simple(all_seqs, query, len_diff)
nr_na_ld_n = nr_na_ld[:int(n)]
return nr_na_ld_n