def generate_alignment(seqrecords, sto_filename, ref_id_func, opts, load=True):
from ..simulation import Simulation
log = getLogger(IDEPI_LOGGER)
hmm = None
if hasattr(opts, 'SIM') and opts.SIM == Simulation.DUMB:
# we're assuming pre-aligned because they're all generated from the same refseq
with open(sto_filename, 'w') as fh:
SeqIO.write(seqrecords, fh, 'stockholm')
else:
try:
tmphmm = generate_hmm_(opts)
tmpaln = generate_alignment_(seqrecords, tmphmm, opts, refseq=opts.REFSEQ)
copyfile(tmpaln, sto_filename)
log.debug('finished alignment, output moved to {0:s}'.format(sto_filename))
with open(tmphmm, 'rb') as hmm_fh:
hmm = hmm_fh.read()
finally:
if exists(tmphmm):
remove(tmphmm)
if exists(tmpaln):
remove(tmpaln)
if load:
with open(sto_filename) as fh:
msa = AlignIO.read(fh, 'stockholm')
refidx = reference_index(msa, ref_id_func)
msa = LabeledMSA.from_msa_with_ref(msa, refidx)
ranges = stockholm_rf_ranges(sto_filename)
return trim_msa_to_ranges(msa, ranges), hmm
return None, hmm
def generate_alignment(seqrecords, sto_filename, ref_id_func, opts, load=True):
from ..simulation import Simulation
log = getLogger(IDEPI_LOGGER)
hmm = None
if hasattr(opts, 'SIM') and opts.SIM == Simulation.DUMB:
# we're assuming pre-aligned because they're all generated from the same refseq
with open(sto_filename, 'w') as fh:
SeqIO.write(seqrecords, fh, 'stockholm')
else:
try:
tmphmm = generate_hmm_(opts)
tmpaln = generate_alignment_(seqrecords,
tmphmm,
opts,
refseq=opts.REFSEQ)
copyfile(tmpaln, sto_filename)
log.debug('finished alignment, output moved to {0:s}'.format(
sto_filename))
with open(tmphmm, 'rb') as hmm_fh:
hmm = hmm_fh.read()
finally:
if exists(tmphmm):
remove(tmphmm)
if exists(tmpaln):
remove(tmpaln)
if load:
with open(sto_filename) as fh:
msa = AlignIO.read(fh, 'stockholm')
refidx = reference_index(msa, ref_id_func)
msa = LabeledMSA.from_msa_with_ref(msa, refidx)
ranges = stockholm_rf_ranges(sto_filename)
return trim_msa_to_ranges(msa, ranges), hmm
return None, hmm
def test_discrete(ARGS):
# set these to this so we don't exclude anything (just testing file generation and parsing)
ARGS.NUM_FEATURES = 15 # should be enough, the number is known to be 13
ARGS.MRMR_METHOD = 'MID'
ARGS.MAX_CONSERVATION = 1.0
ARGS.MAX_GAP_RATIO = 1.0
ARGS.MIN_CONSERVATION = 1.0
ARGS.CUTOFF = 20.
# if we don't do this, DOOMBUNNIES
set_util_params(ARGS.REFSEQ_IDS)
fd, sto_filename = mkstemp(); close(fd)
try:
fh = open(sto_filename, 'w')
print(TEST_AMINO_STO, file=fh)
fh.close()
alignment = AlignIO.read(sto_filename, 'stockholm')
for ARGS.ENCODER in (AminoEncoder, StanfelEncoder):
if ARGS.ENCODER == StanfelEncoder:
TEST_NAMES = TEST_STANFEL_NAMES
TEST_X = TEST_STANFEL_X
else:
TEST_NAMES = TEST_AMINO_NAMES
TEST_X = TEST_AMINO_X
# test mRMR and LSVM file generation
ylabeler = Labeler(
seqrecord_get_values,
lambda row: is_refseq(row) or False, # TODO: again filtration function
lambda x: x > ARGS.CUTOFF,
False
)
alignment, y, ic50 = ylabeler(alignment)
refidx = reference_index(alignment, is_refseq)
alignment = LabeledMSA.from_msa_with_ref(alignment, refidx)
extractor = SiteVectorizer(ARGS.ENCODER)
x = extractor.fit_transform(alignment)
colnames = extractor.get_feature_names()
# test the feature names portion
try:
assert(len(colnames) == len(TEST_NAMES))
except AssertionError:
raise AssertionError('gen: %s\ntruth: %s' % (colnames, TEST_NAMES))
for name in TEST_NAMES:
try:
assert(name in colnames)
except AssertionError:
raise AssertionError('ERROR: \'%s\' not found in %s' % (name, ', '.join(colnames)))
assert(np.all(TEST_X == x))
assert(np.all(TEST_Y == y))
# generate and test the mRMR portion
mrmr = MRMR(
estimator=SVC(kernel='linear'),
n_features_to_select=ARGS.NUM_FEATURES,
method=ARGS.MRMR_METHOD,
normalize=ARGS.MRMR_NORMALIZE,
similar=ARGS.SIMILAR
)
mrmr.fit(x, y)
finally:
remove(sto_filename)
print('ALL TESTS PASS', file=sys.stderr)
def test_discrete(ARGS):
# set these to this so we don't exclude anything (just testing file generation and parsing)
ARGS.NUM_FEATURES = 15 # should be enough, the number is known to be 13
ARGS.MRMR_METHOD = 'MID'
ARGS.MAX_CONSERVATION = 1.0
ARGS.MAX_GAP_RATIO = 1.0
ARGS.MIN_CONSERVATION = 1.0
ARGS.CUTOFF = 20.
# if we don't do this, DOOMBUNNIES
set_util_params(ARGS.REFSEQ_IDS)
fd, sto_filename = mkstemp(); close(fd)
try:
fh = open(sto_filename, 'w')
print(TEST_AMINO_STO, file=fh)
fh.close()
alignment = AlignIO.read(sto_filename, 'stockholm')
for ARGS.ENCODER in (AminoEncoder, StanfelEncoder):
if ARGS.ENCODER == StanfelEncoder:
TEST_NAMES = TEST_STANFEL_NAMES
TEST_X = TEST_STANFEL_X
else:
TEST_NAMES = TEST_AMINO_NAMES
TEST_X = TEST_AMINO_X
# test mRMR and LSVM file generation
ylabeler = Labeler(
seqrecord_get_values,
lambda row: is_refseq(row) or False, # TODO: again filtration function
lambda x: x > ARGS.CUTOFF,
False
)
alignment, y, ic50 = ylabeler(alignment)
refidx = reference_index(alignment, is_refseq)
alignment = LabeledMSA.from_msa_with_ref(alignment, refidx)
extractor = MSAVectorizer(ARGS.ENCODER)
x = extractor.fit_transform(alignment)
colnames = extractor.get_feature_names()
# test the feature names portion
try:
assert(len(colnames) == len(TEST_NAMES))
except AssertionError:
raise AssertionError('gen: %s\ntruth: %s' % (colnames, TEST_NAMES))
for name in TEST_NAMES:
try:
assert(name in colnames)
except AssertionError:
raise AssertionError('ERROR: \'%s\' not found in %s' % (name, ', '.join(colnames)))
assert(np.all(TEST_X == x))
assert(np.all(TEST_Y == y))
# generate and test the mRMR portion
mrmr = MRMR(
estimator=SVC(kernel='linear'),
n_features_to_select=ARGS.NUM_FEATURES,
method=ARGS.MRMR_METHOD,
normalize=ARGS.MRMR_NORMALIZE,
similar=ARGS.SIMILAR
)
mrmr.fit(x, y)
finally:
remove(sto_filename)
print('ALL TESTS PASS', file=sys.stderr)
