def main(argv=sys.argv):
global OPTIONS
# so some option parsing
option_parser = setup_option_parser()
(OPTIONS, args) = option_parser.parse_args(argv)
# do some argument parsing
if OPTIONS.TEST:
run_tests()
return 0
if OPTIONS.RAND_SEED is not None:
seed(OPTIONS.RAND_SEED)
if len(args) != 2:
option_parser.error('ANTIBODY is a required argument')
# check to make sure our mode is exclusive, and set the default (AMINO) if none is set
if sum([1 for v in (OPTIONS.AMINO, OPTIONS.DNA, OPTIONS.STANFEL) if v]) > 1:
option_parser.error('options --amino, --dna, and --stanfel are mutually exclusive')
elif sum([1 for v in (OPTIONS.AMINO, OPTIONS.DNA, OPTIONS.STANFEL) if v]) == 0:
OPTIONS.AMINO = True
# validate the regression method
cvopts = {}
if OPTIONS.REGRESSOR_METHOD in regressor_classes:
cvopts['regressorcls'] = regressor_classes[OPTIONS.REGRESSOR_METHOD]
else:
option_parser.error('%s not in the list of available regression methods: \n %s' % (OPTIONS.REGRESSOR_METHOD,
'\n '.join(regressor_classes.keys())))
if search(r'(?:lar|lasso)$', OPTIONS.REGRESSOR_METHOD):
if OPTIONS.NUM_FEATURES < 0:
OPTIONS.NUM_FEATURES = _DEFAULT_NUM_FEATURES
cvopts['m'] = OPTIONS.NUM_FEATURES
elif OPTIONS.NUM_FEATURES > 0:
option_parser.error('--numfeats is a useless parameter for regression method `%s\'' % OPTIONS.REGRESSOR_METHOD)
cvopts['logspace'] = OPTIONS.LOGSPACE
# validate the antibody argument, currently a hack exists to make PG9/PG16 work
# TODO: Fix pg9/16 hax
antibody = args[1].strip()
valid_antibodies = sorted(OPTIONS.DATA.antibodies, key=lambda x: x.strip())
if antibody not in valid_antibodies:
if ' ' + antibody not in valid_antibodies:
option_parser.error('%s not in the list of permitted antibodies: \n %s' % (antibody, '\n '.join([ab.strip() for ab in valid_antibodies])))
else:
antibody = ' ' + antibody
# validate the subtype option
valid_subtypes = sorted(OPTIONS.DATA.subtypes, key=lambda x: x.strip().upper())
for subtype in OPTIONS.SUBTYPES:
if subtype not in valid_subtypes:
option_parser.error('%s not in the list of permitted subtypes: \n %s' % (subtype, '\n '.join([st.strip() for st in valid_subtypes])))
if len(OPTIONS.FILTER) != 0:
if OPTIONS.NUM_FEATURES != -1:
option_parser.error('--filter and --numfeats are incompatible options')
else:
OPTIONS.NUM_FEATURES = len(OPTIONS.FILTER)
else: # len(OPTIONS.FILTER) == 0
if OPTIONS.NUM_FEATURES == -1:
OPTIONS.NUM_FEATURES = _DEFAULT_NUM_FEATURES
# destroy the parser because optparse docs recommend it
option_parser.destroy()
# use the default DNA HXB2 Reference seq if we define --dna but don't give a new default HXB2 Reference seq
fix_hxb2_fasta()
# set the util params
set_util_params(OPTIONS.HXB2_IDS)
# fetch the alphabet, we'll probably need it later
alph = Alphabet(mode=Alphabet.STANFEL if OPTIONS.STANFEL else Alphabet.DNA if OPTIONS.DNA else Alphabet.AMINO)
ab_basename = ''.join((
antibody,
'_dna' if OPTIONS.DNA else '_amino',
'_clonal' if OPTIONS.CLONAL else ''
))
alignment_basename = '_'.join((
ab_basename,
OPTIONS.DATA.basename_root,
__VERSION__
))
# grab the relevant antibody from the SQLITE3 data
# format as SeqRecord so we can output as FASTA
# and generate an alignment using HMMER if it doesn't already exist
seqrecords, clonal = OPTIONS.DATA.seqrecords(antibody, OPTIONS.CLONAL, OPTIONS.DNA)
# if clonal isn't supported, fallback to default
if clonal != OPTIONS.CLONAL:
ab_basename = ''.join(ab_basename.rsplit('_clonal', 1))
alignment_basename = ''.join(alignment_basename.rsplit('_clonal', 1))
sto_filename = alignment_basename + '.sto'
alignment = generate_alignment(seqrecords, sto_filename, is_refidx, OPTIONS)[0]
ylabeler = Labeler(
seqrecord_get_values,
lambda seq: is_HXB2(seq) or False, # TODO: again filtration function
)
alignment, y, ic50gt = ylabeler(alignment)
filter = naivefilter(
OPTIONS.MAX_CONSERVATION,
OPTIONS.MIN_CONSERVATION,
OPTIONS.MAX_GAP_RATIO,
)
refidx = alignment_identify_ref(alignment, is_HXB2)
builder = DataBuilder(
alignment,
alph,
refidx,
filter
)
x = builder(alignment, refidx)
colnames = builder.labels
crossvalidator = CrossValidator(
classifier_cls=Regressor,
folds=OPTIONS.CV_FOLDS,
classifier_kwargs=cvopts,
scorer_cls=ContinuousPerfStats,
scorer_kwargs={}
)
results = crossvalidator.crossvalidate(x, y, classifier_kwargs={}, extra=extract_feature_weights)
ret = cv_results_to_output(results, colnames)
print(pretty_fmt_results(ret))
# mean_len = max([len('%.3f' % v.mu) for v in avg_stats.values()])
# std_len = max([len('%.3f' % v.sigma) for v in avg_stats.values()])
# std_len = int(log10(max([1.] + [v.sigma for v in avg_stats.values()]))) + 5
# for k, v in sorted(avg_stats.items(), key = lambda x: x[0][0]):
# v_str = u'= %*.3f \xb1 %*.3f' % (mean_len, v.mu, std_len, v.sigma)
# print(u' %s%s' % (k, v_str))
#
# for k, v in avg_weights.items():
# if abs(v.mu) < 0.0001 and v.sigma == 0.:
# del avg_weights[k]
#
# print('\nSignificant positions (top %d):' % (len(avg_weights)))
#
# if len(avg_weights) > 0:
# name_len = max(len(k) for k in avg_weights.keys())
# mean_len = max(len('% .1f' % v.mu) for v in avg_weights.values())
# std_len = max(len('%.1f' % v.sigma) for v in avg_weights.values())
# N_len = max(len('%d' % len(v.values)) for v in avg_weights.values())
# for k, v in sorted(avg_weights.items(), key=lambda x: int(sub(r'[a-zA-Z\[\]]+', '', x[0]))):
# print(u' %-*s % *.1f \xb1 %*.1f (N = %*d)' % (name_len, k, mean_len, v.mu, std_len, v.sigma, N_len, len(v.values)))
#
# print('\n')
return 0
def main(argv=sys.argv):
global OPTIONS
# so some option parsing
option_parser = setup_option_parser()
(OPTIONS, args) = option_parser.parse_args(argv)
# do some argument parsing
if OPTIONS.TEST:
run_tests()
return 0
if OPTIONS.RAND_SEED is not None:
seed(OPTIONS.RAND_SEED)
if len(args) != 2:
option_parser.error('ANTIBODY is a required argument')
# check to make sure our mode is exclusive, and set the default (AMINO) if none is set
if sum([1
for v in (OPTIONS.AMINO, OPTIONS.DNA, OPTIONS.STANFEL) if v]) > 1:
option_parser.error(
'options --amino, --dna, and --stanfel are mutually exclusive')
elif sum([1 for v in (OPTIONS.AMINO, OPTIONS.DNA, OPTIONS.STANFEL)
if v]) == 0:
OPTIONS.AMINO = True
# validate the regression method
cvopts = {}
if OPTIONS.REGRESSOR_METHOD in regressor_classes:
cvopts['regressorcls'] = regressor_classes[OPTIONS.REGRESSOR_METHOD]
else:
option_parser.error(
'%s not in the list of available regression methods: \n %s' %
(OPTIONS.REGRESSOR_METHOD, '\n '.join(regressor_classes.keys())))
if search(r'(?:lar|lasso)$', OPTIONS.REGRESSOR_METHOD):
if OPTIONS.NUM_FEATURES < 0:
OPTIONS.NUM_FEATURES = _DEFAULT_NUM_FEATURES
cvopts['m'] = OPTIONS.NUM_FEATURES
elif OPTIONS.NUM_FEATURES > 0:
option_parser.error(
'--numfeats is a useless parameter for regression method `%s\'' %
OPTIONS.REGRESSOR_METHOD)
cvopts['logspace'] = OPTIONS.LOGSPACE
# validate the antibody argument, currently a hack exists to make PG9/PG16 work
# TODO: Fix pg9/16 hax
antibody = args[1].strip()
valid_antibodies = sorted(OPTIONS.DATA.antibodies, key=lambda x: x.strip())
if antibody not in valid_antibodies:
if ' ' + antibody not in valid_antibodies:
option_parser.error(
'%s not in the list of permitted antibodies: \n %s' %
(antibody, '\n '.join([ab.strip()
for ab in valid_antibodies])))
else:
antibody = ' ' + antibody
# validate the subtype option
valid_subtypes = sorted(OPTIONS.DATA.subtypes,
key=lambda x: x.strip().upper())
for subtype in OPTIONS.SUBTYPES:
if subtype not in valid_subtypes:
option_parser.error(
'%s not in the list of permitted subtypes: \n %s' %
(subtype, '\n '.join([st.strip() for st in valid_subtypes])))
if len(OPTIONS.FILTER) != 0:
if OPTIONS.NUM_FEATURES != -1:
option_parser.error(
'--filter and --numfeats are incompatible options')
else:
OPTIONS.NUM_FEATURES = len(OPTIONS.FILTER)
else: # len(OPTIONS.FILTER) == 0
if OPTIONS.NUM_FEATURES == -1:
OPTIONS.NUM_FEATURES = _DEFAULT_NUM_FEATURES
# destroy the parser because optparse docs recommend it
option_parser.destroy()
# use the default DNA HXB2 Reference seq if we define --dna but don't give a new default HXB2 Reference seq
fix_hxb2_fasta()
# set the util params
set_util_params(OPTIONS.HXB2_IDS)
# fetch the alphabet, we'll probably need it later
alph = Alphabet(mode=Alphabet.STANFEL if OPTIONS.STANFEL else Alphabet.
DNA if OPTIONS.DNA else Alphabet.AMINO)
ab_basename = ''.join((antibody, '_dna' if OPTIONS.DNA else '_amino',
'_clonal' if OPTIONS.CLONAL else ''))
alignment_basename = '_'.join(
(ab_basename, OPTIONS.DATA.basename_root, __VERSION__))
# grab the relevant antibody from the SQLITE3 data
# format as SeqRecord so we can output as FASTA
# and generate an alignment using HMMER if it doesn't already exist
seqrecords, clonal = OPTIONS.DATA.seqrecords(antibody, OPTIONS.CLONAL,
OPTIONS.DNA)
# if clonal isn't supported, fallback to default
if clonal != OPTIONS.CLONAL:
ab_basename = ''.join(ab_basename.rsplit('_clonal', 1))
alignment_basename = ''.join(alignment_basename.rsplit('_clonal', 1))
sto_filename = alignment_basename + '.sto'
alignment = generate_alignment(seqrecords, sto_filename, is_refidx,
OPTIONS)[0]
ylabeler = Labeler(
seqrecord_get_values,
lambda seq: is_HXB2(seq) or False, # TODO: again filtration function
)
alignment, y, ic50gt = ylabeler(alignment)
filter = naivefilter(
OPTIONS.MAX_CONSERVATION,
OPTIONS.MIN_CONSERVATION,
OPTIONS.MAX_GAP_RATIO,
)
refidx = alignment_identify_ref(alignment, is_HXB2)
builder = DataBuilder(alignment, alph, refidx, filter)
x = builder(alignment, refidx)
colnames = builder.labels
crossvalidator = CrossValidator(classifier_cls=Regressor,
folds=OPTIONS.CV_FOLDS,
classifier_kwargs=cvopts,
scorer_cls=ContinuousPerfStats,
scorer_kwargs={})
results = crossvalidator.crossvalidate(x,
y,
classifier_kwargs={},
extra=extract_feature_weights)
ret = cv_results_to_output(results, colnames)
print(pretty_fmt_results(ret))
# mean_len = max([len('%.3f' % v.mu) for v in avg_stats.values()])
# std_len = max([len('%.3f' % v.sigma) for v in avg_stats.values()])
# std_len = int(log10(max([1.] + [v.sigma for v in avg_stats.values()]))) + 5
# for k, v in sorted(avg_stats.items(), key = lambda x: x[0][0]):
# v_str = u'= %*.3f \xb1 %*.3f' % (mean_len, v.mu, std_len, v.sigma)
# print(u' %s%s' % (k, v_str))
#
# for k, v in avg_weights.items():
# if abs(v.mu) < 0.0001 and v.sigma == 0.:
# del avg_weights[k]
#
# print('\nSignificant positions (top %d):' % (len(avg_weights)))
#
# if len(avg_weights) > 0:
# name_len = max(len(k) for k in avg_weights.keys())
# mean_len = max(len('% .1f' % v.mu) for v in avg_weights.values())
# std_len = max(len('%.1f' % v.sigma) for v in avg_weights.values())
# N_len = max(len('%d' % len(v.values)) for v in avg_weights.values())
# for k, v in sorted(avg_weights.items(), key=lambda x: int(sub(r'[a-zA-Z\[\]]+', '', x[0]))):
# print(u' %-*s % *.1f \xb1 %*.1f (N = %*d)' % (name_len, k, mean_len, v.mu, std_len, v.sigma, N_len, len(v.values)))
#
# print('\n')
return 0
def run_tests():
# set these to this so we don't exclude anything (just testing file generation and parsing)
OPTIONS.NUM_FEATURES = 15 # should be enough, the number is known to be 13
OPTIONS.MAXREL = False
OPTIONS.DNA = False
OPTIONS.MAX_CONSERVATION = 1.0
OPTIONS.MAX_GAP_RATIO = 1.0
OPTIONS.MIN_CONSERVATION = 1.0
# if we don't do this, DOOMBUNNIES
set_util_params(OPTIONS.HXB2_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 OPTIONS.STANFEL in (True, False):
if OPTIONS.STANFEL:
OPTIONS.AMINO = False
_TEST_NAMES = _TEST_STANFEL_NAMES
_TEST_X = _TEST_STANFEL_X
else:
OPTIONS.AMINO = True
_TEST_NAMES = _TEST_AMINO_NAMES
_TEST_X = _TEST_AMINO_X
alph = Alphabet(Alphabet.STANFEL if OPTIONS.STANFEL else Alphabet.DNA if OPTIONS.DNA else Alphabet.AMINO)
# test mRMR and LSVM file generation
ylabeler = Labeler(
seqrecord_get_values,
lambda seq: is_HXB2(seq) or False, # TODO: again filtration function
)
alignment, y, ic50gt = ylabeler(alignment)
filter = naivefilter(
OPTIONS.MAX_CONSERVATION,
OPTIONS.MIN_CONSERVATION,
OPTIONS.MAX_GAP_RATIO
)
refidx = alignment_identify_ref(alignment, is_HXB2)
builder = DataBuilder(
alignment,
alph,
refidx,
filter
)
x = builder(alignment, refidx)
colnames = builder.labels
# 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))
# TODO: generate and test the regressor data generation
# print y, "\n", x
finally:
remove(sto_filename)
print('ALL TESTS PASS', file=sys.stderr)
def run_tests():
# set these to this so we don't exclude anything (just testing file generation and parsing)
OPTIONS.NUM_FEATURES = 15 # should be enough, the number is known to be 13
OPTIONS.MAXREL = False
OPTIONS.DNA = False
OPTIONS.MAX_CONSERVATION = 1.0
OPTIONS.MAX_GAP_RATIO = 1.0
OPTIONS.MIN_CONSERVATION = 1.0
# if we don't do this, DOOMBUNNIES
set_util_params(OPTIONS.HXB2_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 OPTIONS.STANFEL in (True, False):
if OPTIONS.STANFEL:
OPTIONS.AMINO = False
_TEST_NAMES = _TEST_STANFEL_NAMES
_TEST_X = _TEST_STANFEL_X
else:
OPTIONS.AMINO = True
_TEST_NAMES = _TEST_AMINO_NAMES
_TEST_X = _TEST_AMINO_X
alph = Alphabet(Alphabet.STANFEL if OPTIONS.STANFEL else Alphabet.
DNA if OPTIONS.DNA else Alphabet.AMINO)
# test mRMR and LSVM file generation
ylabeler = Labeler(
seqrecord_get_values,
lambda seq: is_HXB2(seq) or
False, # TODO: again filtration function
)
alignment, y, ic50gt = ylabeler(alignment)
filter = naivefilter(OPTIONS.MAX_CONSERVATION,
OPTIONS.MIN_CONSERVATION,
OPTIONS.MAX_GAP_RATIO)
refidx = alignment_identify_ref(alignment, is_HXB2)
builder = DataBuilder(alignment, alph, refidx, filter)
x = builder(alignment, refidx)
colnames = builder.labels
# 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))
# TODO: generate and test the regressor data generation
# print y, "\n", x
finally:
remove(sto_filename)
print('ALL TESTS PASS', file=sys.stderr)
