def _score(self, alignment):
if self.use_seq_weights:
seq_weights = alignment.get_seq_weights()
else:
seq_weights = [1.0] * len(alignment.msa)
if self.bg_distribution is None:
# Estimate bg distribution from this alignment
q = weighted_freq_count_pseudocount((aa for seq in alignment.msa for aa in seq), seq_weights, PSEUDOCOUNT)
else:
q = self.bg_distribution
scores = []
for i in xrange(len(alignment.msa[0])):
col = get_column(i, alignment.msa)
n_gaps = col.count("-")
assert n_gaps < len(col)
if self.gap_cutoff != 1 and n_gaps / len(col) > self.gap_cutoff:
score = self.SCORE_OVER_GAP_CUTOFF
else:
score = self._score_col(col, seq_weights, q)
if self.use_gap_penalty:
# vn_entropy has this commented out for some reason
score *= weighted_gap_penalty(col, seq_weights)
scores.append(score)
return scores
def _score(self, alignment):
if self.use_seq_weights:
seq_weights = alignment.get_seq_weights()
else:
seq_weights = [1.] * len(alignment.msa)
# Estimate bg distribution from this alignment
if hasattr(self, 'bg_distribution'):
if not self.bg_distribution:
q = dict((aa, 0) for aa in amino_acids)
for seq in self.msa:
for aa in seq:
q[aa] += 1
self.bg_distribution = q
scores = []
for i in xrange(len(alignment.msa[0])):
col = get_column(i, alignment.msa)
n_gaps = col.count('-')
assert n_gaps < len(col)
if self.gap_cutoff != 1 and n_gaps/len(col) > self.gap_cutoff:
score = self.SCORE_OVER_GAP_CUTOFF
else:
score = self._score_col(col, seq_weights)
if self.use_gap_penalty:
# vn_entropy has this commented out for some reason
score *= weighted_gap_penalty(col, seq_weights)
scores.append(score)
return scores
def write_scores(alignment, scores_cols, scorer_names, f=sys.stdout, header=None):
"""
Write scores to `f` in human-readable format. Columns written are:
(position index, aa's in column, score by scorer 1, score by scorer 2, ...)
Note that score.py has been changed to only support scoring using 1 scorer, so only
3 columns are printed.
"""
# sanity check
if not len(scores_cols) == len(scorer_names):
raise ValueError("Mismatch between inputs 'scores_cols' and 'scorer_names'")
f.write("# Alignment: %s\n" % alignment.align_file)
f.write("# Num sites: %d\n" % len(alignment.msa[0]))
f.write("# Num sequences: %d\n" % len(alignment.names))
if alignment.filtered:
f.write("# Num sequences before filtering: %d\n" % alignment.orig_num_sequences)
f.write("\n")
if header:
# Check if header lines start with '#'?
f.write(header)
f.write("\n")
# print scores
f.write("# i\tcolumn\t%s\n" % "\t".join(scorer_names))
score_tups = zip(*scores_cols)
for i, score_tup in enumerate(score_tups):
site = "".join(get_column(i, alignment.msa))
f.write("%d\t%s\t%s\n" % (i+1, site, "\t".join(map(write_score_helper, score_tup))))
def _estimate_r(self, alignment, names_map, prior_distr):
tree = alignment.get_phylotree()
# Pre-compute the probabilities for every branch and rate.
# This can be done because the discrete gamma distribution tells us
# which rates P(rt) will be computed for when scoring columns.
P_cached = precompute_tree_probs(tree, prior_distr.get_rates(), self.sub_model)
# E-step
rates = []
rates_for_est = []
log_marginal = 0
for i in xrange(len(alignment.msa[0])):
col = get_column(i, alignment.msa)
n_gaps = col.count('-')
assert n_gaps < len(col)
if n_gaps == len(col) - 1:
# Return mean rate.
rate = 1
else:
rate, marginal = self._estimate_r_col(col, names_map, prior_distr, P_cached, tree)
rates_for_est.append(rate)
log_marginal += np.log(marginal)
rates.append(rate)
return rates, rates_for_est, log_marginal
def get_batchscores(dataset_name, batchscore_ids=[], align_files_only=False):
"""
Useful for evaluators.
Get an iterator on (alignment, scores_col) where scores_col consists
of lists of scores for each id in `batchscore_ids`. This iterator is over
all alignments in `dataset_name`.
"""
# Sanity check.
ds_dir = get_batchscore_dir(dataset_name)
if not os.path.exists(ds_dir):
raise IOError("%s for dataset %r does not exist"
% (ds_dir, dataset_name))
for batchscore_id in batchscore_ids:
sc_dir = os.path.join(ds_dir, batchscore_id)
if not os.path.exists(sc_dir):
raise IOError("%s for dataset %r, scorer %r does not exist"
% (sc_dir, dataset_name, batchscore_id))
dataset_config = DATASET_CONFIGS[dataset_name]
align_files = dataset_config.get_align_files()
# Be particular about which alignments we can evaluate.
afs = []
for align_file in align_files:
alignment = Alignment(align_file)
n_gapped_cols = 0
for i in xrange(len(alignment.msa[0])):
col = get_column(i, alignment.msa)
if col.count('-') > len(col) / 2:
n_gapped_cols += 1
if n_gapped_cols > len(alignment.msa[0]) / 2:
continue
include = True
for batchscore_id in batchscore_ids:
sc_dir = os.path.join(ds_dir, batchscore_id)
out_file = dataset_config.get_out_file(align_file, sc_dir)
if not os.path.exists(out_file):
include = False
break
if include:
afs.append(align_file)
print "Evaluating dataset %r: %d/%d scored alignments after minor filtering" \
% (dataset_name, len(afs), len(align_files))
if align_files_only:
for af in afs:
yield af
return
# Iterate through score files in dataset, per alignment.
for align_file in afs:
scores_cols = []
for batchscore_id in batchscore_ids:
sc_dir = os.path.join(ds_dir, batchscore_id)
out_file = dataset_config.get_out_file(align_file, sc_dir)
scores = read_batchscores(out_file)
scores_cols.append(scores)
alignment = Alignment(align_file,
test_file=dataset_config.get_test_file(align_file),
parse_testset_fn=dataset_config.parse_testset_fn)
yield alignment, scores_cols