def prefix_filter_flowgrams(flowgrams, squeeze=False):
"""Filters flowgrams by common prefixes.
flowgrams: iterable source of flowgrams
squeeze: if True, collapse all poly-X to X
Returns prefix mapping.
"""
# collect flowgram sequences
if squeeze:
seqs = imap(
lambda f: (f.Name, squeeze_seq(str(f.toSeq(truncate=True)))),
flowgrams)
else:
seqs = imap(lambda f: (f.Name, str(f.toSeq(truncate=True))), flowgrams)
# equivalent but more efficient than
#seqs = [(f.Name, str(f.toSeq(truncate=True))) for f in flowgrams]
# get prefix mappings
mapping = build_prefix_map(seqs)
l = len(mapping)
orig_l = sum([len(a) for a in mapping.values()]) + l
return (l, orig_l, mapping)
def prefix_filter_flowgrams(flowgrams, squeeze=False):
"""Filters flowgrams by common prefixes.
flowgrams: iterable source of flowgrams
squeeze: if True, collapse all poly-X to X
Returns prefix mapping.
"""
#collect flowgram sequences
if squeeze:
seqs = imap(lambda f: (f.Name, squeeze_seq(str(f.toSeq(truncate=True)))),
flowgrams)
else:
seqs = imap(lambda f: (f.Name, str(f.toSeq(truncate=True))), flowgrams)
#equivalent but more efficient than
#seqs = [(f.Name, str(f.toSeq(truncate=True))) for f in flowgrams]
#get prefix mappings
mapping = build_prefix_map(seqs)
l = len(mapping)
orig_l=sum([len(a) for a in mapping.values()]) +l;
return (l, orig_l, mapping)
def __call__(self, seq_path, result_path=None, log_path=None):
"""Returns dict mapping {otu_id:[seq_ids]} for each otu.
Parameters:
seq_path: path to file of sequences
result_path: path to file of results. If specified,
dumps the result to the desired path instead of returning it.
log_path: path to log, which includes dump of params.
"""
log_lines = []
# Get the appropriate sequence iterator
if self.Params['Reverse']:
# Reverse the sequences prior to building the prefix map.
# This effectively creates a suffix map.
# Also removes descriptions from seq identifier lines
seqs = imap(lambda s: (s[0].split()[0], s[1][::-1]),\
MinimalFastaParser(open(seq_path)))
log_lines.append(\
'Seqs reversed for suffix mapping (rather than prefix mapping).')
else:
# remove descriptions from seq identifier lines
seqs = imap(lambda s: (s[0].split()[0], s[1]),\
MinimalFastaParser(open(seq_path)))
# Build the mapping
mapping = build_prefix_map(seqs)
log_lines.append('Num OTUs: %d' % len(mapping))
if result_path:
# if the user provided a result_path, write the
# results to file with one tab-separated line per
# cluster
of = open(result_path, 'w')
for i, (otu_id, members) in enumerate(mapping.iteritems()):
of.write('%s\t%s\n' % (i, '\t'.join([otu_id] + members)))
of.close()
result = None
log_lines.append('Result path: %s' % result_path)
else:
# if the user did not provide a result_path, store
# the clusters in a dict of {otu_id:[seq_ids]}, where
# otu_id is arbitrary
#add key to cluster_members
for key in mapping.keys():
mapping[key].append(key)
result = dict(enumerate(mapping.values()))
log_lines.append('Result path: None, returned as dict.')
if log_path:
# if the user provided a log file path, log the run
log_file = open(log_path, 'w')
log_lines = [str(self)] + log_lines
log_file.write('\n'.join(log_lines))
# return the result (note this is None if the data was
# written to file)
return result
def __call__(self, seq_path, result_path=None, log_path=None):
"""Returns dict mapping {otu_id:[seq_ids]} for each otu.
Parameters:
seq_path: path to file of sequences
result_path: path to file of results. If specified,
dumps the result to the desired path instead of returning it.
log_path: path to log, which includes dump of params.
"""
log_lines = []
# Get the appropriate sequence iterator
if self.Params["Reverse"]:
# Reverse the sequences prior to building the prefix map.
# This effectively creates a suffix map.
# Also removes descriptions from seq identifier lines
seqs = imap(lambda s: (s[0].split()[0], s[1][::-1]), MinimalFastaParser(open(seq_path)))
log_lines.append("Seqs reversed for suffix mapping (rather than prefix mapping).")
else:
# remove descriptions from seq identifier lines
seqs = imap(lambda s: (s[0].split()[0], s[1]), MinimalFastaParser(open(seq_path)))
# Build the mapping
mapping = build_prefix_map(seqs)
log_lines.append("Num OTUs: %d" % len(mapping))
if result_path:
# if the user provided a result_path, write the
# results to file with one tab-separated line per
# cluster
of = open(result_path, "w")
for i, (otu_id, members) in enumerate(mapping.iteritems()):
of.write("%s\t%s\n" % (i, "\t".join([otu_id] + members)))
of.close()
result = None
log_lines.append("Result path: %s" % result_path)
else:
# if the user did not provide a result_path, store
# the clusters in a dict of {otu_id:[seq_ids]}, where
# otu_id is arbitrary
# add key to cluster_members
for key in mapping.keys():
mapping[key].append(key)
result = dict(enumerate(mapping.values()))
log_lines.append("Result path: None, returned as dict.")
if log_path:
# if the user provided a log file path, log the run
log_file = open(log_path, "w")
log_lines = [str(self)] + log_lines
log_file.write("\n".join(log_lines))
# return the result (note this is None if the data was
# written to file)
return result
def _prefilter_with_trie(self, seq_path):
trunc_id = lambda (a, b): (a.split()[0], b)
# get the prefix map
mapping = build_prefix_map(imap(trunc_id, MinimalFastaParser(open(seq_path))))
for key in mapping.keys():
mapping[key].append(key)
# collect the representative seqs
filtered_seqs = []
for (label, seq) in MinimalFastaParser(open(seq_path)):
label = label.split()[0]
if label in mapping:
filtered_seqs.append((label, seq))
return filtered_seqs, mapping
def _prefilter_with_trie(self, seq_path):
trunc_id = lambda (a, b): (a.split()[0], b)
# get the prefix map
mapping = build_prefix_map(
imap(trunc_id, MinimalFastaParser(open(seq_path))))
for key in mapping.keys():
mapping[key].append(key)
# collect the representative seqs
filtered_seqs = []
for (label, seq) in MinimalFastaParser(open(seq_path)):
label = label.split()[0]
if label in mapping:
filtered_seqs.append((label, seq))
return filtered_seqs, mapping
