def write(self, outfile, twoheaders=False): name = str_to_bytes(self.name) if self.qualities is not None: s = b'@' + name + b'\n' + self.sequence + b'\n+' if twoheaders: s += name s += b'\n' + self.qualities + b'\n' else: s = b'>' + name + b'\n' + self.sequence + b'\n' if PY3: outfile.buffer.write(s) else: outfile.write(s)
def write(self, outfile, twoheaders=False): name = str_to_bytes(self.name) if self.qualities is not None: s = b'@' + name + b'\n' + self.sequence + b'\n+' if twoheaders: s += name s += b'\n' + self.qualities + b'\n' else: s = b'>' + name + b'\n' + self.sequence + b'\n' if PY3: outfile.buffer.write(s) else: outfile.write(s)
def __init__(self,
sequence,
where,
max_error_rate,
min_overlap=3,
match_read_wildcards=False,
match_adapter_wildcards=False,
name=None,
indels=True):
if name is None:
self.name = str(self.__class__.automatic_name)
self.__class__.automatic_name += 1
self.name_is_generated = True
else:
self.name = name
self.name_is_generated = False
if isinstance(sequence, str) and PY3:
self.sequence = str_to_bytes(sequence).upper()
else:
self.sequence = sequence.upper()
self.where = where
self.max_error_rate = max_error_rate
self.min_overlap = min_overlap
self.indels = indels
assert where != FRONT or self.indels
self.wildcard_flags = 0
self.match_adapter_wildcards = match_adapter_wildcards and b'N' in self.sequence
if match_read_wildcards:
self.wildcard_flags |= align.ALLOW_WILDCARD_SEQ2
if self.match_adapter_wildcards:
self.wildcard_flags |= align.ALLOW_WILDCARD_SEQ1
# redirect to appropriate trimmed() function depending on
# adapter type
trimmers = {
FRONT: self._trimmed_front,
PREFIX: self._trimmed_front,
BACK: self._trimmed_back,
ANYWHERE: self._trimmed_anywhere
}
self.trimmed = trimmers[where]
if where == ANYWHERE:
self._front_flag = None # means: guess
else:
self._front_flag = where != BACK
# statistics about length of removed sequences
self.lengths_front = defaultdict(int)
self.lengths_back = defaultdict(int)
self.errors_front = defaultdict(lambda: defaultdict(int))
self.errors_back = defaultdict(lambda: defaultdict(int))
def __init__(self, sequence, where, max_error_rate, min_overlap=3,
match_read_wildcards=False, match_adapter_wildcards=False,
name=None, indels=True):
if name is None:
self.name = str(self.__class__.automatic_name)
self.__class__.automatic_name += 1
self.name_is_generated = True
else:
self.name = name
self.name_is_generated = False
if isinstance(sequence, str) and PY3:
self.sequence = str_to_bytes(sequence).upper()
else:
self.sequence = sequence.upper()
self.sequence = self.sequence.replace(b'U', b'T')
self.where = where
self.max_error_rate = max_error_rate
self.min_overlap = min_overlap
self.indels = indels
assert where != FRONT or self.indels
self.wildcard_flags = 0
self.match_adapter_wildcards = match_adapter_wildcards and b'N' in self.sequence
if match_read_wildcards:
self.wildcard_flags |= align.ALLOW_WILDCARD_SEQ2
if self.match_adapter_wildcards:
self.wildcard_flags |= align.ALLOW_WILDCARD_SEQ1
# redirect to appropriate trimmed() function depending on
# adapter type
trimmers = {
FRONT: self._trimmed_front,
PREFIX: self._trimmed_front,
BACK: self._trimmed_back,
ANYWHERE: self._trimmed_anywhere
}
self.trimmed = trimmers[where]
if where == ANYWHERE:
self._front_flag = None # means: guess
else:
self._front_flag = where != BACK
# statistics about length of removed sequences
self.lengths_front = defaultdict(int)
self.lengths_back = defaultdict(int)
self.errors_front = defaultdict(lambda: defaultdict(int))
self.errors_back = defaultdict(lambda: defaultdict(int))
