def __init__(
self,
seq,
id=UNKNOWN_ID,
name=UNKNOWN_NAME,
description=UNKNOWN_DESCRIPTION,
dbxrefs=None,
features=None,
annotations=None,
letter_annotations=None,
qual=None,
):
if id == UNKNOWN_ID and name != UNKNOWN_NAME:
id = name
# We don't want a Biopython Seq, we need our repr
if not isinstance(seq, Seq) and not isinstance(seq, UnknownSeq):
raise ValueError("seq should be a franklin Seq")
SeqRecord.__init__(
self,
seq,
id=id,
name=name,
description=description,
dbxrefs=dbxrefs,
features=features,
annotations=annotations,
letter_annotations=letter_annotations,
)
if qual is not None:
self.qual = qual
def _init_with_SeqRecord(self,record):
# Initialize self using existing SeqRecord object
SeqRecord.__init__(self, seq=record.seq, id=record.id,
name=record.name, description=record.description,
dbxrefs=record.dbxrefs, features=record.features,
annotations=record.annotations,
letter_annotations=record.letter_annotations)
def __init__(self, seq, id="<unknown id>", name="<unknown name>", description="<unknown description>",
dbxrefs=None, features=None, annotations=None, letter_annotations=None):
self.id = id
self.tempseq = seq
temp = self.id.split('|')
self.GeneID = temp[0]
self.TranscriptID = temp[1]
self.GeneName = temp[2]
self.ExonRank = temp[3]
if temp[4] == '': self.ConstExon = False
else: self.ConstExon = True
try: self.FPUTRend = int(temp[5])
except: self.FPUTRend = ''
try: self.TPUTRstart = int(temp[6])
except: self.TPUTRstart = ''
try: self.exonStart = int(temp[7])
except: self.exonStart = ''
try: self.exonEnd = int(temp[8])
except: self.exonEnd = ''
if self.FPUTRend != '':
sequence = str(self.tempseq)[(self.FPUTRend-self.exonStart):(self.exonEnd-self.exonStart)]
elif self.TPUTRstart != '':
sequence = str(self.tempseq)[0:(self.TPUTRstart-self.exonStart)]
else:
sequence = str(self.tempseq)
SeqRecord.__init__(self, Seq(sequence, IUPAC.unambiguous_dna), id, name, description, dbxrefs=None,
features=None, annotations=None, letter_annotations=None)
def __init__(self, seq, seq_id, **kwargs):
SeqRecord.__init__(self, seq=seq, id=seq_id)
try:
self.frame = find_frame(seq)
except ValueError:
self.frame = None
self.frequency = None
self.mutations = []
for k, v in list(kwargs.items()):
self.__dict__[k] = v
def __init__(self, readSeq, readID, qualStr, R='R1'):
SeqRecord.__init__(self, readSeq, readID)
self.qualStr = qualStr
self.R = R
if self.R == 'R2':
self.seq = self.seq.reverse_complement()
self.sim_fastq_entry()
def _init_with_SeqRecord(self,record):
# Check if record has phred_quality letter annotations and convert to
# ASCII string
if 'phred_quality' in record.letter_annotations and isinstance(record.letter_annotations['phred_quality'], types.ListType):
qual = ''.join([chr(q+33) for q in record.letter_annotations['phred_quality']])
record.letter_annotations['phred_quality'] = qual
# Initialize self using existing SeqRecord object
SeqRecord.__init__(self, seq=record.seq, id=record.id,
name=record.name, description=record.description,
dbxrefs=record.dbxrefs, features=record.features,
annotations=record.annotations,
letter_annotations=record.letter_annotations)
def __init__(self, seq_record, cut_site, **kwargs):
"""
__init__ requires a string representation of the recognition
sequence, `seq_str`, and the one-based index of the last base
before the cut site `cut_site`.
E.g., NotI:
5'---GC GGCCGC---3'
3'---CGCCGG CG---5'
noti = RecognitionSeq('GCGGCCGC', 2)
E.g., EcoRV:
5'---GAT ATC---3'
3'---CTA TAG---5'
ecorv = RecognitionSeq('GATATC', 3)
"""
if isinstance(seq_record, SeqRecord):
SeqRecord.__init__(
self,
seq=seq_record.seq,
id=seq_record.id,
name=seq_record.name,
description=seq_record.description,
letter_annotations=seq_record.letter_annotations,
annotations=seq_record.annotations,
features=seq_record.features,
dbxrefs=seq_record.dbxrefs)
else:
SeqRecord.__init__(self,
seq=Seq(str(seq_record).upper(),
alphabet=IUPAC.unambiguous_dna),
id=kwargs.get('id', '<unknown id>'),
name=kwargs.get('name', '<unknown name>'),
description=kwargs.get('description',
'<unknown description>'),
letter_annotations=kwargs.get(
'letter_annotations', None),
annotations=kwargs.get('annotations', None),
features=kwargs.get('features', None),
dbxrefs=kwargs.get('dbxrefs', None))
for base in str(self.seq):
if base.upper() not in ['A', 'C', 'G', 'T']:
raise InvalidRecognitionSeqError(
"Invalid base {0!r}:\n\t".format(base.upper()) +
"RecognitionSeq only supports unambiguous DNA")
self.cut_site = int(cut_site)
if self.cut_site < 0 or self.cut_site > len(self):
raise InvalidRecognitionSeqError(
"Invalid cut_site {0} for recognition sequence {1}".format(
self.cut_site, str(self.seq)))
self.overhang = len(self) - (2 * self.cut_site)
def __init__(self, seq_record, cut_site, **kwargs):
"""
__init__ requires a string representation of the recognition
sequence, `seq_str`, and the one-based index of the last base
before the cut site `cut_site`.
E.g., NotI:
5'---GC GGCCGC---3'
3'---CGCCGG CG---5'
noti = RecognitionSeq('GCGGCCGC', 2)
E.g., EcoRV:
5'---GAT ATC---3'
3'---CTA TAG---5'
ecorv = RecognitionSeq('GATATC', 3)
"""
if isinstance(seq_record, SeqRecord):
SeqRecord.__init__(self,
seq = seq_record.seq,
id = seq_record.id,
name = seq_record.name,
description = seq_record.description,
letter_annotations = seq_record.letter_annotations,
annotations = seq_record.annotations,
features = seq_record.features,
dbxrefs = seq_record.dbxrefs)
else:
SeqRecord.__init__(self,
seq = Seq(str(seq_record).upper(),
alphabet=IUPAC.unambiguous_dna),
id = kwargs.get('id', '<unknown id>'),
name = kwargs.get('name', '<unknown name>'),
description = kwargs.get('description',
'<unknown description>'),
letter_annotations = kwargs.get('letter_annotations',
None),
annotations = kwargs.get('annotations', None),
features = kwargs.get('features', None),
dbxrefs = kwargs.get('dbxrefs', None))
for base in str(self.seq):
if base.upper() not in ['A', 'C', 'G', 'T']:
raise InvalidRecognitionSeqError(
"Invalid base {0!r}:\n\t".format(base.upper()) +
"RecognitionSeq only supports unambiguous DNA")
self.cut_site = int(cut_site)
if self.cut_site < 0 or self.cut_site > len(self):
raise InvalidRecognitionSeqError(
"Invalid cut_site {0} for recognition sequence {1}".format(
self.cut_site, str(self.seq)))
self.overhang = len(self) - (2*self.cut_site)
def __init__(self,
seq_record,
start_site,
end_site,
overhang,
five_prime_terminus=False,
three_prime_terminus=False,
**kwargs):
if start_site > end_site:
raise InvalidFragmentError(
"A Fragment's start position ({0}) cannot be greater than "
"its end position ({1})".format(start_site, end_site))
if isinstance(seq_record, SeqRecord):
SeqRecord.__init__(
self,
seq=seq_record.seq,
id=seq_record.id,
name=seq_record.name,
description=seq_record.description,
letter_annotations=seq_record.letter_annotations,
annotations=seq_record.annotations,
features=seq_record.features,
dbxrefs=seq_record.dbxrefs)
else:
SeqRecord.__init__(self,
seq=Seq(str(seq_record).upper(),
alphabet=IUPAC.ambiguous_dna),
id=kwargs.get('id', '<unknown id>'),
name=kwargs.get('name', '<unknown name>'),
description=kwargs.get('description',
'<unknown description>'),
letter_annotations=kwargs.get(
'letter_annotations', None),
annotations=kwargs.get('annotations', None),
features=kwargs.get('features', None),
dbxrefs=kwargs.get('dbxrefs', None))
self.start = int(start_site)
self.end = int(end_site)
self.length = self.end - self.start + 1
if self.length != len(self):
raise InvalidFragmentError(
"The fragment's sequence length ({0}) does not match its "
"start ({1}) and end ({2}) sites".format(
len(self), self.start, self.end))
self.overhang = int(overhang)
self.five_prime_terminus = five_prime_terminus
self.three_prime_terminus = three_prime_terminus
def __init__(self, seq_obj, position=None, footprint=None, tail=None):
self.position = position
self.footprint = footprint
self.tail = tail
seq_obj.seq.alphabet = ambiguous_dna
SeqRecord.__init__(self,
seq=seq_obj.seq,
id=seq_obj.id,
name=seq_obj.name,
description=seq_obj.description,
dbxrefs=seq_obj.dbxrefs,
features=seq_obj.features,
annotations=seq_obj.annotations,
letter_annotations=seq_obj.letter_annotations)
def __init__(self,
seq_record,
start_site,
end_site,
overhang,
five_prime_terminus=False,
three_prime_terminus=False,
**kwargs):
if start_site > end_site:
raise InvalidFragmentError(
"A Fragment's start position ({0}) cannot be greater than "
"its end position ({1})".format(start_site, end_site))
if isinstance(seq_record, SeqRecord):
SeqRecord.__init__(self,
seq = seq_record.seq,
id = seq_record.id,
name = seq_record.name,
description = seq_record.description,
letter_annotations = seq_record.letter_annotations,
annotations = seq_record.annotations,
features = seq_record.features,
dbxrefs = seq_record.dbxrefs)
else:
SeqRecord.__init__(self,
seq = Seq(str(seq_record).upper(),
alphabet=IUPAC.ambiguous_dna),
id = kwargs.get('id', '<unknown id>'),
name = kwargs.get('name', '<unknown name>'),
description = kwargs.get('description',
'<unknown description>'),
letter_annotations = kwargs.get('letter_annotations',
None),
annotations = kwargs.get('annotations', None),
features = kwargs.get('features', None),
dbxrefs = kwargs.get('dbxrefs', None))
self.start = int(start_site)
self.end = int(end_site)
self.length = self.end - self.start + 1
if self.length != len(self):
raise InvalidFragmentError(
"The fragment's sequence length ({0}) does not match its "
"start ({1}) and end ({2}) sites".format(len(self),
self.start, self.end))
self.overhang = int(overhang)
self.five_prime_terminus = five_prime_terminus
self.three_prime_terminus = three_prime_terminus
def __init__(self, sequence, **kwargs):
SeqRecord.__init__(self, sequence, **kwargs)
sequence = upper(sequence)
g_count = sequence.count('G')
c_count = sequence.count('C')
# make GC content as a percent
content = sum([g_count, c_count]) / float(len(sequence))
content = content * 100
self.gc_content = round(content, 0)
# set the start stop in parent seq
self.start = int(kwargs.get('id', -1))
self.stop = self.start + len(sequence) - 1
# set up score
self.score = -1
self.genes = []
def __init__(self,
seq_obj,
position=None,
footprint=None,
tail=None):
self.position = position
self.footprint = footprint
self.tail = tail
seq_obj.seq.alphabet = ambiguous_dna
SeqRecord.__init__(self,
seq = seq_obj.seq,
id = seq_obj.id,
name = seq_obj.name,
description = seq_obj.description,
dbxrefs = seq_obj.dbxrefs,
features = seq_obj.features,
annotations = seq_obj.annotations,
letter_annotations = seq_obj.letter_annotations)
def __init__(self, *args, **kw):
"""Initialize ImmuneChain
This is performed either with a prebuilt SeqRecord object or as a
native SeqRecord object.
"""
if len(args) > 0 and isinstance(args[0],SeqRecord): # pre-built SeqRecord
self._init_with_SeqRecord(args[0])
elif kw.has_key('record'): # pre-built SeqRecord
self._init_with_SeqRecord(kw['record'])
else: # native SeqRecord init
SeqRecord.__init__(self,*args,**kw)
# precompute hash on features for performance
self._update_feature_dict()
# load `source` feature qualifiers into annotations and delete `source`
# feature, if it exists
self._process_source_feature()
# define a set for uniq tags
self._tags = set(self.annotations.setdefault('tags',[]))
def __init__(self, *args, **kw):
"""Initialize ImmuneChain
This is performed either with a prebuilt SeqRecord object or as a
native SeqRecord object.
"""
if len(args) > 0 and isinstance(args[0],SeqRecord): # pre-built SeqRecord
self._init_with_SeqRecord(args[0])
elif kw.has_key('record'): # pre-built SeqRecord
self._init_with_SeqRecord(kw['record'])
else: # native SeqRecord init
SeqRecord.__init__(self,*args,**kw)
# precompute hash on features for performance
self._update_feature_dict()
# load `source` feature qualifiers into annotations and delete `source`
# feature, if it exists
self._process_source_feature()
# define a set for uniq tags
self._tags = set(self.annotations.setdefault('tags',[]))
def __init__(self, kmer_str, freq_dict=None):
SeqRecord.__init__(self, Seq(kmer_str), id=kmer_str, description="")
if freq_dict:
self.freq = freq_dict.get(kmer_str, 1)
else:
self.freq = 1
def __init__(self, rec):
SeqRecord.__init__(self, rec.seq, rec.id, rec.name, rec.description,
rec.dbxrefs,rec.features,rec.annotations)
