def transcribe(self):
"""Transcribe DNA into RNA.
DNA sequence is assumed to be the coding strand. Thymine (T) is
replaced with uracil (U) in the transcribed sequence.
Returns
-------
RNA
Transcribed sequence.
See Also
--------
translate
translate_six_frames
Notes
-----
DNA sequence's metadata and positional metadata are included in the
transcribed RNA sequence.
Examples
--------
Transcribe DNA into RNA:
>>> from skbio import DNA
>>> dna = DNA('TAACGTTA')
>>> dna
DNA
--------------------------
Stats:
length: 8
has gaps: False
has degenerates: False
has definites: True
GC-content: 25.00%
--------------------------
0 TAACGTTA
>>> dna.transcribe()
RNA
--------------------------
Stats:
length: 8
has gaps: False
has degenerates: False
has definites: True
GC-content: 25.00%
--------------------------
0 UAACGUUA
"""
seq = self._string.replace(b'T', b'U')
# turn off validation because `seq` is guaranteed to be valid
return skbio.RNA(seq,
metadata=self.metadata,
positional_metadata=self.positional_metadata,
validate=False)
def _series_to_fasta_format(ff, data, sequence_type="DNA"):
with ff.open() as f:
for id_, seq in data.iteritems():
if sequence_type == "protein":
sequence = skbio.Protein(seq, metadata={'id': id_})
elif sequence_type == "DNA":
sequence = skbio.DNA(seq, metadata={'id': id_})
elif sequence_type == "RNA":
sequence = skbio.RNA(seq, metadata={'id': id_})
else:
raise NotImplementedError(
"pd.Series can only be converted to DNA or "
"protein FASTA format.")
skbio.io.write(sequence, format='fasta', into=f)