def __format__(self, format_spec):
"""Returns the alignment as a string in the specified file format.
This method supports the python format() function added in
Python 2.6/3.0. The format_spec should be a lower case
string supported by Bio.AlignIO as an output file format.
See also the alignment's format() method."""
if format_spec:
from anarci.Bio._py3k import StringIO
from anarci.Bio import AlignIO
handle = StringIO()
AlignIO.write([self], handle, format_spec)
return handle.getvalue()
else:
# Follow python convention and default to using __str__
return str(self)
def __format__(self, format_spec):
"""Returns the record as a string in the specified file format.
This method supports the python format() function added in
Python 2.6/3.0. The format_spec should be a lower case string
supported by Bio.SeqIO as an output file format. See also the
SeqRecord's format() method.
Under Python 3 please note that for binary formats a bytes
string is returned, otherwise a (unicode) string is returned.
"""
if not format_spec:
# Follow python convention and default to using __str__
return str(self)
from anarci.Bio import SeqIO
if format_spec in SeqIO._BinaryFormats:
# Return bytes on Python 3
from io import BytesIO
handle = BytesIO()
else:
from anarci.Bio._py3k import StringIO
handle = StringIO()
SeqIO.write(self, handle, format_spec)
return handle.getvalue()
def get(self, offset):
return self._parse(StringIO(_bytes_to_string(self.get_raw(offset))))
>>><<<
579 residues in 3 query sequences
45119 residues in 180 library sequences
Scomplib [34.26]
start: Tue May 20 16:38:45 2008 done: Tue May 20 16:38:45 2008
Total Scan time: 0.020 Total Display time: 0.010
Function used was FASTA [version 34.26 January 12, 2007]
"""
from anarci.Bio._py3k import StringIO
alignments = list(FastaM10Iterator(StringIO(simple_example)))
assert len(alignments) == 4, len(alignments)
assert len(alignments[0]) == 2
for a in alignments:
print("Alignment %i sequences of length %i" %
(len(a), a.get_alignment_length()))
for r in a:
print("%s %s %i" % (r.seq, r.id, r.annotations["original_length"]))
# print(a.annotations)
print("Done")
import os
path = "../../Tests/Fasta/"
files = sorted(f for f in os.listdir(path)
if os.path.splitext(f)[-1] == ".m10")
for filename in files:
raise ValueError("Need a DNA, RNA or Protein alphabet")
if __name__ == "__main__":
from anarci.Bio._py3k import StringIO
print("Quick self test")
print("")
print("Repeated names without a TAXA block")
handle = StringIO("""#NEXUS
[TITLE: NoName]
begin data;
dimensions ntax=4 nchar=50;
format interleave datatype=protein gap=- symbols="FSTNKEYVQMCLAWPHDRIG";
matrix
CYS1_DICDI -----MKVIL LFVLAVFTVF VSS------- --------RG IPPEEQ----
ALEU_HORVU MAHARVLLLA LAVLATAAVA VASSSSFADS NPIRPVTDRA ASTLESAVLG
CATH_HUMAN ------MWAT LPLLCAGAWL LGV------- -PVCGAAELS VNSLEK----
CYS1_DICDI -----MKVIL LFVLAVFTVF VSS------- --------RG IPPEEQ---X
;
end;
""")
for a in NexusIterator(handle):
print(a)
for r in a:
print("%r %s %s" % (r.seq, r.name, r.id))
print("Done")
print("")
print("Repeated names with a TAXA block")
def get(self, offset):
"""Returns SeqRecord."""
# Should be overridden for binary file formats etc:
return self._parse(StringIO(_bytes_to_string(self.get_raw(offset))))