def local_pairwise_align_ssw(sequence1, sequence2, **kwargs):
"""Align query and target sequences with Striped Smith-Waterman.
Parameters
----------
sequence1 : DNA, RNA, or Protein
The first unaligned sequence
sequence2 : DNA, RNA, or Protein
The second unaligned sequence
Returns
-------
tuple
``TabularMSA`` object containing the aligned sequences, alignment score
(float), and start/end positions of each input sequence (iterable
of two-item tuples). Note that start/end positions are indexes into the
unaligned sequences.
Notes
-----
This is a wrapper for the SSW package [1]_.
For a complete list of optional keyword-arguments that can be provided,
see ``skbio.alignment.StripedSmithWaterman``.
The following kwargs will not have any effect: `suppress_sequences`,
`zero_index`, and `protein`
If an alignment does not meet a provided filter, `None` will be returned.
References
----------
.. [1] Zhao, Mengyao, Wan-Ping Lee, Erik P. Garrison, & Gabor T.
Marth. "SSW Library: An SIMD Smith-Waterman C/C++ Library for
Applications". PLOS ONE (2013). Web. 11 July 2014.
http://www.plosone.org/article/info:doi/10.1371/journal.pone.0082138
See Also
--------
skbio.alignment.StripedSmithWaterman
"""
for seq in sequence1, sequence2:
if not isinstance(seq, (DNA, RNA, Protein)):
raise TypeError(
"`sequence1` and `sequence2` must be DNA, RNA, or Protein, "
"not type %r" % type(seq).__name__)
if type(sequence1) is not type(sequence2):
raise TypeError(
"`sequence1` and `sequence2` must be the same type: %r != %r"
% (type(sequence1).__name__, type(sequence2).__name__))
# We need the sequences for `TabularMSA` to make sense, so don't let the
# user suppress them.
kwargs['suppress_sequences'] = False
kwargs['zero_index'] = True
kwargs['protein'] = False
if isinstance(sequence1, Protein):
kwargs['protein'] = True
query = StripedSmithWaterman(str(sequence1), **kwargs)
alignment = query(str(sequence2))
# If there is no cigar, then it has failed a filter. Return None.
if not alignment.cigar:
return None
start_end = None
if alignment.query_begin != -1:
start_end = [
(alignment.query_begin, alignment.query_end),
(alignment.target_begin, alignment.target_end_optimal)
]
metadata1 = metadata2 = None
if sequence1.has_metadata():
metadata1 = sequence1.metadata
if sequence2.has_metadata():
metadata2 = sequence2.metadata
constructor = type(sequence1)
msa = TabularMSA([
constructor(alignment.aligned_query_sequence, metadata=metadata1,
validate=False),
constructor(alignment.aligned_target_sequence, metadata=metadata2,
validate=False)
])
return msa, alignment.optimal_alignment_score, start_end
def local_pairwise_align_ssw(sequence1,
sequence2,
constructor=Sequence,
**kwargs):
"""Align query and target sequences with Striped Smith-Waterman.
Parameters
----------
sequence1 : str or Sequence
The first unaligned sequence
sequence2 : str or Sequence
The second unaligned sequence
constructor : Sequence subclass
A constructor to use if `protein` is not True.
Returns
-------
``skbio.alignment.Alignment``
The resulting alignment as an Alignment object
Notes
-----
This is a wrapper for the SSW package [1]_.
For a complete list of optional keyword-arguments that can be provided,
see ``skbio.alignment.StripedSmithWaterman``.
The following kwargs will not have any effect: `suppress_sequences` and
`zero_index`
If an alignment does not meet a provided filter, `None` will be returned.
References
----------
.. [1] Zhao, Mengyao, Wan-Ping Lee, Erik P. Garrison, & Gabor T.
Marth. "SSW Library: An SIMD Smith-Waterman C/C++ Library for
Applications". PLOS ONE (2013). Web. 11 July 2014.
http://www.plosone.org/article/info:doi/10.1371/journal.pone.0082138
See Also
--------
skbio.alignment.StripedSmithWaterman
"""
# We need the sequences for `Alignment` to make sense, so don't let the
# user suppress them.
kwargs['suppress_sequences'] = False
kwargs['zero_index'] = True
if isinstance(sequence1, Protein):
kwargs['protein'] = True
query = StripedSmithWaterman(str(sequence1), **kwargs)
alignment = query(str(sequence2))
# If there is no cigar, then it has failed a filter. Return None.
if not alignment.cigar:
return None
start_end = None
if alignment.query_begin != -1:
start_end = [(alignment.query_begin, alignment.query_end),
(alignment.target_begin, alignment.target_end_optimal)]
if kwargs.get('protein', False):
seqs = [
Protein(alignment.aligned_query_sequence, metadata={'id':
'query'}),
Protein(alignment.aligned_target_sequence,
metadata={'id': 'target'})
]
else:
seqs = [
constructor(alignment.aligned_query_sequence,
metadata={'id': 'query'}),
constructor(alignment.aligned_target_sequence,
metadata={'id': 'target'})
]
return Alignment(seqs,
score=alignment.optimal_alignment_score,
start_end_positions=start_end)