def get_subsequence(self, resnums, new_id=None, copy_letter_annotations=True):
"""Get a subsequence as a new SeqProp object given a list of residue numbers"""
# XTODO: documentation
if not self.seq_record:
raise ValueError('No chain sequence stored')
biop_compound_list = []
for resnum in resnums:
feat = FeatureLocation(resnum - 1, resnum)
biop_compound_list.append(feat)
if len(biop_compound_list) == 0:
log.info('Zero length subsequences')
return
elif len(biop_compound_list) == 1:
log.debug('Subsequence only one residue long')
sub_feature_location = biop_compound_list[0]
else:
sub_feature_location = CompoundLocation(biop_compound_list)
sub_feature = sub_feature_location.extract(self.seq_record)
if not new_id:
new_id = '{}_subseq'.format(self.id)
new_sp = SeqProp(id=new_id, seq=sub_feature)
if copy_letter_annotations:
new_sp.letter_annotations = sub_feature.letter_annotations
return new_sp
def get_subsequence(self, resnums):
"""Get a subsequence as a new SeqProp object given a list of residue numbers"""
biop_compound_list = []
for resnum in resnums:
feat = FeatureLocation(resnum - 1, resnum)
biop_compound_list.append(feat)
sub_feature_location = CompoundLocation(biop_compound_list)
sub_feature = sub_feature_location.extract(self)
new_sp = SeqProp(id='{}_subseq'.format(self.id), seq=sub_feature)
new_sp.letter_annotations = sub_feature.letter_annotations
return new_sp
def nucleic_sequence(self, feature_type):
"""
:type feature_type: str
:rtype: Bio.Seq.Seq
"""
locations = self._get_features(feature_type)
if locations:
if len(locations) > 1:
feature = CompoundLocation(locations)
else:
feature = locations[0]
return feature.extract(self.chromosome.nucleic_sequence)
return None
def get_subsequence_from_property(self,
property_key,
property_value,
condition,
return_resnums=False):
"""Get a subsequence as a new SeqProp object given a certain property you want to find in
this chain's letter_annotation
See documentation for :func:`ssbio.protein.sequence.seqprop.SeqProp.get_subsequence_from_property`
Args:
property_key (str): Property key in the ``letter_annotations`` attribute that you want to filter using
property_value (str): Property value that you want to filter by
condition (str): ``<``, ``=``, ``>``, ``>=``, or ``<=`` to filter the values by
return_resnums (bool): If resnums should be returned as well
Returns:
SeqProp: New SeqProp object that you can run computations on or just extract its properties
"""
if not self.seq_record:
raise ValueError('No chain sequence stored')
if property_key not in self.seq_record.letter_annotations:
raise KeyError(
'{}: {} not contained in the letter annotations'.format(
self.seq_record.id, property_key))
subfeat_indices = list(
locate(
self.seq_record.letter_annotations[property_key], lambda x:
ssbio.utils.check_condition(x, condition, property_value)))
biop_compound_list = []
for idx in subfeat_indices:
feat = FeatureLocation(idx, idx + 1)
biop_compound_list.append(feat)
sub_feature_location = CompoundLocation(biop_compound_list)
sub_feature = sub_feature_location.extract(self.seq_record)
new_sp = SeqProp(id='{}-{}_{}_{}_{}_extracted'.format(
self.pdb_parent, self.id, property_key, condition, property_value),
seq=sub_feature)
new_sp.letter_annotations = sub_feature.letter_annotations
if return_resnums:
return new_sp, [x + 1 for x in subfeat_indices]
else:
return new_sp
def nucleic_coding_sequence(self):
"""
:rtype: Bio.Seq.Seq
"""
if not self._nucleic_coding_sequence:
if self.cds and len(self.cds) > 1:
cds = CompoundLocation(self.cds)
else:
cds = self.cds[0]
self._nucleic_coding_sequence = cds.extract(
self.chromosome.nucleic_sequence)
if self.location.strand == -1:
self._nucleic_coding_sequence = Seq(
self._nucleic_coding_sequence).reverse_complement()
return self._nucleic_coding_sequence
def get_subsequence(self,
resnums,
new_id=None,
copy_letter_annotations=True):
"""Get a subsequence as a new SeqProp object given a list of residue numbers"""
# XTODO: documentation
biop_compound_list = []
for resnum in resnums:
# XTODO can be sped up by separating into ranges based on continuous resnums
feat = FeatureLocation(resnum - 1, resnum)
biop_compound_list.append(feat)
if len(biop_compound_list) == 0:
log.debug('Zero length subsequence')
return
elif len(biop_compound_list) == 1:
log.debug('Subsequence only one residue long')
sub_feature_location = biop_compound_list[0]
else:
sub_feature_location = CompoundLocation(biop_compound_list)
try:
sub_feature = sub_feature_location.extract(self)
except TypeError:
log.critical(
'SeqProp {}: unknown error when trying to get subsequence - please investigate! '
'Try using a feature to extract a subsequence from the SeqProp'
.format(self.id))
return
if not new_id:
new_id = '{}_subseq'.format(self.id)
new_sp = SeqProp(id=new_id, seq=sub_feature.seq)
if copy_letter_annotations:
new_sp.letter_annotations = sub_feature.letter_annotations
return new_sp
def get_subsequence_from_property(self,
property_key,
property_value,
condition,
return_resnums=False):
"""Get a subsequence as a new SeqProp object given a certain property you want to find in the
original SeqProp's letter_annotation
This can be used to do something like extract the subsequence of exposed residues, so you can can run
calculations on that subsequence. Useful if you have questions like "are there any predicted surface exposed
cysteines in my protein sequence?"
Example:
>>> sp = SeqProp(id='tester', seq='MQSLE')
>>> sp.letter_annotations['a_key'] = [2, 2, 3, 1, 0]
>>> pk = 'a_key'
>>> pv = 2
>>> cond = '<'
>>> new_sp = sp.get_subsequence_from_property(pk, pv, cond)
>>> new_sp.letter_annotations[pk]
[1, 0]
>>> new_sp
SeqProp(seq=Seq('LE', ExtendedIUPACProtein()), id='tester_a_key_<_2_extracted', name='<unknown name>', description='<unknown description>', dbxrefs=[])
Args:
property_key (str): Property key in the ``letter_annotations`` attribute that you want to filter using
property_value (str): Property value that you want to filter by
condition (str): ``<``, ``=``, ``>``, ``>=``, or ``<=`` to filter the values by
Returns:
SeqProp: New SeqProp object that you can run computations on or just extract its properties
"""
if property_key not in self.letter_annotations:
raise KeyError(
'{}: {} not contained in the letter annotations'.format(
self.id, property_key))
subfeat_indices = list(
locate(
self.letter_annotations[property_key], lambda x: ssbio.utils.
check_condition(x, condition, property_value)))
biop_compound_list = []
for idx in subfeat_indices:
feat = FeatureLocation(idx, idx + 1)
biop_compound_list.append(feat)
sub_feature_location = CompoundLocation(biop_compound_list)
sub_feature = sub_feature_location.extract(self)
new_sp = SeqProp(id='{}_{}_{}_{}_extracted'.format(
self.id, property_key, condition, property_value),
seq=sub_feature)
new_sp.letter_annotations = sub_feature.letter_annotations
if return_resnums:
return new_sp, [x + 1 for x in subfeat_indices]
else:
return new_sp