def get_relevant_substituents(self, residue, monosaccharides=None):
'''
Retrieve the set of substituents not implicitly included
in the base type's symbol name.
'''
if monosaccharides is None:
monosaccharides = self.monosaccharide_reference
positions = [p for p, sub in residue.substituents() if not sub._derivatize]
substituents = [sub.name for p, sub in residue.substituents() if not sub._derivatize]
if identity.is_a(residue, monosaccharides["NeuAc"], exact=False, short_circuit=True):
try:
i = substituents.index("n_acetyl")
substituents.pop(i)
j = positions.pop(i)
substituents.insert(i, "acetyl")
positions.insert(i, j)
except Exception: # pragma: no cover
pass
elif identity.is_a(residue, monosaccharides["NeuGc"], exact=False, short_circuit=True):
try:
i = substituents.index("n_glycolyl")
substituents.pop(i)
j = positions.pop(i)
substituents.insert(i, "glycolyl")
positions.insert(i, j)
except Exception: # pragma: no cover
pass
elif identity.is_a(residue, monosaccharides["Neu"], exact=False, short_circuit=True):
i = substituents.index("amino")
substituents.pop(i)
positions.pop(i)
return zip(substituents, positions)
def test_identify_substituents(self):
self.assertTrue(
identity.is_a(Substituent("n-acetyl"), Substituent("n-acetyl")))
self.assertFalse(
identity.is_a(Substituent('methyl'), Substituent('n-acetyl')))
self.assertFalse(
identity.is_a(monosaccharides.Man, Substituent('n-acetyl')))
self.assertFalse(
identity.is_a(Substituent('n-acetyl'), monosaccharides.Man))
def get_relevant_substituents(residue):
'''
Retrieve the set of substituents not implicitly included
in the base type's symbol name.
'''
positions = [p for p, sub in residue.substituents()]
substituents = [sub.name for p, sub in residue.substituents()]
if identity.is_a(residue, monosaccharide_reference["HexNAc"], exact=False) or\
identity.is_a(residue, monosaccharide_reference["NeuAc"], exact=False):
i = substituents.index("n_acetyl")
substituents.pop(i)
positions.pop(i)
elif identity.is_a(residue, monosaccharide_reference["NeuGc"], exact=False):
i = substituents.index("n_glycolyl")
substituents.pop(i)
positions.pop(i)
return zip(substituents, positions)
def is_special_case(node):
'''
Check to see if `node` is a special case which requires a different layout
scheme. See `special_cases`
'''
for case in special_cases:
if identity.is_a(node, case) and len(list(node.children())) == 0:
return True
return False
def is_dhex(residue):
try:
return is_a(
strip_derivatization(residue.clone(
monosaccharide_type=MonosaccharideResidue)), dhex)
except TypeError:
if not isinstance(residue, MonosaccharideResidue):
return False
else:
raise
def is_dhex(residue):
try:
return is_a(
strip_derivatization(
residue.clone(monosaccharide_type=MonosaccharideResidue)),
dhex)
except TypeError:
if not isinstance(residue, MonosaccharideResidue):
return False
else:
raise
def glycan_composition_to_terms(self, glycan_composition):
out = []
term = self.resolve_gnome(glycan_composition)
if term is not None:
out.append({
"accession": term.id,
"name": term.name,
"cvRef": term.vocabulary.name
})
reinterpreted = glycan_composition.clone().reinterpret(valid_monosaccharides)
for mono, count in reinterpreted.items():
if isinstance(mono, SubstituentResidue):
subst = inverted_substituent_map.get(
mono.name.replace("@", ""))
if subst is not None:
out.append({
"name": "monosaccharide count",
"value": ("%s:%d" % (subst, count)),
"accession": "MS:XXXXX2",
"cvRef": "PSI-MS"
})
else:
out.append({
"name": "unknown monosaccharide count",
"value": ("%s:%0.3f:%d" % (mono.name.replace("@", ""), mono.mass(), count)),
"accession": "MS:XXXXX3",
"cvRef": "PSI-MS"
})
elif isinstance(mono, MonosaccharideResidue):
for known in valid_monosaccharides:
if identity.is_a(mono, known):
out.append({
"name": "monosaccharide count",
"value": ("%s:%d" % (monosaccharide_to_term(known), count)),
"accession": "MS:XXXXX2",
"cvRef": "PSI-MS"
})
break
else:
out.append({
"name": "unknown monosaccharide count",
"value": ("%s:%0.3f:%d" % (monosaccharide_to_term(mono), mono.mass(), count)),
"accession": "MS:XXXXX3",
"cvRef": "PSI-MS"
})
else:
raise TypeError("Cannot handle unexpected component of type %s" % (type(mono), ))
return out
def monosaccharide_to_linear_code(monosaccharide, max_tolerance=3):
'''
Perform iteratively permissive attempts to translate `monosaccharide` into
a nomenclature symbol.
.. note::
Uses a multi-pass approach. Could alternatively do a single pass
and keep the best match.
Parameters
----------
monosaccharide: Monosaccharide
The residue to be translated
max_tolerance: int
The maximum error tolerance to allow while looking for a match
Returns
-------
str
Raises
------
ValueError:
When no suitable translation can be found
KeyError:
When an unknown symbol is encountered
'''
tolerance = 0
if identity.is_generic_monosaccharide(monosaccharide):
raise LinearCodeError("Linear Code does not support generic monosaccharide %s" % str(monosaccharide))
while tolerance <= max_tolerance:
for k, v in monosaccharides_to.items():
if k not in monosaccharide_reference:
continue
if identity.is_a(monosaccharide, monosaccharide_reference[k], tolerance=tolerance):
residue_sym = v
substituents_sym = [(
substituent_to_linear_code(
*s)) for s in get_relevant_substituents(monosaccharide)]
if len(substituents_sym) > 0:
residue_sym = residue_sym + '[{}]'.format(', '.join(substituents_sym))
residue_sym = residue_sym + anomer_map_to[monosaccharide.anomer]
return residue_sym
tolerance += 1
raise LinearCodeError("Cannot map {} to Linear Code".format(monosaccharide))
def test_precision(self):
self.assertFalse(identity.is_a(monosaccharides.Kdn, monosaccharides.NeuAc))
self.assertFalse(identity.is_a(monosaccharides.NeuAc, monosaccharides.Kdn))
def test_is_a_predicate(self):
for name, monosaccharide in monosaccharides.items():
result = identity.is_a(monosaccharide, name)
self.assertTrue(result)