def convert(self, structure_text):
if structure_text in self.cache:
return self.cache[structure_text]
structure = glycoct.loads(structure_text)
gc = HashableGlycanComposition.from_glycan(structure).thaw()
gc.drop_stems()
gc.drop_configurations()
gc.drop_positions()
gc = HashableGlycanComposition(gc)
self.cache[structure_text] = gc
return gc
def parse_glycan_composition(string):
try:
return glycan_composition_cache[string]
except KeyError:
gc = HashableGlycanComposition.parse(string)
glycan_composition_cache[string] = gc
return gc
def to_decoy_glycan(string):
try:
return decoy_glycan_cache[string]
except KeyError:
gc = HashableGlycanComposition.parse(string)
gc["#decoy#"] = 2
decoy_glycan_cache[string] = gc
return gc
def convert(self, structure_text):
if structure_text in self.cache:
return self.cache[structure_text]
structure = glycoct.loads(structure_text)
gc = HashableGlycanComposition.from_glycan(structure).thaw()
gc.drop_stems()
gc.drop_configurations()
gc.drop_positions()
gc = HashableGlycanComposition(gc)
self.cache[structure_text] = gc
return gc
def _from_csv(cls, row):
def _try_parse(value):
try:
return int(value)
except (ValueError, TypeError):
try:
return float(value)
except (ValueError, TypeError):
return value
mass = float(row.pop("weighted_neutral_mass"))
apex_time = float(row.pop("apex_time"))
total_signal = float(row.pop("total_signal"))
gc = HashableGlycanComposition.parse(row.pop("glycan_composition"))
kwargs = {k: _try_parse(v) for k, v in row.items()}
return cls(mass, apex_time, total_signal, gc, **kwargs)
def validate_glycan_text(path):
from glycan_profiling.database.builder.glycan.glycan_source import TextFileGlycanCompositionLoader
with open(path, 'r') as handle:
loader = TextFileGlycanCompositionLoader(handle)
n = 0
glycan_classes = set()
residues = set()
unresolved = set()
for line in loader:
n += 1
glycan_classes.update(line[1])
glycan_composition = HashableGlycanComposition.parse(line[0])
for residue in glycan_composition.keys():
if residue.mass() == 0:
unresolved.add(residue)
residues.add(residue)
click.secho("%d glycan compositions" % (n,))
click.secho("Residues:")
for residue in residues:
click.secho("\t%s - %f" % (str(residue), residue.mass()))
if unresolved:
click.secho("Unresolved Residues:", fg='yellow')
click.secho("\n".join(str(r) for r in unresolved), fg='yellow')
def validate_glycan_text(path):
from glycan_profiling.database.builder.glycan.glycan_source import TextFileGlycanCompositionLoader
with open(path, 'r') as handle:
loader = TextFileGlycanCompositionLoader(handle)
n = 0
glycan_classes = set()
residues = set()
unresolved = set()
for line in loader:
n += 1
glycan_classes.update(line[1])
glycan_composition = HashableGlycanComposition.parse(line[0])
for residue in glycan_composition.keys():
if residue.mass() == 0:
unresolved.add(residue)
residues.add(residue)
click.secho("%d glycan compositions" % (n, ))
click.secho("Residues:")
for residue in residues:
click.secho("\t%s - %f" % (str(residue), residue.mass()))
if unresolved:
click.secho("Unresolved Residues:", fg='yellow')
click.secho("\n".join(str(r) for r in unresolved), fg='yellow')
import glypy
import matplotlib
matplotlib.use("agg")
from matplotlib import pyplot as plt
import matplotlib_venn
from glypy.structure.glycan_composition import HashableGlycanComposition
with open("combinatorial-glycans.txt") as combfile:
combinatorial = []
for line in combfile:
combinatorial.append(
HashableGlycanComposition.parse(line.split("\t")[0]))
with open("krambeck_glycan_compositions.txt") as krambeck_file:
krambeck = []
for line in krambeck_file:
krambeck.append(HashableGlycanComposition.parse(line.split("\t")[0]))
with open("glyspace_glycan_compositions.txt") as glyspace_file:
glyspace = []
for line in glyspace_file:
glyspace.append(HashableGlycanComposition.parse(line.split("\t")[0]))
combinatorial = set(combinatorial)
krambeck = set(krambeck)
glyspace = set(glyspace)
c = len(combinatorial)
k = len(krambeck)
g = len(glyspace)
substituents_to_detatch = [
glypy.Substituent("sulfate"),
glypy.Substituent("phosphate")
]
compositions = set()
for i, structure in enumerate(structures):
if i % 100 == 0:
print("Converted %d glycan structures. %d glycan compositions." % (i, len(compositions)))
glycan_comp = GlycanComposition.from_glycan(structure)
glycan_comp.drop_configurations()
glycan_comp.drop_stems()
glycan_comp.drop_positions()
glycan_comp = detatch_monosaccharide_substituents(glycan_comp, substituents_to_detatch)
try:
compositions.add(HashableGlycanComposition(glycan_comp))
except ValueError as ex:
print(ex)
continue
valid_components = {"Hex", "HexNAc", "Neu5Ac", "Fuc", "@sulfate"}
filtered_compositions = set()
for i, composition in enumerate(compositions):
if i % 100 == 0:
print("%d glycan compositions filtered. %d glycan compositions accepted." % (i, len(filtered_compositions)))
components = {str(k) for k in composition.keys()}
if len(components - valid_components) > 0:
continue
filtered_compositions.add(composition)
import csv
from glypy.structure.glycan_composition import HashableGlycanComposition
with open("./Default_Combination_V2.csv") as fh, open(
"krambeck_glycan_compositions.txt", 'wb') as out:
reader = csv.reader(fh)
# skip header
next(reader)
for i, row in enumerate(reader):
if i % 100 == 0:
print("%d glycan compositions processed" % (i, ))
gc = HashableGlycanComposition({
k: v
for k, v in dict(
HexNAc=row[0], Hex=row[1], Fuc=row[2], NeuAc=row[3]).items()
if v > 0
})
out.write("%s\tN-Linked\n" % (gc, ))
print("%d glycan compositions parsed" % (i, ))
def shift_glycan_composition(self, delta):
inst = self.__class__.from_obj(self)
inst.glycan_composition = HashableGlycanComposition(
self.glycan_composition) - delta
return inst
def _from_dict(cls, d):
d['composition'] = HashableGlycanComposition.parse(d['composition'])
d['glycan_types'] = [GlycanTypes[t] for t in d['glycan_types']]
return cls(**d)
def _from_dict(cls, d):
d['composition'] = HashableGlycanComposition.parse(d['composition'])
d['glycan_types'] = [GlycanTypes[t] for t in d['glycan_types']]
return cls(**d)