def _build_protein_index(self):
hypothesis_id = self.hypothesis_id
theoretical_counts = self.session.query(
Protein.name, Protein.id,
func.count(Glycopeptide.id)).join(Glycopeptide).group_by(
Protein.id).filter(
Protein.hypothesis_id == hypothesis_id).all()
matched_counts = self.session.query(
Protein.name, Protein.id, func.count(
IdentifiedGlycopeptide.id)).join(Protein.glycopeptides).join(
IdentifiedGlycopeptide, IdentifiedGlycopeptide.structure_id
== Glycopeptide.id).group_by(Protein.id).filter(
IdentifiedGlycopeptide.ms2_score > self.threshold,
IdentifiedGlycopeptide.analysis_id ==
self.analysis_id).all()
listing = []
index = {}
for protein_name, protein_id, glycopeptide_count in theoretical_counts:
index[protein_id] = {
"protein_name": protein_name,
"protein_id": protein_id,
}
for protein_name, protein_id, glycopeptide_count in matched_counts:
entry = index[protein_id]
entry['identified_glycopeptide_count'] = glycopeptide_count
listing.append(entry)
self.protein_index = sorted(
listing,
key=lambda x: x["identified_glycopeptide_count"],
reverse=True)
for protein_entry in self.protein_index:
protein_entry['protein'] = self.session.query(Protein).get(
protein_entry["protein_id"])
return self.protein_index
def _build_protein_index(self):
hypothesis_id = self.hypothesis_id
theoretical_counts = self.session.query(Protein.name, Protein.id, func.count(Glycopeptide.id)).join(
Glycopeptide).group_by(Protein.id).filter(
Protein.hypothesis_id == hypothesis_id).all()
matched_counts = self.session.query(Protein.name, Protein.id, func.count(IdentifiedGlycopeptide.id)).join(
Glycopeptide).join(
IdentifiedGlycopeptide, IdentifiedGlycopeptide.structure_id == Glycopeptide.id).group_by(
Protein.id).filter(
IdentifiedGlycopeptide.ms2_score > self.threshold,
IdentifiedGlycopeptide.analysis_id == self.analysis_id).all()
listing = []
index = {}
for protein_name, protein_id, glycopeptide_count in theoretical_counts:
index[protein_id] = {
"protein_name": protein_name,
"protein_id": protein_id,
}
for protein_name, protein_id, glycopeptide_count in matched_counts:
entry = index[protein_id]
entry['identified_glycopeptide_count'] = glycopeptide_count
listing.append(entry)
self.protein_index = sorted(listing, key=lambda x: x["identified_glycopeptide_count"], reverse=True)
for protein_entry in self.protein_index:
protein_entry['protein'] = self.session.query(Protein).get(protein_entry["protein_id"])
return self.protein_index
def __len__(self):
try:
return self.hypothesis.parameters['database_size']
except KeyError:
stmt = select([func.count(self.identity_field)
]).select_from(self.selectable)
stmt = self._limit_to_hypothesis(stmt)
return self.session.execute(stmt).scalar()
def __len__(self):
try:
return self.hypothesis.parameters['database_size']
except KeyError:
stmt = select([func.count(self.identity_field)]).select_from(
self.selectable)
stmt = self._limit_to_hypothesis(stmt)
return self.session.execute(stmt).scalar()
def _count_produced_glycopeptides(self):
count = self.query(
func.count(Glycopeptide.id)).filter(
Glycopeptide.hypothesis_id == self.hypothesis_id).scalar()
self.log("Generated %d glycopeptides" % count)
self.set_parameters({
"database_size": count
})
return count
def summarize_glycopeptide_hypothesis(database_connection, hypothesis_identifier):
session = database_connection.session
hypothesis = get_by_name_or_id(session, GlycopeptideHypothesis, hypothesis_identifier)
counts = session.query(Protein, func.count(Glycopeptide.id)).join(
Glycopeptide).group_by(Protein.id).filter(Protein.hypothesis_id == hypothesis.id).all()
counts = sorted(counts, key=lambda x: x[1], reverse=1)
total = 0
for protein, count in counts:
click.echo("%s: %d" % (protein.name, count))
total += count
click.echo("Total: %d" % (total,))
def digest_proteins(self):
digestor = ProteinDigestor(self.protease, self.constant_modifications,
self.variable_modifications,
self.max_missed_cleavages)
task = MultipleProcessProteinDigestor(self._original_connection,
self.hypothesis_id,
self.protein_ids(),
digestor,
n_processes=self.n_processes)
task.run()
n_peptides = self.query(func.count(Peptide.id)).filter(
Peptide.hypothesis_id == self.hypothesis_id).scalar()
self.log("%d Base Peptides Produced" % (n_peptides, ))
def digest_proteins(self):
digestor = ProteinDigestor(
self.protease, self.constant_modifications, self.variable_modifications,
self.max_missed_cleavages, semispecific=self.semispecific)
task = MultipleProcessProteinDigestor(
self._original_connection,
self.hypothesis_id,
self.protein_ids(),
digestor, n_processes=self.n_processes)
task.run()
n_peptides = self.query(func.count(Peptide.id)).filter(
Peptide.hypothesis_id == self.hypothesis_id).scalar()
self.log("%d Base Peptides Produced" % (n_peptides,))
def summarize_glycopeptide_hypothesis(database_connection,
hypothesis_identifier):
session = database_connection.session
hypothesis = get_by_name_or_id(session, GlycopeptideHypothesis,
hypothesis_identifier)
counts = session.query(Protein, func.count(
Glycopeptide.id)).join(Glycopeptide).group_by(
Protein.id).filter(Protein.hypothesis_id == hypothesis.id).all()
counts = sorted(counts, key=lambda x: x[1], reverse=1)
total = 0
for protein, count in counts:
click.echo("%s: %d" % (protein.name, count))
total += count
click.echo("Total: %d" % (total, ))
def protein_index(session, hypothesis_id):
theoretical_counts = session.query(Protein.name, Protein.id, func.count(Glycopeptide.id)).join(
Glycopeptide).group_by(Protein.id).filter(
Protein.hypothesis_id == hypothesis_id).all()
listing = []
for protein_name, protein_id, glycopeptide_count in theoretical_counts:
entry = {
"protein_name": protein_name,
"protein_id": protein_id,
"theoretical_count": glycopeptide_count
}
listing.append(entry)
protein_index = sorted(listing, key=lambda x: x["protein_name"])
for protein_entry in protein_index:
protein_entry['protein'] = session.query(Protein).get(protein_entry["protein_id"])
return protein_index
def _count_produced_glycopeptides(self):
count = self.query(
func.count(Glycopeptide.id)).filter(
Glycopeptide.hypothesis_id == self.hypothesis_id).scalar()
self.log("Generated %d glycopeptides" % count)
def __len__(self):
stmt = select([func.count(self.identity_field)
]).select_from(self.selectable)
stmt = self._limit_to_hypothesis(stmt)
return self.session.execute(stmt).scalar()
def _count_produced_glycopeptides(self):
count = self.query(func.count(Glycopeptide.id)).filter(
Glycopeptide.hypothesis_id == self.hypothesis_id).scalar()
self.log("Generated %d glycopeptides" % count)
self.set_parameters({"database_size": count})
return count