def build_combinatorial_hypothesis(rule_file, database_connection, reduction,
derivatization, name, channel):
if name is not None:
name = validate_glycan_hypothesis_name(None, database_connection, name)
channel.send(Message("Building Glycan Hypothesis %s" % name, 'info'))
try:
reduction = str(reduction) if reduction is not None else None
validate_reduction(None, reduction)
except Abort:
channel.send(Message("Could not validate reduction %s" % reduction),
'error')
return
try:
derivatization = str(
derivatization) if derivatization is not None else None
validate_derivatization(None, derivatization)
except Abort:
channel.send(
Message("Could not validate derivatization %s" % derivatization,
'error'))
return
try:
builder = CombinatorialGlycanHypothesisSerializer(
rule_file,
database_connection,
reduction=reduction,
derivatization=derivatization,
hypothesis_name=name)
builder.start()
record = project_hypothesis.HypothesisRecordSet(database_connection)
hypothesis_record = None
for item in record:
if item.uuid == builder.hypothesis.uuid:
hypothesis_record = item
hypothesis_record = hypothesis_record._replace(
user_id=channel.user.id)
channel.send(
Message(hypothesis_record.to_json(), "new-hypothesis"))
break
else:
channel.send(
Message("Something went wrong (%r)" % (list(record), )))
except Exception:
channel.send(Message.traceback())
raise
def mzid_glycopeptide(database_connection, mzid_file, name, occupied_glycosites, target_protein,
processes, glycan_source, glycan_source_type, glycan_source_identifier,
channel):
context = None
proteins = validate_mzid_proteins(
context, mzid_file, target_protein, [])
try:
validate_glycan_source(context, database_connection,
glycan_source, glycan_source_type,
glycan_source_identifier)
except Abort:
channel.abort("Could not validate the glycan source, %s, %s" % (glycan_source, glycan_source_type))
if name is not None:
name = validate_glycopeptide_hypothesis_name(
context, database_connection, name)
glycan_hypothesis_id = _glycan_hypothesis_builders[
glycan_source_type](database_connection, glycan_source,
name, glycan_source_identifier)
builder = MultipleProcessMzIdentMLGlycopeptideHypothesisSerializer(
mzid_file, database_connection,
glycan_hypothesis_id=glycan_hypothesis_id,
hypothesis_name=name,
target_proteins=proteins,
max_glycosylation_events=occupied_glycosites,
n_processes=processes)
try:
builder.start()
record = project_hypothesis.HypothesisRecordSet(database_connection)
hypothesis_record = None
for item in record:
if item.uuid == builder.hypothesis.uuid:
hypothesis_record = item
hypothesis_record = hypothesis_record._replace(user_id=channel.user.id)
channel.send(Message(hypothesis_record.to_json(), "new-hypothesis"))
break
else:
channel.send(Message("Something went wrong (%r)" % (list(record),)))
except Exception:
channel.abort(Message.traceback())
def merge_glycan_hypothesis(database_connection, hypothesis_ids, name, channel):
if name is not None:
name = validate_glycan_hypothesis_name(None, database_connection, name)
channel.send(Message("Merging Glycan Hypothesis %s" % name, 'info'))
try:
task = GlycanCompositionHypothesisMerger(database_connection, [
(conn, hid) for conn, hid in hypothesis_ids], name)
task.start()
record = project_hypothesis.HypothesisRecordSet(database_connection)
hypothesis_record = None
for item in record:
if item.uuid == task.hypothesis.uuid:
hypothesis_record = item
hypothesis_record = hypothesis_record._replace(user_id=channel.user.id)
channel.send(Message(hypothesis_record.to_json(), "new-hypothesis"))
break
else:
channel.send(Message("Something went wrong (%r)" % (list(record),)))
except Exception:
channel.send(Message.traceback())
channel.abort("An error occurred during merging.")
def fasta_glycopeptide(database_connection, fasta_file, enzyme,
missed_cleavages, occupied_glycosites, name,
constant_modification, variable_modification, processes,
glycan_source, glycan_source_type,
glycan_source_identifier, peptide_length_range,
semispecific_digest, generate_full_crossproduct,
generate_reverse_decoys, channel):
context = None
try:
validate_modifications(context,
constant_modification + variable_modification)
except Exception:
channel.abort(
"Could not validate the modification specification, Constant: %s, Variable: %s"
% (constant_modification, variable_modification))
try:
validate_glycan_source(context, database_connection, glycan_source,
glycan_source_type, glycan_source_identifier)
except Abort:
channel.abort("Could not validate the glycan source, %s, %s" %
(glycan_source, glycan_source_type))
if name is not None:
name = validate_glycopeptide_hypothesis_name(context,
database_connection, name)
mt = RestrictedModificationTable(None, constant_modification,
variable_modification)
constant_modification = [mt[c] for c in constant_modification]
variable_modification = [mt[c] for c in variable_modification]
glycan_hypothesis_id = _glycan_hypothesis_builders[glycan_source_type](
database_connection, glycan_source, name, glycan_source_identifier)
builder = MultipleProcessFastaGlycopeptideHypothesisSerializer(
fasta_file,
database_connection,
glycan_hypothesis_id=glycan_hypothesis_id,
protease=enzyme,
constant_modifications=constant_modification,
variable_modifications=variable_modification,
max_missed_cleavages=missed_cleavages,
max_glycosylation_events=occupied_glycosites,
hypothesis_name=name,
peptide_length_range=peptide_length_range,
semispecific=semispecific_digest,
n_processes=processes,
full_cross_product=generate_full_crossproduct)
decoy_builder = None
decoy_database_connection = None
if generate_reverse_decoys:
prefix, ext = database_connection.rsplit(".", 1)
decoy_database_connection = "%s.decoy.%s" % (prefix, ext)
try:
validate_glycan_source(context, decoy_database_connection,
glycan_source, glycan_source_type,
glycan_source_identifier)
except Abort:
channel.abort("Could not validate the glycan source, %s, %s" %
(glycan_source, glycan_source_type))
decoy_glycan_hypothesis_id = _glycan_hypothesis_builders[
glycan_source_type](decoy_database_connection, glycan_source, name,
glycan_source_identifier)
decoy_builder = ReversingMultipleProcessFastaGlycopeptideHypothesisSerializer(
fasta_file,
decoy_database_connection,
glycan_hypothesis_id=decoy_glycan_hypothesis_id,
protease=enzyme,
constant_modifications=constant_modification,
variable_modifications=variable_modification,
max_missed_cleavages=missed_cleavages,
max_glycosylation_events=occupied_glycosites,
hypothesis_name=name,
peptide_length_range=peptide_length_range,
semispecific=semispecific_digest,
n_processes=processes,
full_cross_product=generate_full_crossproduct)
try:
builder.start()
record = project_hypothesis.HypothesisRecordSet(database_connection)
hypothesis_record = None
decoy_hypothesis_record = None
if decoy_builder:
decoy_builder.start()
decoy_record = project_hypothesis.HypothesisRecordSet(
decoy_database_connection)
for item in decoy_record:
if item.uuid == decoy_builder.hypothesis.uuid:
decoy_hypothesis_record = item._replace(
user_id=channel.user.id,
options={
'full_crossproduct': generate_full_crossproduct
})
break
else:
channel.send(
Message("Something went wrong (%r)" % (list(record), )))
channel.abort("Could not extract decoy hypothesis")
for item in record:
if item.uuid == builder.hypothesis.uuid:
hypothesis_record = item
hypothesis_record = hypothesis_record._replace(
user_id=channel.user.id,
options={'full_crossproduct': generate_full_crossproduct})
if decoy_hypothesis_record is not None:
hypothesis_record = hypothesis_record._replace(
decoy_hypothesis=decoy_hypothesis_record)
channel.send(
Message(hypothesis_record.to_json(), "new-hypothesis"))
break
else:
channel.send(
Message("Something went wrong (%r)" % (list(record), )))
except Exception:
channel.send(Message.traceback())
def mzid_glycopeptide(database_connection, mzid_file, name,
occupied_glycosites, target_protein, processes,
glycan_source, glycan_source_type,
glycan_source_identifier, peptide_length_range,
generate_full_crossproduct, generate_reverse_decoys,
channel):
context = None
proteins = validate_mzid_proteins(context, mzid_file, target_protein, [])
try:
validate_glycan_source(context, database_connection, glycan_source,
glycan_source_type, glycan_source_identifier)
except Abort:
channel.abort("Could not validate the glycan source, %s, %s" %
(glycan_source, glycan_source_type))
if name is not None:
name = validate_glycopeptide_hypothesis_name(context,
database_connection, name)
glycan_hypothesis_id = _glycan_hypothesis_builders[glycan_source_type](
database_connection, glycan_source, name, glycan_source_identifier)
builder = MultipleProcessMzIdentMLGlycopeptideHypothesisSerializer(
mzid_file,
database_connection,
glycan_hypothesis_id=glycan_hypothesis_id,
hypothesis_name=name,
target_proteins=proteins,
max_glycosylation_events=occupied_glycosites,
peptide_length_range=peptide_length_range,
n_processes=processes,
full_cross_product=generate_full_crossproduct)
decoy_builder = None
decoy_database_connection = None
if generate_reverse_decoys:
# TODO Implement reversing mzIdentML database build
prefix, ext = database_connection.rsplit(".", 1)
decoy_database_connection = "%s.decoy.%s" % (prefix, ext)
try:
validate_glycan_source(context, decoy_database_connection,
glycan_source, glycan_source_type,
glycan_source_identifier)
except Abort:
channel.abort("Could not validate the glycan source, %s, %s" %
(glycan_source, glycan_source_type))
channel.abort("Cannot build a reversed mzIdentML hypothesis")
# decoy_glycan_hypothesis_id = _glycan_hypothesis_builders[
# glycan_source_type](decoy_database_connection, glycan_source,
# name, glycan_source_identifier)
# decoy_builder = ReversingMultipleProcessFastaGlycopeptideHypothesisSerializer(
# mzid_file, decoy_database_connection,
# glycan_hypothesis_id=decoy_glycan_hypothesis_id,
# max_glycosylation_events=occupied_glycosites,
# hypothesis_name="Reverse " + name,
# peptide_length_range=peptide_length_range,
# n_processes=processes,
# full_cross_product=full_cross_product)
try:
builder.start()
record = project_hypothesis.HypothesisRecordSet(database_connection)
hypothesis_record = None
decoy_hypothesis_record = None
if decoy_builder:
decoy_builder.start()
decoy_record = project_hypothesis.HypothesisRecordSet(
decoy_database_connection)
for item in decoy_record:
if item.uuid == decoy_builder.hypothesis.uuid:
decoy_hypothesis_record = item
decoy_hypothesis_record = decoy_hypothesis_record._replace(
user_id=channel.user.id,
options={
'full_cross_product': generate_full_crossproduct
})
break
for item in record:
if item.uuid == builder.hypothesis.uuid:
hypothesis_record = item
hypothesis_record = hypothesis_record._replace(
user_id=channel.user.id,
options={'full_cross_product': generate_full_crossproduct})
if decoy_hypothesis_record is not None:
hypothesis_record = hypothesis_record._replace(
decoy_hypothesis=decoy_hypothesis_record)
channel.send(
Message(hypothesis_record.to_json(), "new-hypothesis"))
break
else:
channel.send(
Message("Something went wrong (%r)" % (list(record), )))
except Exception:
channel.abort(Message.traceback())
def build_prebuilt_hypothesis(recipes, database_connection, reduction,
derivatization, name, channel):
if not validate_database_unlocked(database_connection):
channel.send(Message("Database is locked.", "error"))
return
if name is not None:
name = validate_glycan_hypothesis_name(None, database_connection, name)
channel.send(Message("Building Glycan Hypothesis %s" % name, 'info'))
try:
reduction = str(reduction) if reduction is not None else None
validate_reduction(None, reduction)
except Abort:
channel.send(Message("Could not validate reduction %s" % reduction),
'error')
return
try:
derivatization = str(
derivatization) if derivatization is not None else None
validate_derivatization(None, derivatization)
except Abort:
channel.send(
Message("Could not validate derivatization %s" % derivatization,
'error'))
return
try:
if len(recipes) == 1:
task = recipes[0]
builder = task(database_connection,
reduction=reduction,
derivatization=derivatization,
hypothesis_name=name)
else:
sub_builders = []
for task in recipes:
builder = task(database_connection,
reduction=reduction,
derivatization=derivatization)
sub_builders.append(builder)
builder = GlycanCompositionHypothesisMerger(
database_connection,
[(database_connection, s.hypothesis.id) for s in sub_builders],
hypothesis_name=name)
builder.start()
record = project_hypothesis.HypothesisRecordSet(database_connection)
hypothesis_record = None
for item in record:
if item.uuid == builder.hypothesis.uuid:
hypothesis_record = item
hypothesis_record = hypothesis_record._replace(
user_id=channel.user.id)
channel.send(
Message(hypothesis_record.to_json(), "new-hypothesis"))
break
else:
channel.send(
Message("Something went wrong (%r)" % (list(record), )))
except Exception:
channel.send(Message.traceback())
def fasta_glycopeptide(database_connection, fasta_file, enzyme,
missed_cleavages, occupied_glycosites, name,
constant_modification, variable_modification, processes,
glycan_source, glycan_source_type,
glycan_source_identifier, channel):
context = None
try:
validate_modifications(context,
constant_modification + variable_modification)
except Exception:
channel.abort(
"Could not validate the modification specification, Constant: %s, Variable: %s"
% (constant_modification, variable_modification))
try:
validate_glycan_source(context, database_connection, glycan_source,
glycan_source_type, glycan_source_identifier)
except Abort:
channel.abort("Could not validate the glycan source, %s, %s" %
(glycan_source, glycan_source_type))
if name is not None:
name = validate_glycopeptide_hypothesis_name(context,
database_connection, name)
mt = RestrictedModificationTable(None, constant_modification,
variable_modification)
constant_modification = [mt[c] for c in constant_modification]
variable_modification = [mt[c] for c in variable_modification]
glycan_hypothesis_id = _glycan_hypothesis_builders[glycan_source_type](
database_connection, glycan_source, name, glycan_source_identifier)
builder = MultipleProcessFastaGlycopeptideHypothesisSerializer(
fasta_file,
database_connection,
glycan_hypothesis_id=glycan_hypothesis_id,
protease=enzyme,
constant_modifications=constant_modification,
variable_modifications=variable_modification,
max_missed_cleavages=missed_cleavages,
max_glycosylation_events=occupied_glycosites,
hypothesis_name=name,
n_processes=processes)
try:
builder.start()
record = project_hypothesis.HypothesisRecordSet(database_connection)
hypothesis_record = None
for item in record:
if item.uuid == builder.hypothesis.uuid:
hypothesis_record = item
hypothesis_record = hypothesis_record._replace(
user_id=channel.user.id)
channel.send(
Message(hypothesis_record.to_json(), "new-hypothesis"))
break
else:
channel.send(
Message("Something went wrong (%r)" % (list(record), )))
except Exception:
channel.send(Message.traceback())