def _init_sites(self):
try:
parsed_sequence = self._get_sequence()
except residue.UnknownAminoAcidException:
return
sites = []
try:
n_glycosites = sequence.find_n_glycosylation_sequons(parsed_sequence)
for n_glycosite in n_glycosites:
sites.append(
ProteinSite(name=ProteinSite.N_GLYCOSYLATION, location=n_glycosite))
except residue.UnknownAminoAcidException:
pass
# The O- and GAG-linker sites are not determined by a multi AA sequon. We don't
# need to abstract them away and they are much too common.
# try:
# o_glycosites = sequence.find_o_glycosylation_sequons(
# parsed_sequence)
# for o_glycosite in o_glycosites:
# sites.append(
# ProteinSite(name=ProteinSite.O_GLYCOSYLATION, location=o_glycosite))
# except residue.UnknownAminoAcidException:
# pass
# try:
# gag_sites = sequence.find_glycosaminoglycan_sequons(
# parsed_sequence)
# for gag_site in gag_sites:
# sites.append(
# ProteinSite(name=ProteinSite.GAGYLATION, location=gag_site))
# except residue.UnknownAminoAcidException:
# pass
self.sites.extend(sites)
def __init__(self, peptide_dict, enzyme=None, constant_modifications=None,
modification_translation_table=None, process=True):
if modification_translation_table is None:
modification_translation_table = dict()
if constant_modifications is None:
constant_modifications = list()
self.peptide_dict = peptide_dict
self.insert_sites = []
self.deleteion_sites = []
self.modification_counter = 0
self.missed_cleavages = 0
self.base_sequence = peptide_dict["PeptideSequence"]
self.peptide_sequence = PeptideSequence(peptide_dict["PeptideSequence"])
self.glycosite_candidates = sequence.find_n_glycosylation_sequons(
self.peptide_sequence, WHITELIST_GLYCOSITE_PTMS)
self.constant_modifications = constant_modifications
self.modification_translation_table = modification_translation_table
self.enzyme = enzyme
self.mzid_id = peptide_dict.get('id')
if process:
self.process()
def __init__(self, peptide_dict, enzyme=None, constant_modifications=None,
modification_translation_table=None, process=True):
if modification_translation_table is None:
modification_translation_table = dict()
if constant_modifications is None:
constant_modifications = list()
self.peptide_dict = peptide_dict
self.insert_sites = []
self.deleteion_sites = []
self.modification_counter = 0
self.missed_cleavages = 0
self.base_sequence = peptide_dict["PeptideSequence"]
self.peptide_sequence = PeptideSequence(peptide_dict["PeptideSequence"])
self.glycosite_candidates = sequence.find_n_glycosylation_sequons(
self.peptide_sequence, WHITELIST_GLYCOSITE_PTMS)
self.constant_modifications = constant_modifications
self.modification_translation_table = modification_translation_table
self.enzyme = enzyme
self.mzid_id = peptide_dict.get('id')
if process:
self.process()
def n_glycan_sequon_sites(self):
if self._n_glycan_sequon_sites is None:
try:
self._n_glycan_sequon_sites = sequence.find_n_glycosylation_sequons(
self.protein_sequence)
except residue.UnknownAminoAcidException:
return []
return self._n_glycan_sequon_sites
def n_glycan_sequon_sites(peptide, protein, use_local_sequence=False):
sites = set()
sites |= set(site - peptide.start_position for site in span_test(
protein.n_glycan_sequon_sites, peptide.start_position, peptide.end_position))
if use_local_sequence:
sites |= set(sequence.find_n_glycosylation_sequons(
peptide.modified_peptide_sequence))
return sorted(sites)
def n_glycan_sequon_sites(peptide, protein, use_local_sequence=False):
sites = set()
sites |= set(site - peptide.start_position for site in protein.n_glycan_sequon_sites
if peptide.start_position <= site < peptide.end_position)
if use_local_sequence:
sites |= set(sequence.find_n_glycosylation_sequons(
peptide.modified_peptide_sequence))
return list(sites)
def parent_sequence_aware_n_glycan_sequon_sites(peptide, protein):
sites = set(
sequence.find_n_glycosylation_sequons(
peptide.modified_peptide_sequence))
sites |= set(site - peptide.start_position
for site in protein.glycosylation_sites
if peptide.start_position <= site < peptide.end_position)
return list(sites)
def extract_proteins(self):
i = 0
for protein in ProteinFastaFileParser(self.fasta_file):
original_sequence = protein.protein_sequence
n = len(original_sequence)
if "(" in protein.protein_sequence:
try:
protein.protein_sequence = str(
reverse_sequence(protein.protein_sequence,
suffix_len=0))
except UnknownAminoAcidException:
continue
else:
protein.protein_sequence = protein.protein_sequence[::-1]
protein.hypothesis_id = self.hypothesis_id
sites = []
try:
original_sequence = PeptideSequence(original_sequence)
except UnknownAminoAcidException:
continue
try:
n_glycosites = find_n_glycosylation_sequons(original_sequence)
for n_glycosite in n_glycosites:
sites.append(
ProteinSite(name=ProteinSite.N_GLYCOSYLATION,
location=n - n_glycosite - 1))
except UnknownAminoAcidException:
pass
# See Protein._init_sites for explanation
# try:
# o_glycosites = find_o_glycosylation_sequons(original_sequence)
# for o_glycosite in o_glycosites:
# sites.append(
# ProteinSite(name=ProteinSite.O_GLYCOSYLATION, location=n - o_glycosite - 1))
# except UnknownAminoAcidException:
# pass
# try:
# gag_sites = find_glycosaminoglycan_sequons(original_sequence)
# for gag_site in gag_sites:
# sites.append(
# ProteinSite(name=ProteinSite.GAGYLATION, location=n - gag_site - 1))
# except UnknownAminoAcidException:
# pass
protein.sites.extend(sites)
self.session.add(protein)
i += 1
if i % 5000 == 0:
self.log("... %d Proteins Extracted" % (i, ))
self.session.commit()
self.session.commit()
self.log("%d Proteins Extracted" % (i, ))
return i
def n_glycan_sequon_sites(self):
if self._n_glycan_sequon_sites is None:
sites = self.sites.filter(ProteinSite.name == ProteinSite.N_GLYCOSYLATION).all()
if sites:
self._n_glycan_sequon_sites = [int(i) for i in sites]
elif self.sites.count() == 0:
try:
self._n_glycan_sequon_sites = sequence.find_n_glycosylation_sequons(self._get_sequence())
except residue.UnknownAminoAcidException:
return []
else:
return []
return self._n_glycan_sequon_sites
def extract_proteins(self):
i = 0
for protein in ProteinFastaFileParser(self.fasta_file):
original_sequence = protein.protein_sequence
n = len(original_sequence)
protein.protein_sequence = str(reverse_sequence(protein.protein_sequence, suffix_len=0))
protein.hypothesis_id = self.hypothesis_id
original_sequence = PeptideSequence(original_sequence)
try:
n_glycosites = find_n_glycosylation_sequons(original_sequence)
for n_glycosite in n_glycosites:
protein.sites.append(
ProteinSite(name=ProteinSite.N_GLYCOSYLATION, location=n - n_glycosite - 1))
except UnknownAminoAcidException:
pass
try:
o_glycosites = find_o_glycosylation_sequons(original_sequence)
for o_glycosite in o_glycosites:
protein.sites.append(
ProteinSite(name=ProteinSite.O_GLYCOSYLATION, location=n - o_glycosite - 1))
except UnknownAminoAcidException:
pass
try:
gag_sites = find_glycosaminoglycan_sequons(original_sequence)
for gag_site in gag_sites:
protein.sites.append(
ProteinSite(name=ProteinSite.GAGYLATION, location=n - gag_site - 1))
except UnknownAminoAcidException:
pass
self.session.add(protein)
i += 1
if i % 100 == 0:
self.log("... %d Proteins Extracted" % (i,))
self.session.commit()
self.session.commit()
self.log("%d Proteins Extracted" % (i,))
return i
def _init_sites(self):
try:
n_glycosites = sequence.find_n_glycosylation_sequons(self._get_sequence())
for n_glycosite in n_glycosites:
self.sites.append(
ProteinSite(name=ProteinSite.N_GLYCOSYLATION, location=n_glycosite))
except residue.UnknownAminoAcidException:
pass
try:
o_glycosites = sequence.find_o_glycosylation_sequons(self._get_sequence())
for o_glycosite in o_glycosites:
self.sites.append(
ProteinSite(name=ProteinSite.O_GLYCOSYLATION, location=o_glycosite))
except residue.UnknownAminoAcidException:
pass
try:
gag_sites = sequence.find_glycosaminoglycan_sequons(self._get_sequence())
for gag_site in gag_sites:
self.sites.append(
ProteinSite(name=ProteinSite.GAGYLATION, location=gag_site))
except residue.UnknownAminoAcidException:
pass