def can_create_arrestins(self, family, residue_numbering_scheme, accession,
uniprot):
# get/create protein source
try:
source, created = ProteinSource.objects.get_or_create(
name=uniprot['source'], defaults={'name': uniprot['source']})
if created:
self.logger.info('Created protein source ' + source.name)
except IntegrityError:
source = ProteinSource.objects.get(name=uniprot['source'])
# get/create species
try:
species, created = Species.objects.get_or_create(
latin_name=uniprot['species_latin_name'],
defaults={
'common_name': uniprot['species_common_name'],
})
if created:
self.logger.info('Created species ' + species.latin_name)
except IntegrityError:
species = Species.objects.get(
latin_name=uniprot['species_latin_name'])
# get/create protein sequence type
# Wild-type for all sequences from source file
try:
sequence_type, created = ProteinSequenceType.objects.get_or_create(
slug='wt', defaults={
'slug': 'wt',
'name': 'Wild-type',
})
if created:
self.logger.info('Created protein sequence type Wild-type')
except:
self.logger.error(
'Failed creating protein sequence type Wild-type')
# create protein
p = Protein()
p.family = family
p.species = species
p.source = source
p.residue_numbering_scheme = residue_numbering_scheme
p.sequence_type = sequence_type
if accession:
p.accession = accession
p.entry_name = uniprot['entry_name'].lower()
p.name = uniprot['names'][0]
p.sequence = uniprot['sequence']
try:
p.save()
self.logger.info('Created protein {}'.format(p.entry_name))
except:
self.logger.error('Failed creating protein {}'.format(
p.entry_name))
# protein aliases
for i, alias in enumerate(uniprot['names']):
pcan = Protein.objects.get(
entry_name=uniprot['entry_name'].lower())
a = ProteinAlias()
a.protein = pcan
a.name = alias
a.position = i
try:
a.save()
self.logger.info('Created protein alias ' + a.name +
' for protein ' + p.name)
except:
self.logger.error('Failed creating protein alias ' + a.name +
' for protein ' + p.name)
# genes
for i, gene in enumerate(uniprot['genes']):
g = False
try:
g, created = Gene.objects.get_or_create(name=gene,
species=species,
position=i)
if created:
self.logger.info('Created gene ' + g.name +
' for protein ' + p.name)
except IntegrityError:
g = Gene.objects.get(name=gene, species=species, position=i)
if g:
pcan = Protein.objects.get(
entry_name=uniprot['entry_name'].lower())
g.proteins.add(pcan)
# structures
for i, structure in enumerate(uniprot['structures']):
try:
res = structure[1]
if res == '-':
res = 0
structure, created = SignprotStructure.objects.get_or_create(
PDB_code=structure[0], resolution=res)
if created:
self.logger.info('Created structure ' +
structure.PDB_code + ' for protein ' +
p.name)
except IntegrityError:
self.logger.error('Failed creating structure ' +
structure.PDB_code + ' for protein ' +
p.name)
if g:
pcan = Protein.objects.get(
entry_name=uniprot['entry_name'].lower())
structure.origin.add(pcan)
structure.save()
def create_protein(self, name, family, sequence_type,
residue_numbering_scheme, accession, uniprot):
# get/create protein source
try:
source, created = ProteinSource.objects.get_or_create(
name=uniprot['source'], defaults={'name': uniprot['source']})
if created:
self.logger.info('Created protein source ' + source.name)
except IntegrityError:
source = ProteinSource.objects.get(name=uniprot['source'])
# get/create species
try:
species, created = Species.objects.get_or_create(
latin_name=uniprot['species_latin_name'],
defaults={
'common_name': uniprot['species_common_name'],
})
if created:
self.logger.info('Created species ' + species.latin_name)
except IntegrityError:
species = Species.objects.get(
latin_name=uniprot['species_latin_name'])
# create protein
p = Protein()
p.family = family
p.species = species
p.source = source
p.residue_numbering_scheme = residue_numbering_scheme
p.sequence_type = sequence_type
if accession:
p.accession = accession
p.entry_name = uniprot['entry_name']
p.name = name
p.sequence = uniprot['sequence']
try:
p.save()
self.logger.info('Created protein {}'.format(p.entry_name))
except:
self.logger.error('Failed creating protein {}'.format(
p.entry_name))
# protein conformations
try:
ps, created = ProteinState.objects.get_or_create(
slug=settings.DEFAULT_PROTEIN_STATE,
defaults={'name': settings.DEFAULT_PROTEIN_STATE.title()})
except IntegrityError:
ps = ProteinState.objects.get(slug=settings.DEFAULT_PROTEIN_STATE)
pc = ProteinConformation.objects.create(protein=p, state=ps)
# protein aliases
for i, alias in enumerate(uniprot['names']):
a = ProteinAlias()
a.protein = p
a.name = alias
a.position = i
try:
a.save()
self.logger.info('Created protein alias ' + a.name +
' for protein ' + p.name)
except:
self.logger.error('Failed creating protein alias ' + a.name +
' for protein ' + p.name)
# genes
for i, gene in enumerate(uniprot['genes']):
g = False
try:
g, created = Gene.objects.get_or_create(name=gene,
species=species,
position=i)
if created:
self.logger.info('Created gene ' + g.name +
' for protein ' + p.name)
except IntegrityError:
g = Gene.objects.get(name=gene, species=species, position=i)
if g:
g.proteins.add(p)
def cgn_creat_gproteins(self, family, residue_numbering_scheme, accession, uniprot):
# get/create protein source
try:
source, created = ProteinSource.objects.get_or_create(name=uniprot['source'],
defaults={'name': uniprot['source']})
if created:
self.logger.info('Created protein source ' + source.name)
except IntegrityError:
source = ProteinSource.objects.get(name=uniprot['source'])
# get/create species
try:
species, created = Species.objects.get_or_create(latin_name=uniprot['species_latin_name'],
defaults={
'common_name': uniprot['species_common_name'],
})
if created:
self.logger.info('Created species ' + species.latin_name)
except IntegrityError:
species = Species.objects.get(latin_name=uniprot['species_latin_name'])
# get/create protein sequence type
# Wild-type for all sequences from source file
try:
sequence_type, created = ProteinSequenceType.objects.get_or_create(slug='wt',
defaults={
'slug': 'wt',
'name': 'Wild-type',
})
if created:
self.logger.info('Created protein sequence type Wild-type')
except:
self.logger.error('Failed creating protein sequence type Wild-type')
# create protein
p = Protein()
p.family = family
p.species = species
p.source = source
p.residue_numbering_scheme = residue_numbering_scheme
p.sequence_type = sequence_type
if accession:
p.accession = accession
p.entry_name = uniprot['entry_name'].lower()
p.name = uniprot['names'][0].split('Guanine nucleotide-binding protein ')[1]
p.sequence = uniprot['sequence']
try:
p.save()
self.logger.info('Created protein {}'.format(p.entry_name))
except:
self.logger.error('Failed creating protein {}'.format(p.entry_name))
# protein aliases
for i, alias in enumerate(uniprot['names']):
pcgn = Protein.objects.get(entry_name=uniprot['entry_name'].lower())
a = ProteinAlias()
a.protein = pcgn
a.name = alias
a.position = i
try:
a.save()
self.logger.info('Created protein alias ' + a.name + ' for protein ' + p.name)
except:
self.logger.error('Failed creating protein alias ' + a.name + ' for protein ' + p.name)
# genes
for i, gene in enumerate(uniprot['genes']):
g = False
try:
g, created = Gene.objects.get_or_create(name=gene, species=species, position=i)
if created:
self.logger.info('Created gene ' + g.name + ' for protein ' + p.name)
except IntegrityError:
g = Gene.objects.get(name=gene, species=species, position=i)
if g:
pcgn = Protein.objects.get(entry_name=uniprot['entry_name'].lower())
g.proteins.add(pcgn)
# structures
for i, structure in enumerate(uniprot['structures']):
try:
res = structure[1]
if res == '-':
res = 0
structure, created = SignprotStructure.objects.get_or_create(PDB_code=structure[0], resolution=res)
if created:
self.logger.info('Created structure ' + structure.PDB_code + ' for protein ' + p.name)
except IntegrityError:
self.logger.error('Failed creating structure ' + structure.PDB_code + ' for protein ' + p.name)
if g:
pcgn = Protein.objects.get(entry_name=uniprot['entry_name'].lower())
structure.origin.add(pcgn)
structure.save()
def create_protein(self, name, family, sequence_type, residue_numbering_scheme, accession, uniprot):
# get/create protein source
try:
source, created = ProteinSource.objects.get_or_create(name=uniprot['source'],
defaults={'name': uniprot['source']})
if created:
self.logger.info('Created protein source ' + source.name)
except IntegrityError:
source = ProteinSource.objects.get(name=uniprot['source'])
# get/create species
try:
species, created = Species.objects.get_or_create(latin_name=uniprot['species_latin_name'],
defaults={
'common_name': uniprot['species_common_name'],
})
if created:
self.logger.info('Created species ' + species.latin_name)
except IntegrityError:
species = Species.objects.get(latin_name=uniprot['species_latin_name'])
# create protein
p = Protein()
p.family = family
p.species = species
p.source = source
p.residue_numbering_scheme = residue_numbering_scheme
p.sequence_type = sequence_type
if accession:
p.accession = accession
p.entry_name = uniprot['entry_name']
p.name = name
p.sequence = uniprot['sequence']
try:
p.save()
self.logger.info('Created protein {}'.format(p.entry_name))
except Exception as e:
self.logger.error('Failed creating protein {} {}'.format(p.entry_name, str(e)))
# protein conformations
try:
ps, created = ProteinState.objects.get_or_create(slug=settings.DEFAULT_PROTEIN_STATE,
defaults={'name': settings.DEFAULT_PROTEIN_STATE.title()})
except IntegrityError:
ps = ProteinState.objects.get(slug=settings.DEFAULT_PROTEIN_STATE)
pc = ProteinConformation.objects.create(protein=p, state=ps)
# protein aliases
for i, alias in enumerate(uniprot['names']):
a = ProteinAlias()
a.protein = p
a.name = alias
a.position = i
try:
a.save()
self.logger.info('Created protein alias ' + a.name + ' for protein ' + p.name)
except:
self.logger.error('Failed creating protein alias ' + a.name + ' for protein ' + p.name)
# genes
for i, gene in enumerate(uniprot['genes']):
g = False
try:
g, created = Gene.objects.get_or_create(name=gene, species=species, position=i)
if created:
self.logger.info('Created gene ' + g.name + ' for protein ' + p.name)
except IntegrityError:
g = Gene.objects.get(name=gene, species=species, position=i)
if g:
g.proteins.add(p)