def create_g_proteins(self, filenames=False):
self.logger.info('CREATING GPROTEINS')
self.purge_data()
translation = {'Gs family':'100_000_001', 'Gi/Go family':'100_000_002', 'Gq/G11 family':'100_000_003','G12/G13 family':'100_000_004',}
# read source files
if not filenames:
filenames = [fn for fn in os.listdir(self.gprotein_data_dir) if fn.endswith('.csv')]
for filename in filenames:
filepath = os.sep.join([self.gprotein_data_dir, filename])
with open(filepath, 'r') as f:
reader = csv.reader(f)
for row in reader:
entry_name = row[4]
primary = row[8]
secondary = row[9]
# fetch protein
try:
p = Protein.objects.get(entry_name=entry_name)
except Protein.DoesNotExist:
self.logger.warning('Protein not found for entry_name {}'.format(entry_name))
print('error',entry_name)
continue
primary = primary.replace("G protein (identity unknown)","None") #replace none
primary = primary.split(", ")
secondary = secondary.replace("G protein (identity unknown)","None") #replace none
secondary = secondary.split(", ")
if primary=='None' and secondary=='None':
print('no data for ',entry_name)
continue
for gp in primary:
if gp in ['None','_-arrestin','Arrestin','G protein independent mechanism']: #skip bad ones
continue
g = ProteinGProtein.objects.get_or_create(name=gp, slug=translation[gp])[0]
gpair = ProteinGProteinPair(protein=p, g_protein=g, transduction='primary')
gpair.save()
for gp in secondary:
if gp in ['None','_-arrestin','Arrestin','G protein independent mechanism', '']: #skip bad ones
continue
if gp in primary: #sip those that were already primary
continue
g = ProteinGProtein.objects.get_or_create(name=gp, slug=translation[gp])[0]
gpair = ProteinGProteinPair(protein=p, g_protein=g, transduction='secondary')
gpair.save()
self.logger.info('COMPLETED CREATING G PROTEINS')
def create_g_proteins(self, filenames=False):
self.logger.info('CREATING GPROTEINS')
# read source files
if not filenames:
filenames = os.listdir(self.gprotein_data_dir)
for filename in filenames:
filepath = os.sep.join([self.gprotein_data_dir, filename])
with open(filepath, 'r') as f:
reader = csv.reader(f)
for row in reader:
entry_name = row[4]
primary = row[8]
secondary = row[9]
# fetch protein
try:
p = Protein.objects.get(entry_name=entry_name)
except Protein.DoesNotExist:
self.logger.warning(
'Protein not found for entry_name {}'.format(
entry_name))
print('error', entry_name)
continue
primary = primary.replace("G protein (identity unknown)",
"None") #replace none
primary = primary.split(", ")
secondary = secondary.replace(
"G protein (identity unknown)", "None") #replace none
secondary = secondary.split(", ")
#print(entry_name,primary,"|",secondary)
if primary == 'None' and secondary == 'None':
print('no data for ', entry_name)
continue
for gp in primary:
if gp in [
'None', '_-arrestin', 'Arrestin',
'G protein independent mechanism'
]: #skip bad ones
continue
g = ProteinGProtein.objects.get_or_create(
name=gp, sequence='')[0]
print(p, g)
gpair = ProteinGProteinPair(protein=p,
g_protein=g,
transduction='primary')
gpair.save()
for gp in secondary:
if gp in [
'None', '_-arrestin', 'Arrestin',
'G protein independent mechanism', ''
]: #skip bad ones
continue
if gp in primary: #sip those that were already primary
continue
g = ProteinGProtein.objects.get_or_create(
name=gp, sequence='')[0]
print(p, g)
gpair = ProteinGProteinPair(protein=p,
g_protein=g,
transduction='secondary')
gpair.save()
# if p:
# # create a link
# link, created = WebLink.objects.get_or_create(web_resource=resource, index=link_index)
# if created:
# num_created_links += 1
# # add the link to this protein
# p.web_links.add(link)
# if num_created_links:
# self.logger.info('Created {} web links for resource {}'.format(num_created_links, resource.name))
self.logger.info('COMPLETED CREATING LINKS')
def create_g_proteins(self, filenames=False):
self.logger.info('CREATING GPROTEINS')
# read source files
if not filenames:
filenames = os.listdir(self.gprotein_data_dir)
for filename in filenames:
filepath = os.sep.join([self.gprotein_data_dir, filename])
with open(filepath, 'r') as f:
reader = csv.reader(f)
for row in reader:
entry_name = row[4]
primary = row[8]
secondary = row[9]
# fetch protein
try:
p = Protein.objects.get(entry_name=entry_name)
except Protein.DoesNotExist:
self.logger.warning('Protein not found for entry_name {}'.format(entry_name))
print('error',entry_name)
continue
primary = primary.replace("G protein (identity unknown)","None") #replace none
primary = primary.split(", ")
secondary = secondary.replace("G protein (identity unknown)","None") #replace none
secondary = secondary.split(", ")
#print(entry_name,primary,"|",secondary)
if primary=='None' and secondary=='None':
print('no data for ',entry_name)
continue
for gp in primary:
if gp in ['None','_-arrestin','Arrestin','G protein independent mechanism']: #skip bad ones
continue
g = ProteinGProtein.objects.get_or_create(name=gp, sequence = '')[0]
print(p,g)
gpair = ProteinGProteinPair(protein=p,g_protein=g,transduction='primary')
gpair.save()
for gp in secondary:
if gp in ['None','_-arrestin','Arrestin','G protein independent mechanism', '']: #skip bad ones
continue
if gp in primary: #sip those that were already primary
continue
g = ProteinGProtein.objects.get_or_create(name=gp, sequence = '')[0]
print(p,g)
gpair = ProteinGProteinPair(protein=p,g_protein=g,transduction='secondary')
gpair.save()
# if p:
# # create a link
# link, created = WebLink.objects.get_or_create(web_resource=resource, index=link_index)
# if created:
# num_created_links += 1
# # add the link to this protein
# p.web_links.add(link)
# if num_created_links:
# self.logger.info('Created {} web links for resource {}'.format(num_created_links, resource.name))
self.logger.info('COMPLETED CREATING LINKS')