def populate_organism():
def add_organism(name, accession):
# get the object, this also checks for duplicates
o, created = Organism.objects.get_or_create(name=name,
accession=accession)
return o
def merge_acc_names(accession_list):
acc_name_dict = {}
db = "nuccore"
# Doing batches of 200 to make sure requests to NCBI are not too big
for i in range(0, len(accession_list), 200):
j = i + 200
result_handle = Entrez.efetch(db=db,
rettype="gb",
id=accession_list[i:j])
# Populate result per organism name
records = SeqIO.parse(result_handle, 'genbank')
for record in tqdm(records):
# Using NCBI name, which should match accession number passed
acc_name_dict[record.name] = record.annotations['organism']
return acc_name_dict
with open(os.path.join(DATA_DIR, 'bac_accession_list.txt')) as f:
acc_name_dict = list(read_accession_file(f))
# acc_name_dict = merge_acc_names(accession_list)
for acc in acc_name_dict:
add_organism(name=acc_name_dict[acc], accession=acc)
def populate_organism():
def add_organism(name, accession):
# get the object, this also checks for duplicates
o, created = Organism.objects.get_or_create(
name=name, accession=accession)
return o
def merge_acc_names(accession_list):
acc_name_dict = {}
db = "nuccore"
# Doing batches of 200 to make sure requests to NCBI are not too big
for i in range(0, len(accession_list), 200):
j = i + 200
result_handle = Entrez.efetch(
db=db, rettype="gb", id=accession_list[i:j])
# Populate result per organism name
records = SeqIO.parse(result_handle, 'genbank')
for record in tqdm(records):
# Using NCBI name, which should match accession number passed
acc_name_dict[record.name] = record.annotations['organism']
return acc_name_dict
with open(os.path.join(DATA_DIR, 'bac_accession_list.txt')) as f:
acc_name_dict = list(read_accession_file(f))
# acc_name_dict = merge_acc_names(accession_list)
for acc in acc_name_dict:
add_organism(name=acc_name_dict[acc], accession=acc)
def populate_anticrispr():
with open(os.path.join(DATA_DIR, 'antiCRISPR_accessions.txt')) as f:
accession_list = list(read_accession_file(f))
print("Fetching AntiCRISPR entries")
result_handle = Entrez.efetch(db='protein',
rettype="fasta",
id=accession_list)
for record in tqdm(SeqIO.parse(result_handle, 'fasta')):
spacer, _ = AntiCRISPR.objects.get_or_create(accession=record.name,
sequence=str(record.seq))
spacer.save()
def populate_anticrispr():
with open(os.path.join(DATA_DIR, 'antiCRISPR_accessions.txt')) as f:
accession_list = list(read_accession_file(f))
print("Fetching AntiCRISPR entries")
result_handle = Entrez.efetch(
db='protein', rettype="fasta", id=accession_list)
for record in tqdm(SeqIO.parse(result_handle, 'fasta')):
spacer, _ = AntiCRISPR.objects.get_or_create(
accession=record.name,
sequence=str(record.seq))
spacer.save()
def test_read_accession_file_check_formatting():
f = io.StringIO("""
# comment on left
123left
345right
987middle
# comment in middle, with trailing space
# ^^ blank line
""")
assert list(read_accession_file(f)) == [
'123left',
'345right',
'987middle',
]
def test_read_accession_file_empty():
assert list(read_accession_file(io.StringIO(""))) == []