def generate_hgnc(genes):
"""Generate lines from a file with reduced hgnc information
Args:
genes(dict): A dictionary with hgnc_id as key and hgnc_symbol as value
outpath(str): Defaults to hgnc_reduced_path
Yields:
print_line(str): Lines from the reduced file
"""
LOG.info("Generating new hgnc reduced file")
# fetch the latest hgnc file here
hgnc_gene_lines = fetch_hgnc()
header = None
genes_found = 0
# Loop over all hgnc gene lines
for i, line in enumerate(hgnc_gene_lines):
line = line.rstrip()
# Skip lines that are empty
if not len(line) > 0:
continue
# If we are reading the header, print it
if i == 0:
header = line.split('\t')
yield line
continue
# Parse the hgnc gene line
gene = parse_hgnc_line(line, header)
if not gene:
continue
hgnc_id = int(gene['hgnc_id'])
# Check if the gene is in the reduced
if hgnc_id in genes:
genes_found += 1
yield line
LOG.info("Number of genes printed to file: %s", genes_found)
def generate_hgnc(genes):
"""Generate lines from a file with reduced hgnc information
Args:
genes(dict): A dictionary with hgnc_id as key and hgnc_symbol as value
outpath(str): Defaults to hgnc_reduced_path
Yields:
print_line(str): Lines from the reduced file
"""
LOG.info("Generating new hgnc reduced file")
# fetch the latest hgnc file here
hgnc_gene_lines = fetch_hgnc()
header = None
genes_found = 0
# Loop over all hgnc gene lines
for i,line in enumerate(hgnc_gene_lines):
line = line.rstrip()
# Skip lines that are empty
if not len(line) > 0:
continue
# If we are reading the header, print it
if i == 0:
header = line.split('\t')
yield line
continue
# Parse the hgnc gene line
gene = parse_hgnc_line(line, header)
if not gene:
continue
hgnc_id = int(gene['hgnc_id'])
# Check if the gene is in the reduced
if hgnc_id in genes:
genes_found += 1
yield line
LOG.info("Number of genes printed to file: %s", genes_found)
def test_parse_hgnc_line(hgnc_handle):
"""Test to parse a hgnc gene line"""
header = next(hgnc_handle).split('\t')
first_gene = next(hgnc_handle)
gene_info = parse_hgnc_line(header=header, line=first_gene)
assert gene_info['hgnc_id'] == int(first_gene.split('\t')[0].split(':')[1])
def test_parse_hgnc_line(hgnc_handle):
"""Test to parse a hgnc gene line"""
header = next(hgnc_handle).split('\t')
first_gene = next(hgnc_handle)
gene_info = parse_hgnc_line(header=header, line=first_gene)
assert gene_info['hgnc_id'] == int(first_gene.split('\t')[0].split(':')[1])
def test_parse_hgnc_line(hgnc_handle):
"""Test to parse a hgnc gene line"""
header = next(hgnc_handle).split("\t")
first_gene = next(hgnc_handle)
gene_info = parse_hgnc_line(header=header, line=first_gene)
assert gene_info["hgnc_id"] == int(first_gene.split("\t")[0].split(":")[1])