def build_database(connection):
"""Build the hpo database
Args:
conn (sqlite3.connect): A database connection object
"""
logger.info("Fetching disease to gene file")
disease_to_genes = getreader('utf-8')(gzip.open(disease_to_genes_path),
errors='replace')
logger.info("Fetching phenotypes file")
phenotype_to_genes = getreader('utf-8')(gzip.open(phenotypes_path),
errors='replace')
logger.info("Fetching genes file")
genes = getreader('utf-8')(gzip.open(genes_path), errors='replace')
logger.info("Parsing phenotypes to gene file")
phenotypes = parse_phenotypes(phenotype_to_genes)
logger.info("Parsing disease to gene file")
diseases = parse_diseases(disease_to_genes)
logger.info("Parsing genes file")
genes = parse_genes(genes)
logger.info("Populating hpo table")
populate_hpo(connection=connection, hpo_terms=phenotypes)
logger.debug("Hpo table populated")
logger.info("Populating disease table")
populate_disease(connection=connection, disease_terms=diseases)
logger.debug("Disease table populated")
logger.info("Populating gene table")
populate_genes(connection=connection, genes=genes)
logger.debug("Gene table populated")
def mim_terms(request):
"""Get mim terms"""
mim_lines = [
"#Format: diseaseId<tab>gene-symbol<tab>gene-id(entrez)<tab>HPO-ID<tab>HPO-term-name",
"OMIM:600920\tSCARF2\t91179\tHP:0000767\tPectus excavatum",
"OMIM:600920\tSCARF2\t91179\tHP:0003042\tElbow dislocation",
"OMIM:600920\tSCARF2\t91179\tHP:0005280\tDepressed nasal bridge",
"OMIM:600920\tSCARF2\t91179\tHP:0001363\tCraniosynostosis",
"OMIM:600920\tSCARF2\t91179\tHP:0000772\tAbnormality of the ribs",
"OMIM:600920\tSCARF2\t91179\tHP:0001195\tSingle umbilical artery",
"OMIM:600920\tSCARF2\t91179\tHP:0002987\tElbow flexion contracture",
"OMIM:613376\tHSPB3\t8988\tHP:0000006\tAutosomal dominant inheritance",
"OMIM:613376\tHSPB3\t8988\tHP:0002355\tDifficulty walking",
"OMIM:613376\tHSPB3\t8988\tHP:0002600\tHyporeflexia of lower limbs",
"OMIM:613376\tHSPB3\t8988\tHP:0003445\tEMG: neuropathic changes",
"OMIM:613376\tHSPB3\t8988\tHP:0009830\tPeripheral neuropathy",
"OMIM:613376\tHSPB3\t8988\tHP:0003376\tSteppage gait",
"OMIM:613376\tHSPB3\t8988\tHP:0009053\tDistal lower limb muscle weakness",
"OMIM:613376\tHSPB3\t8988\tHP:0008959\tDistal upper limb muscle weakness",
"OMIM:613376\tHSPB3\t8988\tHP:0002522\tAreflexia of lower limbs",
"OMIM:613376\tHSPB3\t8988\tHP:0003677\tSlow progression",
"OMIM:613376\tHSPB3\t8988\tHP:0003202\tSkeletal muscle atrophy",
"OMIM:615206\tCARD11\t84433\tHP:0004313\tDecreased antibody level in blood",
"OMIM:615206\tCARD11\t84433\tHP:0003593\tInfantile onset",
"OMIM:615206\tCARD11\t84433\tHP:0002205\tRecurrent respiratory infections",
"OMIM:615206\tCARD11\t84433\tHP:0002721\tImmunodeficiency",
"OMIM:615206\tCARD11\t84433\tHP:0000007\tAutosomal recessive inheritance",
]
return parse_diseases(mim_lines)
def build_database(connection):
"""Build the hpo database
Args:
conn (sqlite3.connect): A database connection object
"""
logger.info("Fetching disease to gene file")
disease_to_genes = getreader('utf-8')(
gzip.open(disease_to_genes_path), errors='replace')
logger.info("Fetching phenotypes file")
phenotype_to_genes = getreader('utf-8')(
gzip.open(phenotypes_path), errors='replace')
logger.info("Fetching genes file")
genes = getreader('utf-8')(
gzip.open(genes_path), errors='replace')
logger.info("Parsing phenotypes to gene file")
phenotypes = parse_phenotypes(phenotype_to_genes)
logger.info("Parsing disease to gene file")
diseases = parse_diseases(disease_to_genes)
logger.info("Parsing genes file")
genes = parse_genes(genes)
logger.info("Populating hpo table")
populate_hpo(
connection=connection,
hpo_terms=phenotypes
)
logger.debug("Hpo table populated")
logger.info("Populating disease table")
populate_disease(
connection=connection,
disease_terms=diseases
)
logger.debug("Disease table populated")
logger.info("Populating gene table")
populate_genes(
connection=connection,
genes=genes
)
logger.debug("Gene table populated")
