def test_load_transcripts(adapter, gene_bulk, transcripts_handle):
# GIVEN a empty database
assert sum(1 for i in adapter.all_genes()) == 0
assert sum(1 for i in adapter.transcripts()) == 0
# WHEN inserting a number of genes and some transcripts
adapter.load_hgnc_bulk(gene_bulk)
load_transcripts(adapter, transcripts_lines=transcripts_handle, build="37")
# THEN assert all genes have been added to the database
assert sum(1 for i in adapter.all_genes()) == len(gene_bulk)
# THEN assert that the transcripts where loaded loaded
assert sum(1 for i in adapter.transcripts()) > 0
def test_load_transcripts(adapter, gene_bulk, transcripts_handle):
# GIVEN a empty database
assert adapter.all_genes().count() == 0
assert adapter.transcripts().count() == 0
# WHEN inserting a number of genes and some transcripts
adapter.load_hgnc_bulk(gene_bulk)
load_transcripts(adapter, transcripts_lines=transcripts_handle, build='37')
# THEN assert all genes have been added to the database
assert adapter.all_genes().count() == len(gene_bulk)
# THEN assert that the transcripts where loaded loaded
assert adapter.transcripts().count() > 0
def test_load_transcripts_request(adapter, gene_bulk, transcripts_df):
# GIVEN a empty database
assert adapter.all_genes().count() == 0
assert adapter.transcripts().count() == 0
# WHEN inserting a number of genes and some transcripts
adapter.load_hgnc_bulk(gene_bulk)
load_transcripts(adapter, transcripts_lines=transcripts_df, build='37')
# THEN assert all genes have been added to the database
assert adapter.all_genes().count() == len(gene_bulk)
# THEN assert that the transcripts where loaded loaded
assert adapter.transcripts().count() > 0
def test_load_exons(adapter, gene_bulk, transcripts_file, exons_handle):
# GIVEN a empty database
assert sum(1 for i in adapter.all_genes()) == 0
assert sum(1 for i in adapter.transcripts()) == 0
assert sum(1 for i in adapter.exons()) == 0
# WHEN inserting a number of genes and some transcripts and the exons
adapter.load_hgnc_bulk(gene_bulk)
transcripts_handle = get_file_handle(transcripts_file)
load_transcripts(adapter, transcripts_handle, build="37")
adapter.transcript_collection.create_index([("build", pymongo.ASCENDING),
("hgnc_id", pymongo.ASCENDING)
])
load_exons(adapter, exons_handle, build="37", nr_exons=19826)
assert sum(1 for i in adapter.exons()) > 1
def gene_database(request, institute_database, genes):
"Returns an adapter to a database populated with user, institute, case and genes"
adapter = institute_database
gene_objs = load_hgnc_genes(adapter=adapter, genes=genes, build='37')
LOG.info("Creating index on hgnc collection")
adapter.hgnc_collection.create_index([('build', pymongo.ASCENDING),
('hgnc_symbol', pymongo.ASCENDING)])
transcripts_handle = get_file_handle(transcripts37_reduced_path)
load_transcripts(adapter, transcripts_handle, build='37')
adapter.transcript_collection.create_index([('build', pymongo.ASCENDING),
('hgnc_id', pymongo.ASCENDING)
])
LOG.info("Index done")
return adapter
def load_hgnc(
adapter,
genes=None,
ensembl_lines=None,
hgnc_lines=None,
exac_lines=None,
mim2gene_lines=None,
genemap_lines=None,
hpo_lines=None,
transcripts_lines=None,
build="37",
omim_api_key="",
):
"""Load Genes and transcripts into the database
If no resources are provided the correct ones will be fetched.
Args:
adapter(scout.adapter.MongoAdapter)
genes(dict): If genes are already parsed
ensembl_lines(iterable(str)): Lines formated with ensembl gene information
hgnc_lines(iterable(str)): Lines with gene information from genenames.org
exac_lines(iterable(str)): Lines with information pLi-scores from ExAC
mim2gene(iterable(str)): Lines with map from omim id to gene symbol
genemap_lines(iterable(str)): Lines with information of omim entries
hpo_lines(iterable(str)): Lines information about map from hpo terms to genes
transcripts_lines(iterable): iterable with ensembl transcript lines
build(str): What build to use. Defaults to '37'
"""
gene_objs = load_hgnc_genes(
adapter=adapter,
genes=genes,
ensembl_lines=ensembl_lines,
hgnc_lines=hgnc_lines,
exac_lines=exac_lines,
mim2gene_lines=mim2gene_lines,
genemap_lines=genemap_lines,
hpo_lines=hpo_lines,
build=build,
omim_api_key=omim_api_key,
)
ensembl_genes = {}
for gene_obj in gene_objs:
ensembl_genes[gene_obj["ensembl_id"]] = gene_obj
transcript_objs = load_transcripts(
adapter=adapter,
transcripts_lines=transcripts_lines,
build=build,
ensembl_genes=ensembl_genes,
)
