def __init__(self,
graph_type,
are_bnodes_skolemized,
data_release_version=None):
super().__init__(
graph_type=graph_type,
are_bnodes_skolemized=are_bnodes_skolemized,
data_release_version=data_release_version,
name='omia',
ingest_title='Online Mendelian Inheritance in Animals',
ingest_url='https://omia.org',
ingest_logo='source-omia.png',
# ingest_desc=None,
license_url=None,
data_rights='http://sydney.edu.au/disclaimer.shtml',
# file_handle=None
)
self.id_hash = {
'article': {},
'phene': {},
'breed': {},
'taxon': {},
'gene': {}
}
self.label_hash = {}
# used to store the omia to omim phene mappings
self.omia_omim_map = {}
# used to store the unique genes that have phenes
# (for fetching orthology)
self.annotated_genes = set()
self.test_ids = {
'disease': [
'OMIA:001702', 'OMIA:001867', 'OMIA:000478', 'OMIA:000201',
'OMIA:000810', 'OMIA:001400'
],
'gene': [
'492297', '434', '492296', '3430235', '200685834', '394659996',
'200685845', '28713538', '291822383'
],
'taxon': [
'9691', '9685', '9606', '9615', '9913', '93934', '37029',
'9627', '9825'
],
# to be filled in during parsing of breed table
# for lookup by breed-associations
'breed': []
}
# to store a map of omia ids and any molecular info
# to write a report for curation
self.stored_omia_mol_gen = {}
self.graph = self.graph
self.ncbi = NCBIGene(self.graph_type, self.are_bnodes_skized)
def fetch(self, is_dl_forced=False):
"""
:param is_dl_forced:
:return:
"""
self.get_files(is_dl_forced)
ncbi = NCBIGene(self.graph_type, self.are_bnodes_skized)
# ncbi.fetch()
gene_group = ncbi.files['gene_group']
self.fetch_from_url(gene_group['url'], '/'.join(
(ncbi.rawdir, gene_group['file'])), False)
def fetch(self, is_dl_forced=False):
"""
:param is_dl_forced:
:return:
"""
self.get_files(is_dl_forced)
ncbi = NCBIGene(self.graph_type, self.are_bnodes_skized)
# ncbi.fetch()
gene_group = ncbi.files['gene_group']
self.fetch_from_url(gene_group['url'], '/'.join(
(ncbi.rawdir, gene_group['file'])), False)
# load and tag a list of OMIM IDs with types
# side effect of populating omim replaced
self.omim_type = self.find_omim_type()
return
def parse(self, limit=None):
# names of tables to iterate - probably don't need all these:
# Article_Breed, Article_Keyword, Article_Gene, Article_Keyword,
# Article_People, Article_Phene, Articles, Breed, Breed_Phene,
# Genes_gb, Group_Categories, Group_MPO, Inherit_Type, Keywords,
# Landmark, Lida_Links, OMIA_Group, OMIA_author, Omim_Xref, People,
# Phene, Phene_Gene, Publishers, Resources, Species_gb, Synonyms
self.scrub()
if limit is not None:
logger.info("Only parsing first %d rows", limit)
logger.info("Parsing files...")
if self.testOnly:
self.testMode = True
if self.testMode:
self.g = self.testgraph
else:
self.g = self.graph
# we do three passes through the file
# first process species (two others reference this one)
self.process_species(limit)
# then, process the breeds, genes, articles, and other static stuff
self.process_classes(limit)
# next process the association data
self.process_associations(limit)
# process the vertebrate orthology for genes
# that are annotated with phenotypes
ncbi = NCBIGene(self.graph_type, self.are_bnodes_skized)
ncbi.add_orthologs_by_gene_group(self.g, self.annotated_genes)
logger.info("Done parsing.")
self.write_molgen_report()
return
def setUp(self):
self.source = NCBIGene('rdf_graph', True)
self.source.settestonly(True)
self._setDirToSource()
return
def setUp(self):
self.source = NCBIGene('rdf_graph', True)
self.source.test_ids = self._get_conf()['test_ids']['gene']
self.source.settestonly(True)
self._setDirToSource()
return
