def _process_phene_gene_row(self, row):
geno = Genotype(self.graph)
model = Model(self.graph)
gene_id = self.id_hash['gene'].get(row['gene_id'])
phene_id = self.id_hash['phene'].get(row['phene_id'])
omia_id = self._get_omia_id_from_phene_id(phene_id)
if self.test_mode and not (omia_id in self.test_ids['disease']
and row['gene_id'] in self.test_ids['gene']
) or gene_id is None or phene_id is None:
return
# occasionally some phenes are missing! (ex: 406)
if phene_id is None:
LOG.warning("Phene id %s is missing", str(row['phene_id']))
return
gene_label = self.label_hash[gene_id]
# some variant of gene_id has phenotype d
var = self.make_id(gene_id.split(':')[-1] + 'VL', '_')
geno.addAllele(var, 'some variant of ' + gene_label)
geno.addAlleleOfGene(var, gene_id)
geno.addAffectedLocus(var, gene_id)
model.addBlankNodeAnnotation(var)
assoc = G2PAssoc(self.graph, self.name, var, phene_id)
assoc.add_association_to_graph()
# add the gene id to the set of annotated genes
# for later lookup by orthology
self.annotated_genes.add(gene_id)
def parse(self, limit=None):
"""
Override Source.parse()
Parses version and interaction information from CTD
Args:
:param limit (int, optional) limit the number of rows processed
Returns:
:return None
"""
if limit is not None:
LOG.info("Only parsing first %d rows", limit)
LOG.info("Parsing files...")
if self.test_only:
self.test_mode = True
self.geno = Genotype(self.graph)
self.pathway = Pathway(self.graph)
src_key = 'chemical_disease_associations'
self._parse_ctd_file(limit, src_key)
# self._parse_ctd_file(limit, 'gene_pathway')
# self._parse_ctd_file(limit, 'gene_disease')
src_key = 'publications'
file_path = '/'.join((self.rawdir, self.api_fetch[src_key]['file']))
if os.path.exists(file_path) is True:
self._parse_curated_chem_disease(file_path, limit)
else:
LOG.error('Batch Query file "%s" does not exist', file_path)
LOG.info("Done parsing files.")
def _process_phene_gene_row(self, row):
geno = Genotype(self.g)
model = Model(self.g)
gene_id = self.id_hash['gene'].get(row['gene_id'])
phene_id = self.id_hash['phene'].get(row['phene_id'])
omia_id = self._get_omia_id_from_phene_id(phene_id)
if self.testMode and not (
omia_id in self.test_ids['disease'] and
row['gene_id'] in self.test_ids['gene']) or\
gene_id is None or phene_id is None:
return
# occasionally some phenes are missing! (ex: 406)
if phene_id is None:
logger.warning("Phene id %s is missing", str(row['phene_id']))
return
gene_label = self.label_hash[gene_id]
# some variant of gene_id has phenotype d
vl = '_:'+re.sub(r'NCBIGene:', '', str(gene_id)) + 'VL'
geno.addAllele(vl, 'some variant of ' + gene_label)
geno.addAlleleOfGene(vl, gene_id)
geno.addAffectedLocus(vl, gene_id)
model.addBlankNodeAnnotation(vl)
assoc = G2PAssoc(self.g, self.name, vl, phene_id)
assoc.add_association_to_graph()
# add the gene id to the set of annotated genes
# for later lookup by orthology
self.annotated_genes.add(gene_id)
return
def _add_snp_gene_relation(self, snp_id, snp_gene_nums,
upstream_gene_num, downstream_gene_num):
if self.testMode:
g = self.testgraph
else:
g = self.graph
geno = Genotype(g)
# add the feature as a sequence alteration
# affecting various genes
# note that intronic variations don't necessarily list
# the genes such as for rs10448080 FIXME
if snp_gene_nums != '':
for s in re.split(r',', snp_gene_nums):
s = s.strip()
# still have to test for this,
# because sometimes there's a leading comma
if s != '':
gene_id = 'NCBIGene:' + s
geno.addAffectedLocus(snp_id, gene_id)
# add the up and downstream genes if they are available
if upstream_gene_num != '':
downstream_gene_id = 'NCBIGene:' + downstream_gene_num
g.addTriple(
snp_id,
Feature.object_properties[
r'upstream_of_sequence_of'],
downstream_gene_id)
if downstream_gene_num != '':
upstream_gene_id = 'NCBIGene:' + upstream_gene_num
g.addTriple(
snp_id,
Feature.object_properties[
'downstream_of_sequence_of'],
upstream_gene_id)
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(
graph_type,
are_bnodes_skolemized,
'decipher',
ingest_title='Development Disorder Genotype Phenotype Database',
ingest_url='https://decipher.sanger.ac.uk/',
license_url='https://decipher.sanger.ac.uk/legal',
data_rights='https://decipher.sanger.ac.uk/datasharing',
# file_handle=None
)
if 'disease' not in self.all_test_ids:
LOG.warning("not configured with disease test ids.")
self.test_ids = []
else:
self.test_ids = self.all_test_ids['disease']
self.graph = self.graph
self.geno = Genotype(self.graph)
self.model = Model(self.graph)
self.graph_type = graph_type
self.are_bnodes_skolemized = are_bnodes_skolemized
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(
graph_type,
are_bnodes_skolemized,
'ctd',
ingest_title='Comparative Toxicogenomics Database',
ingest_url='http://ctdbase.org',
license_url=None,
data_rights='http://ctdbase.org/about/legal.jsp'
# file_handle=None
)
if 'gene' not in self.all_test_ids:
LOG.warning("not configured with gene test ids.")
self.test_geneids = []
else:
self.test_geneids = self.all_test_ids['gene']
if 'disease' not in self.all_test_ids:
LOG.warning("not configured with disease test ids.")
self.test_diseaseids = []
else:
self.test_diseaseids = self.all_test_ids['disease']
self.geno = Genotype(self.graph)
self.pathway = Pathway(self.graph)
return
def _add_snp_gene_relation(self, snp_id, snp_gene_nums, upstream_gene_num,
downstream_gene_num):
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
geno = Genotype(graph)
# add the feature as a sequence alteration
# affecting various genes
# note that intronic variations don't necessarily list
# the genes such as for rs10448080 FIXME
if snp_gene_nums != '':
for geneid in re.split(r',', snp_gene_nums):
geneid = geneid.strip()
# still have to test for this,
# because sometimes there's a leading comma
if geneid != '':
geno.addAffectedLocus(snp_id, 'ENSEMBL:' + geneid)
# add the up and downstream genes if they are available
if upstream_gene_num != '':
downstream_gene_id = 'ENSEMBL:' + downstream_gene_num
graph.addTriple(snp_id,
self.globaltt['is upstream of sequence of'],
downstream_gene_id)
if downstream_gene_num != '':
upstream_gene_id = 'ENSEMBL:' + upstream_gene_num
graph.addTriple(snp_id,
self.globaltt['is downstream of sequence of'],
upstream_gene_id)
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'ctd')
self.dataset = Dataset(
'ctd', 'CTD', 'http://ctdbase.org', None,
'http://ctdbase.org/about/legal.jsp')
if 'test_ids' not in config.get_config() \
or 'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
self.test_geneids = []
else:
self.test_geneids = config.get_config()['test_ids']['gene']
if 'test_ids' not in config.get_config() \
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_diseaseids = []
else:
self.test_diseaseids = config.get_config()['test_ids']['disease']
self.g = self.graph
self.geno = Genotype(self.graph)
self.pathway = Pathway(self.graph)
return
def _build_gene_disease_model(self,
gene_id,
relation_id,
disease_id,
variant_label,
consequence_predicate=None,
consequence_id=None,
allelic_requirement=None,
pmids=None):
"""
Builds gene variant disease model
:return: None
"""
model = Model(self.graph)
geno = Genotype(self.graph)
pmids = [] if pmids is None else pmids
is_variant = False
variant_or_gene = gene_id
variant_id_string = variant_label
variant_bnode = self.make_id(variant_id_string, "_")
if consequence_predicate is not None \
and consequence_id is not None:
is_variant = True
model.addTriple(variant_bnode, consequence_predicate,
consequence_id)
# Hack to add labels to terms that
# don't exist in an ontology
if consequence_id.startswith(':'):
model.addLabel(consequence_id,
consequence_id.strip(':').replace('_', ' '))
if is_variant:
variant_or_gene = variant_bnode
# Typically we would type the variant using the
# molecular consequence, but these are not specific
# enough for us to make mappings (see translation table)
model.addIndividualToGraph(variant_bnode, variant_label,
self.globaltt['variant_locus'])
geno.addAffectedLocus(variant_bnode, gene_id)
model.addBlankNodeAnnotation(variant_bnode)
assoc = G2PAssoc(self.graph, self.name, variant_or_gene, disease_id,
relation_id)
assoc.source = pmids
assoc.add_association_to_graph()
if allelic_requirement is not None and is_variant is False:
model.addTriple(assoc.assoc_id,
self.globaltt['has_allelic_requirement'],
allelic_requirement)
if allelic_requirement.startswith(':'):
model.addLabel(
allelic_requirement,
allelic_requirement.strip(':').replace('_', ' '))
def process_disease_association(self, limit):
raw = '/'.join((self.rawdir, self.files['disease_assoc']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
model = Model(g)
logger.info("Processing disease models")
geno = Genotype(g)
line_counter = 0
worm_taxon = 'NCBITaxon:6239'
with open(raw, 'r') as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
if re.match(r'!', ''.join(row)): # header
continue
line_counter += 1
(db, gene_num, gene_symbol, is_not, disease_id, ref,
eco_symbol, with_or_from, aspect, gene_name, gene_synonym,
gene_class, taxon, date, assigned_by, blank, blank2) = row
if self.testMode and gene_num not in self.test_ids['gene']:
continue
# TODO add NOT phenotypes
if is_not == 'NOT':
continue
# WB WBGene00000001 aap-1 DOID:2583 PMID:19029536 IEA ENSEMBL:ENSG00000145675|OMIM:615214 D Y110A7A.10 gene taxon:6239 20150612 WB
gene_id = 'WormBase:' + gene_num
# make a variant of the gene
vl = '_:' + '-'.join((gene_num, 'unspecified'))
vl_label = 'some variant of ' + gene_symbol
geno.addAffectedLocus(vl, gene_id)
model.addBlankNodeAnnotation(vl)
animal_id = geno.make_experimental_model_with_genotype(
vl, vl_label, worm_taxon, 'worm')
assoc = G2PAssoc(g, self.name, animal_id, disease_id,
model.object_properties['model_of'])
ref = re.sub(r'WB_REF:', 'WormBase:', ref)
if ref != '':
assoc.add_source(ref)
eco_id = None
if eco_symbol == 'IEA':
eco_id = 'ECO:0000501' # IEA is this now
if eco_id is not None:
assoc.add_evidence(eco_id)
assoc.add_association_to_graph()
return
def setUp(self):
self.graph = RDFGraph()
self.curie_map = curie_map.get()
self.genotype = Genotype(self.graph)
self.cutil = CurieUtil(self.curie_map)
self.test_cat_pred = self.cutil.get_uri(blv.terms['category'])
self.test_cat_genotype_category = self.cutil.get_uri(
blv.terms['Genotype'])
self.test_cat_background_category = self.cutil.get_uri(
blv.terms['PopulationOfIndividualOrganisms'])
def parse(self, limit=None):
"""
:param limit:
:return:
"""
if limit is not None:
logger.info("Only parsing first %s rows fo each file", str(limit))
logger.info("Parsing files...")
if self.testOnly:
self.testMode = True
g = self.testgraph
else:
g = self.graph
tmap = '/'.join((self.rawdir, self.files['trait_mappings']['file']))
self._process_trait_mappings(tmap, limit)
geno = Genotype(g)
# organisms = ['chicken']
organisms = [
'chicken', 'pig', 'horse', 'rainbow_trout', 'sheep', 'cattle']
for o in organisms:
tax_id = self._get_tax_by_common_name(o)
geno.addGenome(tax_id, o)
build_id = None
build = None
k = o + '_bp'
if k in self.files:
file = self.files[k]['file']
m = re.search(r'QTL_([\w\.]+)\.gff.txt.gz', file)
if m is None:
logger.error("Can't match a gff build")
else:
build = m.group(1)
build_id = self._map_build_by_abbrev(build)
logger.info("Build = %s", build_id)
geno.addReferenceGenome(build_id, build, tax_id)
if build_id is not None:
self._process_QTLs_genomic_location(
'/'.join((self.rawdir, file)), tax_id, build_id, build,
limit)
k = o+'_cm'
if k in self.files:
file = self.files[k]['file']
self._process_QTLs_genetic_location(
'/'.join((self.rawdir, file)), tax_id, o, limit)
logger.info("Finished parsing")
return
def _make_pheno_assoc(self, g, gene_id, gene_symbol, disorder_num,
disorder_label, phene_key):
geno = Genotype(g)
model = Model(g)
disorder_id = ':'.join(('OMIM', disorder_num))
rel_id = model.object_properties['has_phenotype'] # default
rel_label = 'causes'
if re.match(r'\[', disorder_label):
rel_id = model.object_properties['is_marker_for']
rel_label = 'is a marker for'
elif re.match(r'\{', disorder_label):
rel_id = model.object_properties['contributes_to']
rel_label = 'contributes to'
elif re.match(r'\?', disorder_label):
# this is a questionable mapping! skip?
rel_id = model.object_properties['contributes_to']
rel_label = 'contributes to'
evidence = self._map_phene_mapping_code_to_eco(phene_key)
# we actually want the association between the gene and the disease
# to be via an alternate locus not the "wildtype" gene itself.
# so we make an anonymous alternate locus,
# and put that in the association.
# but we only need to do that in the cases when it's not an NCBIGene
# (as that is a sequence feature itself)
if re.match(r'OMIM:', gene_id):
alt_locus = '_:' + re.sub(r':', '',
gene_id) + '-' + disorder_num + 'VL'
alt_label = gene_symbol.strip()
if alt_label is not None and alt_label != '':
alt_label = \
' '.join(('some variant of', alt_label,
'that', rel_label, disorder_label))
else:
alt_label = None
model.addIndividualToGraph(alt_locus, alt_label,
Genotype.genoparts['variant_locus'])
geno.addAffectedLocus(alt_locus, gene_id)
model.addBlankNodeAnnotation(alt_locus)
else:
# assume it's already been added
alt_locus = gene_id
assoc = G2PAssoc(g, self.name, alt_locus, disorder_id, rel_id)
assoc.add_evidence(evidence)
assoc.add_association_to_graph()
return
def _process_all(self, limit):
"""
This takes the list of omim identifiers from the omimTitles file,
excludes those designated as obsolete and iteratively queries the omim api
in batches of 20 for the json-formatted data.
This will create OMIM classes, with the label & definition.
If an entry is "removed",
it is added as a deprecated class.
If an entry is "moved",
it is deprecated and consider annotations are added.
Additionally, we extract:
*phenotypicSeries ids as superclasses
*equivalent ids for Orphanet and UMLS
If set to testMode,
it will write only those items in the test_ids to the testgraph.
:param limit:
"""
omimids = list(self.omim_type.keys() - self.omim_replaced.keys())
LOG.info('Have %i omim numbers to fetch records from their API',
len(omimids))
LOG.info('Have %i omim types ', len(self.omim_type))
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
geno = Genotype(graph)
model = Model(graph)
tax_label = 'H**o sapiens'
tax_id = self.globaltt[tax_label]
# add genome and taxon
geno.addGenome(tax_id, tax_label)
model.addClassToGraph(tax_id, tax_label)
includes = set()
includes.add('all')
self.process_entries(omimids, self._transform_entry, includes, graph,
limit)
# since we are not fetching obsolete records any more add them all in here
for omim_id in self.omim_replaced:
model.addDeprecatedClass(
'OMIM:' + omim_id,
['OMIM:' + o for o in self.omim_replaced[omim_id]])
def _process_gene_row(self, row):
model = Model(self.graph)
geno = Genotype(self.graph)
if self.test_mode and row['gene_id'] not in self.test_ids['gene']:
return
gene_id = 'NCBIGene:' + str(row['gene_id'])
self.id_hash['gene'][row['gene_id']] = gene_id
gene_label = row['symbol']
self.label_hash[gene_id] = gene_label
tax_id = 'NCBITaxon:' + str(row['gb_species_id'])
if row['gene_type'] is not None:
gene_type_id = self.resolve(row['gene_type'])
model.addClassToGraph(gene_id, gene_label, gene_type_id)
geno.addTaxon(tax_id, gene_id)
def process_gene_ids(self, limit):
src_key = 'gene_ids'
raw = '/'.join((self.rawdir, self.files[src_key]['file']))
graph = self.graph
model = Model(graph)
geno = Genotype(graph)
col = self.files[src_key]['columns']
LOG.info("Processing: %s", self.files[src_key]['file'])
with gzip.open(raw, 'rb') as csvfile:
reader = csv.reader(io.TextIOWrapper(csvfile, newline=""),
delimiter=',',
quotechar='\"')
# no header row to check
collen = len(col)
for row in reader:
if len(row) != collen:
LOG.error('In %s line %i expected %i colums but got %s.',
self.files[src_key]['file'], reader.line_num,
collen, row)
pass
taxon_num = row[col.index('taxon_num')]
gene_num = row[col.index('gene_num')]
gene_symbol = row[col.index('gene_symbol')]
gene_synonym = row[col.index('gene_synonym')]
live = row[col.index('live')]
# gene_type = row[col.index('gene_type')]
# 6239,WBGene00000001,aap-1,Y110A7A.10,Live,protein_coding_gene
taxon_curie = 'NCBITaxon:' + taxon_num
gene_curie = 'WormBase:' + gene_num
if gene_symbol == '':
gene_symbol = gene_synonym # these are not the same in my book tec.
if gene_symbol == '':
gene_symbol = None
model.addClassToGraph(gene_curie, gene_symbol,
self.globaltt['gene'])
if live == 'Dead':
model.addDeprecatedClass(gene_curie,
old_id_category=blv.terms['Gene'])
geno.addTaxon(taxon_curie, gene_curie)
if gene_synonym is not None and gene_synonym != '':
model.addSynonym(gene_curie, gene_synonym)
if limit is not None and reader.line_num > limit:
break
def _add_variant_gene_relationship(self, variant_id, hgnc_symbol):
"""
:param variant_id
:param hgnc_symbol
:return: None
"""
gu = GraphUtils(curie_map.get())
geno = Genotype(self.graph)
if hgnc_symbol in self.gene_map:
gene_id = self.gene_map[hgnc_symbol]
else:
gene_id = self.make_cgd_id("{0}{1}".format(variant_id, hgnc_symbol))
logger.warn("Can't map gene symbol {0} "
"to entrez ID".format(hgnc_symbol))
gu.addClassToGraph(self.graph, gene_id, hgnc_symbol)
geno.addAlleleOfGene(variant_id, gene_id)
return
def _process_all(self, limit):
"""
This takes the list of omim identifiers from the omim.txt.Z file,
and iteratively queries the omim api for the json-formatted data.
This will create OMIM classes, with the label,
definition, and some synonyms.
If an entry is "removed",
it is added as a deprecated class.
If an entry is "moved",
it is deprecated and consider annotations are added.
Additionally, we extract:
*phenotypicSeries ids as superclasses
*equivalent ids for Orphanet and UMLS
If set to testMode,
it will write only those items in the test_ids to the testgraph.
:param limit:
:return:
"""
omimids = self._get_omim_ids() # store the set of omim identifiers
if self.testMode:
g = self.testgraph
else:
g = self.graph
geno = Genotype(g)
model = Model(g)
# tax_num = '9606' # TODO PYLINT unused
tax_id = 'NCBITaxon:9606'
tax_label = 'Human'
# add genome and taxon
geno.addGenome(tax_id, tax_label) # tax label can get added elsewhere
model.addClassToGraph(tax_id, None) # label added elsewhere
includes = set()
includes.add('all')
self.process_entries(
omimids, self._transform_entry, includes, g, limit)
return
def process_gene_ids(self, limit):
raw = '/'.join((self.rawdir, self.files['gene_ids']['file']))
if self.testMode:
graph = self.testgraph
else:
graph = self.graph
model = Model(graph)
logger.info("Processing: %s", self.files['gene_ids']['file'])
line_counter = 0
geno = Genotype(graph)
with gzip.open(raw, 'rb') as csvfile:
filereader = csv.reader(io.TextIOWrapper(csvfile, newline=""),
delimiter=',',
quotechar='\"')
for row in filereader:
line_counter += 1
(taxon_num, gene_num, gene_symbol, gene_synonym, live,
gene_type) = row
# 6239,WBGene00000001,aap-1,Y110A7A.10,Live,protein_coding_gene
if self.testMode and gene_num not in self.test_ids['gene']:
continue
taxon_id = 'NCBITaxon:' + taxon_num
gene_id = 'WormBase:' + gene_num
if gene_symbol == '':
gene_symbol = gene_synonym
if gene_symbol == '':
gene_symbol = None
model.addClassToGraph(gene_id, gene_symbol,
self.globaltt['gene'])
if live == 'Dead':
model.addDeprecatedClass(gene_id)
geno.addTaxon(taxon_id, gene_id)
if gene_synonym != '' and gene_synonym is not None:
model.addSynonym(gene_id, gene_synonym)
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def _create_genome_builds(self):
"""
Various resources will map variations to either UCSC (hg*)
or to NCBI assemblies. Here we create the equivalences between them.
Data taken from:
https://genome.ucsc.edu/FAQ/FAQreleases.html#release1
:return:
"""
# TODO add more species
graph = self.graph
geno = Genotype(graph)
model = Model(graph)
logger.info("Adding equivalent assembly identifiers")
for sp in self.species:
tax_id = self.resolve(sp)
txid_num = tax_id.split(':')[1]
for key in self.files[txid_num]['assembly']:
ucsc_id = key
try:
ucsc_label = ucsc_id.split(':')[1]
except IndexError:
logger.error('%s Assembly id: "%s" is problematic', sp,
key)
continue
if key in self.localtt:
mapped_id = self.localtt[key]
else:
logger.error(
'%s Assembly id: "%s" is not in local translation table',
sp, key)
mapped_label = mapped_id.split(':')[1]
mapped_label = 'NCBI build ' + str(mapped_label)
geno.addReferenceGenome(ucsc_id, ucsc_label, tax_id)
geno.addReferenceGenome(mapped_id, mapped_label, tax_id)
model.addSameIndividual(ucsc_id, mapped_id)
return
def parse(self, limit=None):
if limit is not None:
LOG.info("Only parsing first %s rows", limit)
LOG.info("Parsing files...")
if self.test_only:
self.test_mode = True
self.graph = self.testgraph
else:
self.graph = self.graph
self.geno = Genotype(self.graph)
# rare disease-phenotype associations
self._process_ddg2p_annotations(limit)
LOG.info("Finished parsing.")
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'decipher')
self.dataset = Dataset(
'decipher', 'Development Disorder Genotype – Phenotype Database',
'https://decipher.sanger.ac.uk/', None,
'https://decipher.sanger.ac.uk/legal')
if 'test_ids' not in config.get_config() \
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = []
else:
self.test_ids = config.get_config()['test_ids']['disease']
self.g = self.graph
self.geno = Genotype(self.g)
self.model = Model(self.g)
return
def _parse_genepage2gene(self, limit) -> Dict[str, List[str]]:
"""
:return:
"""
src_key = 'genepage2gene'
columns = self.files[src_key]['columns']
raw = '/'.join((self.rawdir, self.files[src_key]['file']))
geno = Genotype(self.graph)
genepage2gene = {}
LOG.info("Processing GenePage to Gene file")
with open(raw, 'r', encoding="utf8") as csvfile:
reader = csv.reader(csvfile, delimiter='\t')
for row in reader:
gene_page = row[columns.index('gene_page_id')]
# gene_page_label = row[columns.index('gene_page_label')]
tropicalis_id = row[columns.index('tropicalis_id')]
tropicalis_label = row[columns.index('tropicalis_label')]
laevis_l_id = row[columns.index('laevis_l_id')]
laevis_l_label = row[columns.index('laevis_l_label')]
laevis_s_id = row[columns.index('laevis_s_id')]
laevis_s_label = row[columns.index('laevis_s_label')]
tropicalis_curie = 'Xenbase:' + tropicalis_id
laevis_l_curie = 'Xenbase:' + laevis_l_id
laevis_s_curie = 'Xenbase:' + laevis_s_id
genepage2gene[gene_page] = [tropicalis_curie, laevis_l_curie, laevis_s_curie]
geno.addGene(tropicalis_curie, tropicalis_label)
geno.addGene(laevis_l_curie, laevis_l_label)
geno.addGene(laevis_s_curie, laevis_s_label)
if not self.test_mode and limit is not None and reader.line_num > limit:
break
return genepage2gene
def parse(self, limit=None):
"""
Override Source.parse()
Parses version and interaction information from CTD
Args:
:param limit (int, optional) limit the number of rows processed
Returns:
:return None
"""
if limit is not None:
logger.info("Only parsing first %d rows", limit)
logger.info("Parsing files...")
# pub_map = dict()
# file_path = '/'.join((self.rawdir,
# self.static_files['publications']['file']))
# if os.path.exists(file_path) is True:
# pub_map = self._parse_publication_file(
# self.static_files['publications']['file']
# )
if self.testOnly:
self.testMode = True
if self.testMode:
self.g = self.testgraph
else:
self.g = self.graph
self.geno = Genotype(self.g)
self.pathway = Pathway(self.g)
self._parse_ctd_file(
limit, self.files['chemical_disease_interactions']['file'])
self._parse_ctd_file(limit, self.files['gene_pathway']['file'])
self._parse_ctd_file(limit, self.files['gene_disease']['file'])
self._parse_curated_chem_disease(limit)
logger.info("Done parsing files.")
return
def parse(self, limit=None):
"""
Override Source.parse()
Parses version and interaction information from CTD
Args:
:param limit (int, optional) limit the number of rows processed
Returns:
:return None
"""
if limit is not None:
LOG.info("Only parsing first %d rows", limit)
LOG.info("Parsing files...")
if self.test_only:
self.test_mode = True
self.geno = Genotype(self.graph)
self.pathway = Pathway(self.graph)
src_key = 'chemical_disease_associations'
self._parse_ctd_file(limit, src_key)
def _add_gene_anatomy_association(self, gene_id, anatomy_curie, rank):
"""
:param gene_id: str Non curified ID
:param gene_label: str Gene symbol
:param anatomy_curie: str curified anatomy term
:param rank: str rank
:return: None
"""
g2a_association = Assoc(self.graph, self.name)
genotype = Genotype(self.graph)
model = Model(self.graph)
gene_curie = "ENSEMBL:{}".format(gene_id)
rank = re.sub(r',', '', rank)
model.addIndividualToGraph(ind_id=gene_curie, label=None,
ind_type=genotype.genoparts['gene'])
g2a_association.sub = gene_curie
g2a_association.obj = anatomy_curie
g2a_association.rel = Assoc.object_properties['expressed_in']
g2a_association.add_association_to_graph()
g2a_association.add_predicate_object(
Assoc.datatype_properties['has_quantifier'],
float(rank), 'Literal', 'xsd:float')
return
def _add_g2p_assoc(self, graph, strain_id, sex, assay_id, phenotypes,
comment):
"""
Create an association between a sex-specific strain id
and each of the phenotypes.
Here, we create a genotype from the strain,
and a sex-specific genotype.
Each of those genotypes are created as anonymous nodes.
The evidence code is hardcoded to be:
ECO:experimental_phenotypic_evidence.
:param g:
:param strain_id:
:param sex:
:param assay_id:
:param phenotypes: a list of phenotypes to association with the strain
:param comment:
:return:
"""
geno = Genotype(graph)
model = Model(graph)
eco_id = self.globaltt['experimental phenotypic evidence']
strain_label = self.idlabel_hash.get(strain_id)
# strain genotype
genotype_id = '_' + '-'.join((re.sub(r':', '', strain_id), 'genotype'))
genotype_label = '[' + strain_label + ']'
sex_specific_genotype_id = '_' + '-'.join(
(re.sub(r':', '', strain_id), sex, 'genotype'))
if strain_label is not None:
sex_specific_genotype_label = strain_label + ' (' + sex + ')'
else:
sex_specific_genotype_label = strain_id + '(' + sex + ')'
genotype_type = self.globaltt['sex_qualified_genotype']
if sex == 'm':
genotype_type = self.globaltt['male_genotype']
elif sex == 'f':
genotype_type = self.globaltt['female_genotype']
# add the genotype to strain connection
geno.addGenotype(genotype_id, genotype_label,
self.globaltt['genomic_background'])
graph.addTriple(strain_id, self.globaltt['has_genotype'], genotype_id)
geno.addGenotype(sex_specific_genotype_id, sex_specific_genotype_label,
genotype_type)
# add the strain as the background for the genotype
graph.addTriple(sex_specific_genotype_id,
self.globaltt['has_sex_agnostic_part'], genotype_id)
# ############# BUILD THE G2P ASSOC #############
# TODO add more provenance info when that model is completed
if phenotypes is not None:
for phenotype_id in phenotypes:
assoc = G2PAssoc(graph, self.name, sex_specific_genotype_id,
phenotype_id)
assoc.add_evidence(assay_id)
assoc.add_evidence(eco_id)
assoc.add_association_to_graph()
assoc_id = assoc.get_association_id()
model.addComment(assoc_id, comment)
model._addSexSpecificity(assoc_id, self.resolve(sex))
return
def process_gaf(self, file, limit, id_map=None, eco_map=None):
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
model = Model(graph)
geno = Genotype(graph)
LOG.info("Processing Gene Associations from %s", file)
line_counter = 0
uniprot_hit = 0
uniprot_miss = 0
if '7955' in self.tax_ids:
zfin = ZFIN(self.graph_type, self.are_bnodes_skized)
if '6239' in self.tax_ids:
wbase = WormBase(self.graph_type, self.are_bnodes_skized)
with gzip.open(file, 'rb') as csvfile:
filereader = csv.reader(io.TextIOWrapper(csvfile, newline=""),
delimiter='\t',
quotechar='\"')
for row in filereader:
line_counter += 1
# comments start with exclamation
if re.match(r'!', ''.join(row)):
continue
if len(row) > 17 or len(row) < 15:
LOG.warning(
"Wrong number of columns %i, expected 15 or 17\n%s",
len(row), row)
continue
if 17 > len(row) >= 15:
row += [""] * (17 - len(row))
(dbase, gene_num, gene_symbol, qualifier, go_id, ref,
eco_symbol, with_or_from, aspect, gene_name, gene_synonym,
object_type, taxon, date, assigned_by, annotation_extension,
gene_product_form_id) = row
# test for required fields
if (dbase == '' or gene_num == '' or gene_symbol == ''
or go_id == '' or ref == '' or eco_symbol == ''
or aspect == '' or object_type == '' or taxon == ''
or date == '' or assigned_by == ''):
LOG.error(
"Missing required part of annotation on row %d:\n" +
'\t'.join(row), line_counter)
continue
# deal with qualifier NOT, contributes_to, colocalizes_with
if re.search(r'NOT', qualifier):
continue
if dbase in self.localtt:
dbase = self.localtt[dbase]
uniprotid = None
gene_id = None
if dbase == 'UniProtKB':
if id_map is not None and gene_num in id_map:
gene_id = id_map[gene_num]
uniprotid = ':'.join((dbase, gene_num))
(dbase, gene_num) = gene_id.split(':')
uniprot_hit += 1
else:
# LOG.warning(
# "UniProt id %s is without a 1:1 mapping to entrez/ensembl",
# gene_num)
uniprot_miss += 1
continue
else:
gene_num = gene_num.split(':')[-1] # last
gene_id = ':'.join((dbase, gene_num))
if self.test_mode and not (re.match(r'NCBIGene', gene_id)
and int(gene_num) in self.test_ids):
continue
model.addClassToGraph(gene_id, gene_symbol)
if gene_name != '':
model.addDescription(gene_id, gene_name)
if gene_synonym != '':
for syn in re.split(r'\|', gene_synonym):
model.addSynonym(gene_id, syn.strip())
if re.search(r'\|', taxon):
# TODO add annotations with >1 taxon
LOG.info(">1 taxon (%s) on line %d. skipping", taxon,
line_counter)
else:
tax_id = re.sub(r'taxon:', 'NCBITaxon:', taxon)
geno.addTaxon(tax_id, gene_id)
assoc = Assoc(graph, self.name)
assoc.set_subject(gene_id)
assoc.set_object(go_id)
try:
eco_id = eco_map[eco_symbol]
assoc.add_evidence(eco_id)
except KeyError:
LOG.error("Evidence code (%s) not mapped", eco_symbol)
refs = re.split(r'\|', ref)
for ref in refs:
ref = ref.strip()
if ref != '':
prefix = ref.split(':')[0] # sidestep 'MGI:MGI:'
if prefix in self.localtt:
prefix = self.localtt[prefix]
ref = ':'.join((prefix, ref.split(':')[-1]))
refg = Reference(graph, ref)
if prefix == 'PMID':
ref_type = self.globaltt['journal article']
refg.setType(ref_type)
refg.addRefToGraph()
assoc.add_source(ref)
# TODO add the source of the annotations from assigned by?
rel = self.resolve(aspect, mandatory=False)
if rel is not None and aspect == rel:
if aspect == 'F' and re.search(r'contributes_to',
qualifier):
assoc.set_relationship(self.globaltt['contributes to'])
else:
LOG.error(
"Aspect: %s with qualifier: %s is not recognized",
aspect, qualifier)
elif rel is not None:
assoc.set_relationship(rel)
assoc.add_association_to_graph()
else:
LOG.warning("No predicate for association \n%s\n",
str(assoc))
if uniprotid is not None:
assoc.set_description('Mapped from ' + uniprotid)
# object_type should be one of:
# protein_complex; protein; transcript; ncRNA; rRNA; tRNA;
# snRNA; snoRNA; any subtype of ncRNA in the Sequence Ontology.
# If the precise product type is unknown,
# gene_product should be used
#######################################################################
# Derive G2P Associations from IMP annotations
# in version 2.1 Pipe will indicate 'OR'
# and Comma will indicate 'AND'.
# in version 2.0, multiple values are separated by pipes
# where the pipe has been used to mean 'AND'
if eco_symbol == 'IMP' and with_or_from != '':
withitems = re.split(r'\|', with_or_from)
phenotypeid = go_id + 'PHENOTYPE'
# create phenotype associations
for i in withitems:
if i == '' or re.match(
r'(UniProtKB|WBPhenotype|InterPro|HGNC)', i):
LOG.warning(
"Don't know what having a uniprot id " +
"in the 'with' column means of %s", uniprotid)
continue
i = re.sub(r'MGI\:MGI\:', 'MGI:', i)
i = re.sub(r'WB:', 'WormBase:', i)
# for worms and fish, they might give a RNAi or MORPH
# in these cases make a reagent-targeted gene
if re.search('MRPHLNO|CRISPR|TALEN', i):
targeted_gene_id = zfin.make_targeted_gene_id(
gene_id, i)
geno.addReagentTargetedGene(
i, gene_id, targeted_gene_id)
# TODO PYLINT why is this needed?
# Redefinition of assoc type from
# dipper.models.assoc.Association.Assoc to
# dipper.models.assoc.G2PAssoc.G2PAssoc
assoc = G2PAssoc(graph, self.name,
targeted_gene_id, phenotypeid)
elif re.search(r'WBRNAi', i):
targeted_gene_id = wbase.make_reagent_targeted_gene_id(
gene_id, i)
geno.addReagentTargetedGene(
i, gene_id, targeted_gene_id)
assoc = G2PAssoc(graph, self.name,
targeted_gene_id, phenotypeid)
else:
assoc = G2PAssoc(graph, self.name, i, phenotypeid)
for ref in refs:
ref = ref.strip()
if ref != '':
prefix = ref.split(':')[0]
if prefix in self.localtt:
prefix = self.localtt[prefix]
ref = ':'.join((prefix, ref.split(':')[-1]))
assoc.add_source(ref)
# experimental phenotypic evidence
assoc.add_evidence(self.globaltt[
'experimental phenotypic evidence'])
assoc.add_association_to_graph()
# TODO should the G2PAssoc be
# the evidence for the GO assoc?
if not self.test_mode and limit is not None and line_counter > limit:
break
uniprot_tot = (uniprot_hit + uniprot_miss)
uniprot_per = 0.0
if uniprot_tot != 0:
uniprot_per = 100.0 * uniprot_hit / uniprot_tot
LOG.info(
"Uniprot: %.2f%% of %i benefited from the 1/4 day id mapping download",
uniprot_per, uniprot_tot)
return
def _process_haplotype(self, hap_id, hap_label, chrom_num, chrom_pos,
context, risk_allele_frequency, mapped_gene,
so_ontology):
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
geno = Genotype(graph)
model = Model(graph)
# add the feature to the graph
hap_description = None
if risk_allele_frequency not in ['', 'NR']:
hap_description = str(
risk_allele_frequency) + ' [risk allele frequency]'
model.addIndividualToGraph(hap_id, hap_label.strip(),
self.globaltt['haplotype'], hap_description)
geno.addTaxon(self.globaltt["H**o sapiens"], hap_id)
snp_labels = re.split(r';\s?', hap_label)
chrom_nums = re.split(r';\s?', chrom_num)
chrom_positions = re.split(r';\s?', chrom_pos)
context_list = re.split(r';\s?', context)
mapped_genes = re.split(r';\s?', mapped_gene)
# Not having four "PAX5" as a list might be better, but it breaks unit tests
# mapped_genes = list(set(mapped_genes)) # make uniq
# snp_labels = list(set(snp_labels)) # make uniq
snp_curies = list()
for snp in snp_labels:
snp_curie, snp_type = self._get_curie_and_type_from_id(snp)
if snp_type is None:
LOG.info('cant find type for SNP in %s', snp)
# make blank node
snp_curie = self.make_id(snp, "_")
model.addLabel(snp_curie, snp)
elif snp_curie[0] == '_': # arrived an unlabeled blanknode
model.addLabel(snp_curie, snp)
graph.addTriple(hap_id, self.globaltt['has_variant_part'],
snp_curie)
snp_curies.append(snp_curie)
# courtesy http://stackoverflow.com/a/16720915
# check lengths of mutiple lists
length = len(snp_curies)
if not all(
len(lst) == length for lst in
[snp_labels, chrom_nums, chrom_positions, context_list]):
LOG.warning(
"Incongruous data field(s) for haplotype %s \n "
"will not add snp details", hap_label)
else:
variant_in_gene_count = 0
for index, snp_curie in enumerate(snp_curies):
self._add_snp_to_graph(snp_curie, snp_labels[index],
chrom_nums[index],
chrom_positions[index],
context_list[index])
if mapped_genes and len(mapped_genes) != len(snp_labels):
LOG.warning("More mapped genes than snps,"
" cannot disambiguate for\n%s\n%s",
mapped_genes, snp_labels) # hap_label)
else:
so_class = self.resolve(context_list[index])
so_query = """
SELECT ?variant_label
WHERE {{
{0} rdfs:subClassOf+ {1} ;
rdfs:label ?variant_label .
}}
""".format(so_class, self.globaltt['gene_variant'])
query_result = so_ontology.query(so_query)
gene_id = DipperUtil.get_hgnc_id_from_symbol(
mapped_genes[index])
if gene_id is not None and len(list(query_result)) == 1:
if context_list[index] in [
'upstream_gene_variant',
'downstream_gene_variant'
]:
graph.addTriple(snp_curie,
self.resolve(context_list[index]),
gene_id)
else:
geno.addAffectedLocus(snp_curie, gene_id)
variant_in_gene_count += 1
# Seperate in case we want to apply a different relation
# If not this is redundant with triples added above
if len(mapped_genes) == variant_in_gene_count and \
len(set(mapped_genes)) == 1:
gene_id = DipperUtil.get_hgnc_id_from_symbol(mapped_genes[0])
geno.addAffectedLocus(hap_id, gene_id)
def _process_data(self, raw, limit=None):
LOG.info("Processing Data from %s", raw)
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
model = Model(graph)
geno = Genotype(graph)
# Add the taxon as a class
taxon_id = self.globaltt['Mus musculus']
model.addClassToGraph(taxon_id, None)
# with open(raw, 'r', encoding="utf8") as csvfile:
col = self.files['all']['columns']
with gzip.open(raw, 'rt') as csvfile:
reader = csv.reader(csvfile, delimiter=',', quotechar='\"')
row = next(reader) # presumed header
if not self.check_fileheader(col, row):
pass
for row in reader:
# | head -1 | tr ',' '\n' | sed "s|\(.*\)|# \1 = row[col.index('\1')]|g"
marker_accession_id = row[col.index('marker_accession_id')].strip()
marker_symbol = row[col.index('marker_symbol')].strip()
phenotyping_center = row[col.index('phenotyping_center')].strip()
colony_raw = row[col.index('colony_id')].strip()
sex = row[col.index('sex')].strip()
zygosity = row[col.index('zygosity')].strip()
allele_accession_id = row[col.index('allele_accession_id')].strip()
allele_symbol = row[col.index('allele_symbol')].strip()
# allele_name = row[col.index('allele_name')]
strain_accession_id = row[col.index('strain_accession_id')].strip()
strain_name = row[col.index('strain_name')].strip()
# project_name = row[col.index('project_name')]
project_fullname = row[col.index('project_fullname')].strip()
pipeline_name = row[col.index('pipeline_name')].strip()
pipeline_stable_id = row[col.index('pipeline_stable_id')].strip()
procedure_stable_id = row[col.index('procedure_stable_id')].strip()
procedure_name = row[col.index('procedure_name')].strip()
parameter_stable_id = row[col.index('parameter_stable_id')].strip()
parameter_name = row[col.index('parameter_name')].strip()
# top_level_mp_term_id = row[col.index('top_level_mp_term_id')]
# top_level_mp_term_name = row[col.index('top_level_mp_term_name')]
mp_term_id = row[col.index('mp_term_id')].strip()
mp_term_name = row[col.index('mp_term_name')].strip()
p_value = row[col.index('p_value')].strip()
percentage_change = row[col.index('percentage_change')].strip()
effect_size = row[col.index('effect_size')].strip()
statistical_method = row[col.index('statistical_method')].strip()
resource_name = row[col.index('resource_name')].strip()
if self.test_mode and marker_accession_id not in self.gene_ids:
continue
# ##### cleanup some of the identifiers ######
zygosity = zygosity.strip()
zygosity_id = self.resolve(zygosity)
if zygosity_id == zygosity:
LOG.warning(
"Zygosity '%s' unmapped. detting to indeterminate", zygosity)
zygosity_id = self.globaltt['indeterminate']
# colony ids sometimes have <> in them, spaces,
# or other non-alphanumerics and break our system;
# replace these with underscores
colony_id = '_:' + re.sub(r'\W+', '_', colony_raw)
if not re.match(r'MGI', allele_accession_id):
allele_accession_id = '_:IMPC-'+re.sub(
r':', '', allele_accession_id)
if re.search(r'EUROCURATE', strain_accession_id):
# the eurocurate links don't resolve at IMPC
# TODO blank nodes do not maintain identifiers
strain_accession_id = '_:' + strain_accession_id
elif not re.match(r'MGI', strain_accession_id):
LOG.info(
"Found a strange strain accession...%s", strain_accession_id)
strain_accession_id = 'IMPC:'+strain_accession_id
######################
# first, add the marker and variant to the graph as with MGI,
# the allele is the variant locus. IF the marker is not known,
# we will call it a sequence alteration. otherwise,
# we will create a BNode for the sequence alteration.
sequence_alteration_id = variant_locus_id = None
variant_locus_name = sequence_alteration_name = None
# extract out what's within the <> to get the symbol
if re.match(r'.*<.*>', allele_symbol):
sequence_alteration_name = re.match(
r'.*<(.*)>', allele_symbol)
if sequence_alteration_name is not None:
sequence_alteration_name = sequence_alteration_name.group(1)
else:
sequence_alteration_name = allele_symbol
if marker_accession_id is not None and marker_accession_id == '':
LOG.warning("Marker unspecified on row %d", reader.line_num)
marker_accession_id = None
if marker_accession_id is not None:
variant_locus_id = allele_accession_id
variant_locus_name = allele_symbol
variant_locus_type = self.globaltt['variant_locus']
geno.addGene(
marker_accession_id, marker_symbol, self.globaltt['gene'])
geno.addAllele(
variant_locus_id, variant_locus_name, variant_locus_type, None)
geno.addAlleleOfGene(variant_locus_id, marker_accession_id)
# TAG bnode
sequence_alteration_id = '_:seqalt' + re.sub(
r':', '', allele_accession_id)
geno.addSequenceAlterationToVariantLocus(
sequence_alteration_id, variant_locus_id)
else:
sequence_alteration_id = allele_accession_id
# IMPC contains targeted mutations with either gene traps,
# knockouts, insertion/intragenic deletions.
# but I don't really know what the SeqAlt is here,
# so I don't add it.
geno.addSequenceAlteration(
sequence_alteration_id, sequence_alteration_name)
# ############# BUILD THE COLONY #############
# First, let's describe the colony that the animals come from
# The Colony ID refers to the ES cell clone
# used to generate a mouse strain.
# Terry sez: we use this clone ID to track
# ES cell -> mouse strain -> mouse phenotyping.
# The same ES clone maybe used at multiple centers,
# so we have to concatenate the two to have a unique ID.
# some useful reading about generating mice from ES cells:
# http://ki.mit.edu/sbc/escell/services/details
# here, we'll make a genotype
# that derives from an ES cell with a given allele.
# the strain is not really attached to the colony.
# the colony/clone is reflective of the allele, with unknown zygosity
stem_cell_class = self.globaltt['embryonic stem cell line']
if colony_id is None:
print(colony_raw, stem_cell_class, "\nline:\t", reader.line_num)
model.addIndividualToGraph(colony_id, colony_raw, stem_cell_class)
# vslc of the colony has unknown zygosity
# note that we will define the allele
# (and it's relationship to the marker, etc.) later
# FIXME is it really necessary to create this vslc
# when we always know it's unknown zygosity?
vslc_colony = '_:'+re.sub(
r':', '', allele_accession_id + self.globaltt['indeterminate'])
vslc_colony_label = allele_symbol + '/<?>'
# for ease of reading, we make the colony genotype variables.
# in the future, it might be desired to keep the vslcs
colony_genotype_id = vslc_colony
colony_genotype_label = vslc_colony_label
geno.addGenotype(colony_genotype_id, colony_genotype_label)
geno.addParts(
allele_accession_id, colony_genotype_id,
self.globaltt['has_variant_part'])
geno.addPartsToVSLC(
vslc_colony, allele_accession_id, None,
self.globaltt['indeterminate'], self.globaltt['has_variant_part'])
graph.addTriple(
colony_id, self.globaltt['has_genotype'], colony_genotype_id)
# ########## BUILD THE ANNOTATED GENOTYPE ##########
# now, we'll build the genotype of the individual that derives
# from the colony/clone genotype that is attached to
# phenotype = colony_id + strain + zygosity + sex
# (and is derived from a colony)
# this is a sex-agnostic genotype
genotype_id = self.make_id(
(colony_id + phenotyping_center + zygosity + strain_accession_id))
geno.addSequenceDerivesFrom(genotype_id, colony_id)
# build the VSLC of the sex-agnostic genotype
# based on the zygosity
allele1_id = allele_accession_id
allele2_id = allele2_rel = None
allele1_label = allele_symbol
allele2_label = '<?>'
# Making VSLC labels from the various parts,
# can change later if desired.
if zygosity == 'heterozygote':
allele2_label = re.sub(r'<.*', '<+>', allele1_label)
allele2_id = None
elif zygosity == 'homozygote':
allele2_label = allele1_label
allele2_id = allele1_id
allele2_rel = self.globaltt['has_variant_part']
elif zygosity == 'hemizygote':
allele2_label = re.sub(r'<.*', '<0>', allele1_label)
allele2_id = None
elif zygosity == 'not_applicable':
allele2_label = re.sub(r'<.*', '<?>', allele1_label)
allele2_id = None
else:
LOG.warning("found unknown zygosity %s", zygosity)
break
vslc_name = '/'.join((allele1_label, allele2_label))
# Add the VSLC
vslc_id = '-'.join(
(marker_accession_id, allele_accession_id, zygosity))
vslc_id = re.sub(r':', '', vslc_id)
vslc_id = '_:'+vslc_id
model.addIndividualToGraph(
vslc_id, vslc_name,
self.globaltt['variant single locus complement'])
geno.addPartsToVSLC(
vslc_id, allele1_id, allele2_id, zygosity_id,
self.globaltt['has_variant_part'], allele2_rel)
# add vslc to genotype
geno.addVSLCtoParent(vslc_id, genotype_id)
# note that the vslc is also the gvc
model.addType(vslc_id, self.globaltt['genomic_variation_complement'])
# Add the genomic background
# create the genomic background id and name
if strain_accession_id != '':
genomic_background_id = strain_accession_id
else:
genomic_background_id = None
genotype_name = vslc_name
if genomic_background_id is not None:
geno.addGenotype(
genomic_background_id, strain_name,
self.globaltt['genomic_background'])
# make a phenotyping-center-specific strain
# to use as the background
pheno_center_strain_label = strain_name + '-' + phenotyping_center \
+ '-' + colony_raw
pheno_center_strain_id = '-'.join((
re.sub(r':', '', genomic_background_id),
re.sub(r'\s', '_', phenotyping_center),
re.sub(r'\W+', '', colony_raw)))
if not re.match(r'^_', pheno_center_strain_id):
# Tag bnode
pheno_center_strain_id = '_:' + pheno_center_strain_id
geno.addGenotype(
pheno_center_strain_id, pheno_center_strain_label,
self.globaltt['genomic_background'])
geno.addSequenceDerivesFrom(
pheno_center_strain_id, genomic_background_id)
# Making genotype labels from the various parts,
# can change later if desired.
# since the genotype is reflective of the place
# it got made, should put that in to disambiguate
genotype_name = \
genotype_name + ' [' + pheno_center_strain_label + ']'
geno.addGenomicBackgroundToGenotype(
pheno_center_strain_id, genotype_id)
geno.addTaxon(taxon_id, pheno_center_strain_id)
# this is redundant, but i'll keep in in for now
geno.addSequenceDerivesFrom(genotype_id, colony_id)
geno.addGenotype(genotype_id, genotype_name)
# Make the sex-qualified genotype,
# which is what the phenotype is associated with
sex_qualified_genotype_id = \
self.make_id((
colony_id + phenotyping_center + zygosity +
strain_accession_id + sex))
sex_qualified_genotype_label = genotype_name + ' (' + sex + ')'
sq_type_id = self.resolve(sex, False)
if sq_type_id == sex:
sq_type_id = self.globaltt['intrinsic_genotype']
LOG.warning(
"Unknown sex qualifier %s, adding as intrinsic_genotype",
sex)
geno.addGenotype(
sex_qualified_genotype_id, sex_qualified_genotype_label, sq_type_id)
geno.addParts(
genotype_id, sex_qualified_genotype_id,
self.globaltt['has_variant_part'])
if genomic_background_id is not None and genomic_background_id != '':
# Add the taxon to the genomic_background_id
geno.addTaxon(taxon_id, genomic_background_id)
else:
# add it as the genomic background
geno.addTaxon(taxon_id, genotype_id)
# ############# BUILD THE G2P ASSOC #############
# from an old email dated July 23 2014:
# Phenotypes associations are made to
# imits colony_id+center+zygosity+gender
# sometimes phenotype ids are missing. (about 711 early 2020)
if mp_term_id is None or mp_term_id == '':
LOG.warning(
"No phenotype id specified for row %d", reader.line_num)
continue
# hard coded ECO code
eco_id = self.globaltt['mutant phenotype evidence']
# the association comes as a result of a g2p from
# a procedure in a pipeline at a center and parameter tested
assoc = G2PAssoc(
graph, self.name, sex_qualified_genotype_id, mp_term_id)
assoc.add_evidence(eco_id)
# assoc.set_score(float(p_value))
# TODO add evidence instance using
# pipeline_stable_id +
# procedure_stable_id +
# parameter_stable_id
assoc.add_association_to_graph()
assoc_id = assoc.get_association_id()
model._addSexSpecificity(assoc_id, self.resolve(sex))
# add a free-text description
try:
description = ' '.join((
mp_term_name, 'phenotype determined by', phenotyping_center,
'in an', procedure_name, 'assay where', parameter_name.strip(),
'was measured with an effect_size of',
str(round(float(effect_size), 5)),
'(p =', "{:.4e}".format(float(p_value)), ').'))
except ValueError:
description = ' '.join((
mp_term_name, 'phenotype determined by', phenotyping_center,
'in an', procedure_name, 'assay where', parameter_name.strip(),
'was measured with an effect_size of', str(effect_size),
'(p =', "{0}".format(p_value), ').'))
study_bnode = self._add_study_provenance(
phenotyping_center, colony_raw, project_fullname, pipeline_name,
pipeline_stable_id, procedure_stable_id, procedure_name,
parameter_stable_id, parameter_name, statistical_method,
resource_name)
evidence_line_bnode = self._add_evidence(
assoc_id, eco_id, p_value, percentage_change, effect_size,
study_bnode)
self._add_assertion_provenance(assoc_id, evidence_line_bnode)
model.addDescription(evidence_line_bnode, description)
# resource_id = resource_name
# assoc.addSource(graph, assoc_id, resource_id)
if not self.test_mode and limit is not None and reader.line_num > limit:
break
