def _process_phenotype_data(self, limit):
"""
NOTE: If a Strain carries more than one mutation,
then each Mutation description,
i.e., the set: (
Mutation Type - Chromosome - Gene Symbol -
Gene Name - Allele Symbol - Allele Name)
will require a separate line.
Note that MMRRC curates phenotypes to alleles,
even though they distribute only one file with the
phenotypes appearing to be associated with a strain.
So, here we process the allele-to-phenotype relationships separately
from the strain-to-allele relationships.
:param limit:
:return:
"""
if self.testMode:
g = self.testgraph
else:
g = self.graph
line_counter = 0
gu = GraphUtils(curie_map.get())
fname = '/'.join((self.rawdir, self.files['catalog']['file']))
self.strain_hash = {}
self.id_label_hash = {}
genes_with_no_ids = set()
stem_cell_class = 'CL:0000034'
mouse_taxon = 'NCBITaxon:10090'
geno = Genotype(g)
with open(fname, 'r', encoding="utf8") as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
for row in filereader:
line_counter += 1
# skip the first 3 lines which are header, etc.
if line_counter < 4:
continue
(strain_id, strain_label, strain_type_symbol, strain_state,
mgi_allele_id, mgi_allele_symbol, mgi_allele_name,
mutation_type, chrom, mgi_gene_id, mgi_gene_symbol,
mgi_gene_name, sds_url, accepted_date, mp_ids, pubmed_nums,
research_areas) = row
if self.testMode and (strain_id not in self.test_ids):
continue
# strip off stuff after the dash -
# is the holding center important?
# MMRRC:00001-UNC --> MMRRC:00001
strain_id = re.sub(r'-\w+$', '', strain_id)
self.id_label_hash[strain_id] = strain_label
# get the variant or gene to save for later building of
# the genotype
if strain_id not in self.strain_hash:
self.strain_hash[strain_id] = {'variants': set(),
'genes': set()}
# clean up the bad one
if mgi_allele_id == 'multiple mutation':
logger.error("Erroneous gene id: %s", mgi_allele_id)
mgi_allele_id = ''
if mgi_allele_id != '':
self.strain_hash[strain_id]['variants'].add(mgi_allele_id)
self.id_label_hash[mgi_allele_id] = mgi_allele_symbol
# use the following if needing to add the
# sequence alteration types
# var_type =
# self._get_variant_type_from_abbrev(mutation_type)
# make a sequence alteration for this variant locus,
# and link the variation type to it
# sa_id = '_'+re.sub(r':','',mgi_allele_id)+'SA'
# if self.nobnodes:
# sa_id = ':'+sa_id
# gu.addIndividualToGraph(g, sa_id, None, var_type)
# geno.addSequenceAlterationToVariantLocus(sa_id,
# mgi_allele_id)
# scrub out any spaces
mgi_gene_id = re.sub(r'\s+', '', mgi_gene_id)
if mgi_gene_id.strip() != '':
if re.match(r'Gene\s*ID:', mgi_gene_id, re.I):
mgi_gene_id = re.sub(r'Gene\s*ID:\s*', 'NCBIGene:',
mgi_gene_id)
elif not re.match(r'MGI', mgi_gene_id):
logger.info("Gene id not recognized: %s", mgi_gene_id)
if re.match(r'\d+$', mgi_gene_id):
# assume that if it's all numbers, then it's MGI
mgi_gene_id = 'MGI:'+str(mgi_gene_id)
logger.info("Assuming numerics are MGI.")
self.strain_hash[strain_id]['genes'].add(mgi_gene_id)
self.id_label_hash[mgi_gene_id] = mgi_gene_symbol
# catch some errors -
# some things have gene labels, but no identifiers - report
if mgi_gene_symbol.strip() != '' and mgi_gene_id == '':
logger.error(
"Gene label with no identifier for strain %s: %s",
strain_id, mgi_gene_symbol)
genes_with_no_ids.add(mgi_gene_symbol.strip())
# make a temp id for genes that aren't identified
# tmp_gene_id = '_'+mgi_gene_symbol
# self.id_label_hash[tmp_gene_id] = mgi_gene_symbol
# self.strain_hash[strain_id]['genes'].add(tmp_gene_id)
# split apart the mp ids
# ataxia [MP:0001393] ,hypoactivity [MP:0001402] ...
# mp_ids are now a comma delimited list
# with MP terms in brackets
phenotype_ids = []
if mp_ids != '':
for i in re.split(r',', mp_ids):
i = i.strip()
mps = re.search(r'\[(.*)\]', i)
if mps is not None:
mp_id = mps.group(1).strip()
phenotype_ids.append(mp_id)
# pubmed ids are space delimited
pubmed_ids = []
if pubmed_nums.strip() != '':
for i in re.split(r'\s+', pubmed_nums):
pmid = 'PMID:'+i.strip()
pubmed_ids.append(pmid)
r = Reference(pmid,
Reference.ref_types['journal_article'])
r.addRefToGraph(g)
# https://www.mmrrc.org/catalog/sds.php?mmrrc_id=00001
# is a good example of 4 genotype parts
gu.addClassToGraph(g, mouse_taxon, None)
if research_areas.strip() == '':
research_areas = None
else:
research_areas = 'Research Areas: '+research_areas
strain_type = mouse_taxon
if strain_state == 'ES':
strain_type = stem_cell_class
gu.addIndividualToGraph(
g, strain_id, strain_label, strain_type,
research_areas) # an inst of mouse??
gu.makeLeader(g, strain_id)
# phenotypes are associated with the alleles
for pid in phenotype_ids:
# assume the phenotype label is in the ontology
gu.addClassToGraph(g, pid, None)
if mgi_allele_id is not None and mgi_allele_id != '':
assoc = G2PAssoc(self.name, mgi_allele_id, pid,
gu.object_properties['has_phenotype'])
for p in pubmed_ids:
assoc.add_source(p)
assoc.add_association_to_graph(g)
else:
logger.info("Phenotypes and no allele for %s",
strain_id)
if not self.testMode and (
limit is not None and line_counter > limit):
break
# now that we've collected all of the variant information, build it
# we don't know their zygosities
for s in self.strain_hash:
h = self.strain_hash.get(s)
variants = h['variants']
genes = h['genes']
vl_set = set()
# make variant loci for each gene
if len(variants) > 0:
for v in variants:
vl_id = v
vl_symbol = self.id_label_hash[vl_id]
geno.addAllele(vl_id, vl_symbol,
geno.genoparts['variant_locus'])
vl_set.add(vl_id)
if len(variants) == 1 and len(genes) == 1:
for gene in genes:
geno.addAlleleOfGene(vl_id, gene)
else:
geno.addAllele(vl_id, vl_symbol)
else: # len(vars) == 0
# it's just anonymous variants in some gene
for gene in genes:
vl_id = '_'+gene+'-VL'
vl_id = re.sub(r':', '', vl_id)
if self.nobnodes:
vl_id = ':'+vl_id
vl_symbol = self.id_label_hash[gene]+'<?>'
self.id_label_hash[vl_id] = vl_symbol
geno.addAllele(vl_id, vl_symbol,
geno.genoparts['variant_locus'])
geno.addGene(gene, self.id_label_hash[gene])
geno.addAlleleOfGene(vl_id, gene)
vl_set.add(vl_id)
# make the vslcs
vl_list = sorted(vl_set)
vslc_list = []
for vl in vl_list:
# for unknown zygosity
vslc_id = '_'+re.sub(r'^_', '', vl)+'U'
vslc_id = re.sub(r':', '', vslc_id)
if self.nobnodes:
vslc_id = ':' + vslc_id
vslc_label = self.id_label_hash[vl] + '/?'
self.id_label_hash[vslc_id] = vslc_label
vslc_list.append(vslc_id)
geno.addPartsToVSLC(
vslc_id, vl, None, geno.zygosity['indeterminate'],
geno.object_properties['has_alternate_part'], None)
gu.addIndividualToGraph(
g, vslc_id, vslc_label,
geno.genoparts['variant_single_locus_complement'])
if len(vslc_list) > 0:
if len(vslc_list) > 1:
gvc_id = '-'.join(vslc_list)
gvc_id = re.sub(r':', '', gvc_id)
if self.nobnodes:
gvc_id = ':'+gvc_id
gvc_label = \
'; '.join(self.id_label_hash[v] for v in vslc_list)
gu.addIndividualToGraph(
g, gvc_id, gvc_label,
geno.genoparts['genomic_variation_complement'])
for vslc_id in vslc_list:
geno.addVSLCtoParent(vslc_id, gvc_id)
else:
# the GVC == VSLC, so don't have to make an extra piece
gvc_id = vslc_list.pop()
gvc_label = self.id_label_hash[gvc_id]
genotype_label = gvc_label + ' [n.s.]'
bkgd_id = \
'_' + re.sub(r':', '', '-'.join(
(geno.genoparts['unspecified_genomic_background'],
s)))
genotype_id = '-'.join((gvc_id, bkgd_id))
if self.nobnodes:
bkgd_id = ':'+bkgd_id
geno.addTaxon(mouse_taxon, bkgd_id)
geno.addGenomicBackground(
bkgd_id, 'unspecified ('+s+')',
geno.genoparts['unspecified_genomic_background'],
"A placeholder for the " +
"unspecified genetic background for "+s)
geno.addGenomicBackgroundToGenotype(
bkgd_id, genotype_id,
geno.genoparts['unspecified_genomic_background'])
geno.addParts(
gvc_id, genotype_id,
geno.object_properties['has_alternate_part'])
geno.addGenotype(genotype_id, genotype_label)
gu.addTriple(
g, s, geno.object_properties['has_genotype'],
genotype_id)
else:
# logger.debug(
# "Strain %s is not making a proper genotype.", s)
pass
gu.loadProperties(
g, G2PAssoc.object_properties, G2PAssoc.OBJECTPROP)
gu.loadProperties(
g, G2PAssoc.datatype_properties, G2PAssoc.DATAPROP)
gu.loadProperties(
g, G2PAssoc.annotation_properties, G2PAssoc.ANNOTPROP)
gu.loadAllProperties(g)
logger.warning(
"The following gene symbols did not list identifiers: %s",
str(sorted(list(genes_with_no_ids))))
return
def _get_variants(self, limit):
"""
Currently loops through the variant_summary file.
:param limit:
:return:
"""
gu = GraphUtils(curie_map.get())
if self.testMode:
g = self.testgraph
else:
g = self.graph
geno = Genotype(g)
gu.loadAllProperties(g)
f = Feature(None, None, None)
f.loadAllProperties(g)
gu.loadAllProperties(g)
# add the taxon and the genome
tax_num = '9606' # HARDCODE
tax_id = 'NCBITaxon:'+tax_num
tax_label = 'Human'
gu.addClassToGraph(g, tax_id, None)
geno.addGenome(tax_id, tax_label) # label gets added elsewhere
# not unzipping the file
logger.info("Processing Variant records")
line_counter = 0
myfile = '/'.join((self.rawdir, self.files['variant_summary']['file']))
with gzip.open(myfile, 'rb') as f:
for line in f:
# skip comments
line = line.decode().strip()
if re.match(r'^#', line):
continue
# AlleleID integer value as stored in the AlleleID field in ClinVar (//Measure/@ID in the XML)
# Type character, the type of variation
# Name character, the preferred name for the variation
# GeneID integer, GeneID in NCBI's Gene database
# GeneSymbol character, comma-separated list of GeneIDs overlapping the variation
# ClinicalSignificance character, comma-separated list of values of clinical significance reported for this variation
# for the mapping between the terms listed here and the integers in the .VCF files, see
# http://www.ncbi.nlm.nih.gov/clinvar/docs/clinsig/
# RS# (dbSNP) integer, rs# in dbSNP
# nsv (dbVar) character, the NSV identifier for the region in dbVar
# RCVaccession character, list of RCV accessions that report this variant
# TestedInGTR character, Y/N for Yes/No if there is a test registered as specific to this variation in the NIH Genetic Testing Registry (GTR)
# PhenotypeIDs character, list of db names and identifiers for phenotype(s) reported for this variant
# Origin character, list of all allelic origins for this variation
# Assembly character, name of the assembly on which locations are based
# Chromosome character, chromosomal location
# Start integer, starting location, in pter->qter orientation
# Stop integer, end location, in pter->qter orientation
# Cytogenetic character, ISCN band
# ReviewStatus character, highest review status for reporting this measure. For the key to the terms,
# and their relationship to the star graphics ClinVar displays on its web pages,
# see http://www.ncbi.nlm.nih.gov/clinvar/docs/variation_report/#interpretation
# HGVS(c.) character, RefSeq cDNA-based HGVS expression
# HGVS(p.) character, RefSeq protein-based HGVS expression
# NumberSubmitters integer, number of submissions with this variant
# LastEvaluated datetime, the latest time any submitter reported clinical significance
# Guidelines character, ACMG only right now, for the reporting of incidental variation in a Gene
# (NOTE: if ACMG, not a specific to the allele but to the Gene)
# OtherIDs character, list of other identifiers or sources of information about this variant
# VariantID integer, the value used to build the URL for the current default report,
# e.g. http://www.ncbi.nlm.nih.gov/clinvar/variation/1756/
#
# a crude check that there's an expected number of cols.
# if not, error out because something changed.
num_cols = len(line.split('\t'))
expected_numcols = 29
if num_cols != expected_numcols:
logger.error(
"Unexpected number of columns in raw file " +
"(%d actual vs %d expected)",
num_cols, expected_numcols)
(allele_num, allele_type, allele_name, gene_num, gene_symbol,
clinical_significance, dbsnp_num, dbvar_num, rcv_nums,
tested_in_gtr, phenotype_ids, origin, assembly, chr, start,
stop, cytogenetic_loc, review_status, hgvs_c, hgvs_p,
number_of_submitters, last_eval, guidelines, other_ids,
variant_num, reference_allele, alternate_allele, categories,
ChromosomeAccession) = line.split('\t')
# ###set filter=None in init if you don't want to have a filter
# if self.filter is not None:
# if ((self.filter == 'taxids' and\
# (int(tax_num) not in self.tax_ids)) or\
# (self.filter == 'geneids' and\
# (int(gene_num) not in self.gene_ids))):
# continue
# #### end filter
line_counter += 1
pheno_list = []
if phenotype_ids != '-':
# trim any leading/trailing semicolons/commas
phenotype_ids = re.sub(r'^[;,]', '', phenotype_ids)
phenotype_ids = re.sub(r'[;,]$', '', phenotype_ids)
pheno_list = re.split(r'[,;]', phenotype_ids)
if self.testMode:
# get intersection of test disease ids
# and these phenotype_ids
intersect = \
list(
set([str(i)
for i in self.disease_ids]) & set(pheno_list))
if int(gene_num) not in self.gene_ids and\
int(variant_num) not in self.variant_ids and\
len(intersect) < 1:
continue
# TODO may need to switch on assembly to create correct
# assembly/build identifiers
build_id = ':'.join(('NCBIGenome', assembly))
# make the reference genome build
geno.addReferenceGenome(build_id, assembly, tax_id)
allele_type_id = self._map_type_of_allele(allele_type)
bandinbuild_id = None
if str(chr) == '':
# check cytogenic location
if str(cytogenetic_loc).strip() != '':
# use cytogenic location to get the apx location
# oddly, they still put an assembly number even when
# there's no numeric location
if not re.search(r'-', str(cytogenetic_loc)):
band_id = makeChromID(
re.split(r'-', str(cytogenetic_loc)),
tax_num, 'CHR')
geno.addChromosomeInstance(
cytogenetic_loc, build_id, assembly, band_id)
bandinbuild_id = makeChromID(
re.split(r'-', str(cytogenetic_loc)),
assembly, 'MONARCH')
else:
# can't deal with ranges yet
pass
else:
# add the human chromosome class to the graph,
# and add the build-specific version of it
chr_id = makeChromID(str(chr), tax_num, 'CHR')
geno.addChromosomeClass(str(chr), tax_id, tax_label)
geno.addChromosomeInstance(
str(chr), build_id, assembly, chr_id)
chrinbuild_id = makeChromID(str(chr), assembly, 'MONARCH')
seqalt_id = ':'.join(('ClinVarVariant', variant_num))
gene_id = None
# they use -1 to indicate unknown gene
if str(gene_num) != '-1' and str(gene_num) != 'more than 10':
gene_id = ':'.join(('NCBIGene', str(gene_num)))
# FIXME there are some "variants" that are actually haplotypes
# probably will get taken care of when we switch to processing
# the xml for example, variant_num = 38562
# but there's no way to tell if it's a haplotype
# in the csv data so the dbsnp or dbvar
# should probably be primary,
# and the variant num be the vslc,
# with each of the dbsnps being added to it
# TODO clinical significance needs to be mapped to
# a list of terms
# first, make the variant:
f = Feature(seqalt_id, allele_name, allele_type_id)
if start != '-' and start.strip() != '':
f.addFeatureStartLocation(start, chrinbuild_id)
if stop != '-' and stop.strip() != '':
f.addFeatureEndLocation(stop, chrinbuild_id)
f.addFeatureToGraph(g)
f.addTaxonToFeature(g, tax_id)
# make the ClinVarVariant the clique leader
gu.makeLeader(g, seqalt_id)
if bandinbuild_id is not None:
f.addSubsequenceOfFeature(g, bandinbuild_id)
# CHECK - this makes the assumption that there is
# only one affected chromosome per variant what happens with
# chromosomal rearrangement variants?
# shouldn't both chromosomes be here?
# add the hgvs as synonyms
if hgvs_c != '-' and hgvs_c.strip() != '':
gu.addSynonym(g, seqalt_id, hgvs_c)
if hgvs_p != '-' and hgvs_p.strip() != '':
gu.addSynonym(g, seqalt_id, hgvs_p)
# add the dbsnp and dbvar ids as equivalent
if dbsnp_num != '-' and int(dbsnp_num) != -1:
dbsnp_id = 'dbSNP:rs'+str(dbsnp_num)
gu.addIndividualToGraph(g, dbsnp_id, None)
gu.addSameIndividual(g, seqalt_id, dbsnp_id)
if dbvar_num != '-':
dbvar_id = 'dbVar:'+dbvar_num
gu.addIndividualToGraph(g, dbvar_id, None)
gu.addSameIndividual(g, seqalt_id, dbvar_id)
# TODO - not sure if this is right... add as xref?
# the rcv is like the combo of the phenotype with the variant
if rcv_nums != '-':
for rcv_num in re.split(r';', rcv_nums):
rcv_id = 'ClinVar:' + rcv_num
gu.addIndividualToGraph(g, rcv_id, None)
gu.addXref(g, seqalt_id, rcv_id)
if gene_id is not None:
# add the gene
gu.addClassToGraph(g, gene_id, gene_symbol)
# make a variant locus
vl_id = '_'+gene_num+'-'+variant_num
if self.nobnodes:
vl_id = ':'+vl_id
vl_label = allele_name
gu.addIndividualToGraph(
g, vl_id, vl_label, geno.genoparts['variant_locus'])
geno.addSequenceAlterationToVariantLocus(seqalt_id, vl_id)
geno.addAlleleOfGene(vl_id, gene_id)
else:
# some basic reporting
gmatch = re.search(r'\(\w+\)', allele_name)
if gmatch is not None and len(gmatch.groups()) > 0:
logger.info(
"Gene found in allele label, but no id provided: %s",
gmatch.group(1))
elif re.match(r'more than 10', gene_symbol):
logger.info(
"More than 10 genes found; "
"need to process XML to fetch (variant=%d)",
int(variant_num))
else:
logger.info(
"No gene listed for variant %d",
int(variant_num))
# parse the list of "phenotypes" which are diseases.
# add them as an association
# ;GeneReviews:NBK1440,MedGen:C0392514,OMIM:235200,SNOMED CT:35400008;MedGen:C3280096,OMIM:614193;MedGen:CN034317,OMIM:612635;MedGen:CN169374
# the list is both semicolon delimited and comma delimited,
# but i don't know why! some are bad, like:
# Orphanet:ORPHA ORPHA319705,SNOMED CT:49049000
if phenotype_ids != '-':
for p in pheno_list:
m = re.match(r"(Orphanet:ORPHA(?:\s*ORPHA)?)", p)
if m is not None and len(m.groups()) > 0:
p = re.sub(m.group(1), 'Orphanet:', p.strip())
elif re.match(r'SNOMED CT', p):
p = re.sub(r'SNOMED CT', 'SNOMED', p.strip())
assoc = G2PAssoc(self.name, seqalt_id, p.strip())
assoc.add_association_to_graph(g)
if other_ids != '-':
id_list = other_ids.split(',')
# process the "other ids" ex:
# CFTR2:F508del,HGMD:CD890142,OMIM Allelic Variant:602421.0001
# TODO make more xrefs
for xrefid in id_list:
prefix = xrefid.split(':')[0].strip()
if prefix == 'OMIM Allelic Variant':
xrefid = 'OMIM:'+xrefid.split(':')[1]
gu.addIndividualToGraph(g, xrefid, None)
gu.addSameIndividual(g, seqalt_id, xrefid)
elif prefix == 'HGMD':
gu.addIndividualToGraph(g, xrefid, None)
gu.addSameIndividual(g, seqalt_id, xrefid)
elif prefix == 'dbVar' \
and dbvar_num == xrefid.split(':')[1].strip():
pass # skip over this one
elif re.search(r'\s', prefix):
pass
# logger.debug(
# 'xref prefix has a space: %s', xrefid)
else:
# should be a good clean prefix
# note that HGMD variants are in here as Xrefs
# because we can't resolve URIs for them
# logger.info("Adding xref: %s", xrefid)
# gu.addXref(g, seqalt_id, xrefid)
# logger.info("xref prefix to add: %s", xrefid)
pass
if not self.testMode and limit is not None \
and line_counter > limit:
break
gu.loadProperties(g, G2PAssoc.object_properties, gu.OBJPROP)
gu.loadProperties(g, G2PAssoc.annotation_properties, gu.ANNOTPROP)
gu.loadProperties(g, G2PAssoc.datatype_properties, gu.DATAPROP)
logger.info("Finished parsing variants")
return
def _get_var_citations(self, limit):
# Generated weekly, the first of the week
# A tab-delimited report of citations associated with data in ClinVar,
# connected to the AlleleID, the VariationID, and either rs# from dbSNP
# or nsv in dbVar.
#
# AlleleID int value (xpath //Measure/@ID )
# VariationID ID ClinVar uses to anchor default display.
# (xpath //MeasureSet/@ID)
# rs rs identifier from dbSNP
# nsv nsv identifier from dbVar
# citation_source The source of the citation, either PubMed,
# PubMedCentral, or the NCBI Bookshelf
# citation_id The identifier used by that source
gu = GraphUtils(curie_map.get())
logger.info("Processing Citations for variants")
line_counter = 0
myfile = \
'/'.join((self.rawdir, self.files['variant_citations']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
with open(myfile, 'r', encoding="utf8") as f:
filereader = csv.reader(f, delimiter='\t', quotechar='\"')
for line in filereader:
# skip comments
line = line
if re.match(r'^#', line[0]):
continue
(allele_num, variant_num, rs_num, nsv_num, citation_source,
citation_id) = line
line_counter += 1
if self.testMode:
if int(variant_num) not in self.variant_ids:
continue
if citation_id.strip() == '':
logger.info(
"Skipping blank citation for ClinVarVariant:%s",
str(variant_num))
continue
# the citation for a variant is made to some kind of
# combination of the ids here.
# but i'm not sure which, we don't know what the
# citation is for exactly, other than the variant.
# so use mentions
var_id = 'ClinVarVariant:'+variant_num
# citation source: PubMed | PubMedCentral | citation_source
# citation id:
# format the citation id:
ref_id = None
if citation_source == 'PubMed':
ref_id = 'PMID:'+str(citation_id)
gu.makeLeader(g, ref_id)
elif citation_source == 'PubMedCentral':
ref_id = 'PMCID:'+str(citation_id)
if ref_id is not None:
r = Reference(
ref_id, Reference.ref_types['journal_article'])
r.addRefToGraph(g)
gu.addTriple(
g, ref_id, self.properties['is_about'], var_id)
if not self.testMode \
and (limit is not None and line_counter > limit):
break
logger.info("Finished processing citations for variants")
return
def process_catalog(self, limit=None):
"""
:param limit:
:return:
"""
raw = '/'.join((self.rawdir, self.files['catalog']['file']))
logger.info("Processing Data from %s", raw)
gu = GraphUtils(curie_map.get())
if self.testMode: # set the graph to build
g = self.testgraph
else:
g = self.graph
line_counter = 0
geno = Genotype(g)
gu.loadProperties(g, geno.object_properties, gu.OBJPROP)
gu.loadAllProperties(g)
tax_id = 'NCBITaxon:9606' # hardcode
genome_version = 'GRCh38' # hardcode
# build a hashmap of genomic location to identifiers,
# to try to get the equivalences
loc_to_id_hash = {}
with open(raw, 'r', encoding="iso-8859-1") as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
next(filereader, None) # skip the header row
for row in filereader:
if not row:
pass
else:
line_counter += 1
(date_added_to_catalog, pubmed_num, first_author, pub_date,
journal, link, study_name, disease_or_trait,
initial_sample_description, replicate_sample_description,
region, chrom_num, chrom_pos, reported_gene_nums,
mapped_gene, upstream_gene_num, downstream_gene_num,
snp_gene_nums, upstream_gene_distance,
downstream_gene_distance, strongest_snp_risk_allele, snps,
merged, snp_id_current, context, intergenic_flag,
risk_allele_frequency, pvalue, pvalue_mlog, pvalue_text,
or_or_beta, confidence_interval_95,
platform_with_snps_passing_qc, cnv_flag, mapped_trait,
mapped_trait_uri) = row
intersect = \
list(set([str(i) for i in self.test_ids['gene']]) &
set(re.split(r',', snp_gene_nums)))
# skip if no matches found in test set
if self.testMode and len(intersect) == 0:
continue
# 06-May-2015 25917933 Zai CC 20-Nov-2014 J Psychiatr Res http://europepmc.org/abstract/MED/25917933
# A genome-wide association study of suicide severity scores in bipolar disorder.
# Suicide in bipolar disorder
# 959 European ancestry individuals NA
# 10p11.22 10 32704340 C10orf68, CCDC7, ITGB1 CCDC7
# rs7079041-A rs7079041 0 7079041 intron 0 2E-6 5.698970
if chrom_num != '' and chrom_pos != '':
loc = 'chr'+str(chrom_num)+':'+str(chrom_pos)
if loc not in loc_to_id_hash:
loc_to_id_hash[loc] = set()
else:
loc = None
if re.search(r' x ', strongest_snp_risk_allele) \
or re.search(r',', strongest_snp_risk_allele):
# TODO deal with haplotypes
logger.warning(
"We can't deal with haplotypes yet: %s",
strongest_snp_risk_allele)
continue
elif re.match(r'rs', strongest_snp_risk_allele):
rs_id = 'dbSNP:'+strongest_snp_risk_allele.strip()
# remove the alteration
elif re.match(r'kgp', strongest_snp_risk_allele):
# FIXME this isn't correct
rs_id = 'dbSNP:'+strongest_snp_risk_allele.strip()
# http://www.1000genomes.org/faq/what-are-kgp-identifiers
# for some information
# They were created by Illumina for their genotyping
# platform before some variants identified during the
# pilot phase of the project had been assigned
# rs numbers.
elif re.match(r'chr', strongest_snp_risk_allele):
# like: chr10:106180121-G
rs_id = ':gwas-' + \
re.sub(
r':', '-', strongest_snp_risk_allele.strip())
elif strongest_snp_risk_allele.strip() == '':
# logger.debug(
# "No strongest SNP risk allele for %s:\n%s",
# pubmed_num, str(row))
# FIXME still consider adding in the EFO terms
# for what the study measured?
continue
else:
logger.warning(
"There's a snp id i can't manage: %s",
strongest_snp_risk_allele)
continue
alteration = re.search(r'-(.*)$', rs_id)
if alteration is not None \
and re.match(r'[ATGC]', alteration.group(1)):
# add variation to snp
pass # TODO
rs_id = re.sub(r'-.*$', '', rs_id).strip()
if loc is not None:
loc_to_id_hash[loc].add(rs_id)
pubmed_id = 'PMID:'+pubmed_num
r = Reference(
pubmed_id, Reference.ref_types['journal_article'])
r.addRefToGraph(g)
# create the chromosome
chrom_id = makeChromID(chrom_num, genome_version, 'CHR')
# add the feature to the graph
snp_description = None
if risk_allele_frequency != '' and \
risk_allele_frequency != 'NR':
snp_description = \
str(risk_allele_frequency) + \
' [risk allele frequency]'
f = Feature(
rs_id, strongest_snp_risk_allele.strip(),
Feature.types[r'SNP'], snp_description)
if chrom_num != '' and chrom_pos != '':
f.addFeatureStartLocation(chrom_pos, chrom_id)
f.addFeatureEndLocation(chrom_pos, chrom_id)
f.addFeatureToGraph(g)
f.addTaxonToFeature(g, tax_id)
# TODO consider adding allele frequency as property;
# but would need background info to do that
# also want to add other descriptive info about
# the variant from the context
for c in re.split(r';', context):
cid = self._map_variant_type(c.strip())
if cid is not None:
gu.addType(g, rs_id, cid)
# add deprecation information
if merged == 1 and str(snp_id_current.strip()) != '':
# get the current rs_id
current_rs_id = 'dbSNP:'
if not re.match(r'rs', snp_id_current):
current_rs_id += 'rs'
if loc is not None:
loc_to_id_hash[loc].append(current_rs_id)
current_rs_id += str(snp_id_current)
gu.addDeprecatedIndividual(g, rs_id, current_rs_id)
# TODO check on this
# should we add the annotations to the current
# or orig?
gu.makeLeader(g, current_rs_id)
else:
gu.makeLeader(g, rs_id)
# 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.addAlleleOfGene(rs_id, gene_id)
# add the up and downstream genes if they are available
if upstream_gene_num != '':
downstream_gene_id = 'NCBIGene:'+downstream_gene_num
gu.addTriple(
g, rs_id,
Feature.object_properties[
r'upstream_of_sequence_of'],
downstream_gene_id)
if downstream_gene_num != '':
upstream_gene_id = 'NCBIGene:'+upstream_gene_num
gu.addTriple(
g, rs_id,
Feature.object_properties[
'downstream_of_sequence_of'],
upstream_gene_id)
description = 'A study of ' + disease_or_trait + \
' in ' + initial_sample_description
if replicate_sample_description != '':
description = \
' '.join(
(description, 'with',
replicate_sample_description))
if platform_with_snps_passing_qc != '':
description = ' '.join(
(description, 'on platform',
platform_with_snps_passing_qc))
description = ' '.join((description, '(p='+pvalue+')'))
# make associations to the EFO terms; there can be >1
if mapped_trait_uri.strip() != '':
for t in re.split(r',', mapped_trait_uri):
t = t.strip()
cu = CurieUtil(curie_map.get())
tid = cu.get_curie(t)
assoc = G2PAssoc(
self.name, rs_id, tid,
gu.object_properties['contributes_to'])
assoc.add_source(pubmed_id)
# combinatorial evidence
# used in automatic assertion
eco_id = 'ECO:0000213'
assoc.add_evidence(eco_id)
# assoc.set_description(description)
# FIXME score should get added to provenance/study
# assoc.set_score(pvalue)
assoc.add_association_to_graph(g)
if not self.testMode and\
(limit is not None and line_counter > limit):
break
Assoc(self.name).load_all_properties(g)
# loop through the location hash,
# and make all snps at that location equivalent
for l in loc_to_id_hash:
snp_ids = loc_to_id_hash[l]
if len(snp_ids) > 1:
logger.info("%s has >1 snp id: %s", l, str(snp_ids))
return
