def _process_data(self, source, limit=None):
"""
This function will process the data files from Coriell.
We make the assumption that any alleles listed are variants
(alternates to w.t.)
Triples: (examples)
:NIGMSrepository a CLO_0000008 #repository
label : NIGMS Human Genetic Cell Repository
foaf:page
https://catalog.coriell.org/0/sections/collections/NIGMS/?SsId=8
line_id a CL_0000057, #fibroblast line
derives_from patient_id
part_of :NIGMSrepository
RO:model_of OMIM:disease_id
patient id a foaf:person,
label: "fibroblast from patient 12345 with disease X"
member_of family_id #what is the right thing here?
SIO:race EFO:caucasian #subclass of EFO:0001799
in_taxon NCBITaxon:9606
dc:description Literal(remark)
RO:has_phenotype OMIM:disease_id
GENO:has_genotype genotype_id
family_id a owl:NamedIndividual
foaf:page
"https://catalog.coriell.org/0/Sections/BrowseCatalog/FamilyTypeSubDetail.aspx?PgId=402&fam=2104&coll=GM"
genotype_id a intrinsic_genotype
GENO:has_alternate_part allelic_variant_id
we don't necessarily know much about the genotype,
other than the allelic variant. also there's the sex here
pub_id mentions cell_line_id
:param raw:
:param limit:
:return:
"""
raw = '/'.join((self.rawdir, self.files[source]['file']))
LOG.info("Processing Data from %s", raw)
if self.testMode: # set the graph to build
graph = self.testgraph
else:
graph = self.graph
family = Family(graph)
model = Model(graph)
line_counter = 1
geno = Genotype(graph)
diputil = DipperUtil()
col = self.files[source]['columns']
# affords access with
# x = row[col.index('x')].strip()
with open(raw, 'r', encoding="iso-8859-1") as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar=r'"')
# we can keep a close watch on changing file formats
fileheader = next(filereader, None)
fileheader = [c.lower() for c in fileheader]
if col != fileheader: # assert
LOG.error('Expected %s to have columns: %s', raw, col)
LOG.error('But Found %s to have columns: %s', raw, fileheader)
raise AssertionError('Incomming data headers have changed.')
for row in filereader:
line_counter += 1
if len(row) != len(col):
LOG.warning('Expected %i values but find %i in row %i',
len(col), len(row), line_counter)
continue
# (catalog_id, description, omim_number, sample_type,
# cell_line_available, dna_in_stock, dna_ref, gender, age,
# race, ethnicity, affected, karyotype, relprob, mutation,
# gene, family_id, collection, url, cat_remark, pubmed_ids,
# family_member, variant_id, dbsnp_id, species) = row
# example:
# GM00003,HURLER SYNDROME,607014,Fibroblast,Yes,No,
# ,Female,26 YR,Caucasian,,,,
# parent,,,39,NIGMS Human Genetic Cell Repository,
# http://ccr.coriell.org/Sections/Search/Sample_Detail.aspx?Ref=GM00003,
# 46;XX; clinically normal mother of a child with Hurler syndrome;
# proband not in Repository,,
# 2,,18343,H**o sapiens
catalog_id = row[col.index('catalog_id')].strip()
if self.testMode and catalog_id not in self.test_lines:
# skip rows not in our test lines, when in test mode
continue
# ########### BUILD REQUIRED VARIABLES ###########
# Make the cell line ID
cell_line_id = 'Coriell:' + catalog_id
# Map the cell/sample type
cell_type = self.resolve(row[col.index('sample_type')].strip())
# on fail cell_type = self.globaltt['cell'] ?
# Make a cell line label
collection = row[col.index('collection')].strip()
line_label = collection.partition(' ')[0] + '-' + catalog_id
# Map the repository/collection
repository = self.localtt[collection]
# patients are uniquely identified by one of:
# dbsnp id (which is == an individual haplotype)
# family id + family member (if present) OR
# probands are usually family member zero
# cell line id
# since some patients have >1 cell line derived from them,
# we must make sure that the genotype is attached to
# the patient, and can be inferred to the cell line
# examples of repeated patients are:
# famid=1159, member=1; fam=152,member=1
# Make the patient ID
# make an anonymous patient
patient_id = '_:person'
fam_id = row[col.index('fam')].strip()
fammember = row[col.index('fammember')].strip()
if fam_id != '':
patient_id = '-'.join((patient_id, fam_id, fammember))
else:
# make an anonymous patient
patient_id = '-'.join((patient_id, catalog_id))
# properties of the individual patients: sex, family id,
# member/relproband, description descriptions are
# really long and ugly SCREAMING text, so need to clean up
# the control cases are so odd with this labeling scheme;
# but we'll deal with it as-is for now.
description = row[col.index('description')].strip()
short_desc = (description.split(';')[0]).capitalize()
gender = row[col.index('gender')].strip().lower()
affected = row[col.index('affected')].strip()
relprob = row[col.index('relprob')].strip()
if affected == '':
affected = 'unspecified'
elif affected in self.localtt:
affected = self.localtt[affected]
else:
LOG.warning('Novel Affected status %s at row: %i of %s',
affected, line_counter, raw)
patient_label = ' '.join((affected, gender, relprob))
if relprob == 'proband':
patient_label = ' '.join(
(patient_label.strip(), 'with', short_desc))
else:
patient_label = ' '.join(
(patient_label.strip(), 'of proband with', short_desc))
# ############# BUILD THE CELL LINE #############
# Adding the cell line as a typed individual.
cell_line_reagent_id = self.globaltt['cell line']
model.addIndividualToGraph(cell_line_id, line_label,
cell_line_reagent_id)
# add the equivalent id == dna_ref
dna_ref = row[col.index('dna_ref')].strip()
if dna_ref != '' and dna_ref != catalog_id:
equiv_cell_line = 'Coriell:' + dna_ref
# some of the equivalent ids are not defined
# in the source data; so add them
model.addIndividualToGraph(equiv_cell_line, None,
cell_line_reagent_id)
model.addSameIndividual(cell_line_id, equiv_cell_line)
# Cell line derives from patient
geno.addDerivesFrom(cell_line_id, patient_id)
geno.addDerivesFrom(cell_line_id, cell_type)
# Cell line a member of repository
family.addMember(repository, cell_line_id)
cat_remark = row[col.index('cat_remark')].strip()
if cat_remark != '':
model.addDescription(cell_line_id, cat_remark)
# Cell age_at_sampling
# TODO add the age nodes when modeled properly in #78
# if (age != ''):
# this would give a BNode that is an instance of Age.
# but i don't know how to connect
# the age node to the cell line? we need to ask @mbrush
# age_id = '_'+re.sub('\s+','_',age)
# gu.addIndividualToGraph(
# graph,age_id,age,self.globaltt['age'])
# gu.addTriple(
# graph,age_id,self.globaltt['has measurement value'],age,
# True)
# ############# BUILD THE PATIENT #############
# Add the patient ID as an individual.
model.addPerson(patient_id, patient_label)
# TODO map relationship to proband as a class
# (what ontology?)
# Add race of patient
# FIXME: Adjust for subcategories based on ethnicity field
# EDIT: There are 743 different entries for ethnicity...
# Too many to map?
# Add ethnicity as literal in addition to the mapped race?
# Adjust the ethnicity txt (if using)
# to initial capitalization to remove ALLCAPS
# TODO race should go into the individual's background
# and abstracted out to the Genotype class punting for now.
# if race != '':
# mapped_race = self.resolve(race)
# if mapped_race is not None:
# gu.addTriple(
# g,patient_id,self.globaltt['race'], mapped_race)
# model.addSubClass(
# mapped_race,self.globaltt['ethnic_group'])
# ############# BUILD THE FAMILY #############
# Add triples for family_id, if present.
if fam_id != '':
family_comp_id = 'CoriellFamily:' + fam_id
family_label = ' '.join(
('Family of proband with', short_desc))
# Add the family ID as a named individual
model.addIndividualToGraph(family_comp_id, family_label,
self.globaltt['family'])
# Add the patient as a member of the family
family.addMemberOf(patient_id, family_comp_id)
# ############# BUILD THE GENOTYPE #############
# the important things to pay attention to here are:
# karyotype = chr rearrangements (somatic?)
# mutation = protein-level mutation as a label,
# often from omim
# gene = gene symbol - TODO get id
# variant_id = omim variant ids (; delimited)
# dbsnp_id = snp individual ids = full genotype?
# note GM00633 is a good example of chromosomal variation
# - do we have enough to capture this?
# GM00325 has both abnormal karyotype and variation
# make an assumption that if the taxon is blank,
# that it is human!
species = row[col.index('species')].strip()
if species is None or species == '':
species = 'H**o sapiens'
taxon = self.resolve(species)
# if there's a dbSNP id,
# this is actually the individual's genotype
genotype_id = None
genotype_label = None
dbsnp_id = row[col.index('dbsnp_id')].strip()
if dbsnp_id != '':
genotype_id = 'dbSNPIndividual:' + dbsnp_id
omim_map = {}
gvc_id = None
# some of the karyotypes are encoded
# with terrible hidden codes. remove them here
# i've seen a <98> character
karyotype = row[col.index('karyotype')].strip()
karyotype = diputil.remove_control_characters(karyotype)
karyotype_id = None
if karyotype.strip() != '':
karyotype_id = '_:' + re.sub('MONARCH:', '',
self.make_id(karyotype))
# add karyotype as karyotype_variation_complement
model.addIndividualToGraph(
karyotype_id, karyotype,
self.globaltt['karyotype_variation_complement'])
# TODO break down the karyotype into parts
# and map into GENO. depends on #77
# place the karyotype in a location(s).
karyo_chrs = self._get_affected_chromosomes_from_karyotype(
karyotype)
for chrom in karyo_chrs:
chr_id = makeChromID(chrom, taxon, 'CHR')
# add an anonymous sequence feature,
# each located on chr
karyotype_feature_id = '-'.join((karyotype_id, chrom))
karyotype_feature_label = \
'some karyotype alteration on chr' + str(chrom)
feat = Feature(graph, karyotype_feature_id,
karyotype_feature_label,
self.globaltt['sequence_alteration'])
feat.addFeatureStartLocation(None, chr_id)
feat.addFeatureToGraph()
geno.addParts(karyotype_feature_id, karyotype_id,
self.globaltt['has_variant_part'])
gene = row[col.index('gene')].strip()
mutation = row[col.index('mutation')].strip()
if gene != '':
vl = gene + '(' + mutation + ')'
# fix the variant_id so it's always in the same order
variant_id = row[col.index('variant_id')].strip()
vids = variant_id.split(';')
variant_id = ';'.join(sorted(list(set(vids))))
if karyotype.strip() != '' and not self._is_normal_karyotype(
karyotype):
gvc_id = karyotype_id
if variant_id != '':
gvc_id = '_:' + variant_id.replace(';', '-') + '-' \
+ re.sub(r'\w*:', '', karyotype_id)
if mutation.strip() != '':
gvc_label = '; '.join((vl, karyotype))
else:
gvc_label = karyotype
elif variant_id.strip() != '':
gvc_id = '_:' + variant_id.replace(';', '-')
gvc_label = vl
else:
# wildtype?
pass
# add the karyotype to the gvc.
# use reference if normal karyotype
karyo_rel = self.globaltt['has_variant_part']
if self._is_normal_karyotype(karyotype):
karyo_rel = self.globaltt['has_reference_part']
if karyotype_id is not None \
and not self._is_normal_karyotype(karyotype) \
and gvc_id is not None and karyotype_id != gvc_id:
geno.addParts(karyotype_id, gvc_id, karyo_rel)
if variant_id.strip() != '':
# split the variants & add them as part of the genotype
# we don't necessarily know their zygosity,
# just that they are part of the genotype variant ids
# are from OMIM, so prefix as such we assume that the
# sequence alts will be defined in OMIM not here
# TODO sort the variant_id list, if the omim prefix is
# the same, then assume it's the locus make a hashmap
# of the omim id to variant id list;
# then build the genotype hashmap is also useful for
# removing the "genes" from the list of "phenotypes"
# will hold gene/locus id to variant list
omim_map = {}
locus_num = None
for var in variant_id.split(';'):
# handle omim-style and odd var ids
# like 610661.p.R401X
mch = re.match(r'(\d+)\.+(.*)', var.strip())
if mch is not None and len(mch.groups()) == 2:
(locus_num, var_num) = mch.groups()
if locus_num is not None and locus_num not in omim_map:
omim_map[locus_num] = [var_num]
else:
omim_map[locus_num] += [var_num]
for omim in omim_map:
# gene_id = 'OMIM:' + omim # TODO unused
vslc_id = '_:' + '-'.join(
[omim + '.' + a for a in omim_map.get(omim)])
vslc_label = vl
# we don't really know the zygosity of
# the alleles at all.
# so the vslcs are just a pot of them
model.addIndividualToGraph(
vslc_id, vslc_label,
self.globaltt['variant single locus complement'])
for var in omim_map.get(omim):
# this is actually a sequence alt
allele1_id = 'OMIM:' + omim + '.' + var
geno.addSequenceAlteration(allele1_id, None)
# assume that the sa -> var_loc -> gene
# is taken care of in OMIM
geno.addPartsToVSLC(
vslc_id, allele1_id, None,
self.globaltt['indeterminate'],
self.globaltt['has_variant_part'])
if vslc_id != gvc_id:
geno.addVSLCtoParent(vslc_id, gvc_id)
if affected == 'unaffected':
# let's just say that this person is wildtype
model.addType(patient_id, self.globaltt['wildtype'])
elif genotype_id is None:
# make an anonymous genotype id (aka blank node)
genotype_id = '_:geno' + catalog_id.strip()
# add the gvc
if gvc_id is not None:
model.addIndividualToGraph(
gvc_id, gvc_label,
self.globaltt['genomic_variation_complement'])
# add the gvc to the genotype
if genotype_id is not None:
if affected == 'unaffected':
rel = self.globaltt['has_reference_part']
else:
rel = self.globaltt['has_variant_part']
geno.addParts(gvc_id, genotype_id, rel)
if karyotype_id is not None \
and self._is_normal_karyotype(karyotype):
if gvc_label is not None and gvc_label != '':
genotype_label = '; '.join((gvc_label, karyotype))
elif karyotype is not None:
genotype_label = karyotype
if genotype_id is None:
genotype_id = karyotype_id
else:
geno.addParts(karyotype_id, genotype_id,
self.globaltt['has_reference_part'])
else:
genotype_label = gvc_label
# use the catalog id as the background
genotype_label += ' [' + catalog_id.strip() + ']'
if genotype_id is not None and gvc_id is not None:
# only add the genotype if it has some parts
geno.addGenotype(genotype_id, genotype_label,
self.globaltt['intrinsic_genotype'])
geno.addTaxon(taxon, genotype_id)
# add that the patient has the genotype
# TODO check if the genotype belongs to
# the cell line or to the patient
graph.addTriple(patient_id, self.globaltt['has_genotype'],
genotype_id)
else:
geno.addTaxon(taxon, patient_id)
# TODO: Add sex/gender (as part of the karyotype?)
# = row[col.index('')].strip()
# ############# DEAL WITH THE DISEASES #############
omim_num = row[col.index('omim_num')].strip()
# we associate the disease to the patient
if affected == 'affected' and omim_num != '':
for d in omim_num.split(';'):
if d is not None and d != '':
# if the omim number is in omim_map,
# then it is a gene not a pheno
# TEC - another place to use the mimTitle omim
# classifier omia & genereviews are using
if d not in omim_map:
disease_id = 'OMIM:' + d.strip()
# assume the label is taken care of in OMIM
model.addClassToGraph(disease_id, None)
# add the association:
# the patient has the disease
assoc = G2PAssoc(graph, self.name, patient_id,
disease_id)
assoc.add_association_to_graph()
# this line is a model of this disease
# TODO abstract out model into
# it's own association class?
graph.addTriple(cell_line_id,
self.globaltt['is model of'],
disease_id)
else:
LOG.info('drop gene %s from disease list', d)
# ############# ADD PUBLICATIONS #############
pubmed_ids = row[col.index('pubmed_ids')].strip()
if pubmed_ids != '':
for s in pubmed_ids.split(';'):
pubmed_id = 'PMID:' + s.strip()
ref = Reference(graph, pubmed_id)
ref.setType(self.globaltt['journal article'])
ref.addRefToGraph()
graph.addTriple(pubmed_id, self.globaltt['mentions'],
cell_line_id)
if not self.testMode and (limit is not None
and line_counter > limit):
break
return
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
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 _process_data(self, raw, limit=None):
"""
This function will process the data files from Coriell.
We make the assumption that any alleles listed are variants
(alternates to w.t.)
Triples: (examples)
:NIGMSrepository a CLO_0000008 #repository
label : NIGMS Human Genetic Cell Repository
foaf:page https://catalog.coriell.org/0/sections/collections/NIGMS/?SsId=8
line_id a CL_0000057, #fibroblast line
derives_from patient_id
part_of :NIGMSrepository
RO:model_of OMIM:disease_id
patient id a foaf:person,
label: "fibroblast from patient 12345 with disease X"
member_of family_id #what is the right thing here?
SIO:race EFO:caucasian #subclass of EFO:0001799
in_taxon NCBITaxon:9606
dc:description Literal(remark)
RO:has_phenotype OMIM:disease_id
GENO:has_genotype genotype_id
family_id a owl:NamedIndividual
foaf:page "https://catalog.coriell.org/0/Sections/BrowseCatalog/FamilyTypeSubDetail.aspx?PgId=402&fam=2104&coll=GM"
genotype_id a intrinsic_genotype
GENO:has_alternate_part allelic_variant_id
we don't necessarily know much about the genotype,
other than the allelic variant. also there's the sex here
pub_id mentions cell_line_id
:param raw:
:param limit:
:return:
"""
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)
du = DipperUtil()
gu.loadProperties(g, geno.object_properties, gu.OBJPROP)
gu.loadAllProperties(g)
with open(raw, 'r', encoding="iso-8859-1") as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
next(filereader, None) # skip the header row
for row in filereader:
if not row:
pass
else:
line_counter += 1
(catalog_id, description, omim_number, sample_type,
cell_line_available, dna_in_stock, dna_ref, gender, age,
race, ethnicity, affected, karyotype, relprob, mutation,
gene, family_id, collection, url, cat_remark, pubmed_ids,
family_member, variant_id, dbsnp_id, species) = row
# example:
# GM00003,HURLER SYNDROME,607014,Fibroblast,Yes,No,,Female,26 YR,Caucasian,,,,
# parent,,,39,NIGMS Human Genetic Cell Repository,
# http://ccr.coriell.org/Sections/Search/Sample_Detail.aspx?Ref=GM00003,
# 46;XX; clinically normal mother of a child with Hurler syndrome; proband not in Repository,,
# 2,,18343,H**o sapiens
if self.testMode and catalog_id not in self.test_lines:
# skip rows not in our test lines, when in test mode
continue
# ########### BUILD REQUIRED VARIABLES ###########
# Make the cell line ID
cell_line_id = 'Coriell:'+catalog_id.strip()
# Map the cell/sample type
cell_type = self._map_cell_type(sample_type)
# Make a cell line label
line_label = \
collection.partition(' ')[0]+'-'+catalog_id.strip()
# Map the repository/collection
repository = self._map_collection(collection)
# patients are uniquely identified by one of:
# dbsnp id (which is == an individual haplotype)
# family id + family member (if present) OR
# probands are usually family member zero
# cell line id
# since some patients have >1 cell line derived from them,
# we must make sure that the genotype is attached to
# the patient, and can be inferred to the cell line
# examples of repeated patients are:
# famid=1159, member=1; fam=152,member=1
# Make the patient ID
# make an anonymous patient
patient_id = '_person'
if self.nobnodes:
patient_id = ':'+patient_id
if family_id != '':
patient_id = \
'-'.join((patient_id, family_id, family_member))
else:
# make an anonymous patient
patient_id = '-'.join((patient_id, catalog_id.strip()))
# properties of the individual patients: sex, family id,
# member/relproband, description descriptions are
# really long and ugly SCREAMING text, so need to clean up
# the control cases are so odd with this labeling scheme;
# but we'll deal with it as-is for now.
short_desc = (description.split(';')[0]).capitalize()
if affected == 'Yes':
affected = 'affected'
elif affected == 'No':
affected = 'unaffected'
gender = gender.lower()
patient_label = ' '.join((affected, gender, relprob))
if relprob == 'proband':
patient_label = \
' '.join(
(patient_label.strip(), 'with', short_desc))
else:
patient_label = \
' '.join(
(patient_label.strip(), 'of proband with',
short_desc))
# ############# BUILD THE CELL LINE #############
# Adding the cell line as a typed individual.
cell_line_reagent_id = 'CLO:0000031'
gu.addIndividualToGraph(
g, cell_line_id, line_label, cell_line_reagent_id)
# add the equivalent id == dna_ref
if dna_ref != '' and dna_ref != catalog_id:
equiv_cell_line = 'Coriell:'+dna_ref
# some of the equivalent ids are not defined
# in the source data; so add them
gu.addIndividualToGraph(
g, equiv_cell_line, None, cell_line_reagent_id)
gu.addSameIndividual(g, cell_line_id, equiv_cell_line)
# Cell line derives from patient
geno.addDerivesFrom(cell_line_id, patient_id)
geno.addDerivesFrom(cell_line_id, cell_type)
# Cell line a member of repository
gu.addMember(g, repository, cell_line_id)
if cat_remark != '':
gu.addDescription(g, cell_line_id, cat_remark)
# Cell age_at_sampling
# TODO add the age nodes when modeled properly in #78
# if (age != ''):
# this would give a BNode that is an instance of Age.
# but i don't know how to connect
# the age node to the cell line? we need to ask @mbrush
# age_id = '_'+re.sub('\s+','_',age)
# gu.addIndividualToGraph(
# g,age_id,age,self.terms['age'])
# gu.addTriple(
# g,age_id,self.properties['has_measurement'],age,
# True)
# ############# BUILD THE PATIENT #############
# Add the patient ID as an individual.
gu.addPerson(g, patient_id, patient_label)
# TODO map relationship to proband as a class
# (what ontology?)
# Add race of patient
# FIXME: Adjust for subcategories based on ethnicity field
# EDIT: There are 743 different entries for ethnicity...
# Too many to map?
# Add ethnicity as literal in addition to the mapped race?
# Adjust the ethnicity txt (if using)
# to initial capitalization to remove ALLCAPS
# TODO race should go into the individual's background
# and abstracted out to the Genotype class punting for now.
# if race != '':
# mapped_race = self._map_race(race)
# if mapped_race is not None:
# gu.addTriple(
# g,patient_id,self.terms['race'],mapped_race)
# gu.addSubclass(
# g,self.terms['ethnic_group'],mapped_race)
# ############# BUILD THE FAMILY #############
# Add triples for family_id, if present.
if family_id != '':
family_comp_id = 'CoriellFamily:'+family_id
family_label = \
' '.join(('Family of proband with', short_desc))
# Add the family ID as a named individual
gu.addIndividualToGraph(
g, family_comp_id, family_label,
geno.genoparts['family'])
# Add the patient as a member of the family
gu.addMemberOf(g, patient_id, family_comp_id)
# ############# BUILD THE GENOTYPE #############
# the important things to pay attention to here are:
# karyotype = chr rearrangements (somatic?)
# mutation = protein-level mutation as a label,
# often from omim
# gene = gene symbol - TODO get id
# variant_id = omim variant ids (; delimited)
# dbsnp_id = snp individual ids = full genotype?
# note GM00633 is a good example of chromosomal variation
# - do we have enough to capture this?
# GM00325 has both abnormal karyotype and variation
# make an assumption that if the taxon is blank,
# that it is human!
if species is None or species == '':
species = 'H**o sapiens'
taxon = self._map_species(species)
# if there's a dbSNP id,
# this is actually the individual's genotype
genotype_id = None
genotype_label = None
if dbsnp_id != '':
genotype_id = 'dbSNPIndividual:'+dbsnp_id.strip()
omim_map = {}
gvc_id = None
# some of the karyotypes are encoded
# with terrible hidden codes. remove them here
# i've seen a <98> character
karyotype = du.remove_control_characters(karyotype)
karyotype_id = None
if karyotype.strip() != '':
karyotype_id = \
'_'+re.sub('MONARCH:', '', self.make_id(karyotype))
if self.nobnodes:
karyotype_id = ':'+karyotype_id
# add karyotype as karyotype_variation_complement
gu.addIndividualToGraph(
g, karyotype_id, karyotype,
geno.genoparts['karyotype_variation_complement'])
# TODO break down the karyotype into parts
# and map into GENO. depends on #77
# place the karyotype in a location(s).
karyo_chrs = \
self._get_affected_chromosomes_from_karyotype(
karyotype)
for c in karyo_chrs:
chr_id = makeChromID(c, taxon, 'CHR')
# add an anonymous sequence feature,
# each located on chr
karyotype_feature_id = '-'.join((karyotype_id, c))
karyotype_feature_label = \
'some karyotype alteration on chr'+str(c)
f = Feature(
karyotype_feature_id, karyotype_feature_label,
geno.genoparts['sequence_alteration'])
f.addFeatureStartLocation(None, chr_id)
f.addFeatureToGraph(g)
f.loadAllProperties(g)
geno.addParts(
karyotype_feature_id, karyotype_id,
geno.object_properties['has_alternate_part'])
if gene != '':
vl = gene+'('+mutation+')'
# fix the variant_id so it's always in the same order
vids = variant_id.split(';')
variant_id = ';'.join(sorted(list(set(vids))))
if karyotype.strip() != '' \
and not self._is_normal_karyotype(karyotype):
mutation = mutation.strip()
gvc_id = karyotype_id
if variant_id != '':
gvc_id = '_' + variant_id.replace(';', '-') + '-' \
+ re.sub(r'\w*:', '', karyotype_id)
if mutation.strip() != '':
gvc_label = '; '.join((vl, karyotype))
else:
gvc_label = karyotype
elif variant_id.strip() != '':
gvc_id = '_' + variant_id.replace(';', '-')
gvc_label = vl
else:
# wildtype?
pass
if gvc_id is not None and gvc_id != karyotype_id \
and self.nobnodes:
gvc_id = ':'+gvc_id
# add the karyotype to the gvc.
# use reference if normal karyotype
karyo_rel = geno.object_properties['has_alternate_part']
if self._is_normal_karyotype(karyotype):
karyo_rel = \
geno.object_properties['has_reference_part']
if karyotype_id is not None \
and not self._is_normal_karyotype(karyotype) \
and gvc_id is not None and karyotype_id != gvc_id:
geno.addParts(karyotype_id, gvc_id, karyo_rel)
if variant_id.strip() != '':
# split the variants & add them as part of the genotype
# we don't necessarily know their zygosity,
# just that they are part of the genotype variant ids
# are from OMIM, so prefix as such we assume that the
# sequence alts will be defined in OMIM not here
# TODO sort the variant_id list, if the omim prefix is
# the same, then assume it's the locus make a hashmap
# of the omim id to variant id list;
# then build the genotype hashmap is also useful for
# removing the "genes" from the list of "phenotypes"
# will hold gene/locus id to variant list
omim_map = {}
locus_num = None
for v in variant_id.split(';'):
# handle omim-style and odd var ids
# like 610661.p.R401X
m = re.match(r'(\d+)\.+(.*)', v.strip())
if m is not None and len(m.groups()) == 2:
(locus_num, var_num) = m.groups()
if locus_num is not None \
and locus_num not in omim_map:
omim_map[locus_num] = [var_num]
else:
omim_map[locus_num] += [var_num]
for o in omim_map:
# gene_id = 'OMIM:' + o # TODO unused
vslc_id = \
'_' + '-'.join(
[o + '.' + a for a in omim_map.get(o)])
if self.nobnodes:
vslc_id = ':'+vslc_id
vslc_label = vl
# we don't really know the zygosity of
# the alleles at all.
# so the vslcs are just a pot of them
gu.addIndividualToGraph(
g, vslc_id, vslc_label,
geno.genoparts[
'variant_single_locus_complement'])
for v in omim_map.get(o):
# this is actually a sequence alt
allele1_id = 'OMIM:'+o+'.'+v
geno.addSequenceAlteration(allele1_id, None)
# assume that the sa -> var_loc -> gene
# is taken care of in OMIM
geno.addPartsToVSLC(
vslc_id, allele1_id, None,
geno.zygosity['indeterminate'],
geno.object_properties[
'has_alternate_part'])
if vslc_id != gvc_id:
geno.addVSLCtoParent(vslc_id, gvc_id)
if affected == 'unaffected':
# let's just say that this person is wildtype
gu.addType(g, patient_id, geno.genoparts['wildtype'])
elif genotype_id is None:
# make an anonymous genotype id
genotype_id = '_geno'+catalog_id.strip()
if self.nobnodes:
genotype_id = ':'+genotype_id
# add the gvc
if gvc_id is not None:
gu.addIndividualToGraph(
g, gvc_id, gvc_label,
geno.genoparts['genomic_variation_complement'])
# add the gvc to the genotype
if genotype_id is not None:
if affected == 'unaffected':
rel = \
geno.object_properties[
'has_reference_part']
else:
rel = \
geno.object_properties[
'has_alternate_part']
geno.addParts(gvc_id, genotype_id, rel)
if karyotype_id is not None \
and self._is_normal_karyotype(karyotype):
if gvc_label is not None and gvc_label != '':
genotype_label = \
'; '.join((gvc_label, karyotype))
else:
genotype_label = karyotype
if genotype_id is None:
genotype_id = karyotype_id
else:
geno.addParts(
karyotype_id, genotype_id,
geno.object_properties[
'has_reference_part'])
else:
genotype_label = gvc_label
# use the catalog id as the background
genotype_label += ' ['+catalog_id.strip()+']'
if genotype_id is not None and gvc_id is not None:
# only add the genotype if it has some parts
geno.addGenotype(
genotype_id, genotype_label,
geno.genoparts['intrinsic_genotype'])
geno.addTaxon(taxon, genotype_id)
# add that the patient has the genotype
# TODO check if the genotype belongs to
# the cell line or to the patient
gu.addTriple(
g, patient_id,
geno.properties['has_genotype'], genotype_id)
else:
geno.addTaxon(taxon, patient_id)
# TODO: Add sex/gender (as part of the karyotype?)
# ############# DEAL WITH THE DISEASES #############
# we associate the disease to the patient
if affected == 'affected':
if omim_number != '':
for d in omim_number.split(';'):
if d is not None and d != '':
# if the omim number is in omim_map,
# then it is a gene not a pheno
if d not in omim_map:
disease_id = 'OMIM:'+d.strip()
# assume the label is taken care of
gu.addClassToGraph(g, disease_id, None)
# add the association:
# the patient has the disease
assoc = G2PAssoc(
self.name, patient_id, disease_id)
assoc.add_association_to_graph(g)
# this line is a model of this disease
# TODO abstract out model into
# it's own association class?
gu.addTriple(
g, cell_line_id,
gu.properties['model_of'],
disease_id)
else:
logger.info(
'removing %s from disease list ' +
'since it is a gene', d)
# ############# ADD PUBLICATIONS #############
if pubmed_ids != '':
for s in pubmed_ids.split(';'):
pubmed_id = 'PMID:'+s.strip()
ref = Reference(pubmed_id)
ref.setType(Reference.ref_types['journal_article'])
ref.addRefToGraph(g)
gu.addTriple(
g, pubmed_id, gu.properties['mentions'],
cell_line_id)
if not self.testMode \
and (limit is not None and line_counter > limit):
break
Assoc(self.name).load_all_properties(g)
return
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:
"""
src_key = 'catalog'
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
model = Model(graph)
fname = '/'.join((self.rawdir, self.files[src_key]['file']))
self.strain_hash = {}
self.id_label_hash = {}
genes_with_no_ids = set()
stem_cell_class = self.globaltt['stem cell']
mouse_taxon = self.globaltt['Mus musculus']
geno = Genotype(graph)
with open(fname, 'r', encoding="utf8") as csvfile:
reader = csv.reader(csvfile, delimiter=',', quotechar='\"')
# First line is header not date/version info. This changed recently,
# apparently as of Sep 2019. Also, 3rd line is no longer blank.
row = [x.strip() for x in next(reader)] # messy messy
col = self.files['catalog']['columns']
strain_missing_allele = [] # to count the ones w/insufficent info
if not self.check_fileheader(col, row):
pass
for row in reader:
strain_id = row[col.index('STRAIN/STOCK_ID')].strip()
strain_label = row[col.index('STRAIN/STOCK_DESIGNATION')]
# strain_type_symbol = row[col.index('STRAIN_TYPE')]
strain_state = row[col.index('STATE')]
mgi_allele_id = row[col.index(
'MGI_ALLELE_ACCESSION_ID')].strip()
mgi_allele_symbol = row[col.index('ALLELE_SYMBOL')]
# mgi_allele_name = row[col.index('ALLELE_NAME')]
# mutation_type = row[col.index('MUTATION_TYPE')]
# chrom = row[col.index('CHROMOSOME')]
mgi_gene_id = row[col.index('MGI_GENE_ACCESSION_ID')].strip()
mgi_gene_symbol = row[col.index('GENE_SYMBOL')].strip()
mgi_gene_name = row[col.index('GENE_NAME')]
# sds_url = row[col.index('SDS_URL')]
# accepted_date = row[col.index('ACCEPTED_DATE')]
mpt_ids = row[col.index('MPT_IDS')].strip()
pubmed_nums = row[col.index('PUBMED_IDS')].strip()
research_areas = row[col.index('RESEARCH_AREAS')].strip()
if self.test_mode and (strain_id not in self.test_ids) \
or mgi_gene_name == 'withdrawn':
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()
}
# flag bad ones
if mgi_allele_id[:4] != 'MGI:' and mgi_allele_id != '':
LOG.error("Erroneous MGI allele id: %s", mgi_allele_id)
if mgi_allele_id[:3] == 'MG:':
mgi_allele_id = 'MGI:' + mgi_allele_id[3:]
else:
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.localtt[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, fix known issues
mgi_gene_id = re.sub(r'\s+', '', mgi_gene_id)
if mgi_gene_id == 'NULL':
mgi_gene_id = ''
elif mgi_gene_id[:7] == 'GeneID:':
mgi_gene_id = 'NCBIGene:' + mgi_gene_id[7:]
if mgi_gene_id != '':
try:
[curie, localid] = mgi_gene_id.split(':')
except ValueError as verror:
LOG.warning(
"Problem parsing mgi_gene_id %s from file %s: %s",
mgi_gene_id, fname, verror)
if curie not in ['MGI', 'NCBIGene']:
LOG.info("MGI Gene id not recognized: %s", mgi_gene_id)
self.strain_hash[strain_id]['genes'].add(mgi_gene_id)
self.id_label_hash[mgi_gene_id] = mgi_gene_symbol
# catch some errors - too many. report summary at the end
# some things have gene labels, but no identifiers - report
if mgi_gene_symbol != '' and mgi_gene_id == '':
# LOG.error(
# "Gene label with no MGI identifier for strain %s: %s",
# strain_id, mgi_gene_symbol)
genes_with_no_ids.add(mgi_gene_symbol)
# make a temp id for genes that aren't identified ... err wow.
# tmp_gene_id = '_' + mgi_gene_symbol
# self.id_label_hash[tmp_gene_id.strip()] = mgi_gene_symbol
# self.strain_hash[strain_id]['genes'].add(tmp_gene_id)
# split apart the mp ids
# ataxia [MP:0001393] ,hypoactivity [MP:0001402] ...
# mpt_ids are a comma delimited list
# labels with MP terms following in brackets
phenotype_ids = []
if mpt_ids != '':
for lb_mp in mpt_ids.split(r','):
lb_mp = lb_mp.strip()
if lb_mp[-1:] == ']' and lb_mp[-12:-8] == '[MP:':
phenotype_ids.append(lb_mp[-11:-2])
# pubmed ids are space delimited
pubmed_ids = []
if pubmed_nums != '':
for pm_num in re.split(r'\s+', pubmed_nums):
pmid = 'PMID:' + pm_num.strip()
pubmed_ids.append(pmid)
ref = Reference(graph, pmid,
self.globaltt['journal article'])
ref.addRefToGraph()
# https://www.mmrrc.org/catalog/sds.php?mmrrc_id=00001
# is a good example of 4 genotype parts
model.addClassToGraph(mouse_taxon, None)
if research_areas == '':
research_areas = None
else:
research_areas = 'Research Areas: ' + research_areas
strain_type = mouse_taxon
if strain_state == 'ES':
strain_type = stem_cell_class
model.addIndividualToGraph( # an inst of mouse??
strain_id, strain_label, strain_type, research_areas)
model.makeLeader(strain_id)
# phenotypes are associated with the alleles
for pid in phenotype_ids:
# assume the phenotype label is in some ontology
model.addClassToGraph(pid, None)
if mgi_allele_id is not None and mgi_allele_id != '':
assoc = G2PAssoc(graph, self.name, mgi_allele_id, pid,
self.globaltt['has phenotype'])
for p in pubmed_ids:
assoc.add_source(p)
assoc.add_association_to_graph()
else:
# too chatty here. report aggregate
# LOG.info("Phenotypes and no allele for %s", strain_id)
strain_missing_allele.append(strain_id)
if not self.test_mode and (limit is not None
and reader.line_num > limit):
break
# report misses
if strain_missing_allele:
LOG.info("Phenotypes and no allele for %i strains",
len(strain_missing_allele))
# 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 variants:
for var in variants:
vl_id = var.strip()
vl_symbol = self.id_label_hash[vl_id]
geno.addAllele(vl_id, vl_symbol,
self.globaltt['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 = '_:' + re.sub(r':', '', gene) + '-VL'
vl_symbol = self.id_label_hash[gene] + '<?>'
self.id_label_hash[vl_id] = vl_symbol
geno.addAllele(vl_id, vl_symbol,
self.globaltt['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)
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,
self.globaltt['indeterminate'],
self.globaltt['has_variant_part'],
None)
model.addIndividualToGraph(
vslc_id, vslc_label,
self.globaltt['variant single locus complement'])
if vslc_list:
if len(vslc_list) > 1:
gvc_id = '-'.join(vslc_list)
gvc_id = re.sub(r'_|:', '', gvc_id)
gvc_id = '_:' + gvc_id
gvc_label = '; '.join(self.id_label_hash[v]
for v in vslc_list)
model.addIndividualToGraph(
gvc_id, gvc_label,
self.globaltt['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(
(self.globaltt['unspecified_genomic_background'],
s)))
genotype_id = '-'.join((gvc_id, bkgd_id))
bkgd_id = '_:' + bkgd_id
geno.addTaxon(mouse_taxon, bkgd_id)
geno.addGenomicBackground(
bkgd_id, 'unspecified (' + s + ')',
self.globaltt['unspecified_genomic_background'],
"A placeholder for the unspecified genetic background for "
+ s)
geno.addGenomicBackgroundToGenotype(
bkgd_id, genotype_id,
self.globaltt['unspecified_genomic_background'])
geno.addParts(gvc_id, genotype_id,
self.globaltt['has_variant_part'])
geno.addGenotype(genotype_id, genotype_label)
graph.addTriple(s, self.globaltt['has_genotype'],
genotype_id)
else:
# LOG.debug(
# "Strain %s is not making a proper genotype.", s)
pass
LOG.warning(
"The following gene symbols did not list identifiers: %s",
str(sorted(list(genes_with_no_ids))))
LOG.error('%i symbols given are missing their gene identifiers',
len(genes_with_no_ids))
return
def _process_data(self, raw, limit=None):
logger.info("Processing Data from %s", raw)
gu = GraphUtils(curie_map.get())
if self.testMode:
g = self.testgraph
else:
g = self.graph
geno = Genotype(g)
line_counter = 0
gu.loadAllProperties(g)
gu.loadObjectProperties(g, geno.object_properties)
# Add the taxon as a class
taxon_id = 'NCBITaxon:10090' # map to Mus musculus
gu.addClassToGraph(g, taxon_id, None)
# with open(raw, 'r', encoding="utf8") as csvfile:
with gzip.open(raw, 'rt') as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
next(filereader, None) # skip the header row
for row in filereader:
line_counter += 1
(marker_accession_id, marker_symbol, phenotyping_center,
colony, sex, zygosity, allele_accession_id, allele_symbol,
allele_name, strain_accession_id, strain_name, project_name,
project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name, top_level_mp_term_id, top_level_mp_term_name,
mp_term_id, mp_term_name, p_value, percentage_change,
effect_size, statistical_method, resource_name) = row
if self.testMode and marker_accession_id not in self.test_ids:
continue
# ##### cleanup some of the identifiers ######
zygosity_id = self._map_zygosity(zygosity)
# 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)
if self.nobnodes:
colony_id = ':'+colony_id
if not re.match(r'MGI', allele_accession_id):
allele_accession_id = \
'_IMPC-'+re.sub(r':', '', allele_accession_id)
if self.nobnodes:
allele_accession_id = ':'+allele_accession_id
if re.search(r'EUROCURATE', strain_accession_id):
# the eurocurate links don't resolve at IMPC
strain_accession_id = '_'+strain_accession_id
if self.nobnodes:
strain_accession_id = ':'+strain_accession_id
elif not re.match(r'MGI', strain_accession_id):
logger.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).group(1)
else:
sequence_alteration_name = allele_symbol
if marker_accession_id is not None and \
marker_accession_id == '':
logger.warning(
"Marker unspecified on row %d", line_counter)
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 = geno.genoparts['variant_locus']
geno.addGene(marker_accession_id, marker_symbol,
geno.genoparts['gene'])
geno.addAllele(variant_locus_id, variant_locus_name,
variant_locus_type, None)
geno.addAlleleOfGene(variant_locus_id, marker_accession_id)
sequence_alteration_id = \
'_seqalt'+re.sub(r':', '', allele_accession_id)
if self.nobnodes:
sequence_alteration_id = ':'+sequence_alteration_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 = 'ERO:0002002'
gu.addIndividualToGraph(g, colony_id, colony, 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 = \
'_'+allele_accession_id+geno.zygosity['indeterminate']
vslc_colony = re.sub(r':', '', vslc_colony)
if self.nobnodes:
vslc_colony = ':'+vslc_colony
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,
geno.object_properties['has_alternate_part'])
geno.addPartsToVSLC(
vslc_colony, allele_accession_id, None,
geno.zygosity['indeterminate'],
geno.object_properties['has_alternate_part'])
gu.addTriple(
g, colony_id,
geno.object_properties['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 = geno.object_properties['has_alternate_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:
logger.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)
if self.nobnodes:
vslc_id = ':'+vslc_id
gu.addIndividualToGraph(
g, vslc_id, vslc_name,
geno.genoparts['variant_single_locus_complement'])
geno.addPartsToVSLC(
vslc_id, allele1_id, allele2_id, zygosity_id,
geno.object_properties['has_alternate_part'],
allele2_rel)
# add vslc to genotype
geno.addVSLCtoParent(vslc_id, genotype_id)
# note that the vslc is also the gvc
gu.addType(
g, vslc_id,
Genotype.genoparts['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,
geno.genoparts['genomic_background'])
# make a phenotyping-center-specific strain
# to use as the background
pheno_center_strain_label = \
strain_name + '/' + phenotyping_center
pheno_center_strain_id = \
'-'.join((re.sub(r':', '', genomic_background_id),
re.sub(r'\s', '_', phenotyping_center)))
if not re.match(r'^_', pheno_center_strain_id):
pheno_center_strain_id = '_'+pheno_center_strain_id
if self.nobnodes:
pheno_center_strain_id = ':'+pheno_center_strain_id
geno.addGenotype(pheno_center_strain_id,
pheno_center_strain_label,
geno.genoparts['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(pheno_center_strain_id, taxon_id)
# this is redundant, but i'll keep in in for now
geno.addSequenceDerivesFrom(genotype_id, colony_id)
genotype_name += '['+colony+']'
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+')'
if sex == 'male':
sq_type_id = geno.genoparts['male_genotype']
elif sex == 'female':
sq_type_id = geno.genoparts['female_genotype']
else:
sq_type_id = geno.genoparts['sex_qualified_genotype']
geno.addGenotype(
sex_qualified_genotype_id,
sex_qualified_genotype_label, sq_type_id)
geno.addParts(
genotype_id, sex_qualified_genotype_id,
geno.object_properties['has_alternate_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
phenotype_id = mp_term_id
# it seems that sometimes phenotype ids are missing.
# indicate here
if phenotype_id is None or phenotype_id == '':
logger.warning(
"No phenotype id specified for row %d: %s",
line_counter, str(row))
continue
# experimental_phenotypic_evidence This was used in ZFIN
eco_id = "ECO:0000059"
# the association comes as a result of a g2p from
# a procedure in a pipeline at a center and parameter tested
assoc = G2PAssoc(self.name, sex_qualified_genotype_id,
phenotype_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(g)
assoc_id = assoc.get_association_id()
# add a free-text description
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)), ').'))
gu.addDescription(g, assoc_id, description)
# TODO add provenance information
# resource_id = resource_name
# assoc.addSource(g, assoc_id, resource_id)
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)
return
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
model = Model(g)
line_counter = 0
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) \
or mgi_gene_name == 'withdrawn':
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(g, pmid,
Reference.ref_types['journal_article'])
r.addRefToGraph()
# https://www.mmrrc.org/catalog/sds.php?mmrrc_id=00001
# is a good example of 4 genotype parts
model.addClassToGraph(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
model.addIndividualToGraph(
strain_id, strain_label, strain_type,
research_areas) # an inst of mouse??
model.makeLeader(strain_id)
# phenotypes are associated with the alleles
for pid in phenotype_ids:
# assume the phenotype label is in the ontology
model.addClassToGraph(pid, None)
if mgi_allele_id is not None and mgi_allele_id != '':
assoc = G2PAssoc(
g, self.name, mgi_allele_id, pid,
model.object_properties['has_phenotype'])
for p in pubmed_ids:
assoc.add_source(p)
assoc.add_association_to_graph()
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 = '_:' + re.sub(r':', '', gene) + '-VL'
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)
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)
model.addIndividualToGraph(
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)
gvc_id = '_:' + gvc_id
gvc_label = \
'; '.join(self.id_label_hash[v] for v in vslc_list)
model.addIndividualToGraph(
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))
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)
g.addTriple(s, geno.object_properties['has_genotype'],
genotype_id)
else:
# logger.debug(
# "Strain %s is not making a proper genotype.", s)
pass
logger.warning(
"The following gene symbols did not list identifiers: %s",
str(sorted(list(genes_with_no_ids))))
return
def _process_data(self, raw, limit=None):
logger.info("Processing Data from %s", raw)
if self.testMode:
g = self.testgraph
else:
g = self.graph
model = Model(g)
geno = Genotype(g)
line_counter = 0
impc_map = self.open_and_parse_yaml(self.map_files['impc_map'])
impress_map = json.loads(
self.fetch_from_url(
self.map_files['impress_map']).read().decode('utf-8'))
# Add the taxon as a class
taxon_id = 'NCBITaxon:10090' # map to Mus musculus
model.addClassToGraph(taxon_id, None)
# with open(raw, 'r', encoding="utf8") as csvfile:
with gzip.open(raw, 'rt') as csvfile:
filereader = csv.reader(csvfile, delimiter=',', quotechar='\"')
next(filereader, None) # skip the header row
for row in filereader:
line_counter += 1
(marker_accession_id, marker_symbol, phenotyping_center,
colony, sex, zygosity, allele_accession_id, allele_symbol,
allele_name, strain_accession_id, strain_name, project_name,
project_fullname, pipeline_name, pipeline_stable_id,
procedure_stable_id, procedure_name, parameter_stable_id,
parameter_name, top_level_mp_term_id, top_level_mp_term_name,
mp_term_id, mp_term_name, p_value, percentage_change,
effect_size, statistical_method, resource_name) = row
if self.testMode and marker_accession_id not in self.test_ids:
continue
# ##### cleanup some of the identifiers ######
zygosity_id = self._map_zygosity(zygosity)
# 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)
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
strain_accession_id = '_:' + strain_accession_id
elif not re.match(r'MGI', strain_accession_id):
logger.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).group(1)
else:
sequence_alteration_name = allele_symbol
if marker_accession_id is not None and \
marker_accession_id == '':
logger.warning("Marker unspecified on row %d",
line_counter)
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 = geno.genoparts['variant_locus']
geno.addGene(marker_accession_id, marker_symbol,
geno.genoparts['gene'])
geno.addAllele(variant_locus_id, variant_locus_name,
variant_locus_type, None)
geno.addAlleleOfGene(variant_locus_id, marker_accession_id)
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 = 'ERO:0002002'
model.addIndividualToGraph(colony_id, colony, 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+geno.zygosity['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,
geno.object_properties['has_alternate_part'])
geno.addPartsToVSLC(
vslc_colony, allele_accession_id, None,
geno.zygosity['indeterminate'],
geno.object_properties['has_alternate_part'])
g.addTriple(colony_id, geno.object_properties['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 = geno.object_properties['has_alternate_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:
logger.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,
geno.genoparts['variant_single_locus_complement'])
geno.addPartsToVSLC(
vslc_id, allele1_id, allele2_id, zygosity_id,
geno.object_properties['has_alternate_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,
Genotype.genoparts['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,
geno.genoparts['genomic_background'])
# make a phenotyping-center-specific strain
# to use as the background
pheno_center_strain_label = \
strain_name + '-' + phenotyping_center + '-' + colony
pheno_center_strain_id = \
'-'.join((re.sub(r':', '', genomic_background_id),
re.sub(r'\s', '_', phenotyping_center),
re.sub(r'\W+', '', colony)))
if not re.match(r'^_', pheno_center_strain_id):
pheno_center_strain_id = '_:' + pheno_center_strain_id
geno.addGenotype(pheno_center_strain_id,
pheno_center_strain_label,
geno.genoparts['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 + ')'
if sex == 'male':
sq_type_id = geno.genoparts['male_genotype']
elif sex == 'female':
sq_type_id = geno.genoparts['female_genotype']
else:
sq_type_id = geno.genoparts['sex_qualified_genotype']
geno.addGenotype(sex_qualified_genotype_id,
sex_qualified_genotype_label, sq_type_id)
geno.addParts(genotype_id, sex_qualified_genotype_id,
geno.object_properties['has_alternate_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
phenotype_id = mp_term_id
# it seems that sometimes phenotype ids are missing.
# indicate here
if phenotype_id is None or phenotype_id == '':
logger.warning("No phenotype id specified for row %d: %s",
line_counter, str(row))
continue
# hard coded ECO code
eco_id = "ECO:0000015"
# the association comes as a result of a g2p from
# a procedure in a pipeline at a center and parameter tested
assoc = G2PAssoc(g, self.name, sex_qualified_genotype_id,
phenotype_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()
# 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(
impc_map, impress_map, phenotyping_center, colony,
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, impc_map, p_value, percentage_change,
effect_size, study_bnode)
self._add_assertion_provenance(assoc_id, evidence_line_bnode,
impc_map)
model.addDescription(evidence_line_bnode, description)
# resource_id = resource_name
# assoc.addSource(g, assoc_id, resource_id)
if not self.testMode and \
limit is not None and line_counter > limit:
break
return
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:
"""
src_key = 'catalog'
if self.test_mode:
graph = self.testgraph
else:
graph = self.graph
model = Model(graph)
fname = '/'.join((self.rawdir, self.files[src_key]['file']))
self.strain_hash = {}
self.id_label_hash = {}
genes_with_no_ids = set()
stem_cell_class = self.globaltt['stem cell']
mouse_taxon = self.globaltt['Mus musculus']
geno = Genotype(graph)
with open(fname, 'r', encoding="utf8") as csvfile:
reader = csv.reader(csvfile, delimiter=',', quotechar='\"')
# This MMRRC catalog data file was generated on YYYY-MM-DD
# insert or check date w/dataset
line = next(reader)
# gen_date = line[-10:]
line = next(reader)
col = self.files['catalog']['columns']
if col != line:
LOG.error(
'%s\nExpected Headers:\t%s\nRecived Headers:\t%s\n',
src_key, col, line)
LOG.info(set(col) - set(line))
line = next(reader)
if line != []:
LOG.warning('Expected third line to be blank. got "%s" instead', line)
for row in reader:
strain_id = row[col.index('STRAIN/STOCK_ID')].strip()
strain_label = row[col.index('STRAIN/STOCK_DESIGNATION')]
# strain_type_symbol = row[col.index('STRAIN_TYPE')]
strain_state = row[col.index('STATE')]
mgi_allele_id = row[col.index('MGI_ALLELE_ACCESSION_ID')].strip()
mgi_allele_symbol = row[col.index('ALLELE_SYMBOL')]
# mgi_allele_name = row[col.index('ALLELE_NAME')]
# mutation_type = row[col.index('MUTATION_TYPE')]
# chrom = row[col.index('CHROMOSOME')]
mgi_gene_id = row[col.index('MGI_GENE_ACCESSION_ID')].strip()
mgi_gene_symbol = row[col.index('GENE_SYMBOL')].strip()
mgi_gene_name = row[col.index('GENE_NAME')]
# sds_url = row[col.index('SDS_URL')]
# accepted_date = row[col.index('ACCEPTED_DATE')]
mpt_ids = row[col.index('MPT_IDS')].strip()
pubmed_nums = row[col.index('PUBMED_IDS')].strip()
research_areas = row[col.index('RESEARCH_AREAS')].strip()
if self.test_mode and (strain_id not in self.test_ids) \
or mgi_gene_name == 'withdrawn':
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()}
# flag bad ones
if mgi_allele_id[:4] != 'MGI:' and mgi_allele_id != '':
LOG.error("Erroneous MGI allele id: %s", mgi_allele_id)
if mgi_allele_id[:3] == 'MG:':
mgi_allele_id = 'MGI:' + mgi_allele_id[3:]
else:
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.localtt[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, fix known issues
mgi_gene_id = re.sub(r'\s+', '', mgi_gene_id)
if mgi_gene_id == 'NULL':
mgi_gene_id = ''
elif mgi_gene_id[:7] == 'GeneID:':
mgi_gene_id = 'NCBIGene:' + mgi_gene_id[7:]
if mgi_gene_id != '':
[curie, localid] = mgi_gene_id.split(':')
if curie not in ['MGI', 'NCBIGene']:
LOG.info("MGI Gene id not recognized: %s", mgi_gene_id)
self.strain_hash[strain_id]['genes'].add(mgi_gene_id)
self.id_label_hash[mgi_gene_id] = mgi_gene_symbol
# catch some errors - too many. report summary at the end
# some things have gene labels, but no identifiers - report
if mgi_gene_symbol != '' and mgi_gene_id == '':
# LOG.error(
# "Gene label with no MGI identifier for strain %s: %s",
# strain_id, mgi_gene_symbol)
genes_with_no_ids.add(mgi_gene_symbol)
# make a temp id for genes that aren't identified ... err wow.
# tmp_gene_id = '_' + mgi_gene_symbol
# self.id_label_hash[tmp_gene_id.strip()] = mgi_gene_symbol
# self.strain_hash[strain_id]['genes'].add(tmp_gene_id)
# split apart the mp ids
# ataxia [MP:0001393] ,hypoactivity [MP:0001402] ...
# mpt_ids are a comma delimited list
# labels with MP terms following in brackets
phenotype_ids = []
if mpt_ids != '':
for lb_mp in mpt_ids.split(r','):
lb_mp = lb_mp.strip()
if lb_mp[-1:] == ']' and lb_mp[-12:-8] == '[MP:':
phenotype_ids.append(lb_mp[-11:-2])
# pubmed ids are space delimited
pubmed_ids = []
if pubmed_nums != '':
for pm_num in re.split(r'\s+', pubmed_nums):
pmid = 'PMID:' + pm_num.strip()
pubmed_ids.append(pmid)
ref = Reference(graph, pmid, self.globaltt['journal article'])
ref.addRefToGraph()
# https://www.mmrrc.org/catalog/sds.php?mmrrc_id=00001
# is a good example of 4 genotype parts
model.addClassToGraph(mouse_taxon, None)
if research_areas == '':
research_areas = None
else:
research_areas = 'Research Areas: ' + research_areas
strain_type = mouse_taxon
if strain_state == 'ES':
strain_type = stem_cell_class
model.addIndividualToGraph( # an inst of mouse??
strain_id, strain_label, strain_type, research_areas)
model.makeLeader(strain_id)
# phenotypes are associated with the alleles
for pid in phenotype_ids:
# assume the phenotype label is in some ontology
model.addClassToGraph(pid, None)
if mgi_allele_id is not None and mgi_allele_id != '':
assoc = G2PAssoc(
graph, self.name, mgi_allele_id, pid,
self.globaltt['has phenotype'])
for p in pubmed_ids:
assoc.add_source(p)
assoc.add_association_to_graph()
else:
LOG.info("Phenotypes and no allele for %s", strain_id)
if not self.test_mode and (
limit is not None and reader.line_num > 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 var in variants:
vl_id = var.strip()
vl_symbol = self.id_label_hash[vl_id]
geno.addAllele(
vl_id, vl_symbol, self.globaltt['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 = '_:' + re.sub(r':', '', gene) + '-VL'
vl_symbol = self.id_label_hash[gene]+'<?>'
self.id_label_hash[vl_id] = vl_symbol
geno.addAllele(
vl_id, vl_symbol, self.globaltt['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)
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, self.globaltt['indeterminate'],
self.globaltt['has_variant_part'], None)
model.addIndividualToGraph(
vslc_id, vslc_label,
self.globaltt['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)
gvc_id = '_:'+gvc_id
gvc_label = '; '.join(self.id_label_hash[v] for v in vslc_list)
model.addIndividualToGraph(
gvc_id, gvc_label,
self.globaltt['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((
self.globaltt['unspecified_genomic_background'], s)))
genotype_id = '-'.join((gvc_id, bkgd_id))
bkgd_id = '_:' + bkgd_id
geno.addTaxon(mouse_taxon, bkgd_id)
geno.addGenomicBackground(
bkgd_id, 'unspecified (' + s + ')',
self.globaltt['unspecified_genomic_background'],
"A placeholder for the unspecified genetic background for " + s)
geno.addGenomicBackgroundToGenotype(
bkgd_id, genotype_id,
self.globaltt['unspecified_genomic_background'])
geno.addParts(
gvc_id, genotype_id, self.globaltt['has_variant_part'])
geno.addGenotype(genotype_id, genotype_label)
graph.addTriple(
s, self.globaltt['has_genotype'], genotype_id)
else:
# LOG.debug(
# "Strain %s is not making a proper genotype.", s)
pass
LOG.warning(
"The following gene symbols did not list identifiers: %s",
str(sorted(list(genes_with_no_ids))))
LOG.error(
'%i symbols given are missing their gene identifiers',
len(genes_with_no_ids))
return
