def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'ctd')
self.dataset = Dataset(
'ctd', 'CTD', 'http://ctdbase.org', None,
'http://ctdbase.org/about/legal.jsp')
if 'test_ids' not in config.get_config() \
or 'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
self.test_geneids = []
else:
self.test_geneids = config.get_config()['test_ids']['gene']
if 'test_ids' not in config.get_config() \
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_diseaseids = []
else:
self.test_diseaseids = config.get_config()['test_ids']['disease']
self.g = self.graph
self.geno = Genotype(self.graph)
self.pathway = Pathway(self.graph)
return
def __init__(self, graph_type, are_bnodes_skolemized, tax_ids=None):
super().__init__(graph_type, are_bnodes_skolemized, 'biogrid')
self.tax_ids = tax_ids
self.dataset = Dataset(
'biogrid', 'The BioGrid', 'http://thebiogrid.org/', None,
'http://wiki.thebiogrid.org/doku.php/terms_and_conditions')
# Defaults
# our favorite animals
# taxids = [9606,10090,10116,7227,7955,6239,8355]
if self.tax_ids is None:
self.tax_ids = [9606, 10090, 7955]
if 'test_ids' not in config.get_config() or \
'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
else:
self.test_ids = config.get_config()['test_ids']['gene']
# data-source specific warnings
# (will be removed when issues are cleared)
logger.warning(
"several MI experimental codes do not exactly map to ECO; "
"using approximations.")
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'mmrrc')
self.strain_hash = {}
self.id_label_hash = {}
self.dataset = Dataset(
'mmrrc', 'Mutant Mouse Regional Resource Centers',
'https://www.mmrrc.org', None,
'https://www.mmrrc.org/about/data_download.php')
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'wormbase')
# update the dataset object with details about this resource
# NO LICENSE for this resource
self.dataset = Dataset('wormbase', 'WormBase',
'http://www.wormbase.org', None, None,
'http://www.wormbase.org/about/policies#012')
self.version_num = None
return
def setUp(self):
self.dataset = Dataset(identifier=self.identifier,
data_release_version=self.data_release_version,
ingest_name=self.identifier,
ingest_title=self.ingest_title,
ingest_url=self.ingest_url,
ingest_logo=self.ingest_logo_url,
ingest_description=self.ingest_description,
license_url=self.license_url,
data_rights=self.data_rights)
# put all triples in a list for debugging below
self.all_triples = list(self.dataset.graph.triples((None, None, None)))
def __init__(self):
Source.__init__(self, 'ctd')
self.dataset = Dataset(
'ctd', 'CTD', 'http://ctdbase.org', None,
'http://ctdbase.org/about/legal.jsp')
if 'test_ids' not in config.get_config() \
or 'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
self.test_geneids = []
else:
self.test_geneids = config.get_config()['test_ids']['gene']
if 'test_ids' not in config.get_config() \
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_diseaseids = []
else:
self.test_diseaseids = config.get_config()['test_ids']['disease']
self.gu = GraphUtils(curie_map.get())
self.g = self.graph
self.geno = Genotype(self.g)
return
def __init__(self,
graph_type,
are_bnodes_skolemized,
tax_ids=None,
gene_ids=None):
super().__init__(graph_type, are_bnodes_skolemized, 'ensembl')
self.tax_ids = tax_ids
self.gene_ids = gene_ids
self.dataset = Dataset('ensembl', 'ENSEMBL',
'http://uswest.ensembl.org', None)
# Defaults
if self.tax_ids is None:
self.tax_ids = [9606, 10090, 7955]
self.gene_ids = []
if 'test_ids' not in config.get_config() \
or 'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
else:
self.gene_ids = config.get_config()['test_ids']['gene']
self.properties = Feature.properties
logger.setLevel(logging.INFO)
return
def __init__(self, graph_type, are_bnodes_skolemized, tax_ids=None):
super().__init__(graph_type, are_bnodes_skolemized, 'go')
# Defaults
self.tax_ids = tax_ids
if self.tax_ids is None:
self.tax_ids = [9606, 10090, 7955]
logger.info("No taxa set. Defaulting to %s", str(tax_ids))
else:
logger.info("Filtering on the following taxa: %s", str(tax_ids))
# update the dataset object with details about this resource
# NO LICENSE for this resource
self.dataset = Dataset(
'go', 'GeneOntology', 'http://www.geneontology.org', None,
"https://creativecommons.org/licenses/by/4.0/legalcode",
'http://geneontology.org/page/use-and-license')
if 'test_ids' not in config.get_config() or \
'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
else:
self.test_ids = config.get_config()['test_ids']['gene']
return
def __init__(self, tax_ids=None):
super().__init__("biogrid")
self.tax_ids = tax_ids
self.load_bindings()
self.dataset = Dataset(
"biogrid",
"The BioGrid",
"http://thebiogrid.org/",
None,
"http://wiki.thebiogrid.org/doku.php/terms_and_conditions",
)
# Defaults
# taxids = [9606,10090,10116,7227,7955,6239,8355] #our favorite animals
if self.tax_ids is None:
self.tax_ids = [9606, 10090, 7955]
if "test_ids" not in config.get_config() or "gene" not in config.get_config()["test_ids"]:
logger.warn("not configured with gene test ids.")
else:
self.test_ids = config.get_config()["test_ids"]["gene"]
# data-source specific warnings (will be removed when issues are cleared)
logger.warn("several MI experimental codes do not exactly map to ECO; using approximations.")
return
def __init__(self):
Source.__init__(self, 'mpd')
# @N, not sure if this step is required
self.namespaces.update(curie_map.get())
self.stdevthreshold = 2
self.nobnodes = True # FIXME
# update the dataset object with details about this resource
# @N: Note that there is no license as far as I can tell
self.dataset = Dataset(
'mpd', 'MPD', 'http://phenome.jax.org', None, None)
# TODO add a citation for mpd dataset as a whole
self.dataset.set_citation('PMID:15619963')
self.assayhash = {}
self.idlabel_hash = {}
# to store the mean/zscore of each measure by strain+sex
self.score_means_by_measure = {}
# to store the mean value for each measure by strain+sex
self.strain_scores_by_measure = {}
self.geno = Genotype(self.graph)
self.gu = GraphUtils(curie_map.get())
return
def __init__(self):
Source.__init__(self, 'hpoa')
self.load_bindings()
self.dataset = Dataset(
'hpoa', 'Human Phenotype Ontology',
'http://www.human-phenotype-ontology.org', None,
'http://www.human-phenotype-ontology.org/contao/index.php/legal-issues.html')
self.replaced_id_count = 0
if 'test_ids' not in config.get_config()\
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = []
else:
self.test_ids = config.get_config()['test_ids']['disease']
# data-source specific warnings to be removed when issues are cleared
logger.warning(
"note that some ECO classes are missing for ICE, PCS, and ITM;" +
" using temporary mappings.")
return
def __init__(self, tax_ids=None):
super().__init__('biogrid')
self.tax_ids = tax_ids
self.load_bindings()
self.dataset = Dataset(
'biogrid', 'The BioGrid', 'http://thebiogrid.org/', None,
'http://wiki.thebiogrid.org/doku.php/terms_and_conditions')
# Defaults
# our favorite animals
# taxids = [9606,10090,10116,7227,7955,6239,8355]
if self.tax_ids is None:
self.tax_ids = [9606, 10090, 7955]
if 'test_ids' not in config.get_config() or \
'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
else:
self.test_ids = config.get_config()['test_ids']['gene']
# data-source specific warnings
# (will be removed when issues are cleared)
logger.warning(
"several MI experimental codes do not exactly map to ECO; "
"using approximations.")
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'omim')
self.dataset = Dataset(
'omim', 'Online Mendelian Inheritance in Man',
'http://www.omim.org', None,
'http://omim.org/help/agreement')
self.omim_ncbigene_idmap = {}
# data-source specific warnings
# (will be removed when issues are cleared)
# check if config exists; if it doesn't, error out and let user know
if 'keys' not in config.get_config() and \
'omim' not in config.get_config()['keys']:
logger.error("not configured with API key.")
# check to see if there's any ids configured in the config;
# otherwise, warn
if 'test_ids' not in config.get_config() or \
'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
else:
# select ony those test ids that are omim's.
self.test_ids += \
[obj.replace('OMIM:', '')
for obj in config.get_config()['test_ids']['disease']
if re.match(r'OMIM:', obj)]
return
def __init__(self,
graph_type,
are_bnodes_skolemized,
tax_ids=None,
gene_ids=None):
super().__init__(graph_type, are_bnodes_skolemized, 'clinvar')
self.tax_ids = tax_ids
self.gene_ids = gene_ids
self.filter = 'taxids'
self.dataset = Dataset(
'ClinVar', 'National Center for Biotechnology Information',
'http://www.ncbi.nlm.nih.gov/clinvar/', None,
'http://www.ncbi.nlm.nih.gov/About/disclaimer.html',
'https://creativecommons.org/publicdomain/mark/1.0/')
if 'test_ids' not in config.get_config() or \
'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
else:
self.gene_ids = config.get_config()['test_ids']['gene']
if 'test_ids' not in config.get_config() or \
'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
else:
self.disease_ids = config.get_config()['test_ids']['disease']
self.properties = Feature.properties
return
def test_distribution_level_no_license_url_default_value(self):
self.dataset = Dataset(identifier=self.identifier,
data_release_version=None,
ingest_name=self.identifier,
ingest_title=self.ingest_title,
ingest_url=self.ingest_url,
ingest_logo=self.ingest_logo_url,
ingest_description=self.ingest_description,
license_url=None,
data_rights=self.data_rights)
triples = list(
self.dataset.graph.triples(
(self.distribution_level_IRI_ttl_default_version,
self.iri_license, URIRef(self.license_url_default))))
self.assertTrue(
len(triples) == 1,
"distribution level default license triple not set")
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'sgd')
self.dataset = Dataset('sgd', 'SGD', 'https://www.yeastgenome.org/',
None, None)
self.global_terms = Source.open_and_parse_yaml(
'../../translationtable/global_terms.yaml')
self.apo_term_id = SGD.make_apo_map()
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'monarch')
self.dataset = Dataset(
'monarch', 'MonarchInitiative', 'https://monarchinitiative.org',
None, 'https://creativecommons.org/licenses/by/4.0/', None)
return
def __init__(self,
graph_type,
are_bnodes_skolemized,
tax_ids=None,
version=None):
super().__init__(graph_type, are_bnodes_skolemized, 'string')
self.dataset = Dataset(
'string', 'String', 'http://string-db.org/', None,
'http://string-db.org/cgi/access.pl?footer_active_subpage=licensing'
)
if tax_ids is None:
self.tax_ids = StringDB.DEFAULT_TAXA
else:
logger.info("Filtering on taxa {}".format(tax_ids))
self.tax_ids = tax_ids
if version is None:
self.version = 'v10.5'
self.files = {
'protein_links': {
'path':
'{}protein.links.detailed.{}/'.format(StringDB.STRING_BASE,
self.version),
'pattern':
'protein.links.detailed.{}.txt.gz'.format(self.version)
}
}
self.id_map_files = {
9606: {
'url': 'https://string-db.org/mapping_files/entrez_mappings/'
'entrez_gene_id.vs.string.v10.28042015.tsv',
'file': 'entrez_gene_id.vs.string.v10.28042015.tsv'
},
10090: {
'url': 'https://data.monarchinitiative.org/dipper/'
'cache/10090.string2mgi.tsv',
'file': '10090.string2mgi.tsv'
},
6239: {
'url': 'https://data.monarchinitiative.org/dipper/'
'cache/6239.string2ensembl_gene.tsv',
'file': '6239.string2ensembl_gene.tsv'
},
7227: {
'url': 'https://data.monarchinitiative.org/dipper/'
'cache/7227.string2ensembl_gene.tsv',
'file': '7227.string2ensembl_gene.tsv'
},
7955: {
'url': 'https://data.monarchinitiative.org/dipper/'
'cache/7955.string2zfin.tsv',
'file': '7955.string2zfin.tsv'
}
}
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'eom')
# update the dataset object with details about this resource
# TODO put this into a conf file?
self.dataset = Dataset(
'eom', 'EOM', 'http://elementsofmorphology.nih.gov', None,
'http://www.genome.gov/copyright.cfm',
'https://creativecommons.org/publicdomain/mark/1.0/')
# check if config exists; if it doesn't, error out and let user know
if 'dbauth' not in config.get_config() or \
'disco' not in config.get_config()['dbauth']:
logger.error("not configured with PG user/password.")
# source-specific warnings. will be cleared when resolved.
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'mmrrc')
self.strain_hash = {}
self.id_label_hash = {}
self.dataset = Dataset(
'mmrrc', 'Mutant Mouse Regional Resource Centers',
'https://www.mmrrc.org', None,
'https://www.mmrrc.org/about/data_download.php')
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'mychem')
self.dataset = Dataset(
'mychem', 'MYCHEM', 'https://mychem.info/', None,
None)
self.global_terms = Source.open_and_parse_yaml('../../translationtable/global_terms.yaml')
self.inchikeys = MyChem.chunks(l=MyChem.get_inchikeys(), n=10)
self.drugbank_targets = list()
self.drugcentral_interactors = list()
def test_version_level_version_set_explicitly(self):
self.dataset = Dataset(
identifier=self.identifier,
data_release_version=self.data_release_version,
ingest_name=self.identifier,
ingest_title=self.ingest_title,
ingest_url=self.ingest_url,
ingest_logo=self.ingest_logo_url,
ingest_description=self.ingest_description,
license_url=None,
data_rights=self.data_rights
)
triples = list(self.dataset.graph.triples(
(self.version_level_IRI, self.iri_version, None)))
self.assertTrue(len(triples) == 1,
"didn't get exactly one version level version triple")
self.assertEqual(triples[0][2],
Literal(self.data_release_version, datatype=XSD.date),
"version level version triple (set explicitly) is wrong ")
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'wormbase')
# update the dataset object with details about this resource
# NO LICENSE for this resource
self.dataset = Dataset(
'wormbase', 'WormBase', 'http://www.wormbase.org', None, None,
'http://www.wormbase.org/about/policies#012')
self.version_num = None
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'coriell')
self.dataset = Dataset('coriell', 'Coriell', 'http://ccr.coriell.org/',
None)
# data-source specific warnings
# (will be removed when issues are cleared)
logger.warning('We assume that if a species is not provided, '
'that it is a Human-derived cell line')
logger.warning('We map all omim ids as a disease/phenotype entity, '
'but should be fixed in the future') # TODO
# check if config exists; if it doesn't, error out and let user know
if 'dbauth' not in config.get_config() or \
'coriell' not in config.get_config()['dbauth']:
logger.error("not configured with FTP user/password.")
return
def __init__(self):
Source.__init__(self, 'mmrrc')
self.strain_hash = {}
self.id_label_hash = {}
self.load_bindings()
self.dataset = Dataset(
'mmrrc', 'Mutant Mouse Regional Resource Centers',
'https://www.mmrrc.org', None,
'https://www.mmrrc.org/about/data_download.php')
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'genereviews')
self.dataset = Dataset('genereviews', 'Gene Reviews',
'http://genereviews.org/', None,
'http://www.ncbi.nlm.nih.gov/books/NBK138602/')
self.dataset.set_citation('GeneReviews:NBK1116')
self.book_ids = set()
self.all_books = {}
if 'test_ids' not in config.get_config() or\
'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = list()
else:
# select ony those test ids that are omim's.
self.test_ids = config.get_config()['test_ids']['disease']
return
def __init__(self):
Source.__init__(self, 'wormbase')
# update the dataset object with details about this resource
# NO LICENSE for this resource
self.dataset = Dataset(
'wormbase', 'WormBase', 'http://www.wormbase.org', None, None,
'http://www.wormbase.org/about/policies#012')
self.version_num = None
return
def __init__(self, database, username, password=None, host=None):
super().__init__('cgd', database, username, password, host)
self.dataset = Dataset('cgd', 'cgd', 'http://ga4gh.org')
self.gene_map = {}
self.disease_map = {}
self.drug_map = {}
self.transcript_xrefs = {'RefSeq': {}, 'UniProt': {}}
self.bindings = {}
for k in curie_map.get().keys():
v = curie_map.get()[k]
self.bindings[k] = Namespace(v)
def __init__(self, graph_type, are_bnodes_skolemized):
Source.__init__(self, graph_type, are_bnodes_skolemized, 'mpd')
# @N, not sure if this step is required
self.stdevthreshold = 2
# update the dataset object with details about this resource
# @N: Note that there is no license as far as I can tell
self.dataset = Dataset(
'mpd', 'MPD', 'http://phenome.jax.org', None, None)
# TODO add a citation for mpd dataset as a whole
self.dataset.set_citation('PMID:15619963')
self.assayhash = {}
self.idlabel_hash = {}
# to store the mean/zscore of each measure by strain+sex
self.score_means_by_measure = {}
# to store the mean value for each measure by strain+sex
self.strain_scores_by_measure = {}
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'impc')
# update the dataset object with details about this resource
self.dataset = Dataset(
'impc', 'IMPC', 'http://www.mousephenotype.org', None,
'https://raw.githubusercontent.com/mpi2/PhenotypeArchive/master/LICENSE'
)
# TODO add a citation for impc dataset as a whole
# :impc cito:citesAsAuthority PMID:24194600
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'animalqtldb')
# update the dataset object with details about this resource
self.dataset = Dataset(
'animalqtldb', 'Animal QTL db',
'http://www.animalgenome.org/cgi-bin/QTLdb/index', None, None,
AQDL + '/faq#23', graph_type=graph_type)
# source-specific warnings. will be cleared when resolved.
logger.warning(
"No licences or rights exist for the raw data from this resource.")
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'hpoa')
self.dataset = Dataset(
'hpoa', 'Human Phenotype Ontology',
'http://www.human-phenotype-ontology.org', None,
'http://www.human-phenotype-ontology.org/contao/index.php/legal-issues.html'
)
self.replaced_id_count = 0
if 'test_ids' not in config.get_config()\
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = []
else:
self.test_ids = config.get_config()['test_ids']['disease']
# data-source specific warnings to be removed when issues are cleared
logger.warning(
"note that some ECO classes are missing for ICE, PCS, and ITM;" +
" using temporary mappings.")
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'orphanet')
self.dataset = Dataset(
'orphanet', 'Orphanet', 'http://www.orpha.net', None,
'http://creativecommons.org/licenses/by-nd/3.0/',
'http://omim.org/help/agreement')
# check to see if there's any ids configured in the config;
# otherwise, warn
if 'test_ids' not in config.get_config() or \
'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
return
def __init__(self):
Source.__init__(self, 'coriell')
self.load_bindings()
self.dataset = Dataset('coriell', 'Coriell', 'http://ccr.coriell.org/', None)
# data-source specific warnings (will be removed when issues are cleared)
logger.warn('We assume that if a species is not provided, that it is a Human-derived cell line')
logger.warn('We map all omim ids as a disease/phenotype entity, but should be fixed in the future')
# check if config exists; if it doesn't, error out and let user know
if 'dbauth' not in config.get_config() or 'coriell' not in config.get_config()['dbauth']:
logger.error("not configured with FTP user/password.")
return
def __init__(self):
Source.__init__(self, 'eom')
self.namespaces.update(curie_map.get())
# update the dataset object with details about this resource
# TODO put this into a conf file?
self.dataset = Dataset('eom', 'EOM', 'http://elementsofmorphology.nih.gov', None,
'http://www.genome.gov/copyright.cfm',
'https://creativecommons.org/publicdomain/mark/1.0/')
# check if config exists; if it doesn't, error out and let user know
if 'dbauth' not in config.get_config() or 'disco' not in config.get_config()['dbauth']:
logger.error("not configured with PG user/password.")
# source-specific warnings. will be cleared when resolved.
return
def __init__(self, graph_type, are_bnodes_skolemized, tax_ids=None):
super().__init__(graph_type, are_bnodes_skolemized, 'monochrom')
self.tax_ids = tax_ids
# Defaults
if self.tax_ids is None:
self.tax_ids = [
9606, 10090, 7955, 10116, 9913, 9031, 9823, 9940, 9796
]
self._check_tax_ids()
# TODO add license
self.dataset = Dataset('monochrom', 'Monarch Chromosome Ontology',
'http://monarchinitiative.org', None,
'http://creativecommons.org/licenses/by/4.0/')
return
def __init__(self, graph_type, are_bnodes_skolemized, tax_ids=None):
super().__init__(graph_type, are_bnodes_skolemized, 'panther')
self.tax_ids = tax_ids
self.dataset = Dataset(
'panther', 'Protein ANalysis THrough Evolutionary Relationships',
'http://pantherdb.org/', None,
'http://www.pantherdb.org/terms/disclaimer.jsp')
# # Defaults
# if self.tax_ids is None:
# self.tax_ids = [9606, 10090, 7955]
if 'test_ids' not in config.get_config() \
or 'protein' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
else:
self.test_ids = config.get_config()['test_ids']['protein']
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'decipher')
self.dataset = Dataset(
'decipher', 'Development Disorder Genotype – Phenotype Database',
'https://decipher.sanger.ac.uk/', None,
'https://decipher.sanger.ac.uk/legal')
if 'test_ids' not in config.get_config() \
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = []
else:
self.test_ids = config.get_config()['test_ids']['disease']
self.g = self.graph
self.geno = Genotype(self.g)
self.model = Model(self.g)
return
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'genereviews')
self.dataset = Dataset(
'genereviews', 'Gene Reviews', 'http://genereviews.org/',
None, 'http://www.ncbi.nlm.nih.gov/books/NBK138602/')
self.dataset.set_citation('GeneReviews:NBK1116')
self.book_ids = set()
self.all_books = {}
if 'test_ids' not in config.get_config() or\
'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = list()
else:
# select ony those test ids that are omim's.
self.test_ids = config.get_config()['test_ids']['disease']
return
def __init__(self, graph_type, are_bnodes_skolemized,
tax_ids=None, gene_ids=None):
super().__init__(graph_type, are_bnodes_skolemized, 'hgnc')
self.tax_ids = tax_ids
self.gene_ids = gene_ids
self.dataset = Dataset(
'hgnc', 'HGNC', 'http://www.genenames.org', None)
self.gene_ids = []
if 'test_ids' not in config.get_config() \
or 'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
else:
self.gene_ids = config.get_config()['test_ids']['gene']
self.properties = Feature.properties
return
def __init__(self, graph_type, are_bnodes_skolemized, tax_ids=None, version=None):
"""
:param tax_ids: [int,], List of taxa
:return:
"""
super().__init__(graph_type, are_bnodes_skolemized, 'bgee')
if tax_ids is None:
self.tax_ids = Bgee.DEFAULT_TAXA
else:
logger.info("Filtering on taxa {}".format(tax_ids))
self.tax_ids = tax_ids
self.dataset = Dataset(
'Bgee', 'Bgee Gene expression data in animals',
'http://bgee.org/')
if version is None:
self.version = 'current'
else:
self.version = version
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'omia')
self.dataset = Dataset('omia',
'Online Mendelian Inheritance in Animals',
'http://omia.angis.org.au', None, None,
'http://sydney.edu.au/disclaimer.shtml')
self.id_hash = {
'article': {},
'phene': {},
'breed': {},
'taxon': {},
'gene': {}
}
self.label_hash = {}
# used to store the omia to omim phene mappings
self.omia_omim_map = {}
# used to store the unique genes that have phenes
# (for fetching orthology)
self.annotated_genes = set()
self.test_ids = {
'disease': [
'OMIA:001702', 'OMIA:001867', 'OMIA:000478', 'OMIA:000201',
'OMIA:000810', 'OMIA:001400'
],
'gene': [
492297, 434, 492296, 3430235, 200685834, 394659996, 200685845,
28713538, 291822383
],
'taxon': [9691, 9685, 9606, 9615, 9913, 93934, 37029, 9627, 9825],
# to be filled in during parsing of breed table
# for lookup by breed-associations
'breed': []
}
# to store a map of omia ids and any molecular info
# to write a report for curation
self.stored_omia_mol_gen = {}
self.g = self.graph
return
def __init__(self, graph_type, are_bnodes_skolemized):
Source.__init__(self, graph_type, are_bnodes_skolemized, 'mpd')
# @N, not sure if this step is required
self.stdevthreshold = 2
# update the dataset object with details about this resource
# @N: Note that there is no license as far as I can tell
self.dataset = Dataset(
'mpd', 'MPD', 'http://phenome.jax.org', None, None)
# TODO add a citation for mpd dataset as a whole
self.dataset.set_citation('PMID:15619963')
self.assayhash = {}
self.idlabel_hash = {}
# to store the mean/zscore of each measure by strain+sex
self.score_means_by_measure = {}
# to store the mean value for each measure by strain+sex
self.strain_scores_by_measure = {}
return
def __init__(self):
Source.__init__(self, 'genereviews')
self.load_bindings()
self.dataset = Dataset(
'genereviews', 'Gene Reviews', 'http://genereviews.org/',
None, 'http://www.ncbi.nlm.nih.gov/books/NBK138602/')
self.dataset.set_citation('GeneReviews:NBK1116')
self.gu = GraphUtils(curie_map.get())
self.book_ids = set()
self.all_books = {}
if 'test_ids' not in config.get_config() or\
'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = list()
else:
# select ony those test ids that are omim's.
self.test_ids = config.get_config()['test_ids']['disease']
return
class EOM(PostgreSQLSource):
"""
Elements of Morphology is a resource from NHGRI that has definitions of
morphological abnormalities, together with image depictions.
We pull those relationships, as well as our local mapping of equivalences
between EOM and HP terminologies.
The website is crawled monthly by NIF's DISCO crawler system,
which we utilize here.
Be sure to have pg user/password connection details in your conf.json file,
like:
dbauth : {
'disco' : {'user' : '<username>', 'password' : '<password>'}
}
Monarch-curated data for the HP to EOM mapping is stored at
https://phenotype-ontologies.googlecode.com
Since this resource is so small, the entirety of it is the "test" set.
"""
# we are using the production view here; should we be using services?
tables = [
'dvp.pr_nlx_157874_1'
]
files = {
'map': {
'file': 'hp-to-eom-mapping.tsv',
'url': 'https://phenotype-ontologies.googlecode.com/svn/trunk/src/ontology/hp/mappings/hp-to-eom-mapping.tsv'
}
}
def __init__(self):
super().__init__('eom')
self.namespaces.update(curie_map.get())
# update the dataset object with details about this resource
# TODO put this into a conf file?
self.dataset = Dataset(
'eom', 'EOM', 'http://elementsofmorphology.nih.gov', None,
'http://www.genome.gov/copyright.cfm',
'https://creativecommons.org/publicdomain/mark/1.0/')
# check if config exists; if it doesn't, error out and let user know
if 'dbauth' not in config.get_config() or \
'disco' not in config.get_config()['dbauth']:
logger.error("not configured with PG user/password.")
# source-specific warnings. will be cleared when resolved.
return
def fetch(self, is_dl_forced=False):
'''create the connection details for DISCO'''
cxn = config.get_config()['dbauth']['disco']
cxn.update(
{'host': 'nif-db.crbs.ucsd.edu', 'database': 'disco_crawler',
'port': 5432})
self.dataset.setFileAccessUrl(
''.join(('jdbc:postgresql://', cxn['host'], ':', str(cxn['port']),
'/', cxn['database'])))
# process the tables
# self.fetch_from_pgdb(self.tables,cxn,100) #for testing
self.fetch_from_pgdb(self.tables, cxn)
self.get_files(is_dl_forced)
# FIXME: Everything needed for data provenance?
st = os.stat('/'.join((self.rawdir, 'dvp.pr_nlx_157874_1')))
filedate = datetime.utcfromtimestamp(st[ST_CTIME]).strftime("%Y-%m-%d")
self.dataset.setVersion(filedate)
return
def parse(self, limit=None):
'''
Over ride Source.parse inherited via PostgreSQLSource
'''
if limit is not None:
logger.info("Only parsing first %s rows of each file", limit)
if self.testOnly:
self.testMode = True
logger.info("Parsing files...")
self._process_nlx_157874_1_view('/'.join((self.rawdir,
'dvp.pr_nlx_157874_1')),
limit)
self._map_eom_terms('/'.join((self.rawdir, self.files['map']['file'])),
limit)
logger.info("Finished parsing.")
self.load_bindings()
# since it's so small,
# we default to copying the entire graph to the test set
self.testgraph = self.graph
logger.info("Found %s nodes", len(self.graph))
return
def _process_nlx_157874_1_view(self, raw, limit=None):
"""
This table contains the Elements of Morphology data that has been
screen-scraped into DISCO.
Note that foaf:depiction is inverse of foaf:depicts relationship.
Since it is bad form to have two definitions,
we concatenate the two into one string.
Triples:
<eom id> a owl:Class
rdf:label Literal(eom label)
OIO:hasRelatedSynonym Literal(synonym list)
IAO:definition Literal(objective_def. subjective def)
foaf:depiction Literal(small_image_url),
Literal(large_image_url)
foaf:page Literal(page_url)
rdfs:comment Literal(long commented text)
:param raw:
:param limit:
:return:
"""
gu = GraphUtils(curie_map.get())
line_counter = 0
with open(raw, 'r') as f1:
f1.readline() # read the header row; skip
filereader = csv.reader(f1, delimiter='\t', quotechar='\"')
for line in filereader:
line_counter += 1
(morphology_term_id, morphology_term_num,
morphology_term_label, morphology_term_url,
terminology_category_label, terminology_category_url,
subcategory, objective_definition, subjective_definition,
comments, synonyms, replaces, small_figure_url,
large_figure_url, e_uid, v_uid, v_uuid,
v_last_modified) = line
# note:
# e_uid v_uuid v_last_modified terminology_category_url
# subcategory v_uid morphology_term_num
# terminology_category_label hp_label notes
# are currently unused.
# Add morphology term to graph as a class
# with label, type, and description.
gu.addClassToGraph(self.graph, morphology_term_id,
morphology_term_label)
# Assemble the description text
if subjective_definition != '' and not (
re.match(r'.+\.$', subjective_definition)):
# add a trailing period.
subjective_definition = subjective_definition.strip() + '.'
if objective_definition != '' and not (
re.match(r'.+\.$', objective_definition)):
# add a trailing period.
objective_definition = objective_definition.strip() + '.'
definition = \
' '.join(
(objective_definition, subjective_definition)).strip()
gu.addDefinition(self.graph, morphology_term_id, definition)
# <term id> FOAF:depicted_by literal url
# <url> type foaf:depiction
# do we want both images?
# morphology_term_id has depiction small_figure_url
if small_figure_url != '':
gu.addDepiction(self.graph, morphology_term_id,
small_figure_url)
# morphology_term_id has depiction large_figure_url
if large_figure_url != '':
gu.addDepiction(self.graph, morphology_term_id,
large_figure_url)
# morphology_term_id has comment comments
if comments != '':
gu.addComment(self.graph, morphology_term_id,
comments.strip())
if synonyms != '':
for s in synonyms.split(';'):
gu.addSynonym(
self.graph, morphology_term_id, s.strip(),
gu.properties['hasExactSynonym'])
# morphology_term_id hasRelatedSynonym replaces (; delimited)
if replaces != '' and replaces != synonyms:
for s in replaces.split(';'):
gu.addSynonym(
self.graph, morphology_term_id, s.strip(),
gu.properties['hasRelatedSynonym'])
# morphology_term_id has page morphology_term_url
gu.addPage(self.graph, morphology_term_id, morphology_term_url)
if limit is not None and line_counter > limit:
break
return
def _map_eom_terms(self, raw, limit=None):
"""
This table contains the HP ID mappings from the local tsv file.
Triples:
<eom id> owl:equivalentClass <hp id>
:param raw:
:param limit:
:return:
"""
gu = GraphUtils(curie_map.get())
line_counter = 0
with open(raw, 'r') as f1:
f1.readline() # read the header row; skip
for line in f1:
line_counter += 1
(morphology_term_id, morphology_term_label, hp_id, hp_label,
notes) = line.split('\t')
# Sub out the underscores for colons.
hp_id = re.sub('_', ':', hp_id)
if re.match(".*HP:.*", hp_id):
# add the HP term as a class
gu.addClassToGraph(self.graph, hp_id, None)
# Add the HP ID as an equivalent class
gu.addEquivalentClass(
self.graph, morphology_term_id, hp_id)
else:
logger.warning('No matching HP term for %s',
morphology_term_label)
if limit is not None and line_counter > limit:
break
return
def getTestSuite(self):
import unittest
# TODO PYLINT: Unable to import 'tests.test_eom'
from tests.test_eom import EOMTestCase
test_suite = unittest.TestLoader().loadTestsFromTestCase(EOMTestCase)
return test_suite
class Coriell(Source):
"""
The Coriell Catalog provided to Monarch includes metadata and descriptions
of NIGMS, NINDS, NHGRI, and NIA cell lines. These lines are made available
for research purposes. Here, we create annotations for the cell lines as
models of the diseases from which they originate.
We create a handle for a patient from which the given cell line is derived
(since there may be multiple cell lines created from a given patient).
A genotype is assembled for a patient, which includes a karyotype
(if specified) and/or a collection of variants.
Both the genotype (has_genotype) and disease are linked to the patient
(has_phenotype), and the cell line is listed as derived from the patient.
The cell line is classified by it's
[CLO cell type](http://www.ontobee.org/browser/index.php?o=clo),
which itself is linked to a tissue of origin.
Unfortunately, the omim numbers listed in this file are both for genes
& diseases; we have no way of knowing a priori if a designated omim number
is a gene or disease; so we presently link the patient to any omim id via
the has_phenotype relationship.
Notice: The Coriell catalog is delivered to Monarch in a specific format,
and requires ssh rsa fingerprint identification. Other groups wishing to
get this data in it's raw form will need to contact Coriell for credential
This needs to be placed into your configuration file for it to work.
"""
terms = {
'cell_line_repository': 'CLO:0000008',
'race': 'SIO:001015',
'ethnic_group': 'EFO:0001799',
'age': 'EFO:0000246',
'sampling_time': 'EFO:0000689',
'collection': 'ERO:0002190'
}
files = {
'NINDS': {
'file': 'NINDS.csv',
'id': 'NINDS',
'label': 'NINDS Human Genetics DNA and Cell line Repository',
'page': 'https://catalog.coriell.org/1/NINDS'},
'NIGMS': {
'file': 'NIGMS.csv',
'id': 'NIGMS',
'label': 'NIGMS Human Genetic Cell Repository',
'page': 'https://catalog.coriell.org/1/NIGMS'},
'NIA': {
'file': 'NIA.csv',
'id': 'NIA',
'label': 'NIA Aging Cell Repository',
'page': 'https://catalog.coriell.org/1/NIA'},
'NHGRI': {
'file': 'NHGRI.csv',
'id': 'NHGRI',
'label': 'NHGRI Sample Repository for Human Genetic Research',
'page': 'https://catalog.coriell.org/1/NHGRI'}
}
# the following will house the specific cell lines to use for test output
test_lines = [
'ND02380', 'ND02381', 'ND02383', 'ND02384', 'GM17897', 'GM17898',
'GM17896', 'GM17944', 'GM17945', 'ND00055', 'ND00094', 'ND00136',
'GM17940', 'GM17939', 'GM20567', 'AG02506', 'AG04407', 'AG07602'
'AG07601', 'GM19700', 'GM19701', 'GM19702', 'GM00324', 'GM00325',
'GM00142', 'NA17944', 'AG02505', 'GM01602', 'GM02455', 'AG00364',
'GM13707', 'AG00780']
def __init__(self):
Source.__init__(self, 'coriell')
self.load_bindings()
self.dataset = Dataset(
'coriell', 'Coriell', 'http://ccr.coriell.org/', None)
# data-source specific warnings
# (will be removed when issues are cleared)
logger.warning(
'We assume that if a species is not provided, '
'that it is a Human-derived cell line')
logger.warning(
'We map all omim ids as a disease/phenotype entity, '
'but should be fixed in the future')
# check if config exists; if it doesn't, error out and let user know
if 'dbauth' not in config.get_config() or \
'coriell' not in config.get_config()['dbauth']:
logger.error("not configured with FTP user/password.")
return
def fetch(self, is_dl_forced=False):
"""
Here we connect to the coriell sftp server using private connection
details. They dump bi-weekly files with a timestamp in the filename.
For each catalog, we poll the remote site and pull the most-recently
updated file, renaming it to our local *_latest.csv.
Be sure to have pg user/password connection details in your conf.json
file, like:
dbauth : {
"coriell" : {
"user" : "<username>", "password" : "<password>",
"host" : <host>, "private_key"=path/to/rsa_key}
}
:param is_dl_forced:
:return:
"""
host = config.get_config()['dbauth']['coriell']['host']
user = config.get_config()['dbauth']['coriell']['user']
passwd = config.get_config()['dbauth']['coriell']['password']
key = config.get_config()['dbauth']['coriell']['private_key']
with pysftp.Connection(
host, username=user, password=passwd, private_key=key) as sftp:
# check to make sure each file is in there
# get the remote files
remote_files = sftp.listdir_attr()
files_by_repo = {}
for attr in remote_files:
# for each catalog, get the most-recent filename
m = re.match('(NIGMS|NIA|NHGRI|NINDS)', attr.filename)
if m is not None and len(m.groups()) > 0:
# there should just be one now
files_by_repo[m.group(1)] = attr
# sort each array in hash,
# & get the name and time of the most-recent file for each catalog
for r in self.files:
logger.info("Checking on %s catalog file", r)
fname = self.files[r]['file']
remotef = files_by_repo[r]
target_name = '/'.join((self.rawdir, fname))
# check if the local file is out of date, if so, download.
# otherwise, skip.
# we rename (for simplicity) the original file
st = None
if os.path.exists(target_name):
st = os.stat(target_name)
logger.info(
"Local file date: %s",
datetime.utcfromtimestamp(st[stat.ST_CTIME]))
if st is None or remotef.st_mtime > st[stat.ST_CTIME]:
if st is None:
logger.info(
"File does not exist locally; downloading...")
else:
logger.info(
"There's a new version of %s catalog available; "
"downloading...", r)
sftp.get(remotef.filename, target_name)
logger.info(
"Fetched remote %s -> %s",
remotef.filename, target_name)
st = os.stat(target_name)
filedate = \
datetime.utcfromtimestamp(
remotef.st_mtime).strftime("%Y-%m-%d")
logger.info(
"New file date: %s",
datetime.utcfromtimestamp(st[stat.ST_CTIME]))
else:
logger.info("File %s exists; using local copy", fname)
filedate = \
datetime.utcfromtimestamp(
st[stat.ST_CTIME]).strftime("%Y-%m-%d")
self.dataset.setFileAccessUrl(remotef.filename)
self.dataset.setVersion(filedate)
return
def parse(self, limit=None):
if limit is not None:
logger.info("Only parsing first %s rows of each file", limit)
logger.info("Parsing files...")
if self.testOnly:
self.testMode = True
for f in self.files:
file = '/'.join((self.rawdir, self.files[f]['file']))
self._process_collection(
self.files[f]['id'],
self.files[f]['label'],
self.files[f]['page'])
self._process_data(file, limit)
logger.info("Finished parsing.")
self.load_bindings()
logger.info("Found %d nodes in graph", len(self.graph))
logger.info("Found %d nodes in testgraph", len(self.testgraph))
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_collection(self, collection_id, label, page):
"""
This function will process the data supplied internally
about the repository from Coriell.
Triples:
Repository a ERO:collection
rdf:label Literal(label)
foaf:page Literal(page)
:param collection_id:
:param label:
:param page:
:return:
"""
# ############# BUILD THE CELL LINE REPOSITORY #############
for g in [self.graph, self.testgraph]:
# FIXME: How to devise a label for each repository?
gu = GraphUtils(curie_map.get())
repo_id = 'CoriellCollection:'+collection_id
repo_label = label
repo_page = page
gu.addIndividualToGraph(
g, repo_id, repo_label, self.terms['collection'])
gu.addPage(g, repo_id, repo_page)
return
@staticmethod
def _map_cell_type(sample_type):
ctype = None
type_map = {
# FIXME: mesenchymal stem cell of adipose
'Adipose stromal cell': 'CL:0002570',
# FIXME: amniocyte?
'Amniotic fluid-derived cell line': 'CL:0002323',
# B cell
'B-Lymphocyte': 'CL:0000236',
# FIXME: No Match
'Chorionic villus-derived cell line': 'CL:0000000',
# endothelial cell
'Endothelial': 'CL:0000115',
# epithelial cell
'Epithelial': 'CL:0000066',
# FIXME: No Match. "Abnormal precursor (virally transformed)
# of mouse erythrocytes that can be grown in culture and
# induced to differentiate by treatment with, for example, DMSO."
'Erythroleukemic cell line': 'CL:0000000',
'Fibroblast': 'CL:0000057', # fibroblast
'Keratinocyte': 'CL:0000312', # keratinocyte
'Melanocyte': 'CL:0000148', # melanocyte
'Mesothelial': 'CL:0000077',
'Microcell hybrid': 'CL:0000000', # FIXME: No Match
'Myoblast': 'CL:0000056', # myoblast
'Smooth muscle': 'CL:0000192', # smooth muscle cell
'Stem cell': 'CL:0000034', # stem cell
'T-Lymphocyte': 'CL:0000084', # T cell
# FIXME: No Match. "Cells isolated from a mass of neoplastic cells,
# i.e., a growth formed by abnormal cellular proliferation."
# Oncocyte? CL:0002198
'Tumor-derived cell line': 'CL:0002198'
}
if sample_type.strip() in type_map:
ctype = type_map.get(sample_type)
else:
logger.error("Cell type not mapped: %s", sample_type)
return ctype
@staticmethod
def _map_race(race):
rtype = None
type_map = {
'African American': 'EFO:0003150',
# 'American Indian': 'EFO',
'Asian': 'EFO:0003152',
# FIXME: Asian?
'Asian; Other': 'EFO:0003152',
# Asian Indian
'Asiatic Indian': 'EFO:0003153',
# FIXME: African American? There is also African.
'Black': 'EFO:0003150',
'Caucasian': 'EFO:0003156',
'Chinese': 'EFO:0003157',
'East Indian': 'EFO:0003158', # Eastern Indian
'Filipino': 'EFO:0003160',
# Hispanic: EFO:0003169, Latino: EFO:0003166 see next
'Hispanic/Latino': 'EFO:0003169',
'Japanese': 'EFO:0003164',
'Korean': 'EFO:0003165',
# 'More than one race': 'EFO',
# 'Not Reported': 'EFO',
# 'Other': 'EFO',
# Asian/Pacific Islander
'Pacific Islander': 'EFO:0003154',
# Asian/Pacific Islander
'Polynesian': 'EFO:0003154',
# 'Unknown': 'EFO',
# Asian
'Vietnamese': 'EFO:0003152',
}
if race.strip() in type_map:
rtype = type_map.get(race)
else:
logger.warning("Race type not mapped: %s", race)
return rtype
@staticmethod
def _map_species(species):
tax = None
type_map = {
'Mus musculus': 'NCBITaxon:10090',
'Peromyscus peromyscus californicus': 'NCBITaxon:42520',
'Peromyscus peromyscus maniculatus': 'NCBITaxon:10042',
'Peromyscus peromyscus leucopus': 'NCBITaxon:10041',
'Peromyscus peromyscus polionotus': 'NCBITaxon:42413',
'Macaca fascicularis': 'NCBITaxon:9541',
'Rattus norvegicus': 'NCBITaxon:10116',
'Papio anubis': 'NCBITaxon:9555',
'Cricetulus griseus': 'NCBITaxon:10029',
'Geochelone elephantopus': 'NCBITaxon:66189',
'Muntiacus muntjak': 'NCBITaxon:9888',
'Ailurus fulgens': 'NCBITaxon:9649',
'Sus scrofa': 'NCBITaxon:9823',
'Bos taurus': 'NCBITaxon:9913',
'Oryctolagus cuniculus': 'NCBITaxon:9986',
'Macaca nemestrina': 'NCBITaxon:9545',
'Canis familiaris': 'NCBITaxon:9615',
'Equus caballus': 'NCBITaxon:9796',
'Macaca mulatta': 'NCBITaxon:9544',
'Mesocricetus auratus': 'NCBITaxon:10036',
'Macaca nigra': 'NCBITaxon:54600',
'Erythrocebus patas': 'NCBITaxon:9538',
'Pongo pygmaeus': 'NCBITaxon:9600',
'Callicebus moloch': 'NCBITaxon:9523',
'Lagothrix lagotricha': 'NCBITaxon:9519',
'Saguinus fuscicollis': 'NCBITaxon:9487',
'Saimiri sciureus': 'NCBITaxon:9521',
'Saguinus labiatus': 'NCBITaxon:78454',
'Pan paniscus': 'NCBITaxon:9597',
'Ovis aries': 'NCBITaxon:9940',
'Felis catus': 'NCBITaxon:9685',
'H**o sapiens': 'NCBITaxon:9606'
}
if species.strip() in type_map:
tax = type_map.get(species)
else:
logger.warning("Species type not mapped: %s", species)
return tax
@staticmethod
def _map_collection(collection):
ctype = None
type_map = {
'NINDS Repository':
'CoriellCollection:NINDS',
'NIGMS Human Genetic Cell Repository':
'CoriellCollection:NIGMS',
'NIA Aging Cell Culture Repository':
'CoriellCollection:NIA',
'NHGRI Sample Repository for Human Genetic Research':
'CoriellCollection:NHGRI'
}
if collection.strip() in type_map:
ctype = type_map.get(collection)
else:
logger.warning("ERROR: Collection type not mapped: %s", collection)
return ctype
@staticmethod
def _get_affected_chromosomes_from_karyotype(karyotype):
affected_chromosomes = set()
chr_regex = r'(\d+|X|Y|M|\?);?'
abberation_regex = r'(?:add|del|der|i|idic|inv|r|rec|t)\([\w;]+\)'
sex_regex = r'(?:;)(X{2,}Y+|X?Y{2,}|X{3,}|X|Y)(?:;|$)'
# first fetch the set of abberations
abberations = re.findall(abberation_regex, karyotype)
# iterate over them to get the chromosomes
for a in abberations:
chrs = re.findall(chr_regex, a)
affected_chromosomes = affected_chromosomes.union(set(chrs))
# remove the ? as a chromosome, since it isn't valid
if '?' in affected_chromosomes:
affected_chromosomes.remove('?')
# check to see if there are any abnormal sex chromosomes
m = re.search(sex_regex, karyotype)
if m is not None:
if re.search(r'X?Y{2,}', m.group(1)):
# this is the only case where there is an extra Y chromosome
affected_chromosomes.add('Y')
else:
affected_chromosomes.add('X')
return affected_chromosomes
@staticmethod
def _is_normal_karyotype(karyotype):
"""
This will default to true if no karyotype is provided.
This is assuming human karyotypes.
:param karyotype:
:return:
"""
is_normal = True
if karyotype is not None:
karyotype = karyotype.strip()
if karyotype not in ['46;XX', '46;XY', '']:
is_normal = False
return is_normal
def getTestSuite(self):
import unittest
from tests.test_coriell import CoriellTestCase
# TODO add G2PAssoc, Genotype tests
test_suite = \
unittest.TestLoader().loadTestsFromTestCase(CoriellTestCase)
return test_suite
class Source:
"""
Abstract class for any data sources that we'll import and process.
Each of the subclasses will fetch() the data, scrub() it as necessary,
then parse() it into a graph. The graph will then be written out to
a single self.name().<dest_fmt> file.
Also provides a means to marshal metadata in a consistent fashion
Houses the global translation table (from ontology label to ontology term)
so it may as well be used everywhere.
"""
namespaces = {}
files = {}
def __init__(
self,
graph_type='rdf_graph', # or streamed_graph
are_bnodes_skized=False, # typically True
name=None, # identifier; make an IRI for nquads
ingest_title=None,
ingest_url=None,
license_url=None, # only if it is _our_ lic
data_rights=None, # external page that points to their current lic
file_handle=None
):
# pull in the common test identifiers
self.all_test_ids = self.open_and_parse_yaml('../../resources/test_ids.yaml')
self.graph_type = graph_type
self.are_bnodes_skized = are_bnodes_skized
self.ingest_url = ingest_url
self.ingest_title = ingest_title
self.localtt = self.load_local_translationtable(name)
if name is not None:
self.name = name.lower()
elif self.whoami() is not None:
self.name = self.whoami().lower()
LOG.info("Processing Source \"%s\"", self.name)
self.test_only = False
self.path = ""
# to be used to store a subset of data for testing downstream.
self.triple_count = 0
self.outdir = 'out'
self.testdir = 'tests'
self.rawdir = 'raw'
self.rawdir = '/'.join((self.rawdir, self.name))
self.testname = name + "_test"
self.testfile = '/'.join((self.outdir, self.testname + ".ttl"))
self.datasetfile = None
# still need to pull in file suffix -- this ia a curie not a url
self.archive_url = 'MonarchArchive:' + 'ttl/' + self.name + '.ttl'
# if raw data dir doesn't exist, create it
if not os.path.exists(self.rawdir):
os.makedirs(self.rawdir)
pth = os.path.abspath(self.rawdir)
LOG.info("creating raw directory for %s at %s", self.name, pth)
# if output dir doesn't exist, create it
if not os.path.exists(self.outdir):
os.makedirs(self.outdir)
pth = os.path.abspath(self.outdir)
LOG.info("created output directory %s", pth)
LOG.info("Creating Test graph %s", self.testname)
# note: tools such as protoge need slolemized blank nodes
self.testgraph = RDFGraph(True, self.testname)
if graph_type == 'rdf_graph':
graph_id = ':MONARCH_' + str(self.name) + "_" + \
datetime.now().isoformat(' ').split()[0]
LOG.info("Creating graph %s", graph_id)
self.graph = RDFGraph(are_bnodes_skized, graph_id)
elif graph_type == 'streamed_graph':
# need to expand on export formats
dest_file = open(pth + '/' + name + '.nt', 'w') # where is the close?
self.graph = StreamedGraph(are_bnodes_skized, dest_file)
# leave test files as turtle (better human readibility)
else:
LOG.error(
"%s graph type not supported\n"
"valid types: rdf_graph, streamed_graph", graph_type)
# pull in global ontology mapping datastructures
self.globaltt = self.graph.globaltt
self.globaltcid = self.graph.globaltcid
self.curie_map = self.graph.curie_map
# self.prefix_base = {v: k for k, v in self.curie_map.items()}
# will be set to True if the intention is
# to only process and write the test data
self.test_only = False
self.test_mode = False
# this may eventually support Bagits
self.dataset = Dataset(
self.archive_url,
self.ingest_title,
self.ingest_url,
None, # description
license_url, # only _OUR_ lic
data_rights, # tries to point to others lics
graph_type,
file_handle
)
for graph in [self.graph, self.testgraph]:
self.declareAsOntology(graph)
def fetch(self, is_dl_forced=False):
"""
abstract method to fetch all data from an external resource.
this should be overridden by subclasses
:return: None
"""
raise NotImplementedError
def parse(self, limit):
"""
abstract method to parse all data from an external resource,
that was fetched in fetch() this should be overridden by subclasses
:return: None
"""
raise NotImplementedError
def write(self, fmt='turtle', stream=None):
"""
This convenience method will write out all of the graphs
associated with the source.
Right now these are hardcoded to be a single "graph"
and a "src_dataset.ttl" and a "src_test.ttl"
If you do not supply stream='stdout'
it will default write these to files.
In addition, if the version number isn't yet set in the dataset,
it will be set to the date on file.
:return: None
"""
fmt_ext = {
'rdfxml': 'xml',
'turtle': 'ttl',
'nt': 'nt', # ntriples
'nquads': 'nq',
'n3': 'n3' # notation3
}
# make the regular graph output file
dest = None
if self.name is not None:
dest = '/'.join((self.outdir, self.name))
if fmt in fmt_ext:
dest = '.'.join((dest, fmt_ext.get(fmt)))
else:
dest = '.'.join((dest, fmt))
LOG.info("Setting outfile to %s", dest)
# make the dataset_file name, always format as turtle
self.datasetfile = '/'.join(
(self.outdir, self.name + '_dataset.ttl'))
LOG.info("Setting dataset file to %s", self.datasetfile)
if self.dataset is not None and self.dataset.version is None:
self.dataset.set_version_by_date()
LOG.info("No version for %s setting to date issued.", self.name)
else:
LOG.warning("No output file set. Using stdout")
stream = 'stdout'
gu = GraphUtils(None)
# the _dataset description is always turtle
gu.write(self.dataset.getGraph(), 'turtle', filename=self.datasetfile)
if self.test_mode:
# unless we stop hardcoding, the test dataset is always turtle
LOG.info("Setting testfile to %s", self.testfile)
gu.write(self.testgraph, 'turtle', filename=self.testfile)
# print graph out
if stream is None:
outfile = dest
elif stream.lower().strip() == 'stdout':
outfile = None
else:
LOG.error("I don't understand our stream.")
return
gu.write(self.graph, fmt, filename=outfile)
def whoami(self):
'''
pointless convieniance
'''
LOG.info("Ingest is %s", self.name)
@staticmethod
def make_id(long_string, prefix='MONARCH'):
"""
a method to create DETERMINISTIC identifiers
based on a string's digest. currently implemented with sha1
:param long_string:
:return:
"""
return ':'.join((prefix, Source.hash_id(long_string)))
@staticmethod
def hash_id(wordage): # same as graph/GraphUtils.digest_id(wordage)
"""
prepend 'b' to avoid leading with digit
truncate to a 20 char sized word with a leading 'b'
return truncated sha1 hash of string.
by the birthday paradox;
expect 50% chance of collision after 69 billion invocations
however these are only hoped to be unique within a single file
Consider reducing to 17 hex chars to fit in a 64 bit word
16 discounting a leading constant
gives a 50% chance of collision at about 4.3b billion unique input strings
(currently _many_ orders of magnitude below that)
:param long_string: str string to be hashed
:return: str hash of id
"""
return 'b' + hashlib.sha1(wordage.encode('utf-8')).hexdigest()[1:20]
def checkIfRemoteIsNewer(self, remote, local, headers):
"""
Given a remote file location, and the corresponding local file
this will check the datetime stamp on the files to see if the remote
one is newer.
This is a convenience method to be used so that we don't have to
re-fetch files that we already have saved locally
:param remote: URL of file to fetch from remote server
:param local: pathname to save file to locally
:return: True if the remote file is newer and should be downloaded
"""
LOG.info("Checking if remote file is newer than local \n(%s)", local)
# check if local file exists
# if no local file, then remote is newer
if os.path.exists(local):
LOG.info("Local File exists as %s", local)
else:
LOG.info("Local File does NOT exist as %s", local)
return True
# get remote file details
if headers is None:
headers = self._get_default_request_headers()
req = urllib.request.Request(remote, headers=headers)
LOG.info("Request header: %s", str(req.header_items()))
response = urllib.request.urlopen(req)
try:
resp_headers = response.info()
size = resp_headers.get('Content-Length')
last_modified = resp_headers.get('Last-Modified')
except urllib.error.URLError as err:
resp_headers = None
size = 0
last_modified = None
LOG.error(err)
if size is not None and size != '':
size = int(size)
else:
size = 0
fstat = os.stat(local)
LOG.info(
"Local File date: %s",
datetime.utcfromtimestamp(fstat[ST_CTIME]))
if last_modified is not None:
# Thu, 07 Aug 2008 16:20:19 GMT
dt_obj = datetime.strptime(
last_modified, "%a, %d %b %Y %H:%M:%S %Z")
# get local file details
# check date on local vs remote file
if dt_obj > datetime.utcfromtimestamp(fstat[ST_CTIME]):
# check if file size is different
if fstat[ST_SIZE] < size:
LOG.info("New Remote File exists")
return True
if fstat[ST_SIZE] > size:
LOG.warning("New Remote File exists but it is SMALLER")
return True
# filesize is a fairly imperfect metric here
LOG.info("New Remote fFle has same filesize--will not download")
elif fstat[ST_SIZE] != size:
LOG.info(
"Remote File is %i \t Local File is %i", size, fstat[ST_SIZE])
return True
return False
def get_files(self, is_dl_forced, files=None):
"""
Given a set of files for this source, it will go fetch them, and
set a default version by date. If you need to set the version number
by another method, then it can be set again.
:param is_dl_forced - boolean
:param files dict - override instance files dict
:return: None
"""
fstat = None
if files is None:
files = self.files
for fname in files:
headers = None
filesource = files[fname]
if 'headers' in filesource:
headers = filesource['headers']
LOG.info("Getting %s", fname)
# if the key 'clean' exists in the sources `files` dict
# expose that instead of the longer url
if 'clean' in filesource and filesource['clean'] is not None:
self.dataset.setFileAccessUrl(filesource['clean'])
else:
self.dataset.setFileAccessUrl(filesource['url'])
LOG.info('Fetching %s', filesource['url'])
self.fetch_from_url(
filesource['url'], '/'.join((self.rawdir, filesource['file'])),
is_dl_forced, headers)
fstat = os.stat('/'.join((self.rawdir, filesource['file'])))
# only keeping the date from the last file
filedate = datetime.utcfromtimestamp(fstat[ST_CTIME]).strftime("%Y-%m-%d")
# FIXME
# change this so the date is attached only to each file, not the entire dataset
self.dataset.set_date_issued(filedate)
def fetch_from_url(
self, remotefile, localfile=None, is_dl_forced=False, headers=None):
"""
Given a remote url and a local filename, attempt to determine
if the remote file is newer; if it is,
fetch the remote file and save it to the specified localfile,
reporting the basic file information once it is downloaded
:param remotefile: URL of remote file to fetch
:param localfile: pathname of file to save locally
:return: None
"""
response = None
if ((is_dl_forced is True) or localfile is None or
(self.checkIfRemoteIsNewer(remotefile, localfile, headers))):
# TODO url verification, etc
if headers is None:
headers = self._get_default_request_headers()
request = urllib.request.Request(remotefile, headers=headers)
response = urllib.request.urlopen(request)
if localfile is not None:
with open(localfile, 'wb') as binwrite:
while True:
chunk = response.read(CHUNK)
if not chunk:
break
binwrite.write(chunk)
LOG.info("Finished. Wrote file to %s", localfile)
if self.compare_local_remote_bytes(remotefile, localfile, headers):
LOG.debug("local file is same size as remote after download")
else:
raise Exception(
"Error downloading file: local file size != remote file size")
fstat = os.stat(localfile)
LOG.info("file size: %s", fstat[ST_SIZE])
LOG.info(
"file created: %s", time.asctime(time.localtime(fstat[ST_CTIME])))
else:
LOG.error('Local filename is required')
exit(-1)
else:
LOG.info("Using existing file %s", localfile)
return response
# TODO: rephrase as mysql-dump-xml specific format
def process_xml_table(self, elem, table_name, processing_function, limit):
"""
This is a convenience function to process the elements of an xml dump of
a mysql relational database.
The "elem" is akin to a mysql table, with it's name of ```table_name```.
It will process each ```row``` given the ```processing_function``` supplied.
:param elem: The element data
:param table_name: The name of the table to process
:param processing_function: The row processing function
:param limit:
Appears to be making calls to the elementTree library
although it not explicitly imported here.
:return:
"""
line_counter = 0
table_data = elem.find("[@name='" + table_name + "']")
if table_data is not None:
LOG.info("Processing " + table_name)
row = {}
for line in table_data.findall('row'):
for field in line.findall('field'):
atts = dict(field.attrib)
row[atts['name']] = field.text
processing_function(row)
line_counter += 1
if self.test_mode and limit is not None and line_counter > limit:
continue
elem.clear() # discard the element
@staticmethod
def _check_list_len(row, length):
"""
Sanity check for csv parser
:param row
:param length
:return:None
"""
if len(row) != length:
raise Exception(
"row length does not match expected length of " +
str(length) + "\nrow: " + str(row))
@staticmethod
def get_file_md5(directory, filename, blocksize=2**20):
# reference:
# http://stackoverflow.com/questions/1131220/get-md5-hash-of-big-files-in-python
md5 = hashlib.md5()
with open(os.path.join(directory, filename), "rb") as bin_reader:
while True:
buff = bin_reader.read(blocksize)
if not buff:
break
md5.update(buff)
return md5.hexdigest()
def get_remote_content_len(self, remote, headers=None):
"""
:param remote:
:return: size of remote file
"""
if headers is None:
headers = self._get_default_request_headers()
req = urllib.request.Request(remote, headers=headers)
try:
response = urllib.request.urlopen(req)
resp_header = response.info()
byte_size = resp_header.get('Content-length')
except OSError as err:
byte_size = None
LOG.error(err)
return byte_size
@staticmethod
def get_local_file_size(localfile):
"""
:param localfile:
:return: size of file
"""
byte_size = os.stat(localfile)
return byte_size[ST_SIZE]
def compare_local_remote_bytes(self, remotefile, localfile, remote_headers=None):
"""
test to see if fetched file is the same size as the remote file
using information in the content-length field in the HTTP header
:return: True or False
"""
is_equal = True
remote_size = self.get_remote_content_len(remotefile, remote_headers)
local_size = self.get_local_file_size(localfile)
if remote_size is not None and local_size != int(remote_size):
is_equal = False
LOG.error(
'local file and remote file different sizes\n'
'%s has size %s, %s has size %s',
localfile, local_size, remotefile, remote_size)
return is_equal
@staticmethod
def file_len(fname):
with open(fname) as lines:
length = sum(1 for line in lines)
return length
@staticmethod
def get_eco_map(url):
"""
To convert the three column file to
a hashmap we join primary and secondary keys,
for example
IEA GO_REF:0000002 ECO:0000256
IEA GO_REF:0000003 ECO:0000501
IEA Default ECO:0000501
becomes
IEA-GO_REF:0000002: ECO:0000256
IEA-GO_REF:0000003: ECO:0000501
IEA: ECO:0000501
:return: dict
"""
# this would go in a translation table but it is generated dynamically
# maybe when we move to a make driven system
eco_map = {}
request = urllib.request.Request(url)
response = urllib.request.urlopen(request)
for line in response:
line = line.decode('utf-8').rstrip()
if re.match(r'^#', line):
continue
(code, go_ref, eco_curie) = line.split('\t')
if go_ref != 'Default':
eco_map["{}-{}".format(code, go_ref)] = eco_curie
else:
eco_map[code] = eco_curie
return eco_map
def settestonly(self, testonly):
"""
Set that this source should only be processed in testMode
:param testOnly:
:return: None
"""
self.test_only = testonly
def settestmode(self, mode):
"""
Set testMode to (mode).
- True: run the Source in testMode;
- False: run it in full mode
:param mode:
:return: None
"""
self.test_mode = mode
def getTestSuite(self):
"""
An abstract method that should be overwritten with
tests appropriate for the specific source.
:return:
"""
return None
# TODO: pramaterising the release date
def declareAsOntology(self, graph):
"""
The file we output needs to be declared as an ontology,
including it's version information.
TEC: I am not convinced dipper reformatting external data as RDF triples
makes an OWL ontology (nor that it should be considered a goal).
Proper ontologies are built by ontologists. Dipper reformats data
and annotates/decorates it with a minimal set of carefully arranged
terms drawn from from multiple proper ontologies.
Which allows the whole (dipper's RDF triples and parent ontologies)
to function as a single ontology we can reason over when combined
in a store such as SciGraph.
Including more than the minimal ontological terms in dipper's RDF
output constitutes a liability as it allows greater divergence
between dipper artifacts and the proper ontologies.
Further information will be augmented in the dataset object.
:param version:
:return:
"""
# <http://data.monarchinitiative.org/ttl/biogrid.ttl> a owl:Ontology ;
# owl:versionInfo
# <https://archive.monarchinitiative.org/YYYYMM/ttl/biogrid.ttl>
model = Model(graph)
# is self.outfile suffix set yet???
ontology_file_id = 'MonarchData:' + self.name + ".ttl"
model.addOntologyDeclaration(ontology_file_id)
# add timestamp as version info
cur_time = datetime.now()
t_string = cur_time.strftime("%Y-%m-%d")
ontology_version = t_string
# TEC this means the MonarchArchive IRI needs the release updated
# maybe extract the version info from there
# should not hardcode the suffix as it may change
archive_url = 'MonarchArchive:' + 'ttl/' + self.name + '.ttl'
model.addOWLVersionIRI(ontology_file_id, archive_url)
model.addOWLVersionInfo(ontology_file_id, ontology_version)
# TODO make sure this is synced with the Dataset class
@staticmethod
def remove_backslash_r(filename, encoding):
"""
A helpful utility to remove Carriage Return from any file.
This will read a file into memory,
and overwrite the contents of the original file.
TODO: This function may be a liability
:param filename:
:return:
"""
with open(filename, 'r', encoding=encoding, newline=r'\n') as filereader:
contents = filereader.read()
contents = re.sub(r'\r', '', contents)
with open(filename, "w") as filewriter:
filewriter.truncate()
filewriter.write(contents)
@staticmethod
def open_and_parse_yaml(yamlfile):
"""
:param file: String, path to file containing label-id mappings in
the first two columns of each row
:return: dict where keys are labels and values are ids
"""
# ??? what if the yaml file does not contain a dict datastructure?
mapping = dict()
if os.path.exists(os.path.join(os.path.dirname(__file__), yamlfile)):
map_file = open(os.path.join(os.path.dirname(__file__), yamlfile), 'r')
mapping = yaml.safe_load(map_file)
map_file.close()
else:
LOG.warning("file: %s not found", yamlfile)
return mapping
@staticmethod
def parse_mapping_file(file):
"""
:param file: String, path to file containing label-id mappings
in the first two columns of each row
:return: dict where keys are labels and values are ids
"""
id_map = {}
if os.path.exists(os.path.join(os.path.dirname(__file__), file)):
with open(os.path.join(os.path.dirname(__file__), file)) as tsvfile:
reader = csv.reader(tsvfile, delimiter="\t")
for row in reader:
key = row[0]
value = row[1]
id_map[key] = value
return id_map
@staticmethod
def _get_default_request_headers():
return {
'User-Agent': USER_AGENT
}
# @staticmethod
# def getTestSuite(ingest): # WIP
# '''
# try to avoid having one of these per ingest
# '''
# import unittest
# testcase = ingest + 'TestCase'
# # construct import names ... how
# from tests.test_ + ingest import testcase
# return unittest.TestLoader().loadTestsFromTestCase(testcase)
def load_local_translationtable(self, name):
'''
Load "ingest specific" translation from whatever they called something
to the ontology label we need to map it to.
To facilitate seeing more ontology labels in dipper ingests
a reverse mapping from ontology labels to external strings is also generated
and available as a dict localtcid
'---\n# %s.yaml\n"": "" # example'
'''
localtt_file = 'translationtable/' + name + '.yaml'
try:
with open(localtt_file):
pass
except IOError:
# write a stub file as a place holder if none exists
with open(localtt_file, 'w') as write_yaml:
print('---\n# %s.yaml\n"": "" # example' % name, file=write_yaml)
finally:
with open(localtt_file, 'r') as read_yaml:
localtt = yaml.safe_load(read_yaml)
# inverse local translation.
# note: keeping this invertable will be work.
# Useful to not litter an ingest with external syntax
self.localtcid = {v: k for k, v in localtt.items()}
return localtt
def resolve(self, word, mandatory=True, default=None):
'''
composite mapping
given f(x) and g(x)
here: localtt & globaltt respectivly
return g(f(x))|g(x)||f(x)|x in order of preference
returns x on fall through if finding a mapping
is not mandatory (by default finding is mandatory).
This may be specialized further from any mapping
to a global mapping only; if need be.
:param word: the srting to find as a key in translation tables
:param mandatory: boolean to cauae failure when no key exists
:return
value from global translation table,
or value from local translation table,
or the query key if finding a value is not mandatory (in this order)
'''
assert word is not None
# we may not agree with a remote sources use of a global term we have
# this provides opportunity for us to override
if word in self.localtt:
label = self.localtt[word]
if label in self.globaltt:
term_id = self.globaltt[label]
else:
logging.info(
"Translated to '%s' but no global term_id for: '%s'", label, word)
term_id = label
elif word in self.globaltt:
term_id = self.globaltt[word]
else:
if mandatory:
raise KeyError("Mapping required for: ", word)
logging.warning("We have no translation for: '%s'", word)
if default is not None:
term_id = default
else:
term_id = word
return term_id
@staticmethod
def check_fileheader(expected, received):
'''
Compare file headers received versus file headers expected
if the expected headers are a subset (proper or not)
of received headers report suscess (warn if proper subset)
param: expected list
param: received list
return: truthyness
'''
exp = set(expected)
got = set(received)
if expected != received:
LOG.error('\nExpected header: %s\nRecieved header: %s', expected, received)
# pass reordering and adding new columns (after protesting)
# hard fail on missing expected columns (temper with mandatory cols?)
if exp - got != set():
LOG.error('Missing: %s', exp - got)
raise AssertionError('Incomming headers are missing expected column.')
if got - exp != set():
LOG.warrning('Addtional new columns: %s', got - exp)
else:
LOG.warrning('Check columns order')
return (exp ^ got) & exp == set()
class CTD(Source):
"""
The Comparative Toxicogenomics Database (CTD) includes curated data
describing cross-species chemical–gene/protein interactions and
chemical– and gene–disease associations to illuminate molecular mechanisms
underlying variable susceptibility and environmentally influenced diseases.
Here, we fetch, parse, and convert data from CTD into triples,
leveraging only the associations based on DIRECT evidence
(not using the inferred associations).
We currently process the following associations:
* chemical-disease
* gene-pathway
* gene-disease
CTD curates relationships between genes and chemicals/diseases with
marker/mechanism and/or therapeutic.
Unfortunately, we cannot disambiguate between marker (gene expression) and
mechanism (causation) for these associations. Therefore, we are left to
relate these simply by "marker".
CTD also pulls in genes and pathway membership from KEGG and REACTOME.
We create groups of these following the pattern that the specific pathway
is a subclass of 'cellular process' (a go process), and the gene is
"involved in" that process.
For diseases, we preferentially use OMIM identifiers when they can be used
uniquely over MESH. Otherwise, we use MESH ids.
Note that we scrub the following identifiers and their associated data:
* REACT:REACT_116125 - generic disease class
* MESH:D004283 - dog diseases
* MESH:D004195 - disease models, animal
* MESH:D030342 - genetic diseases, inborn
* MESH:D040181 - genetic dieases, x-linked
* MESH:D020022 - genetic predisposition to a disease
"""
files = {
'chemical_disease_interactions': {
'file': 'CTD_chemicals_diseases.tsv.gz',
'url': 'http://ctdbase.org/reports/CTD_chemicals_diseases.tsv.gz'
},
'gene_pathway': {
'file': 'CTD_genes_pathways.tsv.gz',
'url': 'http://ctdbase.org/reports/CTD_genes_pathways.tsv.gz'
},
'gene_disease': {
'file': 'CTD_genes_diseases.tsv.gz',
'url': 'http://ctdbase.org/reports/CTD_genes_diseases.tsv.gz'
}
}
static_files = {
'publications': {'file': 'CTD_curated_references.tsv'}
}
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'ctd')
self.dataset = Dataset(
'ctd', 'CTD', 'http://ctdbase.org', None,
'http://ctdbase.org/about/legal.jsp')
if 'test_ids' not in config.get_config() \
or 'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
self.test_geneids = []
else:
self.test_geneids = config.get_config()['test_ids']['gene']
if 'test_ids' not in config.get_config() \
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_diseaseids = []
else:
self.test_diseaseids = config.get_config()['test_ids']['disease']
self.g = self.graph
self.geno = Genotype(self.graph)
self.pathway = Pathway(self.graph)
return
def fetch(self, is_dl_forced=False):
"""
Override Source.fetch()
Fetches resources from CTD using the CTD.files dictionary
Args:
:param is_dl_forced (bool): Force download
Returns:
:return None
"""
self.get_files(is_dl_forced)
self._fetch_disambiguating_assoc()
# consider creating subsets of the files that
# only have direct annotations (not inferred)
return
def parse(self, limit=None):
"""
Override Source.parse()
Parses version and interaction information from CTD
Args:
:param limit (int, optional) limit the number of rows processed
Returns:
:return None
"""
if limit is not None:
logger.info("Only parsing first %d rows", limit)
logger.info("Parsing files...")
# pub_map = dict()
# file_path = '/'.join((self.rawdir,
# self.static_files['publications']['file']))
# if os.path.exists(file_path) is True:
# pub_map = self._parse_publication_file(
# self.static_files['publications']['file']
# )
if self.testOnly:
self.testMode = True
if self.testMode:
self.g = self.testgraph
else:
self.g = self.graph
self.geno = Genotype(self.g)
self.pathway = Pathway(self.g)
self._parse_ctd_file(
limit, self.files['chemical_disease_interactions']['file'])
self._parse_ctd_file(limit, self.files['gene_pathway']['file'])
self._parse_ctd_file(limit, self.files['gene_disease']['file'])
self._parse_curated_chem_disease(limit)
logger.info("Done parsing files.")
return
def _parse_ctd_file(self, limit, file):
"""
Parses files in CTD.files dictionary
Args:
:param limit (int): limit the number of rows processed
:param file (str): file name (must be defined in CTD.file)
Returns:
:return None
"""
row_count = 0
version_pattern = re.compile(r'^# Report created: (.+)$')
is_versioned = False
file_path = '/'.join((self.rawdir, file))
with gzip.open(file_path, 'rt') as tsvfile:
reader = csv.reader(tsvfile, delimiter="\t")
for row in reader:
# Scan the header lines until we get the version
# There is no official version sp we are using
# the upload timestamp instead
if is_versioned is False:
match = re.match(version_pattern, ' '.join(row))
if match:
version = re.sub(r'\s|:', '-', match.group(1))
# TODO convert this timestamp to a proper timestamp
self.dataset.setVersion(version)
is_versioned = True
elif re.match(r'^#', ' '.join(row)):
pass
else:
row_count += 1
if file == self.files[
'chemical_disease_interactions']['file']:
self._process_interactions(row)
elif file == self.files['gene_pathway']['file']:
self._process_pathway(row)
elif file == self.files['gene_disease']['file']:
self._process_disease2gene(row)
if not self.testMode and \
limit is not None and row_count >= limit:
break
return
def _process_pathway(self, row):
"""
Process row of CTD data from CTD_genes_pathways.tsv.gz
and generate triples
Args:
:param row (list): row of CTD data
Returns:
:return None
"""
model = Model(self.g)
self._check_list_len(row, 4)
(gene_symbol, gene_id, pathway_name, pathway_id) = row
if self.testMode and (int(gene_id) not in self.test_geneids):
return
entrez_id = 'NCBIGene:' + gene_id
pathways_to_scrub = [
'REACT:REACT_116125', # disease
"REACT:REACT_111045", # developmental biology
"REACT:REACT_200794", # Mus musculus biological processes
"REACT:REACT_13685"] # neuronal system ?
if pathway_id in pathways_to_scrub:
# these are lame "pathways" like generic
# "disease" and "developmental biology"
return
# convert KEGG pathway ids... KEGG:12345 --> KEGG-path:map12345
if re.match(r'KEGG', pathway_id):
pathway_id = re.sub(r'KEGG:', 'KEGG-path:map', pathway_id)
# just in case, add it as a class
model.addClassToGraph(entrez_id, None)
self.pathway.addPathway(pathway_id, pathway_name)
self.pathway.addGeneToPathway(entrez_id, pathway_id)
return
def _fetch_disambiguating_assoc(self):
"""
For any of the items in the chemical-disease association file that have
ambiguous association types we fetch the disambiguated associations
using the batch query API, and store these in a file. Elsewhere, we can
loop through the file and create the appropriate associations.
:return:
"""
disambig_file = '/'.join(
(self.rawdir, self.static_files['publications']['file']))
assoc_file = '/'.join(
(self.rawdir, self.files['chemical_disease_interactions']['file']))
# check if there is a local association file,
# and download if it's dated later than the original intxn file
if os.path.exists(disambig_file):
dfile_dt = os.stat(disambig_file)
afile_dt = os.stat(assoc_file)
if dfile_dt < afile_dt:
logger.info(
"Local file date before chem-disease assoc file. "
" Downloading...")
else:
logger.info(
"Local file date after chem-disease assoc file. "
" Skipping download.")
return
all_pubs = set()
dual_evidence = re.compile(r'^marker\/mechanism\|therapeutic$')
# first get all the unique publications
with gzip.open(assoc_file, 'rt') as tsvfile:
reader = csv.reader(tsvfile, delimiter="\t")
for row in reader:
if re.match(r'^#', ' '.join(row)):
continue
self._check_list_len(row, 10)
(chem_name, chem_id, cas_rn, disease_name, disease_id,
direct_evidence, inferred_gene_symbol, inference_score,
omim_ids, pubmed_ids) = row
if direct_evidence == '' or not \
re.match(dual_evidence, direct_evidence):
continue
if pubmed_ids is not None and pubmed_ids != '':
all_pubs.update(set(re.split(r'\|', pubmed_ids)))
sorted_pubs = sorted(list(all_pubs))
# now in batches of 4000, we fetch the chemical-disease associations
batch_size = 4000
params = {
'inputType': 'reference',
'report': 'diseases_curated',
'format': 'tsv',
'action': 'Download'
}
url = 'http://ctdbase.org/tools/batchQuery.go?q'
start = 0
end = min((batch_size, len(all_pubs))) # get them in batches of 4000
with open(disambig_file, 'wb') as f:
while start < len(sorted_pubs):
params['inputTerms'] = '|'.join(sorted_pubs[start:end])
# fetch the data from url
logger.info(
'fetching %d (%d-%d) refs: %s',
len(re.split(r'\|', params['inputTerms'])),
start, end, params['inputTerms'])
data = urllib.parse.urlencode(params)
encoding = 'utf-8'
binary_data = data.encode(encoding)
req = urllib.request.Request(url, binary_data)
resp = urllib.request.urlopen(req)
f.write(resp.read())
start = end
end = min((start + batch_size, len(sorted_pubs)))
return
def _process_interactions(self, row):
"""
Process row of CTD data from CTD_chemicals_diseases.tsv.gz
and generate triples. Only create associations based on direct evidence
(not using the inferred-via-gene), and unambiguous relationships.
(Ambiguous ones will be processed in the sister method using the
disambiguated file). There are no OMIM ids for diseases in these cases,
so we associate with only the mesh disease ids.
Args:
:param row (list): row of CTD data
Returns:
:return None
"""
model = Model(self.g)
self._check_list_len(row, 10)
(chem_name, chem_id, cas_rn, disease_name, disease_id, direct_evidence,
inferred_gene_symbol, inference_score, omim_ids, pubmed_ids) = row
if direct_evidence == '':
return
evidence_pattern = re.compile(r'^therapeutic|marker\/mechanism$')
# dual_evidence = re.compile(r'^marker\/mechanism\|therapeutic$')
# filter on those diseases that are mapped to omim ids in the test set
intersect = list(
set(['OMIM:' + str(i) for i in omim_ids.split('|')] +
[disease_id]) & set(self.test_diseaseids))
if self.testMode and len(intersect) < 1:
return
chem_id = 'MESH:' + chem_id
reference_list = self._process_pubmed_ids(pubmed_ids)
if re.match(evidence_pattern, direct_evidence):
rel_id = self._get_relationship_id(direct_evidence)
model.addClassToGraph(chem_id, chem_name)
model.addClassToGraph(disease_id, None)
self._make_association(chem_id, disease_id, rel_id, reference_list)
else:
# there's dual evidence, but haven't mapped the pubs
pass
# logger.debug(
# "Dual evidence for %s (%s) and %s (%s)",
# chem_name, chem_id, disease_name, disease_id)
return
def _process_disease2gene(self, row):
"""
Here, we process the disease-to-gene associations.
Note that we ONLY process direct associations
(not inferred through chemicals).
Furthermore, we also ONLY process "marker/mechanism" associations.
We preferentially utilize OMIM identifiers over MESH identifiers
for disease/phenotype.
Therefore, if a single OMIM id is listed under the "omim_ids" list,
we will choose this over any MeSH id that might be listed as
the disease_id. If multiple OMIM ids are listed in the omim_ids column,
we toss this for now.
(Mostly, we are not sure what to do with this information.)
We associate "some variant of gene X" with the phenotype,
rather than the gene directly.
We also pull in the MeSH labels here (but not OMIM) to ensure that
we have them (as they may not be brought in separately).
:param row:
:return:
"""
# if self.testMode:
# g = self.testgraph
# else:
# g = self.graph
# self._check_list_len(row, 9)
# geno = Genotype(g)
# gu = GraphUtils(curie_map.get())
model = Model(self.g)
(gene_symbol, gene_id, disease_name, disease_id, direct_evidence,
inference_chemical_name, inference_score, omim_ids, pubmed_ids) = row
# we only want the direct associations; skipping inferred for now
if direct_evidence == '' or direct_evidence != 'marker/mechanism':
return
# scrub some of the associations...
# it seems odd to link human genes to the following "diseases"
diseases_to_scrub = [
'MESH:D004283', # dog diseases
'MESH:D004195', # disease models, animal
'MESH:D030342', # genetic diseases, inborn
'MESH:D040181', # genetic dieases, x-linked
'MESH:D020022'] # genetic predisposition to a disease
if disease_id in diseases_to_scrub:
logger.info(
"Skipping association between NCBIGene:%s and %s",
str(gene_id), disease_id)
return
intersect = list(
set(['OMIM:' + str(i) for i in omim_ids.split('|')] +
[disease_id]) & set(self.test_diseaseids))
if self.testMode and (
int(gene_id) not in self.test_geneids or len(intersect) < 1):
return
# there are three kinds of direct evidence:
# (marker/mechanism | marker/mechanism|therapeutic | therapeutic)
# we are only using the "marker/mechanism" for now
# TODO what does it mean for a gene to be therapeutic for disease?
# a therapeutic target?
gene_id = 'NCBIGene:' + gene_id
preferred_disease_id = disease_id
if omim_ids is not None and omim_ids != '':
omim_id_list = re.split(r'\|', omim_ids)
# If there is only one OMIM ID for the Disease ID
# or in the omim_ids list,
# use the OMIM ID preferentially over any MeSH ID.
if re.match(r'OMIM:.*', disease_id):
if len(omim_id_list) > 1:
# the disease ID is an OMIM ID and
# there is more than one OMIM entry in omim_ids.
# Currently no entries satisfy this condition
pass
elif disease_id != ('OMIM:' + omim_ids):
# the disease ID is an OMIM ID and
# there is only one non-equiv OMIM entry in omim_ids
# we preferentially use the disease_id here
logger.warning(
"There may be alternate identifier for %s: %s",
disease_id, omim_ids)
# TODO: What should be done with the alternate disease IDs?
else:
if len(omim_id_list) == 1:
# the disease ID is not an OMIM ID
# and there is only one OMIM entry in omim_ids.
preferred_disease_id = 'OMIM:' + omim_ids
elif len(omim_id_list) > 1:
# This is when the disease ID is not an OMIM ID and
# there is more than one OMIM entry in omim_ids.
pass
# we actually want the association between the gene and the disease
# to be via an alternate locus not the "wildtype" gene itself. So we
# make an anonymous alternate locus, and put that in the association.
alt_id = gene_id + '-' + preferred_disease_id + 'VL'
# can't have colons in the bnodes
alt_locus = re.sub(r':', '', alt_id)
alt_locus = "_:" + alt_locus
alt_label = 'some variant of ' + gene_symbol + ' that is ' \
+ direct_evidence + ' for ' + disease_name
model.addIndividualToGraph(
alt_locus, alt_label,
self.geno.genoparts['variant_locus'])
# assume that the label gets added elsewhere
model.addClassToGraph(gene_id, None)
self.geno.addAffectedLocus(alt_locus, gene_id)
model.addBlankNodeAnnotation(alt_locus)
# not sure if MESH is getting added separately.
# adding labels here for good measure
dlabel = None
if re.match(r'MESH', preferred_disease_id):
dlabel = disease_name
model.addClassToGraph(preferred_disease_id, dlabel)
# Add the disease to gene relationship.
rel_id = self._get_relationship_id(direct_evidence)
refs = self._process_pubmed_ids(pubmed_ids)
self._make_association(alt_locus, preferred_disease_id, rel_id, refs)
return
def _make_association(self, subject_id, object_id, rel_id, pubmed_ids):
"""
Make a reified association given an array of pubmed identifiers.
Args:
:param subject_id id of the subject of the association (gene/chem)
:param object_id id of the object of the association (disease)
:param rel_id relationship id
:param pubmed_ids an array of pubmed identifiers
Returns:
:return None
"""
# TODO pass in the relevant Assoc class rather than relying on G2P
assoc = G2PAssoc(self.g, self.name, subject_id, object_id, rel_id)
if pubmed_ids is not None and len(pubmed_ids) > 0:
eco = self._get_evidence_code('TAS')
for pmid in pubmed_ids:
r = Reference(
self.g, pmid, Reference.ref_types['journal_article'])
r.addRefToGraph()
assoc.add_source(pmid)
assoc.add_evidence(eco)
assoc.add_association_to_graph()
return
@staticmethod
def _process_pubmed_ids(pubmed_ids):
"""
Take a list of pubmed IDs and add PMID prefix
Args:
:param pubmed_ids - string representing publication
ids seperated by a | symbol
Returns:
:return list: Pubmed curies
"""
if pubmed_ids.strip() == '':
id_list = []
else:
id_list = pubmed_ids.split('|')
for (i, val) in enumerate(id_list):
id_list[i] = 'PMID:' + val
return id_list
@staticmethod
def _get_evidence_code(evidence):
"""
Get curie for evidence class label
Args:
:param evidence (str): evidence label
Label:
:return str: curie for evidence label from ECO
"""
eco_map = {
'TAS': 'ECO:0000033'
}
return eco_map[evidence]
@staticmethod
def _get_relationship_id(rel):
"""
Get curie from relationship property label
Args:
:param rel (str): relationship label
Returns:
:return str: curie for relationship label
"""
rel_map = {
'therapeutic': Model.object_properties['substance_that_treats'],
'marker/mechanism': Model.object_properties['is_marker_for'],
}
return str(rel_map[rel])
@staticmethod
def _get_class_id(clslab):
"""
Get curie from CLASS_MAP dictionary
Args:
:param cls (str): class label
Returns:
:return str: curie for class label
"""
class_map = {
'pathway': 'PW:0000001',
'signal transduction': 'GO:0007165'
}
return class_map[clslab]
def _parse_curated_chem_disease(self, limit):
model = Model(self.g)
line_counter = 0
file_path = '/'.join(
(self.rawdir, self.static_files['publications']['file']))
with open(file_path, 'r') as tsvfile:
reader = csv.reader(tsvfile, delimiter="\t")
for row in reader:
# catch comment lines
if re.match(r'^#', ' '.join(row)):
continue
line_counter += 1
self._check_list_len(row, 10)
(pub_id, disease_label, disease_id, disease_cat, evidence,
chem_label, chem_id, cas_rn, gene_symbol, gene_acc) = row
if disease_id.strip() == '' or chem_id.strip() == '':
continue
rel_id = self._get_relationship_id(evidence)
chem_id = 'MESH:' + chem_id
model.addClassToGraph(chem_id, chem_label)
model.addClassToGraph(disease_id, None)
if pub_id != '':
pub_id = 'PMID:' + pub_id
r = Reference(
pub_id, Reference.ref_types['journal_article'])
r.addRefToGraph(self.g)
pubids = [pub_id]
else:
pubids = None
self._make_association(chem_id, disease_id, rel_id, pubids)
if not self.testMode and limit is not None \
and line_counter >= limit:
break
return
def getTestSuite(self):
import unittest
from tests.test_ctd import CTDTestCase
test_suite = unittest.TestLoader().loadTestsFromTestCase(CTDTestCase)
# test_suite.addTests(
# unittest.TestLoader().loadTestsFromTestCase(InteractionsTestCase))
return test_suite
def __init__(
self,
graph_type='rdf_graph', # or streamed_graph
are_bnodes_skized=False, # typically True
name=None, # identifier; make an IRI for nquads
ingest_title=None,
ingest_url=None,
license_url=None, # only if it is _our_ lic
data_rights=None, # external page that points to their current lic
file_handle=None
):
# pull in the common test identifiers
self.all_test_ids = self.open_and_parse_yaml('../../resources/test_ids.yaml')
self.graph_type = graph_type
self.are_bnodes_skized = are_bnodes_skized
self.ingest_url = ingest_url
self.ingest_title = ingest_title
self.localtt = self.load_local_translationtable(name)
if name is not None:
self.name = name.lower()
elif self.whoami() is not None:
self.name = self.whoami().lower()
LOG.info("Processing Source \"%s\"", self.name)
self.test_only = False
self.path = ""
# to be used to store a subset of data for testing downstream.
self.triple_count = 0
self.outdir = 'out'
self.testdir = 'tests'
self.rawdir = 'raw'
self.rawdir = '/'.join((self.rawdir, self.name))
self.testname = name + "_test"
self.testfile = '/'.join((self.outdir, self.testname + ".ttl"))
self.datasetfile = None
# still need to pull in file suffix -- this ia a curie not a url
self.archive_url = 'MonarchArchive:' + 'ttl/' + self.name + '.ttl'
# if raw data dir doesn't exist, create it
if not os.path.exists(self.rawdir):
os.makedirs(self.rawdir)
pth = os.path.abspath(self.rawdir)
LOG.info("creating raw directory for %s at %s", self.name, pth)
# if output dir doesn't exist, create it
if not os.path.exists(self.outdir):
os.makedirs(self.outdir)
pth = os.path.abspath(self.outdir)
LOG.info("created output directory %s", pth)
LOG.info("Creating Test graph %s", self.testname)
# note: tools such as protoge need slolemized blank nodes
self.testgraph = RDFGraph(True, self.testname)
if graph_type == 'rdf_graph':
graph_id = ':MONARCH_' + str(self.name) + "_" + \
datetime.now().isoformat(' ').split()[0]
LOG.info("Creating graph %s", graph_id)
self.graph = RDFGraph(are_bnodes_skized, graph_id)
elif graph_type == 'streamed_graph':
# need to expand on export formats
dest_file = open(pth + '/' + name + '.nt', 'w') # where is the close?
self.graph = StreamedGraph(are_bnodes_skized, dest_file)
# leave test files as turtle (better human readibility)
else:
LOG.error(
"%s graph type not supported\n"
"valid types: rdf_graph, streamed_graph", graph_type)
# pull in global ontology mapping datastructures
self.globaltt = self.graph.globaltt
self.globaltcid = self.graph.globaltcid
self.curie_map = self.graph.curie_map
# self.prefix_base = {v: k for k, v in self.curie_map.items()}
# will be set to True if the intention is
# to only process and write the test data
self.test_only = False
self.test_mode = False
# this may eventually support Bagits
self.dataset = Dataset(
self.archive_url,
self.ingest_title,
self.ingest_url,
None, # description
license_url, # only _OUR_ lic
data_rights, # tries to point to others lics
graph_type,
file_handle
)
for graph in [self.graph, self.testgraph]:
self.declareAsOntology(graph)
class GeneReviews(Source):
"""
Here we process the GeneReviews mappings to OMIM,
plus inspect the GeneReviews (html) books to pull the clinical descriptions
in order to populate the definitions of the terms in the ontology.
We define the GeneReviews items as classes that are either grouping classes
over OMIM disease ids (gene ids are filtered out),
or are made as subclasses of DOID:4 (generic disease).
Note that GeneReviews
[copyright policy](http://www.ncbi.nlm.nih.gov/books/NBK138602/)
(as of 2015.11.20) says:
GeneReviews® chapters are owned by the University of Washington, Seattle,
© 1993-2015. Permission is hereby granted to reproduce, distribute,
and translate copies of content materials provided that
(i) credit for source (www.ncbi.nlm.nih.gov/books/NBK1116/)
and copyright (University of Washington, Seattle)
are included with each copy;
(ii) a link to the original material is provided whenever the material is
published elsewhere on the Web; and
(iii) reproducers, distributors, and/or translators comply with this
copyright notice and the GeneReviews Usage Disclaimer.
This script doesn't pull the GeneReviews books from the NCBI Bookshelf
directly; scripting this task is expressly prohibited by
[NCBIBookshelf policy](http://www.ncbi.nlm.nih.gov/books/NBK45311/).
However, assuming you have acquired the books (in html format) via
permissible means, a parser for those books is provided here to extract
the clinical descriptions to define the NBK identified classes.
"""
files = {
'idmap': {'file': 'NBKid_shortname_OMIM.txt',
'url': GRDL + '/NBKid_shortname_OMIM.txt'},
'titles': {'file': 'GRtitle_shortname_NBKid.txt',
'url': GRDL + '/GRtitle_shortname_NBKid.txt'}
}
def __init__(self):
Source.__init__(self, 'genereviews')
self.load_bindings()
self.dataset = Dataset(
'genereviews', 'Gene Reviews', 'http://genereviews.org/',
None, 'http://www.ncbi.nlm.nih.gov/books/NBK138602/')
self.dataset.set_citation('GeneReviews:NBK1116')
self.gu = GraphUtils(curie_map.get())
self.book_ids = set()
self.all_books = {}
if 'test_ids' not in config.get_config() or\
'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = list()
else:
# select ony those test ids that are omim's.
self.test_ids = config.get_config()['test_ids']['disease']
return
def fetch(self, is_dl_forced=False):
"""
We fetch GeneReviews id-label map and id-omim mapping files from NCBI.
:return: None
"""
self.get_files(is_dl_forced)
return
def parse(self, limit=None):
"""
:return: None
"""
if self.testOnly:
self.testMode = True
self._get_titles(limit)
self._get_equivids(limit)
self.create_books()
self.process_nbk_html(limit)
self.load_bindings()
# no test subset for now; test == full graph
self.testgraph = self.graph
logger.info("Found %d nodes", len(self.graph))
return
def _get_equivids(self, limit):
"""
The file processed here is of the format:
#NBK_id GR_shortname OMIM
NBK1103 trimethylaminuria 136132
NBK1103 trimethylaminuria 602079
NBK1104 cdls 122470
Where each of the rows represents a mapping between
a gr id and an omim id. These are a 1:many relationship,
and some of the omim ids are genes(not diseases).
Therefore, we need to create a loose coupling here.
We make the assumption that these NBKs are generally higher-level
grouping classes; therefore the OMIM ids are treated as subclasses.
(This assumption is poor for those omims that are actually genes,
but we have no way of knowing what those are here...
we will just have to deal with that for now.)
:param limit:
:return:
"""
raw = '/'.join((self.rawdir, self.files['idmap']['file']))
gu = GraphUtils(curie_map.get())
line_counter = 0
# we look some stuff up in OMIM, so initialize here
omim = OMIM()
id_map = {}
allomimids = set()
with open(raw, 'r', encoding="utf8") as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
line_counter += 1
if line_counter == 1: # skip header
continue
(nbk_num, shortname, omim_num) = row
gr_id = 'GeneReviews:'+nbk_num
omim_id = 'OMIM:'+omim_num
if not (
(self.testMode and
len(self.test_ids) > 0 and
omim_id in self.test_ids) or not
self.testMode):
continue
# sometimes there's bad omim nums
if len(omim_num) > 6:
logger.warning(
"OMIM number incorrectly formatted " +
"in row %d; skipping:\n%s",
line_counter, '\t'.join(row))
continue
# build up a hashmap of the mappings; then process later
if nbk_num not in id_map:
id_map[nbk_num] = set()
id_map[nbk_num].add(omim_num)
# add the class along with the shortname
gu.addClassToGraph(self.graph, gr_id, None)
gu.addSynonym(self.graph, gr_id, shortname)
allomimids.add(omim_num)
if not self.testMode and \
limit is not None and line_counter > limit:
break
# end looping through file
# get the omim ids that are not genes
entries_that_are_phenotypes = \
omim.process_entries(
list(allomimids), filter_keep_phenotype_entry_ids,
None, None, limit)
logger.info("Filtered out %d/%d entries that are genes or features",
len(allomimids)-len(entries_that_are_phenotypes),
len(allomimids))
for nbk_num in self.book_ids:
gr_id = 'GeneReviews:'+nbk_num
if nbk_num in id_map:
omim_ids = id_map.get(nbk_num)
for omim_num in omim_ids:
omim_id = 'OMIM:'+omim_num
# add the gene reviews as a superclass to the omim id,
# but only if the omim id is not a gene
if omim_id in entries_that_are_phenotypes:
gu.addClassToGraph(self.graph, omim_id, None)
gu.addSubclass(self.graph, gr_id, omim_id)
# add this as a generic subclass of DOID:4
gu.addSubclass(self.graph, 'DOID:4', gr_id)
return
def _get_titles(self, limit):
"""
The file processed here is of the format:
#NBK_id GR_shortname OMIM
NBK1103 trimethylaminuria 136132
NBK1103 trimethylaminuria 602079
NBK1104 cdls 122470
Where each of the rows represents a mapping between
a gr id and an omim id. These are a 1:many relationship,
and some of the omim ids are genes (not diseases).
Therefore, we need to create a loose coupling here.
We make the assumption that these NBKs are generally higher-level
grouping classes; therefore the OMIM ids are treated as subclasses.
(This assumption is poor for those omims that are actually genes,
but we have no way of knowing what those are here...
we will just have to deal with that for now.)
:param limit:
:return:
"""
raw = '/'.join((self.rawdir, self.files['titles']['file']))
gu = GraphUtils(curie_map.get())
line_counter = 0
with open(raw, 'r', encoding='latin-1') as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
line_counter += 1
if line_counter == 1: # skip header
continue
(shortname, title, nbk_num) = row
gr_id = 'GeneReviews:'+nbk_num
self.book_ids.add(nbk_num) # a global set of the book nums
if limit is None or line_counter < limit:
gu.addClassToGraph(self.graph, gr_id, title)
gu.addSynonym(self.graph, gr_id, shortname)
return
def create_books(self):
# note that although we put in the url to the book,
# NCBI Bookshelf does not allow robots to download content
book_item = {'file': 'books/',
'url': ''}
for nbk in self.book_ids:
b = book_item.copy()
b['file'] = '/'.join(('books', nbk+'.html'))
b['url'] = 'http://www.ncbi.nlm.nih.gov/books/'+nbk
self.all_books[nbk] = b
return
def process_nbk_html(self, limit):
"""
Here we process the gene reviews books to fetch
the clinical descriptions to include in the ontology.
We only use books that have been acquired manually,
as NCBI Bookshelf does not permit automated downloads.
This parser will only process the books that are found in
the ```raw/genereviews/books``` directory,
permitting partial completion.
:param limit:
:return:
"""
c = 0
books_not_found = set()
for nbk in self.book_ids:
c += 1
nbk_id = 'GeneReviews:'+nbk
book_item = self.all_books.get(nbk)
url = '/'.join((self.rawdir, book_item['file']))
# figure out if the book is there; if so, process, otherwise skip
book_dir = '/'.join((self.rawdir, 'books'))
book_files = os.listdir(book_dir)
if ''.join((nbk, '.html')) not in book_files:
# logger.warning("No book found locally for %s; skipping", nbk)
books_not_found.add(nbk)
continue
logger.info("Processing %s", nbk)
page = open(url)
soup = BeautifulSoup(page.read())
# sec0 == clinical description
clin_summary = \
soup.find(
'div', id=re.compile(".*Summary.sec0"))
if clin_summary is not None:
p = clin_summary.find('p')
ptext = p.text
ptext = re.sub(r'\s+', ' ', ptext)
ul = clin_summary.find('ul')
if ul is not None:
item_text = list()
for li in ul.find_all('li'):
item_text.append(re.sub(r'\s+', ' ', li.text))
ptext += ' '.join(item_text)
# add in the copyright and citation info to description
ptext = \
' '.join(
(ptext,
'[GeneReviews:NBK1116, GeneReviews:NBK138602, ' +
nbk_id+']'))
self.gu.addDefinition(self.graph, nbk_id, ptext.strip())
# get the pubs
pmid_set = set()
pub_div = soup.find('div', id=re.compile(r".*Literature_Cited"))
if pub_div is not None:
ref_list = pub_div.find_all('div', attrs={'class': "bk_ref"})
for r in ref_list:
for a in r.find_all(
'a', attrs={'href': re.compile(r"pubmed")}):
if re.match(r'PubMed:', a.text):
pmnum = re.sub(r'PubMed:\s*', '', a.text)
else:
pmnum = \
re.search(
r'\/pubmed\/(\d+)$', a['href']).group(1)
if pmnum is not None:
pmid = 'PMID:'+str(pmnum)
self.gu.addTriple(
self.graph, pmid,
self.gu.object_properties['is_about'],
nbk_id)
pmid_set.add(pmnum)
r = Reference(
pmid, Reference.ref_types['journal_article'])
r.addRefToGraph(self.graph)
# TODO add author history, copyright, license to dataset
# TODO get PMID-NBKID equivalence (near foot of page),
# and make it "is about" link
# self.gu.addTriple(
# self.graph, pmid,
# self.gu.object_properties['is_about'], nbk_id)
# for example: NBK1191 PMID:20301370
# add the book to the dataset
self.dataset.setFileAccessUrl(book_item['url'])
if limit is not None and c > limit:
break
# finish looping through books
l = len(books_not_found)
if len(books_not_found) > 0:
if l > 100:
logger.warning("There were %d books not found.", l)
else:
logger.warning(
"The following %d books were not found locally: %s",
l, str(books_not_found))
logger.info(
"Finished processing %d books for clinical descriptions", c-l)
return
def getTestSuite(self):
import unittest
from tests.test_genereviews import GeneReviewsTestCase
test_suite = \
unittest.TestLoader().loadTestsFromTestCase(GeneReviewsTestCase)
return test_suite
class HPOAnnotations(Source):
"""
The [Human Phenotype Ontology](http://human-phenotype-ontology.org) group
curates and assembles over 115,000 annotations to hereditary diseases
using the HPO ontology. Here we create OBAN-style associations
between diseases and phenotypic features, together with their evidence,
and age of onset and frequency (if known).
The parser currently only processes the "abnormal" annotations.
Association to "remarkable normality" will be added in the near future.
We create additional associations from text mining. See info at
http://pubmed-browser.human-phenotype-ontology.org/.
Also, you can read about these annotations in
[PMID:26119816](http://www.ncbi.nlm.nih.gov/pubmed/26119816).
In order to properly test this class,
you should have a conf.json file configured with some test ids, in
the structure of:
# as examples. put your favorite ids in the config.
<pre>
test_ids: {"disease" : ["OMIM:119600", "OMIM:120160"]}
</pre>
"""
files = {
'annot': {
'file': 'phenotype_annotation.tab',
'url': HPOADL + '/phenotype_annotation.tab'},
'version': {
'file': 'data_version.txt',
'url': HPOADL + '/data_version.txt'},
# 'neg_annot': {
# 'file': 'phenotype_annotation.tab',
# 'url': HPOADL + '/negative_phenotype_annotation.tab'},
'doid': {
'file': 'doid.owl',
'url': 'http://purl.obolibrary.org/obo/doid.owl'
}
}
# note, two of these codes are awaiting term requests. see #114 and
# https://code.google.com/p/evidenceontology/issues/detail?id=32
# TODO TEC see if the GC issue translated into a GH issue
eco_dict = {
# FIXME currently using "curator inference used in manual assertion"
"ICE": "ECO:0000305",
# Inferred from Electronic Annotation
"IEA": "ECO:0000501",
# FIXME currently is"experimental evidence used in manual assertion"
"PCS": "ECO:0000269",
# Traceable Author Statement
"TAS": "ECO:0000304",
# FIXME currently using computational combinatorial evidence
# in automatic assertion
"ITM": "ECO:0000246",
}
def __init__(self, graph_type, are_bnodes_skolemized):
super().__init__(graph_type, are_bnodes_skolemized, 'hpoa')
self.dataset = Dataset(
'hpoa', 'Human Phenotype Ontology',
'http://www.human-phenotype-ontology.org', None,
'http://www.human-phenotype-ontology.org/contao/index.php/legal-issues.html')
self.replaced_id_count = 0
if 'test_ids' not in config.get_config()\
or 'disease' not in config.get_config()['test_ids']:
logger.warning("not configured with disease test ids.")
self.test_ids = []
else:
self.test_ids = config.get_config()['test_ids']['disease']
# data-source specific warnings to be removed when issues are cleared
logger.warning(
"note that some ECO classes are missing for ICE, PCS, and ITM;" +
" using temporary mappings.")
return
def fetch(self, is_dl_forced=False):
self.get_files(is_dl_forced)
self.scrub()
# get the latest build from jenkins
# use the files['version'] file as the version
fname = '/'.join((self.rawdir, self.files['version']['file']))
with open(fname, 'r', encoding="utf8") as f:
# 2015-04-23 13:01
v = f.readline() # read the first line (the only line, really)
d = datetime.strptime(
v.strip(), '%Y-%m-%d %H:%M').strftime("%Y-%m-%d-%H-%M")
f.close()
st = os.stat(fname)
filedate = datetime.utcfromtimestamp(st[ST_CTIME]).strftime("%Y-%m-%d")
# this will cause two dates to be attached to the dataset
# (one from the filedate, and the other from here)
# TODO when #112 is implemented,
# this will result in only the whole dataset being versioned
self.dataset.setVersion(filedate, d)
self.get_common_files()
return
def scrub(self):
"""
Perform various data-scrubbing on the raw data files prior to parsing.
For this resource, this currently includes:
* revise errors in identifiers for some OMIM and PMIDs
:return: None
"""
# scrub file of the oddities...lots of publication rewriting
f = '/'.join((self.rawdir, self.files['annot']['file']))
logger.info('scrubbing PubMed:12345 --> PMID:12345')
pysed.replace(r'PubMed:', 'PMID:', f)
logger.info('scrubbing pmid:12345 --> PMID:12345')
pysed.replace(r'pmid:', 'PMID:', f)
logger.info('scrubbing PMID: 12345 --> PMID:12345')
pysed.replace(r'PMID: *', 'PMID:', f)
logger.info('scrubbing PMID12345 --> PMID:12345')
pysed.replace(r'PMID([0-9][0-9]*)', r'PMID:\1', f)
logger.info('scrubbing MIM12345 --> OMIM:12345')
pysed.replace(r'MIM([0-9][0-9]*)', r'OMIM:\1', f)
logger.info('scrubbing MIM:12345 --> OMIM:12345')
pysed.replace(r";MIM", ";OMIM", f)
logger.info('scrubbing ORPHANET --> Orphanet')
pysed.replace("ORPHANET", "Orphanet", f)
logger.info('scrubbing ORPHA --> Orphanet')
pysed.replace("ORPHA", "Orphanet", f)
return
def parse(self, limit=None):
if limit is not None:
logger.info("Only parsing first %s rows", limit)
self.add_common_files_to_file_list()
logger.info("Parsing files...")
if self.testOnly:
self.testMode = True
# rare disease-phenotype associations
self._process_phenotype_tab('/'.join((self.rawdir,
self.files['annot']['file'])),
limit)
# TODO add negative phenotype statements #113
# self._process_negative_phenotype_tab(self.rawfile,self.outfile,limit)
# common disease-phenotype associations from text mining work
self.process_all_common_disease_files(limit)
logger.info("Finished parsing.")
return
def _map_evidence_to_codes(self, code_string):
"""
A simple mapping of the code_string to it's ECO class
using the dictionary defined here
Currently includes ICE, IEA, PCS, TAS
:param code_string:
:return:
"""
return self.eco_dict.get(code_string)
def _process_phenotype_tab(self, raw, limit):
"""
see info on format here:
http://www.human-phenotype-ontology.org/contao/index.php/annotation-guide.html
:param raw:
:param limit:
:return:
"""
if self.testMode:
g = self.testgraph
else:
g = self.graph
model = Model(g)
line_counter = 0
with open(raw, 'r', encoding="utf8") as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
line_counter += 1
row = [str(col).strip() for col in row]
# Note from Seb in Dec 2017, a 15th column was added
# inadverterntly and will be removed in the winter 2018
# release of hpo data
(db, num, name, qual, pheno_id, publist, eco, onset, freq, w,
asp, syn, date, curator, extra) = row
disease_id = db + ":" + num
if self.testMode:
try:
id_list = self.test_ids
if id_list is None \
or disease_id not in id_list:
continue
except AttributeError:
continue
# logger.info('adding %s', disease_id)
model.addClassToGraph(disease_id, None)
model.addClassToGraph(pheno_id, None)
eco_id = self._map_evidence_to_codes(eco)
model.addClassToGraph(eco_id, None)
if onset is not None and onset != '':
model.addClassToGraph(onset, None)
# we want to do things differently depending on
# the aspect of the annotation
# TODO PYLINT Redefinition of assoc type from
# dipper.models.assoc.D2PAssoc.D2PAssoc to
# dipper.models.assoc.DispositionAssoc.DispositionAssoc
if asp == 'O' or asp == 'M': # organ abnormality or mortality
assoc = D2PAssoc(
g, self.name, disease_id, pheno_id, onset, freq)
elif asp == 'I': # inheritance patterns for the whole disease
assoc = DispositionAssoc(
g, self.name, disease_id, pheno_id)
elif asp == 'C': # clinical course / onset
assoc = DispositionAssoc(
g, self.name, disease_id, pheno_id)
else:
logger.error("I don't know what this aspect is: %s", asp)
assoc.add_evidence(eco_id)
publist = re.split(r'[,;]', publist)
# blow these apart if there is a list of pubs
for pub in publist:
pub = pub.strip()
pubtype = None
if pub != '':
# if re.match(
# r'http://www.ncbi.nlm.nih.gov/bookshelf/br\.fcgi\?book=gene',
# pub):
# #http://www.ncbi.nlm.nih.gov/bookshelf/br.fcgi?book=gene&part=ced
# m = re.search(r'part\=(\w+)', pub)
# pub_id = 'GeneReviews:'+m.group(1)
# elif re.search(
# r'http://www.orpha.net/consor/cgi-bin/OC_Exp\.php\?lng\=en\&Expert\=',
# pub):
# m = re.search(r'Expert=(\d+)', pub)
# pub_id = 'Orphanet:'+m.group(1)
if re.match(r'(PMID|ISBN-13|ISBN-10|ISBN|HPO)', pub):
if re.match(r'PMID', pub):
pubtype = \
Reference.ref_types['journal_article']
elif re.match(r'HPO', pub):
pubtype = Reference.ref_types['person']
else:
pubtype = Reference.ref_types['publication']
r = Reference(g, pub, pubtype)
r.addRefToGraph()
elif re.match(r'(OMIM|Orphanet|DECIPHER)', pub):
# make the pubs a reference to the website,
# instead of the curie
if re.match(r'OMIM', pub):
omimnum = re.sub(r'OMIM:', '', pub)
omimurl = '/'.join(('http://omim.org/entry',
str(omimnum).strip()))
pub = omimurl
elif re.match(r'Orphanet:', pub):
orphanetnum = re.sub(r'Orphanet:', '', pub)
orphaneturl = \
''.join((
'http://www.orpha.net/consor/cgi-bin/OC_Exp.php?lng=en&Expert=',
str(orphanetnum)))
pub = orphaneturl
elif re.match(r'DECIPHER:', pub):
deciphernum = re.sub(r'DECIPHER:', '', pub)
decipherurl = '/'.join(
('https://decipher.sanger.ac.uk/syndrome',
deciphernum))
pub = decipherurl
pubtype = Reference.ref_types['webpage']
elif re.match(r'http', pub):
pass
else:
logger.error('Unknown pub type for %s: %s',
disease_id, pub)
print(disease_id, 'pubs:', str(publist))
continue
if pub is not None:
assoc.add_source(pub)
# TODO add curator
assoc.add_association_to_graph()
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def get_common_files(self):
"""
Fetch the raw hpo-annotation-data by cloning/pulling the
[repository](https://github.com/monarch-initiative/hpo-annotation-data.git)
These files get added to the files object,
and iterated over separately.
:return:
"""
repo_dir = '/'.join((self.rawdir, 'git'))
REMOTE_URL = \
"[email protected]:monarch-initiative/hpo-annotation-data.git"
HTTPS_URL = \
"https://github.com/monarch-initiative/hpo-annotation-data.git"
# TODO if repo doesn't exist, then clone otherwise pull
if os.path.isdir(repo_dir):
shutil.rmtree(repo_dir)
logger.info("Cloning common disease files from %s", REMOTE_URL)
try:
Repo.clone_from(REMOTE_URL, repo_dir)
except GitCommandError:
# Try with https and if this doesn't work fail
Repo.clone_from(HTTPS_URL, repo_dir)
return
def add_common_files_to_file_list(self):
repo_dir = '/'.join((self.rawdir, 'git'))
common_disease_dir = '/'.join((repo_dir, 'common-diseases'))
# add the files to the self.files object
filelist = os.listdir(common_disease_dir)
fcount = 0
for f in filelist:
if not re.search(r'\.tab', f):
continue
fcount += 1
self.files['common'+str(fcount).zfill(7)] = {
'file': '/'.join((common_disease_dir, f)),
# TODO add url to reference the file?
# need to get git version somehow?
}
# TODO add this to the dataset
logger.info("Found %d common disease files", fcount)
return
def process_all_common_disease_files(self, limit=None):
"""
Loop through all of the files that we previously fetched from git,
creating the disease-phenotype assoc.
:param limit:
:return:
"""
self.replaced_id_count = 0
unpadded_doids = self.get_doid_ids_for_unpadding()
total_processed = 0
logger.info("Iterating over all common disease files")
common_file_count = 0
for f in self.files:
if not re.match(r'common', f):
continue
common_file_count += 1
raw = self.files[f]['file']
total_processed += self.process_common_disease_file(
raw, unpadded_doids, limit)
if not self.testMode \
and limit is not None and total_processed > limit:
break
logger.info("Finished iterating over all common disease files.")
logger.info("Fixed %d/%d incorrectly zero-padded ids",
self.replaced_id_count, common_file_count)
return
def get_doid_ids_for_unpadding(self):
"""
Here, we fetch the doid owl file, and get all the doids.
We figure out which are not zero-padded, so we can map the DOID
to the correct identifier when processing the common annotation files.
This may become obsolete when
https://github.com/monarch-initiative/hpo-annotation-data/issues/84
is addressed.
:return:
"""
logger.info("Building list of non-zero-padded DOIDs")
raw_file = '/'.join((self.rawdir, self.files['doid']['file']))
doids = set()
# scan the file and get all doids
with open(raw_file, 'r', encoding="utf8") as f:
for line in f:
matches = re.search(r'(DOID_\d+)', line)
if matches is not None:
for m in matches.groups():
doids.add(re.sub(r'_', ':', m))
nopad_doids = set()
for d in doids:
num = re.sub(r'DOID[:_]', '', d)
# look for things not starting with zero
if not re.match(r'^0', str(num)):
nopad_doids.add(num)
logger.info("Found %d/%d DOIDs are not zero-padded",
len(nopad_doids), len(doids))
return nopad_doids
def process_common_disease_file(self, raw, unpadded_doids, limit=None):
"""
Make disaese-phenotype associations.
Some identifiers need clean up:
* DOIDs are listed as DOID-DOID: --> DOID:
* DOIDs may be unnecessarily zero-padded.
these are remapped to their non-padded equivalent.
:param raw:
:param unpadded_doids:
:param limit:
:return:
"""
if self.testMode:
g = self.testgraph
else:
g = self.graph
line_counter = 0
assoc_count = 0
replace_id_flag = False
with open(raw, 'r', encoding="utf8") as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
header = csvfile.readline() # skip the header row
logger.info("HEADER: %s", header)
disease_id = None
for row in filereader:
if 21 == len(row):
(did, dname, gid, gene_name, genotype, gene_symbols,
phenotype_id, phenotype_name, age_of_onset_id,
age_of_onset_name, eid, evidence_name, frequency, sex_id,
sex_name, negation_id, negation_name, description,
pub_ids, assigned_by,
date_created) = [str(col).strip() for col in row]
else:
logger.warning(
"Wrong number of columns! expected 21, got: %s in: %s",
len(row), raw)
logger.warning("%s", row)
continue
# b/c "PMID: 17223397"
pub_ids = re.sub(r' *', '', pub_ids)
disease_id = re.sub(r'DO(ID)?[-\:](DOID:)?', 'DOID:', did)
disease_id = re.sub(r'MESH-', 'MESH:', disease_id)
if not re.search(r'(DOID\:|MESH\:\w)\d+', disease_id):
logger.warning("Invalid id format: %s", disease_id)
# figure out if the doid should be unpadded,
# then use the unpadded version instead
if re.match(r'DOID', disease_id):
unpadded_num = re.sub(r'DOID:', '', disease_id)
unpadded_num = unpadded_num.lstrip('0')
if unpadded_num in unpadded_doids:
fixed_id = 'DOID:' + unpadded_num
replace_id_flag = True
disease_id = fixed_id.strip()
if self.testMode and disease_id not in self.test_ids:
# since these are broken up into disease-by-disease,
# just skip the whole file
return 0
else:
line_counter += 1
if negation_id != '':
continue # TODO add negative associations
if disease_id != '' and phenotype_id != '':
assoc = D2PAssoc(
g, self.name, disease_id, phenotype_id.strip())
if age_of_onset_id != '':
assoc.onset = age_of_onset_id
if frequency != '':
assoc.frequency = frequency
eco_id = self._map_evidence_to_codes(eid)
if eco_id is None:
eco_id = self._map_evidence_to_codes('ITM')
assoc.add_evidence(eco_id)
# TODO add sex? - not in dataset yet
if description != '':
assoc.set_description(description)
if pub_ids != '':
for p in pub_ids.split(';'):
p = re.sub(r' *', '', p)
if re.search(r'(DOID|MESH)', p) \
or re.search(r'Disease name contained',
description):
# skip "pubs" that are derived from
# the classes themselves
continue
assoc.add_source(p.strip())
# TODO assigned by?
assoc.add_association_to_graph()
assoc_count += 1
if not self.testMode and limit is not None\
and line_counter > limit:
break
if replace_id_flag:
logger.info("replaced DOID with unpadded version")
self.replaced_id_count += 1
logger.info(
"Added %d associations for %s.", assoc_count, disease_id)
return assoc_count
def getTestSuite(self):
import unittest
from tests.test_hpoa import HPOATestCase
test_suite = unittest.TestLoader().loadTestsFromTestCase(HPOATestCase)
return test_suite
class MPD(Source):
"""
From the [MPD](http://phenome.jax.org/) website:
This resource is a collaborative standardized collection of measured data
on laboratory mouse strains and populations. Includes baseline phenotype
data sets as well as studies of drug, diet, disease and aging effect.
Also includes protocols, projects and publications, and SNP,
variation and gene expression studies.
Here, we pull the data and model the genotypes using GENO and
the genotype-to-phenotype associations using the OBAN schema.
MPD provide measurements for particular assays for several strains.
Each of these measurements is itself mapped to a MP or VT term
as a phenotype. Therefore, we can create a strain-to-phenotype association
based on those strains that lie outside of the "normal" range for the given
measurements. We can compute the average of the measurements
for all strains tested, and then threshold any extreme measurements being
beyond some threshold beyond the average.
Our default threshold here, is +/-2 standard deviations beyond the mean.
Because the measurements are made and recorded at the level of
a specific sex of each strain, we associate the MP/VT phenotype with
the sex-qualified genotype/strain.
"""
MPDDL = 'http://phenomedoc.jax.org/MPD_downloads'
files = {
'ontology_mappings': {
'file': 'ontology_mappings.csv',
'url': MPDDL + '/ontology_mappings.csv'},
'straininfo': {
'file': 'straininfo.csv',
'url': MPDDL + '/straininfo.csv'},
'assay_metadata': {
'file': 'measurements.csv',
'url': MPDDL + '/measurements.csv'},
'strainmeans': {
'file': 'strainmeans.csv.gz',
'url': MPDDL + '/strainmeans.csv.gz'},
# 'mpd_datasets_metadata': { #TEC does not seem to be used
# 'file': 'mpd_datasets_metadata.xml.gz',
# 'url': MPDDL + '/mpd_datasets_metadata.xml.gz'},
}
# the following are strain ids for testing
# test_ids = [
# "MPD:2", "MPD:3", "MPD:5", "MPD:6", "MPD:9", "MPD:11", "MPD:18",
# "MPD:20", "MPD:24", "MPD:28", "MPD:30", "MPD:33", "MPD:34", "MPD:36",
# "MPD:37", "MPD:39", "MPD:40", "MPD:42", "MPD:47", "MPD:66", "MPD:68",
# "MPD:71", "MPD:75", "MPD:78", "MPD:122", "MPD:169", "MPD:438",
# "MPD:457","MPD:473", "MPD:481", "MPD:759", "MPD:766", "MPD:770",
# "MPD:849", "MPD:857", "MPD:955", "MPD:964", "MPD:988", "MPD:1005",
# "MPD:1017", "MPD:1204", "MPD:1233", "MPD:1235", "MPD:1236", "MPD:1237"]
test_ids = [
'MPD:6', 'MPD:849', 'MPD:425', 'MPD:569', "MPD:10", "MPD:1002",
"MPD:39", "MPD:2319"]
mgd_agent_id = "MPD:db/q?rtn=people/allinv"
mgd_agent_label = "Mouse Phenotype Database"
mgd_agent_type = "foaf:organization"
def __init__(self, graph_type, are_bnodes_skolemized):
Source.__init__(self, graph_type, are_bnodes_skolemized, 'mpd')
# @N, not sure if this step is required
self.stdevthreshold = 2
# update the dataset object with details about this resource
# @N: Note that there is no license as far as I can tell
self.dataset = Dataset(
'mpd', 'MPD', 'http://phenome.jax.org', None, None)
# TODO add a citation for mpd dataset as a whole
self.dataset.set_citation('PMID:15619963')
self.assayhash = {}
self.idlabel_hash = {}
# to store the mean/zscore of each measure by strain+sex
self.score_means_by_measure = {}
# to store the mean value for each measure by strain+sex
self.strain_scores_by_measure = {}
return
def fetch(self, is_dl_forced=False):
self.get_files(is_dl_forced)
return
def parse(self, limit=None):
"""
MPD data is delivered in four separate csv files and one xml file,
which we process iteratively and write out as
one large graph.
:param limit:
:return:
"""
if limit is not None:
logger.info("Only parsing first %s rows fo each file", str(limit))
logger.info("Parsing files...")
self._process_straininfo(limit)
# the following will provide us the hash-lookups
# These must be processed in a specific order
# mapping between assays and ontology terms
self._process_ontology_mappings_file(limit)
# this is the metadata about the measurements
self._process_measurements_file(limit)
# get all the measurements per strain
self._process_strainmeans_file(limit)
# The following will use the hash populated above
# to lookup the ids when filling in the graph
self._fill_provenance_graph(limit)
logger.info("Finished parsing.")
return
def _process_ontology_mappings_file(self, limit):
# line_counter = 0 # TODO unused
logger.info("Processing ontology mappings...")
raw = '/'.join((self.rawdir, 'ontology_mappings.csv'))
with open(raw, 'r') as f:
reader = csv.reader(f)
# read the header row; skip
self.check_header(self.files['ontology_mappings']['file'], f.readline())
for row in reader:
try:
(assay_id, ont_term, descrip) = row
except ValueError:
continue
assay_id = int(assay_id)
if re.match(r'(MP|VT)', ont_term):
# add the mapping denovo
if assay_id not in self.assayhash:
self.assayhash[assay_id] = {}
self.assayhash[assay_id]['ont_terms'] = set()
self.assayhash[assay_id]['ont_terms'].add(ont_term)
return
def _process_straininfo(self, limit):
# line_counter = 0 # TODO unused
if self.testMode:
g = self.testgraph
else:
g = self.graph
model = Model(g)
logger.info("Processing measurements ...")
raw = '/'.join((self.rawdir, self.files['straininfo']['file']))
tax_id = 'NCBITaxon:10090'
with open(raw, 'r') as f:
reader = csv.reader(f, delimiter=',', quotechar='\"')
self.check_header(self.files['straininfo']['file'], f.readline())
for row in reader:
(strain_name, vendor, stocknum, panel, mpd_strainid,
straintype, n_proj, n_snp_datasets, mpdshortname, url) = row
# C57BL/6J,J,000664,,7,IN,225,17,,http://jaxmice.jax.org/strain/000664.html
# create the strain as an instance of the taxon
if self.testMode and \
'MPD:' + str(mpd_strainid) not in self.test_ids:
continue
strain_id = 'MPD-strain:' + str(mpd_strainid)
model.addIndividualToGraph(strain_id, strain_name, tax_id)
if mpdshortname.strip() != '':
model.addSynonym(strain_id, mpdshortname.strip())
self.idlabel_hash[strain_id] = strain_name
# make it equivalent to the vendor+stock
if stocknum != '':
if vendor == 'J':
jax_id = 'JAX:'+stocknum
model.addSameIndividual(strain_id, jax_id)
elif vendor == 'Rbrc':
# reiken
reiken_id = 'RBRC:'+re.sub(r'RBRC', '', stocknum)
model.addSameIndividual(strain_id, reiken_id)
else:
if url != '':
model.addXref(strain_id, url, True)
if vendor != '':
model.addXref(
strain_id, ':'.join((vendor, stocknum)),
True)
# add the panel information
if panel != '':
desc = panel+' [panel]'
model.addDescription(strain_id, desc)
# TODO make the panels as a resource collection
return
def _process_measurements_file(self, limit):
line_counter = 0
logger.info("Processing measurements ...")
raw = '/'.join((self.rawdir, 'measurements.csv'))
with open(raw, 'r') as f:
reader = csv.reader(f)
# read the header row; skip
self.check_header(
self.files['assay_metadata']['file'], f.readline())
for row in reader:
line_counter += 1
assay_id = int(row[0])
assay_label = row[4]
assay_units = row[5]
assay_type = row[6] if row[6] is not '' else None
if assay_id not in self.assayhash:
self.assayhash[assay_id] = {}
description = self.build_measurement_description(row)
self.assayhash[assay_id]['description'] = description
self.assayhash[assay_id]['assay_label'] = assay_label
self.assayhash[assay_id]['assay_type'] = assay_type
self.assayhash[assay_id]['assay_units'] = assay_units
# TODO add projectsym property?
# TODO add intervention?
# ageweeks might be useful for adding to phenotype assoc
# end loop on measurement metadata
return
def _process_strainmeans_file(self, limit):
"""
This will store the entire set of strain means in a hash.
Not the most efficient representation,
but easy access.
We will loop through this later to then apply cutoffs
and add associations
:param limit:
:return:
"""
logger.info("Processing strain means ...")
line_counter = 0
raw = '/'.join((self.rawdir, self.files['strainmeans']['file']))
with gzip.open(raw, 'rb') as f:
f = io.TextIOWrapper(f)
reader = csv.reader(f)
self.check_header(self.files['strainmeans']['file'], f.readline())
score_means_by_measure = {}
strain_scores_by_measure = {}
for row in reader:
try:
(measnum, varname, strain, strainid, sex, mean, nmice, sd,
sem, cv, minval, maxval, logmean, logsd, zscore,
logzscore) = row
except ValueError:
continue
line_counter += 1
strain_num = int(strainid)
assay_num = int(measnum)
# assuming the zscore is across all the items
# in the same measure+var+strain+sex
# note: it seems that there is only ever 1 varname per measnum.
# note: some assays only tested one sex!
# we split this here by sex
if assay_num not in score_means_by_measure:
score_means_by_measure[assay_num] = {}
if sex not in score_means_by_measure[assay_num]:
score_means_by_measure[assay_num][sex] = list()
score_means_by_measure[assay_num][sex].append(float(mean))
if strain_num not in strain_scores_by_measure:
strain_scores_by_measure[strain_num] = {}
if sex not in strain_scores_by_measure[strain_num]:
strain_scores_by_measure[strain_num][sex] = {}
strain_scores_by_measure[strain_num][sex][assay_num] = \
{'mean': float(mean), 'zscore': float(zscore)}
# end loop over strainmeans
self.score_means_by_measure = score_means_by_measure
self.strain_scores_by_measure = strain_scores_by_measure
return
def _fill_provenance_graph(self, limit):
logger.info("Building graph ...")
if self.testMode:
g = self.testgraph
else:
g = self.graph
model = Model(g)
taxon_id = 'NCBITaxon:10090' # hardcode to Mus musculus
model.addClassToGraph(taxon_id, None)
scores_passing_threshold_count = 0
scores_passing_threshold_with_ontologies_count = 0
scores_not_passing_threshold_count = 0
# loop through all the strains,
# and make G2P assoc for those with scores beyond threshold
for strain_num in self.strain_scores_by_measure:
if self.testMode and 'MPD:'+str(strain_num) not in self.test_ids:
continue
strain_id = 'MPD-strain:'+str(strain_num)
for sex in self.strain_scores_by_measure[strain_num]:
measures = self.strain_scores_by_measure[strain_num][sex]
for m in measures:
assay_id = 'MPD-assay:'+str(m)
# TODO consider using the means
# instead of precomputed zscores
if 'zscore' in measures[m]:
zscore = measures[m]['zscore']
if abs(zscore) >= self.stdevthreshold:
scores_passing_threshold_count += 1
# logger.info(
# "Score passing threshold: %s | %s | %s",
# strain_id, assay_id, zscore)
# add the G2P assoc
prov = Provenance(self.graph)
try:
assay_label = self.assayhash[m]['assay_label']
assay_description = \
self.assayhash[m]['description']
ont_term_ids = self.assayhash[m].get('ont_terms')
comment = ' '.join((assay_label,
'(zscore='+str(zscore)+')'))
except KeyError:
assay_label = None
assay_description = None
ont_term_ids = None
if assay_label is not None:
assay_label += ' ('+str(m)+')'
# TODO unused
# assay_type = self.assayhash[m]['assay_type']
assay_type_id = Provenance.provenance_types['assay']
if ont_term_ids is not None:
scores_passing_threshold_with_ontologies_count += 1
prov.add_assay_to_graph(
assay_id, assay_label, assay_type_id,
assay_description)
self._add_g2p_assoc(
g, strain_id, sex, assay_id, ont_term_ids,
comment)
else:
scores_not_passing_threshold_count += 1
logger.info("Scores passing threshold: %d",
scores_passing_threshold_count)
logger.info("Scores passing threshold with ontologies: %d",
scores_passing_threshold_with_ontologies_count)
logger.info("Scores not passing threshold: %d",
scores_not_passing_threshold_count)
return
def _add_g2p_assoc(self, g, strain_id, sex, assay_id, phenotypes, comment):
"""
Create an association between a sex-specific strain id
and each of the phenotypes.
Here, we create a genotype from the strain,
and a sex-specific genotype.
Each of those genotypes are created as anonymous nodes.
The evidence code is hardcoded to be:
ECO:experimental_phenotypic_evidence.
:param g:
:param strain_id:
:param sex:
:param assay_id:
:param phenotypes: a list of phenotypes to association with the strain
:param comment:
:return:
"""
geno = Genotype(g)
model = Model(g)
eco_id = "ECO:0000059" # experimental_phenotypic_evidence
strain_label = self.idlabel_hash.get(strain_id)
# strain genotype
genotype_id = '_'+'-'.join((re.sub(r':', '', strain_id), 'genotype'))
genotype_label = '[' + strain_label + ']'
sex_specific_genotype_id = '_'+'-'.join((re.sub(r':', '', strain_id),
sex, 'genotype'))
if strain_label is not None:
sex_specific_genotype_label = strain_label + ' (' + sex + ')'
else:
sex_specific_genotype_label = strain_id + '(' + sex + ')'
genotype_type = Genotype.genoparts['sex_qualified_genotype']
if sex == 'm':
genotype_type = Genotype.genoparts['male_genotype']
elif sex == 'f':
genotype_type = Genotype.genoparts['female_genotype']
# add the genotype to strain connection
geno.addGenotype(
genotype_id, genotype_label,
Genotype.genoparts['genomic_background'])
g.addTriple(
strain_id, Genotype.object_properties['has_genotype'], genotype_id)
geno.addGenotype(
sex_specific_genotype_id, sex_specific_genotype_label,
genotype_type)
# add the strain as the background for the genotype
g.addTriple(
sex_specific_genotype_id,
Genotype.object_properties['has_sex_agnostic_genotype_part'],
genotype_id)
# ############# BUILD THE G2P ASSOC #############
# TODO add more provenance info when that model is completed
if phenotypes is not None:
for phenotype_id in phenotypes:
assoc = G2PAssoc(
g, self.name, sex_specific_genotype_id, phenotype_id)
assoc.add_evidence(assay_id)
assoc.add_evidence(eco_id)
assoc.add_association_to_graph()
assoc_id = assoc.get_association_id()
model.addComment(assoc_id, comment)
return
def getTestSuite(self):
import unittest
from tests.test_mpd import MPDTestCase
test_suite = unittest.TestLoader().loadTestsFromTestCase(MPDTestCase)
return test_suite
@staticmethod
def normalise_units(units):
# todo:
return units
@staticmethod
def build_measurement_description(row):
(measnum,
mpdsector,
projsym,
varname,
descrip,
units,
method,
intervention,
paneldesc,
datatype,
sextested,
nstrainstested,
ageweeks,) = row
if sextested == 'f':
sextested = 'female'
elif sextested == 'm':
sextested = 'male'
elif sextested == 'fm':
sextested = 'male and female'
else:
logger.warning("Unknown sex tested key: %s", sextested)
description = "This is an assay of [" + descrip + "] shown as a [" + \
datatype + "] measured in [" + units + "]"
if intervention is not None and intervention != "":
description += " in response to [" + intervention + "]"
"""
As of 9/28/2017 intparm is no longer in the measurements.tsv
if intparm is not None and intervention != "":
description += \
". This represents the [" + intparm + \
"] arm, using materials and methods that included [" + \
method + "]"
"""
description += \
". The overall experiment is entitled [" + projsym + "]. "
description += \
"It was conducted in [" + sextested + "] mice at [" + \
ageweeks + "] of age in" + " [" + nstrainstested + \
"] different mouse strains. "
"""
As of 9/28/2017 cat1-3 are no longer in the measurements.tsv
description += "Keywords: " + cat1 + \
((", " + cat2) if cat2.strip() is not "" else "") + \
((", " + cat3) if cat3.strip() is not "" else "") + "."
"""
return description
# def _log_missing_ids(self, missing_id, name_of_file_from_which_missing):
# if missing_id not in self.missing_assay_hash:
# self.missing_assay_hash[missing_id] = set()
# self.missing_assay_hash[missing_id].add(name_of_file_from_which_missing)
# # todo: remove the offending ids from the hash
# return
@staticmethod
def check_header(filename, header):
header = header.rstrip("\n")
header_map = {
'strainmeans.csv.gz':
'measnum,varname,strain,strainid,sex,mean,'
'nmice,sd,sem,cv,minval,maxval,logmean,'
'logsd,zscore,logzscore',
'straininfo.csv':
'strainname,vendor,stocknum,panel,mpd_strainid,'
'straintype,n_proj,n_snp_datasets,mpd_shortname,url',
'measurements.csv':
'measnum,mpdsector,projsym,varname,descrip,units,'
'method,intervention,paneldesc,datatype,sextested,'
'nstrainstested,ageweeks',
'ontology_mappings.csv':
'measnum,ont_term,descrip'
}
if header != header_map[filename]:
raise ValueError(
"header in {} \n {}\n"
"does not match expected:\n {}"
.format(filename, header, header_map[filename])
)
class BioGrid(Source):
"""
Biogrid interaction data
"""
# TODO write up class summary for docstring
files = {
'interactions': {
'file': 'interactions.mitab.zip',
'url': BGDL + '/BIOGRID-ALL-LATEST.mitab.zip'},
'identifiers': {
'file': 'identifiers.tab.zip',
'url': BGDL + '/BIOGRID-IDENTIFIERS-LATEST.tab.zip'}
}
# biogrid-specific identifiers for use in subsetting identifier mapping
biogrid_ids = [
106638, 107308, 107506, 107674, 107675, 108277, 108506, 108767, 108814,
108899, 110308, 110364, 110678, 111642, 112300, 112365, 112771, 112898,
199832, 203220, 247276, 120150, 120160, 124085]
def __init__(self, tax_ids=None):
super().__init__('biogrid')
self.tax_ids = tax_ids
self.load_bindings()
self.dataset = Dataset(
'biogrid', 'The BioGrid', 'http://thebiogrid.org/', None,
'http://wiki.thebiogrid.org/doku.php/terms_and_conditions')
# Defaults
# our favorite animals
# taxids = [9606,10090,10116,7227,7955,6239,8355]
if self.tax_ids is None:
self.tax_ids = [9606, 10090, 7955]
if 'test_ids' not in config.get_config() or \
'gene' not in config.get_config()['test_ids']:
logger.warning("not configured with gene test ids.")
else:
self.test_ids = config.get_config()['test_ids']['gene']
# data-source specific warnings
# (will be removed when issues are cleared)
logger.warning(
"several MI experimental codes do not exactly map to ECO; "
"using approximations.")
return
def fetch(self, is_dl_forced=False):
"""
:param is_dl_forced:
:return: None
"""
self.get_files(is_dl_forced)
# the version number is encoded in the filename in the zip.
# for example, the interactions file may unzip to
# BIOGRID-ALL-3.2.119.mitab.txt, where the version number is 3.2.119
f = '/'.join((self.rawdir, self.files['interactions']['file']))
st = os.stat(f)
filedate = datetime.utcfromtimestamp(st[ST_CTIME]).strftime("%Y-%m-%d")
with ZipFile(f, 'r') as myzip:
flist = myzip.namelist()
# assume that the first entry is the item
fname = flist[0]
# get the version from the filename
version = \
re.match(r'BIOGRID-ALL-(\d+\.\d+\.\d+)\.mitab.txt', fname)
myzip.close()
self.dataset.setVersion(filedate, str(version.groups()[0]))
return
def parse(self, limit=None):
"""
:param limit:
:return:
"""
if self.testOnly:
self.testMode = True
self._get_interactions(limit)
self._get_identifiers(limit)
self.load_bindings()
logger.info("Loaded %d test graph nodes", len(self.testgraph))
logger.info("Loaded %d full graph nodes", len(self.graph))
return
def _get_interactions(self, limit):
logger.info("getting interactions")
line_counter = 0
f = '/'.join((self.rawdir, self.files['interactions']['file']))
myzip = ZipFile(f, 'r')
# assume that the first entry is the item
fname = myzip.namelist()[0]
matchcounter = 0
with myzip.open(fname, 'r') as csvfile:
for line in csvfile:
# skip comment lines
if re.match(r'^#', line.decode()):
logger.debug("Skipping header line")
continue
line_counter += 1
line = line.decode().strip()
# print(line)
(interactor_a, interactor_b, alt_ids_a, alt_ids_b, aliases_a,
aliases_b, detection_method, pub_author, pub_id, taxid_a,
taxid_b, interaction_type, source_db, interaction_id,
confidence_val) = line.split('\t')
# get the actual gene ids,
# typically formated like: gene/locuslink:351|BIOGRID:106848
gene_a_num = re.search(
r'locuslink\:(\d+)\|?', interactor_a).groups()[0]
gene_b_num = re.search(
r'locuslink\:(\d+)\|?', interactor_b).groups()[0]
if self.testMode:
g = self.testgraph
# skip any genes that don't match our test set
if (int(gene_a_num) not in self.test_ids) or\
(int(gene_b_num) not in self.test_ids):
continue
else:
g = self.graph
# when not in test mode, filter by taxon
if int(re.sub(r'taxid:', '', taxid_a.rstrip())) not in\
self.tax_ids or\
int(re.sub(
r'taxid:', '', taxid_b.rstrip())) not in\
self.tax_ids:
continue
else:
matchcounter += 1
gene_a = 'NCBIGene:'+gene_a_num
gene_b = 'NCBIGene:'+gene_b_num
# get the interaction type
# psi-mi:"MI:0407"(direct interaction)
int_type = re.search(r'MI:\d+', interaction_type).group()
rel = self._map_MI_to_RO(int_type)
# scrub pubmed-->PMID prefix
pub_id = re.sub(r'pubmed', 'PMID', pub_id)
# remove bogus whitespace
pub_id = pub_id.strip()
# get the method, and convert to evidence code
det_code = re.search(r'MI:\d+', detection_method).group()
evidence = self._map_MI_to_ECO(det_code)
# note that the interaction_id is some kind of internal biogrid
# identifier that does not map to a public URI.
# we will construct a monarch identifier from this
assoc = InteractionAssoc(self.name, gene_a, gene_b, rel)
assoc.add_evidence(evidence)
assoc.add_source(pub_id)
assoc.add_association_to_graph(g)
assoc.load_all_properties(g)
if not self.testMode and (
limit is not None and line_counter > limit):
break
myzip.close()
return
def _get_identifiers(self, limit):
"""
This will process the id mapping file provided by Biogrid.
The file has a very large header, which we scan past,
then pull the identifiers, and make equivalence axioms
:param limit:
:return:
"""
logger.info("getting identifier mapping")
line_counter = 0
f = '/'.join((self.rawdir, self.files['identifiers']['file']))
myzip = ZipFile(f, 'r')
# assume that the first entry is the item
fname = myzip.namelist()[0]
foundheader = False
gu = GraphUtils(curie_map.get())
# TODO align this species filter with the one above
# speciesfilters = 'H**o sapiens,Mus musculus,Drosophila melanogaster,
# Danio rerio, Caenorhabditis elegans,Xenopus laevis'.split(',')
speciesfilters = 'H**o sapiens,Mus musculus'.split(',')
with myzip.open(fname, 'r') as csvfile:
for line in csvfile:
# skip header lines
if not foundheader:
if re.match(r'BIOGRID_ID', line.decode()):
foundheader = True
continue
line = line.decode().strip()
# BIOGRID_ID
# IDENTIFIER_VALUE
# IDENTIFIER_TYPE
# ORGANISM_OFFICIAL_NAME
# 1 814566 ENTREZ_GENE Arabidopsis thaliana
(biogrid_num, id_num, id_type,
organism_label) = line.split('\t')
if self.testMode:
g = self.testgraph
# skip any genes that don't match our test set
if int(biogrid_num) not in self.biogrid_ids:
continue
else:
g = self.graph
# for each one of these,
# create the node and add equivalent classes
biogrid_id = 'BIOGRID:'+biogrid_num
prefix = self._map_idtype_to_prefix(id_type)
# TODO make these filters available as commandline options
# geneidtypefilters='NCBIGene,OMIM,MGI,FlyBase,ZFIN,MGI,HGNC,
# WormBase,XenBase,ENSEMBL,miRBase'.split(',')
geneidtypefilters = 'NCBIGene,MGI,ENSEMBL,ZFIN,HGNC'.split(',')
# proteinidtypefilters='HPRD,Swiss-Prot,NCBIProtein'
if (speciesfilters is not None) \
and (organism_label.strip() in speciesfilters):
line_counter += 1
if (geneidtypefilters is not None) \
and (prefix in geneidtypefilters):
mapped_id = ':'.join((prefix, id_num))
gu.addEquivalentClass(g, biogrid_id, mapped_id)
# this symbol will only get attached to the biogrid class
elif id_type == 'OFFICIAL_SYMBOL':
gu.addClassToGraph(g, biogrid_id, id_num)
# elif (id_type == 'SYNONYM'):
# FIXME - i am not sure these are synonyms, altids?
# gu.addSynonym(g,biogrid_id,id_num)
if not self.testMode and limit is not None \
and line_counter > limit:
break
myzip.close()
return
@staticmethod
def _map_MI_to_RO(mi_id):
rel = InteractionAssoc.interaction_object_properties
mi_ro_map = {
# colocalization
'MI:0403': rel['colocalizes_with'],
# direct interaction
'MI:0407': rel['interacts_with'],
# synthetic genetic interaction defined by inequality
'MI:0794': rel['genetically_interacts_with'],
# suppressive genetic interaction defined by inequality
'MI:0796': rel['genetically_interacts_with'],
# additive genetic interaction defined by inequality
'MI:0799': rel['genetically_interacts_with'],
# association
'MI:0914': rel['interacts_with'],
# physical association
'MI:0915': rel['interacts_with']
}
ro_id = rel['interacts_with'] # default
if mi_id in mi_ro_map:
ro_id = mi_ro_map.get(mi_id)
return ro_id
@staticmethod
def _map_MI_to_ECO(mi_id):
eco_id = 'ECO:0000006' # default to experimental evidence
mi_to_eco_map = {
'MI:0018': 'ECO:0000068', # yeast two-hybrid
'MI:0004': 'ECO:0000079', # affinity chromatography
'MI:0047': 'ECO:0000076', # far western blotting
'MI:0055': 'ECO:0000021', # should be FRET, but using physical_interaction FIXME
'MI:0090': 'ECO:0000012', # desired: protein complementation, using: functional complementation
'MI:0096': 'ECO:0000085', # desired: pull down, using: immunoprecipitation
'MI:0114': 'ECO:0000324', # desired: x-ray crystallography, using: imaging assay
'MI:0254': 'ECO:0000011', # desired: genetic interference, using: genetic interaction evidence
'MI:0401': 'ECO:0000172', # desired: biochemical, using: biochemical trait evidence
'MI:0415': 'ECO:0000005', # desired: enzymatic study, using: enzyme assay evidence
'MI:0428': 'ECO:0000324', # imaging
'MI:0686': 'ECO:0000006', # desired: unspecified, using: experimental evidence
'MI:1313': 'ECO:0000006' # None?
}
if mi_id in mi_to_eco_map:
eco_id = mi_to_eco_map.get(mi_id)
else:
logger.warning(
"unmapped code %s. Defaulting to experimental_evidence", mi_id)
return eco_id
@staticmethod
def _map_idtype_to_prefix(idtype):
"""
Here we need to reformat the BioGrid source prefixes
to standard ones used in our curie-map.
:param idtype:
:return:
"""
prefix = idtype
idtype_to_prefix_map = {
'XENBASE': 'XenBase',
'TREMBL': 'TrEMBL',
'MGI': 'MGI',
'REFSEQ_DNA_ACCESSION': 'RefSeqNA',
'MAIZEGDB': 'MaizeGDB',
'BEEBASE': 'BeeBase',
'ENSEMBL': 'ENSEMBL',
'TAIR': 'TAIR',
'GENBANK_DNA_GI': 'NCBIgi',
'CGNC': 'CGNC',
'RGD': 'RGD',
'GENBANK_GENOMIC_DNA_GI': 'NCBIgi',
'SWISSPROT': 'Swiss-Prot',
'MIM': 'OMIM',
'FLYBASE': 'FlyBase',
'VEGA': 'VEGA',
'ANIMALQTLDB': 'AQTLDB',
'ENTREZ_GENE_ETG': 'ETG',
'HPRD': 'HPRD',
'APHIDBASE': 'APHIDBASE',
'GENBANK_PROTEIN_ACCESSION': 'NCBIProtein',
'ENTREZ_GENE': 'NCBIGene',
'SGD': 'SGD',
'GENBANK_GENOMIC_DNA_ACCESSION': 'NCBIGenome',
'BGD': 'BGD',
'WORMBASE': 'WormBase',
'ZFIN': 'ZFIN',
'DICTYBASE': 'dictyBase',
'ECOGENE': 'ECOGENE',
'BIOGRID': 'BIOGRID',
'GENBANK_DNA_ACCESSION': 'NCBILocus',
'VECTORBASE': 'VectorBase',
'MIRBASE': 'miRBase',
'IMGT/GENE-DB': 'IGMT',
'HGNC': 'HGNC',
'SYSTEMATIC_NAME': None,
'OFFICIAL_SYMBOL': None,
'REFSEQ_GENOMIC_DNA_ACCESSION': 'NCBILocus',
'GENBANK_PROTEIN_GI': 'NCBIgi',
'REFSEQ_PROTEIN_ACCESSION': 'RefSeqProt',
'SYNONYM': None,
'GRID_LEGACY': None,
# the following showed up in 3.3.124
'UNIPROT-ACCESSION': 'UniprotKB',
'SWISS-PROT': 'Swiss-Prot',
'OFFICIAL SYMBOL': None,
'ENSEMBL RNA': None,
'GRID LEGACY': None,
'ENSEMBL PROTEIN': None,
'REFSEQ-RNA-GI': None,
'REFSEQ-RNA-ACCESSION': None,
'REFSEQ-PROTEIN-GI': None,
'REFSEQ-PROTEIN-ACCESSION-VERSIONED': None,
'REFSEQ-PROTEIN-ACCESSION': None,
'REFSEQ-LEGACY': None,
'SYSTEMATIC NAME': None,
'ORDERED LOCUS': None,
'UNIPROT-ISOFORM': 'UniprotKB',
'ENSEMBL GENE': 'ENSEMBL',
'CGD': None, # Not sure what this is?
'WORMBASE-OLD': 'WormBase'
}
if idtype in idtype_to_prefix_map:
prefix = idtype_to_prefix_map.get(idtype)
else:
logger.warning("unmapped prefix %s", prefix)
return prefix
def getTestSuite(self):
import unittest
from tests.test_biogrid import BioGridTestCase
# TODO add InteractionAssoc tests
# TODO add test about if all prefixes are mapped?
test_suite = \
unittest.TestLoader().loadTestsFromTestCase(BioGridTestCase)
return test_suite
class WormBase(Source):
"""
This is the parser for the
[C. elegans Model Organism Database (WormBase)](http://www.wormbase.org),
from which we process genotype and phenotype data for laboratory worms
(C.elegans and other nematodes).
We generate the wormbase graph to include the following information:
* genes
* sequence alterations (includes SNPs/del/ins/indel and
large chromosomal rearrangements)
* RNAi as expression-affecting reagents
* genotypes, and their components
* strains
* publications (and their mapping to PMIDs, if available)
* allele-to-phenotype associations (including variants by RNAi)
* genetic positional information for genes and sequence alterations
Genotypes leverage the GENO genotype model and includes both
intrinsic and extrinsic genotypes. Where necessary, we create anonymous
nodes of the genotype partonomy (i.e. for variant single locus complements,
genomic variation complements, variant loci, extrinsic genotypes, and
extrinsic genotype parts).
TODO: get people and gene expression
"""
wbftp = 'ftp://ftp.wormbase.org/pub/wormbase/releases/current-development-release'
files = {
'gene_ids': {
'file': 'c_elegans.PRJNA13758.geneIDs.txt.gz',
'url': wbftp +
'/species/c_elegans/PRJNA13758/annotation/c_elegans.PRJNA13758.WSNUMBER.geneIDs.txt.gz'},
# 'gene_desc': { # TEC: no functional_descriptions available 2016 Mar 03
# 'file': 'c_elegans.PRJNA13758.functional_descriptions.txt.gz',
# 'url': wbftp+'/species/c_elegans/PRJNA13758/annotation/c_elegans.PRJNA13758.WSNUMBER.functional_descriptions.txt.gz'},
'allele_pheno': {
'file': 'phenotype_association.wb',
'url': wbftp + '/ONTOLOGY/phenotype_association.WSNUMBER.wb'},
'rnai_pheno': {
'file': 'rnai_phenotypes.wb',
'url': wbftp + '/ONTOLOGY/rnai_phenotypes.WSNUMBER.wb'},
'pub_xrefs': {
'file': 'pub_xrefs.txt',
'url': 'http://tazendra.caltech.edu/~azurebrd/cgi-bin/forms/generic.cgi?action=WpaXref'},
'feature_loc': {
'file': 'c_elegans.PRJNA13758.annotations.gff3.gz',
'url': wbftp + '/species/c_elegans/PRJNA13758/c_elegans.PRJNA13758.WSNUMBER.annotations.gff3.gz'},
'disease_assoc': {
'file': 'disease_association.wb',
'url': 'ftp://ftp.sanger.ac.uk/pub/wormbase/releases/WSNUMBER/ONTOLOGY/disease_association.WSNUMBER.wb'},
# 'genes_during_development': {
# 'file': 'development_association.wb',
# 'url wbftp+'/ONTOLOGY/development_association.WS249.wb'},
# 'genes_in_anatomy': {
# 'file': 'anatomy_association.wb',
# 'url': wbftp+'/ONTOLOGY/anatomy_association.WS249.wb'},
# 'gene_interaction': {
# 'file': 'c_elegans.PRJNA13758.gene_interactions.txt.gz',
# 'url': wbftp+'/species/c_elegans/PRJNA13758/annotation/c_elegans.PRJNA13758.WSNUMBER.gene_interactions.txt.gz'},
# 'orthologs': {
# 'file': 'c_elegans.PRJNA13758.orthologs.txt.gz',
# 'url': wbftp+'/species/c_elegans/PRJNA13758/annotation/c_elegans.PRJNA13758.WS249.orthologs.txt.gz'},
'xrefs': {
'file': 'c_elegans.PRJNA13758.xrefs.txt.gz',
'url': wbftp + '/species/c_elegans/PRJNA13758/c_elegans.PRJNA13758.WSNUMBER.xrefs.txt.gz'},
'letter': {
'file': 'letter.WSNUMBER',
'url': wbftp + '/letter.WSNUMBER'},
}
test_ids = {
'gene': [
'WBGene00001414', 'WBGene00004967', 'WBGene00003916',
'WBGene00004397', 'WBGene00001531'],
'allele': [
'WBVar00087800', 'WBVar00087742', 'WBVar00144481', 'WBVar00248869',
'WBVar00250630'],
'strain': ['BA794', 'RK1', 'HE1006'],
'pub': [] # FIXME
}
def __init__(self):
Source.__init__(self, 'wormbase')
# update the dataset object with details about this resource
# NO LICENSE for this resource
self.dataset = Dataset(
'wormbase', 'WormBase', 'http://www.wormbase.org', None, None,
'http://www.wormbase.org/about/policies#012')
self.version_num = None
return
def fetch(self, is_dl_forced=False):
# figure out the version number by probing the "current_release",
# then edit the file dict accordingly
# connect to wormbase ftp
current_dev_release_dir = \
'pub/wormbase/releases/current-development-release'
ftp = FTP('ftp.wormbase.org')
ftp.login()
ftp.cwd(current_dev_release_dir)
# the current release dir is a redirect to a versioned release.
# pull that from the pwd.
pwd = ftp.pwd()
ftp.quit()
wsver = re.search(r'releases\/(WS\d+)', pwd)
if wsver is None or len(wsver.groups()) < 1:
logger.error(
"Couldn't figure out version number from FTP site. Exiting.")
exit(1)
else:
self.update_wsnum_in_files(wsver.group(1))
self.dataset.set_version_by_num(self.version_num)
# fetch all the files
self.get_files(is_dl_forced)
return
def update_wsnum_in_files(self, vernum):
"""
With the given version number ```vernum```,
update the source's version number, and replace in the file hashmap.
We also save the "letter" for the version
to maintain the version number.
:param vernum:
:return:
"""
self.version_num = vernum
# replace the WSNUMBER in the url paths with the real WS###
for f in self.files:
url = self.files[f].get('url')
url = re.sub(r'WSNUMBER', self.version_num, url)
self.files[f]['url'] = url
logger.debug(
"Replacing WSNUMBER in %s with %s", f, self.version_num)
# also the letter file - keep this so we know the version number
self.files['letter']['file'] = re.sub(r'WSNUMBER',
self.version_num,
self.files['letter']['file'])
return
def parse(self, limit=None):
if limit is not None:
logger.info("Only parsing first %s rows of each file", limit)
if self.version_num is None:
import os
logger.info("Figuring out version num for files")
# probe the raw directory for the WSnumber on
# the "letter.WS###" file.
# this is the only one that we keep the version number on
files = os.listdir(self.rawdir)
letter_file = next(f for f in files if re.match(r'letter', f))
vernum = re.search(r'(WS\d+)', letter_file)
self.update_wsnum_in_files(vernum.group(1))
logger.info("Parsing files...")
if self.testOnly:
self.testMode = True
if self.testMode:
g = self.testgraph
else:
g = self.graph
self.nobnodes = True # FIXME
# to hold any label for a given id
self.id_label_map = {}
# to hold the mappings between genotype and background
self.genotype_backgrounds = {}
self.extrinsic_id_to_enviro_id_hash = {}
# to hold the genes variant due to a seq alt
self.variant_loci_genes = {}
# to hold the parts of an environment
self.environment_hash = {}
self.wildtype_genotypes = []
# stores the rnai_reagent to gene targets
self.rnai_gene_map = {}
self.process_gene_ids(limit)
# self.process_gene_desc(limit) #TEC imput file is mia 2016-Mar-03
self.process_allele_phenotype(limit)
self.process_rnai_phenotypes(limit)
self.process_pub_xrefs(limit)
self.process_feature_loc(limit)
self.process_disease_association(limit)
# TODO add this when when complete
# self.process_gene_interaction(limit)
logger.info("Finished parsing.")
self.load_bindings()
gu = GraphUtils(curie_map.get())
gu.loadAllProperties(g)
gu.loadObjectProperties(g, Genotype.object_properties)
logger.info("Found %d nodes in graph", len(self.graph))
logger.info("Found %d nodes in testgraph", len(self.testgraph))
return
def process_gene_ids(self, limit):
raw = '/'.join((self.rawdir, self.files['gene_ids']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
gu = GraphUtils(curie_map.get())
logger.info("Processing Gene IDs")
line_counter = 0
geno = Genotype(g)
with gzip.open(raw, 'rb') as csvfile:
filereader = csv.reader(
io.TextIOWrapper(csvfile, newline=""), delimiter=',',
quotechar='\"')
for row in filereader:
line_counter += 1
(taxon_num, gene_num, gene_symbol, gene_synonym, live) = row
# 6239,WBGene00000001,aap-1,Y110A7A.10,Live
if self.testMode and gene_num not in self.test_ids['gene']:
continue
taxon_id = 'NCBITaxon:'+taxon_num
gene_id = 'WormBase:'+gene_num
if gene_symbol == '':
gene_symbol = gene_synonym
if gene_symbol == '':
gene_symbol = None
gu.addClassToGraph(
g, gene_id, gene_symbol, Genotype.genoparts['gene'])
if live == 'Dead':
gu.addDeprecatedClass(g, gene_id)
geno.addTaxon(taxon_id, gene_id)
if gene_synonym != '':
gu.addSynonym(g, gene_id, gene_synonym)
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def process_gene_desc(self, limit):
raw = '/'.join((self.rawdir, self.files['gene_desc']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
gu = GraphUtils(curie_map.get())
logger.info("Processing Gene descriptions")
line_counter = 0
# geno = Genotype(g) # TODO unused
with gzip.open(raw, 'rb') as csvfile:
filereader = csv.reader(
io.TextIOWrapper(csvfile, newline=""), delimiter='\t',
quotechar='\"')
for row in filereader:
if re.match(r'\#', ''.join(row)):
continue
line_counter += 1
if line_counter == 1:
continue
(gene_num, public_name, molecular_name, concise_description,
provisional_description, detailed_description,
automated_description, gene_class_description) = row
if self.testMode and gene_num not in self.test_ids['gene']:
continue
gene_id = 'WormBase:'+gene_num
if concise_description != 'none available':
gu.addDefinition(g, gene_id, concise_description)
# remove the description if it's identical to the concise
descs = {
'provisional': provisional_description,
'automated': automated_description,
'detailed': detailed_description,
'gene class': gene_class_description
}
for d in descs:
text = descs.get(d)
if text == concise_description \
or re.match(r'none', text) or text == '':
pass # don't use it
else:
text = ' '.join((text, '['+d+']'))
descs[d] = text
gu.addDescription(g, gene_id, text)
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def process_allele_phenotype(self, limit=None):
"""
This file compactly lists variant to phenotype associations,
such that in a single row, there may be >1 variant listed
per phenotype and paper. This indicates that each variant is
individually assocated with the given phenotype,
as listed in 1+ papers.
(Not that the combination of variants is producing the phenotype.)
:param limit:
:return:
"""
raw = '/'.join((self.rawdir, self.files['allele_pheno']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
# gu = GraphUtils(curie_map.get()) # TODO unused
logger.info("Processing Allele phenotype associations")
line_counter = 0
geno = Genotype(g)
with open(raw, 'r') as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
if re.match(r'!', ''.join(row)): # header
continue
line_counter += 1
(db, gene_num, gene_symbol, is_not, phenotype_id, ref,
eco_symbol, with_or_from, aspect, gene_name, gene_synonym,
gene_class, taxon, date, assigned_by, blank, blank2) = row
if self.testMode and gene_num not in self.test_ids['gene']:
continue
# TODO add NOT phenotypes
if is_not == 'NOT':
continue
eco_id = None
if eco_symbol == 'IMP':
eco_id = 'ECO:0000015'
elif eco_symbol.strip() != '':
logger.warning(
"Encountered an ECO code we don't have: %s",
eco_symbol)
# according to the GOA spec, persons are not allowed to be
# in the reference column, therefore they the variant and
# persons are swapped between the reference and with column.
# we unswitch them here.
temp_var = temp_ref = None
if re.search(r'WBVar|WBRNAi', ref):
temp_var = ref
# move the paper from the with column into the ref
if re.search(r'WBPerson', with_or_from):
temp_ref = with_or_from
if temp_var is not None or temp_ref is not None:
with_or_from = temp_var
ref = temp_ref
allele_list = re.split(r'\|', with_or_from)
if len(allele_list) == 0:
logger.error(
"Missing alleles from phenotype assoc at line %d",
line_counter)
continue
else:
for a in allele_list:
allele_num = re.sub(r'WB:', '', a.strip())
allele_id = 'WormBase:'+allele_num
gene_id = 'WormBase:'+gene_num
if re.search(r'WBRNAi', allele_id):
# make the reagent-targeted gene,
# & annotate that instead of the RNAi item directly
rnai_num = re.sub(r'WormBase:', '', allele_id)
rnai_id = allele_id
rtg_id = self.make_reagent_targeted_gene_id(
gene_num, rnai_num, self.nobnodes)
geno.addReagentTargetedGene(
rnai_id, 'WormBase:'+gene_num, rtg_id)
geno.addGeneTargetingReagent(
rnai_id, None, geno.genoparts['RNAi_reagent'],
gene_id)
allele_id = rtg_id
elif re.search(r'WBVar', allele_id):
# this may become deprecated by using wormmine
# make the allele to gene relationship
# the WBVars are really sequence alterations
# the public name will come from elsewhere
geno.addSequenceAlteration(allele_id, None)
vl_id = '_'+'-'.join((gene_num, allele_num))
if self.nobnodes:
vl_id = ':'+vl_id
geno.addSequenceAlterationToVariantLocus(
allele_id, vl_id)
geno.addAlleleOfGene(vl_id, gene_id)
else:
logger.warning(
"Some kind of allele I don't recognize: %s",
allele_num)
continue
assoc = G2PAssoc(self.name, allele_id, phenotype_id)
if eco_id is not None:
assoc.add_evidence(eco_id)
if ref is not None and ref != '':
ref = re.sub(r'(WB:|WB_REF:)', 'WormBase:', ref)
r = Reference(ref)
if re.search(r'Person', ref):
r.setType(r.ref_types['person'])
# also add
# inferred from background scientific knowledge
assoc.add_evidence('ECO:0000001')
r.addRefToGraph(g)
assoc.add_source(ref)
assoc.add_association_to_graph(g)
# finish looping through all alleles
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def process_rnai_phenotypes(self, limit=None):
raw = '/'.join((self.rawdir, self.files['rnai_pheno']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
# gu = GraphUtils(curie_map.get()) # TODO unused
logger.info("Processing RNAi phenotype associations")
line_counter = 0
geno = Genotype(g)
with open(raw, 'r') as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
line_counter += 1
(gene_num, gene_alt_symbol, phenotype_label, phenotype_id,
rnai_and_refs) = row
# WBGene00001908 F17E9.9 locomotion variant WBPhenotype:0000643 WBRNAi00025129|WBPaper00006395 WBRNAi00025631|WBPaper00006395
# WBGene00001908 F17E9.9 avoids bacterial lawn WBPhenotype:0000402 WBRNAi00095640|WBPaper00040984
# WBGene00001908 F17E9.9 RAB-11 recycling endosome localization variant WBPhenotype:0002107 WBRNAi00090830|WBPaper00041129
if self.testMode and gene_num not in self.test_ids['gene']:
continue
gene_id = 'WormBase:'+gene_num
# refs = list() # TODO unused
# the rnai_and_refs has this so that
# WBRNAi00008687|WBPaper00005654 WBRNAi00025197|WBPaper00006395 WBRNAi00045381|WBPaper00025054
# space delimited between RNAi sets;
# then each RNAi should have a paper
rnai_sets = re.split(r' ', rnai_and_refs)
for s in rnai_sets:
# get the rnai_id
(rnai_num, ref_num) = re.split(r'\|', s)
if len(re.split(r'\|', s)) > 2:
logger.warning(
"There's an unexpected number of items in %s", s)
if rnai_num not in self.rnai_gene_map:
self.rnai_gene_map[rnai_num] = set()
# to use for looking up later
self.rnai_gene_map[rnai_num].add(gene_num)
rnai_id = 'WormBase:'+rnai_num
geno.addGeneTargetingReagent(
rnai_id, None, geno.genoparts['RNAi_reagent'], gene_id)
# make the "allele" of the gene
# that is targeted by the reagent
allele_id = self.make_reagent_targeted_gene_id(
gene_num, rnai_num, self.nobnodes)
allele_label = gene_alt_symbol+'<'+rnai_num+'>'
geno.addReagentTargetedGene(
rnai_id, gene_id, allele_id, allele_label)
assoc = G2PAssoc(self.name, allele_id, phenotype_id)
assoc.add_source('WormBase:'+ref_num)
# eco_id = 'ECO:0000019' # RNAi evidence # TODO unused
assoc.add_association_to_graph(g)
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def process_pub_xrefs(self, limit=None):
raw = '/'.join((self.rawdir, self.files['pub_xrefs']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
gu = GraphUtils(curie_map.get())
logger.info("Processing publication xrefs")
line_counter = 0
with open(raw, 'r') as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
line_counter += 1
(wb_ref, xref) = row
# WBPaper00000009 pmid8805<BR>
# WBPaper00000011 doi10.1139/z78-244<BR>
# WBPaper00000012 cgc12<BR>
if self.testMode and wb_ref not in self.test_ids['pub']:
continue
ref_id = 'WormBase:'+wb_ref
xref_id = r = None
xref = re.sub(r'<BR>', '', xref)
xref = xref.strip()
if re.match(r'pmid', xref):
xref_id = 'PMID:'+re.sub(r'pmid\s*', '', xref)
r = Reference(
xref_id, Reference.ref_types['journal_article'])
elif re.search(r'[\(\)\<\>\[\]\s]', xref):
continue
elif re.match(r'doi', xref):
xref_id = 'DOI:'+re.sub(r'doi', '', xref.strip())
r = Reference(xref_id)
elif re.match(r'cgc', xref):
# TODO not sure what to do here with cgc xrefs
continue
else:
# logger.debug("Other xrefs like %s", xref)
continue
if xref_id is not None:
r.addRefToGraph(g)
gu.addSameIndividual(g, ref_id, xref_id)
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def process_feature_loc(self, limit):
raw = '/'.join((self.rawdir, self.files['feature_loc']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
gu = GraphUtils(curie_map.get())
logger.info("Processing Feature location and attributes")
line_counter = 0
geno = Genotype(g)
strain_to_variant_map = {}
build_num = self.version_num
build_id = 'WormBase:'+build_num
with gzip.open(raw, 'rb') as csvfile:
filereader = csv.reader(
io.TextIOWrapper(csvfile, newline=""), delimiter='\t',
quotechar='\"')
for row in filereader:
if re.match(r'\#', ''.join(row)):
continue
(chrom, db, feature_type_label, start, end, score, strand,
phase, attributes) = row
# I interpolated_pmap_position gene 1 559768 . . . ID=gmap:spe-13;gmap=spe-13;status=uncloned;Note=-21.3602 cM (+/- 1.84 cM)
# I WormBase gene 3747 3909 . - . ID=Gene:WBGene00023193;Name=WBGene00023193;interpolated_map_position=-21.9064;sequence_name=Y74C9A.6;biotype=snoRNA;Alias=Y74C9A.6
# I absolute_pmap_position gene 4119 10230 . . . ID=gmap:homt-1;gmap=homt-1;status=cloned;Note=-21.8252 cM (+/- 0.00 cM)
# dbs = re.split(
# r' ', 'assembly_component expressed_sequence_match Coding_transcript Genomic_canonical Non_coding_transcript Orfeome Promoterome Pseudogene RNAi_primary RNAi_secondary Reference Transposon Transposon_CDS cDNA_for_RNAi miRanda ncRNA operon polyA_signal_sequence polyA_site snlRNA')
#
# if db not in dbs:
# continue
if feature_type_label not in [
'gene', 'point_mutation', 'deletion', 'RNAi_reagent',
'duplication', 'enhancer', 'binding_site',
'biological_region', 'complex_substitution',
'substitution', 'insertion', 'inverted_repeat']:
# note biological_regions include balancers
# other options here: promoter, regulatory_region, reagent
continue
line_counter += 1
attribute_dict = {}
if attributes != '':
attribute_dict = dict(
item.split("=")for item in
re.sub(r'"', '', attributes).split(";"))
fid = flabel = desc = None
if 'ID' in attribute_dict:
fid = attribute_dict.get('ID')
if re.search(r'WB(Gene|Var|sf)', fid):
fid = re.sub(r'^\w+:WB', 'WormBase:WB', fid)
elif re.match(r'(gmap|landmark)', fid):
continue
else:
logger.info('other identifier %s', fid)
fid = None
elif 'variation' in attribute_dict:
fid = 'WormBase:'+attribute_dict.get('variation')
flabel = attribute_dict.get('public_name')
sub = attribute_dict.get('substitution')
ins = attribute_dict.get('insertion')
# if it's a variation:
# variation=WBVar00604246;public_name=gk320600;strain=VC20384;substitution=C/T
desc = ''
if sub is not None:
desc = 'substitution='+sub
if ins is not None:
desc = 'insertion='+ins
# keep track of the strains with this variation,
# for later processing
strain_list = attribute_dict.get('strain')
if strain_list is not None:
for s in re.split(r',', strain_list):
if s.strip() not in strain_to_variant_map:
strain_to_variant_map[s.strip()] = set()
strain_to_variant_map[s.strip()].add(fid)
# if feature_type_label == 'RNAi_reagent':
# Target=WBRNAi00096030 1 4942
# this will tell us where the RNAi is actually binding
# target = attribute_dict.get('Target') # TODO unused
# rnai_num = re.split(r' ', target)[0] # TODO unused
# it will be the reagent-targeted-gene that has a position,
# (i think)
# TODO finish the RNAi binding location
name = attribute_dict.get('Name')
polymorphism = attribute_dict.get('polymorphism')
if fid is None:
if name is not None and re.match(r'WBsf', name):
fid = 'WormBase:'+name
name = None
else:
continue
if self.testMode \
and re.sub(r'WormBase:', '', fid) \
not in self.test_ids['gene']+self.test_ids['allele']:
continue
# these really aren't that interesting
if polymorphism is not None:
continue
if name is not None and not re.search(name, fid):
if flabel is None:
flabel = name
else:
gu.addSynonym(g, fid, name)
if desc is not None:
gu.addDescription(g, fid, desc)
alias = attribute_dict.get('Alias')
biotype = attribute_dict.get('biotype')
note = attribute_dict.get('Note')
other_name = attribute_dict.get('other_name')
for n in [alias, other_name]:
if n is not None:
gu.addSynonym(g, fid, other_name)
ftype = self.get_feature_type_by_class_and_biotype(
feature_type_label, biotype)
chr_id = makeChromID(chrom, build_id, 'CHR')
geno.addChromosomeInstance(chrom, build_id, build_num)
f = Feature(fid, flabel, ftype)
f.addFeatureStartLocation(start, chr_id, strand)
f.addFeatureEndLocation(start, chr_id, strand)
feature_is_class = False
if feature_type_label == 'gene':
feature_is_class = True
f.addFeatureToGraph(g, True, None, feature_is_class)
if note is not None:
gu.addDescription(g, fid, note)
if not self.testMode \
and limit is not None and line_counter > limit:
break
# RNAi reagents:
# I RNAi_primary RNAi_reagent 4184 10232 . + . Target=WBRNAi00001601 1 6049 +;laboratory=YK;history_name=SA:yk326e10
# I RNAi_primary RNAi_reagent 4223 10147 . + . Target=WBRNAi00033465 1 5925 +;laboratory=SV;history_name=MV_SV:mv_G_YK5052
# I RNAi_primary RNAi_reagent 5693 9391 . + . Target=WBRNAi00066135 1 3699 +;laboratory=CH
# TODO TF bindiing sites and network:
# I TF_binding_site_region TF_binding_site 1861 2048 . + . Name=WBsf292777;tf_id=WBTranscriptionFactor000025;tf_name=DAF-16
# I TF_binding_site_region TF_binding_site 3403 4072 . + . Name=WBsf331847;tf_id=WBTranscriptionFactor000703;tf_name=DPL-1
return
def process_disease_association(self, limit):
raw = '/'.join((self.rawdir, self.files['disease_assoc']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
gu = GraphUtils(curie_map.get())
logger.info("Processing disease models")
geno = Genotype(g, self.nobnodes)
line_counter = 0
worm_taxon = 'NCBITaxon:6239'
with open(raw, 'r') as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
if re.match(r'!', ''.join(row)): # header
continue
line_counter += 1
(db, gene_num, gene_symbol, is_not, disease_id, ref,
eco_symbol, with_or_from, aspect, gene_name, gene_synonym,
gene_class, taxon, date, assigned_by, blank, blank2) = row
if self.testMode and gene_num not in self.test_ids['gene']:
continue
# TODO add NOT phenotypes
if is_not == 'NOT':
continue
# WB WBGene00000001 aap-1 DOID:2583 PMID:19029536 IEA ENSEMBL:ENSG00000145675|OMIM:615214 D Y110A7A.10 gene taxon:6239 20150612 WB
gene_id = 'WormBase:'+gene_num
# make a variant of the gene
vl = '_'+'-'.join((gene_num, 'unspecified'))
if self.nobnodes:
vl = ':'+vl
vl_label = 'some variant of '+gene_symbol
geno.addAlleleOfGene(vl, gene_id)
animal_id = geno.make_experimental_model_with_genotype(
g, vl, vl_label, worm_taxon, 'worm')
assoc = G2PAssoc(
self.name, animal_id,
disease_id, gu.object_properties['model_of'])
ref = re.sub(r'WB_REF:', 'WormBase:', ref)
if ref != '':
assoc.add_source(ref)
eco_id = None
if eco_symbol == 'IEA':
eco_id = 'ECO:0000501' # IEA is this now
if eco_id is not None:
assoc.add_evidence(eco_id)
assoc.add_association_to_graph(g)
return
def process_gene_interaction(self, limit):
"""
The gene interaction file includes identified interactions,
that are between two or more gene (products).
In the case of interactions with >2 genes, this requires creating
groups of genes that are involved in the interaction.
From the wormbase help list: In the example WBInteraction000007779
it would likely be misleading to suggest that lin-12 interacts with
(suppresses in this case) smo-1 ALONE or that lin-12 suppresses let-60
ALONE; the observation in the paper; see Table V in paper PMID:15990876
was that a lin-12 allele (heterozygous lin-12(n941/+)) could suppress
the "multivulva" phenotype induced synthetically by simultaneous
perturbation of BOTH smo-1 (by RNAi) AND let-60 (by the n2021 allele).
So this is necessarily a three-gene interaction.
Therefore, we can create groups of genes based on their "status" of
Effector | Effected.
Status: IN PROGRESS
:param limit:
:return:
"""
raw = '/'.join((self.rawdir, self.files['gene_interaction']['file']))
if self.testMode:
g = self.testgraph
else:
g = self.graph
gu = GraphUtils(curie_map.get())
logger.info("Processing gene interaction associations")
line_counter = 0
with gzip.open(raw, 'rb') as csvfile:
filereader = csv.reader(
io.TextIOWrapper(csvfile, newline=""), delimiter='\t',
quotechar="'")
for row in filereader:
line_counter += 1
if re.match(r'#', ''.join(row)):
continue
(interaction_num, interaction_type, interaction_subtype,
summary, citation) = row[0:5]
print(row)
interaction_id = 'WormBase:'+interaction_num
# TODO deal with subtypes
interaction_type_id = None
if interaction_type == 'Genetic':
interaction_type_id = \
InteractionAssoc.interaction_object_properties[
'genetically_interacts_with']
elif interaction_type == 'Physical':
interaction_type_id = \
InteractionAssoc.interaction_object_properties[
'molecularly_interacts_with']
elif interaction_type == 'Regulatory':
interaction_type_id = \
InteractionAssoc.interaction_object_properties[
'regulates']
else:
logger.info(
"An interaction type I don't understand %s",
interaction_type)
num_interactors = (len(row) - 5) / 3
if num_interactors != 2:
logger.info(
"Skipping interactions with !=2 participants:\n %s",
str(row))
continue
gene_a_id = 'WormBase:'+row[5]
gene_b_id = 'WormBase:'+row[8]
if self.testMode \
and gene_a_id not in self.test_ids['gene'] \
and gene_b_id not in self.test_ids['gene']:
continue
assoc = InteractionAssoc(
self.name, gene_a_id, gene_b_id, interaction_type_id)
assoc.set_association_id(interaction_id)
assoc.add_association_to_graph(g)
assoc_id = assoc.get_association_id()
# citation is not a pmid or WBref - get this some other way
gu.addDescription(g, assoc_id, summary)
if not self.testMode \
and limit is not None and line_counter > limit:
break
return
def get_feature_type_by_class_and_biotype(self, ftype, biotype):
ftype_id = None
biotype_map = {
'lincRNA': 'SO:0001641',
'miRNA': 'SO:0001265',
'ncRNA': 'SO:0001263',
'piRNA': 'SO:0001638',
'rRNA': 'SO:0001637',
'scRNA': 'SO:0001266',
'snRNA': 'SO:0001268',
'snoRNA': 'SO:0001267',
'tRNA': 'SO:0001272',
# transposable element gene
'transposon_protein_coding': 'SO:0000111',
'transposon_pseudogene': 'SO:0001897',
'pseudogene': 'SO:0000336',
'protein_coding': 'SO:0001217',
'asRNA': 'SO:0001263', # using ncRNA gene TODO make term request
}
ftype_map = {
'point_mutation': 'SO:1000008',
'deletion': 'SO:0000159',
'RNAi_reagent': 'SO:0000337',
'duplication': 'SO:1000035',
'enhancer': 'SO:0000165',
'binding_site': 'SO:0000409',
'biological_region': 'SO:0001411',
'complex_substitution': 'SO:1000005'
}
if ftype == 'gene':
if biotype in biotype_map:
ftype_id = biotype_map.get(biotype)
else:
ftype_id = ftype_map.get(ftype)
return ftype_id
def make_reagent_targeted_gene_id(
self, gene_id, reagent_id, nobnodes=False):
rtg_id = '_'+'-'.join((gene_id, reagent_id))
# TODO targeted_gene_id unused
# targeted_gene_id = re.sub(r'W(orm)?B(ase)?:', '', rtg_id)
if nobnodes:
rtg_id = ':'+rtg_id
return rtg_id
def getTestSuite(self):
import unittest
from tests.test_wormbase import WormBaseTestCase
test_suite = \
unittest.TestLoader().loadTestsFromTestCase(WormBaseTestCase)
return test_suite
class HPOAnnotations(Source):
"""
The [Human Phenotype Ontology](http://human-phenotype-ontology.org) group curates and assembles
over 115,000 annotations to hereditary diseases using the HPO ontology.
Here we create OBAN-style associations between diseases and phenotypic features, together with their
evidence, and age of onset and frequency (if known).
The parser currently only processes the "abnormal" annotations. Association to "remarkable normality"
will be added in the near future.
In order to properly test this class, you should have a conf.json file configured with some test ids, in
the structure of:
<pre>
test_ids: {
"disease" : ["OMIM:119600", "OMIM:120160"] # as examples. put your favorite ids in the config.
}
</pre>
"""
files = {
'annot': {'file' : 'phenotype_annotation.tab',
'url' : 'http://compbio.charite.de/hudson/job/hpo.annotations/lastStableBuild/artifact/misc/phenotype_annotation.tab'},
'version': {'file' : 'data_version.txt',
'url' : 'http://compbio.charite.de/hudson/job/hpo.annotations/lastStableBuild/artifact/misc/data_version.txt'},
# 'neg_annot': {'file' : 'phenotype_annotation.tab',
# 'url' : 'http://compbio.charite.de/hudson/job/hpo.annotations/lastStableBuild/artifact/misc/negative_phenotype_annotation.tab'
# },
}
# note, two of these codes are awaiting term requests. see #114 and
# https://code.google.com/p/evidenceontology/issues/detail?id=32
eco_dict = {
"ICE": "ECO:0000305", # FIXME currently using "curator inference used in manual assertion"
"IEA": "ECO:0000501", # Inferred from Electronic Annotation
"PCS": "ECO:0000269", # FIXME currently using "experimental evidence used in manual assertion"
"TAS": "ECO:0000304" # Traceable Author Statement
}
def __init__(self):
Source.__init__(self, 'hpoa')
self.load_bindings()
self.dataset = Dataset('hpoa', 'Human Phenotype Ontology',
'http://www.human-phenotype-ontology.org', None,
'http://www.human-phenotype-ontology.org/contao/index.php/legal-issues.html')
if 'test_ids' not in config.get_config() or 'disease' not in config.get_config()['test_ids']:
logger.warn("not configured with disease test ids.")
else:
self.test_ids = config.get_config()['test_ids']['disease']
# data-source specific warnings (will be removed when issues are cleared)
logger.warn("note that some ECO classes are missing for ICE and PCS; using temporary mappings.")
return
def fetch(self, is_dl_forced=False):
self.get_files(is_dl_forced)
self.scrub()
# get the latest build from jenkins
# NOT DOING THIS ANY MORE - but leaving it in for reference
# jenkins_info = eval(urllib.request.urlopen('http://compbio.charite.de/hudson/job/hpo.annotations/lastSuccessfulBuild/api/python').read())
# version = jenkins_info['number']
# use the files['version'] file as the version
fname = '/'.join((self.rawdir, self.files['version']['file']))
with open(fname, 'r', encoding="utf8") as f:
# 2015-04-23 13:01
v = f.readline() # read the first line (the only line, really)
d = datetime.strptime(v.strip(), '%Y-%m-%d %H:%M').strftime("%Y-%m-%d-%H-%M")
f.close()
st = os.stat(fname)
filedate = datetime.utcfromtimestamp(st[ST_CTIME]).strftime("%Y-%m-%d")
# this will cause two dates to be attached to the dataset (one from the filedate, and the other from here)
# TODO when #112 is implemented, this will result in only the whole dataset being versioned
self.dataset.setVersion(filedate, d)
return
def scrub(self):
"""
Perform various data-scrubbing on the raw data files prior to parsing.
For this resource, this currently includes:
* revise errors in identifiers for some OMIM and PMIDs
:return: None
"""
# scrub file of the oddities...lots of publication rewriting
f = '/'.join((self.rawdir, self.files['annot']['file']))
logger.info('scrubbing PubMed:12345 --> PMID:12345')
pysed.replace("PubMed", 'PMID', f)
logger.info('scrubbing pmid:12345 --> PMID:12345')
pysed.replace("pmid", 'PMID', f)
logger.info('scrubbing PMID12345 --> PMID:12345')
pysed.replace("PMID([0-9][0-9]*)", 'PMID:\\1', f)
logger.info('scrubbing MIM12345 --> OMIM:12345')
pysed.replace('MIM([0-9][0-9]*)', 'OMIM:\\1', f)
logger.info('scrubbing MIM:12345 --> OMIM:12345')
pysed.replace(";MIM", ";OMIM", f)
logger.info('scrubbing ORPHANET --> Orphanet')
pysed.replace("ORPHANET", "Orphanet", f)
return
# here we're reading and building a full named graph of this resource, then dumping it all at the end
# we can investigate doing this line-by-line later
# supply a limit if you want to test out parsing the head X lines of the file
def parse(self, limit=None):
if limit is not None:
logger.info("Only parsing first %s rows", limit)
logger.info("Parsing files...")
if self.testOnly:
self.testMode = True
self._process_phenotype_tab('/'.join((self.rawdir, self.files['annot']['file'])), limit)
# TODO add negative phenotype statements #113
# self._process_negative_phenotype_tab(self.rawfile,self.outfile,limit)
logger.info("Finished parsing.")
return
def _map_evidence_to_codes(self, code_string):
"""
A simple mapping of the code_string to it's ECO class using the dictionary defined here
Currently includes ICE, IEA, PCS, TAS
:param code_string:
:return:
"""
return self.eco_dict.get(code_string)
def _process_phenotype_tab(self, raw, limit):
if self.testMode:
g = self.testgraph
else:
g = self.graph
line_counter = 0
gu = GraphUtils(curie_map.get())
with open(raw, 'r', encoding="utf8") as csvfile:
filereader = csv.reader(csvfile, delimiter='\t', quotechar='\"')
for row in filereader:
line_counter += 1
(db, num, name, qual, pheno_id, publist, eco, onset, freq, w, asp, syn, date, curator) = row
disease_id = db + ":" + str(num)
if self.testMode and disease_id.strip() not in config.get_config()['test_ids']['disease']:
continue
# logger.info('adding %s', disease_id)
gu.addClassToGraph(g, disease_id, None)
gu.addClassToGraph(g, pheno_id, None)
eco_id = self._map_evidence_to_codes(eco)
gu.addClassToGraph(g, eco_id, None)
if onset is not None and onset.strip() != '':
gu.addClassToGraph(g, onset, None)
# we want to do things differently depending on the aspect of the annotation
if asp == 'O' or asp == 'M': # organ abnormality or mortality
assoc = D2PAssoc(self.name, disease_id, pheno_id, onset, freq)
elif asp == 'I': # inheritance patterns for the whole disease
assoc = DispositionAssoc(self.name, disease_id, pheno_id)
elif asp == 'C': # clinical course / onset
assoc = DispositionAssoc(self.name, disease_id, pheno_id)
else:
logger.error("I don't know what this aspect is:", asp)
assoc.add_evidence(eco_id)
publist = publist.split(';')
# blow these apart if there is a list of pubs
for pub in publist:
pub = pub.strip()
if pub != '':
# if re.match('http://www.ncbi.nlm.nih.gov/bookshelf/br\.fcgi\?book=gene', pub):
# #http://www.ncbi.nlm.nih.gov/bookshelf/br.fcgi?book=gene&part=ced
# m = re.search('part\=(\w+)', pub)
# pub_id = 'GeneReviews:'+m.group(1)
# elif re.search('http://www.orpha.net/consor/cgi-bin/OC_Exp\.php\?lng\=en\&Expert\=', pub):
# m = re.search('Expert=(\d+)', pub)
# pub_id = 'Orphanet:'+m.group(1)
if not re.match('http', pub):
r = Reference(pub)
if re.match('PMID', pub):
r.setType(Reference.ref_types['journal_article'])
r.addRefToGraph(g)
# TODO add curator
assoc.add_source(pub)
assoc.add_association_to_graph(g)
if not self.testMode and limit is not None and line_counter > limit:
break
Assoc(None).load_all_properties(g)
return
def getTestSuite(self):
import unittest
from tests.test_hpoa import HPOATestCase
# TODO add D2PAssoc tests
test_suite = unittest.TestLoader().loadTestsFromTestCase(HPOATestCase)
return test_suite
class MMRRC(Source):
"""
Here we process the Mutant Mouse Resource and Research Center
(https://www.mmrrc.org) strain data,
which includes:
* strains, their mutant alleles
* phenotypes of the alleles
* descriptions of the research uses of the strains
Note that some gene identifiers are not included
(for many of the transgenics with human genes) in the raw data.
We do our best to process the links between the variant and
the affected gene, but sometimes the mapping is not clear,
and we do not include it.
Many of these details will be solved by merging this source with
the MGI data source, who has the variant-to-gene designations.
Also note that even though the strain pages at the MMRRC site do list
phenotypic differences in the context of the strain backgrounds,
they do not provide that data to us,
and thus we cannot supply that disambiguation here.
"""
files = {
'catalog': {
'file': 'mmrrc_catalog_data.csv',
'url': 'https://www.mmrrc.org/about/mmrrc_catalog_data.csv'},
}
test_ids = [
'MMRRC:037507-MU', 'MMRRC:041175-UCD', 'MMRRC:036933-UNC',
'MMRRC:037884-UCD', 'MMRRC:000255-MU', 'MMRRC:037372-UCD',
'MMRRC:000001-UNC'
]
def __init__(self):
Source.__init__(self, 'mmrrc')
self.strain_hash = {}
self.id_label_hash = {}
self.load_bindings()
self.dataset = Dataset(
'mmrrc', 'Mutant Mouse Regional Resource Centers',
'https://www.mmrrc.org', None,
'https://www.mmrrc.org/about/data_download.php')
return
def fetch(self, is_dl_forced=False):
self.get_files(is_dl_forced)
fname = '/'.join((self.rawdir, self.files['catalog']['file']))
st = os.stat(fname)
filedate = datetime.utcfromtimestamp(st[ST_CTIME]).strftime("%Y-%m-%d")
# TODO note: can set the data version to what is in the header
# first line like:
# This MMRRC catalog data file was generated on 2015-04-22
self.dataset.setVersion(filedate)
return
def parse(self, limit=None):
if limit is not None:
logger.info("Only parsing first %s rows", limit)
logger.info("Parsing files...")
if self.testOnly:
self.testMode = True
self._process_phenotype_data(limit)
logger.info("Finished parsing.")
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
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
@staticmethod
def _get_variant_type_from_abbrev(abbrev):
"""
All variants are generically typed as "sequence_alterations"
unless otherwise stated.
:param abbrev:
:return:
"""
variant_type = None
var_dict = {
'SM': 'SO:0001059', # spontaneous mutation
'TM': 'SO:0001059', # targeted mutation
'TG': 'SO:xxxxxxx', # transgenic
'GT': 'SO:0001059', # gene trap
'CI': 'SO:0001059', # chemically induced mutation
'RAD': 'SO:0001059', # radiation induced mutation
# chromosomal aberration --> chromosomal structure variation
'CH': 'SO:1000183',
'RB': 'SO:1000043', # Robertsonian translocation
'TL': 'SO:1000048', # reciprocal translocation
'TP': 'SO:0000453', # transposition
'INV': 'SO:1000036', # inversion
'INS': 'SO:0000667', # insertion
'DEL': 'SO:0000159', # deletion
'DP': 'SO:1000035', # duplication
'OTH': 'SO:0001059' # other
}
if abbrev in var_dict:
variant_type = var_dict[abbrev]
else:
logger.warning("Variant type not recognized: %s", abbrev)
return variant_type
def getTestSuite(self):
import unittest
from tests.test_mmrrc import MMRRCTestCase
test_suite = unittest.TestLoader().loadTestsFromTestCase(MMRRCTestCase)
return test_suite
class BioGrid(Source):
"""
Biogrid interaction data
"""
# TODO write up class summary for docstring
files = {
"interactions": {
"file": "interactions.mitab.zip",
"url": "http://thebiogrid.org/downloads/archives/Latest%20Release/BIOGRID-ALL-LATEST.mitab.zip",
},
"identifiers": {
"file": "identifiers.tab.zip",
"url": "http://thebiogrid.org/downloads/archives/Latest%20Release/BIOGRID-IDENTIFIERS-LATEST.tab.zip",
},
}
# biogrid-specific identifiers for use in subsetting identifier mapping
biogrid_ids = [
106638,
107308,
107506,
107674,
107675,
108277,
108506,
108767,
108814,
108899,
110308,
110364,
110678,
111642,
112300,
112365,
112771,
112898,
199832,
203220,
247276,
120150,
120160,
124085,
]
def __init__(self, tax_ids=None):
super().__init__("biogrid")
self.tax_ids = tax_ids
self.load_bindings()
self.dataset = Dataset(
"biogrid",
"The BioGrid",
"http://thebiogrid.org/",
None,
"http://wiki.thebiogrid.org/doku.php/terms_and_conditions",
)
# Defaults
# taxids = [9606,10090,10116,7227,7955,6239,8355] #our favorite animals
if self.tax_ids is None:
self.tax_ids = [9606, 10090, 7955]
if "test_ids" not in config.get_config() or "gene" not in config.get_config()["test_ids"]:
logger.warn("not configured with gene test ids.")
else:
self.test_ids = config.get_config()["test_ids"]["gene"]
# data-source specific warnings (will be removed when issues are cleared)
logger.warn("several MI experimental codes do not exactly map to ECO; using approximations.")
return
def fetch(self, is_dl_forced=False):
"""
:param is_dl_forced:
:return: None
"""
self.get_files(is_dl_forced)
# the version number is encoded in the filename in the zip.
# for example, the interactions file may unzip to BIOGRID-ALL-3.2.119.mitab.txt,
# where the version number is 3.2.119
f = "/".join((self.rawdir, self.files["interactions"]["file"]))
st = os.stat(f)
filedate = datetime.utcfromtimestamp(st[ST_CTIME]).strftime("%Y-%m-%d")
with ZipFile(f, "r") as myzip:
flist = myzip.namelist()
# assume that the first entry is the item
fname = flist[0]
# get the version from the filename
version = re.match("BIOGRID-ALL-(\d+\.\d+\.\d+)\.mitab.txt", fname)
myzip.close()
self.dataset.setVersion(filedate, str(version.groups()[0]))
return
def parse(self, limit=None):
"""
:param limit:
:return:
"""
if self.testOnly:
self.testMode = True
self._get_interactions(limit)
self._get_identifiers(limit)
self.load_bindings()
logger.info("Loaded %d test graph nodes", len(self.testgraph))
logger.info("Loaded %d full graph nodes", len(self.graph))
return
def _get_interactions(self, limit):
logger.info("getting interactions")
line_counter = 0
f = "/".join((self.rawdir, self.files["interactions"]["file"]))
myzip = ZipFile(f, "r")
# assume that the first entry is the item
fname = myzip.namelist()[0]
matchcounter = 0
with myzip.open(fname, "r") as csvfile:
for line in csvfile:
# skip comment lines
if re.match("^#", line.decode()):
logger.debug("Skipping header line")
continue
line_counter += 1
line = line.decode().strip()
# print(line)
(
interactor_a,
interactor_b,
alt_ids_a,
alt_ids_b,
aliases_a,
aliases_b,
detection_method,
pub_author,
pub_id,
taxid_a,
taxid_b,
interaction_type,
source_db,
interaction_id,
confidence_val,
) = line.split("\t")
# get the actual gene ids, typically formated like: gene/locuslink:351|BIOGRID:106848
gene_a_num = re.search("locuslink\:(\d+)\|?", interactor_a).groups()[0]
gene_b_num = re.search("locuslink\:(\d+)\|?", interactor_b).groups()[0]
if self.testMode:
g = self.testgraph
# skip any genes that don't match our test set
if (int(gene_a_num) not in self.test_ids) or (int(gene_b_num) not in self.test_ids):
continue
else:
g = self.graph
# when not in test mode, filter by taxon
if (
int(re.sub("taxid:", "", taxid_a.rstrip())) not in self.tax_ids
or int(re.sub("taxid:", "", taxid_b.rstrip())) not in self.tax_ids
):
continue
else:
matchcounter += 1
gene_a = "NCBIGene:" + gene_a_num
gene_b = "NCBIGene:" + gene_b_num
# get the interaction type
# psi-mi:"MI:0407"(direct interaction)
int_type = re.search("MI:\d+", interaction_type).group()
rel = self._map_MI_to_RO(int_type)
# scrub pubmed-->PMID prefix
pub_id = re.sub("pubmed", "PMID", pub_id)
# remove bogus whitespace
pub_id = pub_id.strip()
# get the method, and convert to evidence code
det_code = re.search("MI:\d+", detection_method).group()
evidence = self._map_MI_to_ECO(det_code)
# note that the interaction_id is some kind of internal biogrid identifier that does not
# map to a public URI. we will construct a monarch identifier from this
assoc = InteractionAssoc(self.name, gene_a, gene_b, rel)
assoc.add_evidence(evidence)
assoc.add_source(pub_id)
assoc.add_association_to_graph(g)
assoc.load_all_properties(g)
if not self.testMode and (limit is not None and line_counter > limit):
break
myzip.close()
return
def _get_identifiers(self, limit):
"""
This will process the id mapping file provided by Biogrid.
The file has a very large header, which we scan past, then pull the identifiers, and make
equivalence axioms
:param limit:
:return:
"""
logger.info("getting identifier mapping")
line_counter = 0
f = "/".join((self.rawdir, self.files["identifiers"]["file"]))
myzip = ZipFile(f, "r")
# assume that the first entry is the item
fname = myzip.namelist()[0]
foundheader = False
gu = GraphUtils(curie_map.get())
# TODO align this species filter with the one above
# speciesfilters = 'H**o sapiens,Mus musculus,Drosophila melanogaster,Danio rerio,
# Caenorhabditis elegans,Xenopus laevis'.split(',')
speciesfilters = "H**o sapiens,Mus musculus".split(",")
with myzip.open(fname, "r") as csvfile:
for line in csvfile:
# skip header lines
if not foundheader:
if re.match("BIOGRID_ID", line.decode()):
foundheader = True
continue
line = line.decode().strip()
# BIOGRID_ID IDENTIFIER_VALUE IDENTIFIER_TYPE ORGANISM_OFFICIAL_NAME
# 1 814566 ENTREZ_GENE Arabidopsis thaliana
(biogrid_num, id_num, id_type, organism_label) = line.split("\t")
if self.testMode:
g = self.testgraph
# skip any genes that don't match our test set
if int(biogrid_num) not in self.biogrid_ids:
continue
else:
g = self.graph
# for each one of these, create the node and add equivalent classes
biogrid_id = "BIOGRID:" + biogrid_num
prefix = self._map_idtype_to_prefix(id_type)
# TODO make these filters available as commandline options
# geneidtypefilters='NCBIGene,OMIM,MGI,FlyBase,ZFIN,MGI,HGNC,WormBase,XenBase,ENSEMBL,miRBase'.split(',')
geneidtypefilters = "NCBIGene,MGI,ENSEMBL,ZFIN,HGNC".split(",")
# proteinidtypefilters='HPRD,Swiss-Prot,NCBIProtein'
if (speciesfilters is not None) and (organism_label.strip() in speciesfilters):
line_counter += 1
if (geneidtypefilters is not None) and (prefix in geneidtypefilters):
mapped_id = ":".join((prefix, id_num))
gu.addEquivalentClass(g, biogrid_id, mapped_id)
elif id_type == "OFFICIAL_SYMBOL": # this symbol will only get attached to the biogrid class
gu.addClassToGraph(g, biogrid_id, id_num)
# elif (id_type == 'SYNONYM'):
# gu.addSynonym(g,biogrid_id,id_num) #FIXME - i am not sure these are synonyms, altids?
if not self.testMode and limit is not None and line_counter > limit:
break
myzip.close()
return
@staticmethod
def _map_MI_to_RO(mi_id):
rel = InteractionAssoc.interaction_object_properties
mi_ro_map = {
"MI:0403": rel["colocalizes_with"], # colocalization
"MI:0407": rel["interacts_with"], # direct interaction
"MI:0794": rel["genetically_interacts_with"], # synthetic genetic interaction defined by inequality
"MI:0796": rel["genetically_interacts_with"], # suppressive genetic interaction defined by inequality
"MI:0799": rel["genetically_interacts_with"], # additive genetic interaction defined by inequality
"MI:0914": rel["interacts_with"], # association
"MI:0915": rel["interacts_with"], # physical association
}
ro_id = rel["interacts_with"] # default
if mi_id in mi_ro_map:
ro_id = mi_ro_map.get(mi_id)
return ro_id
@staticmethod
def _map_MI_to_ECO(mi_id):
eco_id = "ECO:0000006" # default to experimental evidence
mi_to_eco_map = {
"MI:0018": "ECO:0000068", # yeast two-hybrid
"MI:0004": "ECO:0000079", # affinity chromatography
"MI:0047": "ECO:0000076", # far western blotting
"MI:0055": "ECO:0000021", # should be FRET, but using physical_interaction FIXME
"MI:0090": "ECO:0000012", # desired: protein complementation, using: functional complementation
"MI:0096": "ECO:0000085", # desired: pull down, using: immunoprecipitation
"MI:0114": "ECO:0000324", # desired: x-ray crystallography, using: imaging assay
"MI:0254": "ECO:0000011", # desired: genetic interference, using: genetic interaction evidence
"MI:0401": "ECO:0000172", # desired: biochemical, using: biochemical trait evidence
"MI:0415": "ECO:0000005", # desired: enzymatic study, using: enzyme assay evidence
"MI:0428": "ECO:0000324", # imaging
"MI:0686": "ECO:0000006", # desired: unspecified, using: experimental evidence
"MI:1313": "ECO:0000006", # None?
}
if mi_id in mi_to_eco_map:
eco_id = mi_to_eco_map.get(mi_id)
else:
logger.warn("unmapped code %s. Defaulting to experimental_evidence", mi_id)
return eco_id
@staticmethod
def _map_idtype_to_prefix(idtype):
"""
Here we need to reformat the BioGrid source prefixes to standard ones used in our curie-map.
:param idtype:
:return:
"""
prefix = idtype
idtype_to_prefix_map = {
"XENBASE": "XenBase",
"TREMBL": "TrEMBL",
"MGI": "MGI",
"REFSEQ_DNA_ACCESSION": "RefSeqNA",
"MAIZEGDB": "MaizeGDB",
"BEEBASE": "BeeBase",
"ENSEMBL": "ENSEMBL",
"TAIR": "TAIR",
"GENBANK_DNA_GI": "NCBIgi",
"CGNC": "CGNC",
"RGD": "RGD",
"GENBANK_GENOMIC_DNA_GI": "NCBIgi",
"SWISSPROT": "Swiss-Prot",
"MIM": "OMIM",
"FLYBASE": "FlyBase",
"VEGA": "VEGA",
"ANIMALQTLDB": "AQTLDB",
"ENTREZ_GENE_ETG": "ETG",
"HPRD": "HPRD",
"APHIDBASE": "APHIDBASE",
"GENBANK_PROTEIN_ACCESSION": "NCBIProtein",
"ENTREZ_GENE": "NCBIGene",
"SGD": "SGD",
"GENBANK_GENOMIC_DNA_ACCESSION": "NCBIGenome",
"BGD": "BGD",
"WORMBASE": "WormBase",
"ZFIN": "ZFIN",
"DICTYBASE": "dictyBase",
"ECOGENE": "ECOGENE",
"BIOGRID": "BIOGRID",
"GENBANK_DNA_ACCESSION": "NCBILocus",
"VECTORBASE": "VectorBase",
"MIRBASE": "miRBase",
"IMGT/GENE-DB": "IGMT",
"HGNC": "HGNC",
"SYSTEMATIC_NAME": None,
"OFFICIAL_SYMBOL": None,
"REFSEQ_GENOMIC_DNA_ACCESSION": "NCBILocus",
"GENBANK_PROTEIN_GI": "NCBIgi",
"REFSEQ_PROTEIN_ACCESSION": "RefSeqProt",
"SYNONYM": None,
"GRID_LEGACY": None,
# the following showed up in 3.3.124
"UNIPROT-ACCESSION": "UniprotKB",
"SWISS-PROT": "Swiss-Prot",
"OFFICIAL SYMBOL": None,
"ENSEMBL RNA": None,
"GRID LEGACY": None,
"ENSEMBL PROTEIN": None,
"REFSEQ-RNA-GI": None,
"REFSEQ-RNA-ACCESSION": None,
"REFSEQ-PROTEIN-GI": None,
"REFSEQ-PROTEIN-ACCESSION-VERSIONED": None,
"REFSEQ-PROTEIN-ACCESSION": None,
"REFSEQ-LEGACY": None,
"SYSTEMATIC NAME": None,
"ORDERED LOCUS": None,
"UNIPROT-ISOFORM": "UniprotKB",
"ENSEMBL GENE": "ENSEMBL",
"CGD": None, # Not sure what this is?
"WORMBASE-OLD": "WormBase",
}
if idtype in idtype_to_prefix_map:
prefix = idtype_to_prefix_map.get(idtype)
else:
logger.warn("unmapped prefix %s", prefix)
return prefix
def getTestSuite(self):
import unittest
from tests.test_biogrid import BioGridTestCase
# TODO add InteractionAssoc tests
# TODO add test about if all prefixes are mapped?
test_suite = unittest.TestLoader().loadTestsFromTestCase(BioGridTestCase)
return test_suite
