def test_quote(self):
a = "word1 word2"
self.assertEqual('"word1 word2"', ensure_quotes(a))
b = "word1"
self.assertEqual('word1', ensure_quotes(b))
c = "word1$#"
self.assertEqual('"word1$#"', ensure_quotes(c))
def test_str_has_both(self):
namespace, identifier = n(), n()
node = abundance(namespace=namespace, identifier=identifier)
self.assertEqual(
'a({namespace}:{identifier})'.format(
namespace=namespace, identifier=ensure_quotes(identifier)),
node.as_bel())
def test_str_has_name(self):
namespace, name = n(), n()
node = abundance(namespace=namespace, name=name)
self.assertEqual(
'a({namespace}:{name})'.format(namespace=namespace,
name=ensure_quotes(name)),
node.as_bel())
def _write_hierarchy_body(self, file=None):
print('SET Citation = {{"{}","{}"}}'.format(CITATION_TYPE_URL,
self.version_iri),
file=file)
print('SET Evidence = "Automatically generated hierarchy from {}"\n'.
format(self.version_iri),
file=file)
for parent, child in self._get_hierarchy():
print(
'{fn}({keyword}:{child}) {relation} {fn}({keyword}:{parent})'.
format(fn=self.bel_function,
keyword=self.preferred_prefix,
relation=IS_A,
parent=ensure_quotes(parent),
child=ensure_quotes(child)),
file=file)
def write_hgnc_gene_families(file, df=None):
"""Writes the HGNC gene family hierarchy a BEL script.
:param file file: A writable file or file-like
:param pandas.DataFrame df: A data frame containing the original data source
"""
df = get_data() if df is None else df
write_boilerplate(
document_name='HGNC Gene Family Definitions',
authors='Charles Tapley Hoyt',
contact='*****@*****.**',
licenses='Creative Commons by 4.0',
copyright=
'Copyright (c) 2017 Charles Tapley Hoyt. All Rights Reserved.',
description=
"""This BEL document represents the gene families curated by HGNC, describing various functional, structural, and logical classifications""",
namespace_dict={
'HGNC': HGNC_HUMAN_GENES,
'GFAM': HGNC_GENE_FAMILIES,
},
namespace_patterns={},
annotations_dict={'Confidence': CONFIDENCE},
annotations_patterns={},
file=file)
print('SET Citation = {"PubMed","HGNC","25361968"}', file=file)
print('SET Evidence = "HGNC Definitions"', file=file)
print('SET Confidence = "Axiomatic"', file=file)
for _, gfam, gene in df[['Gene family description',
'Approved Symbol']].itertuples():
gfam_clean = ensure_quotes(gfam.strip())
gene_clean = ensure_quotes(gene.strip())
print('g(HGNC:{}) {} g(GFAM:{})'.format(gene_clean, IS_A, gfam_clean),
file=file)
def write_bel_association(abundance1,
namespace1,
accession1,
abundance2,
namespace2,
accession2,
file=None):
"""Prints a BEL association.
:param str abundance1: Abundance of the subject
:param str namespace1: Namespace of the subject
:param str accession1: Identifier of the subject
:param str abundance2: Abundance of the object
:param str namespace2: Namespace of the object
:param str accession2: Identifier of the object
:param file file: A writeable file or file like. Defaults to stdout
"""
print('{}({}:{}) -- {}({}:{})'.format(ensure_quotes(abundance1),
ensure_quotes(namespace1),
ensure_quotes(accession1),
ensure_quotes(abundance2),
ensure_quotes(namespace2),
ensure_quotes(accession2)),
file=file)
def get_neurommsig_bel(
df: pd.DataFrame,
disease: str,
nift_values: Mapping[str, str],
) -> BELGraph:
"""Generate the NeuroMMSig BEL graph.
:param df:
:param disease:
:param nift_values: a dictionary of lower-cased to normal names in NIFT
"""
missing_features = set()
fixed_caps = set()
nift_value_originals = set(nift_values.values())
graph = BELGraph(
name=f'NeuroMMSigDB for {disease}',
description=f'SNP and Clinical Features for Subgraphs in {disease}',
authors=
'Daniel Domingo-Fernández, Charles Tapley Hoyt, Mufassra Naz, Aybuge Altay, Anandhi Iyappan',
contact='*****@*****.**',
version=time.strftime('%Y%m%d'),
)
for pathway, pathway_df in df.groupby(PATHWAY_COLUMN_NAME):
sorted_pathway_df = pathway_df.sort_values(GENE_COLUMN_NAME)
sliced_df = sorted_pathway_df[columns].itertuples()
for _, gene, pubmeds, lit_snps, gwas_snps, ld_block_snps, clinical_features, clinical_snps in sliced_df:
gene = ensure_quotes(gene)
for snp in itt.chain(lit_snps or [], gwas_snps or [], ld_block_snps
or [], clinical_snps or []):
if not snp.strip():
continue
graph.add_association(
Gene('HGNC', gene),
Gene('DBSNP', snp),
evidence=CANNED_EVIDENCE,
citation=CANNED_CITATION,
annotations={
'MeSHDisease': disease,
},
)
for clinical_feature in clinical_features or []:
if not clinical_feature.strip():
continue
if clinical_feature.lower() not in nift_values:
missing_features.add(clinical_feature)
continue
if clinical_feature not in nift_value_originals:
fixed_caps.add((clinical_feature,
nift_values[clinical_feature.lower()]))
clinical_feature = nift_values[
clinical_feature.lower()] # fix capitalization
graph.add_association(
Gene('HGNC', gene),
Abundance('NIFT', clinical_feature),
evidence=CANNED_EVIDENCE,
citation=CANNED_CITATION,
annotations={
'MeSHDisease': disease,
},
)
if clinical_snps:
for clinical_snp in clinical_snps:
graph.add_association(
Gene('DBSNP', clinical_snp),
Abundance('NIFT', clinical_feature),
evidence=CANNED_EVIDENCE,
citation=CANNED_CITATION,
annotations={
'MeSHDisease': disease,
},
)
if missing_features:
logger.warning('Missing Features in %s', disease)
for feature in missing_features:
logger.warning(feature)
if fixed_caps:
logger.warning('Fixed capitalization')
for broken, fixed in fixed_caps:
logger.warning('%s -> %s', broken, fixed)
return graph
def write_neurommsig_bel(file, df, disease, nift_values):
"""Writes the NeuroMMSigDB excel sheet to BEL
:param file: a file or file-like that can be writen to
:param pandas.DataFrame df:
:param str disease:
:param dict nift_values: a dictionary of lowercased to normal names in NIFT
"""
write_boilerplate(
document_name='NeuroMMSigDB for {}'.format(disease),
description='SNP and Clinical Features for Subgraphs in {}'.format(disease),
authors='Daniel Domingo, Charles Tapley Hoyt, Mufassra Naz, Aybuge Altay, Anandhi Iyappan',
contact='*****@*****.**',
namespace_dict={
'NIFT': NIFT_URL,
'HGNC': FRAUNHOFER_RESOURCES + 'hgnc-human-genes.belns',
},
namespace_patterns={
'dbSNP': DBSNP_PATTERN
},
annotations_dict={
'Subgraph': FRAUNHOFER_RESOURCES + 'subgraph.belanno',
'MeSHDisease': FRAUNHOFER_RESOURCES + 'mesh-diseases.belanno'
},
file=file
)
print('SET Citation = {"Other", "NeuroMMSigDB", "http://neurommsig.scai.fraunhofer.de/"}', file=file)
print('SET Evidence = "Serialized from NeuroMMSigDB"', file=file)
print('SET MeSHDisease = "{}"\n'.format(disease), file=file)
missing_features = set()
fixed_caps = set()
nift_value_originals = set(nift_values.values())
for pathway, pathway_df in df.groupby(pathway_column):
print('SET Subgraph = "{}"'.format(pathway), file=file)
for _, gene, lit_snps, gwas_snps, clinical_features, clinical_snp in pathway_df[columns].itertuples():
gene = ensure_quotes(gene)
if lit_snps is None:
lit_snps = []
if gwas_snps is None:
gwas_snps = []
if clinical_snp is None:
clinical_snp = []
for snp in itt.chain(lit_snps, gwas_snps, clinical_snp):
if not snp.strip():
continue
print('g(HGNC:{}) -- g(dbSNP:{})'.format(gene, snp), file=file)
for clinical_feature in clinical_features or []:
if not clinical_feature.strip():
continue
if clinical_feature.lower() not in nift_values:
missing_features.add(clinical_feature)
continue
if clinical_feature not in nift_value_originals:
fixed_caps.add((clinical_feature, nift_values[clinical_feature.lower()]))
clinical_feature = nift_values[clinical_feature.lower()] # fix capitalization
print('g(HGNC:{}) -- a(NIFT:{})'.format(gene, ensure_quotes(clinical_feature)), file=file)
print('UNSET Subgraph\n', file=file)
print('UNSET MeSHDisease', file=file)
print('UNSET Evidence', file=file)
print('UNSET Citation', file=file)
log.warning('Missing Features in %s', disease)
for feature in missing_features:
log.warning(feature)
log.warning('Fixed capitalization')
for broken, fixed in fixed_caps:
log.warning('%s -> %s', broken, fixed)
def write_neurommsig_bel(file, df, disease, nift_values):
"""Writes the NeuroMMSigDB excel sheet to BEL
:param file: a file or file-like that can be writen to
:param pandas.DataFrame df:
:param str disease:
:param dict nift_values: a dictionary of lowercased to normal names in NIFT
"""
write_neurommsig_biolerplate(disease, file)
missing_features = set()
fixed_caps = set()
nift_value_originals = set(nift_values.values())
for pathway, pathway_df in df.groupby(pathway_column):
print('SET Subgraph = "{}"'.format(pathway), file=file)
sorted_pathway_df = pathway_df.sort_values(genes_column)
sliced_df = sorted_pathway_df[columns].itertuples()
for _, gene, pubmeds, lit_snps, gwas_snps, ld_block_snps, clinical_features, clinical_snps in sliced_df:
gene = ensure_quotes(gene)
for snp in itt.chain(lit_snps or [], gwas_snps or [], ld_block_snps or [], clinical_snps or []):
if not snp.strip():
continue
print('g(HGNC:{}) -- g(dbSNP:{})'.format(gene, snp), file=file)
for clinical_feature in clinical_features or []:
if not clinical_feature.strip():
continue
if clinical_feature.lower() not in nift_values:
missing_features.add(clinical_feature)
continue
if clinical_feature not in nift_value_originals:
fixed_caps.add((clinical_feature, nift_values[clinical_feature.lower()]))
clinical_feature = nift_values[clinical_feature.lower()] # fix capitalization
print('g(HGNC:{}) -- a(NIFT:{})'.format(gene, ensure_quotes(clinical_feature)), file=file)
if clinical_snps:
for clinical_snp in clinical_snps:
print('g(dbSNP:{} -- a(NIFT:{})'.format(clinical_snp, ensure_quotes(clinical_feature)),
file=file)
print('UNSET Subgraph\n', file=file)
print('UNSET MeSHDisease', file=file)
print('UNSET Evidence', file=file)
print('UNSET Citation', file=file)
if missing_features:
log.warning('Missing Features in %s', disease)
for feature in missing_features:
log.warning(feature)
if fixed_caps:
log.warning('Fixed capitalization')
for broken, fixed in fixed_caps:
log.warning('%s -> %s', broken, fixed)