def update_pubchem_mesh_map():
url = 'https://ftp.ncbi.nlm.nih.gov/pubchem/Compound/Extras/CID-MeSH'
res = requests.get(url)
# We first get mapping pairs from the table
mappings = []
for line in res.text.split('\n'):
parts = line.split('\t')
for part in parts[1:]:
mappings.append((parts[0], part))
# The table has (1) rows with multiple MeSH terms separated by tabs,
# (2) multiple rows with the same PubChem CID and (3) multiple rows
# with the same MeSH term. We retain only one-to-one mappings here.
pc_count = Counter([m[0] for m in mappings])
mesh_count = Counter([m[1] for m in mappings])
unique_mappings = [m for m in mappings if pc_count[m[0]] == 1
and mesh_count[m[1]] == 1]
# The mappings table is given using MeSH term names so we need
# to convert these to IDs. Lookups can fail for several reasons:
# some entries are simply not valid MeSH names, others are not
# yet included in the INDRA MeSH resources/ontology.
unique_with_id = []
for pcid, meshname in unique_mappings:
mesh_ns_id_tuple = bio_ontology.get_id_from_name('MESH', meshname)
if mesh_ns_id_tuple:
unique_with_id.append((pcid, mesh_ns_id_tuple[1]))
fname = os.path.join(path, 'pubchem_mesh_map.tsv')
logger.info('Saving into %s' % fname)
write_unicode_csv(fname, unique_with_id, delimiter='\t')
def get_ligands():
# Read and extract cell surface proteins from CSPA DB
wb = openpyxl.load_workbook(SURFACE_PROTEINS_WB)
surface_protein_set = set(row[4].value for row in wb['Sheet 1']
if row[6].value == 'yes')
updated_surface_protein_set = {
hgnc_client.get_hgnc_name(hgnc_client.get_current_hgnc_id(g))
for g in surface_protein_set
} - {None}
logger.info('Got %d surface proteins from spreadsheet' %
len(surface_protein_set))
ligand_terms = [
'cytokine activity', 'hormone activity', 'growth factor activity',
'extracellular matrix structural constituent'
]
# Getting GO id's for ligands and receptors by using
# GO terms
ligand_go_ids = [
bio_ontology.get_id_from_name('GO', term)[1] for term in ligand_terms
]
ligand_go_ids = expand_with_child_go_terms(ligand_go_ids)
# Converting GO id's to gene symbols
ligand_genes_go = get_genes_for_go_ids(ligand_go_ids)
manual_ligands = set()
ligand_genes_go = updated_surface_protein_set | ligand_genes_go | manual_ligands | get_cpdb_ligands(
)
ligand_genes_go = {
hgnc_client.get_hgnc_name(hgnc_client.get_current_hgnc_id(g))
for g in ligand_genes_go
} - {None}
ligand_genes_go = ligand_genes_go - (get_cpdb_receptors()
| get_ion_channels())
return ligand_genes_go
def get_receptors():
receptor_terms = ['signaling receptor activity']
receptor_go_ids = [
bio_ontology.get_id_from_name('GO', term)[1] for term in receptor_terms
]
receptor_go_ids = expand_with_child_go_terms(receptor_go_ids)
# Filtering out the nuclear receptors from the receptor list
receptor_go_ids = {r for r in receptor_go_ids if 'receptor' in
bio_ontology.get_name('GO', r)} - \
expand_with_child_go_terms(['GO:0004879'])
receptor_genes_go = get_genes_for_go_ids(receptor_go_ids)
receptor_genes_go -= {'NR2C2', 'EGF'}
# Add ION channels to the receptor list
ion_channels = set()
with open(ION_CHANNELS, 'r') as fh:
for line in fh:
ion_channels.add(line.strip())
receptor_genes_go |= ion_channels
return receptor_genes_go
def get_go_receptors():
receptor_terms = ['signaling receptor activity']
receptor_go_ids = [
bio_ontology.get_id_from_name('GO', term)[1] for term in receptor_terms
]
receptor_go_ids = expand_with_child_go_terms(receptor_go_ids)
# Filtering out the nuclear receptors from the receptor list
receptor_go_ids = {
r
for r in receptor_go_ids
if 'receptor' in bio_ontology.get_name('GO', r)
or 'sensor' in bio_ontology.get_name('GO', r)
or 'channel' in bio_ontology.get_name('GO', r)
}
nuclear_receptor_go_ids = expand_with_child_go_terms(['GO:0004879'])
receptor_genes_go = get_genes_for_go_ids(receptor_go_ids) - \
get_genes_for_go_ids(nuclear_receptor_go_ids)
receptor_genes_go -= {'NR2C2', 'EGF'}
return receptor_genes_go
def get_ligands():
# Read and extract cell surface proteins from CSPA DB
wb = openpyxl.load_workbook(SURFACE_PROTEINS_WB)
surface_protein_set = set(row[4].value for row in wb['Sheet 1']
if row[6].value == 'yes')
logger.info('Got %d surface proteins from spreadsheet' %
len(surface_protein_set))
ligand_terms = [
'cytokine activity', 'hormone activity', 'growth factor activity',
'extracellular matrix structural constituent'
]
# Getting GO id's for ligands and receptors by using
# GO terms
ligand_go_ids = [
bio_ontology.get_id_from_name('GO', term)[1] for term in ligand_terms
]
ligand_go_ids = expand_with_child_go_terms(ligand_go_ids)
# Converting GO id's to gene symbols
ligand_genes_go = get_genes_for_go_ids(ligand_go_ids)
# Remove one more nuclear receptor
#manual_ligands = {'THBS1'}
manual_ligands = set()
return surface_protein_set | ligand_genes_go | manual_ligands
def test_name_lookup_obsolete():
# This is a regression test to make sure we don't return another node
# with the same name but which is obsolete (HGNC:11093)
assert bio_ontology.get_id_from_name('HGNC', 'ALDH3A2') == \
('HGNC', '403')
def get_identifier(namespace: str, name: str) -> str:
_, identifier = bio_ontology.get_id_from_name(namespace, name)
return identifier
# Read and extract cell surface proteins from CSPA DB
wb = openpyxl.load_workbook(SURFACE_PROTEINS_WB)
surface_protein_set = set(row[4].value for row in wb['Sheet 1']
if row[6].value == 'yes')
logger.info('Got %d surface proteins from spreadsheet' %
len(surface_protein_set))
ligand_terms = [
'cytokine activity', 'hormone activity', 'growth factor activity'
]
receptor_terms = ['signaling receptor activity']
# Getting GO id's for ligands and receptors by using
# GO terms
ligand_go_ids = [
bio_ontology.get_id_from_name('GO', term)[1] for term in ligand_terms
]
receptor_go_ids = [
bio_ontology.get_id_from_name('GO', term)[1] for term in receptor_terms
]
# Converting GO id's to gene symbols
ligand_genes_go = get_genes_for_go_ids(ligand_go_ids, GOA)
receptor_genes_go = get_genes_for_go_ids(receptor_go_ids, GOA)
manual_ligands = {'THBS1'}
# remove all the receptors from the surface_protein_set
full_ligand_set = \
(surface_protein_set - receptor_genes_go) | ligand_genes_go | \
manual_ligands