def _check_agent_mod(self, agent, mods, do_methionine_offset=True,
do_orthology_mapping=True,
do_isoform_mapping=True):
"""Check an agent for invalid sites and look for mappings.
Look up each modification site on the agent in Uniprot and then the
site map.
Parameters
----------
agent : :py:class:`indra.statements.Agent`
Agent to check for invalid modification sites.
mods : list of :py:class:`indra.statements.ModCondition`
Modifications to check for validity and map.
do_methionine_offset : boolean
Whether to check for off-by-one errors in site position (possibly)
attributable to site numbering from mature proteins after
cleavage of the initial methionine. If True, checks the reference
sequence for a known modification at 1 site position greater
than the given one; if there exists such a site, creates the
mapping. Default is True.
do_orthology_mapping : boolean
Whether to check sequence positions for known modification sites
in mouse or rat sequences (based on PhosphoSitePlus data). If a
mouse/rat site is found that is linked to a site in the human
reference sequence, a mapping is created. Default is True.
do_isoform_mapping : boolean
Whether to check sequence positions for known modifications
in other human isoforms of the protein (based on PhosphoSitePlus
data). If a site is found that is linked to a site in the human
reference sequence, a mapping is created. Default is True.
Returns
-------
list
A list of invalid sites, where each entry in the list has two
elements: ((gene_name, residue, position), mapped_site). If the
invalid position was not found in the site map, mapped_site is
None; otherwise it is a tuple consisting of (residue, position,
comment).
"""
invalid_sites = []
up_id = _get_uniprot_id(agent)
# If the uniprot entry is not found, let it pass
if not up_id:
logger.debug("No uniprot ID for %s" % agent.name)
return [] # Same effect as valid sites
# Look up all of the modifications in uniprot, and add them to the list
# of invalid sites if they are missing
for old_mod in mods:
# If no site information for this residue, skip
if old_mod.position is None or old_mod.residue is None:
continue
site_key = (agent.name, old_mod.residue, old_mod.position)
# Increase our count for this site
self._sitecount[site_key] = self._sitecount.get(site_key, 0) + 1
# First, check the cache to potentially avoid a costly sequence
# lookup
cached_site = self._cache.get(site_key)
if cached_site is not None:
if cached_site == 'VALID':
pass
else:
invalid_sites.append((site_key, cached_site))
continue
# If not cached, continue
# Look up the residue/position in uniprot
site_valid = uniprot_client.verify_location(up_id,
old_mod.residue,
old_mod.position)
# If it's not found in Uniprot, then look it up in the site map
if site_valid:
self._cache[site_key] = 'VALID'
continue
# Check the agent for a Uniprot ID
up_id = agent.db_refs.get('UP')
hgnc_id = agent.db_refs.get('HGNC')
if not hgnc_id:
logger.debug("No HGNC ID for %s, only curated sites will be "
"mapped" % agent.name)
# NOTE: The following lookups can only be performed if the
# Phosphosite Data is available.
if phosphosite_client.has_data():
# First, look for other entries in phosphosite for this protein
# where this sequence position is legit (i.e., other isoforms)
if do_isoform_mapping and up_id and hgnc_id:
human_pos = phosphosite_client.map_to_human_site(
up_id, old_mod.residue, old_mod.position)
if human_pos:
mapped_site = (old_mod.residue, human_pos,
'INFERRED_ALTERNATIVE_ISOFORM')
self._cache[site_key] = mapped_site
invalid_sites.append((site_key, mapped_site))
continue
# Try looking for rat or mouse sites
if do_orthology_mapping and up_id and hgnc_id:
# Get the mouse ID for this protein
up_mouse = uniprot_client.get_mouse_id(up_id)
# Get mouse sequence
human_pos = phosphosite_client.map_to_human_site(
up_mouse, old_mod.residue, old_mod.position)
if human_pos:
mapped_site = (old_mod.residue, human_pos,
'INFERRED_MOUSE_SITE')
self._cache[site_key] = mapped_site
invalid_sites.append((site_key, mapped_site))
continue
# Try the rat sequence
up_rat = uniprot_client.get_rat_id(up_id)
human_pos = phosphosite_client.map_to_human_site(
up_rat, old_mod.residue, old_mod.position)
if human_pos:
mapped_site = (old_mod.residue, human_pos,
'INFERRED_RAT_SITE')
self._cache[site_key] = mapped_site
invalid_sites.append((site_key, mapped_site))
continue
# Check for methionine offset (off by one)
if do_methionine_offset and up_id and hgnc_id:
try:
offset_pos = str(int(old_mod.position) + 1)
except ValueError:
logger.warning("Invalid position: %s" %
old_mod.position)
continue
human_pos = phosphosite_client.map_to_human_site(
up_id, old_mod.residue, offset_pos)
# If it's valid at the offset position, create the mapping
# and continue
if human_pos:
mapped_site = (old_mod.residue, human_pos,
'INFERRED_METHIONINE_CLEAVAGE')
self._cache[site_key] = mapped_site
invalid_sites.append((site_key, mapped_site))
continue
# Now check the site map
mapped_site = self.site_map.get(site_key, None)
if mapped_site is None:
# No entry in the site map--set site info to None
self._cache[site_key] = None
invalid_sites.append((site_key, None))
# Manually mapped in the site map
else:
self._cache[site_key] = mapped_site
invalid_sites.append((site_key, mapped_site))
return invalid_sites
def test_rat_from_human():
assert uniprot_client.get_rat_id('P04049') == 'P11345'
def test_rat_from_human():
assert uniprot_client.get_rat_id('P04049') == 'P11345'