def should_include(self, lookup: str, compound: ChemblCompound,
data: NestedDotDict, target: Target) -> bool:
bad_flags = {
"potential missing data",
"potential transcription error",
"outside typical range",
}
if (data.get_as("data_validity_comment",
lambda s: s.lower()) in bad_flags or data.req_as(
"standard_relation", str) not in ["=", "<", "<="]
or data.req_as("assay_type", str) != "B"
or data.get("target_tax_id") is None
or data.get_as("target_tax_id", int) not in self.tax
or data.get("pchembl_value") is None or
data.req_as("pchembl_value", float) < self.config.min_pchembl):
return False
if data.get("data_validity_comment") is not None:
logger.warning(
f"Activity annotation for {lookup} has flag '{data.get('data_validity_comment')} (ok)"
)
# The `target_organism` doesn't always match the `assay_organism`
# Ex: see assay CHEMBL823141 / document CHEMBL1135642 for h**o sapiens in xenopus laevis
# However, it's often something like yeast expressing a human / mouse / etc receptor
# So there's no need to filter by it
assay = self.api.assay.get(data.req_as("assay_chembl_id", str))
confidence_score = assay.get("confidence_score")
if confidence_score is None or confidence_score < self.config.min_confidence_score:
return False
if target.type.is_trash or target.type.is_strange and self.config.min_confidence_score > 3:
logger.warning(f"Excluding {target} with type {target.type}")
return False
return True
def process(self, lookup: str, compound: ChemblCompound,
indication: NestedDotDict) -> IndicationHit:
"""
Args:
lookup:
compound:
indication:
Returns:
"""
return IndicationHit(
indication.req_as("drugind_id", str),
compound.chid,
compound.inchikey,
lookup,
compound.name,
object_id=indication.req_as("mesh_id", str),
object_name=indication.req_as("mesh_heading", str).strip("\n"),
max_phase=indication.req_as("max_phase_for_ind", int),
)
def _extract(self, lookup: str, compound: ChemblCompound,
data: NestedDotDict) -> NestedDotDict:
# we know these exist from the query
organism = data.req_as("target_organism", str)
tax_id = data.req_as("target_tax_id", int)
tax = self.tax.req(tax_id)
if organism != tax.name:
logger.warning(f"Target organism {organism} is not {tax.name}")
return NestedDotDict(
dict(
record_id=data.req_as("activity_id", str),
compound_id=compound.chid,
inchikey=compound.inchikey,
compound_name=compound.name,
compound_lookup=lookup,
taxon_id=tax.id,
taxon_name=tax.name,
pchembl=data.req_as("pchembl_value", float),
std_type=data.req_as("standard_type", str),
src_id=data.req_as("src_id", str),
exact_target_id=data.req_as("target_chembl_id", str),
))