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 load(cls, data: NestedDotDict) -> Settings:
# 117571
if IN_CLI:
cache_path = (
Path(__file__).parent.parent.parent / "tests" / "resources" / ".mandos-cache"
)
else:
cache_path = Path.home() / ".mandos" / "chembl"
return Settings(
data.get_as("is_testing", bool, False),
data.get_as("mandos.taxon", int, 7742),
data.get_as("mandos.min_pchembl", float, 6.0),
data.get_as("mandos.min_confidence_score", int, 4),
data.get_as("mandos.min_phase", int, 3),
data.get_as("chembl.cache_path", Path, cache_path),
data.get_as("chembl.n_retries", int, 1),
data.get_as("chembl.fast_save", bool, True),
data.get_as("chembl.timeout_sec", int, 1),
)