def get_raw_references(datapath, phenotype_set):
"""Parse a phenotype file and collect descriptions and raw phenotypes
raw phenotypes are phenotypes in the original ontology
Args:
datapath path to phenotab file
phenotype_set set of acceptable phenotypes
Returns:
two objects
- dict mapping reference codes to reference descriptions and phenotypes
- set of phenotypes that could not be mapped
"""
badphenotypes = set()
references = dict()
with open_file(datapath, "rt") as f:
reader = csv.DictReader(f, delimiter="\t", quotechar="\"")
for row in reader:
if not valid_reference_id(row["Reference"]):
continue
phenotype = row["Phenotype"]
if phenotype not in phenotype_set:
badphenotypes.add(phenotype)
continue
rowval = tofreq[row["Frequency"]]
id = row["Source"] + ":" + row["Disease_number"]
if id not in references:
references[id] = Representation(name=id)
references[id].title = row["Disease_title"]
references[id].set(phenotype, rowval)
return references, badphenotypes
def make_target_reference(reference, oomap, oo_median=None):
"""convert a single representation from one ontology to another."""
result = Representation(name=reference.name)
result.title = reference.title
for phenotype, value in reference.data.items():
for oo_phenotype, oo_score in oomap[phenotype]:
# perhaps compute a rescaled oo value
newvalue = value
if oo_median is not None:
newvalue = value * tanh(oo_score / oo_median)
# always take the larger value if previously set
if result.has(oo_phenotype):
newvalue = max(newvalue, result.get(oo_phenotype))
result.set(oo_phenotype, newvalue)
return result
