Merge pull request #245 from monarch-initiative/ielis/issue236

Allow using `Sex` and disease diagnosis as a genotype predicate

docs/user-guide/predicates.rst

@@ -399,6 +399,45 @@ for testing if the individual has at least one missense vs. frameshift vs. synon
 'Genotype group: Missense, Frameshift, Synonymous'
 
 
+.. _sex-predicate:
+
+Partition by the sex of the individual
+======================================
+
+It is easy to investigate the phenotypic differences between females and males.
+The :func:`~gpsea.analysis.predicate.genotype.sex_predicate` provides a predicate
+for partitioning based on the sex of the individual:
+
+>>> from gpsea.analysis.predicate.genotype import sex_predicate
+>>> gt_predicate = sex_predicate()
+>>> gt_predicate.display_question()
+'Sex of the individual: FEMALE, MALE'
+
+The individuals with :class:`~gpsea.model.Sex.UNKNOWN_SEX` will be omitted from the analysis.
+
+
+.. _diagnosis-predicate:
+
+Partition by a diagnosis
+========================
+
+It is also possible to bin the individuals based on a diagnosis.
+The :func:`~gpsea.analysis.predicate.genotype.diagnosis_predicate` 
+prepares a genotype predicate for assigning an individual into a diagnosis group:
+
+>>> from gpsea.analysis.predicate.genotype import diagnosis_predicate
+>>> gt_predicate = diagnosis_predicate(
+...     diagnoses=('OMIM:154700', 'OMIM:129600'),
+...     labels=('Marfan syndrome', 'Ectopia lentis, familial'),
+... )
+>>> gt_predicate.display_question()
+'What disease was diagnosed: OMIM:154700, OMIM:129600'
+
+Note, an individual must match only one diagnosis group. Any individuals labeled with two or more diagnoses
+(e.g. an individual with both *Marfan syndrome* and *Ectopia lentis, familial*)
+will be automatically omitted from the analysis.
+
+
 .. _phenotype-predicates:
 
 ********************

src/gpsea/analysis/predicate/genotype/__init__.py

@@ -1,13 +1,13 @@
 from ._api import GenotypePolyPredicate
 from ._api import VariantPredicate
 from ._counter import AlleleCounter
-from ._gt_predicates import boolean_predicate, groups_predicate, filtering_predicate
+from ._gt_predicates import boolean_predicate, groups_predicate, filtering_predicate, sex_predicate, diagnosis_predicate
 from ._gt_predicates import ModeOfInheritancePredicate
 from ._variant import VariantPredicates, ProteinPredicates
 
 __all__ = [
     'GenotypePolyPredicate',
-    'boolean_predicate', 'groups_predicate', 'filtering_predicate',
+    'boolean_predicate', 'groups_predicate', 'filtering_predicate', 'sex_predicate', 'diagnosis_predicate',
     'ModeOfInheritancePredicate',
     'AlleleCounter', 'VariantPredicate',
     'VariantPredicates', 'ProteinPredicates',