Merge pull request #264 from monarch-initiative/improve-moi-handling

Improve mode of inheritance handling
monarch-initiative · Sep 11, 2024 · 84d8a90 · 84d8a90
2 parents 44cab77 + b0b157c
commit 84d8a90
Show file tree

Hide file tree

Showing 14 changed files with 364 additions and 623 deletions.
diff --git a/docs/report/tbx5_frameshift_vs_missense.csv b/docs/report/tbx5_frameshift_vs_missense.csv
@@ -1,4 +1,4 @@
-Genotype group,Missense,Missense,Frameshift,Frameshift,,
+Allele group,Missense,Missense,Frameshift,Frameshift,,
 ,Count,Percent,Count,Percent,Corrected p values,p values
 Ventricular septal defect [HP:0001629],31/60,52%,19/19,100%,0.0008990549794102921,5.6190936213143254e-05
 Abnormal atrioventricular conduction [HP:0005150],0/22,0%,3/3,100%,0.003478260869565217,0.00043478260869565214
@@ -12,7 +12,7 @@ Muscular ventricular septal defect [HP:0011623],6/59,10%,6/25,24%,0.299992259972
 Pulmonary arterial hypertension [HP:0002092],4/6,67%,0/2,0%,0.6857142857142857,0.42857142857142855
 Hypoplasia of the ulna [HP:0003022],1/12,8%,2/10,20%,0.831168831168831,0.5714285714285713
 Hypoplasia of the radius [HP:0002984],30/62,48%,6/14,43%,1.0,0.7735491022101784
-Atrial septal defect [HP:0001631],42/44,95%,20/20,100%,1.0,1.0
 Short thumb [HP:0009778],11/41,27%,8/30,27%,1.0,1.0
+Atrial septal defect [HP:0001631],42/44,95%,20/20,100%,1.0,1.0
 Absent radius [HP:0003974],7/32,22%,6/25,24%,1.0,1.0
 Short humerus [HP:0005792],7/17,41%,4/9,44%,1.0,1.0
diff --git a/docs/tutorial.rst b/docs/tutorial.rst
@@ -189,21 +189,19 @@ Prepare genotype and phenotype predicates
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 We will create a predicate to bin patients into group
-depending on presence of a missense and frameshift variant to test
+depending on presence of a single allele of a missense or frameshift variant to test
 if there is a difference between frameshift and non-frameshift variants
 in the individuals of the *TBX5* cohort.
 
 >>> from gpsea.model import VariantEffect
->>> from gpsea.analysis.predicate.genotype import VariantPredicates, groups_predicate
->>> gt_predicate = groups_predicate(
-...     predicates=(
-...         VariantPredicates.variant_effect(VariantEffect.MISSENSE_VARIANT, tx_id),
-...         VariantPredicates.variant_effect(VariantEffect.FRAMESHIFT_VARIANT, tx_id)
-...     ),
-...     group_names=('Missense', 'Frameshift'),
+>>> from gpsea.analysis.predicate.genotype import VariantPredicates, monoallelic_predicate
+>>> gt_predicate = monoallelic_predicate(
+...     a_predicate=VariantPredicates.variant_effect(VariantEffect.MISSENSE_VARIANT, tx_id),
+...     b_predicate=VariantPredicates.variant_effect(VariantEffect.FRAMESHIFT_VARIANT, tx_id),
+...     names=('Missense', 'Frameshift')
 ... )
 >>> gt_predicate.display_question()
-'Genotype group: Missense, Frameshift'
+'Allele group: Missense, Frameshift'
 
 .. note::
 

diff --git a/docs/user-guide/predicates/filtering_predicate.rst b/docs/user-guide/predicates/filtering_predicate.rst
diff --git a/docs/user-guide/predicates/genotype_predicates.rst b/docs/user-guide/predicates/genotype_predicates.rst
@@ -24,7 +24,6 @@ the :class:`~gpsea.analysis.predicate.genotype.VariantPredicate` is all about.
 
   variant_predicates
   mode_of_inheritance_predicate
-  filtering_predicate
   male_female_predicate
   diagnosis_predicate
   groups_predicate

diff --git a/docs/user-guide/stats.rst b/docs/user-guide/stats.rst
@@ -127,7 +127,7 @@ First, we create a :class:`~gpsea.analysis.predicate.genotype.VariantPredicate`
 to test if the variant leads to a frameshift (in this case):
 
 >>> from gpsea.model import VariantEffect
->>> from gpsea.analysis.predicate.genotype import VariantPredicates, boolean_predicate
+>>> from gpsea.analysis.predicate.genotype import VariantPredicates
 >>> tx_id = 'NM_181486.4'
 >>> is_frameshift = VariantPredicates.variant_effect(VariantEffect.FRAMESHIFT_VARIANT, tx_id)
 >>> is_frameshift.get_question()

diff --git a/src/gpsea/analysis/predicate/genotype/__init__.py b/src/gpsea/analysis/predicate/genotype/__init__.py
@@ -1,13 +1,15 @@
 from ._api import GenotypePolyPredicate
 from ._api import VariantPredicate
 from ._counter import AlleleCounter
-from ._gt_predicates import boolean_predicate, groups_predicate, filtering_predicate, sex_predicate, diagnosis_predicate
+from ._gt_predicates import groups_predicate, sex_predicate, diagnosis_predicate
+from ._gt_predicates import monoallelic_predicate, biallelic_predicate
 from ._gt_predicates import ModeOfInheritancePredicate
 from ._variant import VariantPredicates, ProteinPredicates
 
 __all__ = [
     'GenotypePolyPredicate',
-    'boolean_predicate', 'groups_predicate', 'filtering_predicate', 'sex_predicate', 'diagnosis_predicate',
+    'groups_predicate', 'sex_predicate', 'diagnosis_predicate',
+    'monoallelic_predicate', 'biallelic_predicate',
     'ModeOfInheritancePredicate',
     'AlleleCounter', 'VariantPredicate',
     'VariantPredicates', 'ProteinPredicates',