From 7f0ca21cc3ae1c8b8f288636f19d3d5f4c0f59a4 Mon Sep 17 00:00:00 2001
From: Alyssa Dai <alyssa.ydai@gmail.com>
Date: Tue, 13 Aug 2024 14:46:32 -0400
Subject: [PATCH] [FIX] Ensure subjects without imaging sessions are considered
 in main query (#333)

* use left join approach for imaging session subquery

* update default non-aggregated query
---
 app/api/utility.py               |  1 +
 docs/default_neurobagel_query.rq | 28 +++++++++++++---------------
 2 files changed, 14 insertions(+), 15 deletions(-)

diff --git a/app/api/utility.py b/app/api/utility.py
index 1bb60d7..e09c80a 100644
--- a/app/api/utility.py
+++ b/app/api/utility.py
@@ -247,6 +247,7 @@ def create_query(
             {{
                 SELECT ?subject (count(distinct ?imaging_session) as ?num_matching_imaging_sessions)
                 WHERE {{
+                    ?subject a nb:Subject.
                     OPTIONAL {{
                         ?subject nb:hasSession ?imaging_session.
                         ?imaging_session a nb:ImagingSession;
diff --git a/docs/default_neurobagel_query.rq b/docs/default_neurobagel_query.rq
index c4dc71c..ae2ff14 100644
--- a/docs/default_neurobagel_query.rq
+++ b/docs/default_neurobagel_query.rq
@@ -9,13 +9,13 @@ SELECT DISTINCT ?dataset_uuid ?dataset_name ?dataset_portal_uri ?sub_id ?age ?se
 ?diagnosis ?subject_group ?num_matching_phenotypic_sessions ?num_matching_imaging_sessions ?session_id ?session_type ?assessment ?image_modal ?session_file_path
 WHERE {
     ?dataset_uuid a nb:Dataset;
-            nb:hasLabel ?dataset_name;
-            nb:hasSamples ?subject.
+        nb:hasLabel ?dataset_name;
+        nb:hasSamples ?subject.
     ?subject a nb:Subject;
-            nb:hasLabel ?sub_id;
-            nb:hasSession ?session.
+        nb:hasLabel ?sub_id;
+        nb:hasSession ?session.
     ?session a ?session_type;
-             nb:hasLabel ?session_id.
+        nb:hasLabel ?session_id.
     OPTIONAL {
         ?session nb:hasAcquisition/nb:hasContrastType ?image_modal.
         OPTIONAL {?session nb:hasFilePath ?session_file_path.}
@@ -29,17 +29,15 @@ WHERE {
     {
         SELECT ?subject (count(distinct ?phenotypic_session) as ?num_matching_phenotypic_sessions)
         WHERE {
-            ?subject a nb:Subject.
-            OPTIONAL {
-                ?subject nb:hasSession ?phenotypic_session.
-                ?phenotypic_session a nb:PhenotypicSession.
+            ?subject nb:hasSession ?phenotypic_session.
+            ?phenotypic_session a nb:PhenotypicSession.
+
+            OPTIONAL {?phenotypic_session nb:hasAge ?age.}
+            OPTIONAL {?phenotypic_session nb:hasSex ?sex.}
+            OPTIONAL {?phenotypic_session nb:hasDiagnosis ?diagnosis.}
+            OPTIONAL {?phenotypic_session nb:isSubjectGroup ?subject_group.}
+            OPTIONAL {?phenotypic_session nb:hasAssessment ?assessment.}
 
-                OPTIONAL {?phenotypic_session nb:hasAge ?age.}
-                OPTIONAL {?phenotypic_session nb:hasSex ?sex.}
-                OPTIONAL {?phenotypic_session nb:hasDiagnosis ?diagnosis.}
-                OPTIONAL {?phenotypic_session nb:isSubjectGroup ?subject_group.}
-                OPTIONAL {?phenotypic_session nb:hasAssessment ?assessment.}
-            }
 
         } GROUP BY ?subject
     }