diff --git a/efo/fetch_efo_ontology_from_pubmed.py b/efo/fetch_efo_ontology_from_pubmed.py
index afe98b0..1b038ea 100644
--- a/efo/fetch_efo_ontology_from_pubmed.py
+++ b/efo/fetch_efo_ontology_from_pubmed.py
@@ -1,9 +1,14 @@
+#%% [markdown]
+# The following codes query the EFO ontology and retrives tasks and concepts that are assigned with readable labels. Then search PubMed Central for the number of articles on 
+
 #%%
 # pip install rdflib
 from rdflib import OWL, Graph
 from rdflib.util import guess_format
 from owlready2 import *
 
+import time
+
 from rdflib import URIRef
 
 from rdflib import Graph
@@ -27,12 +32,15 @@
 
     SELECT ?label
     WHERE {{
-    ?task rdfs:subClassOf :{class_name};
+    ?task rdfs:subClassOf* :{class_name};
             rdfs:label ?label
     }}
     """
-    # select the first rdfs:label and convert it to python string
-    return [labels[0].toPython() for labels in graph.query(query)]
+
+    # select the all rdfs:labels, flatten the list of labels, and convert them to python string
+    labels = [labels for labels in graph.query(query)]
+    flatten_labels = [l.toPython() for ll in labels for l in ll]
+    return flatten_labels
 
 # preapre RDFLib graph for SPARQL queries
 graph = default_world.as_rdflib_graph()
@@ -40,9 +48,13 @@
 tasks = query_labels(graph, "Task")
 concepts = query_labels(graph, "ExecutiveFunction")
 
+print(tasks)
 
 print(f"Tasks: {len(tasks)}, Concepts: {len(concepts)}")
 
+time_estimate = len(tasks) * len(concepts)
+
+print(f"it taks ~ {time_estimate}s to query PubMed Central for these tasks and concepts.")
 
 #%%
 # goal: create rows with the following data: <task>,<concept>,<hits>,<task_total>
@@ -50,7 +62,36 @@
 from metapub import PubMedFetcher
 fetcher = PubMedFetcher()
 
-for task, concept in [(task, concept) for task in tasks for concept in concepts]:
-    query = f"({task}[TIAB]) AND ({concept}[TIAB])"
-    pmids = fetcher.pmids_for_query(query=f'{query}', retmax=1000000, since='2010', pmc_only=True)
-    print(f"{query}: {len(pmids)}")
+#tasks = ["Reversal Learning"]
+#concepts = ["Behavioral Control"]
+
+def query_pubmed_for_task(task, concept):
+    suffixes = ['',' task',' game',' test']
+    task_queries = map(lambda s: task+s, suffixes)
+
+    suffixed_hits = []
+    hits = []
+    for tq in task_queries:
+        query = f"({tq}[TIAB]) AND ({concept}[TIAB])"
+        pmids = fetcher.pmids_for_query(query=f'{query}', retmax=1000000, pmc_only=False)
+        suffixed_hits += pmids
+        if tq == task: hits = pmids
+
+    return (hits, suffixed_hits)
+
+# main loop
+
+with open("data/efo_taskconcept_pubmed_hits.csv", "a+") as csv:
+    csv.write('task,concept,hits,suffixed_hits,concept_hits,timestamp_ms\n')
+    for task, concept in [(task, concept) for task in tasks for concept in concepts]:
+        millis = int(round(time.time() * 1000))
+
+        hits, suffixed_hits = query_pubmed_for_task(task, concept)
+
+        concept_query = f"({concept}[TIAB])"
+        concept_hits = fetcher.pmids_for_query(query=f'{concept_query}', retmax=1000000, pmc_only=False)
+        
+        csv_line = f'{task},{concept},{len(hits)},{len(suffixed_hits)},{len(concept_hits)},{millis}\n'
+        
+        print(csv_line)
+        csv.write(csv_line)

diff --git a/efo/fetch_efo_ontology_from_pubmed.py b/efo/fetch_efo_ontology_from_pubmed.py
index afe98b0..1b038ea 100644
--- a/efo/fetch_efo_ontology_from_pubmed.py
+++ b/efo/fetch_efo_ontology_from_pubmed.py
@@ -1,9 +1,14 @@
+#%% [markdown]
+# The following codes query the EFO ontology and retrives tasks and concepts that are assigned with readable labels. Then search PubMed Central for the number of articles on 
+
 #%%
 # pip install rdflib
 from rdflib import OWL, Graph
 from rdflib.util import guess_format
 from owlready2 import *
 
+import time
+
 from rdflib import URIRef
 
 from rdflib import Graph
@@ -27,12 +32,15 @@
 
     SELECT ?label
     WHERE {{
-    ?task rdfs:subClassOf :{class_name};
+    ?task rdfs:subClassOf* :{class_name};
             rdfs:label ?label
     }}
     """
-    # select the first rdfs:label and convert it to python string
-    return [labels[0].toPython() for labels in graph.query(query)]
+
+    # select the all rdfs:labels, flatten the list of labels, and convert them to python string
+    labels = [labels for labels in graph.query(query)]
+    flatten_labels = [l.toPython() for ll in labels for l in ll]
+    return flatten_labels
 
 # preapre RDFLib graph for SPARQL queries
 graph = default_world.as_rdflib_graph()
@@ -40,9 +48,13 @@
 tasks = query_labels(graph, "Task")
 concepts = query_labels(graph, "ExecutiveFunction")
 
+print(tasks)
 
 print(f"Tasks: {len(tasks)}, Concepts: {len(concepts)}")
 
+time_estimate = len(tasks) * len(concepts)
+
+print(f"it taks ~ {time_estimate}s to query PubMed Central for these tasks and concepts.")
 
 #%%
 # goal: create rows with the following data: <task>,<concept>,<hits>,<task_total>
@@ -50,7 +62,36 @@
 from metapub import PubMedFetcher
 fetcher = PubMedFetcher()
 
-for task, concept in [(task, concept) for task in tasks for concept in concepts]:
-    query = f"({task}[TIAB]) AND ({concept}[TIAB])"
-    pmids = fetcher.pmids_for_query(query=f'{query}', retmax=1000000, since='2010', pmc_only=True)
-    print(f"{query}: {len(pmids)}")
+#tasks = ["Reversal Learning"]
+#concepts = ["Behavioral Control"]
+
+def query_pubmed_for_task(task, concept):
+    suffixes = ['',' task',' game',' test']
+    task_queries = map(lambda s: task+s, suffixes)
+
+    suffixed_hits = []
+    hits = []
+    for tq in task_queries:
+        query = f"({tq}[TIAB]) AND ({concept}[TIAB])"
+        pmids = fetcher.pmids_for_query(query=f'{query}', retmax=1000000, pmc_only=False)
+        suffixed_hits += pmids
+        if tq == task: hits = pmids
+
+    return (hits, suffixed_hits)
+
+# main loop
+
+with open("data/efo_taskconcept_pubmed_hits.csv", "a+") as csv:
+    csv.write('task,concept,hits,suffixed_hits,concept_hits,timestamp_ms\n')
+    for task, concept in [(task, concept) for task in tasks for concept in concepts]:
+        millis = int(round(time.time() * 1000))
+
+        hits, suffixed_hits = query_pubmed_for_task(task, concept)
+
+        concept_query = f"({concept}[TIAB])"
+        concept_hits = fetcher.pmids_for_query(query=f'{concept_query}', retmax=1000000, pmc_only=False)
+        
+        csv_line = f'{task},{concept},{len(hits)},{len(suffixed_hits)},{len(concept_hits)},{millis}\n'
+        
+        print(csv_line)
+        csv.write(csv_line)
diff --git a/py/vscode_jupyter_test.py b/py/vscode_jupyter_test.py
deleted file mode 100644
index ccecc43..0000000
--- a/py/vscode_jupyter_test.py
+++ /dev/null
@@ -1,4 +0,0 @@
-#%%
-print("test")
-
-#%%