Add the additional queries from the manuscript.

fusion-jena · Nov 21, 2024 · 908b5ae · 908b5ae
1 parent 0369564
commit 908b5ae
Show file tree

Hide file tree

Showing 25 changed files with 93 additions and 3 deletions.
diff --git a/sparql_query/q1.rq b/sparql_query/q1.rq
@@ -1,3 +1,5 @@
+# Research articles by research field
+
 SELECT ?research_field (COUNT(DISTINCT ?article) AS ?number_of_articles)
 WHERE {
   ?repository <http://purl.org/pav/retrievedFrom> ?article .

diff --git a/sparql_query/q10.rq b/sparql_query/q10.rq
@@ -1,3 +1,5 @@
+# Exceptions occurring in Jupyter notebooks in our corpus.
+
 SELECT ?exception (COUNT(?exception) AS ?count)
 WHERE {
   ?execution  a <https://w3id.org/reproduceme/CellExecution> ;

diff --git a/sparql_query/q11.rq b/sparql_query/q11.rq
@@ -1,3 +1,5 @@
+# Jupyter notebook exceptions by research field, taking as a proxy the highest-level MeSH terms of the article associated with the notebook.
+
 PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
 SELECT DISTINCT ?research_field (COUNT(?exception) AS ?exception_count)
 WHERE {

diff --git a/sparql_query/q12.rq b/sparql_query/q12.rq
@@ -1,3 +1,5 @@
+# Notebooks with successful executions with same and different results
+
 PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
 SELECT (COUNT(?processed_different_result) AS ?count_different_result) (COUNT(?processed_same_result) AS ?count_same_result) (?count_same_result + ?count_different_result AS ?count_successful_executions)
 WHERE {

diff --git a/sparql_query/q13.rq b/sparql_query/q13.rq
@@ -1,3 +1,4 @@
+# Notebooks with code style errors and  their description
 SELECT ?notebook ?error ?description
 WHERE {
   ?error a <https://w3id.org/reproduceme/NotebookCodeStyleError> ;

diff --git a/sparql_query/q14.rq b/sparql_query/q14.rq
@@ -1,3 +1,5 @@
+# Notebooks by search term: 'immun' AND ('stem' OR 'differentiation')
+
 SELECT DISTINCT ?notebook_url ?article_label ?keywords WHERE {
   ?article <https://w3id.org/reproduceme/keywords> ?keywords .
   ?article <http://www.w3.org/2000/01/rdf-schema#label> ?article_label .

diff --git a/sparql_query/q15.rq b/sparql_query/q15.rq
@@ -1,3 +1,4 @@
+# Article by keywords, e.g., `open source'
 SELECT DISTINCT ?article ?keywords WHERE {
   ?article <https://w3id.org/reproduceme/keywords> ?keywords .
   FILTER (REGEX(LCASE(?keywords), "open(.)source"))

diff --git a/sparql_query/q16.rq b/sparql_query/q16.rq
@@ -1,3 +1,4 @@
+# Most common errors in immunology
 SELECT DISTINCT ?exception (COUNT(?exception) AS ?count) WHERE {
     ?execution  a <https://w3id.org/reproduceme/CellExecution> ;
     <https://w3id.org/reproduceme/exception> ?exception ;

diff --git a/sparql_query/q17.rq b/sparql_query/q17.rq
@@ -1,3 +1,5 @@
+# Most common errors in Nature journal
+
 PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 SELECT  ?exception (COUNT(?exception) AS ?count) WHERE {
     ?execution  a <https://w3id.org/reproduceme/CellExecution> ;

diff --git a/sparql_query/q18.rq b/sparql_query/q18.rq
@@ -1,3 +1,4 @@
+# MeSH terms ranked by 'ModuleNotFoundError' frequency
 PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
 SELECT DISTINCT ?research_field (COUNT(?exception) AS ?exception_count)
 WHERE {

diff --git a/sparql_query/q19.rq b/sparql_query/q19.rq
@@ -1,3 +1,5 @@
+# Repositories by their stargazers count
+
 PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
 SELECT DISTINCT ?repo ?stargazers_count WHERE {
   ?repo <https://w3id.org/reproduceme/stargazers_count> ?count.

diff --git a/sparql_query/q2.rq b/sparql_query/q2.rq
@@ -1,3 +1,5 @@
+# Research field (MeSH terms) by the number of GitHub repositories that contain at least one Jupyter notebook.
+
 PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 PREFIX xsd: <http://www.w3.org/2001/XMLSchema#>
 PREFIX repr: <https://w3id.org/reproduceme/>

diff --git a/sparql_query/q20.rq b/sparql_query/q20.rq
@@ -1,5 +1,6 @@
-PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+# Match articles between FAIR Jupyter and Wikidata via DOI
 
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 PREFIX wikidata_wd: <http://www.wikidata.org/entity/>
 PREFIX wikidata_wdt: <http://www.wikidata.org/prop/direct/>
 

diff --git a/sparql_query/q21.rq b/sparql_query/q21.rq
@@ -1,5 +1,6 @@
-PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+# Match articles between FAIR Jupyter and Wikidata via PMC ID
 
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 PREFIX wikidata_wd: <http://www.wikidata.org/entity/>
 PREFIX wikidata_wdt: <http://www.wikidata.org/prop/direct/>
 

diff --git a/sparql_query/q22.rq b/sparql_query/q22.rq
@@ -1,5 +1,6 @@
-PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+# Match articles between FAIR Jupyter and Wikidata via MeSH in different language, i.e Malayalam
 
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
 PREFIX wikidata_wd: <http://www.wikidata.org/entity/>
 PREFIX wikidata_wdt: <http://www.wikidata.org/prop/direct/>
 

diff --git a/sparql_query/q23.rq b/sparql_query/q23.rq
@@ -0,0 +1,25 @@
+# Match articles between FAIR Jupyter and MaRDI via DOI and get co-used software
+
+PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
+PREFIX wikibase: <http://wikiba.se/ontology#>
+PREFIX mardi_wd: <https://portal.mardi4nfdi.de/entity/>
+PREFIX mardi_wdt: <https://portal.mardi4nfdi.de/prop/direct/>
+
+PREFIX bd: <http://www.bigdata.com/rdf#>
+PREFIX wikibase: <http://wikiba.se/ontology#>
+
+SELECT DISTINCT ?title ?doi ?method ?methodLabel
+
+WHERE {
+  ?fj_article <https://w3id.org/reproduceme/doi> ?doi .
+
+  service <http://query.portal.mardi4nfdi.de/proxy/wdqs/bigdata/namespace/wdq/sparql> {
+    ?mardi_paper mardi_wdt:P27 ?doi .
+    ?mardi_paper mardi_wdt:P159 ?title .
+
+    ?mardi_paper mardi_wdt:P1463 ?method .
+    ?method rdfs:label ?methodLabel .
+  }
+
+}
+LIMIT 1000
diff --git a/sparql_query/q24.rq b/sparql_query/q24.rq
@@ -0,0 +1,12 @@
+# GitHub repositories and their Software Heritage snapshot
+
+# List of GitHub repositories covered by https://doi.org/10.1093/gigascience/giad113 , 
+# with pointers to their Software Heritage snapshots as per https://doi.org/10.5281/zenodo.12806151
+
+SELECT DISTINCT 
+(URI(?repo_url_base) AS ?GitHub_URL)
+(URI (CONCAT("https://archive.softwareheritage.org/browse/origin/directory/?origin_url=", ENCODE_FOR_URI(STR(?repo_url_base)))) AS ?SWH_URL)
+WHERE {
+  ?repository <https://w3id.org/reproduceme/url> ?repo_url_base .
+}
+ORDER BY ASC(?repo_url_base)
diff --git a/sparql_query/q25.rq b/sparql_query/q25.rq
@@ -0,0 +1,18 @@
+# Articles and repositories with notebooks in Julia
+
+SELECT DISTINCT ?title
+(URI(CONCAT("https://www.ncbi.nlm.nih.gov/pmc/articles/PMC", STR(?pmcid))) AS ?PMC_URL)
+(URI(?repo_url_base) AS ?GitHub_URL)
+?Notebook_URL
+WHERE {
+  ?notebook a <https://w3id.org/reproduceme/Notebook> ;
+            <https://w3id.org/reproduceme/language> "julia" .
+  ?notebook <http://purl.org/pav/retrievedFrom> ?repository .
+  ?article ^<http://purl.org/pav/retrievedFrom> ?repository .
+  ?article <https://w3id.org/reproduceme/pmc> ?pmcid .
+  ?article <http://www.w3.org/2000/01/rdf-schema#label> ?title .
+  ?notebook <http://www.w3.org/2000/01/rdf-schema#label> ?notebook_label . 
+  ?repository <https://w3id.org/reproduceme/url> ?repo_url_base . 
+  BIND(URI(CONCAT( ?repo_url_base, "/blob/master/", ?notebook_label)) AS ?Notebook_URL) 
+}
+ORDER BY DESC(?Notebook_URL)
diff --git a/sparql_query/q3.rq b/sparql_query/q3.rq
@@ -1,3 +1,5 @@
+# Journals with the highest number of articles that had a valid GitHub repository and at least one Jupyter notebook.
+
 SELECT ?journal_name (COUNT(?article) as ?article_count)
 WHERE {
   ?article <https://w3id.org/reproduceme/publishedIn> ?journal .

diff --git a/sparql_query/q4.rq b/sparql_query/q4.rq
@@ -1,3 +1,5 @@
+# Journals by the number of GitHub repositories and by the number of GitHub repositories with at least one Jupyter notebook.
+
 SELECT ?journal_name (COUNT(?repository) as ?repository_count) (COUNT(?repository_nb) as ?repositories_with_notebooks_count) WHERE
   {
   ?article <https://w3id.org/reproduceme/publishedIn> ?journal .

diff --git a/sparql_query/q5.rq b/sparql_query/q5.rq
@@ -1,3 +1,5 @@
+# Journals by number of GitHub repositories with Jupyter notebooks.
+
 SELECT ?journal_name (COUNT(?repository_nb) AS ?repositories_with_notebooks_count)
         ?max_notebooks_count
 WHERE {

diff --git a/sparql_query/q6.rq b/sparql_query/q6.rq
@@ -1,3 +1,5 @@
+# Programming languages of the notebooks.
+
 SELECT ?language (COUNT(?notebook) as ?notebook_count)
 WHERE {
   ?notebook a <https://w3id.org/reproduceme/Notebook> ;

diff --git a/sparql_query/q7.rq b/sparql_query/q7.rq
@@ -1,3 +1,4 @@
+# Python notebooks by Python version by year of first commit to the notebook’s GitHub repository.
 SELECT ?created_year ?language (COUNT(?notebook) as ?notebook_count)
 WHERE {
   ?notebook a <https://w3id.org/reproduceme/Notebook> ;

diff --git a/sparql_query/q8.rq b/sparql_query/q8.rq
@@ -1,3 +1,4 @@
+# Python notebooks by minor Python version by year of first commit to the GitHub repository containing the notebook.
 SELECT ?created_year ?minor_version (COUNT(?notebook) as ?count_minor_version)
 WHERE {
   ?notebook a <https://w3id.org/reproduceme/Notebook> ;

diff --git a/sparql_query/q9.rq b/sparql_query/q9.rq
@@ -1,3 +1,5 @@
+# Python notebooks by major Python version by year of first commit to the notebook’s GitHub repository.
+
 SELECT ?created_year ?major_version (COUNT(?notebook) as ?count_major_version)
 WHERE {
   ?notebook a <https://w3id.org/reproduceme/Notebook> ;