Update sankey diagrams

.github/workflows/tests.yml

@@ -50,6 +50,8 @@ jobs:
 #      run: bash tests/pipelines/test_curation_pipelines.sh
 
     - name: Upload the coverage data to Coveralls
-      env: 
-        GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
-      run: coveralls
+      uses: coverallsapp/github-action@v2
+      with:
+        github-token: ${{ secrets.GITHUB_TOKEN }}
+        # Ensure failure to upload coverage does not fail the workflow
+        fail-on-error: false

data-exploration/clinvar-variant-types/README.md

@@ -2,7 +2,7 @@
 
 The script in this directory parses the ClinVar XML data dump and constructs several diagrams and tables which illustrate how variation and disease data are represented. This helps guide the design of the pipeline and its output structure.
 
-The data was last updated on **2025-09-04.** Graphs can be enlarged by clicking on them.
+The data was last updated on **2026-02-20.** Graphs can be enlarged by clicking on them.
 
 
 

data-exploration/clinvar-variant-types/clinvar-variant-types.py

@@ -61,8 +61,7 @@ def generate_diagram(self, threshold=None):
         s.draw()
         plt.savefig(self.name, bbox_inches='tight')
 
-    def _format_label(self, label):
-        max_len = 20
+    def _format_label(self, label, max_len=20):
         words = label.split()
         lines = []
         line = []
@@ -75,7 +74,7 @@ def _format_label(self, label):
 
     def _apply_threshold(self, nodes, flows, threshold):
         """Recompute nodes and flows by combining nodes at the final level with value less than threshold."""
-        new_node_name = 'Other'
+        new_node_name = '[Other]'
         new_nodes = nodes[:-1]
         new_final_level = []
         new_value = 0
@@ -382,8 +381,8 @@ def main(clinvar_xml, process_items=None):
     # Output the code for Sankey diagrams. Transitions are sorted in decreasing number of counts, so that the most frequent
     # cases are on top.
     for sankey_diagram in (sankey_variation_representation, sankey_trait_representation, sankey_trait_quality,
-                           sankey_clinical_classification, sankey_somatic_classification,
-                           sankey_mode_of_inheritance, sankey_allele_origin, sankey_inheritance_origin):
+                           sankey_somatic_classification, sankey_mode_of_inheritance, sankey_allele_origin,
+                           sankey_inheritance_origin):
         print('\n')
         print(sankey_diagram)
         try:
@@ -393,12 +392,14 @@ def main(clinvar_xml, process_items=None):
             continue
 
     # Sankey diagrams requiring thresholding
-    print('\n')
-    print(sankey_star_rating)
-    try:
-        sankey_star_rating.generate_diagram(threshold=1000)
-    except Exception as e:
-        print(e)
+    for sankey_diagram, threshold in [(sankey_star_rating, 1000), (sankey_clinical_classification, 500)]:
+        print('\n')
+        print(sankey_diagram)
+        try:
+            sankey_diagram.generate_diagram(threshold=threshold)
+        except Exception as e:
+            print(e)
+            continue
 
     # Output the supplementary tables for the report.
     for supplementary_table in (counter_trait_xrefs, counter_clin_class_complex, counter_clin_class_all,