clusterExpression: add Function column for genes

The migrated 'Genes expressed in <cluster>' (clusterExpression) query did not
surface the gene Function column that v2 prod shows. Gene molecular-function
categories (e.g. Enzyme, Small_molecule_binding) are stored as Neo4j labels on
the Gene node, so Function is now derived from labels(g), excluding the
structural/availability labels (Entity, Class, Individual, Gene, Feature and
any has* facet) and sorted.

Added as a new column alongside the existing ones (Gene, Cell type, Expression
Level, Expression Extent, Tags); also added to preview_columns. The reverse
expressionCluster query (rows are clusters, not genes) is left unchanged.

Minor bump to 1.18.0 so the major.minor solr_result_cache key rotates and the
cached clusterExpression results are recomputed with the Function column.

Validated read-only against prod pdb: 128up -> 'Enzyme; Small_molecule_binding'
(matches prod); Nup153 -> 'DNA_binding; Structural_molecule'; genes with no
function category render blank.

Author: Robbie1977

setup.py

@@ -3,7 +3,7 @@
 
 here = path.abspath(path.dirname(__file__))
 
-__version__ = "1.17.0"
+__version__ = "1.18.0"
 
 # Get the long description from the README file
 with open(path.join(here, 'README.md')) as f:

src/vfbquery/vfb_queries.py

@@ -1860,7 +1860,7 @@ def clusterExpression_to_schema(name, take_default):
         "default": take_default,
     }
     preview = 5
-    preview_columns = ["id", "name", "tags", "expression_level", "expression_extent"]
+    preview_columns = ["id", "name", "tags", "expression_level", "expression_extent", "function"]
 
     return Query(query=query, label=label, function=function, takes=takes, preview=preview, preview_columns=preview_columns)
 
@@ -4507,7 +4507,8 @@ def get_cluster_expression(cluster_short_form: str, return_dataframe=True, limit
                  iri: g.iri,
                  types: labels(g),
                  unique_facets: apoc.coll.sort(coalesce(g.uniqueFacets, [])),
-                 symbol: coalesce(([]+g.symbol)[0], '')
+                 symbol: coalesce(([]+g.symbol)[0], ''),
+                 function: apoc.coll.sort([l IN labels(g) WHERE NOT l IN ['Entity','Class','Individual','Gene','Feature'] AND NOT l STARTS WITH 'has'])
              }} AS gene,
              primary
         MATCH (a:Anatomy)<-[:composed_primarily_of]-(primary)
@@ -4525,6 +4526,7 @@ def get_cluster_expression(cluster_short_form: str, return_dataframe=True, limit
             apoc.text.join(gene.unique_facets, '|') AS tags,
             expression_level,
             expression_extent,
+            apoc.text.join(coalesce(gene.function, []), '; ') AS function,
             apoc.text.format("[%s](%s)", [anatomy.label, anatomy.short_form]) AS anatomy
         ORDER BY expression_level DESC, gene.label
     """
@@ -4551,10 +4553,11 @@ def get_cluster_expression(cluster_short_form: str, return_dataframe=True, limit
                 "anatomy": {"title": "Cell type", "type": "markdown", "order": 1},
                 "expression_level": {"title": "Expression Level", "type": "numeric", "order": 2},
                 "expression_extent": {"title": "Expression Extent", "type": "numeric", "order": 3},
-                "tags": {"title": "Tags", "type": "tags", "order": 4}
+                "tags": {"title": "Tags", "type": "tags", "order": 4},
+                "function": {"title": "Function", "type": "text", "order": 5}
             },
             "rows": [
-                {key: row[key] for key in ["id", "name", "anatomy", "expression_level", "expression_extent", "tags"]}
+                {key: row[key] for key in ["id", "name", "anatomy", "expression_level", "expression_extent", "tags", "function"]}
                 for row in safe_to_dict(df, sort_by_id=False)
             ],
             "count": total_count