Merge pull request #125 from reactome/rna-table-100

rnas.csv: list RNA species per network (deltasignal specs/100)

Author: adamjohnwright

src/logic_network_generator.py

@@ -4010,9 +4010,24 @@ def export_pathogens(pathway_logic_network: pd.DataFrame,
                     get_pathogen_entities, "pathogen-derived")
 
 
+def export_rnas(pathway_logic_network: pd.DataFrame,
+               reactome_id_to_uuid: Dict[str, str],
+               output_file: str) -> None:
+    """Write rnas.csv: which entities in THIS network are RNA species (deltasignal
+    specs/100), by :func:`src.neo4j_connector.get_rna_entities`. A consumer joins
+    node copies of one RNA (a root mRNA copy reads the copy transcription makes).
+    Same columns and always-written rule as drugs.csv and pathogens.csv."""
+    from src.neo4j_connector import get_rna_entities
+    # only nodes that ARE an RNA species: a variant of a complex that chose an RNA
+    # member (a miR-26A RISC) is a complex, not the RNA (the drug rule's member
+    # clause would list it; the first variant build listed 2,393 such rows)
+    _export_derived(pathway_logic_network, reactome_id_to_uuid, output_file,
+                    get_rna_entities, "RNA", by_member=False)
+
+
 def _export_derived(pathway_logic_network: pd.DataFrame,
                     reactome_id_to_uuid: Dict[str, str],
-                    output_file: str, finder, label: str) -> None:
+                    output_file: str, finder, label: str, by_member: bool = True) -> None:
     """The node listing shared by drugs.csv and pathogens.csv. ``finder`` maps
     stable ids to {stId: {"schema_class", "name"}} for the derived ones."""
     from src.neo4j_connector import get_reactome_release
@@ -4042,7 +4057,8 @@ def parts(node_id: str):
     rows = []
     for n in sorted(node_ids):
         parent, members = parts(n)
-        hit = parent if parent in derived else next((m for m in members if m in derived), None)
+        hit = parent if parent in derived else \
+            (next((m for m in members if m in derived), None) if by_member else None)
         if hit is None:
             continue
         rows.append({"stable_id": n, "schema_class": derived[hit]["schema_class"],

src/neo4j_connector.py

@@ -942,6 +942,20 @@ def derived(s: str, depth: int = 0) -> bool:
 PROTEIN_REFERENCE_CLASSES = frozenset({"ReferenceGeneProduct", "ReferenceIsoform"})
 
 
+def get_rna_entities(stable_ids) -> Dict[str, Dict[str, str]]:
+    """The entities among ``stable_ids`` that are RNA: an entity whose reference
+    entity is a ReferenceRNASequence (an mRNA, a miRNA), with schema class and
+    display name (deltasignal specs/100). Complexes and sets are not listed: the
+    consumer twins node copies of one RNA species, never of a complex holding one."""
+    ids = sorted({s for s in stable_ids if s})
+    if not ids:
+        return {}
+    rows = get_graph().run(
+        "UNWIND $ids AS s MATCH (e:PhysicalEntity {stId: s})-[:referenceEntity]->(:ReferenceRNASequence) "
+        "RETURN s, e.schemaClass AS c, e.displayName AS n", ids=ids).data()
+    return {r["s"]: {"schema_class": r["c"], "name": r["n"]} for r in rows}
+
+
 def get_pathogen_entities(stable_ids) -> Dict[str, Dict[str, str]]:
     """The entities among ``stable_ids`` that are PATHOGEN-DERIVED, with their
     schema class and display name (deltasignal specs/048).

src/pathway_generator.py

@@ -15,6 +15,7 @@
     export_drugs,
     export_pathogens,
     export_pools,
+    export_rnas,
     export_containment,
     export_containment_structure,
     export_entity_reaction_proxy_mapping,
@@ -234,7 +235,7 @@ def _write_cache_fingerprint(
     "logic_network.csv", "stid_to_uuid_mapping.csv", "entity_reaction_proxy_mapping.csv",
     "nodes.csv", "node_reaction_context.csv", "node_resolution.csv", "node_exclusions.csv",
     "boundary_edges.csv", "cofactors.csv", "containment.csv", "containment_structure.csv",
-    "drugs.csv", "pathogens.csv",
+    "drugs.csv", "pathogens.csv", "rnas.csv",
     "pools.csv", "pool_transitions.csv", "pool_carriers.csv", "carrier_loops.csv",
 )
 
@@ -615,6 +616,17 @@ def generate_pathway_file(
             logger.error(f"Failed to write pathogens.csv: {e}", exc_info=True)
             raise
 
+        # RNA species (deltasignal specs/100), likewise on their own.
+        try:
+            export_rnas(
+                result.logic_network,
+                result.uuid_mapping,
+                str(pathway_output_dir / "rnas.csv"),
+            )
+        except Exception as e:
+            logger.error(f"Failed to write rnas.csv: {e}", exc_info=True)
+            raise
+
         # Interconversion pools (deltasignal specs/039), in their own block.
         try:
             export_pools(

tests/test_export_failfast.py

@@ -24,7 +24,7 @@
 EXPORTS = ["export_uuid_to_reactome_mapping", "export_entity_reaction_proxy_mapping",
            "export_nodes", "export_node_reaction_context", "export_node_resolution",
            "export_cofactors", "export_containment", "export_containment_structure",
-           "export_drugs", "export_pathogens", "export_pools"]
+           "export_drugs", "export_pathogens", "export_rnas", "export_pools"]
 
 
 @pytest.fixture

tests/test_provenance_exports.py

@@ -510,3 +510,35 @@ def test_pathogen_polymer_counts_through_its_repeated_unit(monkeypatch):
     monkeypatch.setenv("LNG_PATHOGEN_PROTEIN", "1")
     assert set(neo4j_connector.get_pathogen_entities(cache)) == {"REV", "POLY", "C"}
 
+
+
+# --- rnas.csv (deltasignal specs/100) ------------------------------------------
+
+def test_export_rnas_lists_rna_species(tmp_path, monkeypatch):
+    monkeypatch.setattr(neo4j_connector, "get_rna_entities",
+                        lambda stids: {"R-HSA-MRNA": {"schema_class": "EntityWithAccessionedSequence",
+                                                      "name": "PTEN mRNA [cytosol]"}})
+    monkeypatch.setattr(neo4j_connector, "get_reactome_release", lambda: 97)
+    out = tmp_path / "rnas.csv"
+    risc = "R-HSA-RISC::variant::R-HSA-MRNA"     # a complex variant that chose the RNA
+    m.export_rnas(pd.DataFrame([{"source_id": "u-1", "target_id": "u-2"}, {"source_id": "u-3", "target_id": "u-2"}]),
+                  {"R-HSA-MRNA": "u-1", "R-HSA-P": "u-2", risc: "u-3"}, str(out))
+    df = pd.read_csv(out)
+    assert list(df.columns) == ["stable_id", "schema_class", "name", "reactome_release"]
+    assert list(df.stable_id) == ["R-HSA-MRNA"]                  # the complex variant is not listed
+
+
+def test_rna_finder_reads_the_reference_entity_class(monkeypatch):
+    seen = {}
+    class G:
+        def run(self, q, **kw):
+            seen["q"] = q
+            class R:
+                def data(self_inner):
+                    return [{"s": "R-HSA-MRNA", "c": "EntityWithAccessionedSequence", "n": "PTEN mRNA"}]
+            return R()
+    monkeypatch.setattr(neo4j_connector, "get_graph", lambda: G())
+    assert neo4j_connector.get_rna_entities({"R-HSA-MRNA", "R-HSA-P", ""}) == {
+        "R-HSA-MRNA": {"schema_class": "EntityWithAccessionedSequence", "name": "PTEN mRNA"}}
+    assert "ReferenceRNASequence" in seen["q"]
+    assert neo4j_connector.get_rna_entities(set()) == {}