fix: pathway names

Author: tristan-f-r

datasets/synthetic_data/Snakefile

@@ -81,3 +81,22 @@ rule threshold:
         expand("thresholded/{threshold}/{{pathway}}/gold_standard_edges.txt", threshold=thresholds)
     shell:
         "uv run scripts/sampling.py {wildcards.pathway}"
+
+rule make_pathway_map:
+    input:
+        "raw/pathways.txt"
+    output:
+        "processed/pathway_id_mapping.tsv"
+    shell:
+        "uv run scripts/list_curated_pathways.py"
+
+for pathway in pathways:
+    rule:
+        input:
+            "processed/pathway_id_mapping.tsv",
+            "raw/pc-panther-biopax.owl"
+        output:
+            "intermediate/pathway-data/{pathway}.owl",
+            "intermediate/pathway-data/{pathway}.sif"
+        shell:
+            f"uv run scripts/fetch_pathway.py {pathway}"

datasets/synthetic_data/pathways.jsonc

@@ -1,5 +1,7 @@
 [
-    // "CCKR signaling map", TODO: not a valid pathway name?
+    // Commonly known as the "CCKR signaling map", PathwayCommons also does not map this one correctly:
+    // TODO: report to PathwayCommons: see https://apps.pathwaycommons.org/pathways?uri=https%3A%2F%2Fidentifiers.org%2Fpanther.pathway%3AP06959
+    "Gastrin_CCK2R_240212",
     "Wnt signaling pathway",
     "VEGF signaling pathway",
     "Toll receptor signaling pathway",
@@ -15,7 +17,9 @@
     "Hedgehog signaling pathway",
     "FGF signaling pathway",
     "FAS signaling pathway",
-    // "Endothelin signaling pathway", TODO: not a valid pathway name?
+    // This is actually the Endothelin signaling pathway.
+    // TODO: report to PathwayCommons: see https://apps.pathwaycommons.org/pathways?uri=https%3A%2F%2Fidentifiers.org%2Fpanther.pathway%3AP00019.
+    "untitled",
     "EGF receptor signaling pathway",
     "Cadherin signaling pathway",
     "Apoptosis signaling pathway",

pyproject.toml

@@ -28,7 +28,7 @@ line-length = 150
 exclude = ["spras"]
 
 [tool.ruff.lint]
-unfixable = ["E712"]
+extend-ignore = ["E712"]
 
 [tool.uv]
 package = true