Merge pull request #237 from Knowledge-Graph-Hub/transform_naming_fixes

Fix bactotraits source name, update rhea_mappings, use constants when…
Knowledge-Graph-Hub · Aug 30, 2024 · f2a75e7 · f2a75e7
2 parents 60e2165 + 99ceab5
commit f2a75e7
Show file tree

Hide file tree

Showing 7 changed files with 35 additions and 33 deletions.
diff --git a/hpc/run_parallel_transform.slurm b/hpc/run_parallel_transform.slurm
@@ -26,7 +26,7 @@ transforms=(
     bacdive
     mediadive
     madin_etal
-    rheamappings
+    rhea_mappings
     bactotraits
     uniprot_human
     ctd

diff --git a/kg_microbe/transform_utils/bactotraits/bactotraits.py b/kg_microbe/transform_utils/bactotraits/bactotraits.py
@@ -15,6 +15,7 @@
     BACDIVE_ID_COLUMN,
     BACDIVE_PREFIX,
     BACDIVE_TMP_DIR,
+    BACTOTRAITS,
     BACTOTRAITS_TMP_DIR,
     BIOLOGICAL_PROCESS,
     CAPABLE_OF_PREDICATE,
@@ -157,7 +158,7 @@ def __init__(
         self, input_dir: Optional[Union[str, Path]], output_dir: Optional[Union[str, Path]]
     ):
         """Initialize BactoTraitsTransform."""
-        source_name = "BactoTraits"
+        source_name = BACTOTRAITS
         super().__init__(source_name, input_dir, output_dir)
         self.ncbi_impl = get_adapter(f"sqlite:{NCBITAXON_SOURCE}")
 

diff --git a/kg_microbe/transform_utils/constants.py b/kg_microbe/transform_utils/constants.py
@@ -8,7 +8,7 @@
 BACDIVE = "bacdive"
 MEDIADIVE = "mediadive"
 BACTOTRAITS = "bactotraits"
-RHEAMAPPINGS = "rheamappings"
+RHEAMAPPINGS = "rhea_mappings"
 ONTOLOGIES = "ontologies"
 WALLEN_ETAL = "wallen_etal"
 CTD = "ctd"

diff --git a/kg_microbe/transform_utils/ctd/ctd.py b/kg_microbe/transform_utils/ctd/ctd.py
@@ -16,6 +16,7 @@
     CHEBI_XREFS_FILEPATH,
     CHEMICAL_CATEGORY,
     CHEMICAL_TO_DISEASE_EDGE,
+    CTD,
     CTD_CAS_RN_COLUMN,
     CTD_CHEMICAL_MESH_COLUMN,
     CTD_DISEASE_MESH_COLUMN,
@@ -53,7 +54,7 @@ def __init__(self, input_dir: Optional[Path] = None, output_dir: Optional[Path]
                            If None, a default directory may be used.
         :type output_dir: Optional[Path]
         """
-        source_name = "ctd"
+        source_name = CTD
         super().__init__(source_name, input_dir, output_dir)
 
     def run(self, data_file: Union[Optional[Path], Optional[str]] = None, show_status: bool = True):
@@ -221,7 +222,7 @@ def _get_nodes_and_edges(self, data):
                     CHEMICAL_TO_DISEASE_EDGE,
                     disease,
                     RELATIONS_DICT[CHEMICAL_TO_DISEASE_EDGE],
-                    "ctd",
+                    self.source_name,
                 ]
             )
         return node_data, edge_data
diff --git a/.../transform_utils/rheamappings/__init__.py → ...transform_utils/rhea_mappings/__init__.py b/.../transform_utils/rheamappings/__init__.py → ...transform_utils/rhea_mappings/__init__.py
diff --git a/...nsform_utils/rheamappings/rheamappings.py → ...sform_utils/rhea_mappings/rheamappings.py b/...nsform_utils/rheamappings/rheamappings.py → ...sform_utils/rhea_mappings/rheamappings.py
diff --git a/merge.yaml b/merge.yaml
@@ -64,47 +64,47 @@ merged_graph:
           - data/transformed/ontologies/ec_nodes.tsv
           - data/transformed/ontologies/ec_edges.tsv
     bacdive:
-      name: "BacDive"
+      name: "bacdive"
       input:
         format: tsv
         filename:
-          - data/transformed/BacDive/nodes.tsv
-          - data/transformed/BacDive/edges.tsv
+          - data/transformed/bacdive/nodes.tsv
+          - data/transformed/bacdive/edges.tsv
     mediadive:
-      name: "MediaDive"
+      name: "mediadive"
       input:
         format: tsv
         filename:
-          - data/transformed/MediaDive/nodes.tsv
-          - data/transformed/MediaDive/edges.tsv
+          - data/transformed/mediadive/nodes.tsv
+          - data/transformed/mediadive/edges.tsv
     rhea_mappings:
-      name: "RheaMappings"
+      name: "rhea_mappings"
       input:
         format: tsv
         filename:
-          - data/transformed/RheaMappings/nodes.tsv
-          - data/transformed/RheaMappings/edges.tsv
+          - data/transformed/rhea_mappings/nodes.tsv
+          - data/transformed/rhea_mappings/edges.tsv
     upa:
       input:
         name: "upa"
         format: tsv
         filename:
           - data/transformed/ontologies/upa_nodes.tsv
           - data/transformed/ontologies/upa_edges.tsv
-    traits:
+    madin_etal:
       input:
-        name: "traits"
+        name: "madin_etal"
         format: tsv
         filename:
-          - data/transformed/traits/nodes.tsv
-          - data/transformed/traits/edges.tsv
+          - data/transformed/madin_etal/nodes.tsv
+          - data/transformed/madin_etal/edges.tsv
     bactotraits:
       input:
-        name: "BactoTraits"
+        name: "bactotraits"
         format: tsv
         filename:
-          - data/transformed/BactoTraits/nodes.tsv
-          - data/transformed/BactoTraits/edges.tsv
+          - data/transformed/bactotraits/nodes.tsv
+          - data/transformed/bactotraits/edges.tsv
     # ctd:
     #   input:
     #     name: "ctd"
@@ -119,28 +119,28 @@ merged_graph:
     #     filename:
     #       - data/transformed/disbiome/nodes.tsv
     #       - data/transformed/disbiome/edges.tsv
-    # pdmetagenomics:
+    # wallen_etal:
     #   input:
-    #     name: "PdMetagenomics"
+    #     name: "wallen_etal"
     #     format: tsv
     #     filename:
-    #       - data/transformed/PdMetagenomics/nodes.tsv
-    #       - data/transformed/PdMetagenomics/edges.tsv
+    #       - data/transformed/wallen_etal/nodes.tsv
+    #       - data/transformed/wallen_etal/edges.tsv
     # Not feasible using kgx merge process
-    # uniprot_genome_features:
+    # uniprot_functional_microbes:
     #   input:
-    #     name: "uniprot_genome_features"
+    #     name: "uniprot_functional_microbes"
     #     format: tsv
     #     filename:
-    #       - data/transformed/uniprot_genome_features/nodes.tsv
-    #       - data/transformed/uniprot_genome_features/edges.tsv
-    # uniprot_genome_features_human:
+    #       - data/transformed/uniprot_functional_microbes/nodes.tsv
+    #       - data/transformed/uniprot_functional_microbes/edges.tsv
+    # uniprot_human:
     #   input:
-    #     name: "uniprot_genome_features_human"
+    #     name: "uniprot_human"
     #     format: tsv
     #     filename:
-    #       - data/transformed/uniprot_genome_features_human/nodes.tsv
-    #       - data/transformed/uniprot_genome_features_human/edges.tsv
+    #       - data/transformed/uniprot_human/nodes.tsv
+    #       - data/transformed/uniprot_human/edges.tsv
   operations:
     - name: kgx.graph_operations.summarize_graph.generate_graph_stats
       args: