Bumped version of Uniprot mapping file and pharos class file

Sage-Bionetworks · Dec 18, 2024 · 361a8bb · 361a8bb
1 parent e33f0a0
commit 361a8bb
Show file tree

Hide file tree

Showing 3 changed files with 11 additions and 9 deletions.
diff --git a/config.yaml b/config.yaml
@@ -167,10 +167,10 @@ datasets:
           id: syn51942280.4
           format: csv
         - name: ensg_to_uniprot_mapping
-          id: syn54113663.3
+          id: syn54113663.5
           format: tsv
         - name: pharos_classes
-          id: syn64123611.1
+          id: syn64123611.2
           format: csv
       final_format: json
       custom_transformations:
@@ -203,8 +203,8 @@ datasets:
         - syn27211878.2
         - *genes_biodomains_provenance
         - syn51942280.4
-        - syn54113663.3
-        - syn64123611.1
+        - syn54113663.5
+        - syn64123611.2
       agora_rename:
         symbol: hgnc_symbol
       destination: *dest

diff --git a/data_analysis/agora/notebooks/preprocessing/AG-1388_ENSG_Uniprot_Mapping.ipynb b/data_analysis/agora/notebooks/preprocessing/AG-1388_ENSG_Uniprot_Mapping.ipynb
@@ -65,7 +65,7 @@
    "source": [
     "ensembl_ids = preprocessing_utils.get_all_adt_ensembl_ids(\n",
     "    config_filename=config_filename,\n",
-    "    exclude_files=[\"gene_metadata\", \"druggability\"],\n",
+    "    exclude_files=[\"gene_metadata\", \"ensg_to_uniprot_mapping\"],\n",
     ")\n",
     "print(\"\")\n",
     "print(str(len(ensembl_ids)) + \" Ensembl IDs found.\")"
@@ -125,6 +125,8 @@
     "mapping[\"OPTIONAL_INFORMATION\"].loc[\n",
     "    mapping[\"RESOURCE_IDENTIFIER\"].isin(targets_df[\"ensembl_gene_id\"])\n",
     "] = nomination_string\n",
+    "\n",
+    "mapping = mapping.sort_values(by=\"RESOURCE_IDENTIFIER\")\n",
     "mapping"
    ]
   },

diff --git a/test_config.yaml b/test_config.yaml
@@ -167,10 +167,10 @@ datasets:
           id: syn51942280.4
           format: csv
         - name: ensg_to_uniprot_mapping
-          id: syn54113663.3
+          id: syn54113663.5
           format: tsv
         - name: pharos_classes
-          id: syn64123611.1
+          id: syn64123611.2
           format: csv
       final_format: json
       custom_transformations:
@@ -203,8 +203,8 @@ datasets:
         - syn27211878.2
         - *genes_biodomains_provenance
         - syn51942280.4
-        - syn54113663.3
-        - syn64123611.1
+        - syn54113663.5
+        - syn64123611.2
       agora_rename:
         symbol: hgnc_symbol
       destination: *dest