feat: resolve merge conflicts with main

OpenBioML · Feb 8, 2024 · 3c6521e · 3c6521e
2 parents f5e3f10 + 768f131
commit 3c6521e
Show file tree

Hide file tree

Showing 2 changed files with 4 additions and 3 deletions.
diff --git a/data/text_sampling/preprocess_kg.py b/data/text_sampling/preprocess_kg.py
@@ -75,8 +75,8 @@
     # todo: There are some entries that have the EC number under node3_name and node3_id
     # and this is not handled yet properly.
     #    "compound_protein_go_term": [
-    #        """The {node1_type#} {SMILES#} {rel1_type#} the {node2_type#} {node2_protein_names#} which {rel2_type#} the {node3_name#}.""",  # noqa E501
-    #        """The {node1_type#} {SMILES#} {rel1_type#} the {node2_type#} {node2_protein_names#}. The {node2_type#} {node2_protein_names#} {rel2_type#} the {node3_name#}.""",  # noqa E501
+    #        """The {node1_type#} {SMILES__description} {SMILES#} {rel1_type#} the {node2_type#} {node2_protein_names#} which {rel2_type#} the {node3_name#}.""",  # noqa E501
+    #        """The {node1_type#} {SMILES__description} {SMILES#} {rel1_type#} the {node2_type#} {node2_protein_names#}. The {node2_type#} {node2_protein_names#} {rel2_type#} the {node3_name#}.""",  # noqa E501
     # ],
     "compound_protein_hpo": [
         """The {node1_type#} {SMILES#} {rel1_type#} the {node2_type#} {node2_protein_names#} and {rel2_type#} {node3_name#}.""",  # noqa E501
@@ -167,7 +167,7 @@
         """The {node1_type#} {SMILES#|node1_name#} {rel1_type#} the {node2_type#} {node2_protein_names#}. This {node2_type#} {rel2_type#} the {node3_name#}.""",  # noqa E501
     ],
     "drug_protein_hpo_disease": [
-        """The {node1_type#} {SMILES#} {rel1_type#} the {node2_type#} {node2_protein_names#}. The {node2_type#} {node2_protein_names#} {rel2_type#} {node3_name#}. The {node3_name#} {rel3_type#} the {node4_type#} {node4_name#}.""",  # noqa E501
+        """The {node1_type#} {SMILES__description} {SMILES#} {rel1_type#} the {node2_type#} {node2_protein_names#}. The {node2_type#} {node2_protein_names#} {rel2_type#} {node3_name#}. The {node3_name#} {rel3_type#} the {node4_type#} {node4_name#}.""",  # noqa E501
     ],
     "drug_protein_pathway": [
         """The {node1_type#} {SMILES#|node1_name#} {rel1_type#} the {node2_type#} {node2_protein_names#} which {rel2_type#} the {node3_name#}.""",  # noqa E501

diff --git a/data/text_sampling/text_sampling.py b/data/text_sampling/text_sampling.py
@@ -1186,6 +1186,7 @@ def apply_sampling_and_export(
         # if path.find("data/kg/compound_chebi") == -1: continue
         # if path.find("data/tabular/cyp3a4_substrate_carbonmangels") == -1: continue
         # if path.find("data/tabular/bio_ner") == -1: continue
+        # if path.find("rdkit_features") != -1: continue
 
         # exclude data_clean.csv files with more than 1GB
         if path.find("rdkit_features") != -1: