add smiles to uploader keylookup

biothings · Nov 11, 2024 · e512d47 · e512d47
1 parent 22bb8d5
commit e512d47
Show file tree

Hide file tree

Showing 4 changed files with 10 additions and 5 deletions.
diff --git a/src/hub/dataload/sources/chebi/chebi_upload.py b/src/hub/dataload/sources/chebi/chebi_upload.py
@@ -26,7 +26,9 @@ class ChebiUploader(BaseDrugUploader):
     __metadata__ = {"src_meta": SRC_META}
     keylookup = MyChemKeyLookup([('inchikey', 'chebi.inchikey'),
                                  ('drugbank', 'chebi.xrefs.drugbank'),
-                                 ('chebi', 'chebi.id')], copy_from_doc=True)
+                                 ('chebi', 'chebi.id'),
+                                 ('smiles', 'chebi.smiles')],
+                                copy_from_doc=True)
 
     """
     A document with an ID from `exclusion_ids` would have a long list for one or more of the following fields:

diff --git a/src/hub/dataload/sources/chembl/chembl_upload.py b/src/hub/dataload/sources/chembl/chembl_upload.py
@@ -42,7 +42,8 @@ class ChemblUploader(BaseDrugUploader, ParallelizedSourceUploader):
          ("chembl", "chembl.molecule_chembl_id"),
          ("chebi", "chembl.chebi_par_id"),
          ("drugcentral", "chembl.xrefs.drugcentral.id"),
-         ("drugname", "chembl.pref_name")],
+         ("drugname", "chembl.pref_name"),
+         ('smiles', 'chembl.smiles')],
         # TODO:  handle duplicate keys from pubchem
         # we use RootKeyMergerStorage, but the num. duplicates is too high (>10000)
         # ("pubchem", "chembl.xrefs.pubchem.sid"),

diff --git a/src/hub/dataload/sources/drugcentral/drugcentral_upload.py b/src/hub/dataload/sources/drugcentral/drugcentral_upload.py
@@ -30,7 +30,8 @@ class DrugCentralUploader(BaseDrugUploader):
          ('drugbank', 'drugcentral.xrefs.drugbank_id'),
          ('chebi', 'drugcentral.xrefs.chebi'),
          ('chembl', 'drugcentral.xrefs.chembl_id'),
-         ('pubchem', 'drugcentral.xrefs.pubchem_cid')],
+         ('pubchem', 'drugcentral.xrefs.pubchem_cid'),
+         ('smiles', 'drugcentral.structures.smiles')],
         # ('drugname', 'drugcentral.synonyms')], # unhashable type - list
         copy_from_doc=True,
     )
@@ -41,7 +42,7 @@ def load_data(self, data_folder):
         drugcentral_docs = load_data(data_folder)
         return drugcentral_docs
 
-    @classmethod
+    @ classmethod
     def get_mapping(klass):
         mapping = {
             "drugcentral": {

diff --git a/src/hub/dataload/sources/unii/unii_upload.py b/src/hub/dataload/sources/unii/unii_upload.py
@@ -25,7 +25,8 @@ class UniiUploader(BaseDrugUploader):
 
     keylookup = MyChemKeyLookup([('inchikey', 'unii.inchikey'),
                                  ('pubchem', 'unii.pubchem'),
-                                 ('unii', 'unii.unii')],
+                                 ('unii', 'unii.unii'),
+                                 ('smiles', 'unii.smiles')],
                                 copy_from_doc=True,
                                 )