Merge pull request #472 from Knowledge-Graph-Hub/469-merge-fails-due-…

…to-error-tokenizing-data

Addressing errors in tokenizing input data

download.yaml

@@ -35,9 +35,6 @@
   # drug - target interactions from Drug Central
   url: https://unmtid-shinyapps.net/download/DrugCentral/2021_09_01/drug.target.interaction.tsv.gz
   local_name: drug.target.interaction.tsv.gz
--
-  url: http://juniper.health.unm.edu/tcrd/download/TCRDv6.12.4.tsv
-  local_name: tcrd.zip
 
 #
 # PPI from STRING DB
@@ -46,8 +43,8 @@
 
   # This is protein network data (incl. distinction: direct vs. interologs)
   # constrained to just human interactions.
-  url: https://stringdb-static.org/download/protein.links.full.v11.0/9606.protein.links.full.v11.0.txt.gz
-  local_name: 9606.protein.links.full.v11.0.txt.gz
+  url: https://stringdb-static.org/download/protein.links.full.v11.5/9606.protein.links.full.v11.5.txt.gz
+  local_name: 9606.protein.links.full.v11.5.txt.gz
 
 -
   # gene to ensembl IDs
@@ -81,7 +78,8 @@
 
 #
 # SciBite CORD-19 annotations v1.6
-#
+# As of June 2023 these are no longer available and must be retrieved from previous caches
+
 -
   url: https://media.githubusercontent.com/media/SciBiteLabs/CORD19/master/annotated-CORD-19/1.6/pdf_json_part_1.zip
   local_name: pdf_json_part_1.zip
@@ -95,6 +93,7 @@
   local_name: pmc_json.zip
 
  # SciBite CORD-19 entity co-occurrences v1.2
+ # Also a dead link
 -
   url: https://media.githubusercontent.com/media/SciBiteLabs/CORD19/master/sentence-co-occurrence-CORD-19/1.2/cv19_scc_1_2.zip
   local_name: cv19_scc_1_2.zip

kg_covid_19/transform_utils/drug_central/drug_central.py

@@ -17,7 +17,7 @@
 Ingest drug - drug target interactions from Drug Central.
 
 Essentially just ingests and transforms this file:
-http://unmtid-shinyapps.net/download/drug.target.interaction.tsv.gz
+https://unmtid-shinyapps.net/download/DrugCentral/2021_09_01/drug.target.interaction.tsv.gz
 
 And extracts Drug -> Protein interactions.
 """

kg_covid_19/transform_utils/string_ppi/string_ppi.py

@@ -141,7 +141,7 @@ def run(self, data_file: Optional[str] = None) -> None:
         """
         if not data_file:
             data_file = os.path.join(
-                self.input_base_dir, "9606.protein.links.full.v11.0.txt.gz"
+                self.input_base_dir, "9606.protein.links.full.v11.5.txt.gz"
             )
         os.makedirs(self.output_dir, exist_ok=True)
         protein_node_type = "biolink:Protein"