Fix node header and other docker issues

docker/Dockerfile

@@ -25,7 +25,7 @@ RUN wget -O /sw/nodes.tsv.gz https://askem-mira.s3.amazonaws.com/dkg/$domain/bui
  neo4j-admin import --delimiter='TAB' --skip-duplicate-nodes=true --skip-bad-relationships=true --nodes /sw/nodes.tsv.gz --relationships /sw/edges.tsv.gz
 
 # Python packages
-RUN python -m pip install git+https://github.com/indralab/mira.git@main#egg=mira[web,uvicorn] && \
+RUN python -m pip install git+https://github.com/indralab/mira.git@main#egg=mira[web,uvicorn,dkg-client] && \
  python -m pip uninstall -y flask_bootstrap && \
  python -m pip uninstall -y bootstrap_flask && \
  python -m pip install bootstrap_flask

docker/Dockerfile.local

@@ -24,7 +24,7 @@ RUN sed -i 's/#dbms.default_listen_address/dbms.default_listen_address/' /etc/ne
  neo4j-admin import --delimiter='TAB' --skip-duplicate-nodes=true --skip-bad-relationships=true --nodes /sw/nodes.tsv.gz --relationships /sw/edges.tsv.gz
 
 # Python packages
-RUN python -m pip install git+https://github.com/indralab/mira.git@$branch#egg=mira[web,uvicorn] && \
+RUN python -m pip install git+https://github.com/indralab/mira.git@$branch#egg=mira[web,uvicorn,dkg-client] && \
  python -m pip uninstall -y flask_bootstrap && \
  python -m pip uninstall -y bootstrap_flask && \
  python -m pip install bootstrap_flask

mira/dkg/client.py

@@ -382,13 +382,15 @@ def get_grounder(self, prefix: Union[str, List[str]]) -> "gilda.grounder.Grounde
 
  if isinstance(prefix, str):
  prefix = [prefix]
- terms = list(
- itt.chain.from_iterable(
+ terms = [
+ term
+ for term in itt.chain.from_iterable(
  self.get_grounder_terms(p) for p in tqdm(
  prefix, desc="Caching grounding terms"
  )
  )
- )
+ if term.norm_text
+ ]
  return Grounder(terms)
 
  def get_node_counter(self) -> Counter:
@@ -598,25 +600,29 @@ def get_terms(
  from gilda.process import normalize
  from gilda.term import Term
 
- yield Term(
- norm_text=normalize(name),
- text=name,
- db=prefix,
- id=identifier,
- entry_name=name,
- status="name",
- source=prefix,
- )
- for synonym in synonyms or []:
+ norm_text = normalize(name)
+ if norm_text:
  yield Term(
- norm_text=normalize(synonym),
- text=synonym,
+ norm_text=norm_text,
+ text=name,
  db=prefix,
  id=identifier,
  entry_name=name,
- status="synonym",
+ status="name",
  source=prefix,
  )
+ for synonym in synonyms or []:
+ norm_text = normalize(synonym)
+ if norm_text:
+ yield Term(
+ norm_text=norm_text,
+ text=synonym,
+ db=prefix,
+ id=identifier,
+ entry_name=name,
+ status="synonym",
+ source=prefix,
+ )
 
 
 def build_match_clause(

mira/dkg/constants.py

@@ -12,6 +12,11 @@
  "xrefs:string[]",
  "alts:string[]",
  "version:string",
+ "property_predicates:string[]",
+ "property_values:string[]",
+ "xref_types:string[]",
+ "synonym_types:string[]",
+ "source:string",
 )
 
 #: The used for the edges files in the neo4j bulk import

setup.cfg

@@ -65,6 +65,7 @@ web =
  gilda
  click
  neo4j
+ networkx
  pystow
  tabulate
  pygraphviz