pymetadata 0.5.2__py3-none-any.whl → 0.5.4__py3-none-any.whl

pymetadata/__init__.py

@@ -3,7 +3,7 @@
 from pathlib import Path
 
 __author__ = "Matthias Koenig"
-__version__ = "0.5.2"
+__version__ = "0.5.4"
 
 
 program_name: str = "pymetadata"

pymetadata/chebi.py

@@ -1,28 +1,19 @@
 """Module for working with chebi."""
 
 from pathlib import Path
-from pprint import pprint
 from typing import Any, Dict, Optional
-
-from zeep import Client
-
+import requests
 
 import pymetadata
 from pymetadata import log
 from pymetadata.cache import DataclassJSONEncoder, read_json_cache, write_json_cache
+from pymetadata.console import console
 
 logger = log.get_logger(__name__)
 
-# FIXME: copy the file to the cache dir
-client = Client(str(pymetadata.RESOURCES_DIR / "chebi_webservice_wsdl.xml"))
-
 
 class ChebiQuery:
-    """Class to query information from ChEBI.
-
-    An overview over available methods:
-        python -mzeep https://www.ebi.ac.uk/webservices/chebi/2.0/webservice?wsdl
-    """
+    """Class to query information from ChEBI."""
 
     @staticmethod
     def query(
@@ -52,27 +43,28 @@ class ChebiQuery:
 
         # fetch and cache data
         if not data:
-            try:
-                result = client.service.getCompleteEntity(chebi)
-                # print(result)
-            except Exception:
+            response = requests.get(
+                url=f"https://www.ebi.ac.uk/chebi/backend/api/public/compounds/?chebi_ids={chebi}"
+            )
+            if response.status_code == 200:
+                result = response.json()
+            else:
                 logger.error(f"CHEBI information could not be retrieved for: {chebi}")
                 return dict()
 
-            # parse formula
-            formula = None
-            formulae = result["Formulae"]
-            if formulae:
-                formula = formulae[0]["data"]
-
+            result = result[chebi]["data"]
+            chemical_data = result["chemical_data"]
+            default_structure = result["default_structure"]
             data = {
                 "chebi": chebi,
-                "name": result["chebiAsciiName"],
+                "name": result["ascii_name"],
                 "definition": result["definition"],
-                "formula": formula,
-                "charge": result["charge"],
-                "mass": result["mass"],
-                "inchikey": result["inchiKey"],
+                "formula": chemical_data["formula"] if chemical_data else None,
+                "charge": chemical_data["charge"] if chemical_data else None,
+                "mass": chemical_data["mass"] if chemical_data else None,
+                "inchikey": default_structure["standard_inchi_key"]
+                if default_structure
+                else None,
             }
 
             logger.info(f"Write chebi: {chebi_path}")
@@ -86,7 +78,7 @@ class ChebiQuery:
 if __name__ == "__main__":
     chebis = ["CHEBI:2668", "CHEBI:138366", "CHEBI:9637", "CHEBI:155897"]
     for chebi in chebis:
-        print(chebi)
+        console.rule(chebi, align="left", style="bold white")
         d = ChebiQuery.query(chebi=chebi, cache=False)
-        pprint(d)
+        console.print(d)
         d = ChebiQuery.query(chebi=chebi, cache=True)

pymetadata/core/annotation.py

@@ -98,6 +98,8 @@ class RDFAnnotation:
                     f"{resource} does not conform to "
                     f"http(s)://identifiers.org/collection/id or http(s)://identifiers.org/id",
                 )
+
+        # handle urns
         elif resource.startswith("urn:miriam:"):
             match3 = MIRIAM_URN_PATTERN.match(resource)
             if match3:
@@ -113,13 +115,14 @@ class RDFAnnotation:
         else:
             # handle short notation
             tokens = resource.split("/")
-            if len(tokens) == 2:
+            if len(tokens) > 1:
                 self.collection = tokens[0]
                 self.term = "/".join(tokens[1:])
             elif len(tokens) == 1 and ":" in tokens[0]:
                 self.collection = tokens[0].split(":")[0].lower()
                 self.term = tokens[0]
 
+            # validation
             if len(tokens) < 2 and not self.collection:
                 logger.error(
                     f"Resource `{resource}` could not be split in collection and term. "

pymetadata/examples/cache_path_example.py

@@ -9,7 +9,6 @@ from pymetadata.chebi import ChebiQuery
 pymetadata.CACHE_PATH = Path.home() / ".cache" / "pymetadata"
 
 if __name__ == "__main__":
-
     chebis = ["CHEBI:2668", "CHEBI:138366", "CHEBI:9637", "CHEBI:155897"]
     for chebi in chebis:
         d = ChebiQuery.query(chebi=chebi, cache=True)

pymetadata/identifiers/registry.py

@@ -19,7 +19,7 @@ import requests
 import pymetadata
 from pymetadata import log
 from pymetadata.cache import DataclassJSONEncoder, read_json_cache, write_json_cache
-
+from pymetadata.console import console
 
 logger = log.get_logger(__name__)
 
@@ -123,14 +123,6 @@ def ols_namespaces() -> Dict[str, Namespace]:
 
     # Custom namespaces for OLS ontology, for simple support
     namespaces = [
-        Namespace(
-            id=None,
-            prefix="snomed",
-            pattern=r"^\d+$",
-            name="SNOMED",
-            description="SNOMED CT or SNOMED Clinical Terms is a systematically organized computer processable collection of medical terms providing codes, terms, synonyms and definitions used in clinical documentation and reporting.",
-            namespaceEmbeddedInLui=True,
-        ),
         Namespace(
             id=None,
             prefix="omim",
@@ -180,14 +172,6 @@ def ols_namespaces() -> Dict[str, Namespace]:
             description="OPMI: Ontology of Precision Medicine and Investigation",
             namespaceEmbeddedInLui=True,
         ),
-        Namespace(
-            id=None,
-            prefix="mondo",
-            pattern=r"^MONDO:\d+$",
-            name="MONDO",
-            description="MONDO",
-            namespaceEmbeddedInLui=True,
-        ),
         Namespace(
             id=None,
             prefix="atol",
@@ -237,6 +221,14 @@ def ols_namespaces() -> Dict[str, Namespace]:
             description="Measurement method ontology",
             namespaceEmbeddedInLui=True,
         ),
+        Namespace(
+            id=None,
+            prefix="symp",
+            pattern=r"^SYMP:\d+$",
+            name="Symptom ontology",
+            description="The Symptom Ontology has been developed as a standardized ontology for symptoms of human diseases.",
+            namespaceEmbeddedInLui=True,
+        ),
     ]
 
     for ns in namespaces:
@@ -344,21 +336,6 @@ class Registry:
         ns_dict = {}
         for _, data in enumerate(namespaces):
             ns = Namespace.from_dict(data)
-
-            # bugfix OLS4 (https://github.com/identifiers-org/identifiers-org.github.io/issues/231)
-            if ns.resources:
-                for resource in ns.resources:
-                    if resource.urlPattern.startswith("https://www.ebi.ac.uk/ols/"):
-                        resource.urlPattern = resource.urlPattern.replace(
-                            "/ols/", "/ols4/"
-                        )
-                    if resource.resourceHomeUrl.startswith(
-                        "https://www.ebi.ac.uk/ols/"
-                    ):
-                        resource.resourceHomeUrl = resource.resourceHomeUrl.replace(
-                            "/ols/", "/ols4/"
-                        )
-
             ns_dict[ns.prefix] = ns
 
         if custom_namespaces is not None:
@@ -394,4 +371,5 @@ class Registry:
 REGISTRY = Registry()
 
 if __name__ == "__main__":
-    registry = Registry()
+    registry = Registry(cache=False)
+    console.print(registry.ns_dict)