pymetadata 0.5.4__py3-none-any.whl → 0.5.5__py3-none-any.whl

pymetadata/__init__.py

@@ -3,7 +3,7 @@
 from pathlib import Path
 
 __author__ = "Matthias Koenig"
-__version__ = "0.5.4"
+__version__ = "0.5.5"
 
 
 program_name: str = "pymetadata"

pymetadata/core/annotation.py

@@ -5,12 +5,14 @@ Core data structure to store annotations.
 
 import re
 import urllib
+from enum import Enum
 from pprint import pprint
 from typing import Any, Dict, Final, List, Optional, Tuple, Union
 
 import requests
 
 from pymetadata import log
+from pymetadata.console import console
 from pymetadata.core.xref import CrossReference, is_url
 from pymetadata.identifiers.miriam import BQB, BQM
 from pymetadata.identifiers.registry import REGISTRY
@@ -19,19 +21,31 @@ from pymetadata.ontologies.ols import ONTOLOGIES, OLSQuery
 
 OLS_QUERY = OLSQuery(ontologies=ONTOLOGIES)
 
-IDENTIFIERS_ORG_PREFIX: Final = "http://identifiers.org"
+IDENTIFIERS_ORG_PREFIX: Final = "https://identifiers.org"
 IDENTIFIERS_ORG_PATTERN1: Final = re.compile(r"^https?://identifiers.org/(.+?)/(.+)")
 IDENTIFIERS_ORG_PATTERN2: Final = re.compile(r"^https?://identifiers.org/(.+)")
+
+BIOREGISTRY_PREFIX: Final = "https://bioregistry.io"
+BIOREGISTRY_PATTERN: Final = re.compile(r"^https?://bioregistry.io/(.+)")
+
 MIRIAM_URN_PATTERN: Final = re.compile(r"^urn:miriam:(.+)")
 
 logger = log.get_logger(__name__)
 
 
+class ProviderType(str, Enum):
+    """Provider type."""
+
+    IDENTIFIERS_ORG = "identifiers.org"
+    BIOREGISTRY_IO = "bioregistry.io"
+    NONE = "none"
+
+
 class RDFAnnotation:
     """RDFAnnotation class.
 
     Basic storage of annotation information. This consists of the relation
-    and the the resource.
+    and the resource.
     The annotations can be attached to other objects thereby forming
     triples which can be converted to RDF.
 
@@ -40,6 +54,7 @@ class RDFAnnotation:
         - `collection/term`, i.e., the combination of collection and term
         - `http(s)://arbitrary.url`, an arbitrary URL
         - urn:miriam:uniprot:P03023
+        - https://bioregistry.io/chebi:15996 urls via the bioregistry provider
     """
 
     replaced_collections: Dict[str, str] = {
@@ -53,6 +68,7 @@ class RDFAnnotation:
         self.collection: Optional[str] = None
         self.term: Optional[str] = None
         self.resource: str = resource
+        self.provider: ProviderType = ProviderType.IDENTIFIERS_ORG
 
         if not qualifier:
             raise ValueError(
@@ -75,15 +91,19 @@ class RDFAnnotation:
             if match1:
                 # handle identifiers.org pattern
                 self.collection, self.term = match1.group(1), match1.group(2)
+                self.provider = ProviderType.IDENTIFIERS_ORG
 
             if not self.collection:
-                # tests new short pattern
+                # tests new compact patterns
                 match2 = IDENTIFIERS_ORG_PATTERN2.match(resource)
                 if match2:
                     tokens = match2.group(1).split(":")
                     if len(tokens) == 2:
                         self.collection = tokens[0].lower()
+
+                        # check if the namespace is embedded
                         self.term = match2.group(1)
+                        self.provider = ProviderType.IDENTIFIERS_ORG
                     else:
                         logger.warning(
                             f"Identifiers.org URL does not conform to new"
@@ -94,10 +114,16 @@ class RDFAnnotation:
                 # other urls are directly stored as resources without collection
                 self.collection = None
                 self.term = resource
-                logger.debug(
-                    f"{resource} does not conform to "
-                    f"http(s)://identifiers.org/collection/id or http(s)://identifiers.org/id",
-                )
+                if BIOREGISTRY_PATTERN.match(resource):
+                    self.provider = ProviderType.BIOREGISTRY_IO
+                    console.print(self.provider)
+                else:
+                    self.provider = ProviderType.NONE
+                    logger.warning(
+                        f"{resource} does not conform to "
+                        f"http(s)://identifiers.org/collection/id or http(s)://identifiers.org/id or "
+                        f"https://bioregistry.io/id .",
+                    )
 
         # handle urns
         elif resource.startswith("urn:miriam:"):
@@ -106,6 +132,7 @@ class RDFAnnotation:
                 tokens = match3.group(1).split(":")
                 self.collection = tokens[0]
                 self.term = ":".join(tokens[1:]).replace("%3A", ":")
+                self.provider = ProviderType.IDENTIFIERS_ORG
 
                 logger.warning(
                     f"Deprecated urn pattern `{resource}` updated: "
@@ -118,9 +145,11 @@ class RDFAnnotation:
             if len(tokens) > 1:
                 self.collection = tokens[0]
                 self.term = "/".join(tokens[1:])
+                self.provider = ProviderType.IDENTIFIERS_ORG
             elif len(tokens) == 1 and ":" in tokens[0]:
                 self.collection = tokens[0].split(":")[0].lower()
                 self.term = tokens[0]
+                self.provider = ProviderType.IDENTIFIERS_ORG
 
             # validation
             if len(tokens) < 2 and not self.collection:
@@ -132,6 +161,13 @@ class RDFAnnotation:
                 )
                 self.collection = None
                 self.term = resource
+                self.provider = ProviderType.NONE
+
+        # shorten compact terms
+        if self.term and self.collection:
+            self.term = self.shorten_compact_term(
+                term=self.term, collection=self.collection
+            )
 
         # clean legacy collections
         if self.collection in self.replaced_collections:
@@ -139,6 +175,21 @@ class RDFAnnotation:
 
         self.validate()
 
+    @staticmethod
+    def shorten_compact_term(term: str, collection: str) -> str:
+        """Shorten the compact terms and return term.
+
+        If the namespace is not embeddd in the term return the shortened term.
+        """
+        namespace = REGISTRY.ns_dict.get(collection, None)
+        if namespace and not namespace.namespaceEmbeddedInLui:
+            # shorter term
+            if term.lower().startswith(collection):
+                tokens = term.split(":")
+                term = ":".join(tokens[1:])
+
+        return term
+
     @staticmethod
     def from_tuple(t: Tuple[Union[BQB, BQM], str]) -> "RDFAnnotation":
         """Construct from tuple."""
@@ -164,12 +215,12 @@ class RDFAnnotation:
 
     def __repr__(self) -> str:
         """Get representation string."""
-        return f"RDFAnnotation({self.qualifier}|{self.collection}|{self.term})"
+        return f"RDFAnnotation({self.qualifier}|{self.collection}|{self.term}|{self.provider.value})"
 
     def to_dict(self) -> Dict:
         """Convert to dict."""
         return {
-            "qualifier": self.qualifier.value,  # FIXME use enums!
+            "qualifier": self.qualifier.value,
             "collection": self.collection,
             "term": self.term,
         }
@@ -346,52 +397,59 @@ class RDFAnnotationData(RDFAnnotation):
 
 if __name__ == "__main__":
     for annotation in [
-        # FIXME: support this
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF,
-            resource="NCIT:C75913",
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF,
-            resource="taxonomy/562",
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF,
-            resource="http://identifiers.org/taxonomy/9606",
-        ),
         RDFAnnotation(
             qualifier=BQB.IS_VERSION_OF,
-            resource="http://identifiers.org/biomodels.sbo/SBO:0000247",
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF, resource="urn:miriam:obo.go:GO%3A0005623"
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF, resource="urn:miriam:chebi:CHEBI%3A33699"
-        ),
-        RDFAnnotation(qualifier=BQB.IS_VERSION_OF, resource="chebi/CHEBI:456215"),
-        RDFAnnotation(
-            qualifier=BQB.IS, resource="https://en.wikipedia.org/wiki/Cytosol"
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF, resource="urn:miriam:uniprot:P03023"
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF,
-            resource="http://identifiers.org/go/GO:0005829",
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF, resource="http://identifiers.org/go/GO:0005829"
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF, resource="http://identifiers.org/GO:0005829"
-        ),
-        RDFAnnotation(
-            qualifier=BQB.IS_VERSION_OF, resource="http://identifiers.org/GO:0005829"
+            resource="https://bioregistry.io/chebi:15996",
         ),
-        RDFAnnotation(qualifier=BQB.IS_VERSION_OF, resource="bto/BTO:0000089"),
-        RDFAnnotation(qualifier=BQB.IS_VERSION_OF, resource="BTO:0000089"),
-        RDFAnnotation(qualifier=BQB.IS_VERSION_OF, resource="chebi/CHEBI:000012"),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF,
+        #     resource="NCIT:C75913",
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF,
+        #     resource="ncit:C75913",
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF,
+        #     resource="taxonomy/562",
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF,
+        #     resource="http://identifiers.org/taxonomy/9606",
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF,
+        #     resource="http://identifiers.org/biomodels.sbo/SBO:0000247",
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF, resource="urn:miriam:obo.go:GO%3A0005623"
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF, resource="urn:miriam:chebi:CHEBI%3A33699"
+        # ),
+        # RDFAnnotation(qualifier=BQB.IS_VERSION_OF, resource="chebi/CHEBI:456215"),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS, resource="https://en.wikipedia.org/wiki/Cytosol"
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF, resource="urn:miriam:uniprot:P03023"
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF,
+        #     resource="http://identifiers.org/go/GO:0005829",
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF, resource="http://identifiers.org/go/GO:0005829"
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF, resource="http://identifiers.org/GO:0005829"
+        # ),
+        # RDFAnnotation(
+        #     qualifier=BQB.IS_VERSION_OF, resource="http://identifiers.org/GO:0005829"
+        # ),
+        # RDFAnnotation(qualifier=BQB.IS_VERSION_OF, resource="bto/BTO:0000089"),
+        # RDFAnnotation(qualifier=BQB.IS_VERSION_OF, resource="BTO:0000089"),
+        # RDFAnnotation(qualifier=BQB.IS_VERSION_OF, resource="chebi/CHEBI:000012"),
     ]:
         print("-" * 80)
         data = RDFAnnotationData(annotation)

pymetadata/identifiers/registry.py

@@ -88,195 +88,6 @@ class Namespace:
             self.resources = list()
 
 
-def ols_namespaces() -> Dict[str, Namespace]:
-    """Define Ontologies available from OLS but not in identifiers.org."""
-    ols_info: Dict = {
-        "deprecated": False,
-        "deprecationDate": None,
-        "institution": {
-            "description": "At EMBL-EBI, we make the "
-            "world’s public biological data "
-            "freely available to the "
-            "scientific community via a "
-            "range of services and tools, "
-            "perform basic research and "
-            "provide professional training "
-            "in bioinformatics. \n"
-            "We are part of the European "
-            "Molecular Biology Laboratory "
-            "(EMBL), an international, "
-            "innovative and "
-            "interdisciplinary research "
-            "organisation funded by 26 "
-            "member states and two "
-            "associate member states.",
-            "homeUrl": "https://www.ebi.ac.uk",
-            "id": 2,
-            "location": {"countryCode": "GB", "countryName": "United Kingdom"},
-            "name": "European Bioinformatics Institute",
-            "rorId": "https://ror.org/02catss52",
-        },
-        "location": {"countryCode": "GB", "countryName": "United Kingdom"},
-        "official": False,
-        "providerCode": "ols",
-    }
-
-    # Custom namespaces for OLS ontology, for simple support
-    namespaces = [
-        Namespace(
-            id=None,
-            prefix="omim",
-            pattern=r"^MI:\d+$",
-            name="OMIM",
-            description="Molecular Interactions Controlled Vocabulary",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="dron",
-            pattern=r"^DRON:\d+$",
-            name="DRON",
-            description="The drug ontology",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="cmo",
-            pattern=r"^CMO:\d+$",
-            name="Chemical methods ontology",
-            description="Morphological and physiological measurement records "
-            "generated from clinical and model organism research and health programs.",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="chmo",
-            pattern=r"^CHMO:\d+$",
-            name="Chemical methods ontology",
-            description="CHMO, the chemical methods ontology",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="vto",
-            pattern=r"^VTO:\d+$",
-            name="Vertebrate Taxonomy Ontology",
-            description="VTO Vertebrate Taxonomy Ontology",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="opmi",
-            pattern=r"^OPMI:\d+$",
-            name="Ontology of Precision Medicine and Investigation",
-            description="OPMI: Ontology of Precision Medicine and Investigation",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="atol",
-            pattern=r"^ATOL:\d+$",
-            name="ATOL",
-            description="Animal Trait Ontology for Livestock",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="nbo",
-            pattern=r"^NBO:\d+$",
-            name="NBO",
-            description="Neuro Behavior Ontology",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="scdo",
-            pattern=r"^SCDO:\d+$",
-            name="Sickle Cell Disease Ontology",
-            description="Sickle Cell Disease Ontology",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="fix",
-            pattern=r"^FIX:\d+$",
-            name="Physico-chemical methods and properties Ontology",
-            description="Physico-chemical methods and properties Ontology",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="oba",
-            pattern=r"^OBA:\d+$",
-            name="Ontology of Biological Attributes",
-            description="PubChem is an open chemistry database at the National "
-            "Institutes of Health (NIH).",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="mmo",
-            pattern=r"^MMO:\d+$",
-            name="Measurement method ontology",
-            description="Measurement method ontology",
-            namespaceEmbeddedInLui=True,
-        ),
-        Namespace(
-            id=None,
-            prefix="symp",
-            pattern=r"^SYMP:\d+$",
-            name="Symptom ontology",
-            description="The Symptom Ontology has been developed as a standardized ontology for symptoms of human diseases.",
-            namespaceEmbeddedInLui=True,
-        ),
-    ]
-
-    for ns in namespaces:
-        if not ns.resources:
-            ns.resources = []
-        if not ns.prefix:
-            continue
-        ns.resources.append(
-            Resource(
-                id=None,
-                name=f"{ns.prefix} through OLS",
-                description=f"{ns.prefix} through OLS",
-                mirId=None,
-                sampleId=None,
-                resourceHomeUrl=None,
-                urlPattern=f"https://www.ebi.ac.uk/ols4/ontologies/{ns.prefix}/terms?obo_id={ns.prefix.upper()}"
-                + ":{$id}",
-                **ols_info,
-            )
-        )
-
-    return {ns.prefix: ns for ns in namespaces}  # type: ignore
-
-
-def misc_namespaces() -> Dict[str, Namespace]:
-    """Define misc namespaces."""
-    namespaces = [
-        Namespace(
-            id="brenda.ligand",
-            pattern=r"^\d+$",
-            name="BRENDA Ligand",
-            prefix=None,
-            description="BRENDA Ligand Information",
-            namespaceEmbeddedInLui=False,
-        ),
-        Namespace(
-            id="metabolights.compound",
-            pattern=r"^MTBLC\d+$",
-            name="Metabolights compound",
-            prefix=None,
-            description="metabolights compound",
-            namespaceEmbeddedInLui=False,
-        ),
-    ]
-
-    return {ns.id: ns for ns in namespaces}  # type: ignore
-
-
 class Registry:
     """Managing the available annotation information.
 
@@ -284,10 +95,6 @@ class Registry:
     """
 
     URL = "https://registry.api.identifiers.org/resolutionApi/getResolverDataset"
-    CUSTOM_NAMESPACES = {
-        **ols_namespaces(),
-        **misc_namespaces(),
-    }
 
     def __init__(
         self,
@@ -325,7 +132,6 @@ class Registry:
 
     @staticmethod
     def update_registry(
-        custom_namespaces: Dict[str, Namespace] = CUSTOM_NAMESPACES,
         registry_path: Optional[Path] = None,
     ) -> Dict[str, Namespace]:
         """Update registry from identifiers.org webservice."""
@@ -338,14 +144,6 @@ class Registry:
             ns = Namespace.from_dict(data)
             ns_dict[ns.prefix] = ns
 
-        if custom_namespaces is not None:
-            for key, ns in custom_namespaces.items():
-                if key in ns_dict:
-                    logger.error(
-                        f"Namespace with key '{key}' exists in MIRIAM. Overwrite namespace!"
-                    )
-                ns_dict[key] = ns
-
         if registry_path is not None:
             write_json_cache(
                 data=ns_dict,