pyobo 0.11.2__py3-none-any.whl → 0.12.0__py3-none-any.whl

pyobo/sources/uniprot/uniprot.py

@@ -1,9 +1,8 @@
 """Converter for UniProt."""
 
 from collections.abc import Iterable
-from operator import attrgetter
 from pathlib import Path
-from typing import Optional, cast
+from typing import cast
 
 from tqdm.auto import tqdm
 
@@ -11,7 +10,17 @@ from pyobo import Obo, Reference
 from pyobo.api.utils import get_version
 from pyobo.constants import RAW_MODULE
 from pyobo.identifier_utils import standardize_ec
-from pyobo.struct import Term, derives_from, enables, from_species, participates_in
+from pyobo.struct import (
+    Term,
+    TypeDef,
+    _parse_str_or_curie_or_uri,
+    default_reference,
+    derives_from,
+    enables,
+    from_species,
+    has_citation,
+    participates_in,
+)
 from pyobo.struct.typedef import gene_product_of, located_in, molecularly_interacts_with
 from pyobo.utils.io import open_reader
 
@@ -43,6 +52,7 @@ PARAMS = {
     "query": QUERY,
     "fields": FIELDS,
 }
+IS_REVIEWED = TypeDef(reference=default_reference(PREFIX, "reviewed"), is_metadata_tag=True)
 
 
 class UniProtGetter(Obo):
@@ -57,6 +67,8 @@ class UniProtGetter(Obo):
         molecularly_interacts_with,
         derives_from,
         located_in,
+        IS_REVIEWED,
+        has_citation,
     ]
 
     def iter_terms(self, force: bool = False) -> Iterable[Term]:
@@ -64,12 +76,7 @@ class UniProtGetter(Obo):
         yield from iter_terms(version=self._version_or_raise)
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get UniProt as OBO."""
-    return UniProtGetter(force=force)
-
-
-def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
+def iter_terms(version: str | None = None) -> Iterable[Term]:
     """Iterate over UniProt Terms."""
     with open_reader(ensure(version=version)) as reader:
         _ = next(reader)  # header
@@ -89,7 +96,7 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
             go_processes,
             bindings,
             description,
-        ) in tqdm(reader, desc="Mapping UniProt", unit_scale=True):
+        ) in tqdm(reader, desc=f"[{PREFIX}] mapping", unit_scale=True):
             if description:
                 description = description.removeprefix("FUNCTION: ")
             term = Term(
@@ -99,19 +106,19 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
             term.set_species(taxonomy_id)
             if gene_ids:
                 for gene_id in gene_ids.split(";"):
-                    term.append_relationship(
-                        gene_product_of, Reference(prefix="ncbigene", identifier=gene_id.strip())
-                    )
+                    if gene_id := gene_id.strip():
+                        term.annotate_object(
+                            gene_product_of, Reference(prefix="ncbigene", identifier=gene_id)
+                        )
 
-            # TODO add type=Reference(prefix="xsd", identifier="boolean")
-            term.append_property("reviewed", "true")
+            term.annotate_boolean(IS_REVIEWED, True)
 
             for go_process_ref in _parse_go(go_processes):
-                term.append_relationship(participates_in, go_process_ref)
+                term.annotate_object(participates_in, go_process_ref)
             for go_function_ref in _parse_go(go_functions):
-                term.append_relationship(enables, go_function_ref)
+                term.annotate_object(enables, go_function_ref)
             for go_component_ref in _parse_go(go_components):
-                term.append_relationship(located_in, go_component_ref)
+                term.annotate_object(located_in, go_component_ref)
 
             if proteome:
                 uniprot_proteome_id = proteome.split(":")[0]
@@ -122,11 +129,11 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
 
             if rhea_curies:
                 for rhea_curie in rhea_curies.split(" "):
-                    term.append_relationship(
+                    term.annotate_object(
                         # FIXME this needs a different relation than enables
                         #  see https://github.com/biopragmatics/pyobo/pull/168#issuecomment-1918680152
                         enables,
-                        cast(Reference, Reference.from_curie(rhea_curie, strict=True)),
+                        cast(Reference, _parse_str_or_curie_or_uri(rhea_curie, strict=True)),
                     )
 
             if bindings:
@@ -136,22 +143,23 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
                     if part.startswith("/ligand_id"):
                         curie = part.removeprefix('/ligand_id="').rstrip('"')
                         binding_references.add(
-                            cast(Reference, Reference.from_curie(curie, strict=True))
+                            cast(Reference, _parse_str_or_curie_or_uri(curie, strict=True))
                         )
-                for binding_reference in sorted(binding_references, key=attrgetter("curie")):
-                    term.append_relationship(molecularly_interacts_with, binding_reference)
+                for binding_reference in sorted(binding_references):
+                    term.annotate_object(molecularly_interacts_with, binding_reference)
 
             if ecs:
                 for ec in ecs.split(";"):
-                    term.append_relationship(
-                        enables, Reference(prefix="eccode", identifier=standardize_ec(ec))
-                    )
+                    if ec := ec.strip():
+                        term.annotate_object(
+                            enables, Reference(prefix="ec", identifier=standardize_ec(ec))
+                        )
             for pubmed in pubmeds.split(";"):
-                if pubmed:
-                    term.append_provenance(Reference(prefix="pubmed", identifier=pubmed.strip()))
+                if pubmed := pubmed.strip():
+                    term.append_provenance(Reference(prefix="pubmed", identifier=pubmed))
             for pdb in pdbs.split(";"):
-                if pdb:
-                    term.append_xref(Reference(prefix="pdb", identifier=pdb.strip()))
+                if pdb := pdb.strip():
+                    term.append_xref(Reference(prefix="pdb", identifier=pdb))
             yield term
 
 
@@ -164,10 +172,10 @@ def _parse_go(go_terms) -> list[Reference]:
     return rv
 
 
-def ensure(version: Optional[str] = None, force: bool = False) -> Path:
+def ensure(version: str | None = None, force: bool = False) -> Path:
     """Ensure the reviewed uniprot names are available."""
     if version is None:
-        version = get_version("uniprot")
+        version = get_version("uniprot", strict=True)
     return RAW_MODULE.ensure(
         PREFIX,
         version,

pyobo/sources/uniprot/uniprot_ptm.py

@@ -1,38 +1,13 @@
-"""Converter for UniProt PTMs.
-
-Line code  Content                         Occurrence in an entry
----------  ---------------------------     ------------------------------
-ID         Identifier (FT description)     Once; starts a PTM entry
-AC         Accession (PTM-xxxx)            Once
-FT         Feature key                     Once
-TG         Target                          Once; two targets separated by
-                                           a dash in case of intrachain
-                                           crosslinks
-PA         Position of the modification    Optional; once
-           on the amino acid
-PP         Position of the modification    Optional; once
-           in the polypeptide
-CF         Correction formula              Optional; once
-MM         Monoisotopic mass difference    Optional; once
-MA         Average mass difference         Optional; once
-LC         Cellular location               Optional; once; alternatives
-                                           can be proposed
-TR         Taxonomic range                 Optional; once or more
-KW         Keyword                         Optional; once or more
-DR         Cross-reference to external     Optional; once or more
-           databases
-//         Terminator                      Once; ends an entr
-
-"""
+"""Converter for UniProt PTMs."""
 
 import itertools as itt
 from collections import defaultdict
 from collections.abc import Iterable, Mapping
-from typing import Optional
 
 from tqdm.auto import tqdm
 
 from pyobo import Obo, Reference, Term
+from pyobo.struct import _parse_str_or_curie_or_uri
 from pyobo.utils.path import ensure_path
 
 __all__ = [
@@ -54,11 +29,6 @@ class UniProtPtmGetter(Obo):
         yield from iter_terms(force=force)
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get UniProt PTMs as OBO."""
-    return UniProtPtmGetter(force=force)
-
-
 def iter_terms(force: bool = False) -> Iterable[Term]:
     """Iterate over UniProt PTM Terms."""
     path = ensure_path(PREFIX, url=URL, force=force)
@@ -71,7 +41,7 @@ def iter_terms(force: bool = False) -> Iterable[Term]:
             yield term
 
 
-def _parse(i, lines: Iterable[tuple[str, str]]) -> Optional[Term]:
+def _parse(i, lines: Iterable[tuple[str, str]]) -> Term | None:
     dd_: defaultdict[str, list[str]] = defaultdict(list)
     for key, value in lines:
         dd_[key].append(value)
@@ -97,7 +67,7 @@ def _parse(i, lines: Iterable[tuple[str, str]]) -> Optional[Term]:
             if line.startswith(y):
                 line = x + line[len(y) :]
 
-        ref = Reference.from_curie(line.replace("; ", ":"))
+        ref = _parse_str_or_curie_or_uri(line.replace("; ", ":"))
         if ref:
             term.append_xref(ref)
         else:

pyobo/sources/utils.py

@@ -2,6 +2,7 @@
 
 import logging
 from collections.abc import Mapping
+from pathlib import Path
 
 from ..utils.io import multisetdict
 
@@ -13,9 +14,9 @@ __all__ = [
 logger = logging.getLogger(__name__)
 
 
-def get_go_mapping(path: str, prefix: str) -> Mapping[str, set[tuple[str, str]]]:
+def get_go_mapping(path: Path, prefix: str) -> Mapping[str, set[tuple[str, str]]]:
     """Get a GO mapping file."""
-    with open(path) as file:
+    with path.open() as file:
         return multisetdict(
             process_go_mapping_line(line.strip(), prefix=prefix) for line in file if line[0] != "!"
         )

pyobo/sources/wikipathways.py

@@ -1,9 +1,11 @@
 """Converter for WikiPathways."""
 
 import logging
-import urllib.error
 from collections.abc import Iterable
 
+from pystow.utils import DownloadError
+from tqdm import tqdm
+
 from .gmt_utils import parse_wikipathways_gmt
 from ..constants import SPECIES_REMAPPING
 from ..struct import Obo, Reference, Term, from_species
@@ -51,21 +53,16 @@ class WikiPathwaysGetter(Obo):
         return iter_terms(version=self._version_or_raise)
 
 
-def get_obo() -> Obo:
-    """Get WikiPathways as OBO."""
-    return WikiPathwaysGetter()
-
-
 def iter_terms(version: str) -> Iterable[Term]:
     """Get WikiPathways terms."""
     base_url = f"http://data.wikipathways.org/{version}/gmt/wikipathways-{version}-gmt"
 
-    for species_code, taxonomy_id in _PATHWAY_INFO:
+    for species_code, taxonomy_id in tqdm(_PATHWAY_INFO, desc=f"[{PREFIX}]", unit="species"):
         url = f"{base_url}-{species_code}.gmt"
         try:
             path = ensure_path(PREFIX, url=url, version=version)
-        except urllib.error.HTTPError as e:
-            logger.warning("HTTP %s error when downloading WikiPathways file %s", e.code, url)
+        except DownloadError as e:
+            tqdm.write(f"[{PREFIX}] {e}")
             continue
         species_code = species_code.replace("_", " ")
         taxonomy_name = SPECIES_REMAPPING.get(species_code, species_code)
@@ -74,7 +71,7 @@ def iter_terms(version: str) -> Iterable[Term]:
             term = Term(reference=Reference(prefix=PREFIX, identifier=identifier, name=name))
             term.set_species(taxonomy_id, taxonomy_name)
             for ncbigene_id in genes:
-                term.append_relationship(
+                term.annotate_object(
                     has_participant,
                     Reference(prefix="ncbigene", identifier=ncbigene_id),
                 )

pyobo/sources/zfin.py

@@ -3,7 +3,6 @@
 import logging
 from collections import defaultdict
 from collections.abc import Iterable
-from typing import Optional
 
 from tqdm.auto import tqdm
 
@@ -12,6 +11,7 @@ from pyobo.struct import (
     Obo,
     Reference,
     Term,
+    _parse_str_or_curie_or_uri,
     from_species,
     has_gene_product,
     orthologous,
@@ -48,11 +48,6 @@ class ZFINGetter(Obo):
         return get_terms(force=force, version=self._version_or_raise)
 
 
-def get_obo(force: bool = False) -> Obo:
-    """Get ZFIN OBO."""
-    return ZFINGetter(force=force)
-
-
 MARKERS_COLUMNS = [
     "zfin_id",
     "name",
@@ -62,7 +57,7 @@ MARKERS_COLUMNS = [
 ]
 
 
-def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Term]:
+def get_terms(force: bool = False, version: str | None = None) -> Iterable[Term]:
     """Get terms."""
     alt_ids_df = ensure_df(
         PREFIX,
@@ -73,7 +68,7 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
         names=["alt", "zfin_id"],
         version=version,
     )
-    primary_to_alt_ids = defaultdict(set)
+    primary_to_alt_ids: defaultdict[str, set[str]] = defaultdict(set)
     for alt_id, zfin_id in alt_ids_df.values:
         primary_to_alt_ids[zfin_id].add(alt_id)
 
@@ -135,7 +130,7 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
         # Entity type is redundant of identifier
         # term.append_property("type", entity_type)
         for alt_id in primary_to_alt_ids[identifier]:
-            term.append_alt(alt_id)
+            term.append_alt(Reference(prefix=PREFIX, identifier=alt_id))
         entrez_id = entrez_mappings.get(identifier)
         if entrez_id:
             try:
@@ -151,7 +146,7 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
         for hgnc_id in human_orthologs.get(identifier, []):
             term.append_relationship(orthologous, Reference(prefix="hgnc", identifier=hgnc_id))
         for mgi_curie in mouse_orthologs.get(identifier, []):
-            mouse_ortholog = Reference.from_curie(mgi_curie)
+            mouse_ortholog = _parse_str_or_curie_or_uri(mgi_curie)
             if mouse_ortholog:
                 term.append_relationship(orthologous, mouse_ortholog)
         for flybase_id in fly_orthologs.get(identifier, []):

pyobo/ssg/__init__.py

@@ -1,11 +1,9 @@
 """Static site generator."""
 
-import itertools as itt
 from collections import defaultdict
 from collections.abc import Sequence
 from operator import attrgetter
 from pathlib import Path
-from typing import Optional, Union
 
 import bioregistry
 from bioregistry.constants import BIOREGISTRY_DEFAULT_BASE_URL
@@ -31,21 +29,22 @@ index_template = environment.get_template("index.html")
 
 def make_site(
     obo: Obo,
-    directory: Union[str, Path],
+    directory: str | Path,
     use_subdirectories: bool = True,
     manifest: bool = False,
-    resource: Optional[bioregistry.Resource] = None,
-    metaregistry_metaprefix: Optional[str] = None,
-    metaregistry_name: Optional[str] = None,
-    metaregistry_base_url: Optional[str] = None,
-    show_properties_in_manifest: Optional[Sequence[tuple[str, str]]] = None,
+    resource: bioregistry.Resource | None = None,
+    metaregistry_metaprefix: str | None = None,
+    metaregistry_name: str | None = None,
+    metaregistry_base_url: str | None = None,
+    show_properties_in_manifest: Sequence[tuple[str, str]] | None = None,
 ) -> None:
     """Make a website in the given directory.
 
     :param obo: The ontology to generate a site for
     :param directory: The directory in which to generate the site
-    :param use_subdirectories: If true, creates directories for each term/property/typedef with an index.html
-        inside. If false, creates HTML files named with the identifiers.
+    :param use_subdirectories: If true, creates directories for each
+        term/property/typedef with an index.html inside. If false, creates HTML files
+        named with the identifiers.
     :param manifest: If true, lists all entries on the homepage.
     :param resource: A custom resource
     """
@@ -65,15 +64,12 @@ def make_site(
     if resource is None:
         raise KeyError
 
+    terms = [term for term in obo if term.prefix == obo.ontology]
+
     if not manifest:
         _manifest = None
     else:
-        _manifest = sorted(
-            (term for term in itt.chain(obo, obo.typedefs or []) if term.prefix == obo.ontology),
-            key=attrgetter("identifier"),
-        )
-
-    terms = [term for term in obo if term.prefix == obo.ontology]
+        _manifest = sorted(terms, key=attrgetter("identifier"))
 
     directory.joinpath("index.html").write_text(
         index_template.render(

pyobo/ssg/index.html

@@ -8,7 +8,7 @@
             Metadata
         </h5>
         <div class="card-body">
-            <p>{{ resource.get_description() }}</p>
+            <p>{{ resource.get_description(use_markdown=True) }}</p>
             <dl>
                 {% if obo.data_version %}
                     <dt>Data Version</dt>
@@ -64,6 +64,30 @@
         </div>
     {% endif %}
 
+    {% if obo.typedefs %}
+        <div class="card" style="margin-top: 1em;">
+            <h5 class="card-header">
+                Type Definitions
+            </h5>
+            <table class="table table-striped">
+                <thead>
+                <tr>
+                    <th>CURIE</th>
+                    <th>Name</th>
+                </tr>
+                </thead>
+                <tbody>
+                    {%- for typedef in obo.typedefs %}
+                    <tr>
+                        <td>{{ typedef.curie }}</td>
+                        <td>{% if typedef.name %}{{ typedef.name }}{% endif %}</td>
+                    </tr>
+                    {%- endfor %}
+                </tbody>
+            </table>
+        </div>
+    {% endif %}
+
     {% if manifest %}
         <div class="card" style="margin-top: 1em;">
             <h5 class="card-header">
@@ -85,7 +109,7 @@
                             {% if term.is_metadata_tag %}
                                 Property
                             {% else %}
-                                {{ term.__class__.__name__ }}
+                                {{ term.type }}
                             {% endif %}
                         </td>
                         <td align="right"><a href="{{ term.identifier }}">{{ term.identifier }}</a></td>
@@ -96,16 +120,5 @@
                 </tbody>
             </table>
         </div>
-    {% elif obo.typedefs %}
-        <div class="card" style="margin-top: 1em;">
-            <h5 class="card-header">
-                Relation Definitions
-            </h5>
-            <ul class="list-group list-group-flush">
-                {% for typedef in obo.typedefs %}
-                    <li class="list-group-item">{{ typedef }}</li>
-                {% endfor %}
-            </ul>
-        </div>
     {% endif %}
 {%- endblock content %}

pyobo/ssg/term.html

@@ -2,6 +2,16 @@
 
 {% block title %}{{ term.name or term.identifier }}{% endblock title %}
 
+{% macro display_value(v) %}
+    {% if v.prefix %}
+        <a href="{{ v.bioregistry_link }}">{{ v.curie }}</a>
+    {% elif v.datatype.identifier == "anyURI" %}
+        <a href="{{ v.value }}">{{ v.value }}</a>
+    {% else %}
+        {{ v.value }}
+    {% endif %}
+{% endmacro %}
+
 {% block content -%}
     <div class="card">
         <h5 class="card-header">
@@ -69,11 +79,11 @@
                     </dt>
                     <dd>
                         {% if values|length == 1 %}
-                            {{ values[0] }}
+                            {{ display_value(values[0]) }}
                         {% else %}
                             <ul>
                                 {% for value in values %}
-                                    <li>{{ value }}</li>
+                                    <li>{{ display_value(value) }}</li>
                                 {% endfor %}
                             </ul>
                         {% endif %}

pyobo/struct/__init__.py

@@ -1,23 +1,31 @@
 """Data structures for OBO."""
 
-from .reference import Reference  # noqa: F401
-from .struct import (  # noqa: F401
+from .reference import (
+    OBOLiteral,
+    Reference,
+    Referenced,
+    _parse_str_or_curie_or_uri,
+    default_reference,
+)
+from .struct import (
+    CHARLIE_TERM,
+    HUMAN_TERM,
+    PYOBO_INJECTED,
     Obo,
     Synonym,
-    SynonymSpecificities,
-    SynonymSpecificity,
     SynonymTypeDef,
     Term,
+    TypeDef,
     make_ad_hoc_ontology,
 )
-from .typedef import (  # noqa: F401
-    RelationHint,
-    TypeDef,
+from .struct_utils import Annotation, Stanza
+from .typedef import (
     derives_from,
     enables,
     from_species,
     gene_product_member_of,
-    get_reference_tuple,
+    has_category,
+    has_citation,
     has_gene_product,
     has_member,
     has_part,
@@ -32,3 +40,41 @@ from .typedef import (  # noqa: F401
     transcribes_to,
     translates_to,
 )
+
+__all__ = [
+    "CHARLIE_TERM",
+    "HUMAN_TERM",
+    "PYOBO_INJECTED",
+    "Annotation",
+    "OBOLiteral",
+    "Obo",
+    "Reference",
+    "Referenced",
+    "Stanza",
+    "Synonym",
+    "SynonymTypeDef",
+    "Term",
+    "TypeDef",
+    "_parse_str_or_curie_or_uri",
+    "default_reference",
+    "derives_from",
+    "enables",
+    "from_species",
+    "gene_product_member_of",
+    "has_category",
+    "has_citation",
+    "has_gene_product",
+    "has_member",
+    "has_part",
+    "has_participant",
+    "is_a",
+    "make_ad_hoc_ontology",
+    "member_of",
+    "orthologous",
+    "part_of",
+    "participates_in",
+    "species_specific",
+    "superclass_of",
+    "transcribes_to",
+    "translates_to",
+]

pyobo/struct/functional/__init__.py

@@ -0,0 +1 @@
+"""Functional OWL interface."""