pyobo 0.11.0__py3-none-any.whl → 0.11.2__py3-none-any.whl

pyobo/sources/rgd.py

@@ -137,7 +137,7 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
                         continue
                     if prefix == "uniprot":
                         term.append_relationship(
-                            has_gene_product, Reference.auto(prefix=prefix, identifier=xref_id)
+                            has_gene_product, Reference(prefix=prefix, identifier=xref_id)
                         )
                     elif prefix == "ensembl":
                         if xref_id.startswith("ENSMUSG") or xref_id.startswith("ENSRNOG"):

pyobo/sources/slm.py

@@ -77,10 +77,10 @@ def iter_terms(version: str, force: bool = False):
         smiles,
         inchi,
         inchikey,
-        chebi_id,
-        lipidmaps_id,
-        hmdb_id,
-        pmids,
+        chebi_ids,
+        lipidmaps_ids,
+        hmdb_ids,
+        pubmed_ids,
     ) in tqdm(
         df[COLUMNS].values, desc=f"[{PREFIX}] generating terms", unit_scale=True, unit="lipid"
     ):
@@ -103,21 +103,35 @@ def iter_terms(version: str, force: bool = False):
                 inchi = inchi[len("InChI=") :]
             term.append_property(has_inchi, inchi)
         if pd.notna(inchikey):
-            if inchikey.startswith("InChIKey="):
-                inchikey = inchikey[len("InChIKey=") :]
-            term.append_exact_match(Reference(prefix="inchikey", identifier=inchikey))
-        if pd.notna(chebi_id):
-            term.append_exact_match(("chebi", chebi_id))
-        if pd.notna(lipidmaps_id):
+            inchikey = inchikey.removeprefix("InChIKey=").strip()
+            if inchikey and inchikey != "none":
+                try:
+                    inchi_ref = Reference(prefix="inchikey", identifier=inchikey)
+                except ValueError:
+                    tqdm.write(
+                        f"[slm:{identifier}] had invalid inchikey reference: ({type(inchikey)}) {inchikey}"
+                    )
+                else:
+                    term.append_exact_match(inchi_ref)
+        for chebi_id in _split(chebi_ids):
+            term.append_xref(("chebi", chebi_id))
+        for lipidmaps_id in _split(lipidmaps_ids):
             term.append_exact_match(("lipidmaps", lipidmaps_id))
-        if pd.notna(hmdb_id):
+        for hmdb_id in _split(hmdb_ids):
             term.append_exact_match(("hmdb", hmdb_id))
-        if pd.notna(pmids):
-            for pmid in pmids.split("|"):
-                term.append_provenance(("pubmed", pmid))
+        for pubmed_id in _split(pubmed_ids):
+            term.append_provenance(("pubmed", pubmed_id))
         # TODO how to handle class, parents, and components?
         yield term
 
 
+def _split(s: str) -> Iterable[str]:
+    if pd.notna(s):
+        for x in s.split("|"):
+            x = x.strip()
+            if x:
+                yield x
+
+
 if __name__ == "__main__":
     get_obo().write_default(write_obo=True, use_tqdm=True)

pyobo/sources/uniprot/uniprot.py

@@ -82,7 +82,7 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
             pubmeds,
             pdbs,
             proteome,
-            gene_id,
+            gene_ids,
             rhea_curies,
             go_components,
             go_functions,
@@ -94,13 +94,14 @@ def iter_terms(version: Optional[str] = None) -> Iterable[Term]:
                 description = description.removeprefix("FUNCTION: ")
             term = Term(
                 reference=Reference(prefix=PREFIX, identifier=uniprot_id, name=accession),
-                definition=description or None,
+                # definition=description or None,
             )
             term.set_species(taxonomy_id)
-            if gene_id:
-                term.append_relationship(
-                    gene_product_of, Reference(prefix="ncbigene", identifier=gene_id)
-                )
+            if gene_ids:
+                for gene_id in gene_ids.split(";"):
+                    term.append_relationship(
+                        gene_product_of, Reference(prefix="ncbigene", identifier=gene_id.strip())
+                    )
 
             # TODO add type=Reference(prefix="xsd", identifier="boolean")
             term.append_property("reviewed", "true")

pyobo/sources/zfin.py

@@ -7,6 +7,7 @@ from typing import Optional
 
 from tqdm.auto import tqdm
 
+from pyobo.resources.so import get_so_name
 from pyobo.struct import (
     Obo,
     Reference,
@@ -113,7 +114,9 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
     )
     df["sequence_ontology_id"] = df["sequence_ontology_id"].map(lambda x: x[len("SO:") :])
     so = {
-        sequence_ontology_id: Reference.auto(prefix="SO", identifier=sequence_ontology_id)
+        sequence_ontology_id: Reference(
+            prefix="SO", identifier=sequence_ontology_id, name=get_so_name(sequence_ontology_id)
+        )
         for sequence_ontology_id in df["sequence_ontology_id"].unique()
     }
     for _, reference in sorted(so.items()):
@@ -135,17 +138,26 @@ def get_terms(force: bool = False, version: Optional[str] = None) -> Iterable[Te
             term.append_alt(alt_id)
         entrez_id = entrez_mappings.get(identifier)
         if entrez_id:
-            term.append_exact_match(Reference(prefix="ncbigene", identifier=entrez_id))
+            try:
+                ncbigene_ref = Reference(prefix="ncbigene", identifier=entrez_id)
+            except ValueError:
+                tqdm.write(f"[zfin] invalid NCBI gene: {entrez_id}")
+            else:
+                term.append_exact_match(ncbigene_ref)
         for uniprot_id in uniprot_mappings.get(identifier, []):
-            term.append_relationship(has_gene_product, Reference.auto("uniprot", uniprot_id))
+            term.append_relationship(
+                has_gene_product, Reference(prefix="uniprot", identifier=uniprot_id)
+            )
         for hgnc_id in human_orthologs.get(identifier, []):
-            term.append_relationship(orthologous, Reference.auto("hgnc", hgnc_id))
+            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, auto=True)
+            mouse_ortholog = Reference.from_curie(mgi_curie)
             if mouse_ortholog:
                 term.append_relationship(orthologous, mouse_ortholog)
         for flybase_id in fly_orthologs.get(identifier, []):
-            term.append_relationship(orthologous, Reference.auto("flybase", flybase_id))
+            term.append_relationship(
+                orthologous, Reference(prefix="flybase", identifier=flybase_id)
+            )
 
         yield term
 

pyobo/struct/reference.py

@@ -8,6 +8,7 @@ from curies.api import ExpansionError
 from pydantic import Field, field_validator, model_validator
 
 from .utils import obo_escape
+from ..constants import GLOBAL_CHECK_IDS
 from ..identifier_utils import normalize_curie
 
 __all__ = [
@@ -45,13 +46,13 @@ class Reference(curies.Reference):
         prefix, identifier = values.get("prefix"), values.get("identifier")
         if not prefix or not identifier:
             return values
-        norm_prefix = bioregistry.normalize_prefix(prefix)
-        if norm_prefix is None:
+        resource = bioregistry.get_resource(prefix)
+        if resource is None:
             raise ExpansionError(f"Unknown prefix: {prefix}")
-        values["prefix"] = norm_prefix
-        values["identifier"] = bioregistry.standardize_identifier(norm_prefix, identifier).strip()
-        # if not bioregistry.is_valid_identifier(norm_prefix, values["identifier"]):
-        #    raise ValueError(f"non-standard identifier: {norm_prefix}:{norm_identifier}")
+        values["prefix"] = resource.prefix
+        values["identifier"] = resource.standardize_identifier(identifier)
+        if GLOBAL_CHECK_IDS and not resource.is_valid_identifier(values["identifier"]):
+            raise ValueError(f"non-standard identifier: {resource.prefix}:{values['identifier']}")
         return values
 
     @classmethod
@@ -60,7 +61,7 @@ class Reference(curies.Reference):
         from ..api import get_name
 
         name = get_name(prefix, identifier)
-        return cls(prefix=prefix, identifier=identifier, name=name)
+        return cls.model_validate({"prefix": prefix, "identifier": identifier, "name": name})
 
     @property
     def bioregistry_link(self) -> str:
@@ -116,7 +117,7 @@ class Reference(curies.Reference):
             return None
         if name is None and auto:
             return cls.auto(prefix=prefix, identifier=identifier)
-        return cls(prefix=prefix, identifier=identifier, name=name)
+        return cls.model_validate({"prefix": prefix, "identifier": identifier, "name": name})
 
     @property
     def _escaped_identifier(self):

pyobo/struct/struct.py

@@ -4,6 +4,7 @@ import gzip
 import json
 import logging
 import os
+import sys
 from collections import defaultdict
 from collections.abc import Collection, Iterable, Iterator, Mapping, Sequence
 from dataclasses import dataclass, field
@@ -603,6 +604,11 @@ class Obo:
 
         return graph_from_obo(self)
 
+    def write_obograph(self, path: Path) -> None:
+        """Write OBO Graph json."""
+        graph = self.get_graph()
+        path.write_text(graph.model_dump_json(indent=2, exclude_none=True, exclude_unset=True))
+
     @classmethod
     def cli(cls) -> None:
         """Run the CLI for this class."""
@@ -616,22 +622,31 @@ class Obo:
         @click.command()
         @verbose_option
         @force_option
+        @click.option("--rewrite", "-r", is_flag=True)
         @click.option("--owl", is_flag=True, help="Write OWL via ROBOT")
-        @click.option("--graph", is_flag=True, help="Write OBO Graph JSON via ROBOT")
         @click.option("--nodes", is_flag=True, help="Write nodes file")
         @click.option(
             "--version", help="Specify data version to get. Use this if bioversions is acting up."
         )
-        def _main(force: bool, owl: bool, graph: bool, nodes: bool, version: Optional[str]):
-            inst = cls(force=force, data_version=version)
-            inst.write_default(
-                write_obograph=graph,
-                write_obo=True,
-                write_owl=owl,
-                write_nodes=nodes,
-                force=force,
-                use_tqdm=True,
-            )
+        def _main(force: bool, owl: bool, nodes: bool, version: Optional[str], rewrite: bool):
+            try:
+                inst = cls(force=force, data_version=version)
+            except Exception as e:
+                click.secho(f"[{cls.ontology}] Got an exception during instantiation - {type(e)}")
+                sys.exit(1)
+
+            try:
+                inst.write_default(
+                    write_obograph=True,
+                    write_obo=True,
+                    write_owl=owl,
+                    write_nodes=nodes,
+                    force=force or rewrite,
+                    use_tqdm=True,
+                )
+            except Exception as e:
+                click.secho(f"[{cls.ontology}] Got an exception during OBO writing {type(e)}")
+                sys.exit(1)
 
         return _main
 
@@ -865,16 +880,11 @@ class Obo:
             relation_df.sort_values(list(relation_df.columns), inplace=True)
             relation_df.to_csv(relations_path, sep="\t", index=False)
 
-        if (write_obo or write_obograph or write_owl) and (not self._obo_path.exists() or force):
+        if (write_obo or write_owl) and (not self._obo_path.exists() or force):
             self.write_obo(self._obo_path, use_tqdm=use_tqdm)
-        if write_obograph:
-            # obo_to_obograph(self._obo_path, self._obograph_path)
-            self._obograph_path.write_text(
-                self.get_graph().json(
-                    indent=2, ensure_ascii=False, exclude_none=True, exclude_unset=True
-                )
-            )
-        if write_owl:
+        if write_obograph and (not self._obograph_path.exists() or force):
+            self.write_obograph(self._obograph_path)
+        if write_owl and (not self._owl_path.exists() or force):
             obo_to_owl(self._obo_path, self._owl_path)
         if write_obonet and (not self._obonet_gz_path.exists() or force):
             logger.debug("writing obonet to %s", self._obonet_gz_path)

pyobo/struct/typedef.py

@@ -365,6 +365,11 @@ has_homepage = TypeDef(
     reference=Reference(prefix="foaf", identifier="homepage", name="homepage"), is_metadata_tag=True
 )
 
+has_category = TypeDef(
+    reference=Reference(prefix="biolink", identifier="category", name="has category"),
+    is_metadata_tag=True,
+)
+
 default_typedefs: dict[tuple[str, str], TypeDef] = {
     v.pair: v for k, v in locals().items() if isinstance(v, TypeDef)
 }

pyobo/version.py

@@ -12,7 +12,7 @@ __all__ = [
     "get_git_hash",
 ]
 
-VERSION = "0.11.0"
+VERSION = "0.11.2"
 
 
 def get_git_hash() -> str:

{pyobo-0.11.0.dist-info → pyobo-0.11.2.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: pyobo
-Version: 0.11.0
+Version: 0.11.2
 Summary: A python package for handling and generating OBO
 Author-email: Charles Tapley Hoyt <cthoyt@gmail.com>
 Maintainer-email: Charles Tapley Hoyt <cthoyt@gmail.com>
@@ -49,40 +49,40 @@ Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
 Classifier: Topic :: Scientific/Engineering :: Chemistry
 Requires-Python: >=3.9
 Description-Content-Type: text/markdown
-License-File: LICENSE
-Requires-Dist: obonet >=0.3.0
+Requires-Dist: obonet>=0.3.0
 Requires-Dist: click
 Requires-Dist: tqdm
 Requires-Dist: pyyaml
 Requires-Dist: pandas
 Requires-Dist: requests
 Requires-Dist: protmapper
-Requires-Dist: more-itertools
-Requires-Dist: more-click >=0.0.2
+Requires-Dist: more_itertools
+Requires-Dist: more_click>=0.0.2
 Requires-Dist: humanize
 Requires-Dist: tabulate
 Requires-Dist: cachier
-Requires-Dist: pystow >=0.2.7
-Requires-Dist: bioversions >=0.5.514
-Requires-Dist: bioregistry >=0.10.20
-Requires-Dist: bioontologies >=0.4.0
-Requires-Dist: zenodo-client >=0.0.5
-Requires-Dist: class-resolver
+Requires-Dist: pystow>=0.2.7
+Requires-Dist: bioversions>=0.5.535
+Requires-Dist: bioregistry>=0.11.23
+Requires-Dist: bioontologies>=0.4.0
+Requires-Dist: zenodo-client>=0.0.5
+Requires-Dist: class_resolver
 Requires-Dist: psycopg2-binary
-Requires-Dist: pydantic >=2.0
-Requires-Dist: drugbank-downloader
-Requires-Dist: chembl-downloader
-Requires-Dist: umls-downloader >=0.1.3
-Requires-Dist: typing-extensions
+Requires-Dist: pydantic>=2.0
+Requires-Dist: requests-ftp
+Requires-Dist: drugbank_downloader
+Requires-Dist: chembl_downloader
+Requires-Dist: umls_downloader>=0.1.3
+Requires-Dist: typing_extensions
 Requires-Dist: rdflib
-Provides-Extra: docs
-Requires-Dist: sphinx >=8 ; extra == 'docs'
-Requires-Dist: sphinx-rtd-theme >=3.0 ; extra == 'docs'
-Requires-Dist: sphinx-click ; extra == 'docs'
-Requires-Dist: sphinx-automodapi ; extra == 'docs'
 Provides-Extra: tests
-Requires-Dist: pytest ; extra == 'tests'
-Requires-Dist: coverage ; extra == 'tests'
+Requires-Dist: pytest; extra == "tests"
+Requires-Dist: coverage; extra == "tests"
+Provides-Extra: docs
+Requires-Dist: sphinx>=8; extra == "docs"
+Requires-Dist: sphinx-rtd-theme>=3.0; extra == "docs"
+Requires-Dist: sphinx-click; extra == "docs"
+Requires-Dist: sphinx_automodapi; extra == "docs"
 
 <!--
 <p align="center">
@@ -109,10 +109,12 @@ Requires-Dist: coverage ; extra == 'tests'
         <img src="https://codecov.io/gh/biopragmatics/pyobo/branch/main/graph/badge.svg" alt="Codecov status" /></a>  
     <a href="https://github.com/cthoyt/cookiecutter-python-package">
         <img alt="Cookiecutter template from @cthoyt" src="https://img.shields.io/badge/Cookiecutter-snekpack-blue" /></a>
-    <a href='https://github.com/psf/black'>
-        <img src='https://img.shields.io/badge/code%20style-black-000000.svg' alt='Code style: black' /></a>
+    <a href="https://github.com/astral-sh/ruff">
+        <img src="https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json" alt="Ruff" style="max-width:100%;"></a>
     <a href="https://github.com/biopragmatics/pyobo/blob/main/.github/CODE_OF_CONDUCT.md">
         <img src="https://img.shields.io/badge/Contributor%20Covenant-2.1-4baaaa.svg" alt="Contributor Covenant"/></a>
+    <a href="https://doi.org/10.5281/zenodo.3381961">
+        <img src="https://zenodo.org/badge/DOI/10.5281/zenodo.3381961.svg" alt="DOI"></a>
 </p>
 
 Tools for biological identifiers, names, synonyms, xrefs, hierarchies, relations, and properties through the
@@ -500,14 +502,14 @@ and make update to the `url` entry for that namespace in the Bioregistry.
 The most recent release can be installed from
 [PyPI](https://pypi.org/project/pyobo/) with:
 
-```shell
-pip install pyobo
+```console
+python3 -m pip install pyobo
 ```
 
 The most recent code and data can be installed directly from GitHub with:
 
-```shell
-pip install git+https://github.com/biopragmatics/pyobo.git
+```console
+python3 -m pip install git+https://github.com/biopragmatics/pyobo.git
 ```
 
 ## 👐 Contributing
@@ -564,10 +566,10 @@ The final section of the README is for if you want to get involved by making a c
 
 To install in development mode, use the following:
 
-```bash
+```console
 git clone git+https://github.com/biopragmatics/pyobo.git
 cd pyobo
-pip install -e .
+python3 -m pip install -e .
 ```
 
 ### Updating Package Boilerplate
@@ -576,8 +578,8 @@ This project uses `cruft` to keep boilerplate (i.e., configuration, contribution
 configuration)
 up-to-date with the upstream cookiecutter package. Update with the following:
 
-```shell
-pip install cruft
+```console
+python3 -m pip install cruft
 cruft update
 ```
 
@@ -586,10 +588,11 @@ available [here](https://github.com/cruft/cruft?tab=readme-ov-file#updating-a-pr
 
 ### 🥼 Testing
 
-After cloning the repository and installing `tox` with `pip install tox tox-uv`, 
+After cloning the repository and installing `tox` with
+`python3 -m pip install tox tox-uv`,
 the unit tests in the `tests/` folder can be run reproducibly with:
 
-```shell
+```console
 tox -e py
 ```
 
@@ -600,12 +603,12 @@ Additionally, these tests are automatically re-run with each commit in a
 
 The documentation can be built locally using the following:
 
-```shell
+```console
 git clone git+https://github.com/biopragmatics/pyobo.git
 cd pyobo
 tox -e docs
 open docs/build/html/index.html
-``` 
+```
 
 The documentation automatically installs the package as well as the `docs`
 extra specified in the [`pyproject.toml`](../../Desktop/pyobo/pyproject.toml). `sphinx` plugins
@@ -661,38 +664,23 @@ You only have to do the following steps once.
 
 #### Configuring your machine's connection to PyPI
 
-You have to do the following steps once per machine. Create a file in your home directory called
-`.pypirc` and include the following:
-
-```ini
-[distutils]
-index-servers =
-    pypi
-    testpypi
-
-[pypi]
-username = __token__
-password = <the API token you just got>
+You have to do the following steps once per machine. 
 
-# This block is optional in case you want to be able to make test releases to the Test PyPI server
-[testpypi]
-repository = https://test.pypi.org/legacy/
-username = __token__
-password = <an API token from test PyPI>
+```console
+$ uv tool install keyring
+$ keyring set https://upload.pypi.org/legacy/ __token__
+$ keyring set https://test.pypi.org/legacy/ __token__
 ```
 
-Note that since PyPI is requiring token-based authentication, we use `__token__` as the user, verbatim.
-If you already have a `.pypirc` file with a `[distutils]` section, just make sure that there is an `index-servers`
-key and that `pypi` is in its associated list. More information on configuring the `.pypirc` file can
-be found [here](https://packaging.python.org/en/latest/specifications/pypirc).
+Note that this deprecates previous workflows using `.pypirc`.
 
 #### Uploading to PyPI
 
 After installing the package in development mode and installing
-`tox` with `pip install tox tox-uv`,
-run the following from the shell:
+`tox` with `python3 -m pip install tox tox-uv`,
+run the following from the console:
 
-```shell
+```console
 tox -e finish
 ```
 
@@ -703,7 +691,7 @@ This script does the following:
    and [`docs/source/conf.py`](../../Desktop/pyobo/docs/source/conf.py) to not have the `-dev` suffix
 2. Packages the code in both a tar archive and a wheel using
    [`uv build`](https://docs.astral.sh/uv/guides/publish/#building-your-package)
-3. Uploads to PyPI using [`twine`](https://github.com/pypa/twine).
+3. Uploads to PyPI using [`uv publish`](https://docs.astral.sh/uv/guides/publish/#publishing-your-package).
 4. Push to GitHub. You'll need to make a release going with the commit where the version was bumped.
 5. Bump the version to the next patch. If you made big changes and want to bump the version by minor, you can
    use `tox -e bumpversion -- minor` after.