pymetadata 0.5.0__py3-none-any.whl

pymetadata/unichem.py

@@ -0,0 +1,190 @@
+"""
+Unichem metadata.
+
+Additional substance information based on inchikeys
+
+https://www.ebi.ac.uk/unichem/info/webservices#GetSrcCpdIdsFromKey
+https://www.ebi.ac.uk/unichem/rest/inchikey/AAOVKJBEBIDNHE-UHFFFAOYSA-N
+"""
+
+import urllib
+from dataclasses import dataclass, field
+from pathlib import Path
+from typing import Dict, List, Optional
+
+import requests
+
+import pymetadata
+from pymetadata import log
+from pymetadata.cache import DataclassJSONEncoder, read_json_cache, write_json_cache
+from pymetadata.core.xref import CrossReference
+
+
+logger = log.get_logger(__name__)
+
+
+@dataclass
+class UnichemSource:
+    """Unichem source.
+
+    src_id (the src_id for this source),
+    src_url (the main home page of the source),
+    name (the unique name for the source in UniChem, always lower case),
+    name_long (the full name of the source, as defined by the source),
+    name_label (A name for the source suitable for use as a 'label' for the source within a web-page. Correct case setting for source, and always less than 30 characters),
+    description (a description of the content of the source),
+    base_id_url_available (an flag indicating whether this source provides a valid base_id_url for creating cpd-specific links [1=yes, 0=no]).
+    base_id_url (the base url for constructing hyperlinks to this source [append an identifier from this source to the end of this url to create a valid url to a specific page for this cpd], unless aux_for_url=1),
+    aux_for_url (A flag to indicate whether the aux_src field should be used to create hyperlinks instead of the src_compound_id [1=yes, 0=no]
+    """
+
+    sourceID: int
+    srcUrl: str
+    name: str
+    nameLabel: str = field(repr=False)
+    nameLong: str = field(repr=False)
+    UCICount: int = field(repr=False)
+    baseIdUrl: str = field(repr=False)
+    description: str = field(repr=False)
+    created: str = field(repr=False)
+    lastUpdated: str = field(repr=False)
+    srcDetails: str = field(repr=False)
+    srcReleaseDate: str = field(repr=False)
+    srcReleaseNumber: int = field(repr=False)
+    updateComments: str = field(repr=False)
+    private: bool = field(repr=False)
+
+
+class UnichemQuery:
+    """Query unichem."""
+
+    sources: Dict[int, UnichemSource] = {}
+
+    def __init__(self, cache_path: Optional[Path] = None, cache: Optional[bool] = None):
+        """Initialize UnichemQuery."""
+        if cache_path is None:
+            cache_path = pymetadata.CACHE_PATH
+        if cache is None:
+            cache = pymetadata.CACHE_USE
+
+        self.cache_path: Path = cache_path
+        self.cache: bool = cache
+
+        if not self.sources:
+            self.sources = self.get_sources()
+
+    def get_sources(self) -> Dict[int, UnichemSource]:
+        """Retrieve or query the sources."""
+
+        sources: Dict[int, UnichemSource]
+        unichem_sources_path = self.cache_path / "unichem_sources.json"
+
+        data: Dict
+        if self.cache and unichem_sources_path.exists():
+            data = read_json_cache(unichem_sources_path)
+            sources = {int(k): UnichemSource(**v) for k, v in data.items()}
+        else:
+            # query data
+            url = "https://www.ebi.ac.uk/unichem/api/v1/sources/"
+            response = requests.get(url)
+            data = response.json()
+            if data["response"].lower() != "success":
+                raise IOError(f"Could not query UniChem sources: '{data}'")
+
+            sources_list: List[UnichemSource] = [
+                UnichemSource(**v) for v in data["sources"]
+            ]
+            sources = {source.sourceID: source for source in sources_list}
+
+            # write cache
+            if self.cache:
+                write_json_cache(
+                    data=sources,
+                    cache_path=unichem_sources_path,
+                    json_encoder=DataclassJSONEncoder,
+                )
+
+        return sources
+
+    def query_xrefs_for_inchikey(self, inchikey: str) -> List[CrossReference]:
+        """Get the cross references for a given inchikey."""
+
+        # cache files
+        xref_base_path = self.cache_path / "unichem"
+        if not xref_base_path.exists():
+            xref_base_path.mkdir(parents=True)
+        xref_path = xref_base_path / f"{inchikey}.json"
+
+        # retrieve or query data
+        data: Dict
+        if self.cache and xref_path.exists():
+            data = read_json_cache(xref_path)
+        else:
+            url = f"https://www.ebi.ac.uk/unichem/rest/inchikey/{inchikey}"
+            response = requests.get(url)
+            data = response.json()
+            write_json_cache(
+                data=data, cache_path=xref_path, json_encoder=DataclassJSONEncoder
+            )
+
+        xrefs: List[CrossReference] = []
+        if data:
+            if "error" in data:
+                logger.error(f"No xrefs for inchikey: '{inchikey}'")
+                return []
+
+            # process data
+            item: Dict[str, str]
+            for item in data:
+                source_id: int = int(item["src_id"])
+                if source_id not in self.sources:
+                    if source_id != 40:
+                        # number 40 is missing from definitions
+                        logger.error(
+                            f"No UniChem source for source id '{source_id}', in item "
+                            f"'{item}'"
+                        )
+                    continue
+
+                source: UnichemSource = self.sources[source_id]
+                accession = item["src_compound_id"]
+                if source.baseIdUrl:
+                    # create and clean url
+                    if not source.baseIdUrl:
+                        continue
+
+                    url = f"{source.baseIdUrl}{accession}"
+
+                    url_accession = urllib.parse.quote(accession)
+                    url = url.replace("{$Id}", url_accession)
+                    url = url.replace("{$id}", url_accession)
+
+                    # handle special case
+                    if source.name == "clinicaltrials":
+                        url = f"{url}%22"
+
+                    # escape whitespace for dailymed | clinicaltrials | ...
+                    url = url.replace(" ", "%20")
+
+                    xref = CrossReference(
+                        name=source.name, accession=accession, url=url
+                    )
+                    xrefs.append(xref)
+
+        return xrefs
+
+
+if __name__ == "__main__":
+    pymetadata.CACHE_PATH = Path.home() / ".cache" / "pymetadata"
+
+    # query sources
+    sources = UnichemQuery().get_sources()
+
+    # query xrefs
+    inchikey = "NGBFQHCMQULJNZ-UHFFFAOYSA-N"
+    xrefs = UnichemQuery(cache=False).query_xrefs_for_inchikey(inchikey=inchikey)
+    print(xrefs)
+    # results = UnichemQuery(cache=True).query_xrefs_for_inchikey(inchikey=inchikey)
+
+    inchikey = "yxsdfasdfs"
+    xrefs = UnichemQuery(cache=False).query_xrefs_for_inchikey(inchikey=inchikey)

pymetadata-0.5.0.dist-info/METADATA

@@ -0,0 +1,154 @@
+Metadata-Version: 2.4
+Name: pymetadata
+Version: 0.5.0
+Summary: pymetadata are python utilities for working with metadata.
+Author-email: Matthias König <konigmatt@googlemail.com>
+Maintainer-email: Matthias König <konigmatt@googlemail.com>
+License-File: LICENSE
+Keywords: COMBINE,annotation,archive,metadata,modeling,standardization
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Scientific/Engineering :: Bio-Informatics
+Requires-Python: >=3.10
+Requires-Dist: depinfo>=2.2.0
+Requires-Dist: fastobo>=0.12.3
+Requires-Dist: jinja2>=3.1.5
+Requires-Dist: lxml>=5.3
+Requires-Dist: pronto>=2.5.8
+Requires-Dist: pydantic>=2.10.4
+Requires-Dist: requests>=2.32.3
+Requires-Dist: rich>=13.9.4
+Requires-Dist: xmltodict>=0.14.2
+Requires-Dist: zeep>=4.3.1
+Provides-Extra: dev
+Requires-Dist: bump-my-version>=0.29.0; extra == 'dev'
+Requires-Dist: hatch; extra == 'dev'
+Requires-Dist: mypy>=1.9.0; extra == 'dev'
+Requires-Dist: pre-commit>=4.0.1; extra == 'dev'
+Requires-Dist: ruff>=0.8.6; extra == 'dev'
+Provides-Extra: test
+Requires-Dist: pytest-cov>=5.0.0; extra == 'test'
+Requires-Dist: pytest>=8.1.1; extra == 'test'
+Requires-Dist: tox>=4.14.2; extra == 'test'
+Description-Content-Type: text/x-rst
+
+.. image:: https://github.com/matthiaskoenig/pymetadata/raw/develop/docs/images/favicon/pymetadata-100x100-300dpi.png
+   :align: left
+   :alt: pymetadata logo
+
+pymetadata: python utilities for metadata and COMBINE archives
+==============================================================
+|icon1| |icon2| |icon3| |icon4| |icon5| |icon6|
+
+
+.. |icon1| image:: https://github.com/matthiaskoenig/pymetadata/workflows/CI-CD/badge.svg
+   :target: https://github.com/matthiaskoenig/pymetadata/workflows/CI-CD
+   :alt: GitHub Actions CI/CD Status
+.. |icon2| image:: https://img.shields.io/pypi/v/pymetadata.svg
+   :target: https://pypi.org/project/pymetadata/
+   :alt: Current PyPI Version
+.. |icon3| image:: https://img.shields.io/pypi/pyversions/pymetadata.svg
+   :target: https://pypi.org/project/pymetadata/
+   :alt: Supported Python Versions
+.. |icon4| image:: https://img.shields.io/pypi/l/pymetadata.svg
+   :target: https://opensource.org/licenses/MIT
+   :alt: MIT License
+.. |icon5| image:: https://zenodo.org/badge/DOI/10.5281/zenodo.5308801.svg
+   :target: https://doi.org/10.5281/zenodo.5308801
+   :alt: Zenodo DOI
+.. |icon6| image:: http://www.mypy-lang.org/static/mypy_badge.svg
+   :target: http://mypy-lang.org/
+   :alt: mypy
+
+pymetadata is a collection of python utilities for working with
+metadata in the context of COMBINE standards with source code available from 
+`https://github.com/matthiaskoenig/pymetadata <https://github.com/matthiaskoenig/pymetadata>`__.
+
+Features include among others
+
+- COMBINE archive version 1 support (OMEX)
+- annotation classes and helpers
+- SBO and KISAO ontology enums
+ 
+If you have any questions or issues please `open an issue <https://github.com/matthiaskoenig/pymetadata/issues>`__.
+
+Documentation
+=============
+Documentation is still work in progress. For an example usage of the COMBINE archive
+see `src/pymetadata/examples/omex_example.py <src/pymetadata/examples/omex_example.py>`__.
+
+How to cite
+===========
+
+.. image:: https://zenodo.org/badge/DOI/10.5281/zenodo.5308801.svg
+   :target: https://doi.org/10.5281/zenodo.5308801
+   :alt: Zenodo DOI
+
+Contributing
+============
+
+Contributions are always welcome! Please read the `contributing guidelines
+<https://github.com/matthiaskoenig/pymetadata/blob/develop/.github/CONTRIBUTING.rst>`__ to
+get started.
+
+License
+=======
+* Source Code: `MIT <https://opensource.org/license/MIT>`__
+* Documentation: `CC BY-SA 4.0 <https://creativecommons.org/licenses/by-sa/4.0/>`__
+
+Funding
+=======
+Matthias König (MK) was supported by the Federal Ministry of Education and Research (BMBF, Germany) within the research network Systems Medicine of the Liver (**LiSyM**, grant number 031L0054). MK is supported by the Federal Ministry of Education and Research (BMBF, Germany) within ATLAS by grant number 031L0304B and by the German Research Foundation (DFG) within the Research Unit Program FOR 5151 QuaLiPerF (Quantifying Liver Perfusion-Function Relationship in Complex Resection - A Systems Medicine Approach) by grant number 436883643 and by grant number 465194077 (Priority Programme SPP 2311, Subproject SimLivA).
+
+Installation
+============
+`pymetadata` is available from `pypi <https://pypi.python.org/pypi/pymetadata>`__ and 
+can be installed via:: 
+
+    pip install pymetadata
+
+Develop version
+---------------
+The latest develop version can be installed via::
+
+    pip install git+https://github.com/matthiaskoenig/pymetadata.git@develop
+
+Or via cloning the repository and installing via::
+
+    git clone https://github.com/matthiaskoenig/pymetadata.git
+    cd pymetadata
+    pip install -e .
+
+
+To install for development use::
+
+    pip install -e .[development]
+
+
+Cache path
+==========
+`pymetadata` caches some information for faster retrieval. The cache path is set to::
+
+    CACHE_PATH: Path = Path.home() / ".cache" / "pymetadata"
+
+To use a custom cache path use::
+
+    import pymetadata
+    pymetadata.CACHE_PATH = <cache_path>
+
+
+Checks
+==========
+- uv for project setup
+- ruff for linting, formating
+- mypy for type checking
+
+© 2021-2025 Matthias König

pymetadata-0.5.0.dist-info/RECORD

@@ -0,0 +1,42 @@
+pymetadata/__init__.py,sha256=-EZKeFfptRrccMcmwrtFlGJkpYRIFY0r47_VT7OzueQ,357
+pymetadata/cache.py,sha256=tQuMIcd1cOfO0dvODQMG92_IrHqgswPfshhFjtl7Pd0,1409
+pymetadata/chebi.py,sha256=EH8sYRx7af3Hi1O8x5Tvj_T9cawGVMtlYp_4B3L8tHY,2730
+pymetadata/console.py,sha256=ouDYOx_81ndvtMW5GVrut71uzPC5xlvibGu9N5YdbRA,332
+pymetadata/log.py,sha256=3uRVMYolalrS0PVWS_4qSme8RYhot3_W2ad1JopI88g,664
+pymetadata/omex.py,sha256=lXdWJQgX-_zDq1OX82zWEk_R1rlJX995jrCKOiQt8JM,29829
+pymetadata/omex_v2.py,sha256=HZBg_wmQWixweOZG3qVj2zqG_o1x9Ljxy-JEP6-ZFhM,584
+pymetadata/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+pymetadata/unichem.py,sha256=slxTabar1ZdZQUyTyRloiWKxD92ixnDGsJ2xk3alrTo,6878
+pymetadata/core/__init__.py,sha256=VWZCD9TgSGldzdtXoarvp_2oUHKXQkC1T-VUSvMLwNA,28
+pymetadata/core/annotation.py,sha256=PO2dyjgDP91J6JcJ2i3CzvdSd-6I0-3lAeTaaRd_cyY,13695
+pymetadata/core/creator.py,sha256=0_z0HPhO2Tq8FnAED_4kuVzUiPfm_tYMiZSvyw73Aho,1307
+pymetadata/core/synonym.py,sha256=-2_1ouSWAtQK5eZv2-p6CIJgYZX4xGKua-09ubBg5uo,155
+pymetadata/core/xref.py,sha256=qlUfAb5wk4bOwPiUCEV0s9gIWVdWf5yup1W8UxR5uHY,1594
+pymetadata/examples/__init__.py,sha256=LHY-XmQoiBxoHQW9mQN1_fUYnpfkALuRsdxDXU9sIeU,31
+pymetadata/examples/cache_path_example.py,sha256=f1-uvvIO28voxpehIvlXuWybNsAkAldmS70Bd77Cb78,377
+pymetadata/examples/omex_example.py,sha256=z8fKyI1z5NMze8DdTfGYvG0rxzinFk61ruiT6NDdcT4,1403
+pymetadata/examples/test.omex,sha256=uVrkDrA59F0S6TpQOk_UulDO-pTu0nU3f6zmaWI7zi4,26219
+pymetadata/examples/results/test_from_files.omex,sha256=wFBnU3v8uUiKkh4RcvMBWSUuaKtSCixQMwwZtbwEiZE,1807
+pymetadata/examples/results/test_from_omex.omex,sha256=tD_0IB8_tEwxEXDzbAzj7p__5R4OcWHMYoAYf2WWe8g,5556
+pymetadata/examples/results/testomex/README.md,sha256=ki5gkAGB0pcfDroiVamBG3qC3BsxwswSTfHVxyL0BDc,103
+pymetadata/examples/results/testomex/manifest.xml,sha256=UWk822KzYmxRxxsXgqzlXBt76ghy1kbwN3mOWTkOkpc,813
+pymetadata/examples/results/testomex/models/omex_comp.xml,sha256=C8zoJ7O2AiE75JlPOonwLDgCQ9pAm6d7erc9mZZosiE,8447
+pymetadata/examples/results/testomex/models/omex_comp_flat.xml,sha256=3avaqyiP07QiF7nVVwgoSk19_8eYyDb0IHRMGuV0i1Q,9658
+pymetadata/examples/results/testomex/models/omex_minimal.xml,sha256=r6FDgMu4rEXR2H_EKyQlSh4JkisH1Yu2clVkqKarPOI,6619
+pymetadata/identifiers/__init__.py,sha256=6Jd-w9Izl_wpWKV8IMBv7rW0Aq067V2czu00LNfPTL8,34
+pymetadata/identifiers/miriam.py,sha256=pa7lB1_C2cKRUuojFPvxAQ6yDI_ZQNjGEoYMb1395pY,982
+pymetadata/identifiers/registry.py,sha256=FzajEoFXlywtAqhGQ2YpxkViAoBRXZM5P82J6ZOHyPc,13081
+pymetadata/metadata/__init__.py,sha256=wrZtmqudWwyxJXrsHoTx235ooDepKgiia8kHKiIZO4Y,154
+pymetadata/metadata/eco.py,sha256=wsF-nRuXdI5Fm8T1e8wWYFtBPgzQ9ap2zIkH3nXjab4,662767
+pymetadata/metadata/kisao.py,sha256=oI3zuCDhDmA-aK5pWLhNJu1Y0XgBvI6IpmLlEnymgdo,89273
+pymetadata/metadata/sbo.py,sha256=rJEtdhOP5YUY1i8-6drWsglDmayFEpWVA2h2t3fjLCo,141756
+pymetadata/ontologies/__init__.py,sha256=vIpTqwqrhOAOYfnavWBQL149dNMAPv-OE5IyloYQCrQ,18
+pymetadata/ontologies/ols.py,sha256=lKmhRMKuEx29QAZsxCRlzUwH48CGtl8YKM2AcsiDFVk,6814
+pymetadata/ontologies/ontology.py,sha256=cnAgXzxPn3XxZ8FUAMuSAH0eOGio-YK1Enzy3ZuKzcc,9100
+pymetadata/resources/chebi_webservice_wsdl.xml,sha256=0AEgcZ48bk4L6l3jO5-6BIVwfTr4yXnRZCtXue5NyHo,23846
+pymetadata/resources/ontologies/README.md,sha256=h1LIKpr42-s0RzwpCufkR_YJ2nWiwOapZX_frRXk3Qg,163
+pymetadata/resources/templates/ontology_enum.pytemplate,sha256=fK7SBTVfRzVk-z_6wiZ_9MDbTNSlEpGGellRoliGqac,1674
+pymetadata-0.5.0.dist-info/METADATA,sha256=R5xPvJVRW71mo79WwmUKkuGpx1lEZQqTZW070IynBrw,5725
+pymetadata-0.5.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+pymetadata-0.5.0.dist-info/licenses/LICENSE,sha256=bIHEDEMiQfVe9c81lFP7Q9hsCOmEuj2c_m50LuotsMM,1058
+pymetadata-0.5.0.dist-info/RECORD,,

pymetadata-0.5.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.27.0
+Root-Is-Purelib: true
+Tag: py3-none-any

pymetadata-0.5.0.dist-info/licenses/LICENSE

@@ -0,0 +1,7 @@
+Copyright (c) 2025 Matthias König
+
+Permission is hereby granted, free of charge, to any person obtaining a copy of this software and associated documentation files (the "Software"), to deal in the Software without restriction, including without limitation the rights to use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies of the Software, and to permit persons to whom the Software is furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.