import methods to load ontologies via pronto (#7)

merges #7

.pre-commit-config.yaml

@@ -26,3 +26,5 @@ repos:
  hooks:
  - id: mypy
  args: ["--strict", "--show-error-codes"]
+ additional_dependencies:
+ - pronto

README.md

@@ -18,7 +18,6 @@ Here, we'll use the example [metals ontology](https://jbiomedsem.biomedcentral.c
 <!-- use absolute URL instead of media/metals.svg for PyPI long_description -->
 
 Note that `NXOntology` represents the ontology as a [`networkx.DiGraph`](https://networkx.org/documentation/stable/reference/classes/digraph.html), where edge direction goes from superterm to subterm.
-Currently, users must create their own `networkx.DiGraph` to use this package.
 
 Given an `NXOntology` instance, here how to compute intrinsic similarity metrics.
 
@@ -82,9 +81,42 @@ Node fill color corresponds to the Sánchez information content, such that darke
 The most informative common ancestor (coinage) is outlined with a bold solid line.
 Nodes that are not an ancestor of gold or silver have an invisible outline.
 
+### Loading ontologies
+
+Pronto supports reading ontologies from the following file formats:
+
+1. [Open Biomedical Ontologies 1.4](http://owlcollab.github.io/oboformat/doc/GO.format.obo-1_4.html): `.obo` extension, uses the [fastobo](https://github.com/fastobo/fastobo-py) parser.
+2. [OBO Graphs JSON](https://github.com/geneontology/obographs): `.json` extension, uses the fastobo parser.
+3. [Ontology Web Language 2 RDF/XML](https://www.w3.org/TR/owl2-overview/%3E): `.owl` extension, uses the pronto `RdfXMLParser`.
+
+The files can be local or at a network location (URL starting with https, http, or ftp).
+Pronto detects and handles gzip, bzip2, and xz compression.
+
+Here are examples operations on the Gene Ontology,
+using pronto to load the ontology:
+
+```python
+>>> from nxontology.imports import from_file
+>>> # versioned URL for the Gene Ontology
+>>> url = "http://release.geneontology.org/2021-02-01/ontology/go-basic.json.gz"
+>>> nxo = from_file(url)
+>>> nxo.n_nodes
+44085
+>>> # similarity between "myelination" and "neurogenesis"
+>>> sim = nxo.similarity("GO:0042552", "GO:0022008")
+>>> round(sim.lin, 2)
+0.21
+>>> import networkx as nx
+>>> # Gene Ontology domains are disconnected, expect 3 components
+>>> nx.number_weakly_connected_components(nxo.graph)
+3
+```
+
+Users can also create their own `networkx.DiGraph` to use this package.
+
 ## Installation
 
-nxontology can be installed with `pip` from [[PyPI](https://pypi.org/project/nxontology/) like:
+nxontology can be installed with `pip` from [PyPI](https://pypi.org/project/nxontology/) like:
 
 ```shell
 # standard installation

nxontology/imports.py

@@ -0,0 +1,64 @@
+import logging
+from os import PathLike
+from typing import AnyStr, BinaryIO, Union
+
+from pronto import Ontology as Prontology # type: ignore [attr-defined]
+
+from nxontology import NXOntology
+from nxontology.exceptions import NodeNotFound
+
+
+def pronto_to_nxontology(onto: Prontology) -> NXOntology:
+ """
+ Create an `NXOntology` from an input `pronto.Ontology`.
+ Obsolete terms are omitted as nodes.
+ Only is_a / subClassOf relationships are used for edges.
+ """
+ nxo = NXOntology()
+ nxo.pronto = onto # type: ignore [attr-defined]
+ for term in onto.terms():
+ if term.obsolete:
+ # obsolete was unreliable in pronto < v2.4.0
+ # https://github.com/althonos/pronto/issues/122
+ continue
+ nxo.add_node(
+ term.id,
+ identifier=term.id,
+ label=term.name,
+ namespace=term.namespace,
+ )
+ for term in onto.terms():
+ # add subClassOf / is_a relations
+ # https://github.com/althonos/pronto/issues/119
+ for child in term.subclasses(distance=1, with_self=False):
+ try:
+ nxo.add_edge(term.id, child.id)
+ except NodeNotFound as e:
+ logging.warning(
+ f"Cannot add edge: {term.id} --> {child.id} "
+ f"({term.name} --> {child.name}): {e}"
+ )
+ return nxo
+
+
+def from_obo_library(slug: str) -> NXOntology:
+ """
+ Read ontology from <http://www.obofoundry.org/>.
+ Delegates to [`pronto.Ontology.from_obo_library`](https://pronto.readthedocs.io/en/stable/api/pronto.Ontology.html#pronto.Ontology.from_obo_library).
+ """
+ onto = Prontology.from_obo_library(slug=slug)
+ nxo = pronto_to_nxontology(onto)
+ nxo.graph.graph["from_obo_library"] = slug
+ return nxo
+
+
+def from_file(handle: Union[BinaryIO, str, "PathLike[AnyStr]"]) -> NXOntology:
+ """
+ Read ontology in OBO, OWL, or JSON (OBO Graphs) format via pronto.
+
+ Arguments:
+ handle: Either the path to a file or a binary file handle
+ that contains a serialized version of the ontology.
+ """
+ onto = Prontology(handle=handle)
+ return pronto_to_nxontology(onto)

nxontology/tests/imports_test.py

@@ -0,0 +1,39 @@
+import pytest
+
+from nxontology.imports import from_file, from_obo_library
+
+
+@pytest.mark.parametrize(
+ "format",
+ [
+ "owl",
+ "obo",
+ ],
+)
+def test_from_obo_library_taxrank(format: str) -> None:
+ """
+ http://www.obofoundry.org/ontology/taxrank.html
+ """
+ slug = f"taxrank.{format}"
+ nxo = from_obo_library(slug)
+ (root,) = nxo.roots
+ assert root == "TAXRANK:0000000"
+ cultivar = nxo.node_info("TAXRANK:0000034")
+ assert cultivar.identifier == "TAXRANK:0000034"
+ assert cultivar.label == "cultivar"
+ assert "TAXRANK:0000000" in cultivar.ancestors
+
+
+def test_from_file_go() -> None:
+ url = "http://release.geneontology.org/2021-02-01/ontology/go-basic.json.gz"
+ nxo = from_file(url)
+ assert nxo.n_nodes > 20_000
+ # pronto < 2.4.0 marked GO:0000003 as obsolete
+ # https://github.com/althonos/pronto/issues/122
+ assert "GO:0000003" in nxo.graph
+ info = nxo.node_info("GO:0042552")
+ assert info.identifier == "GO:0042552"
+ assert info.label == "myelination"
+ assert info.data["namespace"] == "biological_process"
+ # has edge from "axon ensheathment" to "myelination"
+ assert nxo.graph.has_edge("GO:0008366", "GO:0042552")

setup.cfg

@@ -30,6 +30,7 @@ include_package_data = True
 python_requires = >=3.7
 install_requires =
  networkx>=2
+ pronto>=v2.4.0
  fsspec
 
 [options.extras_require]