Skip to content

Commit

Permalink
OBO compliance suite (redux of #693) (#715)
Browse files Browse the repository at this point in the history 
* First pass at oboformat and obographs conformance suite.

See

- owlcollab/oboformat#146
- geneontology/obographs#106

Note that that may move from the OAK repo in the longer term.

* Allow choice of format when exporting OWL.
Addung missing features to obo conversion

* lint

* lint

* Lint.
Removing prints.

* Added format_utilities.py -- see #687

* lint

* Fixing spelling mistakes

* dumper

* Fixed tests and dumper

---------

Co-authored-by: Nico Matentzoglu <[email protected]>
  • Loading branch information
@cmungall @matentzn
cmungall and matentzn authored Mar 14, 2024
1 parent 388c78b commit b94123b
Show file tree
Hide file tree
Showing 513 changed files with 15,065 additions and 61 deletions.
248 changes: 248 additions & 0 deletions notebooks/Interfaces/ClassEnrichmentCalculationInterface.ipynb
View file
Original file line number Diff line number Diff line change
@@ -0,0 +1,248 @@
{
"cells": [
{
"cell_type": "markdown",
"source": [
"# ClassEnrichmentCalculationInterface Examples\n",
"\n",
"See also [Python docs](https://incatools.github.io/ontology-access-kit/packages/interfaces/class-enrichment.html)\n",
"\n"
],
"metadata": {
"collapsed": false
},
"id": "37b92ff6d4a9d98c"
},
{
"cell_type": "code",
"execution_count": 6,
"outputs": [],
"source": [
"from oaklib.datamodels.input_specification import InputSpecification\n",
"from oaklib import get_adapter\n",
"spec = InputSpecification(\n",
" ontology_resources={\n",
" \"hp\": {\n",
" \"selector\": \"sqlite:obo:hp\"\n",
" },\n",
" },\n",
" association_resources={\n",
" \"hpoa\": {\n",
" \"selector\": \"hpoa:\"\n",
" }\n",
" }\n",
")\n",
"\n",
"adapter = get_adapter(spec)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-14T00:43:15.716905Z",
"start_time": "2024-03-14T00:42:17.829253Z"
}
},
"id": "d603fc57b88cc6b4"
},
{
"cell_type": "code",
"execution_count": 7,
"outputs": [],
"source": [
"from oaklib.interfaces.association_provider_interface import AssociationProviderInterface\n",
"\n",
"if not isinstance(adapter, AssociationProviderInterface):\n",
" raise ValueError(\"Adapter is not an AssociationProviderInterface\")\n"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-14T00:43:15.721279Z",
"start_time": "2024-03-14T00:43:15.717935Z"
}
},
"id": "7e90e7b35311c8b0"
},
{
"cell_type": "code",
"execution_count": 8,
"outputs": [],
"source": [
"from oaklib.datamodels.vocabulary import IS_A\n",
"\n",
"pinna_associations = list(adapter.associations(objects=[\"HP:0000377\"], object_closure_predicates=[IS_A]))"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-14T00:43:16.024951Z",
"start_time": "2024-03-14T00:43:15.734336Z"
}
},
"id": "935a60c956947ad2"
},
{
"cell_type": "code",
"execution_count": 9,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"OMIM:619426 HP:0020206 Simple ear\n",
"OMIM:619426 HP:0000400 Macrotia\n",
"OMIM:619426 HP:0000369 Low-set ears\n",
"OMIM:619354 HP:0100830 Round ear\n",
"OMIM:117650 HP:0000358 Posteriorly rotated ears\n",
"OMIM:117650 HP:0000369 Low-set ears\n",
"OMIM:615546 HP:0008551 Microtia\n",
"OMIM:618076 HP:0009748 Large earlobe\n",
"OMIM:618076 HP:0000369 Low-set ears\n",
"OMIM:618076 HP:0008551 Microtia\n"
]
}
],
"source": [
"for assoc in pinna_associations[0:10]:\n",
" print(assoc.subject, assoc.object, adapter.label(assoc.object))"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-14T00:43:16.035600Z",
"start_time": "2024-03-14T00:43:16.025992Z"
}
},
"id": "b9fea431d59366fb"
},
{
"cell_type": "code",
"execution_count": 10,
"outputs": [
{
"data": {
"text/plain": "1885"
},
"execution_count": 10,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diseases = {assoc.subject for assoc in pinna_associations}\n",
"len(diseases)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-14T00:43:16.044305Z",
"start_time": "2024-03-14T00:43:16.039789Z"
}
},
"id": "5e7bc45185328732"
},
{
"cell_type": "code",
"execution_count": 11,
"outputs": [],
"source": [
"from oaklib.interfaces.class_enrichment_calculation_interface import ClassEnrichmentCalculationInterface\n",
"\n",
"if not isinstance(adapter, ClassEnrichmentCalculationInterface):\n",
" raise ValueError(\"Adapter is not an AssociationProviderInterface\")\n"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-14T00:43:16.063572Z",
"start_time": "2024-03-14T00:43:16.044169Z"
}
},
"id": "ce52323e5f0c095b"
},
{
"cell_type": "code",
"execution_count": 12,
"outputs": [],
"source": [
"results = list(adapter.enriched_classes(\n",
" subjects=diseases,\n",
" object_closure_predicates=[IS_A],\n",
"))"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-14T00:43:38.162127Z",
"start_time": "2024-03-14T00:43:16.052039Z"
}
},
"id": "e397ed9448310f70"
},
{
"cell_type": "code",
"execution_count": 13,
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"ClassEnrichmentResult(class_id='HP:0000347', class_label=None, rank=1, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=738, sample_total=1885, background_count=1138, background_total=12496, ancestor_of_more_informative_result=None, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0009118', class_label=None, rank=2, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=741, sample_total=1885, background_count=1142, background_total=12496, ancestor_of_more_informative_result=True, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0001167', class_label=None, rank=3, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=960, sample_total=1885, background_count=2064, background_total=12496, ancestor_of_more_informative_result=None, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0009116', class_label=None, rank=4, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=749, sample_total=1885, background_count=1161, background_total=12496, ancestor_of_more_informative_result=True, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0000277', class_label=None, rank=5, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=972, sample_total=1885, background_count=1611, background_total=12496, ancestor_of_more_informative_result=True, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0030791', class_label=None, rank=6, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=1008, sample_total=1885, background_count=1700, background_total=12496, ancestor_of_more_informative_result=True, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0000288', class_label=None, rank=7, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=690, sample_total=1885, background_count=991, background_total=12496, ancestor_of_more_informative_result=None, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0200006', class_label=None, rank=8, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=691, sample_total=1885, background_count=980, background_total=12496, ancestor_of_more_informative_result=None, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0000177', class_label=None, rank=9, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=903, sample_total=1885, background_count=1418, background_total=12496, ancestor_of_more_informative_result=True, descendant_of_more_informative_result=None)\n",
"ClassEnrichmentResult(class_id='HP:0002683', class_label=None, rank=10, p_value=0.0, p_value_adjusted=0.0, false_discovery_rate=None, fold_enrichment=None, probability=None, sample_count=812, sample_total=1885, background_count=1475, background_total=12496, ancestor_of_more_informative_result=None, descendant_of_more_informative_result=None)\n"
]
}
],
"source": [
"for r in results[0:10]:\n",
" print(r)"
],
"metadata": {
"collapsed": false,
"ExecuteTime": {
"end_time": "2024-03-14T00:43:38.166018Z",
"start_time": "2024-03-14T00:43:38.162557Z"
}
},
"id": "3a4052bbf6960d51"
},
{
"cell_type": "code",
"execution_count": null,
"outputs": [],
"source": [],
"metadata": {
"collapsed": false
},
"id": "b69c08ab05ab268e"
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 2
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython2",
"version": "2.7.6"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Loading

0 comments on commit b94123b

Please sign in to comment.