Feat/us6.1 mapping utility

.pre-commit-config.yaml

@@ -22,7 +22,7 @@ default_stages:
 repos:
     # Fast Python linter and formatter with auto-fix support
 -   repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.12.7
+    rev: v0.13.0
     hooks:
     -   id: ruff-check
         args: [--fix, --show-fixes]
@@ -42,7 +42,7 @@ repos:
 
     # Official pre-commit-hooks for general checks
 -   repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v5.0.0    # Check for updates regularly
+    rev: v6.0.0    # Check for updates regularly
     hooks:
     -   id: check-added-large-files
         stages: [pre-commit, pre-push]
@@ -71,7 +71,7 @@ repos:
 
     # Format code blocks in documentation files
 -   repo: https://github.com/asottile/blacken-docs
-    rev: 1.19.1
+    rev: 1.20.0
     hooks:
     -   id: blacken-docs
         stages: [pre-commit]

notebooks/chebi_mix_ontology.ipynb

@@ -0,0 +1,254 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import logging\n",
+    "\n",
+    "from ontograph.utils import translate_ids\n",
+    "from ontograph.client import ClientOntology"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "logging.basicConfig(level=logging.INFO)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "PATH_ONTOLOGY_FILE = '../data/out/swiss_lipids_ontology.obo'\n",
+    "PATH_MAPPING_FILE = '../data/out/swiss_lipids_mapping_ids.csv'"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3",
+   "metadata": {},
+   "source": [
+    "## Experimentation"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4",
+   "metadata": {},
+   "source": [
+    "1. Read an ontology file\n",
+    "\n",
+    "2. Read a mapping file:\n",
+    "   - 2.1. Read the mapping file\n",
+    "   - 2.2. Create a LUT.\n",
+    "\n",
+    "3. When look for terms do the following:\n",
+    "   - 3.1. If a LUT exist:\n",
+    "            - Translate the term\n",
+    "   - 3.2. Return the terms of interest in the table.\n",
+    "\n",
+    "4. Apply the operation in the ontology"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5",
+   "metadata": {},
+   "source": [
+    "Use cases\n",
+    "```markdown\n",
+    "\n",
+    "SwisslipidsOntology.common_ancestors('HMDB0000232', 'HMDB0000765', 'HMDB0000342')\n",
+    "['SWL:0000234']\n",
+    "\n",
+    "SwisslipidsOntology.terms_for('HMDB0000232')\n",
+    "['SWL:0000234']\n",
+    "\n",
+    "\n",
+    "SwisslipidsOntology.mappings()\n",
+    "['hmdb', 'lipidmaps', 'metanetx']\n",
+    "\n",
+    "```"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6",
+   "metadata": {},
+   "source": [
+    "### Read ontology"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "swiss_onto = ClientOntology()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8",
+   "metadata": {},
+   "source": [
+    "### Load ontology file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "swiss_onto.load(file_path_ontology=PATH_ONTOLOGY_FILE)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "10",
+   "metadata": {},
+   "source": [
+    "### Load mapping file"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "11",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "swiss_onto.load_mapping(\n",
+    "    filepath=PATH_MAPPING_FILE,\n",
+    "    delimiter='\\t',\n",
+    "    # target_column=\"chebi_id\",\n",
+    "    target_column='swiss_lipid_id',\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "12",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "test_ids_diverse = [\n",
+    "    'CHEBI:70995',  # chebi\n",
+    "    'SLM:000508824',  # swiss lipids\n",
+    "    'HMDB00032',  # hmdb\n",
+    "    'LMGP01030010',  # lipid maps\n",
+    "    'MNXM2990',  # metanetx\n",
+    "    'CHEBI:88888',  # fake chebi id\n",
+    "]\n",
+    "\n",
+    "test_ids_swiss_lipids = [\n",
+    "    'SLM:000048885',\n",
+    "    'SLM:000508824',\n",
+    "    'SLM:000000042',\n",
+    "    'SLM:000048885',\n",
+    "    'SLM:000000288',\n",
+    "]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "13",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "terms_translated = translate_ids(\n",
+    "    # mapping_lut=None,\n",
+    "    mapping_lut=swiss_onto.get_mapping_lut(),\n",
+    "    terms_id=test_ids_diverse,\n",
+    "    # terms_id=test_ids_swiss_lipids\n",
+    ")\n",
+    "\n",
+    "terms_translated"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "14",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for term in swiss_onto.get_terms(terms_translated):\n",
+    "    print(f'\\n{term}')\n",
+    "    for property in term.annotations:\n",
+    "        print(f'\\t{property.property}: {property.literal}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "15",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for term in swiss_onto.get_terms(test_ids_diverse):\n",
+    "    print(f'\\n{term}')\n",
+    "    for property in term.annotations:\n",
+    "        print(f'\\t{property.property}: {property.literal}')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "16",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "swiss_onto.mappings()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "a = swiss_onto.get_mapping_lut()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "ontograph (3.10.18)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.18"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}