Find matches between terms in proposed CaroliO ontology and existing OBO Foundry ontologies

carolio_matches.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "86692f7c-5cdc-4caa-9e4a-7712f99190f2",
   "metadata": {},
   "outputs": [],
   "source": [
    "import bioontologies\n",
    "import ols_client\n",
    "from pyobo.gilda_utils import get_grounder\n",
    "import gilda\n",
    "import json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dfd80e63-9c10-4ba7-8ac5-e49176b9ab1d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO: [2024-01-24 00:21:26] pyobo.api.species - [hso] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:26] pyobo.api.species - [htn] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:27] pyobo.api.species - [ido] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:28] pyobo.api.species - [mf] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:28] pyobo.api.species - [mfoem] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:29] pyobo.api.species - [mfomd] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:32] pyobo.api.species - [mpio] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:38] pyobo.api.species - [oae] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:40] pyobo.api.species - [ohd] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:41] pyobo.api.species - [omrse] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:41] pystow.utils - downloading with urllib from https://github.com/ufbmi/OMRSE/raw/master/omrse-full.obo to /Users/cthoyt/.data/pyobo/raw/omrse/2024-01-10/omrse-full.obo\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading omrse-full.obo: 0.00B [00:00, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "INFO: [2024-01-24 00:21:42] pyobo.api.species - [ontoneo] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:47] pyobo.api.species - [oostt] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:49] pyobo.api.species - [ovae] no cached species found. getting from OBO loader\n",
      "INFO: [2024-01-24 00:21:52] gilda.term - Filtering 2404074 terms for uniqueness...\n",
      "INFO: [2024-01-24 00:21:55] gilda.term - Got 2091018 unique terms...\n"
     ]
    }
   ],
   "source": [
    "grounder = get_grounder([\n",
    "    # add the subset of OBO ontologies about \"health\"\n",
    "    'doid', \n",
    "    'mondo', 'hp', 'symp', 'maxo', 'obi', 'cmo', \n",
    "    # 'cto',  # trash\n",
    "    'disdriv', 'dron', 'exo', \n",
    "    # 'genepio', # can't be loaded\n",
    "    'hso', 'htn', 'ido', 'mf', 'mfoem', 'mfomd', 'mmo',\n",
    "    'mpath', 'mpio', 'ncit', 'oae', 'ogms', 'ohd', 'omrse',\n",
    "    'ontoneo', 'oostt', 'ovae', 'trans', 'vo', 'xco',\n",
    "    'scdo', 'zp', \n",
    "    # extras\n",
    "    \"chebi\",\n",
    "], strict=False, progress=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "16b595ff-dfb5-4ffd-8881-1d17c87daba7",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Should be able to do this, but ROBOT won't parse it as a remote file for some reason\n",
    "# url = \"https://raw.githubusercontent.com/TootooniLab/CaroliO/main/CaroliO.owl\"\n",
    "# g = bioontologies.get_obograph_by_iri(url)\n",
    "\n",
    "with open(\"/Users/cthoyt/Desktop/CaroliO.json\") as file:\n",
    "    data = json.load(file)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "9e352482-7645-4741-b1cd-c2877b66df13",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "## Lexical matching returned results\n",
      "\n",
      "- `CAROLIO:0000411` mild pain\n",
      "  - [`ncit:C136549`](https://bioregistry.io/ncit:C136549) Neck Pain Score 2 (0.54)\n",
      "- `CAROLIO:0000412` moderate pain\n",
      "  - [`ncit:C121394`](https://bioregistry.io/ncit:C121394) Moderate Extremity Pain (0.54)\n",
      "  - [`ncit:C136551`](https://bioregistry.io/ncit:C136551) Neck Pain Score 4 (0.54)\n",
      "- `CAROLIO:0000413` no pain\n",
      "  - [`ncit:C119987`](https://bioregistry.io/ncit:C119987) Had No Pain (0.54)\n",
      "  - [`ncit:C121390`](https://bioregistry.io/ncit:C121390) No Extremity Pain (0.54)\n",
      "  - [`ncit:C136547`](https://bioregistry.io/ncit:C136547) Neck Pain Score 0 (0.54)\n",
      "- `CAROLIO:0000414` severe pain\n",
      "  - [`ncit:C121395`](https://bioregistry.io/ncit:C121395) Severe Extremity Pain (0.54)\n",
      "  - [`ncit:C136553`](https://bioregistry.io/ncit:C136553) Neck Pain Score 6 (0.54)\n",
      "- `CAROLIO:0001000` caroli syndrome\n",
      "  - [`doid:0081394`](https://bioregistry.io/doid:0081394) Caroli syndrome (0.772)\n",
      "  - [`mondo:0018808`](https://bioregistry.io/mondo:0018808) Caroli syndrome (0.772)\n",
      "- `CAROLIO:0003100` endoscopic treatment\n",
      "  - [`ncit:C16546`](https://bioregistry.io/ncit:C16546) Endoscopic Procedure (0.54)\n",
      "- `CAROLIO:0003120` endoscopic retrograde cholangiopancreatography\n",
      "  - [`maxo:0035049`](https://bioregistry.io/maxo:0035049) endoscopic retrograde cholangiopancreatography (0.778)\n",
      "  - [`ncit:C16430`](https://bioregistry.io/ncit:C16430) Endoscopic Retrograde Cholangiopancreatography (0.762)\n",
      "- `CAROLIO:0003200` interventional radiology procedure\n",
      "  - [`ncit:C63334`](https://bioregistry.io/ncit:C63334) Interventional Radiology Procedure (0.762)\n",
      "- `CAROLIO:0003210` locoregional therapy\n",
      "  - [`ncit:C25388`](https://bioregistry.io/ncit:C25388) Local-Regional (0.54)\n",
      "  - [`ncit:C94796`](https://bioregistry.io/ncit:C94796) Locally Recurrent Malignant Neoplasm (0.54)\n",
      "- `CAROLIO:0003220` paracentesis\n",
      "  - [`maxo:0035106`](https://bioregistry.io/maxo:0035106) paracentesis (0.778)\n",
      "  - [`ncit:C15310`](https://bioregistry.io/ncit:C15310) Paracentesis (0.762)\n",
      "- `CAROLIO:0003250` transjugular intrahepatic portosystemic shunt\n",
      "  - [`ncit:C126288`](https://bioregistry.io/ncit:C126288) Transjugular Intrahepatic Portosystemic Shunt (0.762)\n",
      "- `CAROLIO:0003300` pharmaceutical treatment\n",
      "  - [`maxo:0000058`](https://bioregistry.io/maxo:0000058) pharmacotherapy (0.556)\n",
      "- `CAROLIO:0003310` antibiotic treatment\n",
      "  - [`ncit:C258`](https://bioregistry.io/ncit:C258) Antibiotic (0.762)\n",
      "  - [`chebi:33281`](https://bioregistry.io/chebi:33281) antimicrobial agent (0.556)\n",
      "  - [`xco:0000482`](https://bioregistry.io/xco:0000482) antimicrobial agent (0.556)\n",
      "- `CAROLIO:0003320` antiemetic treatment\n",
      "  - [`chebi:50919`](https://bioregistry.io/chebi:50919) antiemetic (0.778)\n",
      "  - [`xco:0001245`](https://bioregistry.io/xco:0001245) antiemetic (0.778)\n",
      "  - [`ncit:C267`](https://bioregistry.io/ncit:C267) Antiemetic Agent (0.556)\n",
      "- `CAROLIO:0003330` bile acid treatment\n",
      "  - [`chebi:3098`](https://bioregistry.io/chebi:3098) bile acid (0.778)\n",
      "  - [`chebi:22868`](https://bioregistry.io/chebi:22868) bile salt (0.549)\n",
      "  - [`ncit:C74800`](https://bioregistry.io/ncit:C74800) Bile Acid Measurement (0.54)\n",
      "- `CAROLIO:0003340` chemotherapy\n",
      "  - [`maxo:0000647`](https://bioregistry.io/maxo:0000647) chemotherapy (0.778)\n",
      "  - [`ncit:C15632`](https://bioregistry.io/ncit:C15632) Chemotherapy (0.762)\n",
      "- `CAROLIO:0003350` diuretics treatment\n",
      "  - [`chebi:35498`](https://bioregistry.io/chebi:35498) diuretic (0.778)\n",
      "  - [`xco:0000122`](https://bioregistry.io/xco:0000122) diuretic (0.778)\n",
      "  - [`ncit:C448`](https://bioregistry.io/ncit:C448) Diuretic (0.762)\n",
      "- `CAROLIO:0003360` octreotide treatment\n",
      "  - [`chebi:7726`](https://bioregistry.io/chebi:7726) octreotide (0.778)\n",
      "  - [`ncit:C711`](https://bioregistry.io/ncit:C711) Octreotide (0.762)\n",
      "- `CAROLIO:0003370` proton pump inhibitor treatment\n",
      "  - [`xco:0000577`](https://bioregistry.io/xco:0000577) proton pump inhibitor (0.778)\n",
      "  - [`ncit:C29723`](https://bioregistry.io/ncit:C29723) Proton Pump Inhibitor (0.762)\n",
      "  - [`chebi:49200`](https://bioregistry.io/chebi:49200) EC 3.6.3.10 (H(+)/K(+)-exchanging ATPase) inhibitor (0.556)\n",
      "- `CAROLIO:0003380` pruritus treatment\n",
      "  - [`hp:0000989`](https://bioregistry.io/hp:0000989) Pruritus (0.762)\n",
      "  - [`ncit:C3344`](https://bioregistry.io/ncit:C3344) Pruritus (0.762)\n",
      "  - [`scdo:0000935`](https://bioregistry.io/scdo:0000935) Pruritus (0.762)\n",
      "  - [`symp:0000432`](https://bioregistry.io/symp:0000432) itching (0.556)\n",
      "  - [`ncit:C58006`](https://bioregistry.io/ncit:C58006) Pruritus, CTCAE (0.54)\n",
      "- `CAROLIO:0003400` radiation therapy\n",
      "  - [`maxo:0000014`](https://bioregistry.io/maxo:0000014) radiation therapy (0.778)\n",
      "  - [`ncit:C15313`](https://bioregistry.io/ncit:C15313) Radiation Therapy (0.762)\n",
      "- `CAROLIO:0003500` surgical treatment\n",
      "  - [`ncit:C15329`](https://bioregistry.io/ncit:C15329) Surgical Procedure (0.54)\n",
      "- `CAROLIO:0003510` organ transplant\n",
      "  - [`ncit:C122934`](https://bioregistry.io/ncit:C122934) Organ Graft (0.54)\n",
      "- `CAROLIO:0003520` roux-en-y\n",
      "  - [`ncit:C51756`](https://bioregistry.io/ncit:C51756) Roux-en-Y Anastomosis (0.549)\n",
      "- `CAROLIO:0003530` surgical resection\n",
      "  - [`maxo:0000448`](https://bioregistry.io/maxo:0000448) surgical resection (0.778)\n",
      "  - [`ncit:C158758`](https://bioregistry.io/ncit:C158758) Resection (0.54)\n",
      "\n",
      "## Lexical matching returned no results\n",
      "\n",
      "- `CAROLIO:0000400` value partition\n",
      "- `CAROLIO:0000410` pain scale\n",
      "- `CAROLIO:0000420` symptom recurrence status\n",
      "- `CAROLIO:0000421` non-recurrent symptom status\n",
      "- `CAROLIO:0000422` recurrent symptom status\n",
      "- `CAROLIO:0002000` variceal bleeding\n",
      "- `CAROLIO:0003110` endoscopic band ligation\n",
      "- `CAROLIO:0003121` biliary drainage\n",
      "- `CAROLIO:0003122` biliary dilatation\n",
      "- `CAROLIO:0003123` biliary stent placement\n",
      "- `CAROLIO:0003124` gallstones removal\n",
      "- `CAROLIO:0003230` percutaneous aspiration and drainage\n",
      "- `CAROLIO:0003240` percutaneous transhepatic cholangiogram\n"
     ]
    }
   ],
   "source": [
    "safe = []\n",
    "\n",
    "print(\"## Lexical matching returned results\\n\")\n",
    "\n",
    "for graph in data['graphs']:\n",
    "    for node in sorted(graph['nodes'], key=lambda n: n['id']):\n",
    "        id = node['id']\n",
    "        if not id.startswith(\"http://purl.obolibrary.org/obo/CAROLIO_\"):\n",
    "            continue\n",
    "        luid = id.removeprefix(\"http://purl.obolibrary.org/obo/CAROLIO_\")\n",
    "        lbl = node['lbl']\n",
    "        meta = node.get(\"meta\", {})\n",
    "        synonyms = [s['val'] for s in meta.get(\"synonyms\", [])]\n",
    "        #print(node)\n",
    "        node_type = node['type']\n",
    "        if node_type == \"PROPERTY\":\n",
    "            continue\n",
    "        #xx = client.search(lbl)\n",
    "\n",
    "        results = grounder.ground(lbl)\n",
    "        if not results and lbl.endswith(\"treatment\"):\n",
    "            results = grounder.ground(lbl.removesuffix(\"treatment\").strip())\n",
    "        if not results and lbl.endswith(\"therapy\"):\n",
    "            results = grounder.ground(lbl.removesuffix(\"therapy\").strip())\n",
    "        if not results:\n",
    "            safe.append((luid, lbl)) \n",
    "        else:\n",
    "            print(f'- `CAROLIO:{luid}`', lbl)\n",
    "        for res in results:\n",
    "            curie = res.term.get_curie()\n",
    "            print(f'  - [`{curie}`](https://bioregistry.io/{curie}) {res.term.entry_name} ({round(res.score, 3)})')\n",
    "\n",
    "print(\"\\n## Lexical matching returned no results\\n\")\n",
    "for luid, lbl in safe:\n",
    "    print(f'- `CAROLIO:{luid}`', lbl)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}