COCONUT_mongodb_goodies_1.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "f214cd96",
   "metadata": {},
   "source": [
    "# Explore COCONUT MongoDB Locally - Part 2\n",
    "\n",
    "https://adelenel.ai/sugarfreecoconut\n",
    "\n",
    "## Gist 1 of 3 - What Metadata and Properties are available?\n",
    "\n",
    "20/04/2022"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "45895cf6",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pymongo import MongoClient"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "e82a3ecc",
   "metadata": {},
   "outputs": [],
   "source": [
    "client = MongoClient('localhost',27017)\n",
    "db = client.COCONUT_2021_11"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "3751bd63",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['sourceNaturalProduct',\n",
       " 'pubFingerprintsCounts',\n",
       " 'uniqueNaturalProduct',\n",
       " 'fragment',\n",
       " 'nPDatabase',\n",
       " 'quarantined']"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "db.list_collection_names()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "fba9b6de",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "dict_keys(['_id', 'coconut_id', 'contains_sugar', 'heavy_atom_number', 'inchi', 'inchikey', 'smiles', 'unique_smiles', 'clean_smiles', 'sugar_free_smiles', 'deep_smiles', 'name', 'nameTrustLevel', 'annotationLevel', 'synonyms', 'cas', 'iupac_name', 'contains_ring_sugars', 'contains_linear_sugars', 'collection', 'molecular_formula', 'molecular_weight', 'geoLocation', 'npl_noh_score', 'npl_score', 'npl_sugar_score', 'number_of_carbons', 'number_of_nitrogens', 'number_of_oxygens', 'max_number_of_rings', 'min_number_of_rings', 'sugar_free_heavy_atom_number', 'sugar_free_total_atom_number', 'total_atom_number', 'bond_count', 'found_in_databases', 'xrefs', 'fragments', 'fragmentsWithSugar', 'murko_framework', 'ertlFunctionalFragments', 'ertlFunctionalFragmentsPseudoSmiles', 'pubchemFingerprint', 'pfCounts', 'circularFingerprint', 'extendedFingerprint', 'pubchemBits', 'pubchemBitsString', 'citationDOI', 'taxid', 'textTaxa', 'chemicalSuperClass', 'chemicalClass', 'chemicalSubClass', 'directParentClassification', 'allChemClassifications', 'taxonomyReferenceObjects', 'allTaxa', 'absolute_smiles_sources', 'absolute_smiles', 'allWikidataIds', 'alogp', 'alogp2', 'amralogp', 'apol', 'bcutDescriptor', 'bpol', 'eccentricConnectivityIndexDescriptor', 'fmfDescriptor', 'fsp3', 'fragmentComplexityDescriptor', 'gravitationalIndexHeavyAtoms', 'hBondAcceptorCount', 'hBondDonorCount', 'hybridizationRatioDescriptor', 'kappaShapeIndex1', 'kappaShapeIndex2', 'kappaShapeIndex3', 'manholdlogp', 'petitjeanNumber', 'petitjeanShapeTopo', 'petitjeanShapeGeom', 'lipinskiRuleOf5Failures', 'numberSpiroAtoms', 'vabcDescriptor', 'vertexAdjMagnitude', 'weinerPathNumber', 'weinerPolarityNumber', 'xlogp', 'zagrebIndex', 'topoPSA', 'tpsaEfficiency', '_class'])\n"
     ]
    }
   ],
   "source": [
    "print(db.uniqueNaturalProduct.find({})[0].keys()) #of a single document in the collection"
   ]
  }
 ],
 "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": "3.9.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}