fingerprint_screenout_with_words.ipynb

fingerprint screenout with words.ipynb

{
  "cells": [
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "from rdkit import Chem\nfrom rdkit.Chem import DataStructs",
      "execution_count": 1,
      "outputs": []
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "ms = [Chem.MolFromSmiles(x) for x in ('Cc1ccccc1','Cc1ncccc1')]\nq = Chem.MolFromSmiles('c1ccccc1')\n[x.HasSubstructMatch(q) for x in ms]",
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 2,
          "data": {
            "text/plain": "[True, False]"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "pfps = [Chem.PatternFingerprint(x,fpSize=1024) for x in ms]\nqfp = Chem.PatternFingerprint(q,fpSize=1024)",
      "execution_count": 3,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Check the condition for substructure matching with the pattern fingerprints:"
    },
    {
      "metadata": {
        "trusted": true,
        "scrolled": true
      },
      "cell_type": "code",
      "source": "[x&qfp == qfp for x in pfps]",
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 4,
          "data": {
            "text/plain": "[True, False]"
          },
          "metadata": {}
        }
      ]
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "def convert_bv_to_64bit_ints(fp):\n    ''' use a combination of RDKit+python functionality to convert a\n    fingerprint into a list of 64bit ints \n    '''\n    qt = DataStructs.BitVectToBinaryText(fp)\n    words = [int.from_bytes(qt[i:i+8],'big') for i in range(0,len(qt),8)]\n    return words",
      "execution_count": 5,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Convert the query fp and each of the molecule fps to lists of 64 bit ints"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "qwords = convert_bv_to_64bit_ints(qfp)\npwords = [convert_bv_to_64bit_ints(x) for x in pfps]",
      "execution_count": 6,
      "outputs": []
    },
    {
      "metadata": {},
      "cell_type": "markdown",
      "source": "Here's the simple python way to check the substructure condition using those vectors of ints"
    },
    {
      "metadata": {
        "trusted": true
      },
      "cell_type": "code",
      "source": "[all(x&y==y for x,y in zip(pw,qwords)) for pw in pwords]",
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "execute_result",
          "execution_count": 7,
          "data": {
            "text/plain": "[True, False]"
          },
          "metadata": {}
        }
      ]
    }
  ],
  "metadata": {
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3 (ipykernel)",
      "language": "python"
    },
    "toc": {
      "nav_menu": {},
      "number_sections": true,
      "sideBar": true,
      "skip_h1_title": false,
      "base_numbering": 1,
      "title_cell": "Table of Contents",
      "title_sidebar": "Contents",
      "toc_cell": false,
      "toc_position": {},
      "toc_section_display": true,
      "toc_window_display": false
    },
    "language_info": {
      "name": "python",
      "version": "3.9.12",
      "mimetype": "text/x-python",
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "pygments_lexer": "ipython3",
      "nbconvert_exporter": "python",
      "file_extension": ".py"
    },
    "gist": {
      "id": "",
      "data": {
        "description": "fingerprint_screenout_with_words.ipynb",
        "public": true
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}