Datasets
Models
Downloads: 1
Diff of
/Code/Drug Discovery/Meta-Llama-3/SMILES to SELFIES estimator.ipynb
[000000]
..
[404218]
Switch to unified view
| a | b/Code/Drug Discovery/Meta-Llama-3/SMILES to SELFIES estimator.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "nbformat": 4, |
||
| 3 | "nbformat_minor": 0, |
||
| 4 | "metadata": { |
||
| 5 | "colab": { |
||
| 6 | "provenance": [], |
||
| 7 | "machine_shape": "hm" |
||
| 8 | }, |
||
| 9 | "kernelspec": { |
||
| 10 | "name": "python3", |
||
| 11 | "display_name": "Python 3" |
||
| 12 | }, |
||
| 13 | "language_info": { |
||
| 14 | "name": "python" |
||
| 15 | } |
||
| 16 | }, |
||
| 17 | "cells": [ |
||
| 18 | { |
||
| 19 | "cell_type": "code", |
||
| 20 | "execution_count": 1, |
||
| 21 | "metadata": { |
||
| 22 | "colab": { |
||
| 23 | "base_uri": "https://localhost:8080/", |
||
| 24 | "height": 0 |
||
| 25 | }, |
||
| 26 | "id": "gwcBUTqt0Uuz", |
||
| 27 | "outputId": "c97a5433-ce1a-440f-888d-0c2ccbbc4a1a" |
||
| 28 | }, |
||
| 29 | "outputs": [ |
||
| 30 | { |
||
| 31 | "output_type": "stream", |
||
| 32 | "name": "stdout", |
||
| 33 | "text": [ |
||
| 34 | "Collecting selfies\n", |
||
| 35 | " Downloading selfies-2.1.1-py3-none-any.whl (35 kB)\n", |
||
| 36 | "Installing collected packages: selfies\n", |
||
| 37 | "Successfully installed selfies-2.1.1\n" |
||
| 38 | ] |
||
| 39 | } |
||
| 40 | ], |
||
| 41 | "source": [ |
||
| 42 | "# !pip install selfies --upgrade\n", |
||
| 43 | "# github, aspuru-guzik-group/selfies, https://github.com/aspuru-guzik-group/selfies" |
||
| 44 | ] |
||
| 45 | }, |
||
| 46 | { |
||
| 47 | "cell_type": "code", |
||
| 48 | "source": [ |
||
| 49 | "import selfies as sf\n", |
||
| 50 | "\n", |
||
| 51 | "adenine = \"Nc1c2ncNc2ncn1\"\n", |
||
| 52 | "\n", |
||
| 53 | "# SMILES -> SELFIES -> SMILES translation\n", |
||
| 54 | "try:\n", |
||
| 55 | " adenine_sf = sf.encoder(adenine) #\n", |
||
| 56 | " adenine_smi = sf.decoder(adenine_sf) # NC1=NC=NC2=C1N=CN2\n", |
||
| 57 | "except sf.EncoderError:\n", |
||
| 58 | " pass # sf.encoder error!\n", |
||
| 59 | "except sf.DecoderError:\n", |
||
| 60 | " pass # sf.decoder error!\n", |
||
| 61 | "\n", |
||
| 62 | "len_adenine = sf.len_selfies(adenine_sf) # 8\n", |
||
| 63 | "\n", |
||
| 64 | "symbols_adenine = list(sf.split_selfies(adenine_sf))\n", |
||
| 65 | "# ['[C]', '[=C]', '[C]', '[=C]', '[C]', '[=C]', '[Ring1]', '[=Branch1]']\n", |
||
| 66 | "print(\"SMILES =\", adenine_smi)\n", |
||
| 67 | "print(\"SELFIES =\", adenine_sf)" |
||
| 68 | ], |
||
| 69 | "metadata": { |
||
| 70 | "colab": { |
||
| 71 | "base_uri": "https://localhost:8080/", |
||
| 72 | "height": 0 |
||
| 73 | }, |
||
| 74 | "id": "m9c5VU9i0eEh", |
||
| 75 | "outputId": "2253edd6-ecf5-4282-e83f-27e6aa1e2708" |
||
| 76 | }, |
||
| 77 | "execution_count": 8, |
||
| 78 | "outputs": [ |
||
| 79 | { |
||
| 80 | "output_type": "stream", |
||
| 81 | "name": "stdout", |
||
| 82 | "text": [ |
||
| 83 | "SMILES = NC1=C2N=CNC2=NC=N1\n", |
||
| 84 | "SELFIES = [N][C][=C][N][=C][N][C][Ring1][Branch1][=N][C][=N][Ring1][=Branch2]\n" |
||
| 85 | ] |
||
| 86 | } |
||
| 87 | ] |
||
| 88 | } |
||
| 89 | ] |
||
| 90 | } |