Datasets
Models
Downloads: 1
Diff of
/DEMO/case-study-II-Virtual-Screening-for-BindingDB-IC50.ipynb
[000000]
..
[0a9449]
Switch to unified view
| a | b/DEMO/case-study-II-Virtual-Screening-for-BindingDB-IC50.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 1, |
||
| 6 | "metadata": {}, |
||
| 7 | "outputs": [], |
||
| 8 | "source": [ |
||
| 9 | "import os\n", |
||
| 10 | "os.chdir('../')" |
||
| 11 | ] |
||
| 12 | }, |
||
| 13 | { |
||
| 14 | "cell_type": "code", |
||
| 15 | "execution_count": 2, |
||
| 16 | "metadata": { |
||
| 17 | "scrolled": false |
||
| 18 | }, |
||
| 19 | "outputs": [ |
||
| 20 | { |
||
| 21 | "name": "stdout", |
||
| 22 | "output_type": "stream", |
||
| 23 | "text": [ |
||
| 24 | "Downloading...\n", |
||
| 25 | "Loading customized repurposing dataset...\n", |
||
| 26 | "Beginning Downloading Pretrained Model...\n", |
||
| 27 | "Note: if you have already download the pretrained model before, please stop the program and set the input parameter 'pretrained_dir' to the path\n", |
||
| 28 | "Dataset already downloaded in the local system...\n", |
||
| 29 | "Using pretrained model and making predictions...\n", |
||
| 30 | "virtual screening...\n", |
||
| 31 | "Drug Target Interaction Prediction Mode...\n", |
||
| 32 | "in total: 100 drug-target pairs\n", |
||
| 33 | "encoding drug...\n", |
||
| 34 | "unique drugs: 100\n", |
||
| 35 | "encoding protein...\n", |
||
| 36 | "unique target sequence: 91\n", |
||
| 37 | "Done.\n", |
||
| 38 | "predicting...\n", |
||
| 39 | "---------------\n", |
||
| 40 | "Predictions from model 1 with drug encoding MPNN and target encoding CNN are done...\n", |
||
| 41 | "-------------\n", |
||
| 42 | "virtual screening...\n", |
||
| 43 | "Drug Target Interaction Prediction Mode...\n", |
||
| 44 | "in total: 100 drug-target pairs\n", |
||
| 45 | "encoding drug...\n", |
||
| 46 | "unique drugs: 100\n", |
||
| 47 | "encoding protein...\n", |
||
| 48 | "unique target sequence: 91\n", |
||
| 49 | "Done.\n", |
||
| 50 | "predicting...\n", |
||
| 51 | "---------------\n", |
||
| 52 | "Predictions from model 2 with drug encoding CNN and target encoding CNN are done...\n", |
||
| 53 | "-------------\n", |
||
| 54 | "virtual screening...\n", |
||
| 55 | "Drug Target Interaction Prediction Mode...\n", |
||
| 56 | "in total: 100 drug-target pairs\n", |
||
| 57 | "encoding drug...\n", |
||
| 58 | "unique drugs: 100\n", |
||
| 59 | "encoding protein...\n", |
||
| 60 | "unique target sequence: 91\n", |
||
| 61 | "Done.\n", |
||
| 62 | "predicting...\n", |
||
| 63 | "---------------\n", |
||
| 64 | "Predictions from model 3 with drug encoding Morgan and target encoding CNN are done...\n", |
||
| 65 | "-------------\n", |
||
| 66 | "virtual screening...\n", |
||
| 67 | "Drug Target Interaction Prediction Mode...\n", |
||
| 68 | "in total: 100 drug-target pairs\n", |
||
| 69 | "encoding drug...\n", |
||
| 70 | "unique drugs: 100\n", |
||
| 71 | "encoding protein...\n", |
||
| 72 | "unique target sequence: 91\n", |
||
| 73 | "-- Encoding AAC takes time. Time Reference: 24s for ~100 sequences in a CPU.\t\t\t\t Calculate your time by the unique target sequence #, instead of the entire dataset.\n", |
||
| 74 | "Done.\n", |
||
| 75 | "predicting...\n", |
||
| 76 | "---------------\n", |
||
| 77 | "Predictions from model 4 with drug encoding Morgan and target encoding AAC are done...\n", |
||
| 78 | "-------------\n", |
||
| 79 | "virtual screening...\n", |
||
| 80 | "Drug Target Interaction Prediction Mode...\n", |
||
| 81 | "in total: 100 drug-target pairs\n", |
||
| 82 | "encoding drug...\n", |
||
| 83 | "unique drugs: 100\n", |
||
| 84 | "encoding protein...\n", |
||
| 85 | "unique target sequence: 91\n", |
||
| 86 | "-- Encoding AAC takes time. Time Reference: 24s for ~100 sequences in a CPU.\t\t\t\t Calculate your time by the unique target sequence #, instead of the entire dataset.\n", |
||
| 87 | "Done.\n", |
||
| 88 | "predicting...\n", |
||
| 89 | "---------------\n", |
||
| 90 | "Predictions from model 5 with drug encoding Daylight and target encoding AAC are done...\n", |
||
| 91 | "-------------\n", |
||
| 92 | "models prediction finished...\n", |
||
| 93 | "aggregating results...\n", |
||
| 94 | "virtual screening...\n", |
||
| 95 | "Drug Target Interaction Prediction Mode...\n", |
||
| 96 | "in total: 100 drug-target pairs\n", |
||
| 97 | "encoding drug...\n", |
||
| 98 | "unique drugs: 100\n", |
||
| 99 | "encoding protein...\n", |
||
| 100 | "unique target sequence: 91\n", |
||
| 101 | "-- Encoding AAC takes time. Time Reference: 24s for ~100 sequences in a CPU.\t\t\t\t Calculate your time by the unique target sequence #, instead of the entire dataset.\n", |
||
| 102 | "Done.\n", |
||
| 103 | "predicting...\n", |
||
| 104 | "---------------\n", |
||
| 105 | "Virtual Screening Result\n", |
||
| 106 | "+------+-----------+-------------+---------------+\n", |
||
| 107 | "| Rank | Drug Name | Target Name | Binding Score |\n", |
||
| 108 | "+------+-----------+-------------+---------------+\n", |
||
| 109 | "| 1 | Drug 80 | Target 80 | 0.58 |\n", |
||
| 110 | "| 2 | Drug 86 | Target 86 | 0.85 |\n", |
||
| 111 | "| 3 | Drug 4 | Target 4 | 0.89 |\n", |
||
| 112 | "| 4 | Drug 89 | Target 89 | 1.62 |\n", |
||
| 113 | "| 5 | Drug 44 | Target 44 | 1.67 |\n", |
||
| 114 | "| 6 | Drug 58 | Target 58 | 1.87 |\n", |
||
| 115 | "| 7 | Drug 35 | Target 35 | 2.74 |\n", |
||
| 116 | "| 8 | Drug 43 | Target 43 | 2.98 |\n", |
||
| 117 | "| 9 | Drug 23 | Target 23 | 3.95 |\n", |
||
| 118 | "| 10 | Drug 25 | Target 25 | 4.55 |\n", |
||
| 119 | "| 11 | Drug 15 | Target 15 | 4.86 |\n", |
||
| 120 | "| 12 | Drug 97 | Target 97 | 5.03 |\n", |
||
| 121 | "| 13 | Drug 24 | Target 24 | 6.31 |\n", |
||
| 122 | "| 14 | Drug 47 | Target 47 | 6.53 |\n", |
||
| 123 | "| 15 | Drug 48 | Target 48 | 11.22 |\n", |
||
| 124 | "| 16 | Drug 50 | Target 50 | 11.35 |\n", |
||
| 125 | "| 17 | Drug 92 | Target 92 | 16.71 |\n", |
||
| 126 | "| 18 | Drug 66 | Target 66 | 17.49 |\n", |
||
| 127 | "| 19 | Drug 26 | Target 26 | 18.03 |\n", |
||
| 128 | "| 20 | Drug 87 | Target 87 | 18.64 |\n", |
||
| 129 | "| 21 | Drug 93 | Target 93 | 19.38 |\n", |
||
| 130 | "| 22 | Drug 20 | Target 20 | 23.28 |\n", |
||
| 131 | "| 23 | Drug 49 | Target 49 | 27.10 |\n", |
||
| 132 | "| 24 | Drug 30 | Target 30 | 28.13 |\n", |
||
| 133 | "| 25 | Drug 33 | Target 33 | 33.48 |\n", |
||
| 134 | "| 26 | Drug 13 | Target 13 | 33.54 |\n", |
||
| 135 | "| 27 | Drug 45 | Target 45 | 34.65 |\n", |
||
| 136 | "| 28 | Drug 29 | Target 29 | 45.16 |\n", |
||
| 137 | "| 29 | Drug 72 | Target 72 | 46.54 |\n", |
||
| 138 | "| 30 | Drug 28 | Target 28 | 55.87 |\n", |
||
| 139 | "checkout ./save_folder/results_aggregation/virtual_screening.txt for the whole list\n", |
||
| 140 | "\n" |
||
| 141 | ] |
||
| 142 | } |
||
| 143 | ], |
||
| 144 | "source": [ |
||
| 145 | "from DeepPurpose import oneliner\n", |
||
| 146 | "from DeepPurpose.dataset import *\n", |
||
| 147 | "oneliner.virtual_screening(*load_IC50_1000_Samples())" |
||
| 148 | ] |
||
| 149 | }, |
||
| 150 | { |
||
| 151 | "cell_type": "code", |
||
| 152 | "execution_count": null, |
||
| 153 | "metadata": {}, |
||
| 154 | "outputs": [], |
||
| 155 | "source": [] |
||
| 156 | } |
||
| 157 | ], |
||
| 158 | "metadata": { |
||
| 159 | "kernelspec": { |
||
| 160 | "display_name": "Python [conda env:DeepPurpose]", |
||
| 161 | "language": "python", |
||
| 162 | "name": "conda-env-DeepPurpose-py" |
||
| 163 | }, |
||
| 164 | "language_info": { |
||
| 165 | "codemirror_mode": { |
||
| 166 | "name": "ipython", |
||
| 167 | "version": 3 |
||
| 168 | }, |
||
| 169 | "file_extension": ".py", |
||
| 170 | "mimetype": "text/x-python", |
||
| 171 | "name": "python", |
||
| 172 | "nbconvert_exporter": "python", |
||
| 173 | "pygments_lexer": "ipython3", |
||
| 174 | "version": "3.7.7" |
||
| 175 | } |
||
| 176 | }, |
||
| 177 | "nbformat": 4, |
||
| 178 | "nbformat_minor": 4 |
||
| 179 | } |