Datasets
Models
Downloads: 1
Diff of
/notebooks/mapping_covid.ipynb
[000000]
..
[7d5693]
Switch to unified view
| a | b/notebooks/mapping_covid.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 1, |
||
| 6 | "metadata": {}, |
||
| 7 | "outputs": [], |
||
| 8 | "source": [ |
||
| 9 | "%load_ext autoreload\n", |
||
| 10 | "%autoreload 2\n", |
||
| 11 | "\n", |
||
| 12 | "%matplotlib inline" |
||
| 13 | ] |
||
| 14 | }, |
||
| 15 | { |
||
| 16 | "cell_type": "code", |
||
| 17 | "execution_count": 2, |
||
| 18 | "metadata": {}, |
||
| 19 | "outputs": [], |
||
| 20 | "source": [ |
||
| 21 | "import os, sys" |
||
| 22 | ] |
||
| 23 | }, |
||
| 24 | { |
||
| 25 | "cell_type": "code", |
||
| 26 | "execution_count": 3, |
||
| 27 | "metadata": {}, |
||
| 28 | "outputs": [], |
||
| 29 | "source": [ |
||
| 30 | "import pylab as plt\n", |
||
| 31 | "import matplotlib\n", |
||
| 32 | "\n", |
||
| 33 | "import numpy as np\n", |
||
| 34 | "import pandas as pd" |
||
| 35 | ] |
||
| 36 | }, |
||
| 37 | { |
||
| 38 | "cell_type": "code", |
||
| 39 | "execution_count": 4, |
||
| 40 | "metadata": {}, |
||
| 41 | "outputs": [ |
||
| 42 | { |
||
| 43 | "name": "stderr", |
||
| 44 | "output_type": "stream", |
||
| 45 | "text": [ |
||
| 46 | "2022-03-24 14:40:01.676 | WARNING | pyMultiOmics.reactome:get_neo4j_driver:14 - Using a default neo4j server: bolt://localhost:7687\n", |
||
| 47 | "2022-03-24 14:40:01.676 | WARNING | pyMultiOmics.reactome:get_neo4j_driver:19 - Using a default neo4j username or password: neo4j\n", |
||
| 48 | "2022-03-24 14:40:01.677 | INFO | pyMultiOmics.reactome:get_neo4j_driver:24 - Created graph database driver for bolt://localhost:7687 (neo4j)\n" |
||
| 49 | ] |
||
| 50 | } |
||
| 51 | ], |
||
| 52 | "source": [ |
||
| 53 | "sys.path.append('..')\n", |
||
| 54 | "\n", |
||
| 55 | "from pyMultiOmics.base import SingleOmicsData, MultiOmicsData\n", |
||
| 56 | "from pyMultiOmics.constants import HOMO_SAPIENS, PROTEINS, COMPOUNDS, REACTIONS\n", |
||
| 57 | "from pyMultiOmics.mapping import Mapper\n", |
||
| 58 | "from pyMultiOmics.common import set_log_level_info, set_log_level_debug, download_file, extract_zip_file" |
||
| 59 | ] |
||
| 60 | }, |
||
| 61 | { |
||
| 62 | "cell_type": "markdown", |
||
| 63 | "metadata": {}, |
||
| 64 | "source": [ |
||
| 65 | "# Demonstration of pyMultiOmics mapping" |
||
| 66 | ] |
||
| 67 | }, |
||
| 68 | { |
||
| 69 | "cell_type": "markdown", |
||
| 70 | "metadata": {}, |
||
| 71 | "source": [ |
||
| 72 | "## Load the processed Covid data from [1]\n", |
||
| 73 | "\n", |
||
| 74 | "[1] [Shen, Bo, et al. \"Proteomic and metabolomic characterization of COVID-19 patient sera.\" Cell 182.1 (2020): 59-72.](https://www.sciencedirect.com/science/article/pii/S0092867420306279?casa_token=wKwWn9P4MK0AAAAA:v8z5MVnQ1ONrcatncCsigSDoxeOq2ZOcN4da9SofGDcpeDqrC76QK8yNKrKtVUrMWBBAntI8)" |
||
| 75 | ] |
||
| 76 | }, |
||
| 77 | { |
||
| 78 | "cell_type": "code", |
||
| 79 | "execution_count": 5, |
||
| 80 | "metadata": {}, |
||
| 81 | "outputs": [ |
||
| 82 | { |
||
| 83 | "name": "stderr", |
||
| 84 | "output_type": "stream", |
||
| 85 | "text": [ |
||
| 86 | "2022-03-24 14:40:02.949 | INFO | pyMultiOmics.common:download_file:59 - Downloading covid19_dualomics_data.zip\n", |
||
| 87 | "551KB [00:00, 8.89kKB/s] \n", |
||
| 88 | "2022-03-24 14:40:03.061 | INFO | pyMultiOmics.common:extract_zip_file:71 - Extracting covid19_dualomics_data.zip\n", |
||
| 89 | "100%|█████████████████████████████████████████████████████████████████████████████████| 12/12 [00:00<00:00, 1191.03it/s]\n", |
||
| 90 | "2022-03-24 14:40:03.075 | INFO | pyMultiOmics.common:extract_zip_file:77 - Deleting covid19_dualomics_data.zip\n" |
||
| 91 | ] |
||
| 92 | } |
||
| 93 | ], |
||
| 94 | "source": [ |
||
| 95 | "url = 'https://github.com/glasgowcompbio/pyMultiOmics-data/raw/main/covid19_dualomics_data.zip'\n", |
||
| 96 | "out_file = download_file(url)\n", |
||
| 97 | "extract_zip_file(out_file)" |
||
| 98 | ] |
||
| 99 | }, |
||
| 100 | { |
||
| 101 | "cell_type": "code", |
||
| 102 | "execution_count": 6, |
||
| 103 | "metadata": {}, |
||
| 104 | "outputs": [ |
||
| 105 | { |
||
| 106 | "data": { |
||
| 107 | "text/plain": [ |
||
| 108 | "'/Users/joewandy/Work/git/pyMultiOmics/notebooks/covid19_dualomics_data'" |
||
| 109 | ] |
||
| 110 | }, |
||
| 111 | "execution_count": 6, |
||
| 112 | "metadata": {}, |
||
| 113 | "output_type": "execute_result" |
||
| 114 | } |
||
| 115 | ], |
||
| 116 | "source": [ |
||
| 117 | "DATA_FOLDER = os.path.abspath(os.path.join('covid19_dualomics_data'))\n", |
||
| 118 | "DATA_FOLDER" |
||
| 119 | ] |
||
| 120 | }, |
||
| 121 | { |
||
| 122 | "cell_type": "markdown", |
||
| 123 | "metadata": {}, |
||
| 124 | "source": [ |
||
| 125 | "Read proteomics data" |
||
| 126 | ] |
||
| 127 | }, |
||
| 128 | { |
||
| 129 | "cell_type": "code", |
||
| 130 | "execution_count": 7, |
||
| 131 | "metadata": {}, |
||
| 132 | "outputs": [], |
||
| 133 | "source": [ |
||
| 134 | "protein_df = pd.read_csv(os.path.join(DATA_FOLDER, 'protein_data.csv'), index_col='Identifier')\n", |
||
| 135 | "protein_design = pd.read_csv(os.path.join(DATA_FOLDER, 'protein_design.csv'), index_col='sample')" |
||
| 136 | ] |
||
| 137 | }, |
||
| 138 | { |
||
| 139 | "cell_type": "code", |
||
| 140 | "execution_count": 8, |
||
| 141 | "metadata": {}, |
||
| 142 | "outputs": [ |
||
| 143 | { |
||
| 144 | "data": { |
||
| 145 | "text/html": [ |
||
| 146 | "<div>\n", |
||
| 147 | "<style scoped>\n", |
||
| 148 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 149 | " vertical-align: middle;\n", |
||
| 150 | " }\n", |
||
| 151 | "\n", |
||
| 152 | " .dataframe tbody tr th {\n", |
||
| 153 | " vertical-align: top;\n", |
||
| 154 | " }\n", |
||
| 155 | "\n", |
||
| 156 | " .dataframe thead th {\n", |
||
| 157 | " text-align: right;\n", |
||
| 158 | " }\n", |
||
| 159 | "</style>\n", |
||
| 160 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 161 | " <thead>\n", |
||
| 162 | " <tr style=\"text-align: right;\">\n", |
||
| 163 | " <th></th>\n", |
||
| 164 | " <th>h_F1_131N</th>\n", |
||
| 165 | " <th>h_F1_131C</th>\n", |
||
| 166 | " <th>h_F1_132C</th>\n", |
||
| 167 | " <th>h_F2_131N</th>\n", |
||
| 168 | " <th>h_F2_131C</th>\n", |
||
| 169 | " <th>h_F2_132C</th>\n", |
||
| 170 | " <th>h_F3_131N</th>\n", |
||
| 171 | " <th>h_F3_131C</th>\n", |
||
| 172 | " <th>h_F3_132C</th>\n", |
||
| 173 | " <th>h_F4_131N</th>\n", |
||
| 174 | " <th>...</th>\n", |
||
| 175 | " <th>s_F3_128N</th>\n", |
||
| 176 | " <th>s_F3_128C</th>\n", |
||
| 177 | " <th>s_F3_129C</th>\n", |
||
| 178 | " <th>s_F4_128N</th>\n", |
||
| 179 | " <th>s_F4_128C</th>\n", |
||
| 180 | " <th>s_F5_128N</th>\n", |
||
| 181 | " <th>s_F5_128C</th>\n", |
||
| 182 | " <th>s_F6_128N</th>\n", |
||
| 183 | " <th>s_F6_128C</th>\n", |
||
| 184 | " <th>s_F6_133N</th>\n", |
||
| 185 | " </tr>\n", |
||
| 186 | " <tr>\n", |
||
| 187 | " <th>Identifier</th>\n", |
||
| 188 | " <th></th>\n", |
||
| 189 | " <th></th>\n", |
||
| 190 | " <th></th>\n", |
||
| 191 | " <th></th>\n", |
||
| 192 | " <th></th>\n", |
||
| 193 | " <th></th>\n", |
||
| 194 | " <th></th>\n", |
||
| 195 | " <th></th>\n", |
||
| 196 | " <th></th>\n", |
||
| 197 | " <th></th>\n", |
||
| 198 | " <th></th>\n", |
||
| 199 | " <th></th>\n", |
||
| 200 | " <th></th>\n", |
||
| 201 | " <th></th>\n", |
||
| 202 | " <th></th>\n", |
||
| 203 | " <th></th>\n", |
||
| 204 | " <th></th>\n", |
||
| 205 | " <th></th>\n", |
||
| 206 | " <th></th>\n", |
||
| 207 | " <th></th>\n", |
||
| 208 | " <th></th>\n", |
||
| 209 | " </tr>\n", |
||
| 210 | " </thead>\n", |
||
| 211 | " <tbody>\n", |
||
| 212 | " <tr>\n", |
||
| 213 | " <th>P04114</th>\n", |
||
| 214 | " <td>0.750</td>\n", |
||
| 215 | " <td>0.853</td>\n", |
||
| 216 | " <td>0.822</td>\n", |
||
| 217 | " <td>1.191</td>\n", |
||
| 218 | " <td>1.175</td>\n", |
||
| 219 | " <td>1.078</td>\n", |
||
| 220 | " <td>0.693</td>\n", |
||
| 221 | " <td>0.947</td>\n", |
||
| 222 | " <td>0.931</td>\n", |
||
| 223 | " <td>1.057</td>\n", |
||
| 224 | " <td>...</td>\n", |
||
| 225 | " <td>1.044</td>\n", |
||
| 226 | " <td>1.305</td>\n", |
||
| 227 | " <td>1.657</td>\n", |
||
| 228 | " <td>1.323</td>\n", |
||
| 229 | " <td>1.624</td>\n", |
||
| 230 | " <td>1.170</td>\n", |
||
| 231 | " <td>0.981</td>\n", |
||
| 232 | " <td>0.791</td>\n", |
||
| 233 | " <td>1.029</td>\n", |
||
| 234 | " <td>1.195</td>\n", |
||
| 235 | " </tr>\n", |
||
| 236 | " <tr>\n", |
||
| 237 | " <th>P01024</th>\n", |
||
| 238 | " <td>0.782</td>\n", |
||
| 239 | " <td>1.057</td>\n", |
||
| 240 | " <td>0.994</td>\n", |
||
| 241 | " <td>0.864</td>\n", |
||
| 242 | " <td>0.917</td>\n", |
||
| 243 | " <td>0.790</td>\n", |
||
| 244 | " <td>0.823</td>\n", |
||
| 245 | " <td>1.152</td>\n", |
||
| 246 | " <td>0.816</td>\n", |
||
| 247 | " <td>0.920</td>\n", |
||
| 248 | " <td>...</td>\n", |
||
| 249 | " <td>1.100</td>\n", |
||
| 250 | " <td>0.986</td>\n", |
||
| 251 | " <td>1.114</td>\n", |
||
| 252 | " <td>1.210</td>\n", |
||
| 253 | " <td>1.289</td>\n", |
||
| 254 | " <td>1.104</td>\n", |
||
| 255 | " <td>1.111</td>\n", |
||
| 256 | " <td>1.007</td>\n", |
||
| 257 | " <td>1.159</td>\n", |
||
| 258 | " <td>0.979</td>\n", |
||
| 259 | " </tr>\n", |
||
| 260 | " <tr>\n", |
||
| 261 | " <th>P02768</th>\n", |
||
| 262 | " <td>1.183</td>\n", |
||
| 263 | " <td>1.101</td>\n", |
||
| 264 | " <td>1.045</td>\n", |
||
| 265 | " <td>1.086</td>\n", |
||
| 266 | " <td>1.041</td>\n", |
||
| 267 | " <td>1.187</td>\n", |
||
| 268 | " <td>1.234</td>\n", |
||
| 269 | " <td>1.079</td>\n", |
||
| 270 | " <td>1.011</td>\n", |
||
| 271 | " <td>1.099</td>\n", |
||
| 272 | " <td>...</td>\n", |
||
| 273 | " <td>0.786</td>\n", |
||
| 274 | " <td>0.706</td>\n", |
||
| 275 | " <td>0.947</td>\n", |
||
| 276 | " <td>0.831</td>\n", |
||
| 277 | " <td>0.717</td>\n", |
||
| 278 | " <td>0.795</td>\n", |
||
| 279 | " <td>0.776</td>\n", |
||
| 280 | " <td>0.938</td>\n", |
||
| 281 | " <td>0.903</td>\n", |
||
| 282 | " <td>0.743</td>\n", |
||
| 283 | " </tr>\n", |
||
| 284 | " <tr>\n", |
||
| 285 | " <th>P01023</th>\n", |
||
| 286 | " <td>1.066</td>\n", |
||
| 287 | " <td>1.278</td>\n", |
||
| 288 | " <td>0.959</td>\n", |
||
| 289 | " <td>0.811</td>\n", |
||
| 290 | " <td>0.789</td>\n", |
||
| 291 | " <td>0.931</td>\n", |
||
| 292 | " <td>0.971</td>\n", |
||
| 293 | " <td>0.769</td>\n", |
||
| 294 | " <td>1.011</td>\n", |
||
| 295 | " <td>0.866</td>\n", |
||
| 296 | " <td>...</td>\n", |
||
| 297 | " <td>0.817</td>\n", |
||
| 298 | " <td>0.728</td>\n", |
||
| 299 | " <td>0.861</td>\n", |
||
| 300 | " <td>0.798</td>\n", |
||
| 301 | " <td>0.751</td>\n", |
||
| 302 | " <td>0.917</td>\n", |
||
| 303 | " <td>0.809</td>\n", |
||
| 304 | " <td>0.780</td>\n", |
||
| 305 | " <td>1.195</td>\n", |
||
| 306 | " <td>0.706</td>\n", |
||
| 307 | " </tr>\n", |
||
| 308 | " <tr>\n", |
||
| 309 | " <th>P02751</th>\n", |
||
| 310 | " <td>1.085</td>\n", |
||
| 311 | " <td>0.947</td>\n", |
||
| 312 | " <td>0.993</td>\n", |
||
| 313 | " <td>1.343</td>\n", |
||
| 314 | " <td>1.130</td>\n", |
||
| 315 | " <td>0.778</td>\n", |
||
| 316 | " <td>0.731</td>\n", |
||
| 317 | " <td>1.084</td>\n", |
||
| 318 | " <td>1.107</td>\n", |
||
| 319 | " <td>0.909</td>\n", |
||
| 320 | " <td>...</td>\n", |
||
| 321 | " <td>0.566</td>\n", |
||
| 322 | " <td>0.854</td>\n", |
||
| 323 | " <td>1.109</td>\n", |
||
| 324 | " <td>0.630</td>\n", |
||
| 325 | " <td>0.850</td>\n", |
||
| 326 | " <td>0.661</td>\n", |
||
| 327 | " <td>0.848</td>\n", |
||
| 328 | " <td>0.829</td>\n", |
||
| 329 | " <td>0.760</td>\n", |
||
| 330 | " <td>0.811</td>\n", |
||
| 331 | " </tr>\n", |
||
| 332 | " </tbody>\n", |
||
| 333 | "</table>\n", |
||
| 334 | "<p>5 rows × 70 columns</p>\n", |
||
| 335 | "</div>" |
||
| 336 | ], |
||
| 337 | "text/plain": [ |
||
| 338 | " h_F1_131N h_F1_131C h_F1_132C h_F2_131N h_F2_131C h_F2_132C \\\n", |
||
| 339 | "Identifier \n", |
||
| 340 | "P04114 0.750 0.853 0.822 1.191 1.175 1.078 \n", |
||
| 341 | "P01024 0.782 1.057 0.994 0.864 0.917 0.790 \n", |
||
| 342 | "P02768 1.183 1.101 1.045 1.086 1.041 1.187 \n", |
||
| 343 | "P01023 1.066 1.278 0.959 0.811 0.789 0.931 \n", |
||
| 344 | "P02751 1.085 0.947 0.993 1.343 1.130 0.778 \n", |
||
| 345 | "\n", |
||
| 346 | " h_F3_131N h_F3_131C h_F3_132C h_F4_131N ... s_F3_128N \\\n", |
||
| 347 | "Identifier ... \n", |
||
| 348 | "P04114 0.693 0.947 0.931 1.057 ... 1.044 \n", |
||
| 349 | "P01024 0.823 1.152 0.816 0.920 ... 1.100 \n", |
||
| 350 | "P02768 1.234 1.079 1.011 1.099 ... 0.786 \n", |
||
| 351 | "P01023 0.971 0.769 1.011 0.866 ... 0.817 \n", |
||
| 352 | "P02751 0.731 1.084 1.107 0.909 ... 0.566 \n", |
||
| 353 | "\n", |
||
| 354 | " s_F3_128C s_F3_129C s_F4_128N s_F4_128C s_F5_128N s_F5_128C \\\n", |
||
| 355 | "Identifier \n", |
||
| 356 | "P04114 1.305 1.657 1.323 1.624 1.170 0.981 \n", |
||
| 357 | "P01024 0.986 1.114 1.210 1.289 1.104 1.111 \n", |
||
| 358 | "P02768 0.706 0.947 0.831 0.717 0.795 0.776 \n", |
||
| 359 | "P01023 0.728 0.861 0.798 0.751 0.917 0.809 \n", |
||
| 360 | "P02751 0.854 1.109 0.630 0.850 0.661 0.848 \n", |
||
| 361 | "\n", |
||
| 362 | " s_F6_128N s_F6_128C s_F6_133N \n", |
||
| 363 | "Identifier \n", |
||
| 364 | "P04114 0.791 1.029 1.195 \n", |
||
| 365 | "P01024 1.007 1.159 0.979 \n", |
||
| 366 | "P02768 0.938 0.903 0.743 \n", |
||
| 367 | "P01023 0.780 1.195 0.706 \n", |
||
| 368 | "P02751 0.829 0.760 0.811 \n", |
||
| 369 | "\n", |
||
| 370 | "[5 rows x 70 columns]" |
||
| 371 | ] |
||
| 372 | }, |
||
| 373 | "execution_count": 8, |
||
| 374 | "metadata": {}, |
||
| 375 | "output_type": "execute_result" |
||
| 376 | } |
||
| 377 | ], |
||
| 378 | "source": [ |
||
| 379 | "protein_df.head()" |
||
| 380 | ] |
||
| 381 | }, |
||
| 382 | { |
||
| 383 | "cell_type": "code", |
||
| 384 | "execution_count": 9, |
||
| 385 | "metadata": {}, |
||
| 386 | "outputs": [ |
||
| 387 | { |
||
| 388 | "data": { |
||
| 389 | "text/html": [ |
||
| 390 | "<div>\n", |
||
| 391 | "<style scoped>\n", |
||
| 392 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 393 | " vertical-align: middle;\n", |
||
| 394 | " }\n", |
||
| 395 | "\n", |
||
| 396 | " .dataframe tbody tr th {\n", |
||
| 397 | " vertical-align: top;\n", |
||
| 398 | " }\n", |
||
| 399 | "\n", |
||
| 400 | " .dataframe thead th {\n", |
||
| 401 | " text-align: right;\n", |
||
| 402 | " }\n", |
||
| 403 | "</style>\n", |
||
| 404 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 405 | " <thead>\n", |
||
| 406 | " <tr style=\"text-align: right;\">\n", |
||
| 407 | " <th></th>\n", |
||
| 408 | " <th>group</th>\n", |
||
| 409 | " </tr>\n", |
||
| 410 | " <tr>\n", |
||
| 411 | " <th>sample</th>\n", |
||
| 412 | " <th></th>\n", |
||
| 413 | " </tr>\n", |
||
| 414 | " </thead>\n", |
||
| 415 | " <tbody>\n", |
||
| 416 | " <tr>\n", |
||
| 417 | " <th>h_F1_131N</th>\n", |
||
| 418 | " <td>healthy</td>\n", |
||
| 419 | " </tr>\n", |
||
| 420 | " <tr>\n", |
||
| 421 | " <th>h_F1_131C</th>\n", |
||
| 422 | " <td>healthy</td>\n", |
||
| 423 | " </tr>\n", |
||
| 424 | " <tr>\n", |
||
| 425 | " <th>h_F1_132C</th>\n", |
||
| 426 | " <td>healthy</td>\n", |
||
| 427 | " </tr>\n", |
||
| 428 | " <tr>\n", |
||
| 429 | " <th>h_F2_131N</th>\n", |
||
| 430 | " <td>healthy</td>\n", |
||
| 431 | " </tr>\n", |
||
| 432 | " <tr>\n", |
||
| 433 | " <th>h_F2_131C</th>\n", |
||
| 434 | " <td>healthy</td>\n", |
||
| 435 | " </tr>\n", |
||
| 436 | " <tr>\n", |
||
| 437 | " <th>...</th>\n", |
||
| 438 | " <td>...</td>\n", |
||
| 439 | " </tr>\n", |
||
| 440 | " <tr>\n", |
||
| 441 | " <th>s_F5_128N</th>\n", |
||
| 442 | " <td>severe</td>\n", |
||
| 443 | " </tr>\n", |
||
| 444 | " <tr>\n", |
||
| 445 | " <th>s_F5_128C</th>\n", |
||
| 446 | " <td>severe</td>\n", |
||
| 447 | " </tr>\n", |
||
| 448 | " <tr>\n", |
||
| 449 | " <th>s_F6_128N</th>\n", |
||
| 450 | " <td>severe</td>\n", |
||
| 451 | " </tr>\n", |
||
| 452 | " <tr>\n", |
||
| 453 | " <th>s_F6_128C</th>\n", |
||
| 454 | " <td>severe</td>\n", |
||
| 455 | " </tr>\n", |
||
| 456 | " <tr>\n", |
||
| 457 | " <th>s_F6_133N</th>\n", |
||
| 458 | " <td>severe</td>\n", |
||
| 459 | " </tr>\n", |
||
| 460 | " </tbody>\n", |
||
| 461 | "</table>\n", |
||
| 462 | "<p>70 rows × 1 columns</p>\n", |
||
| 463 | "</div>" |
||
| 464 | ], |
||
| 465 | "text/plain": [ |
||
| 466 | " group\n", |
||
| 467 | "sample \n", |
||
| 468 | "h_F1_131N healthy\n", |
||
| 469 | "h_F1_131C healthy\n", |
||
| 470 | "h_F1_132C healthy\n", |
||
| 471 | "h_F2_131N healthy\n", |
||
| 472 | "h_F2_131C healthy\n", |
||
| 473 | "... ...\n", |
||
| 474 | "s_F5_128N severe\n", |
||
| 475 | "s_F5_128C severe\n", |
||
| 476 | "s_F6_128N severe\n", |
||
| 477 | "s_F6_128C severe\n", |
||
| 478 | "s_F6_133N severe\n", |
||
| 479 | "\n", |
||
| 480 | "[70 rows x 1 columns]" |
||
| 481 | ] |
||
| 482 | }, |
||
| 483 | "execution_count": 9, |
||
| 484 | "metadata": {}, |
||
| 485 | "output_type": "execute_result" |
||
| 486 | } |
||
| 487 | ], |
||
| 488 | "source": [ |
||
| 489 | "protein_design" |
||
| 490 | ] |
||
| 491 | }, |
||
| 492 | { |
||
| 493 | "cell_type": "markdown", |
||
| 494 | "metadata": {}, |
||
| 495 | "source": [ |
||
| 496 | "Read metabolomics data" |
||
| 497 | ] |
||
| 498 | }, |
||
| 499 | { |
||
| 500 | "cell_type": "code", |
||
| 501 | "execution_count": 10, |
||
| 502 | "metadata": {}, |
||
| 503 | "outputs": [], |
||
| 504 | "source": [ |
||
| 505 | "compound_df = pd.read_csv(os.path.join(DATA_FOLDER, 'compound_data.csv'), index_col='Identifier')\n", |
||
| 506 | "compound_design = pd.read_csv(os.path.join(DATA_FOLDER, 'compound_design.csv'), index_col='sample')" |
||
| 507 | ] |
||
| 508 | }, |
||
| 509 | { |
||
| 510 | "cell_type": "code", |
||
| 511 | "execution_count": 11, |
||
| 512 | "metadata": {}, |
||
| 513 | "outputs": [ |
||
| 514 | { |
||
| 515 | "data": { |
||
| 516 | "text/html": [ |
||
| 517 | "<div>\n", |
||
| 518 | "<style scoped>\n", |
||
| 519 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 520 | " vertical-align: middle;\n", |
||
| 521 | " }\n", |
||
| 522 | "\n", |
||
| 523 | " .dataframe tbody tr th {\n", |
||
| 524 | " vertical-align: top;\n", |
||
| 525 | " }\n", |
||
| 526 | "\n", |
||
| 527 | " .dataframe thead th {\n", |
||
| 528 | " text-align: right;\n", |
||
| 529 | " }\n", |
||
| 530 | "</style>\n", |
||
| 531 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 532 | " <thead>\n", |
||
| 533 | " <tr style=\"text-align: right;\">\n", |
||
| 534 | " <th></th>\n", |
||
| 535 | " <th>h_jkdz1</th>\n", |
||
| 536 | " <th>h_jkdz2</th>\n", |
||
| 537 | " <th>h_jkdz3</th>\n", |
||
| 538 | " <th>h_jkdz4</th>\n", |
||
| 539 | " <th>h_jkdz5</th>\n", |
||
| 540 | " <th>h_jkdz6</th>\n", |
||
| 541 | " <th>h_jkdz7</th>\n", |
||
| 542 | " <th>h_jkdz8</th>\n", |
||
| 543 | " <th>h_jkdz9</th>\n", |
||
| 544 | " <th>h_jkdz10</th>\n", |
||
| 545 | " <th>...</th>\n", |
||
| 546 | " <th>s_ZX12</th>\n", |
||
| 547 | " <th>s_ZX13</th>\n", |
||
| 548 | " <th>s_ZX14</th>\n", |
||
| 549 | " <th>s_ZX15</th>\n", |
||
| 550 | " <th>s_ZX16</th>\n", |
||
| 551 | " <th>s_ZX17</th>\n", |
||
| 552 | " <th>s_ZX18</th>\n", |
||
| 553 | " <th>s_ZX19</th>\n", |
||
| 554 | " <th>s_ZX20</th>\n", |
||
| 555 | " <th>s_ZX21</th>\n", |
||
| 556 | " </tr>\n", |
||
| 557 | " <tr>\n", |
||
| 558 | " <th>Identifier</th>\n", |
||
| 559 | " <th></th>\n", |
||
| 560 | " <th></th>\n", |
||
| 561 | " <th></th>\n", |
||
| 562 | " <th></th>\n", |
||
| 563 | " <th></th>\n", |
||
| 564 | " <th></th>\n", |
||
| 565 | " <th></th>\n", |
||
| 566 | " <th></th>\n", |
||
| 567 | " <th></th>\n", |
||
| 568 | " <th></th>\n", |
||
| 569 | " <th></th>\n", |
||
| 570 | " <th></th>\n", |
||
| 571 | " <th></th>\n", |
||
| 572 | " <th></th>\n", |
||
| 573 | " <th></th>\n", |
||
| 574 | " <th></th>\n", |
||
| 575 | " <th></th>\n", |
||
| 576 | " <th></th>\n", |
||
| 577 | " <th></th>\n", |
||
| 578 | " <th></th>\n", |
||
| 579 | " <th></th>\n", |
||
| 580 | " </tr>\n", |
||
| 581 | " </thead>\n", |
||
| 582 | " <tbody>\n", |
||
| 583 | " <tr>\n", |
||
| 584 | " <th>C21482</th>\n", |
||
| 585 | " <td>19413052.00</td>\n", |
||
| 586 | " <td>6.381812e+06</td>\n", |
||
| 587 | " <td>9.748316e+06</td>\n", |
||
| 588 | " <td>5.326872e+06</td>\n", |
||
| 589 | " <td>1.998072e+07</td>\n", |
||
| 590 | " <td>3.580375e+06</td>\n", |
||
| 591 | " <td>8.256121e+06</td>\n", |
||
| 592 | " <td>8.079382e+06</td>\n", |
||
| 593 | " <td>1.559659e+07</td>\n", |
||
| 594 | " <td>1.520363e+07</td>\n", |
||
| 595 | " <td>...</td>\n", |
||
| 596 | " <td>1.904349e+06</td>\n", |
||
| 597 | " <td>3.226016e+06</td>\n", |
||
| 598 | " <td>7.378147e+05</td>\n", |
||
| 599 | " <td>2.817698e+06</td>\n", |
||
| 600 | " <td>3.329101e+06</td>\n", |
||
| 601 | " <td>3206752.75</td>\n", |
||
| 602 | " <td>1.466174e+06</td>\n", |
||
| 603 | " <td>2.779301e+06</td>\n", |
||
| 604 | " <td>2.117668e+06</td>\n", |
||
| 605 | " <td>2.184310e+06</td>\n", |
||
| 606 | " </tr>\n", |
||
| 607 | " <tr>\n", |
||
| 608 | " <th>C18218</th>\n", |
||
| 609 | " <td>2711915.25</td>\n", |
||
| 610 | " <td>2.056393e+06</td>\n", |
||
| 611 | " <td>1.445594e+06</td>\n", |
||
| 612 | " <td>2.038765e+06</td>\n", |
||
| 613 | " <td>2.536996e+06</td>\n", |
||
| 614 | " <td>2.638198e+06</td>\n", |
||
| 615 | " <td>2.285757e+06</td>\n", |
||
| 616 | " <td>1.973140e+06</td>\n", |
||
| 617 | " <td>2.015425e+06</td>\n", |
||
| 618 | " <td>2.290842e+06</td>\n", |
||
| 619 | " <td>...</td>\n", |
||
| 620 | " <td>1.409720e+06</td>\n", |
||
| 621 | " <td>1.413307e+06</td>\n", |
||
| 622 | " <td>3.218834e+06</td>\n", |
||
| 623 | " <td>1.602131e+06</td>\n", |
||
| 624 | " <td>1.317878e+06</td>\n", |
||
| 625 | " <td>2930312.75</td>\n", |
||
| 626 | " <td>1.168094e+06</td>\n", |
||
| 627 | " <td>2.946776e+06</td>\n", |
||
| 628 | " <td>1.417311e+06</td>\n", |
||
| 629 | " <td>1.474166e+06</td>\n", |
||
| 630 | " </tr>\n", |
||
| 631 | " <tr>\n", |
||
| 632 | " <th>C05127</th>\n", |
||
| 633 | " <td>87727.25</td>\n", |
||
| 634 | " <td>NaN</td>\n", |
||
| 635 | " <td>9.238706e+04</td>\n", |
||
| 636 | " <td>NaN</td>\n", |
||
| 637 | " <td>1.597879e+05</td>\n", |
||
| 638 | " <td>NaN</td>\n", |
||
| 639 | " <td>NaN</td>\n", |
||
| 640 | " <td>NaN</td>\n", |
||
| 641 | " <td>9.055130e+04</td>\n", |
||
| 642 | " <td>1.214114e+05</td>\n", |
||
| 643 | " <td>...</td>\n", |
||
| 644 | " <td>NaN</td>\n", |
||
| 645 | " <td>NaN</td>\n", |
||
| 646 | " <td>NaN</td>\n", |
||
| 647 | " <td>NaN</td>\n", |
||
| 648 | " <td>NaN</td>\n", |
||
| 649 | " <td>NaN</td>\n", |
||
| 650 | " <td>NaN</td>\n", |
||
| 651 | " <td>1.382788e+05</td>\n", |
||
| 652 | " <td>NaN</td>\n", |
||
| 653 | " <td>NaN</td>\n", |
||
| 654 | " </tr>\n", |
||
| 655 | " <tr>\n", |
||
| 656 | " <th>C01152</th>\n", |
||
| 657 | " <td>58832828.00</td>\n", |
||
| 658 | " <td>5.843934e+07</td>\n", |
||
| 659 | " <td>5.552133e+07</td>\n", |
||
| 660 | " <td>4.516214e+07</td>\n", |
||
| 661 | " <td>5.478952e+07</td>\n", |
||
| 662 | " <td>3.941259e+07</td>\n", |
||
| 663 | " <td>2.987876e+07</td>\n", |
||
| 664 | " <td>6.751726e+07</td>\n", |
||
| 665 | " <td>4.666031e+07</td>\n", |
||
| 666 | " <td>9.118524e+07</td>\n", |
||
| 667 | " <td>...</td>\n", |
||
| 668 | " <td>2.881314e+07</td>\n", |
||
| 669 | " <td>3.164358e+07</td>\n", |
||
| 670 | " <td>2.538767e+07</td>\n", |
||
| 671 | " <td>3.307604e+07</td>\n", |
||
| 672 | " <td>3.915698e+07</td>\n", |
||
| 673 | " <td>24400592.00</td>\n", |
||
| 674 | " <td>2.593375e+07</td>\n", |
||
| 675 | " <td>6.413868e+07</td>\n", |
||
| 676 | " <td>4.020588e+07</td>\n", |
||
| 677 | " <td>4.904488e+07</td>\n", |
||
| 678 | " </tr>\n", |
||
| 679 | " <tr>\n", |
||
| 680 | " <th>C02918</th>\n", |
||
| 681 | " <td>NaN</td>\n", |
||
| 682 | " <td>1.815549e+05</td>\n", |
||
| 683 | " <td>2.240392e+05</td>\n", |
||
| 684 | " <td>1.609397e+05</td>\n", |
||
| 685 | " <td>3.206194e+05</td>\n", |
||
| 686 | " <td>7.176557e+05</td>\n", |
||
| 687 | " <td>3.268182e+05</td>\n", |
||
| 688 | " <td>5.135810e+05</td>\n", |
||
| 689 | " <td>2.734582e+05</td>\n", |
||
| 690 | " <td>NaN</td>\n", |
||
| 691 | " <td>...</td>\n", |
||
| 692 | " <td>3.337245e+05</td>\n", |
||
| 693 | " <td>NaN</td>\n", |
||
| 694 | " <td>4.347152e+05</td>\n", |
||
| 695 | " <td>3.532118e+04</td>\n", |
||
| 696 | " <td>NaN</td>\n", |
||
| 697 | " <td>655827.25</td>\n", |
||
| 698 | " <td>8.359706e+05</td>\n", |
||
| 699 | " <td>4.034381e+06</td>\n", |
||
| 700 | " <td>2.839358e+05</td>\n", |
||
| 701 | " <td>8.062160e+04</td>\n", |
||
| 702 | " </tr>\n", |
||
| 703 | " </tbody>\n", |
||
| 704 | "</table>\n", |
||
| 705 | "<p>5 rows × 96 columns</p>\n", |
||
| 706 | "</div>" |
||
| 707 | ], |
||
| 708 | "text/plain": [ |
||
| 709 | " h_jkdz1 h_jkdz2 h_jkdz3 h_jkdz4 \\\n", |
||
| 710 | "Identifier \n", |
||
| 711 | "C21482 19413052.00 6.381812e+06 9.748316e+06 5.326872e+06 \n", |
||
| 712 | "C18218 2711915.25 2.056393e+06 1.445594e+06 2.038765e+06 \n", |
||
| 713 | "C05127 87727.25 NaN 9.238706e+04 NaN \n", |
||
| 714 | "C01152 58832828.00 5.843934e+07 5.552133e+07 4.516214e+07 \n", |
||
| 715 | "C02918 NaN 1.815549e+05 2.240392e+05 1.609397e+05 \n", |
||
| 716 | "\n", |
||
| 717 | " h_jkdz5 h_jkdz6 h_jkdz7 h_jkdz8 \\\n", |
||
| 718 | "Identifier \n", |
||
| 719 | "C21482 1.998072e+07 3.580375e+06 8.256121e+06 8.079382e+06 \n", |
||
| 720 | "C18218 2.536996e+06 2.638198e+06 2.285757e+06 1.973140e+06 \n", |
||
| 721 | "C05127 1.597879e+05 NaN NaN NaN \n", |
||
| 722 | "C01152 5.478952e+07 3.941259e+07 2.987876e+07 6.751726e+07 \n", |
||
| 723 | "C02918 3.206194e+05 7.176557e+05 3.268182e+05 5.135810e+05 \n", |
||
| 724 | "\n", |
||
| 725 | " h_jkdz9 h_jkdz10 ... s_ZX12 s_ZX13 \\\n", |
||
| 726 | "Identifier ... \n", |
||
| 727 | "C21482 1.559659e+07 1.520363e+07 ... 1.904349e+06 3.226016e+06 \n", |
||
| 728 | "C18218 2.015425e+06 2.290842e+06 ... 1.409720e+06 1.413307e+06 \n", |
||
| 729 | "C05127 9.055130e+04 1.214114e+05 ... NaN NaN \n", |
||
| 730 | "C01152 4.666031e+07 9.118524e+07 ... 2.881314e+07 3.164358e+07 \n", |
||
| 731 | "C02918 2.734582e+05 NaN ... 3.337245e+05 NaN \n", |
||
| 732 | "\n", |
||
| 733 | " s_ZX14 s_ZX15 s_ZX16 s_ZX17 \\\n", |
||
| 734 | "Identifier \n", |
||
| 735 | "C21482 7.378147e+05 2.817698e+06 3.329101e+06 3206752.75 \n", |
||
| 736 | "C18218 3.218834e+06 1.602131e+06 1.317878e+06 2930312.75 \n", |
||
| 737 | "C05127 NaN NaN NaN NaN \n", |
||
| 738 | "C01152 2.538767e+07 3.307604e+07 3.915698e+07 24400592.00 \n", |
||
| 739 | "C02918 4.347152e+05 3.532118e+04 NaN 655827.25 \n", |
||
| 740 | "\n", |
||
| 741 | " s_ZX18 s_ZX19 s_ZX20 s_ZX21 \n", |
||
| 742 | "Identifier \n", |
||
| 743 | "C21482 1.466174e+06 2.779301e+06 2.117668e+06 2.184310e+06 \n", |
||
| 744 | "C18218 1.168094e+06 2.946776e+06 1.417311e+06 1.474166e+06 \n", |
||
| 745 | "C05127 NaN 1.382788e+05 NaN NaN \n", |
||
| 746 | "C01152 2.593375e+07 6.413868e+07 4.020588e+07 4.904488e+07 \n", |
||
| 747 | "C02918 8.359706e+05 4.034381e+06 2.839358e+05 8.062160e+04 \n", |
||
| 748 | "\n", |
||
| 749 | "[5 rows x 96 columns]" |
||
| 750 | ] |
||
| 751 | }, |
||
| 752 | "execution_count": 11, |
||
| 753 | "metadata": {}, |
||
| 754 | "output_type": "execute_result" |
||
| 755 | } |
||
| 756 | ], |
||
| 757 | "source": [ |
||
| 758 | "compound_df.head()" |
||
| 759 | ] |
||
| 760 | }, |
||
| 761 | { |
||
| 762 | "cell_type": "code", |
||
| 763 | "execution_count": 12, |
||
| 764 | "metadata": {}, |
||
| 765 | "outputs": [ |
||
| 766 | { |
||
| 767 | "data": { |
||
| 768 | "text/html": [ |
||
| 769 | "<div>\n", |
||
| 770 | "<style scoped>\n", |
||
| 771 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 772 | " vertical-align: middle;\n", |
||
| 773 | " }\n", |
||
| 774 | "\n", |
||
| 775 | " .dataframe tbody tr th {\n", |
||
| 776 | " vertical-align: top;\n", |
||
| 777 | " }\n", |
||
| 778 | "\n", |
||
| 779 | " .dataframe thead th {\n", |
||
| 780 | " text-align: right;\n", |
||
| 781 | " }\n", |
||
| 782 | "</style>\n", |
||
| 783 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 784 | " <thead>\n", |
||
| 785 | " <tr style=\"text-align: right;\">\n", |
||
| 786 | " <th></th>\n", |
||
| 787 | " <th>group</th>\n", |
||
| 788 | " </tr>\n", |
||
| 789 | " <tr>\n", |
||
| 790 | " <th>sample</th>\n", |
||
| 791 | " <th></th>\n", |
||
| 792 | " </tr>\n", |
||
| 793 | " </thead>\n", |
||
| 794 | " <tbody>\n", |
||
| 795 | " <tr>\n", |
||
| 796 | " <th>h_jkdz1</th>\n", |
||
| 797 | " <td>healthy</td>\n", |
||
| 798 | " </tr>\n", |
||
| 799 | " <tr>\n", |
||
| 800 | " <th>h_jkdz2</th>\n", |
||
| 801 | " <td>healthy</td>\n", |
||
| 802 | " </tr>\n", |
||
| 803 | " <tr>\n", |
||
| 804 | " <th>h_jkdz3</th>\n", |
||
| 805 | " <td>healthy</td>\n", |
||
| 806 | " </tr>\n", |
||
| 807 | " <tr>\n", |
||
| 808 | " <th>h_jkdz4</th>\n", |
||
| 809 | " <td>healthy</td>\n", |
||
| 810 | " </tr>\n", |
||
| 811 | " <tr>\n", |
||
| 812 | " <th>h_jkdz5</th>\n", |
||
| 813 | " <td>healthy</td>\n", |
||
| 814 | " </tr>\n", |
||
| 815 | " <tr>\n", |
||
| 816 | " <th>...</th>\n", |
||
| 817 | " <td>...</td>\n", |
||
| 818 | " </tr>\n", |
||
| 819 | " <tr>\n", |
||
| 820 | " <th>s_ZX17</th>\n", |
||
| 821 | " <td>severe</td>\n", |
||
| 822 | " </tr>\n", |
||
| 823 | " <tr>\n", |
||
| 824 | " <th>s_ZX18</th>\n", |
||
| 825 | " <td>severe</td>\n", |
||
| 826 | " </tr>\n", |
||
| 827 | " <tr>\n", |
||
| 828 | " <th>s_ZX19</th>\n", |
||
| 829 | " <td>severe</td>\n", |
||
| 830 | " </tr>\n", |
||
| 831 | " <tr>\n", |
||
| 832 | " <th>s_ZX20</th>\n", |
||
| 833 | " <td>severe</td>\n", |
||
| 834 | " </tr>\n", |
||
| 835 | " <tr>\n", |
||
| 836 | " <th>s_ZX21</th>\n", |
||
| 837 | " <td>severe</td>\n", |
||
| 838 | " </tr>\n", |
||
| 839 | " </tbody>\n", |
||
| 840 | "</table>\n", |
||
| 841 | "<p>96 rows × 1 columns</p>\n", |
||
| 842 | "</div>" |
||
| 843 | ], |
||
| 844 | "text/plain": [ |
||
| 845 | " group\n", |
||
| 846 | "sample \n", |
||
| 847 | "h_jkdz1 healthy\n", |
||
| 848 | "h_jkdz2 healthy\n", |
||
| 849 | "h_jkdz3 healthy\n", |
||
| 850 | "h_jkdz4 healthy\n", |
||
| 851 | "h_jkdz5 healthy\n", |
||
| 852 | "... ...\n", |
||
| 853 | "s_ZX17 severe\n", |
||
| 854 | "s_ZX18 severe\n", |
||
| 855 | "s_ZX19 severe\n", |
||
| 856 | "s_ZX20 severe\n", |
||
| 857 | "s_ZX21 severe\n", |
||
| 858 | "\n", |
||
| 859 | "[96 rows x 1 columns]" |
||
| 860 | ] |
||
| 861 | }, |
||
| 862 | "execution_count": 12, |
||
| 863 | "metadata": {}, |
||
| 864 | "output_type": "execute_result" |
||
| 865 | } |
||
| 866 | ], |
||
| 867 | "source": [ |
||
| 868 | "compound_design" |
||
| 869 | ] |
||
| 870 | }, |
||
| 871 | { |
||
| 872 | "cell_type": "code", |
||
| 873 | "execution_count": 13, |
||
| 874 | "metadata": {}, |
||
| 875 | "outputs": [ |
||
| 876 | { |
||
| 877 | "data": { |
||
| 878 | "text/plain": [ |
||
| 879 | "1" |
||
| 880 | ] |
||
| 881 | }, |
||
| 882 | "execution_count": 13, |
||
| 883 | "metadata": {}, |
||
| 884 | "output_type": "execute_result" |
||
| 885 | } |
||
| 886 | ], |
||
| 887 | "source": [ |
||
| 888 | "set_log_level_info()" |
||
| 889 | ] |
||
| 890 | }, |
||
| 891 | { |
||
| 892 | "cell_type": "markdown", |
||
| 893 | "metadata": {}, |
||
| 894 | "source": [ |
||
| 895 | "## Create multi-omics container object" |
||
| 896 | ] |
||
| 897 | }, |
||
| 898 | { |
||
| 899 | "cell_type": "code", |
||
| 900 | "execution_count": 14, |
||
| 901 | "metadata": {}, |
||
| 902 | "outputs": [ |
||
| 903 | { |
||
| 904 | "data": { |
||
| 905 | "text/plain": [ |
||
| 906 | "proteins data with (791, 70) measurements" |
||
| 907 | ] |
||
| 908 | }, |
||
| 909 | "execution_count": 14, |
||
| 910 | "metadata": {}, |
||
| 911 | "output_type": "execute_result" |
||
| 912 | } |
||
| 913 | ], |
||
| 914 | "source": [ |
||
| 915 | "protein_data = SingleOmicsData(PROTEINS, protein_df, protein_design)\n", |
||
| 916 | "protein_data" |
||
| 917 | ] |
||
| 918 | }, |
||
| 919 | { |
||
| 920 | "cell_type": "code", |
||
| 921 | "execution_count": 15, |
||
| 922 | "metadata": {}, |
||
| 923 | "outputs": [ |
||
| 924 | { |
||
| 925 | "data": { |
||
| 926 | "text/plain": [ |
||
| 927 | "compounds data with (220, 96) measurements" |
||
| 928 | ] |
||
| 929 | }, |
||
| 930 | "execution_count": 15, |
||
| 931 | "metadata": {}, |
||
| 932 | "output_type": "execute_result" |
||
| 933 | } |
||
| 934 | ], |
||
| 935 | "source": [ |
||
| 936 | "compound_data = SingleOmicsData(COMPOUNDS, compound_df, compound_design)\n", |
||
| 937 | "compound_data" |
||
| 938 | ] |
||
| 939 | }, |
||
| 940 | { |
||
| 941 | "cell_type": "code", |
||
| 942 | "execution_count": 16, |
||
| 943 | "metadata": {}, |
||
| 944 | "outputs": [], |
||
| 945 | "source": [ |
||
| 946 | "publication = 'Proteomic and Metabolomic Characterization of COVID-19 Patient Sera'\n", |
||
| 947 | "url = 'https://www.cell.com/cell/fulltext/S0092-8674(20)30627-9'" |
||
| 948 | ] |
||
| 949 | }, |
||
| 950 | { |
||
| 951 | "cell_type": "code", |
||
| 952 | "execution_count": 17, |
||
| 953 | "metadata": {}, |
||
| 954 | "outputs": [ |
||
| 955 | { |
||
| 956 | "data": { |
||
| 957 | "text/plain": [ |
||
| 958 | "Multi-omics data container\n", |
||
| 959 | "- publication: Proteomic and Metabolomic Characterization of COVID-19 Patient Sera\n", |
||
| 960 | "- URL: https://www.cell.com/cell/fulltext/S0092-8674(20)30627-9\n", |
||
| 961 | "- Views: 2 modalities\n", |
||
| 962 | "\t - proteins data with (791, 70) measurements\n", |
||
| 963 | "\t - compounds data with (220, 96) measurements" |
||
| 964 | ] |
||
| 965 | }, |
||
| 966 | "execution_count": 17, |
||
| 967 | "metadata": {}, |
||
| 968 | "output_type": "execute_result" |
||
| 969 | } |
||
| 970 | ], |
||
| 971 | "source": [ |
||
| 972 | "mo = MultiOmicsData(publication=publication, url=url)\n", |
||
| 973 | "mo.add_data([protein_data, compound_data])\n", |
||
| 974 | "mo" |
||
| 975 | ] |
||
| 976 | }, |
||
| 977 | { |
||
| 978 | "cell_type": "markdown", |
||
| 979 | "metadata": {}, |
||
| 980 | "source": [ |
||
| 981 | "## Create a mapping object" |
||
| 982 | ] |
||
| 983 | }, |
||
| 984 | { |
||
| 985 | "cell_type": "markdown", |
||
| 986 | "metadata": {}, |
||
| 987 | "source": [ |
||
| 988 | "The mapping object uses Reactome to map the different biological entities in the data:\n", |
||
| 989 | "- Transcripts (or genes) are connected to the proteins they encode\n", |
||
| 990 | "- Proteins and compounds are connected to reactions they're involved in\n", |
||
| 991 | "- Reactions are connected to pathways" |
||
| 992 | ] |
||
| 993 | }, |
||
| 994 | { |
||
| 995 | "cell_type": "code", |
||
| 996 | "execution_count": 18, |
||
| 997 | "metadata": {}, |
||
| 998 | "outputs": [ |
||
| 999 | { |
||
| 1000 | "name": "stderr", |
||
| 1001 | "output_type": "stream", |
||
| 1002 | "text": [ |
||
| 1003 | "2022-03-24 14:40:03.534 | INFO | pyMultiOmics.functions:remove_dupes:385 - Removing 9 rows with duplicate identifiers\n", |
||
| 1004 | "2022-03-24 14:40:03.535 | INFO | pyMultiOmics.functions:reactome_mapping:78 - There are 211 observed compound ids\n", |
||
| 1005 | "2022-03-24 14:40:03.535 | INFO | pyMultiOmics.functions:reactome_mapping:81 - Mapping genes -> proteins\n", |
||
| 1006 | "2022-03-24 14:40:06.215 | INFO | pyMultiOmics.functions:reactome_mapping:86 - Mapping proteins -> reactions\n", |
||
| 1007 | "2022-03-24 14:40:07.489 | INFO | pyMultiOmics.functions:reactome_mapping:94 - Mapping compounds -> reactions\n", |
||
| 1008 | "2022-03-24 14:40:11.539 | INFO | pyMultiOmics.functions:reactome_mapping:100 - Mapping reactions -> pathways\n", |
||
| 1009 | "2022-03-24 14:40:12.580 | INFO | pyMultiOmics.functions:reactome_mapping:111 - Mapping reactions -> proteins\n", |
||
| 1010 | "2022-03-24 14:40:18.631 | INFO | pyMultiOmics.functions:reactome_mapping:118 - Mapping reactions -> compounds\n", |
||
| 1011 | "2022-03-24 14:40:21.469 | INFO | pyMultiOmics.functions:reactome_mapping:130 - Mapping proteins -> genes\n", |
||
| 1012 | "2022-03-24 14:40:36.997 | INFO | pyMultiOmics.mapping:_add_nodes:153 - Processing nodes: genes\n", |
||
| 1013 | "2022-03-24 14:40:37.211 | INFO | pyMultiOmics.mapping:_add_nodes:153 - Processing nodes: proteins\n", |
||
| 1014 | "2022-03-24 14:40:37.901 | INFO | pyMultiOmics.mapping:_add_nodes:153 - Processing nodes: compounds\n", |
||
| 1015 | "2022-03-24 14:40:37.981 | INFO | pyMultiOmics.mapping:_add_nodes:153 - Processing nodes: reactions\n", |
||
| 1016 | "2022-03-24 14:40:38.092 | INFO | pyMultiOmics.mapping:_add_nodes:153 - Processing nodes: pathways\n", |
||
| 1017 | "2022-03-24 14:40:38.120 | INFO | pyMultiOmics.mapping:_add_edges:201 - Processing edges: gene_proteins\n", |
||
| 1018 | "2022-03-24 14:40:38.287 | INFO | pyMultiOmics.mapping:_add_edges:201 - Processing edges: protein_reactions\n", |
||
| 1019 | "2022-03-24 14:40:39.634 | INFO | pyMultiOmics.mapping:_add_edges:201 - Processing edges: compound_reactions\n", |
||
| 1020 | "2022-03-24 14:40:39.880 | INFO | pyMultiOmics.mapping:_add_edges:201 - Processing edges: reaction_pathways\n", |
||
| 1021 | "2022-03-24 14:40:40.005 | INFO | pyMultiOmics.mapping:build:51 - Created a multi-omics network with 19645 nodes and 80442 edges\n", |
||
| 1022 | "2022-03-24 14:40:40.499 | INFO | pyMultiOmics.mapping:build:53 - node_counts = {'genes': 7054, 'proteins': 6590, 'compounds': 1078, 'reactions': 3926, 'pathways': 997}\n" |
||
| 1023 | ] |
||
| 1024 | }, |
||
| 1025 | { |
||
| 1026 | "data": { |
||
| 1027 | "text/plain": [ |
||
| 1028 | "<pyMultiOmics.mapping.Mapper at 0x1762619f0>" |
||
| 1029 | ] |
||
| 1030 | }, |
||
| 1031 | "execution_count": 18, |
||
| 1032 | "metadata": {}, |
||
| 1033 | "output_type": "execute_result" |
||
| 1034 | } |
||
| 1035 | ], |
||
| 1036 | "source": [ |
||
| 1037 | "m = Mapper(mo, HOMO_SAPIENS, metabolic_pathway_only=False)\n", |
||
| 1038 | "m.build()" |
||
| 1039 | ] |
||
| 1040 | }, |
||
| 1041 | { |
||
| 1042 | "cell_type": "code", |
||
| 1043 | "execution_count": 19, |
||
| 1044 | "metadata": {}, |
||
| 1045 | "outputs": [ |
||
| 1046 | { |
||
| 1047 | "data": { |
||
| 1048 | "text/plain": [ |
||
| 1049 | "<pyMultiOmics.mapping.Mapper at 0x1762619f0>" |
||
| 1050 | ] |
||
| 1051 | }, |
||
| 1052 | "execution_count": 19, |
||
| 1053 | "metadata": {}, |
||
| 1054 | "output_type": "execute_result" |
||
| 1055 | } |
||
| 1056 | ], |
||
| 1057 | "source": [ |
||
| 1058 | "m" |
||
| 1059 | ] |
||
| 1060 | }, |
||
| 1061 | { |
||
| 1062 | "cell_type": "markdown", |
||
| 1063 | "metadata": {}, |
||
| 1064 | "source": [ |
||
| 1065 | "## Query mapping object" |
||
| 1066 | ] |
||
| 1067 | }, |
||
| 1068 | { |
||
| 1069 | "cell_type": "markdown", |
||
| 1070 | "metadata": {}, |
||
| 1071 | "source": [ |
||
| 1072 | "Below shows some example queries we can perform with the mapping object" |
||
| 1073 | ] |
||
| 1074 | }, |
||
| 1075 | { |
||
| 1076 | "cell_type": "code", |
||
| 1077 | "execution_count": 20, |
||
| 1078 | "metadata": {}, |
||
| 1079 | "outputs": [ |
||
| 1080 | { |
||
| 1081 | "data": { |
||
| 1082 | "text/html": [ |
||
| 1083 | "<div>\n", |
||
| 1084 | "<style scoped>\n", |
||
| 1085 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 1086 | " vertical-align: middle;\n", |
||
| 1087 | " }\n", |
||
| 1088 | "\n", |
||
| 1089 | " .dataframe tbody tr th {\n", |
||
| 1090 | " vertical-align: top;\n", |
||
| 1091 | " }\n", |
||
| 1092 | "\n", |
||
| 1093 | " .dataframe thead th {\n", |
||
| 1094 | " text-align: right;\n", |
||
| 1095 | " }\n", |
||
| 1096 | "</style>\n", |
||
| 1097 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 1098 | " <thead>\n", |
||
| 1099 | " <tr style=\"text-align: right;\">\n", |
||
| 1100 | " <th></th>\n", |
||
| 1101 | " <th>reaction_id</th>\n", |
||
| 1102 | " <th>reaction_name</th>\n", |
||
| 1103 | " <th>num_proteins</th>\n", |
||
| 1104 | " <th>num_compounds</th>\n", |
||
| 1105 | " </tr>\n", |
||
| 1106 | " </thead>\n", |
||
| 1107 | " <tbody>\n", |
||
| 1108 | " <tr>\n", |
||
| 1109 | " <th>0</th>\n", |
||
| 1110 | " <td>R-HSA-114552</td>\n", |
||
| 1111 | " <td>Thrombin-activated pars activate g12/13</td>\n", |
||
| 1112 | " <td>1</td>\n", |
||
| 1113 | " <td>1</td>\n", |
||
| 1114 | " </tr>\n", |
||
| 1115 | " <tr>\n", |
||
| 1116 | " <th>1</th>\n", |
||
| 1117 | " <td>R-HSA-114558</td>\n", |
||
| 1118 | " <td>Thrombin-activated pars activate gq</td>\n", |
||
| 1119 | " <td>1</td>\n", |
||
| 1120 | " <td>1</td>\n", |
||
| 1121 | " </tr>\n", |
||
| 1122 | " <tr>\n", |
||
| 1123 | " <th>2</th>\n", |
||
| 1124 | " <td>R-HSA-1214188</td>\n", |
||
| 1125 | " <td>Prdm9 trimethylates histone h3</td>\n", |
||
| 1126 | " <td>3</td>\n", |
||
| 1127 | " <td>1</td>\n", |
||
| 1128 | " </tr>\n", |
||
| 1129 | " <tr>\n", |
||
| 1130 | " <th>3</th>\n", |
||
| 1131 | " <td>R-HSA-1605591</td>\n", |
||
| 1132 | " <td>Glucosylceramidase cleaves the glucosidic bond...</td>\n", |
||
| 1133 | " <td>1</td>\n", |
||
| 1134 | " <td>1</td>\n", |
||
| 1135 | " </tr>\n", |
||
| 1136 | " <tr>\n", |
||
| 1137 | " <th>4</th>\n", |
||
| 1138 | " <td>R-HSA-163432</td>\n", |
||
| 1139 | " <td>Cholesterol ester + h2o -> cholesterol + fatty...</td>\n", |
||
| 1140 | " <td>1</td>\n", |
||
| 1141 | " <td>1</td>\n", |
||
| 1142 | " </tr>\n", |
||
| 1143 | " <tr>\n", |
||
| 1144 | " <th>...</th>\n", |
||
| 1145 | " <td>...</td>\n", |
||
| 1146 | " <td>...</td>\n", |
||
| 1147 | " <td>...</td>\n", |
||
| 1148 | " <td>...</td>\n", |
||
| 1149 | " </tr>\n", |
||
| 1150 | " <tr>\n", |
||
| 1151 | " <th>223</th>\n", |
||
| 1152 | " <td>R-HSA-9710490</td>\n", |
||
| 1153 | " <td>The gsdme gene promoter is hypermethylated</td>\n", |
||
| 1154 | " <td>3</td>\n", |
||
| 1155 | " <td>1</td>\n", |
||
| 1156 | " </tr>\n", |
||
| 1157 | " <tr>\n", |
||
| 1158 | " <th>224</th>\n", |
||
| 1159 | " <td>R-HSA-9733545</td>\n", |
||
| 1160 | " <td>Bile salts and acids bind alb</td>\n", |
||
| 1161 | " <td>1</td>\n", |
||
| 1162 | " <td>5</td>\n", |
||
| 1163 | " </tr>\n", |
||
| 1164 | " <tr>\n", |
||
| 1165 | " <th>225</th>\n", |
||
| 1166 | " <td>R-HSA-9733960</td>\n", |
||
| 1167 | " <td>Bile salts and acids dissociate from alb</td>\n", |
||
| 1168 | " <td>1</td>\n", |
||
| 1169 | " <td>5</td>\n", |
||
| 1170 | " </tr>\n", |
||
| 1171 | " <tr>\n", |
||
| 1172 | " <th>226</th>\n", |
||
| 1173 | " <td>R-HSA-977071</td>\n", |
||
| 1174 | " <td>Sialyltransferase i can add sialic acid to the...</td>\n", |
||
| 1175 | " <td>1</td>\n", |
||
| 1176 | " <td>1</td>\n", |
||
| 1177 | " </tr>\n", |
||
| 1178 | " <tr>\n", |
||
| 1179 | " <th>227</th>\n", |
||
| 1180 | " <td>R-HSA-977228</td>\n", |
||
| 1181 | " <td>Sialyltransferase i can add sialic acid to the...</td>\n", |
||
| 1182 | " <td>1</td>\n", |
||
| 1183 | " <td>1</td>\n", |
||
| 1184 | " </tr>\n", |
||
| 1185 | " </tbody>\n", |
||
| 1186 | "</table>\n", |
||
| 1187 | "<p>228 rows × 4 columns</p>\n", |
||
| 1188 | "</div>" |
||
| 1189 | ], |
||
| 1190 | "text/plain": [ |
||
| 1191 | " reaction_id reaction_name \\\n", |
||
| 1192 | "0 R-HSA-114552 Thrombin-activated pars activate g12/13 \n", |
||
| 1193 | "1 R-HSA-114558 Thrombin-activated pars activate gq \n", |
||
| 1194 | "2 R-HSA-1214188 Prdm9 trimethylates histone h3 \n", |
||
| 1195 | "3 R-HSA-1605591 Glucosylceramidase cleaves the glucosidic bond... \n", |
||
| 1196 | "4 R-HSA-163432 Cholesterol ester + h2o -> cholesterol + fatty... \n", |
||
| 1197 | ".. ... ... \n", |
||
| 1198 | "223 R-HSA-9710490 The gsdme gene promoter is hypermethylated \n", |
||
| 1199 | "224 R-HSA-9733545 Bile salts and acids bind alb \n", |
||
| 1200 | "225 R-HSA-9733960 Bile salts and acids dissociate from alb \n", |
||
| 1201 | "226 R-HSA-977071 Sialyltransferase i can add sialic acid to the... \n", |
||
| 1202 | "227 R-HSA-977228 Sialyltransferase i can add sialic acid to the... \n", |
||
| 1203 | "\n", |
||
| 1204 | " num_proteins num_compounds \n", |
||
| 1205 | "0 1 1 \n", |
||
| 1206 | "1 1 1 \n", |
||
| 1207 | "2 3 1 \n", |
||
| 1208 | "3 1 1 \n", |
||
| 1209 | "4 1 1 \n", |
||
| 1210 | ".. ... ... \n", |
||
| 1211 | "223 3 1 \n", |
||
| 1212 | "224 1 5 \n", |
||
| 1213 | "225 1 5 \n", |
||
| 1214 | "226 1 1 \n", |
||
| 1215 | "227 1 1 \n", |
||
| 1216 | "\n", |
||
| 1217 | "[228 rows x 4 columns]" |
||
| 1218 | ] |
||
| 1219 | }, |
||
| 1220 | "execution_count": 20, |
||
| 1221 | "metadata": {}, |
||
| 1222 | "output_type": "execute_result" |
||
| 1223 | } |
||
| 1224 | ], |
||
| 1225 | "source": [ |
||
| 1226 | "reactions = m.get_nodes(types=REACTIONS)\n", |
||
| 1227 | "\n", |
||
| 1228 | "data = []\n", |
||
| 1229 | "for reaction_id, reaction_data in reactions:\n", |
||
| 1230 | " reaction_name = reaction_data['display_name']\n", |
||
| 1231 | " proteins = m.get_connected(reaction_id, dest_type=PROTEINS, observed=True)\n", |
||
| 1232 | " compounds = m.get_connected(reaction_id, dest_type=COMPOUNDS, observed=True)\n", |
||
| 1233 | " \n", |
||
| 1234 | " if len(proteins) > 0 and len(compounds) > 0:\n", |
||
| 1235 | " row = [reaction_id, reaction_name, len(proteins), len(compounds)]\n", |
||
| 1236 | " data.append(row)\n", |
||
| 1237 | "\n", |
||
| 1238 | "df = pd.DataFrame(data, columns=['reaction_id', 'reaction_name', 'num_proteins', 'num_compounds'])\n", |
||
| 1239 | "df" |
||
| 1240 | ] |
||
| 1241 | }, |
||
| 1242 | { |
||
| 1243 | "cell_type": "markdown", |
||
| 1244 | "metadata": {}, |
||
| 1245 | "source": [ |
||
| 1246 | "##### List all entities connected to reaction R-HSA-194153" |
||
| 1247 | ] |
||
| 1248 | }, |
||
| 1249 | { |
||
| 1250 | "cell_type": "code", |
||
| 1251 | "execution_count": 21, |
||
| 1252 | "metadata": {}, |
||
| 1253 | "outputs": [ |
||
| 1254 | { |
||
| 1255 | "data": { |
||
| 1256 | "text/html": [ |
||
| 1257 | "<div>\n", |
||
| 1258 | "<style scoped>\n", |
||
| 1259 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 1260 | " vertical-align: middle;\n", |
||
| 1261 | " }\n", |
||
| 1262 | "\n", |
||
| 1263 | " .dataframe tbody tr th {\n", |
||
| 1264 | " vertical-align: top;\n", |
||
| 1265 | " }\n", |
||
| 1266 | "\n", |
||
| 1267 | " .dataframe thead th {\n", |
||
| 1268 | " text-align: right;\n", |
||
| 1269 | " }\n", |
||
| 1270 | "</style>\n", |
||
| 1271 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 1272 | " <thead>\n", |
||
| 1273 | " <tr style=\"text-align: right;\">\n", |
||
| 1274 | " <th></th>\n", |
||
| 1275 | " <th>display_name</th>\n", |
||
| 1276 | " <th>data_type</th>\n", |
||
| 1277 | " <th>observed</th>\n", |
||
| 1278 | " <th>source_id</th>\n", |
||
| 1279 | " </tr>\n", |
||
| 1280 | " <tr>\n", |
||
| 1281 | " <th>entity_id</th>\n", |
||
| 1282 | " <th></th>\n", |
||
| 1283 | " <th></th>\n", |
||
| 1284 | " <th></th>\n", |
||
| 1285 | " <th></th>\n", |
||
| 1286 | " </tr>\n", |
||
| 1287 | " </thead>\n", |
||
| 1288 | " <tbody>\n", |
||
| 1289 | " <tr>\n", |
||
| 1290 | " <th>ENSG00000108846</th>\n", |
||
| 1291 | " <td>Abcc3</td>\n", |
||
| 1292 | " <td>genes</td>\n", |
||
| 1293 | " <td>False</td>\n", |
||
| 1294 | " <td>R-HSA-194153</td>\n", |
||
| 1295 | " </tr>\n", |
||
| 1296 | " <tr>\n", |
||
| 1297 | " <th>O15438</th>\n", |
||
| 1298 | " <td>O15438</td>\n", |
||
| 1299 | " <td>proteins</td>\n", |
||
| 1300 | " <td>False</td>\n", |
||
| 1301 | " <td>R-HSA-194153</td>\n", |
||
| 1302 | " </tr>\n", |
||
| 1303 | " <tr>\n", |
||
| 1304 | " <th>28865</th>\n", |
||
| 1305 | " <td>Taurocholic acid</td>\n", |
||
| 1306 | " <td>compounds</td>\n", |
||
| 1307 | " <td>True</td>\n", |
||
| 1308 | " <td>R-HSA-194153</td>\n", |
||
| 1309 | " </tr>\n", |
||
| 1310 | " <tr>\n", |
||
| 1311 | " <th>30616</th>\n", |
||
| 1312 | " <td>Atp(4-)</td>\n", |
||
| 1313 | " <td>compounds</td>\n", |
||
| 1314 | " <td>False</td>\n", |
||
| 1315 | " <td>R-HSA-194153</td>\n", |
||
| 1316 | " </tr>\n", |
||
| 1317 | " <tr>\n", |
||
| 1318 | " <th>17687</th>\n", |
||
| 1319 | " <td>Glycocholic acid</td>\n", |
||
| 1320 | " <td>compounds</td>\n", |
||
| 1321 | " <td>False</td>\n", |
||
| 1322 | " <td>R-HSA-194153</td>\n", |
||
| 1323 | " </tr>\n", |
||
| 1324 | " <tr>\n", |
||
| 1325 | " <th>36274</th>\n", |
||
| 1326 | " <td>Glycochenodeoxycholic acid</td>\n", |
||
| 1327 | " <td>compounds</td>\n", |
||
| 1328 | " <td>True</td>\n", |
||
| 1329 | " <td>R-HSA-194153</td>\n", |
||
| 1330 | " </tr>\n", |
||
| 1331 | " <tr>\n", |
||
| 1332 | " <th>16525</th>\n", |
||
| 1333 | " <td>Taurochenodeoxycholic acid</td>\n", |
||
| 1334 | " <td>compounds</td>\n", |
||
| 1335 | " <td>False</td>\n", |
||
| 1336 | " <td>R-HSA-194153</td>\n", |
||
| 1337 | " </tr>\n", |
||
| 1338 | " <tr>\n", |
||
| 1339 | " <th>43474</th>\n", |
||
| 1340 | " <td>Hydrogenphosphate</td>\n", |
||
| 1341 | " <td>compounds</td>\n", |
||
| 1342 | " <td>False</td>\n", |
||
| 1343 | " <td>R-HSA-194153</td>\n", |
||
| 1344 | " </tr>\n", |
||
| 1345 | " <tr>\n", |
||
| 1346 | " <th>456216</th>\n", |
||
| 1347 | " <td>Adp(3-)</td>\n", |
||
| 1348 | " <td>compounds</td>\n", |
||
| 1349 | " <td>False</td>\n", |
||
| 1350 | " <td>R-HSA-194153</td>\n", |
||
| 1351 | " </tr>\n", |
||
| 1352 | " <tr>\n", |
||
| 1353 | " <th>16359</th>\n", |
||
| 1354 | " <td>Cholic acid</td>\n", |
||
| 1355 | " <td>compounds</td>\n", |
||
| 1356 | " <td>True</td>\n", |
||
| 1357 | " <td>R-HSA-194153</td>\n", |
||
| 1358 | " </tr>\n", |
||
| 1359 | " <tr>\n", |
||
| 1360 | " <th>9407</th>\n", |
||
| 1361 | " <td>Taurochenodeoxycholate</td>\n", |
||
| 1362 | " <td>compounds</td>\n", |
||
| 1363 | " <td>True</td>\n", |
||
| 1364 | " <td>R-HSA-194153</td>\n", |
||
| 1365 | " </tr>\n", |
||
| 1366 | " <tr>\n", |
||
| 1367 | " <th>16755</th>\n", |
||
| 1368 | " <td>Chenodeoxycholic acid</td>\n", |
||
| 1369 | " <td>compounds</td>\n", |
||
| 1370 | " <td>True</td>\n", |
||
| 1371 | " <td>R-HSA-194153</td>\n", |
||
| 1372 | " </tr>\n", |
||
| 1373 | " <tr>\n", |
||
| 1374 | " <th>R-HSA-159418</th>\n", |
||
| 1375 | " <td>Recycling of bile acids and salts</td>\n", |
||
| 1376 | " <td>pathways</td>\n", |
||
| 1377 | " <td>None</td>\n", |
||
| 1378 | " <td>R-HSA-194153</td>\n", |
||
| 1379 | " </tr>\n", |
||
| 1380 | " </tbody>\n", |
||
| 1381 | "</table>\n", |
||
| 1382 | "</div>" |
||
| 1383 | ], |
||
| 1384 | "text/plain": [ |
||
| 1385 | " display_name data_type observed \\\n", |
||
| 1386 | "entity_id \n", |
||
| 1387 | "ENSG00000108846 Abcc3 genes False \n", |
||
| 1388 | "O15438 O15438 proteins False \n", |
||
| 1389 | "28865 Taurocholic acid compounds True \n", |
||
| 1390 | "30616 Atp(4-) compounds False \n", |
||
| 1391 | "17687 Glycocholic acid compounds False \n", |
||
| 1392 | "36274 Glycochenodeoxycholic acid compounds True \n", |
||
| 1393 | "16525 Taurochenodeoxycholic acid compounds False \n", |
||
| 1394 | "43474 Hydrogenphosphate compounds False \n", |
||
| 1395 | "456216 Adp(3-) compounds False \n", |
||
| 1396 | "16359 Cholic acid compounds True \n", |
||
| 1397 | "9407 Taurochenodeoxycholate compounds True \n", |
||
| 1398 | "16755 Chenodeoxycholic acid compounds True \n", |
||
| 1399 | "R-HSA-159418 Recycling of bile acids and salts pathways None \n", |
||
| 1400 | "\n", |
||
| 1401 | " source_id \n", |
||
| 1402 | "entity_id \n", |
||
| 1403 | "ENSG00000108846 R-HSA-194153 \n", |
||
| 1404 | "O15438 R-HSA-194153 \n", |
||
| 1405 | "28865 R-HSA-194153 \n", |
||
| 1406 | "30616 R-HSA-194153 \n", |
||
| 1407 | "17687 R-HSA-194153 \n", |
||
| 1408 | "36274 R-HSA-194153 \n", |
||
| 1409 | "16525 R-HSA-194153 \n", |
||
| 1410 | "43474 R-HSA-194153 \n", |
||
| 1411 | "456216 R-HSA-194153 \n", |
||
| 1412 | "16359 R-HSA-194153 \n", |
||
| 1413 | "9407 R-HSA-194153 \n", |
||
| 1414 | "16755 R-HSA-194153 \n", |
||
| 1415 | "R-HSA-159418 R-HSA-194153 " |
||
| 1416 | ] |
||
| 1417 | }, |
||
| 1418 | "execution_count": 21, |
||
| 1419 | "metadata": {}, |
||
| 1420 | "output_type": "execute_result" |
||
| 1421 | } |
||
| 1422 | ], |
||
| 1423 | "source": [ |
||
| 1424 | "query_id = 'R-HSA-194153'\n", |
||
| 1425 | "m.get_connected(query_id)" |
||
| 1426 | ] |
||
| 1427 | }, |
||
| 1428 | { |
||
| 1429 | "cell_type": "markdown", |
||
| 1430 | "metadata": {}, |
||
| 1431 | "source": [ |
||
| 1432 | "##### Query the connections between proteins and compounds (through their shared reactions)" |
||
| 1433 | ] |
||
| 1434 | }, |
||
| 1435 | { |
||
| 1436 | "cell_type": "code", |
||
| 1437 | "execution_count": 22, |
||
| 1438 | "metadata": {}, |
||
| 1439 | "outputs": [ |
||
| 1440 | { |
||
| 1441 | "data": { |
||
| 1442 | "text/html": [ |
||
| 1443 | "<div>\n", |
||
| 1444 | "<style scoped>\n", |
||
| 1445 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 1446 | " vertical-align: middle;\n", |
||
| 1447 | " }\n", |
||
| 1448 | "\n", |
||
| 1449 | " .dataframe tbody tr th {\n", |
||
| 1450 | " vertical-align: top;\n", |
||
| 1451 | " }\n", |
||
| 1452 | "\n", |
||
| 1453 | " .dataframe thead th {\n", |
||
| 1454 | " text-align: right;\n", |
||
| 1455 | " }\n", |
||
| 1456 | "</style>\n", |
||
| 1457 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 1458 | " <thead>\n", |
||
| 1459 | " <tr style=\"text-align: right;\">\n", |
||
| 1460 | " <th></th>\n", |
||
| 1461 | " <th>display_name</th>\n", |
||
| 1462 | " <th>data_type</th>\n", |
||
| 1463 | " <th>observed</th>\n", |
||
| 1464 | " <th>source_id</th>\n", |
||
| 1465 | " </tr>\n", |
||
| 1466 | " <tr>\n", |
||
| 1467 | " <th>entity_id</th>\n", |
||
| 1468 | " <th></th>\n", |
||
| 1469 | " <th></th>\n", |
||
| 1470 | " <th></th>\n", |
||
| 1471 | " <th></th>\n", |
||
| 1472 | " </tr>\n", |
||
| 1473 | " </thead>\n", |
||
| 1474 | " <tbody>\n", |
||
| 1475 | " <tr>\n", |
||
| 1476 | " <th>18421</th>\n", |
||
| 1477 | " <td>Superoxide</td>\n", |
||
| 1478 | " <td>compounds</td>\n", |
||
| 1479 | " <td>False</td>\n", |
||
| 1480 | " <td>P02768</td>\n", |
||
| 1481 | " </tr>\n", |
||
| 1482 | " <tr>\n", |
||
| 1483 | " <th>17033</th>\n", |
||
| 1484 | " <td>Biliverdin</td>\n", |
||
| 1485 | " <td>compounds</td>\n", |
||
| 1486 | " <td>True</td>\n", |
||
| 1487 | " <td>P02768</td>\n", |
||
| 1488 | " </tr>\n", |
||
| 1489 | " <tr>\n", |
||
| 1490 | " <th>16990</th>\n", |
||
| 1491 | " <td>Bilirubin ixalpha</td>\n", |
||
| 1492 | " <td>compounds</td>\n", |
||
| 1493 | " <td>True</td>\n", |
||
| 1494 | " <td>P02768</td>\n", |
||
| 1495 | " </tr>\n", |
||
| 1496 | " <tr>\n", |
||
| 1497 | " <th>17627</th>\n", |
||
| 1498 | " <td>Ferroheme b</td>\n", |
||
| 1499 | " <td>compounds</td>\n", |
||
| 1500 | " <td>False</td>\n", |
||
| 1501 | " <td>P02768</td>\n", |
||
| 1502 | " </tr>\n", |
||
| 1503 | " <tr>\n", |
||
| 1504 | " <th>36144</th>\n", |
||
| 1505 | " <td>Ferriheme b</td>\n", |
||
| 1506 | " <td>compounds</td>\n", |
||
| 1507 | " <td>False</td>\n", |
||
| 1508 | " <td>P02768</td>\n", |
||
| 1509 | " </tr>\n", |
||
| 1510 | " <tr>\n", |
||
| 1511 | " <th>456216</th>\n", |
||
| 1512 | " <td>Adp(3-)</td>\n", |
||
| 1513 | " <td>compounds</td>\n", |
||
| 1514 | " <td>False</td>\n", |
||
| 1515 | " <td>P02768</td>\n", |
||
| 1516 | " </tr>\n", |
||
| 1517 | " <tr>\n", |
||
| 1518 | " <th>30616</th>\n", |
||
| 1519 | " <td>Atp(4-)</td>\n", |
||
| 1520 | " <td>compounds</td>\n", |
||
| 1521 | " <td>False</td>\n", |
||
| 1522 | " <td>P02768</td>\n", |
||
| 1523 | " </tr>\n", |
||
| 1524 | " <tr>\n", |
||
| 1525 | " <th>36274</th>\n", |
||
| 1526 | " <td>Glycochenodeoxycholic acid</td>\n", |
||
| 1527 | " <td>compounds</td>\n", |
||
| 1528 | " <td>True</td>\n", |
||
| 1529 | " <td>P02768</td>\n", |
||
| 1530 | " </tr>\n", |
||
| 1531 | " <tr>\n", |
||
| 1532 | " <th>16755</th>\n", |
||
| 1533 | " <td>Chenodeoxycholic acid</td>\n", |
||
| 1534 | " <td>compounds</td>\n", |
||
| 1535 | " <td>True</td>\n", |
||
| 1536 | " <td>P02768</td>\n", |
||
| 1537 | " </tr>\n", |
||
| 1538 | " <tr>\n", |
||
| 1539 | " <th>16359</th>\n", |
||
| 1540 | " <td>Cholic acid</td>\n", |
||
| 1541 | " <td>compounds</td>\n", |
||
| 1542 | " <td>True</td>\n", |
||
| 1543 | " <td>P02768</td>\n", |
||
| 1544 | " </tr>\n", |
||
| 1545 | " <tr>\n", |
||
| 1546 | " <th>28865</th>\n", |
||
| 1547 | " <td>Taurocholic acid</td>\n", |
||
| 1548 | " <td>compounds</td>\n", |
||
| 1549 | " <td>True</td>\n", |
||
| 1550 | " <td>P02768</td>\n", |
||
| 1551 | " </tr>\n", |
||
| 1552 | " <tr>\n", |
||
| 1553 | " <th>17687</th>\n", |
||
| 1554 | " <td>Glycocholic acid</td>\n", |
||
| 1555 | " <td>compounds</td>\n", |
||
| 1556 | " <td>False</td>\n", |
||
| 1557 | " <td>P02768</td>\n", |
||
| 1558 | " </tr>\n", |
||
| 1559 | " <tr>\n", |
||
| 1560 | " <th>9407</th>\n", |
||
| 1561 | " <td>Taurochenodeoxycholate</td>\n", |
||
| 1562 | " <td>compounds</td>\n", |
||
| 1563 | " <td>True</td>\n", |
||
| 1564 | " <td>P02768</td>\n", |
||
| 1565 | " </tr>\n", |
||
| 1566 | " <tr>\n", |
||
| 1567 | " <th>17504</th>\n", |
||
| 1568 | " <td>1-o-acyl-sn-glycero-3-phosphocholine(1+)</td>\n", |
||
| 1569 | " <td>compounds</td>\n", |
||
| 1570 | " <td>False</td>\n", |
||
| 1571 | " <td>P02768</td>\n", |
||
| 1572 | " </tr>\n", |
||
| 1573 | " </tbody>\n", |
||
| 1574 | "</table>\n", |
||
| 1575 | "</div>" |
||
| 1576 | ], |
||
| 1577 | "text/plain": [ |
||
| 1578 | " display_name data_type observed \\\n", |
||
| 1579 | "entity_id \n", |
||
| 1580 | "18421 Superoxide compounds False \n", |
||
| 1581 | "17033 Biliverdin compounds True \n", |
||
| 1582 | "16990 Bilirubin ixalpha compounds True \n", |
||
| 1583 | "17627 Ferroheme b compounds False \n", |
||
| 1584 | "36144 Ferriheme b compounds False \n", |
||
| 1585 | "456216 Adp(3-) compounds False \n", |
||
| 1586 | "30616 Atp(4-) compounds False \n", |
||
| 1587 | "36274 Glycochenodeoxycholic acid compounds True \n", |
||
| 1588 | "16755 Chenodeoxycholic acid compounds True \n", |
||
| 1589 | "16359 Cholic acid compounds True \n", |
||
| 1590 | "28865 Taurocholic acid compounds True \n", |
||
| 1591 | "17687 Glycocholic acid compounds False \n", |
||
| 1592 | "9407 Taurochenodeoxycholate compounds True \n", |
||
| 1593 | "17504 1-o-acyl-sn-glycero-3-phosphocholine(1+) compounds False \n", |
||
| 1594 | "\n", |
||
| 1595 | " source_id \n", |
||
| 1596 | "entity_id \n", |
||
| 1597 | "18421 P02768 \n", |
||
| 1598 | "17033 P02768 \n", |
||
| 1599 | "16990 P02768 \n", |
||
| 1600 | "17627 P02768 \n", |
||
| 1601 | "36144 P02768 \n", |
||
| 1602 | "456216 P02768 \n", |
||
| 1603 | "30616 P02768 \n", |
||
| 1604 | "36274 P02768 \n", |
||
| 1605 | "16755 P02768 \n", |
||
| 1606 | "16359 P02768 \n", |
||
| 1607 | "28865 P02768 \n", |
||
| 1608 | "17687 P02768 \n", |
||
| 1609 | "9407 P02768 \n", |
||
| 1610 | "17504 P02768 " |
||
| 1611 | ] |
||
| 1612 | }, |
||
| 1613 | "execution_count": 22, |
||
| 1614 | "metadata": {}, |
||
| 1615 | "output_type": "execute_result" |
||
| 1616 | } |
||
| 1617 | ], |
||
| 1618 | "source": [ |
||
| 1619 | "query_id = 'P02768'\n", |
||
| 1620 | "m.get_connected(query_id, dest_type=COMPOUNDS)" |
||
| 1621 | ] |
||
| 1622 | }, |
||
| 1623 | { |
||
| 1624 | "cell_type": "code", |
||
| 1625 | "execution_count": 23, |
||
| 1626 | "metadata": {}, |
||
| 1627 | "outputs": [ |
||
| 1628 | { |
||
| 1629 | "data": { |
||
| 1630 | "text/html": [ |
||
| 1631 | "<div>\n", |
||
| 1632 | "<style scoped>\n", |
||
| 1633 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 1634 | " vertical-align: middle;\n", |
||
| 1635 | " }\n", |
||
| 1636 | "\n", |
||
| 1637 | " .dataframe tbody tr th {\n", |
||
| 1638 | " vertical-align: top;\n", |
||
| 1639 | " }\n", |
||
| 1640 | "\n", |
||
| 1641 | " .dataframe thead th {\n", |
||
| 1642 | " text-align: right;\n", |
||
| 1643 | " }\n", |
||
| 1644 | "</style>\n", |
||
| 1645 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 1646 | " <thead>\n", |
||
| 1647 | " <tr style=\"text-align: right;\">\n", |
||
| 1648 | " <th></th>\n", |
||
| 1649 | " <th>display_name</th>\n", |
||
| 1650 | " <th>data_type</th>\n", |
||
| 1651 | " <th>observed</th>\n", |
||
| 1652 | " <th>source_id</th>\n", |
||
| 1653 | " </tr>\n", |
||
| 1654 | " <tr>\n", |
||
| 1655 | " <th>entity_id</th>\n", |
||
| 1656 | " <th></th>\n", |
||
| 1657 | " <th></th>\n", |
||
| 1658 | " <th></th>\n", |
||
| 1659 | " <th></th>\n", |
||
| 1660 | " </tr>\n", |
||
| 1661 | " </thead>\n", |
||
| 1662 | " <tbody>\n", |
||
| 1663 | " <tr>\n", |
||
| 1664 | " <th>Q9NPD5</th>\n", |
||
| 1665 | " <td>Q9NPD5</td>\n", |
||
| 1666 | " <td>proteins</td>\n", |
||
| 1667 | " <td>False</td>\n", |
||
| 1668 | " <td>16990</td>\n", |
||
| 1669 | " </tr>\n", |
||
| 1670 | " <tr>\n", |
||
| 1671 | " <th>P33527</th>\n", |
||
| 1672 | " <td>P33527</td>\n", |
||
| 1673 | " <td>proteins</td>\n", |
||
| 1674 | " <td>False</td>\n", |
||
| 1675 | " <td>16990</td>\n", |
||
| 1676 | " </tr>\n", |
||
| 1677 | " <tr>\n", |
||
| 1678 | " <th>Q9BYK8</th>\n", |
||
| 1679 | " <td>Q9BYK8</td>\n", |
||
| 1680 | " <td>proteins</td>\n", |
||
| 1681 | " <td>False</td>\n", |
||
| 1682 | " <td>16990</td>\n", |
||
| 1683 | " </tr>\n", |
||
| 1684 | " <tr>\n", |
||
| 1685 | " <th>Q96RS0</th>\n", |
||
| 1686 | " <td>Q96RS0</td>\n", |
||
| 1687 | " <td>proteins</td>\n", |
||
| 1688 | " <td>False</td>\n", |
||
| 1689 | " <td>16990</td>\n", |
||
| 1690 | " </tr>\n", |
||
| 1691 | " <tr>\n", |
||
| 1692 | " <th>Q92793</th>\n", |
||
| 1693 | " <td>Q92793</td>\n", |
||
| 1694 | " <td>proteins</td>\n", |
||
| 1695 | " <td>False</td>\n", |
||
| 1696 | " <td>16990</td>\n", |
||
| 1697 | " </tr>\n", |
||
| 1698 | " <tr>\n", |
||
| 1699 | " <th>...</th>\n", |
||
| 1700 | " <td>...</td>\n", |
||
| 1701 | " <td>...</td>\n", |
||
| 1702 | " <td>...</td>\n", |
||
| 1703 | " <td>...</td>\n", |
||
| 1704 | " </tr>\n", |
||
| 1705 | " <tr>\n", |
||
| 1706 | " <th>P08047</th>\n", |
||
| 1707 | " <td>P08047</td>\n", |
||
| 1708 | " <td>proteins</td>\n", |
||
| 1709 | " <td>False</td>\n", |
||
| 1710 | " <td>16990</td>\n", |
||
| 1711 | " </tr>\n", |
||
| 1712 | " <tr>\n", |
||
| 1713 | " <th>P30043</th>\n", |
||
| 1714 | " <td>P30043</td>\n", |
||
| 1715 | " <td>proteins</td>\n", |
||
| 1716 | " <td>True</td>\n", |
||
| 1717 | " <td>16990</td>\n", |
||
| 1718 | " </tr>\n", |
||
| 1719 | " <tr>\n", |
||
| 1720 | " <th>P53004</th>\n", |
||
| 1721 | " <td>P53004</td>\n", |
||
| 1722 | " <td>proteins</td>\n", |
||
| 1723 | " <td>False</td>\n", |
||
| 1724 | " <td>16990</td>\n", |
||
| 1725 | " </tr>\n", |
||
| 1726 | " <tr>\n", |
||
| 1727 | " <th>O75182</th>\n", |
||
| 1728 | " <td>O75182</td>\n", |
||
| 1729 | " <td>proteins</td>\n", |
||
| 1730 | " <td>False</td>\n", |
||
| 1731 | " <td>16990</td>\n", |
||
| 1732 | " </tr>\n", |
||
| 1733 | " <tr>\n", |
||
| 1734 | " <th>Q96ST3</th>\n", |
||
| 1735 | " <td>Q96ST3</td>\n", |
||
| 1736 | " <td>proteins</td>\n", |
||
| 1737 | " <td>False</td>\n", |
||
| 1738 | " <td>16990</td>\n", |
||
| 1739 | " </tr>\n", |
||
| 1740 | " </tbody>\n", |
||
| 1741 | "</table>\n", |
||
| 1742 | "<p>130 rows × 4 columns</p>\n", |
||
| 1743 | "</div>" |
||
| 1744 | ], |
||
| 1745 | "text/plain": [ |
||
| 1746 | " display_name data_type observed source_id\n", |
||
| 1747 | "entity_id \n", |
||
| 1748 | "Q9NPD5 Q9NPD5 proteins False 16990\n", |
||
| 1749 | "P33527 P33527 proteins False 16990\n", |
||
| 1750 | "Q9BYK8 Q9BYK8 proteins False 16990\n", |
||
| 1751 | "Q96RS0 Q96RS0 proteins False 16990\n", |
||
| 1752 | "Q92793 Q92793 proteins False 16990\n", |
||
| 1753 | "... ... ... ... ...\n", |
||
| 1754 | "P08047 P08047 proteins False 16990\n", |
||
| 1755 | "P30043 P30043 proteins True 16990\n", |
||
| 1756 | "P53004 P53004 proteins False 16990\n", |
||
| 1757 | "O75182 O75182 proteins False 16990\n", |
||
| 1758 | "Q96ST3 Q96ST3 proteins False 16990\n", |
||
| 1759 | "\n", |
||
| 1760 | "[130 rows x 4 columns]" |
||
| 1761 | ] |
||
| 1762 | }, |
||
| 1763 | "execution_count": 23, |
||
| 1764 | "metadata": {}, |
||
| 1765 | "output_type": "execute_result" |
||
| 1766 | } |
||
| 1767 | ], |
||
| 1768 | "source": [ |
||
| 1769 | "query_id = '16990'\n", |
||
| 1770 | "m.get_connected(query_id, dest_type=PROTEINS)" |
||
| 1771 | ] |
||
| 1772 | } |
||
| 1773 | ], |
||
| 1774 | "metadata": { |
||
| 1775 | "kernelspec": { |
||
| 1776 | "display_name": "Python 3 (ipykernel)", |
||
| 1777 | "language": "python", |
||
| 1778 | "name": "python3" |
||
| 1779 | }, |
||
| 1780 | "language_info": { |
||
| 1781 | "codemirror_mode": { |
||
| 1782 | "name": "ipython", |
||
| 1783 | "version": 3 |
||
| 1784 | }, |
||
| 1785 | "file_extension": ".py", |
||
| 1786 | "mimetype": "text/x-python", |
||
| 1787 | "name": "python", |
||
| 1788 | "nbconvert_exporter": "python", |
||
| 1789 | "pygments_lexer": "ipython3", |
||
| 1790 | "version": "3.10.1" |
||
| 1791 | } |
||
| 1792 | }, |
||
| 1793 | "nbformat": 4, |
||
| 1794 | "nbformat_minor": 4 |
||
| 1795 | } |