Datasets
Models
Downloads: 1
Diff of
/notebooks/base_test.ipynb
[000000]
..
[7d5693]
Switch to unified view
| a | b/notebooks/base_test.ipynb | ||
|---|---|---|---|
| 1 | { |
||
| 2 | "cells": [ |
||
| 3 | { |
||
| 4 | "cell_type": "code", |
||
| 5 | "execution_count": 1, |
||
| 6 | "metadata": { |
||
| 7 | "tags": [] |
||
| 8 | }, |
||
| 9 | "outputs": [], |
||
| 10 | "source": [ |
||
| 11 | "%load_ext autoreload\n", |
||
| 12 | "%autoreload 2\n", |
||
| 13 | "\n", |
||
| 14 | "%matplotlib inline" |
||
| 15 | ] |
||
| 16 | }, |
||
| 17 | { |
||
| 18 | "cell_type": "code", |
||
| 19 | "execution_count": 2, |
||
| 20 | "metadata": {}, |
||
| 21 | "outputs": [], |
||
| 22 | "source": [ |
||
| 23 | "import os, sys" |
||
| 24 | ] |
||
| 25 | }, |
||
| 26 | { |
||
| 27 | "cell_type": "code", |
||
| 28 | "execution_count": 3, |
||
| 29 | "metadata": {}, |
||
| 30 | "outputs": [], |
||
| 31 | "source": [ |
||
| 32 | "import pylab as plt\n", |
||
| 33 | "import matplotlib\n", |
||
| 34 | "\n", |
||
| 35 | "import numpy as np\n", |
||
| 36 | "import pandas as pd" |
||
| 37 | ] |
||
| 38 | }, |
||
| 39 | { |
||
| 40 | "cell_type": "code", |
||
| 41 | "execution_count": 4, |
||
| 42 | "metadata": {}, |
||
| 43 | "outputs": [ |
||
| 44 | { |
||
| 45 | "name": "stdout", |
||
| 46 | "output_type": "stream", |
||
| 47 | "text": [ |
||
| 48 | "['/Users/joewandy/Work/git/pyMultiOmics/notebooks', '/opt/anaconda3/envs/pyMultiOmics/lib/python310.zip', '/opt/anaconda3/envs/pyMultiOmics/lib/python3.10', '/opt/anaconda3/envs/pyMultiOmics/lib/python3.10/lib-dynload', '', '/opt/anaconda3/envs/pyMultiOmics/lib/python3.10/site-packages']\n" |
||
| 49 | ] |
||
| 50 | } |
||
| 51 | ], |
||
| 52 | "source": [ |
||
| 53 | "os.getcwd()\n", |
||
| 54 | "print(sys.path)" |
||
| 55 | ] |
||
| 56 | }, |
||
| 57 | { |
||
| 58 | "cell_type": "code", |
||
| 59 | "execution_count": 5, |
||
| 60 | "metadata": {}, |
||
| 61 | "outputs": [ |
||
| 62 | { |
||
| 63 | "name": "stderr", |
||
| 64 | "output_type": "stream", |
||
| 65 | "text": [ |
||
| 66 | "2022-03-24 14:39:13.236 | WARNING | pyMultiOmics.reactome:get_neo4j_driver:14 - Using a default neo4j server: bolt://localhost:7687\n", |
||
| 67 | "2022-03-24 14:39:13.236 | WARNING | pyMultiOmics.reactome:get_neo4j_driver:19 - Using a default neo4j username or password: neo4j\n", |
||
| 68 | "2022-03-24 14:39:13.236 | INFO | pyMultiOmics.reactome:get_neo4j_driver:24 - Created graph database driver for bolt://localhost:7687 (neo4j)\n" |
||
| 69 | ] |
||
| 70 | } |
||
| 71 | ], |
||
| 72 | "source": [ |
||
| 73 | "sys.path.append('..')\n", |
||
| 74 | "\n", |
||
| 75 | "from pyMultiOmics.base import SingleOmicsData, MultiOmicsData\n", |
||
| 76 | "from pyMultiOmics.mapping import Mapper\n", |
||
| 77 | "from pyMultiOmics.common import set_log_level_info, set_log_level_debug, download_file, extract_zip_file\n", |
||
| 78 | "from pyMultiOmics.constants import IDENTIFIER_COL, SAMPLE_COL\n", |
||
| 79 | "from pyMultiOmics.constants import GENES, PROTEINS, COMPOUNDS" |
||
| 80 | ] |
||
| 81 | }, |
||
| 82 | { |
||
| 83 | "cell_type": "markdown", |
||
| 84 | "metadata": {}, |
||
| 85 | "source": [ |
||
| 86 | "# Demonstration of pyMultiOmics base classes" |
||
| 87 | ] |
||
| 88 | }, |
||
| 89 | { |
||
| 90 | "cell_type": "markdown", |
||
| 91 | "metadata": { |
||
| 92 | "tags": [] |
||
| 93 | }, |
||
| 94 | "source": [ |
||
| 95 | "### Load the multi-omics COVID-19 data from [1]\n", |
||
| 96 | "\n", |
||
| 97 | "[1] [Overmyer, Katherine A., et al. \"Large-scale multi-omic analysis of COVID-19 severity.\" Cell systems 12.1 (2021): 23-40.](https://www.sciencedirect.com/science/article/pii/S2405471220303719)" |
||
| 98 | ] |
||
| 99 | }, |
||
| 100 | { |
||
| 101 | "cell_type": "code", |
||
| 102 | "execution_count": 6, |
||
| 103 | "metadata": {}, |
||
| 104 | "outputs": [ |
||
| 105 | { |
||
| 106 | "name": "stderr", |
||
| 107 | "output_type": "stream", |
||
| 108 | "text": [ |
||
| 109 | "2022-03-24 14:39:14.454 | INFO | pyMultiOmics.common:download_file:59 - Downloading covid19_multiomics_data.zip\n", |
||
| 110 | "2.36kKB [00:00, 15.6kKB/s] \n", |
||
| 111 | "2022-03-24 14:39:14.634 | INFO | pyMultiOmics.common:extract_zip_file:71 - Extracting covid19_multiomics_data.zip\n", |
||
| 112 | "100%|██████████████████████████████████████████████████████████████████████████████████| 14/14 [00:00<00:00, 256.77it/s]\n", |
||
| 113 | "2022-03-24 14:39:14.692 | INFO | pyMultiOmics.common:extract_zip_file:77 - Deleting covid19_multiomics_data.zip\n" |
||
| 114 | ] |
||
| 115 | } |
||
| 116 | ], |
||
| 117 | "source": [ |
||
| 118 | "url = 'https://github.com/glasgowcompbio/pyMultiOmics-data/raw/main/covid19_multiomics_data.zip'\n", |
||
| 119 | "out_file = download_file(url)\n", |
||
| 120 | "extract_zip_file(out_file)" |
||
| 121 | ] |
||
| 122 | }, |
||
| 123 | { |
||
| 124 | "cell_type": "code", |
||
| 125 | "execution_count": 7, |
||
| 126 | "metadata": {}, |
||
| 127 | "outputs": [ |
||
| 128 | { |
||
| 129 | "data": { |
||
| 130 | "text/plain": [ |
||
| 131 | "'/Users/joewandy/Work/git/pyMultiOmics/notebooks/covid19_multiomics_data'" |
||
| 132 | ] |
||
| 133 | }, |
||
| 134 | "execution_count": 7, |
||
| 135 | "metadata": {}, |
||
| 136 | "output_type": "execute_result" |
||
| 137 | } |
||
| 138 | ], |
||
| 139 | "source": [ |
||
| 140 | "DATA_FOLDER = os.path.abspath(os.path.join('covid19_multiomics_data'))\n", |
||
| 141 | "DATA_FOLDER" |
||
| 142 | ] |
||
| 143 | }, |
||
| 144 | { |
||
| 145 | "cell_type": "markdown", |
||
| 146 | "metadata": {}, |
||
| 147 | "source": [ |
||
| 148 | "### Read the individual dataframes" |
||
| 149 | ] |
||
| 150 | }, |
||
| 151 | { |
||
| 152 | "cell_type": "code", |
||
| 153 | "execution_count": 8, |
||
| 154 | "metadata": {}, |
||
| 155 | "outputs": [], |
||
| 156 | "source": [ |
||
| 157 | "transcript_df = pd.read_csv(os.path.join(DATA_FOLDER, 'covid_genes_include_p.csv'), index_col='Identifier')\n", |
||
| 158 | "transcript_design = pd.read_csv(os.path.join(DATA_FOLDER, 'covid_genes_design.csv'), index_col='sample')" |
||
| 159 | ] |
||
| 160 | }, |
||
| 161 | { |
||
| 162 | "cell_type": "code", |
||
| 163 | "execution_count": 9, |
||
| 164 | "metadata": {}, |
||
| 165 | "outputs": [], |
||
| 166 | "source": [ |
||
| 167 | "protein_df = pd.read_csv(os.path.join(DATA_FOLDER, 'covid_protein_include_p.csv'), index_col='Identifier')\n", |
||
| 168 | "protein_design = pd.read_csv(os.path.join(DATA_FOLDER, 'covid_protein_design.csv'), index_col='sample')" |
||
| 169 | ] |
||
| 170 | }, |
||
| 171 | { |
||
| 172 | "cell_type": "code", |
||
| 173 | "execution_count": 10, |
||
| 174 | "metadata": {}, |
||
| 175 | "outputs": [], |
||
| 176 | "source": [ |
||
| 177 | "compound_df = pd.read_csv(os.path.join(DATA_FOLDER, 'covid_compounds_include_p.csv'), index_col='Identifier')\n", |
||
| 178 | "compound_design = pd.read_csv(os.path.join(DATA_FOLDER, 'covid_compounds_design.csv'), index_col='sample')" |
||
| 179 | ] |
||
| 180 | }, |
||
| 181 | { |
||
| 182 | "cell_type": "markdown", |
||
| 183 | "metadata": {}, |
||
| 184 | "source": [ |
||
| 185 | "### Create single omics data container objects" |
||
| 186 | ] |
||
| 187 | }, |
||
| 188 | { |
||
| 189 | "cell_type": "markdown", |
||
| 190 | "metadata": {}, |
||
| 191 | "source": [ |
||
| 192 | "Some data cleaning is done upon loading in `SingleOmicsData`:\n", |
||
| 193 | "- Duplicate values are removed from the rows and columns\n", |
||
| 194 | "- Duplicate sample names are removed\n", |
||
| 195 | "- Measurements with missing metadata are removed\n", |
||
| 196 | "- Metadata with missing measurements are removed too" |
||
| 197 | ] |
||
| 198 | }, |
||
| 199 | { |
||
| 200 | "cell_type": "code", |
||
| 201 | "execution_count": 11, |
||
| 202 | "metadata": {}, |
||
| 203 | "outputs": [ |
||
| 204 | { |
||
| 205 | "name": "stderr", |
||
| 206 | "output_type": "stream", |
||
| 207 | "text": [ |
||
| 208 | "2022-03-24 14:39:14.981 | WARNING | pyMultiOmics.base:_keep_common_samples:126 - Dropped 4 columns from sample metadata due to missing measurements\n" |
||
| 209 | ] |
||
| 210 | }, |
||
| 211 | { |
||
| 212 | "data": { |
||
| 213 | "text/plain": [ |
||
| 214 | "genes data with (13028, 125) measurements" |
||
| 215 | ] |
||
| 216 | }, |
||
| 217 | "execution_count": 11, |
||
| 218 | "metadata": {}, |
||
| 219 | "output_type": "execute_result" |
||
| 220 | } |
||
| 221 | ], |
||
| 222 | "source": [ |
||
| 223 | "transcript_data = SingleOmicsData(GENES, transcript_df, transcript_design)\n", |
||
| 224 | "transcript_data" |
||
| 225 | ] |
||
| 226 | }, |
||
| 227 | { |
||
| 228 | "cell_type": "code", |
||
| 229 | "execution_count": 12, |
||
| 230 | "metadata": {}, |
||
| 231 | "outputs": [ |
||
| 232 | { |
||
| 233 | "data": { |
||
| 234 | "text/plain": [ |
||
| 235 | "proteins data with (1499, 129) measurements" |
||
| 236 | ] |
||
| 237 | }, |
||
| 238 | "execution_count": 12, |
||
| 239 | "metadata": {}, |
||
| 240 | "output_type": "execute_result" |
||
| 241 | } |
||
| 242 | ], |
||
| 243 | "source": [ |
||
| 244 | "protein_data = SingleOmicsData(PROTEINS, protein_df, protein_design)\n", |
||
| 245 | "protein_data" |
||
| 246 | ] |
||
| 247 | }, |
||
| 248 | { |
||
| 249 | "cell_type": "code", |
||
| 250 | "execution_count": 13, |
||
| 251 | "metadata": {}, |
||
| 252 | "outputs": [ |
||
| 253 | { |
||
| 254 | "data": { |
||
| 255 | "text/plain": [ |
||
| 256 | "compounds data with (46, 129) measurements" |
||
| 257 | ] |
||
| 258 | }, |
||
| 259 | "execution_count": 13, |
||
| 260 | "metadata": {}, |
||
| 261 | "output_type": "execute_result" |
||
| 262 | } |
||
| 263 | ], |
||
| 264 | "source": [ |
||
| 265 | "compound_data = SingleOmicsData(COMPOUNDS, compound_df, compound_design)\n", |
||
| 266 | "compound_data" |
||
| 267 | ] |
||
| 268 | }, |
||
| 269 | { |
||
| 270 | "cell_type": "markdown", |
||
| 271 | "metadata": {}, |
||
| 272 | "source": [ |
||
| 273 | "### Getting values" |
||
| 274 | ] |
||
| 275 | }, |
||
| 276 | { |
||
| 277 | "cell_type": "markdown", |
||
| 278 | "metadata": {}, |
||
| 279 | "source": [ |
||
| 280 | "You can get data out of the container by using the `data_df` and `design_df` attributes.\n", |
||
| 281 | "\n", |
||
| 282 | "Notice that after the data is loaded and cleaned, the number of samples in the measurement dataframe (`data_df`) is the same as the number of rows in the sample metadata dataframe (`design_df`)." |
||
| 283 | ] |
||
| 284 | }, |
||
| 285 | { |
||
| 286 | "cell_type": "code", |
||
| 287 | "execution_count": 14, |
||
| 288 | "metadata": {}, |
||
| 289 | "outputs": [ |
||
| 290 | { |
||
| 291 | "data": { |
||
| 292 | "text/html": [ |
||
| 293 | "<div>\n", |
||
| 294 | "<style scoped>\n", |
||
| 295 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 296 | " vertical-align: middle;\n", |
||
| 297 | " }\n", |
||
| 298 | "\n", |
||
| 299 | " .dataframe tbody tr th {\n", |
||
| 300 | " vertical-align: top;\n", |
||
| 301 | " }\n", |
||
| 302 | "\n", |
||
| 303 | " .dataframe thead th {\n", |
||
| 304 | " text-align: right;\n", |
||
| 305 | " }\n", |
||
| 306 | "</style>\n", |
||
| 307 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 308 | " <thead>\n", |
||
| 309 | " <tr style=\"text-align: right;\">\n", |
||
| 310 | " <th></th>\n", |
||
| 311 | " <th>sample_1</th>\n", |
||
| 312 | " <th>sample_2</th>\n", |
||
| 313 | " <th>sample_3</th>\n", |
||
| 314 | " <th>sample_4</th>\n", |
||
| 315 | " <th>sample_5</th>\n", |
||
| 316 | " <th>sample_6</th>\n", |
||
| 317 | " <th>sample_7</th>\n", |
||
| 318 | " <th>sample_8</th>\n", |
||
| 319 | " <th>sample_9</th>\n", |
||
| 320 | " <th>sample_10</th>\n", |
||
| 321 | " <th>...</th>\n", |
||
| 322 | " <th>sample_120</th>\n", |
||
| 323 | " <th>sample_121</th>\n", |
||
| 324 | " <th>sample_122</th>\n", |
||
| 325 | " <th>sample_123</th>\n", |
||
| 326 | " <th>sample_124</th>\n", |
||
| 327 | " <th>sample_125</th>\n", |
||
| 328 | " <th>sample_126</th>\n", |
||
| 329 | " <th>sample_127</th>\n", |
||
| 330 | " <th>sample_128</th>\n", |
||
| 331 | " <th>sample_129</th>\n", |
||
| 332 | " </tr>\n", |
||
| 333 | " <tr>\n", |
||
| 334 | " <th>Identifier</th>\n", |
||
| 335 | " <th></th>\n", |
||
| 336 | " <th></th>\n", |
||
| 337 | " <th></th>\n", |
||
| 338 | " <th></th>\n", |
||
| 339 | " <th></th>\n", |
||
| 340 | " <th></th>\n", |
||
| 341 | " <th></th>\n", |
||
| 342 | " <th></th>\n", |
||
| 343 | " <th></th>\n", |
||
| 344 | " <th></th>\n", |
||
| 345 | " <th></th>\n", |
||
| 346 | " <th></th>\n", |
||
| 347 | " <th></th>\n", |
||
| 348 | " <th></th>\n", |
||
| 349 | " <th></th>\n", |
||
| 350 | " <th></th>\n", |
||
| 351 | " <th></th>\n", |
||
| 352 | " <th></th>\n", |
||
| 353 | " <th></th>\n", |
||
| 354 | " <th></th>\n", |
||
| 355 | " <th></th>\n", |
||
| 356 | " </tr>\n", |
||
| 357 | " </thead>\n", |
||
| 358 | " <tbody>\n", |
||
| 359 | " <tr>\n", |
||
| 360 | " <th>A0A024R6I7</th>\n", |
||
| 361 | " <td>37.995543</td>\n", |
||
| 362 | " <td>37.353091</td>\n", |
||
| 363 | " <td>37.527875</td>\n", |
||
| 364 | " <td>37.673128</td>\n", |
||
| 365 | " <td>37.983542</td>\n", |
||
| 366 | " <td>37.489959</td>\n", |
||
| 367 | " <td>37.615303</td>\n", |
||
| 368 | " <td>37.534702</td>\n", |
||
| 369 | " <td>37.525762</td>\n", |
||
| 370 | " <td>37.844902</td>\n", |
||
| 371 | " <td>...</td>\n", |
||
| 372 | " <td>37.730180</td>\n", |
||
| 373 | " <td>38.082377</td>\n", |
||
| 374 | " <td>37.661959</td>\n", |
||
| 375 | " <td>37.195828</td>\n", |
||
| 376 | " <td>37.365447</td>\n", |
||
| 377 | " <td>37.564109</td>\n", |
||
| 378 | " <td>37.683884</td>\n", |
||
| 379 | " <td>37.282698</td>\n", |
||
| 380 | " <td>37.655909</td>\n", |
||
| 381 | " <td>37.754401</td>\n", |
||
| 382 | " </tr>\n", |
||
| 383 | " <tr>\n", |
||
| 384 | " <th>A0A0G2JRN3</th>\n", |
||
| 385 | " <td>37.995543</td>\n", |
||
| 386 | " <td>37.353091</td>\n", |
||
| 387 | " <td>37.527875</td>\n", |
||
| 388 | " <td>37.673128</td>\n", |
||
| 389 | " <td>37.983542</td>\n", |
||
| 390 | " <td>37.489959</td>\n", |
||
| 391 | " <td>37.615303</td>\n", |
||
| 392 | " <td>37.534702</td>\n", |
||
| 393 | " <td>37.525762</td>\n", |
||
| 394 | " <td>37.844902</td>\n", |
||
| 395 | " <td>...</td>\n", |
||
| 396 | " <td>37.730180</td>\n", |
||
| 397 | " <td>38.082377</td>\n", |
||
| 398 | " <td>37.661959</td>\n", |
||
| 399 | " <td>37.195828</td>\n", |
||
| 400 | " <td>37.365447</td>\n", |
||
| 401 | " <td>37.564109</td>\n", |
||
| 402 | " <td>37.683884</td>\n", |
||
| 403 | " <td>37.282698</td>\n", |
||
| 404 | " <td>37.655909</td>\n", |
||
| 405 | " <td>37.754401</td>\n", |
||
| 406 | " </tr>\n", |
||
| 407 | " <tr>\n", |
||
| 408 | " <th>A0A075B6H9</th>\n", |
||
| 409 | " <td>27.176361</td>\n", |
||
| 410 | " <td>29.419228</td>\n", |
||
| 411 | " <td>27.174171</td>\n", |
||
| 412 | " <td>28.879702</td>\n", |
||
| 413 | " <td>27.262485</td>\n", |
||
| 414 | " <td>29.535232</td>\n", |
||
| 415 | " <td>27.657446</td>\n", |
||
| 416 | " <td>30.323779</td>\n", |
||
| 417 | " <td>28.194885</td>\n", |
||
| 418 | " <td>29.253091</td>\n", |
||
| 419 | " <td>...</td>\n", |
||
| 420 | " <td>27.731627</td>\n", |
||
| 421 | " <td>27.621776</td>\n", |
||
| 422 | " <td>27.249976</td>\n", |
||
| 423 | " <td>27.403813</td>\n", |
||
| 424 | " <td>27.133006</td>\n", |
||
| 425 | " <td>27.793462</td>\n", |
||
| 426 | " <td>26.876193</td>\n", |
||
| 427 | " <td>27.715091</td>\n", |
||
| 428 | " <td>26.965212</td>\n", |
||
| 429 | " <td>28.376997</td>\n", |
||
| 430 | " </tr>\n", |
||
| 431 | " <tr>\n", |
||
| 432 | " <th>A0A075B6I0</th>\n", |
||
| 433 | " <td>28.294477</td>\n", |
||
| 434 | " <td>29.048510</td>\n", |
||
| 435 | " <td>28.953215</td>\n", |
||
| 436 | " <td>29.527460</td>\n", |
||
| 437 | " <td>28.605867</td>\n", |
||
| 438 | " <td>29.251895</td>\n", |
||
| 439 | " <td>26.943355</td>\n", |
||
| 440 | " <td>29.914134</td>\n", |
||
| 441 | " <td>28.947290</td>\n", |
||
| 442 | " <td>29.108465</td>\n", |
||
| 443 | " <td>...</td>\n", |
||
| 444 | " <td>28.977874</td>\n", |
||
| 445 | " <td>27.961132</td>\n", |
||
| 446 | " <td>29.085045</td>\n", |
||
| 447 | " <td>28.319069</td>\n", |
||
| 448 | " <td>29.418182</td>\n", |
||
| 449 | " <td>29.003245</td>\n", |
||
| 450 | " <td>28.002763</td>\n", |
||
| 451 | " <td>28.660543</td>\n", |
||
| 452 | " <td>28.665092</td>\n", |
||
| 453 | " <td>29.839541</td>\n", |
||
| 454 | " </tr>\n", |
||
| 455 | " <tr>\n", |
||
| 456 | " <th>A0A075B6I4</th>\n", |
||
| 457 | " <td>24.783368</td>\n", |
||
| 458 | " <td>27.573331</td>\n", |
||
| 459 | " <td>25.619161</td>\n", |
||
| 460 | " <td>23.893562</td>\n", |
||
| 461 | " <td>18.440251</td>\n", |
||
| 462 | " <td>25.033513</td>\n", |
||
| 463 | " <td>19.384221</td>\n", |
||
| 464 | " <td>22.054705</td>\n", |
||
| 465 | " <td>27.642444</td>\n", |
||
| 466 | " <td>27.163654</td>\n", |
||
| 467 | " <td>...</td>\n", |
||
| 468 | " <td>27.365780</td>\n", |
||
| 469 | " <td>26.182814</td>\n", |
||
| 470 | " <td>27.649039</td>\n", |
||
| 471 | " <td>25.888229</td>\n", |
||
| 472 | " <td>26.724164</td>\n", |
||
| 473 | " <td>26.577443</td>\n", |
||
| 474 | " <td>27.996742</td>\n", |
||
| 475 | " <td>21.713502</td>\n", |
||
| 476 | " <td>19.659693</td>\n", |
||
| 477 | " <td>20.145198</td>\n", |
||
| 478 | " </tr>\n", |
||
| 479 | " <tr>\n", |
||
| 480 | " <th>...</th>\n", |
||
| 481 | " <td>...</td>\n", |
||
| 482 | " <td>...</td>\n", |
||
| 483 | " <td>...</td>\n", |
||
| 484 | " <td>...</td>\n", |
||
| 485 | " <td>...</td>\n", |
||
| 486 | " <td>...</td>\n", |
||
| 487 | " <td>...</td>\n", |
||
| 488 | " <td>...</td>\n", |
||
| 489 | " <td>...</td>\n", |
||
| 490 | " <td>...</td>\n", |
||
| 491 | " <td>...</td>\n", |
||
| 492 | " <td>...</td>\n", |
||
| 493 | " <td>...</td>\n", |
||
| 494 | " <td>...</td>\n", |
||
| 495 | " <td>...</td>\n", |
||
| 496 | " <td>...</td>\n", |
||
| 497 | " <td>...</td>\n", |
||
| 498 | " <td>...</td>\n", |
||
| 499 | " <td>...</td>\n", |
||
| 500 | " <td>...</td>\n", |
||
| 501 | " <td>...</td>\n", |
||
| 502 | " </tr>\n", |
||
| 503 | " <tr>\n", |
||
| 504 | " <th>V9GYE3</th>\n", |
||
| 505 | " <td>30.157740</td>\n", |
||
| 506 | " <td>29.011826</td>\n", |
||
| 507 | " <td>30.755732</td>\n", |
||
| 508 | " <td>31.037739</td>\n", |
||
| 509 | " <td>30.690791</td>\n", |
||
| 510 | " <td>29.544621</td>\n", |
||
| 511 | " <td>29.991859</td>\n", |
||
| 512 | " <td>29.005067</td>\n", |
||
| 513 | " <td>28.611893</td>\n", |
||
| 514 | " <td>29.039570</td>\n", |
||
| 515 | " <td>...</td>\n", |
||
| 516 | " <td>30.307260</td>\n", |
||
| 517 | " <td>30.378135</td>\n", |
||
| 518 | " <td>29.925498</td>\n", |
||
| 519 | " <td>30.471018</td>\n", |
||
| 520 | " <td>31.777999</td>\n", |
||
| 521 | " <td>31.486205</td>\n", |
||
| 522 | " <td>31.822441</td>\n", |
||
| 523 | " <td>31.144855</td>\n", |
||
| 524 | " <td>32.149526</td>\n", |
||
| 525 | " <td>28.001153</td>\n", |
||
| 526 | " </tr>\n", |
||
| 527 | " <tr>\n", |
||
| 528 | " <th>V9GYG9</th>\n", |
||
| 529 | " <td>30.157740</td>\n", |
||
| 530 | " <td>29.011826</td>\n", |
||
| 531 | " <td>30.755732</td>\n", |
||
| 532 | " <td>31.037739</td>\n", |
||
| 533 | " <td>30.690791</td>\n", |
||
| 534 | " <td>29.544621</td>\n", |
||
| 535 | " <td>29.991859</td>\n", |
||
| 536 | " <td>29.005067</td>\n", |
||
| 537 | " <td>28.611893</td>\n", |
||
| 538 | " <td>29.039570</td>\n", |
||
| 539 | " <td>...</td>\n", |
||
| 540 | " <td>30.307260</td>\n", |
||
| 541 | " <td>30.378135</td>\n", |
||
| 542 | " <td>29.925498</td>\n", |
||
| 543 | " <td>30.471018</td>\n", |
||
| 544 | " <td>31.777999</td>\n", |
||
| 545 | " <td>31.486205</td>\n", |
||
| 546 | " <td>31.822441</td>\n", |
||
| 547 | " <td>31.144855</td>\n", |
||
| 548 | " <td>32.149526</td>\n", |
||
| 549 | " <td>28.001153</td>\n", |
||
| 550 | " </tr>\n", |
||
| 551 | " <tr>\n", |
||
| 552 | " <th>X6R8F3</th>\n", |
||
| 553 | " <td>22.821315</td>\n", |
||
| 554 | " <td>20.147061</td>\n", |
||
| 555 | " <td>21.002496</td>\n", |
||
| 556 | " <td>19.830364</td>\n", |
||
| 557 | " <td>18.213300</td>\n", |
||
| 558 | " <td>22.831885</td>\n", |
||
| 559 | " <td>21.686202</td>\n", |
||
| 560 | " <td>23.468367</td>\n", |
||
| 561 | " <td>20.292526</td>\n", |
||
| 562 | " <td>24.971321</td>\n", |
||
| 563 | " <td>...</td>\n", |
||
| 564 | " <td>20.178151</td>\n", |
||
| 565 | " <td>21.893118</td>\n", |
||
| 566 | " <td>24.072429</td>\n", |
||
| 567 | " <td>18.115715</td>\n", |
||
| 568 | " <td>20.282632</td>\n", |
||
| 569 | " <td>21.229028</td>\n", |
||
| 570 | " <td>23.293898</td>\n", |
||
| 571 | " <td>20.400931</td>\n", |
||
| 572 | " <td>18.845678</td>\n", |
||
| 573 | " <td>26.863133</td>\n", |
||
| 574 | " </tr>\n", |
||
| 575 | " <tr>\n", |
||
| 576 | " <th>P80188</th>\n", |
||
| 577 | " <td>22.821315</td>\n", |
||
| 578 | " <td>20.147061</td>\n", |
||
| 579 | " <td>21.002496</td>\n", |
||
| 580 | " <td>19.830364</td>\n", |
||
| 581 | " <td>18.213300</td>\n", |
||
| 582 | " <td>22.831885</td>\n", |
||
| 583 | " <td>21.686202</td>\n", |
||
| 584 | " <td>23.468367</td>\n", |
||
| 585 | " <td>20.292526</td>\n", |
||
| 586 | " <td>24.971321</td>\n", |
||
| 587 | " <td>...</td>\n", |
||
| 588 | " <td>20.178151</td>\n", |
||
| 589 | " <td>21.893118</td>\n", |
||
| 590 | " <td>24.072429</td>\n", |
||
| 591 | " <td>18.115715</td>\n", |
||
| 592 | " <td>20.282632</td>\n", |
||
| 593 | " <td>21.229028</td>\n", |
||
| 594 | " <td>23.293898</td>\n", |
||
| 595 | " <td>20.400931</td>\n", |
||
| 596 | " <td>18.845678</td>\n", |
||
| 597 | " <td>26.863133</td>\n", |
||
| 598 | " </tr>\n", |
||
| 599 | " <tr>\n", |
||
| 600 | " <th>P80188-2</th>\n", |
||
| 601 | " <td>22.821315</td>\n", |
||
| 602 | " <td>20.147061</td>\n", |
||
| 603 | " <td>21.002496</td>\n", |
||
| 604 | " <td>19.830364</td>\n", |
||
| 605 | " <td>18.213300</td>\n", |
||
| 606 | " <td>22.831885</td>\n", |
||
| 607 | " <td>21.686202</td>\n", |
||
| 608 | " <td>23.468367</td>\n", |
||
| 609 | " <td>20.292526</td>\n", |
||
| 610 | " <td>24.971321</td>\n", |
||
| 611 | " <td>...</td>\n", |
||
| 612 | " <td>20.178151</td>\n", |
||
| 613 | " <td>21.893118</td>\n", |
||
| 614 | " <td>24.072429</td>\n", |
||
| 615 | " <td>18.115715</td>\n", |
||
| 616 | " <td>20.282632</td>\n", |
||
| 617 | " <td>21.229028</td>\n", |
||
| 618 | " <td>23.293898</td>\n", |
||
| 619 | " <td>20.400931</td>\n", |
||
| 620 | " <td>18.845678</td>\n", |
||
| 621 | " <td>26.863133</td>\n", |
||
| 622 | " </tr>\n", |
||
| 623 | " </tbody>\n", |
||
| 624 | "</table>\n", |
||
| 625 | "<p>1499 rows × 129 columns</p>\n", |
||
| 626 | "</div>" |
||
| 627 | ], |
||
| 628 | "text/plain": [ |
||
| 629 | " sample_1 sample_2 sample_3 sample_4 sample_5 sample_6 \\\n", |
||
| 630 | "Identifier \n", |
||
| 631 | "A0A024R6I7 37.995543 37.353091 37.527875 37.673128 37.983542 37.489959 \n", |
||
| 632 | "A0A0G2JRN3 37.995543 37.353091 37.527875 37.673128 37.983542 37.489959 \n", |
||
| 633 | "A0A075B6H9 27.176361 29.419228 27.174171 28.879702 27.262485 29.535232 \n", |
||
| 634 | "A0A075B6I0 28.294477 29.048510 28.953215 29.527460 28.605867 29.251895 \n", |
||
| 635 | "A0A075B6I4 24.783368 27.573331 25.619161 23.893562 18.440251 25.033513 \n", |
||
| 636 | "... ... ... ... ... ... ... \n", |
||
| 637 | "V9GYE3 30.157740 29.011826 30.755732 31.037739 30.690791 29.544621 \n", |
||
| 638 | "V9GYG9 30.157740 29.011826 30.755732 31.037739 30.690791 29.544621 \n", |
||
| 639 | "X6R8F3 22.821315 20.147061 21.002496 19.830364 18.213300 22.831885 \n", |
||
| 640 | "P80188 22.821315 20.147061 21.002496 19.830364 18.213300 22.831885 \n", |
||
| 641 | "P80188-2 22.821315 20.147061 21.002496 19.830364 18.213300 22.831885 \n", |
||
| 642 | "\n", |
||
| 643 | " sample_7 sample_8 sample_9 sample_10 ... sample_120 \\\n", |
||
| 644 | "Identifier ... \n", |
||
| 645 | "A0A024R6I7 37.615303 37.534702 37.525762 37.844902 ... 37.730180 \n", |
||
| 646 | "A0A0G2JRN3 37.615303 37.534702 37.525762 37.844902 ... 37.730180 \n", |
||
| 647 | "A0A075B6H9 27.657446 30.323779 28.194885 29.253091 ... 27.731627 \n", |
||
| 648 | "A0A075B6I0 26.943355 29.914134 28.947290 29.108465 ... 28.977874 \n", |
||
| 649 | "A0A075B6I4 19.384221 22.054705 27.642444 27.163654 ... 27.365780 \n", |
||
| 650 | "... ... ... ... ... ... ... \n", |
||
| 651 | "V9GYE3 29.991859 29.005067 28.611893 29.039570 ... 30.307260 \n", |
||
| 652 | "V9GYG9 29.991859 29.005067 28.611893 29.039570 ... 30.307260 \n", |
||
| 653 | "X6R8F3 21.686202 23.468367 20.292526 24.971321 ... 20.178151 \n", |
||
| 654 | "P80188 21.686202 23.468367 20.292526 24.971321 ... 20.178151 \n", |
||
| 655 | "P80188-2 21.686202 23.468367 20.292526 24.971321 ... 20.178151 \n", |
||
| 656 | "\n", |
||
| 657 | " sample_121 sample_122 sample_123 sample_124 sample_125 \\\n", |
||
| 658 | "Identifier \n", |
||
| 659 | "A0A024R6I7 38.082377 37.661959 37.195828 37.365447 37.564109 \n", |
||
| 660 | "A0A0G2JRN3 38.082377 37.661959 37.195828 37.365447 37.564109 \n", |
||
| 661 | "A0A075B6H9 27.621776 27.249976 27.403813 27.133006 27.793462 \n", |
||
| 662 | "A0A075B6I0 27.961132 29.085045 28.319069 29.418182 29.003245 \n", |
||
| 663 | "A0A075B6I4 26.182814 27.649039 25.888229 26.724164 26.577443 \n", |
||
| 664 | "... ... ... ... ... ... \n", |
||
| 665 | "V9GYE3 30.378135 29.925498 30.471018 31.777999 31.486205 \n", |
||
| 666 | "V9GYG9 30.378135 29.925498 30.471018 31.777999 31.486205 \n", |
||
| 667 | "X6R8F3 21.893118 24.072429 18.115715 20.282632 21.229028 \n", |
||
| 668 | "P80188 21.893118 24.072429 18.115715 20.282632 21.229028 \n", |
||
| 669 | "P80188-2 21.893118 24.072429 18.115715 20.282632 21.229028 \n", |
||
| 670 | "\n", |
||
| 671 | " sample_126 sample_127 sample_128 sample_129 \n", |
||
| 672 | "Identifier \n", |
||
| 673 | "A0A024R6I7 37.683884 37.282698 37.655909 37.754401 \n", |
||
| 674 | "A0A0G2JRN3 37.683884 37.282698 37.655909 37.754401 \n", |
||
| 675 | "A0A075B6H9 26.876193 27.715091 26.965212 28.376997 \n", |
||
| 676 | "A0A075B6I0 28.002763 28.660543 28.665092 29.839541 \n", |
||
| 677 | "A0A075B6I4 27.996742 21.713502 19.659693 20.145198 \n", |
||
| 678 | "... ... ... ... ... \n", |
||
| 679 | "V9GYE3 31.822441 31.144855 32.149526 28.001153 \n", |
||
| 680 | "V9GYG9 31.822441 31.144855 32.149526 28.001153 \n", |
||
| 681 | "X6R8F3 23.293898 20.400931 18.845678 26.863133 \n", |
||
| 682 | "P80188 23.293898 20.400931 18.845678 26.863133 \n", |
||
| 683 | "P80188-2 23.293898 20.400931 18.845678 26.863133 \n", |
||
| 684 | "\n", |
||
| 685 | "[1499 rows x 129 columns]" |
||
| 686 | ] |
||
| 687 | }, |
||
| 688 | "execution_count": 14, |
||
| 689 | "metadata": {}, |
||
| 690 | "output_type": "execute_result" |
||
| 691 | } |
||
| 692 | ], |
||
| 693 | "source": [ |
||
| 694 | "protein_data.data_df" |
||
| 695 | ] |
||
| 696 | }, |
||
| 697 | { |
||
| 698 | "cell_type": "code", |
||
| 699 | "execution_count": 15, |
||
| 700 | "metadata": {}, |
||
| 701 | "outputs": [ |
||
| 702 | { |
||
| 703 | "data": { |
||
| 704 | "text/html": [ |
||
| 705 | "<div>\n", |
||
| 706 | "<style scoped>\n", |
||
| 707 | " .dataframe tbody tr th:only-of-type {\n", |
||
| 708 | " vertical-align: middle;\n", |
||
| 709 | " }\n", |
||
| 710 | "\n", |
||
| 711 | " .dataframe tbody tr th {\n", |
||
| 712 | " vertical-align: top;\n", |
||
| 713 | " }\n", |
||
| 714 | "\n", |
||
| 715 | " .dataframe thead th {\n", |
||
| 716 | " text-align: right;\n", |
||
| 717 | " }\n", |
||
| 718 | "</style>\n", |
||
| 719 | "<table border=\"1\" class=\"dataframe\">\n", |
||
| 720 | " <thead>\n", |
||
| 721 | " <tr style=\"text-align: right;\">\n", |
||
| 722 | " <th></th>\n", |
||
| 723 | " <th>group</th>\n", |
||
| 724 | " </tr>\n", |
||
| 725 | " <tr>\n", |
||
| 726 | " <th>sample</th>\n", |
||
| 727 | " <th></th>\n", |
||
| 728 | " </tr>\n", |
||
| 729 | " </thead>\n", |
||
| 730 | " <tbody>\n", |
||
| 731 | " <tr>\n", |
||
| 732 | " <th>sample_1</th>\n", |
||
| 733 | " <td>covid</td>\n", |
||
| 734 | " </tr>\n", |
||
| 735 | " <tr>\n", |
||
| 736 | " <th>sample_2</th>\n", |
||
| 737 | " <td>covid</td>\n", |
||
| 738 | " </tr>\n", |
||
| 739 | " <tr>\n", |
||
| 740 | " <th>sample_3</th>\n", |
||
| 741 | " <td>covid</td>\n", |
||
| 742 | " </tr>\n", |
||
| 743 | " <tr>\n", |
||
| 744 | " <th>sample_4</th>\n", |
||
| 745 | " <td>covid</td>\n", |
||
| 746 | " </tr>\n", |
||
| 747 | " <tr>\n", |
||
| 748 | " <th>sample_5</th>\n", |
||
| 749 | " <td>covid</td>\n", |
||
| 750 | " </tr>\n", |
||
| 751 | " <tr>\n", |
||
| 752 | " <th>...</th>\n", |
||
| 753 | " <td>...</td>\n", |
||
| 754 | " </tr>\n", |
||
| 755 | " <tr>\n", |
||
| 756 | " <th>sample_125</th>\n", |
||
| 757 | " <td>non_covid</td>\n", |
||
| 758 | " </tr>\n", |
||
| 759 | " <tr>\n", |
||
| 760 | " <th>sample_126</th>\n", |
||
| 761 | " <td>non_covid</td>\n", |
||
| 762 | " </tr>\n", |
||
| 763 | " <tr>\n", |
||
| 764 | " <th>sample_127</th>\n", |
||
| 765 | " <td>non_covid</td>\n", |
||
| 766 | " </tr>\n", |
||
| 767 | " <tr>\n", |
||
| 768 | " <th>sample_128</th>\n", |
||
| 769 | " <td>non_covid</td>\n", |
||
| 770 | " </tr>\n", |
||
| 771 | " <tr>\n", |
||
| 772 | " <th>sample_129</th>\n", |
||
| 773 | " <td>non_covid</td>\n", |
||
| 774 | " </tr>\n", |
||
| 775 | " </tbody>\n", |
||
| 776 | "</table>\n", |
||
| 777 | "<p>129 rows × 1 columns</p>\n", |
||
| 778 | "</div>" |
||
| 779 | ], |
||
| 780 | "text/plain": [ |
||
| 781 | " group\n", |
||
| 782 | "sample \n", |
||
| 783 | "sample_1 covid\n", |
||
| 784 | "sample_2 covid\n", |
||
| 785 | "sample_3 covid\n", |
||
| 786 | "sample_4 covid\n", |
||
| 787 | "sample_5 covid\n", |
||
| 788 | "... ...\n", |
||
| 789 | "sample_125 non_covid\n", |
||
| 790 | "sample_126 non_covid\n", |
||
| 791 | "sample_127 non_covid\n", |
||
| 792 | "sample_128 non_covid\n", |
||
| 793 | "sample_129 non_covid\n", |
||
| 794 | "\n", |
||
| 795 | "[129 rows x 1 columns]" |
||
| 796 | ] |
||
| 797 | }, |
||
| 798 | "execution_count": 15, |
||
| 799 | "metadata": {}, |
||
| 800 | "output_type": "execute_result" |
||
| 801 | } |
||
| 802 | ], |
||
| 803 | "source": [ |
||
| 804 | "protein_data.design_df" |
||
| 805 | ] |
||
| 806 | }, |
||
| 807 | { |
||
| 808 | "cell_type": "markdown", |
||
| 809 | "metadata": {}, |
||
| 810 | "source": [ |
||
| 811 | "### Create a multi-omics data container objects" |
||
| 812 | ] |
||
| 813 | }, |
||
| 814 | { |
||
| 815 | "cell_type": "code", |
||
| 816 | "execution_count": 16, |
||
| 817 | "metadata": {}, |
||
| 818 | "outputs": [], |
||
| 819 | "source": [ |
||
| 820 | "publication = 'Overmyer, Katherine A., et al. \"Large-scale multi-omic analysis of COVID-19 severity.\" Cell systems 12.1 (2021): 23-40.'\n", |
||
| 821 | "url = 'https://www.sciencedirect.com/science/article/pii/S2405471220303719'" |
||
| 822 | ] |
||
| 823 | }, |
||
| 824 | { |
||
| 825 | "cell_type": "code", |
||
| 826 | "execution_count": 17, |
||
| 827 | "metadata": {}, |
||
| 828 | "outputs": [ |
||
| 829 | { |
||
| 830 | "data": { |
||
| 831 | "text/plain": [ |
||
| 832 | "Multi-omics data container\n", |
||
| 833 | "- publication: Overmyer, Katherine A., et al. \"Large-scale multi-omic analysis of COVID-19 severity.\" Cell systems 12.1 (2021): 23-40.\n", |
||
| 834 | "- URL: https://www.sciencedirect.com/science/article/pii/S2405471220303719\n", |
||
| 835 | "- Views: 3 modalities\n", |
||
| 836 | "\t - genes data with (13028, 125) measurements\n", |
||
| 837 | "\t - proteins data with (1499, 129) measurements\n", |
||
| 838 | "\t - compounds data with (46, 129) measurements" |
||
| 839 | ] |
||
| 840 | }, |
||
| 841 | "execution_count": 17, |
||
| 842 | "metadata": {}, |
||
| 843 | "output_type": "execute_result" |
||
| 844 | } |
||
| 845 | ], |
||
| 846 | "source": [ |
||
| 847 | "mo = MultiOmicsData(publication=publication, url=url)\n", |
||
| 848 | "mo.add_data([transcript_data, protein_data, compound_data])\n", |
||
| 849 | "mo" |
||
| 850 | ] |
||
| 851 | } |
||
| 852 | ], |
||
| 853 | "metadata": { |
||
| 854 | "kernelspec": { |
||
| 855 | "display_name": "Python 3 (ipykernel)", |
||
| 856 | "language": "python", |
||
| 857 | "name": "python3" |
||
| 858 | }, |
||
| 859 | "language_info": { |
||
| 860 | "codemirror_mode": { |
||
| 861 | "name": "ipython", |
||
| 862 | "version": 3 |
||
| 863 | }, |
||
| 864 | "file_extension": ".py", |
||
| 865 | "mimetype": "text/x-python", |
||
| 866 | "name": "python", |
||
| 867 | "nbconvert_exporter": "python", |
||
| 868 | "pygments_lexer": "ipython3", |
||
| 869 | "version": "3.10.1" |
||
| 870 | } |
||
| 871 | }, |
||
| 872 | "nbformat": 4, |
||
| 873 | "nbformat_minor": 4 |
||
| 874 | } |