├── genome.png
├── nosce.png
├── seriously.png
├── DNA_articles.png
├── output_34_0.png
├── result.csv
├── README.md
└── DNA.ipynb


/genome.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/lorarjohns/DNA_pandas_selenium/HEAD/genome.png


--------------------------------------------------------------------------------
/nosce.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/lorarjohns/DNA_pandas_selenium/HEAD/nosce.png


--------------------------------------------------------------------------------
/seriously.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/lorarjohns/DNA_pandas_selenium/HEAD/seriously.png


--------------------------------------------------------------------------------
/DNA_articles.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/lorarjohns/DNA_pandas_selenium/HEAD/DNA_articles.png


--------------------------------------------------------------------------------
/output_34_0.png:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/lorarjohns/DNA_pandas_selenium/HEAD/output_34_0.png


--------------------------------------------------------------------------------
/result.csv:
--------------------------------------------------------------------------------
  1 | ,Magnitude,Repute,Summary
  2 | Rs661(A;A),9,Bad,"early onset Alzheimer's disease"
  3 | Rs6647(T;T),0,Good,"Normal; two copies of Pi-M1V allele"
  4 | Rs6647(C;C),0,Good,"Normal; two copies of Pi-M1A allele"
  5 | Rs1303(T;T),0,Good,"common in clinvar"
  6 | Rs28929471(G;G),0,Good,"common in complete genomics"
  7 | Rs28929474(G;G),0,Good,"common in complete genomics"
  8 | Rs28929474(A;A),5.5,Bad,"Alpha-1 Antitrypsin Deficiency"
  9 | Rs17580(A;A),0,Good,"common in complete genomics"
 10 | Rs17580(T;T),2.5,Bad,"a slightly reduced functionality form of Alpha-1 Antitrypsin Deficiency"
 11 | Rs28931568(G;G),0,Good,"common in complete genomics"
 12 | Rs28931568(A;A),4,Bad,"high risk of emphysema due to Alpha 1-Antitrypsin Deficiency"
 13 | Rs28931569(T;T),0,Good,"common in complete genomics"
 14 | Rs28931569(C;C),4,,"high risk of emphysema"
 15 | Rs28931570(C;C),0,Good,"common in complete genomics"
 16 | Rs28929473(A;A),0,Good,"common in complete genomics"
 17 | Rs28929473(T;T),0,,
 18 | Rs28931572(T;T),0,Good,"common in complete genomics"
 19 | Rs28931572(A;A),0,,
 20 | Rs769455(C;C),0,Good,"common in clinvar"
 21 | Rs769452(T;T),0,Good,"common in clinvar"
 22 | Rs28931576(A;A),0,Good,"common in clinvar"
 23 | Rs28931578(G;G),0,Good,"common in clinvar"
 24 | Rs28931579(A;A),0,Good,"common in clinvar"
 25 | Rs28931580(A;A),0,Good,"common in clinvar"
 26 | Rs4987076(G;G),0,Good,"common in clinvar"
 27 | Rs28929478(G;G),0,Good,"common in clinvar"
 28 | Rs28929478(A;A),0,Good,"common on affy axiom data"
 29 | Rs28931581(C;C),0,Good,"common in clinvar"
 30 | Rs28931582(T;T),0,Good,"common in clinvar"
 31 | Rs28929479(T;T),0,Good,"common in clinvar"
 32 | Rs28931586(T;T),0,Good,"common in clinvar"
 33 | Rs1801252(A;A),0,Good,None
 34 | Rs1801252(G;G),3,,
 35 | Rs1042714(C;C),0,Good,normal
 36 | Rs1800888(C;C),0,Good,normal
 37 | Rs1800888(T;T),2.5,Bad,"increased risk of coronary artery disease"
 38 | Rs4994(T;T),0,Good,normal
 39 | Rs4994(C;C),2,Bad,"2x higher risk in certain women for cardiac events; associated with elite endurance performance in men"
 40 | Rs11276(G;G),0,Good,"common in clinvar"
 41 | Rs28362459(T;T),0,Good,"common in clinvar"
 42 | Rs8192466(C;C),0,Good,common
 43 | Rs8192466(T;T),4,,uncertain
 44 | Rs28897672(T;T),0,Good,normal
 45 | Rs4986852(G;G),0,Good,normal
 46 | Rs4986852(A;A),2,,"predisposition to breast cancer?"
 47 | Rs1800709(C;C),0,Good,normal
 48 | Rs1800709(T;T),2,,"predisposition to breast cancer?"
 49 | Rs28931588(G;G),0,Good,"common in complete genomics"
 50 | Rs28931589(G;G),0,Good,"common in complete genomics"
 51 | Rs28931590(A;A),0,Good,"common in complete genomics"
 52 | Rs28931590(T;T),2.5,Bad,"ACUTE MYELOID LEUKEMIA"
 53 | Rs2303790(A;A),0,Good,"common in clinvar"
 54 | Rs5882(G;G),2.1,Good,"Longer lifespan, 0.28x lower risk of dementia, 0.31x lower risk of Alzheimer's."
 55 | Rs5882(A;A),2,Bad,"Faster aging. Increased risk for Dementia. Less good cholesterol."
 56 | Rs28931591(C;C),0,Good,"common in clinvar"
 57 | Rs2230199(C;C),0,Good,common
 58 | Rs2230199(G;G),2,Bad,"2.5x+ risk of ARMD"
 59 | Rs1047286(C;C),0,Good,"common in clinvar"
 60 | Rs1047286(T;T),1.7,Bad,"1.7x increased risk for age-related macular degeneration"
 61 | Rs28929485(C;C),0,Good,"common in clinvar"
 62 | Rs28929485(T;T),6,Bad,"Deafness and keratitis; possible dominant or recessive"
 63 | Rs28931592(A;A),0,Good,"common in clinvar"
 64 | Rs28931592(T;T),0,,
 65 | Rs28931593(G;G),0,Good,"common in clinvar"
 66 | Rs28931594(G;G),0,Good,"common in clinvar"
 67 | Rs28931595(G;G),0,Good,"common in clinvar"
 68 | Rs28931600(G;G),0,Good,"common in clinvar"
 69 | Rs28931601(G;G),0,Good,"common in clinvar"
 70 | Rs11547328(C;C),0,Good,"common in complete genomics"
 71 | Rs231775(A;A),1,Good,"no increased risk of autoimmune thyroid disease"
 72 | Rs28931606(T;T),0,Good,"common in clinvar"
 73 | Rs28931607(G;G),0,Good,"common in clinvar"
 74 | Rs28931608(G;G),0,Good,"common in clinvar"
 75 | Rs4986893(G;G),0,Good,normal
 76 | Rs4986893(A;A),2.1,,"poor metabolizer of several commonly prescribed drugs"
 77 | Rs28399504(A;A),0,Good,normal
 78 | Rs28399504(G;G),2.5,Bad,"poor metabolizer"
 79 | Rs28931609(C;C),0,Good,"common in clinvar"
 80 | Rs28931610(C;C),0,Good,"common in clinvar"
 81 | Rs28931610(T;T),6,Bad,"carrier of a skin fragility/woolly hair syndrome allele"
 82 | Rs28931611(T;T),0,Good,"common in clinvar"
 83 | Rs28931612(G;G),0,Good,"common in complete genomics"
 84 | Rs11570255(G;G),0,Good,"common in complete genomics"
 85 | Rs11570351(G;G),0,Good,"common on affy axiom data"
 86 | Rs5352(G;G),0,Good,common
 87 | Rs5352(A;A),3.5,Bad,"Hirschsprung disease?"
 88 | Rs2234922(A;A),0,Good,"common in clinvar"
 89 | Rs460897(G;G),0,Good,"common in complete genomics"
 90 | Rs28929498(A;A),0,Good,"common in clinvar"
 91 | Rs28931614(G;G),0,Good,"common in clinvar"
 92 | Rs28933068(C;C),0,Good,"common in clinvar"
 93 | Rs28931615(C;C),0,Good,"common in clinvar"
 94 | Rs4647924(C;C),0,Good,"common in clinvar"
 95 | Rs28928868(G;G),0,Good,"common in clinvar"
 96 | Rs6165(G;G),0,Good,"common in clinvar"
 97 | Rs6166(G;G),1,Bad,"Females slightly more likely to be sterile"
 98 | Rs6166(A;A),0,Good,common/normal
 99 | Rs28928870(C;C),0,Good,"common in clinvar"
100 | Rs28928871(G;G),0,Good,"common in clinvar"
101 | Rs17855739(G;G),0,Good,"common in clinvar"
102 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
   1 | # Know Thyself: Using Data Science to Explore Your Own Genome
   2 | ## DNA analysis with pandas and Selenium
   3 | 
   4 | <figure style="width: 900px">
   5 |   <img src="./nosce.png" alt="Geminus’s flaps,  https://exhibitions.lib.cam.ac.uk/vesalius/artifacts/geminuss-flaps1/
   6 | ">
   7 |   <figcaption>"Nosce te ipsum" ("know thyself"), an ancient maxim frequently associated with gory anatomical pop-up books of yore.</figcaption>
   8 | </figure>
   9 | 
  10 | [Image from the University of Cambridge](https://exhibitions.lib.cam.ac.uk/vesalius/artifacts/geminuss-flaps1/)
  11 | 
  12 | [23andme](https://www.23andme.com/) once offered me a free DNA and ancestry test kit if I participated in one of their clinical studies. In exchange for a cheek swab and baring my guts and soul in a score of questionnaires, I got my genome sequenced and gained access to myriad reports on where my ancestors were likely from, whom else on the site I might be related to, and what health conditions and traits I probably have inherited.
  13 | 
  14 | <figure style="width: 900px">
  15 |   <img src="./seriously.png" alt="Bunion and Flat Feet Report, 23andme">
  16 |   <figcaption>Seriously?</figcaption>
  17 | </figure>
  18 | 
  19 | 23andme already provides an overwhelming amount of consumer-ready infographics and tools, but I knew I could do more with the data. The intrepid may download their raw genetic data if they dare, so of course I poured it into pandas to [see what I could make of it](https://github.com/lorarjohns/DNA_pandas_selenium). 
  20 | 
  21 | 
  22 | ```python
  23 | %matplotlib inline
  24 | import seaborn as sns
  25 | sns.set_style('darkgrid')
  26 | sns.color_palette('Spectral')
  27 | import matplotlib.pyplot as plt
  28 | ```
  29 | 
  30 | 
  31 | ```python
  32 | import numpy as np
  33 | import requests
  34 | import pandas as pd
  35 | 
  36 | import re
  37 | ```
  38 | 
  39 | 
  40 | ```python
  41 | from selenium import webdriver
  42 | from selenium.webdriver.support.ui import WebDriverWait
  43 | ```
  44 | 
  45 | ## Importing my DNA into pandas and exploring the genome
  46 | 
  47 | Looking at the .txt file, I could see that I was missing some genotype values, denoted with '--'. 
  48 | 
  49 | Most of the chromosomes are ints, but three are X, Y, and MT (for 'mitochondrial'). I needed to specify the data type properly so that pandas wouldn't throw an error when it found mixed data in the input. 
  50 | 
  51 | The other columns were fairly straightforward. I also wanted pandas to ignore the prefatory comments at the beginning of the file that consisted of lines beginning with an octothorpe.
  52 | 
  53 | The arguments I needed to pass, therefore, were:
  54 | * separator (tab-delimited)
  55 | * dtype (as a dict)
  56 | * na_values ('--') *(n.b.: I decided against this in the end to avoid dealing with more NaNs)*
  57 | * comment ('#')
  58 | 
  59 | ![img](/genome.png)
  60 | 
  61 | 
  62 | ```python
  63 | data = pd.read_csv('genome.txt', sep='\t', dtype={'rsid':'str', 'chromosome':'object', 'position':'int', 'genotype':'str'}, comment='#')
  64 | 
  65 | 
  66 | ```
  67 | 
  68 | 
  69 | ```python
  70 | print(data)
  71 | ```
  72 | 
  73 |                    rsid chromosome  position genotype
  74 |     0       rs548049170          1     69869       TT
  75 |     1        rs13328684          1     74792       --
  76 |     2         rs9283150          1    565508       AA
  77 |     3           i713426          1    726912       --
  78 |     4       rs116587930          1    727841       GG
  79 |     5         rs3131972          1    752721       AG
  80 |     6        rs12184325          1    754105       CC
  81 | 
  82 |     ...             ...        ...       ...      ...
  83 | 
  84 |     [638531 rows x 4 columns]
  85 | 
  86 | 
  87 | A quick note on the column names:
  88 | 
  89 | * rsid stands for Reference SNP cluster ID. It identifies unique SNPs.
  90 | 
  91 | * SNPs are Single Nucleotide Polymorphisms ('snips'), locations in the genome that vary between individuals. They can influence disease risk and drug effects, tell you about your ancestry, and predict aspects of how you look and act.
  92 | 
  93 | * All humans have almost the same sequence of 3 billion DNA bases (A,C,G, or T) distributed between their 23 pairs of chromosomes. But at certain locations, some differences exist that researchers have declared meaningful, for medical or other reasons (like genealogy). 
  94 | 
  95 | I started to navigate my new DataFrame with basic exploratory data analysis and data cleaning.
  96 | 
  97 | 
  98 | ```python
  99 | # Read the data into a pandas DataFrame and do some EDA
 100 | df = pd.DataFrame(data)
 101 | ```
 102 | 
 103 | 
 104 | ```python
 105 | df.head(25)
 106 | ```
 107 | 
 108 | <div>
 109 | <style scoped>
 110 |     .dataframe tbody tr th:only-of-type {
 111 |         vertical-align: middle;
 112 |     }
 113 | 
 114 |     .dataframe tbody tr th {
 115 |         vertical-align: top;
 116 |     }
 117 | 
 118 |     .dataframe thead th {
 119 |         text-align: right;
 120 |     }
 121 | </style>
 122 | <table border="1" class="dataframe">
 123 |   <thead>
 124 |     <tr style="text-align: right;">
 125 |       <th></th>
 126 |       <th>rsid</th>
 127 |       <th>chromosome</th>
 128 |       <th>position</th>
 129 |       <th>genotype</th>
 130 |     </tr>
 131 |   </thead>
 132 |   <tbody>
 133 |     <tr>
 134 |       <th>0</th>
 135 |       <td>rs548049170</td>
 136 |       <td>1</td>
 137 |       <td>69869</td>
 138 |       <td>TT</td>
 139 |     </tr>
 140 |     <tr>
 141 |       <th>1</th>
 142 |       <td>rs13328684</td>
 143 |       <td>1</td>
 144 |       <td>74792</td>
 145 |       <td>--</td>
 146 |     </tr>
 147 |     <tr>
 148 |       <th>2</th>
 149 |       <td>rs9283150</td>
 150 |       <td>1</td>
 151 |       <td>565508</td>
 152 |       <td>AA</td>
 153 |     </tr>
 154 |     <tr>
 155 |       <th>3</th>
 156 |       <td>i713426</td>
 157 |       <td>1</td>
 158 |       <td>726912</td>
 159 |       <td>--</td>
 160 |     </tr>
 161 |     <tr>
 162 |       <th>4</th>
 163 |       <td>rs116587930</td>
 164 |       <td>1</td>
 165 |       <td>727841</td>
 166 |       <td>GG</td>
 167 |     </tr>
 168 |     <tr>
 169 |       <th>5</th>
 170 |       <td>rs3131972</td>
 171 |       <td>1</td>
 172 |       <td>752721</td>
 173 |       <td>AG</td>
 174 |     </tr>
 175 |     <tr>
 176 |       <th>6</th>
 177 |       <td>rs12184325</td>
 178 |       <td>1</td>
 179 |       <td>754105</td>
 180 |       <td>CC</td>
 181 |     </tr>
 182 |     <tr>
 183 |       <th>7</th>
 184 |       <td>rs12567639</td>
 185 |       <td>1</td>
 186 |       <td>756268</td>
 187 |       <td>AA</td>
 188 |     </tr>
 189 |     <tr>
 190 |       <th>8</th>
 191 |       <td>rs114525117</td>
 192 |       <td>1</td>
 193 |       <td>759036</td>
 194 |       <td>GG</td>
 195 |     </tr>
 196 |     <tr>
 197 |       <th>9</th>
 198 |       <td>rs12124819</td>
 199 |       <td>1</td>
 200 |       <td>776546</td>
 201 |       <td>AA</td>
 202 |     </tr>
 203 |     <tr>
 204 |       <th>10</th>
 205 |       <td>rs12127425</td>
 206 |       <td>1</td>
 207 |       <td>794332</td>
 208 |       <td>GG</td>
 209 |     </tr>
 210 |     <tr>
 211 |       <th>11</th>
 212 |       <td>rs79373928</td>
 213 |       <td>1</td>
 214 |       <td>801536</td>
 215 |       <td>TT</td>
 216 |     </tr>
 217 |     <tr>
 218 |       <th>12</th>
 219 |       <td>rs72888853</td>
 220 |       <td>1</td>
 221 |       <td>815421</td>
 222 |       <td>--</td>
 223 |     </tr>
 224 |     <tr>
 225 |       <th>13</th>
 226 |       <td>rs7538305</td>
 227 |       <td>1</td>
 228 |       <td>824398</td>
 229 |       <td>AA</td>
 230 |     </tr>
 231 |     <tr>
 232 |       <th>14</th>
 233 |       <td>rs28444699</td>
 234 |       <td>1</td>
 235 |       <td>830181</td>
 236 |       <td>AA</td>
 237 |     </tr>
 238 |     <tr>
 239 |       <th>15</th>
 240 |       <td>i713449</td>
 241 |       <td>1</td>
 242 |       <td>830731</td>
 243 |       <td>--</td>
 244 |     </tr>
 245 |     <tr>
 246 |       <th>16</th>
 247 |       <td>rs116452738</td>
 248 |       <td>1</td>
 249 |       <td>834830</td>
 250 |       <td>GG</td>
 251 |     </tr>
 252 |     <tr>
 253 |       <th>17</th>
 254 |       <td>rs72631887</td>
 255 |       <td>1</td>
 256 |       <td>835092</td>
 257 |       <td>TT</td>
 258 |     </tr>
 259 |     <tr>
 260 |       <th>18</th>
 261 |       <td>rs28678693</td>
 262 |       <td>1</td>
 263 |       <td>838665</td>
 264 |       <td>TT</td>
 265 |     </tr>
 266 |     <tr>
 267 |       <th>19</th>
 268 |       <td>rs4970382</td>
 269 |       <td>1</td>
 270 |       <td>840753</td>
 271 |       <td>CT</td>
 272 |     </tr>
 273 |     <tr>
 274 |       <th>20</th>
 275 |       <td>rs4475691</td>
 276 |       <td>1</td>
 277 |       <td>846808</td>
 278 |       <td>CC</td>
 279 |     </tr>
 280 |     <tr>
 281 |       <th>21</th>
 282 |       <td>rs72631889</td>
 283 |       <td>1</td>
 284 |       <td>851390</td>
 285 |       <td>GG</td>
 286 |     </tr>
 287 |     <tr>
 288 |       <th>22</th>
 289 |       <td>rs7537756</td>
 290 |       <td>1</td>
 291 |       <td>854250</td>
 292 |       <td>AA</td>
 293 |     </tr>
 294 |     <tr>
 295 |       <th>23</th>
 296 |       <td>rs13302982</td>
 297 |       <td>1</td>
 298 |       <td>861808</td>
 299 |       <td>GG</td>
 300 |     </tr>
 301 |     <tr>
 302 |       <th>24</th>
 303 |       <td>rs376747791</td>
 304 |       <td>1</td>
 305 |       <td>863130</td>
 306 |       <td>AA</td>
 307 |     </tr>
 308 |   </tbody>
 309 | </table>
 310 | </div>
 311 | 
 312 | 
 313 | 
 314 | 
 315 | ```python
 316 | df.isna().any()
 317 | ```
 318 | 
 319 | 
 320 | 
 321 | 
 322 |      rsid         False
 323 |     chromosome    False
 324 |     position      False
 325 |     genotype      False
 326 |     dtype: bool
 327 | 
 328 | 
 329 | 
 330 | 
 331 | ```python
 332 | df.nunique()
 333 | ```
 334 | 
 335 | 
 336 | 
 337 | 
 338 |      rsid         638531
 339 |     chromosome        25
 340 |     position      634934
 341 |     genotype          20
 342 |     dtype: int64
 343 | 
 344 | 
 345 | 
 346 | ```python
 347 | # How many chromosomes am I missing by not 
 348 | # having a Y chromosome?
 349 | Y_chromosome = df[df.chromosome == 'Y']
 350 | ```
 351 | 
 352 | 
 353 | ```python
 354 | len(Y_chromosome)
 355 | ```
 356 | 
 357 | 
 358 | 
 359 | 
 360 |     3733
 361 | 
 362 | 
 363 | I converted the letter chromosomes to numbers, cast them to ints, and created a dictionary to translate them back later so that I could better manipulate the data.
 364 | 
 365 | 
 366 | ```python
 367 | df['chromosome'].unique()
 368 | ```
 369 | 
 370 | 
 371 | 
 372 | 
 373 |     array(['1', '2', '3', '4', '5', '6', '7', '8', 
 374 |           '9', '10', '11', '12','13', '14', '15', 
 375 |           '16', '17', '18', '19', '20', '21', '22',
 376 |           'X','MT'], dtype=object)
 377 | 
 378 | 
 379 | 
 380 | 
 381 | ```python
 382 | df['chromosome'] = df['chromosome'].apply(lambda x: 
 383 |   re.sub(r'X', r'23', x))
 384 | df['chromosome'] = df['chromosome'].apply(lambda x: 
 385 |   re.sub(r'MT', r'24', x))
 386 | ```
 387 | 
 388 | 
 389 | ```python
 390 | df['chromosome'] = df['chromosome'].apply(lambda x: 
 391 |   int(x))
 392 | ```
 393 | 
 394 | 
 395 | ```python
 396 | chromosome_dict = {1:'1', 2:'2', 3:'3', 4:'4', 5:'5', 
 397 |            6:'6', 7:'7', 8:'8', 9:'9', 10:'10', 
 398 |            11:'11', 12:'12', 13:'13', 14:'14', 
 399 |            15:'15', 16:'16', 17:'17', 18:'18', 
 400 |            19:'19', 20:'20', 21:'21', 22:'22', 
 401 |            23:'X', 24:'MT'}
 402 | ```
 403 | 
 404 | 
 405 | ```python
 406 | print(chromosome_dict)
 407 | display(df.info())
 408 | ```
 409 | 
 410 |     {1: '1', 2: '2', 3: '3', 4: '4', 5: '5', 6: '6', 7: '7', 
 411 |      8: '8', 9: '9', 10: '10', 11: '11', 12: '12', 13: '13', 
 412 |      14: '14', 15: '15', 16: '16', 17: '17', 18: '18', 
 413 |      19: '19', 20: '20', 21: '21', 22: '22', 23: 'X', 
 414 |      24: 'MT'}
 415 | 
 416 |     <class 'pandas.core.frame.DataFrame'>
 417 |     Int64Index: 634798 entries, 0 to 638530
 418 | 
 419 |     Data columns (total 4 columns):
 420 | 
 421 |      rsid         634798 non-null object
 422 |     chromosome    634798 non-null int64
 423 |     position      634798 non-null int64
 424 |     genotype      634798 non-null object
 425 | 
 426 |     dtypes: int64(2), object(2)
 427 |     memory usage: 24.2+ MB
 428 | 
 429 |     None
 430 | 
 431 | 
 432 | There were 16,005 genotypes that I simply lacked:
 433 | 
 434 | 
 435 | ```python
 436 | genotype_na = df[df.genotype == '--']
 437 | len(genotype_na)
 438 | ```
 439 |     16005
 440 | 
 441 | 
 442 | ### Some visualizations
 443 | 
 444 | 
 445 | ```python
 446 | df[df.chromosome == 1].info()
 447 | ```
 448 | 
 449 |     <class 'pandas.core.frame.DataFrame'>
 450 |     Int64Index: 49514 entries, 0 to 49513
 451 |     Data columns (total 4 columns):
 452 |      rsid         49514 non-null object
 453 |     chromosome    49514 non-null int64
 454 |     position      49514 non-null int64
 455 |     genotype      49514 non-null object
 456 |     dtypes: int64(2), object(2)
 457 |     memory usage: 1.9+ MB
 458 | 
 459 | 
 460 | ```python
 461 | # Remove that pesky whitespace from the column name
 462 | df.rename({' rsid': 'rsid'}, axis='columns', inplace=True)
 463 | ```
 464 | 
 465 | How many SNPs are there per chromosome?
 466 | 
 467 | 
 468 | ```python
 469 | # We can do this manually with a for loop . . .
 470 | x = []
 471 | y = []
 472 | for k in chromosome_dict:
 473 |     x.append(k)
 474 |     y.append(len(df[df.chromosome == k]))
 475 | rsid_per_chromosome = dict(zip(x,y)) 
 476 | ```
 477 | 
 478 | ```python
 479 | rsid_per_chromosome
 480 | ```
 481 | 
 482 |     {1: 49514,
 483 |      2: 51775,
 484 |      3: 43024,
 485 |      4: 39474,
 486 |      5: 37032,
 487 |      6: 44023,
 488 |      7: 34357,
 489 |      8: 31683,
 490 |      9: 26446,
 491 |      10: 30525,
 492 |      11: 30942,
 493 |      12: 29432,
 494 |      13: 22080,
 495 |      14: 19961,
 496 |      15: 19006,
 497 |      16: 20397,
 498 |      17: 19401,
 499 |      18: 17675,
 500 |      19: 14917,
 501 |      20: 14781,
 502 |      21: 8607,
 503 |      22: 8915,
 504 |      23: 16530,
 505 |      24: 4301}
 506 | 
 507 | 
 508 | ```python
 509 | # . . . but pandas makes it a lot easier!
 510 | rsid_per_chromosome_series = df.groupby('chromosome')['rsid'].count()
 511 | rsid_per_chromosome_series.columns = ['chromosome', 'count']
 512 | ```
 513 | 
 514 | ```python
 515 | rsid_per_chromosome_series.plot.barh(figsize=(16,9), fontsize=15)
 516 | plt.show()
 517 | ```
 518 | 
 519 | <figure style="width: 900px" "height: 900px">
 520 |   <img src="./output_34_0.png" alt="Graph of rsid per chromosome">
 521 |   <figcaption>rsid per chromosome</figcaption>
 522 | </figure>
 523 | 
 524 | 
 525 | ## Getting data on SNPs from SNPedia
 526 | 
 527 | To acquire more information about my DNA, I pulled files from [SNPedia](https://www.snpedia.com/index.php/SNPedia), a wiki investigating human genetics that gathers extensive data and cites to peer-reviewed scientific publications. SNPedia catalogues common, reproducible SNPs (or ones found in meta-analyses or studies of at least 500 patients), or those with other historic or medical significance.
 528 | 
 529 | The columns are:
 530 | 
 531 | * Unnamed: 0 (actually the SNP name)
 532 | * Magnitude (a subjective measure of interest)
 533 | * Repute (a subjective measure of whether the genotype is "good" or "bad" to have based on research, and blank for things like ancestry and eye color)
 534 | * Summary (a narrative description)
 535 | 
 536 | 
 537 | ```python
 538 | snp_df = pd.read_csv('result.csv')
 539 | snp_df.head()
 540 | ```
 541 | 
 542 | <div>
 543 | <style scoped>
 544 |     .dataframe tbody tr th:only-of-type {
 545 |         vertical-align: middle;
 546 |     }
 547 | 
 548 |     .dataframe tbody tr th {
 549 |         vertical-align: top;
 550 |     }
 551 | 
 552 |     .dataframe thead th {
 553 |         text-align: right;
 554 |     }
 555 | </style>
 556 | <table border="1" class="dataframe">
 557 |   <thead>
 558 |     <tr style="text-align: right;">
 559 |       <th></th>
 560 |       <th>Unnamed: 0</th>
 561 |       <th>Magnitude</th>
 562 |       <th>Repute</th>
 563 |       <th>Summary</th>
 564 |     </tr>
 565 |   </thead>
 566 |   <tbody>
 567 |     <tr>
 568 |       <th>0</th>
 569 |       <td>Rs661(A;A)</td>
 570 |       <td>9.0</td>
 571 |       <td>Bad</td>
 572 |       <td>early onset Alzheimer's disease</td>
 573 |     </tr>
 574 |     <tr>
 575 |       <th>1</th>
 576 |       <td>Rs6647(T;T)</td>
 577 |       <td>0.0</td>
 578 |       <td>Good</td>
 579 |       <td>Normal; two copies of Pi-M1V allele</td>
 580 |     </tr>
 581 |     <tr>
 582 |       <th>2</th>
 583 |       <td>Rs6647(C;C)</td>
 584 |       <td>0.0</td>
 585 |       <td>Good</td>
 586 |       <td>Normal; two copies of Pi-M1A allele</td>
 587 |     </tr>
 588 |     <tr>
 589 |       <th>3</th>
 590 |       <td>Rs1303(T;T)</td>
 591 |       <td>0.0</td>
 592 |       <td>Good</td>
 593 |       <td>common in clinvar</td>
 594 |     </tr>
 595 |     <tr>
 596 |       <th>4</th>
 597 |       <td>Rs28929471(G;G)</td>
 598 |       <td>0.0</td>
 599 |       <td>Good</td>
 600 |       <td>common in complete genomics</td>
 601 |     </tr>
 602 |   </tbody>
 603 | </table>
 604 | </div>
 605 | 
 606 | ### Fun with regular expressions
 607 | 
 608 | To align with my original DataFrame, I created a genotype column and used regex to separate out the genotype, which was stitched onto the end of the SNP name.
 609 | 
 610 | 
 611 | ```python
 612 | snp_df['genotype'] = snp_df['Unnamed: 0'].apply(lambda x: 
 613 |   re.sub(r'.*([AGCT]);([AGCT])\)', r'\1\2', x))
 614 | ```
 615 | 
 616 | 
 617 | ```python
 618 | snp_df.head()
 619 | ```
 620 | 
 621 | 
 622 | <div>
 623 | <style scoped>
 624 |     .dataframe tbody tr th:only-of-type {
 625 |         vertical-align: middle;
 626 |     }
 627 | 
 628 |     .dataframe tbody tr th {
 629 |         vertical-align: top;
 630 |     }
 631 | 
 632 |     .dataframe thead th {
 633 |         text-align: right;
 634 |     }
 635 | </style>
 636 | <table border="1" class="dataframe">
 637 |   <thead>
 638 |     <tr style="text-align: right;">
 639 |       <th></th>
 640 |       <th>Unnamed: 0</th>
 641 |       <th>Magnitude</th>
 642 |       <th>Repute</th>
 643 |       <th>Summary</th>
 644 |       <th>genotype</th>
 645 |     </tr>
 646 |   </thead>
 647 |   <tbody>
 648 |     <tr>
 649 |       <th>0</th>
 650 |       <td>Rs661(A;A)</td>
 651 |       <td>9.0</td>
 652 |       <td>Bad</td>
 653 |       <td>early onset Alzheimer's disease</td>
 654 |       <td>AA</td>
 655 |     </tr>
 656 |     <tr>
 657 |       <th>1</th>
 658 |       <td>Rs6647(T;T)</td>
 659 |       <td>0.0</td>
 660 |       <td>Good</td>
 661 |       <td>Normal; two copies of Pi-M1V allele</td>
 662 |       <td>TT</td>
 663 |     </tr>
 664 |     <tr>
 665 |       <th>2</th>
 666 |       <td>Rs6647(C;C)</td>
 667 |       <td>0.0</td>
 668 |       <td>Good</td>
 669 |       <td>Normal; two copies of Pi-M1A allele</td>
 670 |       <td>CC</td>
 671 |     </tr>
 672 |     <tr>
 673 |       <th>3</th>
 674 |       <td>Rs1303(T;T)</td>
 675 |       <td>0.0</td>
 676 |       <td>Good</td>
 677 |       <td>common in clinvar</td>
 678 |       <td>TT</td>
 679 |     </tr>
 680 |     <tr>
 681 |       <th>4</th>
 682 |       <td>Rs28929471(G;G)</td>
 683 |       <td>0.0</td>
 684 |       <td>Good</td>
 685 |       <td>common in complete genomics</td>
 686 |       <td>GG</td>
 687 |     </tr>
 688 |   </tbody>
 689 | </table>
 690 | </div>
 691 | 
 692 | 
 693 | 
 694 | For consistency's sake, I renamed the columns to match my original DataFrame and made sure the rsids were all lower-case.
 695 | 
 696 | 
 697 | ```python
 698 | new_cols = ['rsid', 'magnitude', 'repute', 
 699 | 'summary', 'genotype']
 700 | snp_df.columns = new_cols
 701 | ```
 702 | 
 703 | I used regex to clean up the rsid a little more, too (because I will take any excuse to use more regex).
 704 | 
 705 | 
 706 | ```python
 707 | snp_df['rsid'] = snp_df['rsid'].map(lambda x : x.lower())
 708 | snp_df['rsid'] = snp_df['rsid'].map(lambda x : 
 709 |   re.sub(r'([a-z]{1,}[\d]+)\([agct];[agct]\)', 
 710 |   r'\1', x))
 711 | ```
 712 | 
 713 | 
 714 | ```python
 715 | snp_df.head()
 716 | ```
 717 | 
 718 | <div>
 719 | <style scoped>
 720 |     .dataframe tbody tr th:only-of-type {
 721 |         vertical-align: middle;
 722 |     }
 723 | 
 724 |     .dataframe tbody tr th {
 725 |         vertical-align: top;
 726 |     }
 727 | 
 728 |     .dataframe thead th {
 729 |         text-align: right;
 730 |     }
 731 | </style>
 732 | <table border="1" class="dataframe">
 733 |   <thead>
 734 |     <tr style="text-align: right;">
 735 |       <th></th>
 736 |       <th>rsid</th>
 737 |       <th>magnitude</th>
 738 |       <th>repute</th>
 739 |       <th>summary</th>
 740 |       <th>genotype</th>
 741 |     </tr>
 742 |   </thead>
 743 |   <tbody>
 744 |     <tr>
 745 |       <th>0</th>
 746 |       <td>rs661</td>
 747 |       <td>9.0</td>
 748 |       <td>Bad</td>
 749 |       <td>early onset Alzheimer's disease</td>
 750 |       <td>AA</td>
 751 |     </tr>
 752 |     <tr>
 753 |       <th>1</th>
 754 |       <td>rs6647</td>
 755 |       <td>0.0</td>
 756 |       <td>Good</td>
 757 |       <td>Normal; two copies of Pi-M1V allele</td>
 758 |       <td>TT</td>
 759 |     </tr>
 760 |     <tr>
 761 |       <th>2</th>
 762 |       <td>rs6647</td>
 763 |       <td>0.0</td>
 764 |       <td>Good</td>
 765 |       <td>Normal; two copies of Pi-M1A allele</td>
 766 |       <td>CC</td>
 767 |     </tr>
 768 |     <tr>
 769 |       <th>3</th>
 770 |       <td>rs1303</td>
 771 |       <td>0.0</td>
 772 |       <td>Good</td>
 773 |       <td>common in clinvar</td>
 774 |       <td>TT</td>
 775 |     </tr>
 776 |     <tr>
 777 |       <th>4</th>
 778 |       <td>rs28929471</td>
 779 |       <td>0.0</td>
 780 |       <td>Good</td>
 781 |       <td>common in complete genomics</td>
 782 |       <td>GG</td>
 783 |     </tr>
 784 |   </tbody>
 785 | </table>
 786 | </div>
 787 | 
 788 | 
 789 | 
 790 | ```python
 791 | snp_df.info()
 792 | ```
 793 | 
 794 |     <class 'pandas.core.frame.DataFrame'>
 795 |     RangeIndex: 100 entries, 0 to 99
 796 |     Data columns (total 5 columns):
 797 |     rsid         100 non-null object
 798 |     magnitude    100 non-null float64
 799 |     repute       91 non-null object
 800 |     summary      96 non-null object
 801 |     genotype     100 non-null object
 802 |     dtypes: float64(1), object(4)
 803 |     memory usage: 4.0+ KB
 804 | 
 805 | I overwrote the null reputes and summaries.
 806 | 
 807 | ```python
 808 | null_repute = snp_df[snp_df['repute'].isnull()]
 809 | null_summaries = snp_df[snp_df['summary'].isnull()]
 810 | null_repute_and_summaries = pd.concat([null_repute,null_summaries]).drop_duplicates().reset_index(drop=True)
 811 | display(null_repute_and_summaries)
 812 | ```
 813 | 
 814 | 
 815 | <div>
 816 | <style scoped>
 817 |     .dataframe tbody tr th:only-of-type {
 818 |         vertical-align: middle;
 819 |     }
 820 | 
 821 |     .dataframe tbody tr th {
 822 |         vertical-align: top;
 823 |     }
 824 | 
 825 |     .dataframe thead th {
 826 |         text-align: right;
 827 |     }
 828 | </style>
 829 | <table border="1" class="dataframe">
 830 |   <thead>
 831 |     <tr style="text-align: right;">
 832 |       <th></th>
 833 |       <th>rsid</th>
 834 |       <th>magnitude</th>
 835 |       <th>repute</th>
 836 |       <th>summary</th>
 837 |       <th>genotype</th>
 838 |     </tr>
 839 |   </thead>
 840 |   <tbody>
 841 |     <tr>
 842 |       <th>0</th>
 843 |       <td>rs28931569</td>
 844 |       <td>4.0</td>
 845 |       <td>NaN</td>
 846 |       <td>high risk of emphysema</td>
 847 |       <td>CC</td>
 848 |     </tr>
 849 |     <tr>
 850 |       <th>1</th>
 851 |       <td>rs28929473</td>
 852 |       <td>0.0</td>
 853 |       <td>NaN</td>
 854 |       <td>NaN</td>
 855 |       <td>TT</td>
 856 |     </tr>
 857 |     <tr>
 858 |       <th>2</th>
 859 |       <td>rs28931572</td>
 860 |       <td>0.0</td>
 861 |       <td>NaN</td>
 862 |       <td>NaN</td>
 863 |       <td>AA</td>
 864 |     </tr>
 865 |     <tr>
 866 |       <th>3</th>
 867 |       <td>rs1801252</td>
 868 |       <td>3.0</td>
 869 |       <td>NaN</td>
 870 |       <td>NaN</td>
 871 |       <td>GG</td>
 872 |     </tr>
 873 |     <tr>
 874 |       <th>4</th>
 875 |       <td>rs8192466</td>
 876 |       <td>4.0</td>
 877 |       <td>NaN</td>
 878 |       <td>uncertain</td>
 879 |       <td>TT</td>
 880 |     </tr>
 881 |     <tr>
 882 |       <th>5</th>
 883 |       <td>rs4986852</td>
 884 |       <td>2.0</td>
 885 |       <td>NaN</td>
 886 |       <td>predisposition to breast cancer?</td>
 887 |       <td>AA</td>
 888 |     </tr>
 889 |     <tr>
 890 |       <th>6</th>
 891 |       <td>rs1800709</td>
 892 |       <td>2.0</td>
 893 |       <td>NaN</td>
 894 |       <td>predisposition to breast cancer?</td>
 895 |       <td>TT</td>
 896 |     </tr>
 897 |     <tr>
 898 |       <th>7</th>
 899 |       <td>rs28931592</td>
 900 |       <td>0.0</td>
 901 |       <td>NaN</td>
 902 |       <td>NaN</td>
 903 |       <td>TT</td>
 904 |     </tr>
 905 |     <tr>
 906 |       <th>8</th>
 907 |       <td>rs4986893</td>
 908 |       <td>2.1</td>
 909 |       <td>NaN</td>
 910 |       <td>poor metabolizer of several commonly prescribe...</td>
 911 |       <td>AA</td>
 912 |     </tr>
 913 |   </tbody>
 914 | </table>
 915 | </div>
 916 | 
 917 | 
 918 | 
 919 | ```python
 920 | snp_df['repute'].fillna(value='Neutral', inplace=True)
 921 | snp_df['summary'].fillna(value='None', inplace=True)
 922 | ```
 923 | 
 924 | 
 925 | ```python
 926 | # No no NaNette
 927 | snp_df.isna().any()
 928 | ```
 929 | 
 930 | 
 931 | 
 932 | 
 933 |     rsid         False
 934 |     magnitude    False
 935 |     repute       False
 936 |     summary      False
 937 |     genotype     False
 938 |     dtype: bool
 939 | 
 940 | 
 941 | 
 942 | # Merging my data with SNPedia
 943 | 
 944 | Appropriately enough, I did an inner join of the SNPedia DataFrame on my DNA to see what data, if any, it had on my particular genotypes.
 945 | 
 946 | 
 947 | ```python
 948 | new_df = snp_df.merge(df, how='inner', on=['rsid', 'genotype'], suffixes=('_SNPedia', '_myDNA'))
 949 | ```
 950 | 
 951 | 
 952 | ```python
 953 | new_df.head(20)
 954 | ```
 955 | 
 956 | 
 957 | 
 958 | 
 959 | <div>
 960 | <style scoped>
 961 |     .dataframe tbody tr th:only-of-type {
 962 |         vertical-align: middle;
 963 |     }
 964 | 
 965 |     .dataframe tbody tr th {
 966 |         vertical-align: top;
 967 |     }
 968 | 
 969 |     .dataframe thead th {
 970 |         text-align: right;
 971 |     }
 972 | </style>
 973 | <table border="1" class="dataframe">
 974 |   <thead>
 975 |     <tr style="text-align: right;">
 976 |       <th></th>
 977 |       <th>rsid</th>
 978 |       <th>magnitude</th>
 979 |       <th>repute</th>
 980 |       <th>summary</th>
 981 |       <th>genotype</th>
 982 |       <th>chromosome</th>
 983 |       <th>position</th>
 984 |     </tr>
 985 |   </thead>
 986 |   <tbody>
 987 |     <tr>
 988 |       <th>0</th>
 989 |       <td>rs1303</td>
 990 |       <td>0.0</td>
 991 |       <td>Good</td>
 992 |       <td>common in clinvar</td>
 993 |       <td>TT</td>
 994 |       <td>14</td>
 995 |       <td>94844843</td>
 996 |     </tr>
 997 |     <tr>
 998 |       <th>1</th>
 999 |       <td>rs17580</td>
1000 |       <td>2.5</td>
1001 |       <td>Bad</td>
1002 |       <td>a slightly reduced functionality form of Alpha...</td>
1003 |       <td>TT</td>
1004 |       <td>14</td>
1005 |       <td>94847262</td>
1006 |     </tr>
1007 |     <tr>
1008 |       <th>2</th>
1009 |       <td>rs28931580</td>
1010 |       <td>0.0</td>
1011 |       <td>Good</td>
1012 |       <td>common in clinvar</td>
1013 |       <td>AA</td>
1014 |       <td>12</td>
1015 |       <td>50344783</td>
1016 |     </tr>
1017 |     <tr>
1018 |       <th>3</th>
1019 |       <td>rs1042714</td>
1020 |       <td>0.0</td>
1021 |       <td>Good</td>
1022 |       <td>normal</td>
1023 |       <td>CC</td>
1024 |       <td>5</td>
1025 |       <td>148206473</td>
1026 |     </tr>
1027 |     <tr>
1028 |       <th>4</th>
1029 |       <td>rs1800888</td>
1030 |       <td>0.0</td>
1031 |       <td>Good</td>
1032 |       <td>normal</td>
1033 |       <td>CC</td>
1034 |       <td>5</td>
1035 |       <td>148206885</td>
1036 |     </tr>
1037 |     <tr>
1038 |       <th>5</th>
1039 |       <td>rs2303790</td>
1040 |       <td>0.0</td>
1041 |       <td>Good</td>
1042 |       <td>common in clinvar</td>
1043 |       <td>AA</td>
1044 |       <td>16</td>
1045 |       <td>57017292</td>
1046 |     </tr>
1047 |     <tr>
1048 |       <th>6</th>
1049 |       <td>rs5882</td>
1050 |       <td>2.0</td>
1051 |       <td>Bad</td>
1052 |       <td>Faster aging. Increased risk for Dementia. Les...</td>
1053 |       <td>AA</td>
1054 |       <td>16</td>
1055 |       <td>57016092</td>
1056 |     </tr>
1057 |     <tr>
1058 |       <th>7</th>
1059 |       <td>rs2230199</td>
1060 |       <td>2.0</td>
1061 |       <td>Bad</td>
1062 |       <td>2.5x+ risk of ARMD</td>
1063 |       <td>GG</td>
1064 |       <td>19</td>
1065 |       <td>6718387</td>
1066 |     </tr>
1067 |     <tr>
1068 |       <th>8</th>
1069 |       <td>rs28931608</td>
1070 |       <td>0.0</td>
1071 |       <td>Good</td>
1072 |       <td>common in clinvar</td>
1073 |       <td>GG</td>
1074 |       <td>7</td>
1075 |       <td>75614497</td>
1076 |     </tr>
1077 |     <tr>
1078 |       <th>9</th>
1079 |       <td>rs4986893</td>
1080 |       <td>0.0</td>
1081 |       <td>Good</td>
1082 |       <td>normal</td>
1083 |       <td>GG</td>
1084 |       <td>10</td>
1085 |       <td>96540410</td>
1086 |     </tr>
1087 |     <tr>
1088 |       <th>10</th>
1089 |       <td>rs28399504</td>
1090 |       <td>0.0</td>
1091 |       <td>Good</td>
1092 |       <td>normal</td>
1093 |       <td>AA</td>
1094 |       <td>10</td>
1095 |       <td>96522463</td>
1096 |     </tr>
1097 |     <tr>
1098 |       <th>11</th>
1099 |       <td>rs2234922</td>
1100 |       <td>0.0</td>
1101 |       <td>Good</td>
1102 |       <td>common in clinvar</td>
1103 |       <td>AA</td>
1104 |       <td>1</td>
1105 |       <td>226026406</td>
1106 |     </tr>
1107 |     <tr>
1108 |       <th>12</th>
1109 |       <td>rs28931614</td>
1110 |       <td>0.0</td>
1111 |       <td>Good</td>
1112 |       <td>common in clinvar</td>
1113 |       <td>GG</td>
1114 |       <td>4</td>
1115 |       <td>1806119</td>
1116 |     </tr>
1117 |     <tr>
1118 |       <th>13</th>
1119 |       <td>rs28933068</td>
1120 |       <td>0.0</td>
1121 |       <td>Good</td>
1122 |       <td>common in clinvar</td>
1123 |       <td>CC</td>
1124 |       <td>4</td>
1125 |       <td>1807371</td>
1126 |     </tr>
1127 |   </tbody>
1128 | </table>
1129 | </div>
1130 | 
1131 | 
1132 | 
1133 | ### What's hiding in there?
1134 | 
1135 | 
1136 | ```python
1137 | # Create a DataFrame for some subsets of genes
1138 | good_genes = new_df[new_df.repute == 'Good']
1139 | bad_genes = new_df[new_df.repute == 'Bad']
1140 | interesting_genes = new_df[new_df.magnitude > 4] # 4 is the threshold for "worth your time" given by SNPedia
1141 | ```
1142 | 
1143 | I have plenty of "good" genotypes, but none with a nonzero magnitude.
1144 | 
1145 | 
1146 | ```python
1147 | good_genes
1148 | ```
1149 | 
1150 | 
1151 | 
1152 | 
1153 | <div>
1154 | <style scoped>
1155 |     .dataframe tbody tr th:only-of-type {
1156 |         vertical-align: middle;
1157 |     }
1158 | 
1159 |     .dataframe tbody tr th {
1160 |         vertical-align: top;
1161 |     }
1162 | 
1163 |     .dataframe thead th {
1164 |         text-align: right;
1165 |     }
1166 | </style>
1167 | <table border="1" class="dataframe">
1168 |   <thead>
1169 |     <tr style="text-align: right;">
1170 |       <th></th>
1171 |       <th>rsid</th>
1172 |       <th>magnitude</th>
1173 |       <th>repute</th>
1174 |       <th>summary</th>
1175 |       <th>genotype</th>
1176 |       <th>chromosome</th>
1177 |       <th>position</th>
1178 |     </tr>
1179 |   </thead>
1180 |   <tbody>
1181 |     <tr>
1182 |       <th>0</th>
1183 |       <td>rs1303</td>
1184 |       <td>0.0</td>
1185 |       <td>Good</td>
1186 |       <td>common in clinvar</td>
1187 |       <td>TT</td>
1188 |       <td>14</td>
1189 |       <td>94844843</td>
1190 |     </tr>
1191 |     <tr>
1192 |       <th>2</th>
1193 |       <td>rs28931580</td>
1194 |       <td>0.0</td>
1195 |       <td>Good</td>
1196 |       <td>common in clinvar</td>
1197 |       <td>AA</td>
1198 |       <td>12</td>
1199 |       <td>50344783</td>
1200 |     </tr>
1201 |     <tr>
1202 |       <th>3</th>
1203 |       <td>rs1042714</td>
1204 |       <td>0.0</td>
1205 |       <td>Good</td>
1206 |       <td>normal</td>
1207 |       <td>CC</td>
1208 |       <td>5</td>
1209 |       <td>148206473</td>
1210 |     </tr>
1211 |     <tr>
1212 |       <th>4</th>
1213 |       <td>rs1800888</td>
1214 |       <td>0.0</td>
1215 |       <td>Good</td>
1216 |       <td>normal</td>
1217 |       <td>CC</td>
1218 |       <td>5</td>
1219 |       <td>148206885</td>
1220 |     </tr>
1221 |     <tr>
1222 |       <th>5</th>
1223 |       <td>rs2303790</td>
1224 |       <td>0.0</td>
1225 |       <td>Good</td>
1226 |       <td>common in clinvar</td>
1227 |       <td>AA</td>
1228 |       <td>16</td>
1229 |       <td>57017292</td>
1230 |     </tr>
1231 |     <tr>
1232 |       <th>8</th>
1233 |       <td>rs28931608</td>
1234 |       <td>0.0</td>
1235 |       <td>Good</td>
1236 |       <td>common in clinvar</td>
1237 |       <td>GG</td>
1238 |       <td>7</td>
1239 |       <td>75614497</td>
1240 |     </tr>
1241 |     <tr>
1242 |       <th>9</th>
1243 |       <td>rs4986893</td>
1244 |       <td>0.0</td>
1245 |       <td>Good</td>
1246 |       <td>normal</td>
1247 |       <td>GG</td>
1248 |       <td>10</td>
1249 |       <td>96540410</td>
1250 |     </tr>
1251 |     <tr>
1252 |       <th>10</th>
1253 |       <td>rs28399504</td>
1254 |       <td>0.0</td>
1255 |       <td>Good</td>
1256 |       <td>normal</td>
1257 |       <td>AA</td>
1258 |       <td>10</td>
1259 |       <td>96522463</td>
1260 |     </tr>
1261 |     <tr>
1262 |       <th>11</th>
1263 |       <td>rs2234922</td>
1264 |       <td>0.0</td>
1265 |       <td>Good</td>
1266 |       <td>common in clinvar</td>
1267 |       <td>AA</td>
1268 |       <td>1</td>
1269 |       <td>226026406</td>
1270 |     </tr>
1271 |     <tr>
1272 |       <th>12</th>
1273 |       <td>rs28931614</td>
1274 |       <td>0.0</td>
1275 |       <td>Good</td>
1276 |       <td>common in clinvar</td>
1277 |       <td>GG</td>
1278 |       <td>4</td>
1279 |       <td>1806119</td>
1280 |     </tr>
1281 |     <tr>
1282 |       <th>13</th>
1283 |       <td>rs28933068</td>
1284 |       <td>0.0</td>
1285 |       <td>Good</td>
1286 |       <td>common in clinvar</td>
1287 |       <td>CC</td>
1288 |       <td>4</td>
1289 |       <td>1807371</td>
1290 |     </tr>
1291 |   </tbody>
1292 | </table>
1293 | </div>
1294 | 
1295 | 
1296 | 
1297 | I have three "bad" genotypes with a nonzero magnitude.
1298 | 
1299 | 
1300 | ```python
1301 | bad_genes
1302 | ```
1303 | 
1304 | 
1305 | 
1306 | 
1307 | <div>
1308 | <style scoped>
1309 |     .dataframe tbody tr th:only-of-type {
1310 |         vertical-align: middle;
1311 |     }
1312 | 
1313 |     .dataframe tbody tr th {
1314 |         vertical-align: top;
1315 |     }
1316 | 
1317 |     .dataframe thead th {
1318 |         text-align: right;
1319 |     }
1320 | </style>
1321 | <table border="1" class="dataframe">
1322 |   <thead>
1323 |     <tr style="text-align: right;">
1324 |       <th></th>
1325 |       <th>rsid</th>
1326 |       <th>magnitude</th>
1327 |       <th>repute</th>
1328 |       <th>summary</th>
1329 |       <th>genotype</th>
1330 |       <th>chromosome</th>
1331 |       <th>position</th>
1332 |     </tr>
1333 |   </thead>
1334 |   <tbody>
1335 |     <tr>
1336 |       <th>1</th>
1337 |       <td>rs17580</td>
1338 |       <td>2.5</td>
1339 |       <td>Bad</td>
1340 |       <td>a slightly reduced functionality form of Alpha...</td>
1341 |       <td>TT</td>
1342 |       <td>14</td>
1343 |       <td>94847262</td>
1344 |     </tr>
1345 |     <tr>
1346 |       <th>6</th>
1347 |       <td>rs5882</td>
1348 |       <td>2.0</td>
1349 |       <td>Bad</td>
1350 |       <td>Faster aging. Increased risk for Dementia. Les...</td>
1351 |       <td>AA</td>
1352 |       <td>16</td>
1353 |       <td>57016092</td>
1354 |     </tr>
1355 |     <tr>
1356 |       <th>7</th>
1357 |       <td>rs2230199</td>
1358 |       <td>2.0</td>
1359 |       <td>Bad</td>
1360 |       <td>2.5x+ risk of ARMD</td>
1361 |       <td>GG</td>
1362 |       <td>19</td>
1363 |       <td>6718387</td>
1364 |     </tr>
1365 |   </tbody>
1366 | </table>
1367 | </div>
1368 | 
1369 | 
1370 | 
1371 | Sadly, I had no "interesting" genotypes above the threshold of 4, although hearteningly I did possess some slightly interesting bad ones.
1372 | 
1373 | 
1374 | # Scrape relevant articles with Selenium
1375 | 
1376 | I decided I might like to read up on my bad genetics, so I used Selenium to scrape the abstracts of some scientific papers from PubMed.
1377 | 
1378 | 
1379 | ```python
1380 | # Get the base URL from SNPedia
1381 | base_url = 'https://www.snpedia.com/index.php/'
1382 | ```
1383 | 
1384 | 
1385 | ```python
1386 | # Create URLs for each gene that I want to study
1387 | gene_urls = [base_url + rsid for rsid in bad_genes['rsid']]
1388 | 
1389 | ```
1390 |     
1391 | ```python
1392 | # Initialize Selenium
1393 | browser = webdriver.Chrome()
1394 | ```
1395 | 
1396 | 
1397 | ```python
1398 | import time
1399 | ```
1400 | 
1401 | 
1402 | ```python
1403 | # Write a function to visit the SNPedia URLs, click through to PubMed, 
1404 | # and retrieve the info on the articles for each gene
1405 | 
1406 | def scrape_abstracts(urls):
1407 |     
1408 |     rsid_list = []
1409 |     all_article_title = []
1410 |     all_article_citation = []
1411 |     all_article_authors = []
1412 |     all_article_abstract = []
1413 |     all_article_links = []
1414 | 
1415 |     for url in urls:
1416 |         link_urls = []
1417 |         browser.get(url) #load url
1418 |         rsid = browser.find_element_by_css_selector('.firstHeading').text
1419 |         links_elements = browser.find_elements_by_partial_link_text('PMID')
1420 |         
1421 |         # get the URLs to the PubMed pages
1422 |       for link in links_elements:
1423 |           link_urls.append(link.get_attribute('href')) 
1424 |     
1425 |       # follow each link element to PubMed
1426 |       for element in link_urls:
1427 |           browser.get(element) 
1428 |           time.sleep(2)
1429 |           article_title = browser.find_element_by_xpath("//div[@class='cit']/../h1").text
1430 |           article_citation = browser.find_element_by_class_name('cit').text
1431 |           article_authors = browser.find_element_by_class_name('auths').text
1432 |           article_abstract = browser.find_element_by_class_name('abstr').text
1433 |             
1434 |           rsid_list.append(rsid)
1435 |           all_article_title.append(article_title)
1436 |           all_article_citation.append(article_citation)
1437 |           all_article_authors.append(article_authors)
1438 |           all_article_abstract.append(article_abstract)
1439 |           all_article_links.append(element)
1440 | 
1441 |   # store the information
1442 |     df = pd.DataFrame()
1443 |     df['rsid'] = rsid_list
1444 |     df['article_title'] = all_article_title
1445 |     df['article_citation'] = all_article_citation
1446 |     df['article_authors'] = all_article_authors
1447 |     df['article_abstract'] = all_article_abstract
1448 |     df['link'] = all_article_links
1449 |         
1450 |     df = df.drop_duplicates()
1451 |         
1452 |     df.index = range(len(df.index))
1453 |     
1454 |     return df
1455 | ```
1456 | 
1457 | 
1458 | ```python
1459 | abstracts_df = scrape_abstracts(gene_urls)
1460 | ```
1461 | 
1462 | For later hypochondriacal perusal, I exported my findings, complete with abstracts and hyperlinks, to a CSV file using the pandas DataFrame.to_csv method. 
1463 | 
1464 | 
1465 | ```python
1466 | # DataFrame to CSV
1467 | export_csv = abstracts_df.to_csv(r'/Users/lorajohns/Documents/Python/DNA/DNA_articles.csv')
1468 | ```
1469 | 
1470 | ## Reading up on the medical literature
1471 | 
1472 | <figure style="width: 1200px">
1473 |   <img src="./DNA_articles.png" alt="Formatted DNA_articles.csv in Numbers">
1474 |   <figcaption>DNA_articles.csv in Numbers</figcaption>
1475 | </figure>
1476 | 
1477 | Now I have a handy CSV file, nicely formatted, with citations to scientific articles analyzing and describing my probably un-problematic, but probationally proditory genotypes. Python provides prodigious tools to engage in literal introspection that the sawbones of old could never have imagined. 
1478 | 


--------------------------------------------------------------------------------
/DNA.ipynb:
--------------------------------------------------------------------------------
   1 | {
   2 |  "cells": [
   3 |   {
   4 |    "cell_type": "markdown",
   5 |    "metadata": {},
   6 |    "source": [
   7 |     "# Know Thyself: Using Data Science to Explore Your Own Genome\n",
   8 |     "## DNA analysis with pandas and Selenium"
   9 |    ]
  10 |   },
  11 |   {
  12 |    "cell_type": "markdown",
  13 |    "metadata": {},
  14 |    "source": [
  15 |     "[23andme](https://www.23andme.com/) once offered me a free DNA and ancestry test kit if I participated in one of their clinical studies. In exchange for my genetic data and a bunch of questionnaires, I got my genome sequenced and gained access to myriad reports on where my ancestors were likely from, what health conditions and traits I probably have inherited, and who else on the site I might be related to.\n",
  16 |     "\n",
  17 |     "While 23andme provides an overwhelming amount of consumer-ready infographics and tools, I wondered what else I could do with the data. I knew I could download my raw genetic data from the site in a text file, so I decided to pour it into pandas and see what I could make of it. "
  18 |    ]
  19 |   },
  20 |   {
  21 |    "cell_type": "code",
  22 |    "execution_count": 1,
  23 |    "metadata": {},
  24 |    "outputs": [],
  25 |    "source": [
  26 |     "%matplotlib inline\n",
  27 |     "import seaborn as sns\n",
  28 |     "sns.set_style('darkgrid')\n",
  29 |     "sns.color_palette('Spectral')\n",
  30 |     "import matplotlib.pyplot as plt"
  31 |    ]
  32 |   },
  33 |   {
  34 |    "cell_type": "code",
  35 |    "execution_count": 2,
  36 |    "metadata": {},
  37 |    "outputs": [],
  38 |    "source": [
  39 |     "import numpy as np\n",
  40 |     "import requests\n",
  41 |     "import pandas as pd\n",
  42 |     "\n",
  43 |     "import re"
  44 |    ]
  45 |   },
  46 |   {
  47 |    "cell_type": "code",
  48 |    "execution_count": 3,
  49 |    "metadata": {},
  50 |    "outputs": [],
  51 |    "source": [
  52 |     "from selenium import webdriver\n",
  53 |     "from selenium.webdriver.support.ui import WebDriverWait"
  54 |    ]
  55 |   },
  56 |   {
  57 |    "cell_type": "markdown",
  58 |    "metadata": {},
  59 |    "source": [
  60 |     "## Importing my DNA into pandas and exploring the genome\n",
  61 |     "\n",
  62 |     "Looking at the .txt file, I could see that I was missing some genotype values, which were denoted with '--'. \n",
  63 |     "\n",
  64 |     "While most of the chromosomes are ints, there is an X and a Y (which I may convert later to a number for analytic purposes), but for now I need to make sure to specify the data type properly so that pandas doesn't throw an error when it sees mixed data in the input. \n",
  65 |     "\n",
  66 |     "The other columns are fairly straightforward. I also want pandas to ignore the prefatory comments at the beginning of the file that consist of lines beginning with an octothorpe.\n",
  67 |     "\n",
  68 |     "The arguments I need to pass are:\n",
  69 |     "* separator (tab-delimited)\n",
  70 |     "* dtype (as a dict)\n",
  71 |     "* na_values ('--')\n",
  72 |     "* comment ('#')\n",
  73 |     "\n",
  74 |     "![img](/genome.png)"
  75 |    ]
  76 |   },
  77 |   {
  78 |    "cell_type": "code",
  79 |    "execution_count": 4,
  80 |    "metadata": {},
  81 |    "outputs": [],
  82 |    "source": [
  83 |     "data = pd.read_csv('genome.txt', sep='\\t', dtype={'rsid':'str', 'chromosome':'object', 'position':'int', 'genotype':'str'}, comment='#')\n",
  84 |     "\n"
  85 |    ]
  86 |   },
  87 |   {
  88 |    "cell_type": "code",
  89 |    "execution_count": 5,
  90 |    "metadata": {},
  91 |    "outputs": [
  92 |     {
  93 |      "name": "stdout",
  94 |      "output_type": "stream",
  95 |      "text": [
  96 |       "               rsid chromosome  position genotype\n",
  97 |       "0       rs548049170          1     69869       TT\n",
  98 |       "1        rs13328684          1     74792       --\n",
  99 |       "2         rs9283150          1    565508       AA\n",
 100 |       "3           i713426          1    726912       --\n",
 101 |       "4       rs116587930          1    727841       GG\n",
 102 |       "5         rs3131972          1    752721       AG\n",
 103 |       "6        rs12184325          1    754105       CC\n",
 104 |       "7        rs12567639          1    756268       AA\n",
 105 |       "8       rs114525117          1    759036       GG\n",
 106 |       "9        rs12124819          1    776546       AA\n",
 107 |       "10       rs12127425          1    794332       GG\n",
 108 |       "11       rs79373928          1    801536       TT\n",
 109 |       "12       rs72888853          1    815421       --\n",
 110 |       "13        rs7538305          1    824398       AA\n",
 111 |       "14       rs28444699          1    830181       AA\n",
 112 |       "15          i713449          1    830731       --\n",
 113 |       "16      rs116452738          1    834830       GG\n",
 114 |       "17       rs72631887          1    835092       TT\n",
 115 |       "18       rs28678693          1    838665       TT\n",
 116 |       "19        rs4970382          1    840753       CT\n",
 117 |       "20        rs4475691          1    846808       CC\n",
 118 |       "21       rs72631889          1    851390       GG\n",
 119 |       "22        rs7537756          1    854250       AA\n",
 120 |       "23       rs13302982          1    861808       GG\n",
 121 |       "24      rs376747791          1    863130       AA\n",
 122 |       "25        rs2880024          1    866893       CC\n",
 123 |       "26       rs13302914          1    868404       TT\n",
 124 |       "27       rs76723341          1    872952       CC\n",
 125 |       "28        rs2272757          1    881627       AA\n",
 126 |       "29       rs35471880          1    881918       GG\n",
 127 |       "...             ...        ...       ...      ...\n",
 128 |       "638501      i702582         MT     16399        A\n",
 129 |       "638502     i3001912         MT     16428        G\n",
 130 |       "638503      i705509         MT     16428        G\n",
 131 |       "638504     i3001918         MT     16463        A\n",
 132 |       "638505      i703465         MT     16463        A\n",
 133 |       "638506     i3001919         MT     16465        C\n",
 134 |       "638507      i702453         MT     16465        C\n",
 135 |       "638508     i4000619         MT     16468        T\n",
 136 |       "638509      i704237         MT     16468        T\n",
 137 |       "638510     i3001920         MT     16470        G\n",
 138 |       "638511      i703422         MT     16470        G\n",
 139 |       "638512     i3001921         MT     16471       --\n",
 140 |       "638513      i702337         MT     16471       --\n",
 141 |       "638514     i3001925         MT     16482        A\n",
 142 |       "638515      i708027         MT     16482        A\n",
 143 |       "638516     i3001926         MT     16483        G\n",
 144 |       "638517      i704927         MT     16483        G\n",
 145 |       "638518     i4000691         MT     16488        C\n",
 146 |       "638519      i706404         MT     16488        C\n",
 147 |       "638520      i706772         MT     16494        C\n",
 148 |       "638521     i3001927         MT     16497        A\n",
 149 |       "638522      i705833         MT     16497        A\n",
 150 |       "638523     i4000690         MT     16518        G\n",
 151 |       "638524      i701050         MT     16518        G\n",
 152 |       "638525      i701374         MT     16523        A\n",
 153 |       "638526     i4000693         MT     16524        A\n",
 154 |       "638527      i704756         MT     16524        A\n",
 155 |       "638528      i705255         MT     16525        A\n",
 156 |       "638529     i4000757         MT     16526        G\n",
 157 |       "638530      i701671         MT     16526        G\n",
 158 |       "\n",
 159 |       "[638531 rows x 4 columns]\n"
 160 |      ]
 161 |     }
 162 |    ],
 163 |    "source": [
 164 |     "print(data)"
 165 |    ]
 166 |   },
 167 |   {
 168 |    "cell_type": "markdown",
 169 |    "metadata": {},
 170 |    "source": [
 171 |     "A quick note on the column names:\n",
 172 |     "\n",
 173 |     "* rsid stands for Reference SNP cluster ID. It identifies unique SNPs.\n",
 174 |     "\n",
 175 |     "* SNPs are Single Nucleotide Polymorphisms ('snips'), locations in the genome that are known to vary between individuals. They can influence disease risk, drug efficacy and side-effects, tell you about your ancestry, and predict aspects of how you look and act.\n",
 176 |     "\n",
 177 |     "* All humans have almost the same sequence of 3 billion DNA bases (A,C,G, or T) distributed between their 23 pairs of chromosomes. But at certain locations there are differences that have been reported to be meaningful, either medically or for other reasons (such as for genealogy). The SNPedia catalogues SNPs that have significant medical consequences, are common, are reproducible (or found in meta-analyses or studies of at least 500 patients), or have other historic or medical significance.\n",
 178 |     "\n",
 179 |     "I started off by navigating my new data frame with some basic exploratory data analysis and data cleaning."
 180 |    ]
 181 |   },
 182 |   {
 183 |    "cell_type": "code",
 184 |    "execution_count": 6,
 185 |    "metadata": {},
 186 |    "outputs": [],
 187 |    "source": [
 188 |     "# Read the data into a pandas DataFrame and do some EDA\n",
 189 |     "df = pd.DataFrame(data)"
 190 |    ]
 191 |   },
 192 |   {
 193 |    "cell_type": "code",
 194 |    "execution_count": 7,
 195 |    "metadata": {
 196 |     "scrolled": true
 197 |    },
 198 |    "outputs": [
 199 |     {
 200 |      "data": {
 201 |       "text/html": [
 202 |        "<div>\n",
 203 |        "<style scoped>\n",
 204 |        "    .dataframe tbody tr th:only-of-type {\n",
 205 |        "        vertical-align: middle;\n",
 206 |        "    }\n",
 207 |        "\n",
 208 |        "    .dataframe tbody tr th {\n",
 209 |        "        vertical-align: top;\n",
 210 |        "    }\n",
 211 |        "\n",
 212 |        "    .dataframe thead th {\n",
 213 |        "        text-align: right;\n",
 214 |        "    }\n",
 215 |        "</style>\n",
 216 |        "<table border=\"1\" class=\"dataframe\">\n",
 217 |        "  <thead>\n",
 218 |        "    <tr style=\"text-align: right;\">\n",
 219 |        "      <th></th>\n",
 220 |        "      <th>rsid</th>\n",
 221 |        "      <th>chromosome</th>\n",
 222 |        "      <th>position</th>\n",
 223 |        "      <th>genotype</th>\n",
 224 |        "    </tr>\n",
 225 |        "  </thead>\n",
 226 |        "  <tbody>\n",
 227 |        "    <tr>\n",
 228 |        "      <th>0</th>\n",
 229 |        "      <td>rs548049170</td>\n",
 230 |        "      <td>1</td>\n",
 231 |        "      <td>69869</td>\n",
 232 |        "      <td>TT</td>\n",
 233 |        "    </tr>\n",
 234 |        "    <tr>\n",
 235 |        "      <th>1</th>\n",
 236 |        "      <td>rs13328684</td>\n",
 237 |        "      <td>1</td>\n",
 238 |        "      <td>74792</td>\n",
 239 |        "      <td>--</td>\n",
 240 |        "    </tr>\n",
 241 |        "    <tr>\n",
 242 |        "      <th>2</th>\n",
 243 |        "      <td>rs9283150</td>\n",
 244 |        "      <td>1</td>\n",
 245 |        "      <td>565508</td>\n",
 246 |        "      <td>AA</td>\n",
 247 |        "    </tr>\n",
 248 |        "    <tr>\n",
 249 |        "      <th>3</th>\n",
 250 |        "      <td>i713426</td>\n",
 251 |        "      <td>1</td>\n",
 252 |        "      <td>726912</td>\n",
 253 |        "      <td>--</td>\n",
 254 |        "    </tr>\n",
 255 |        "    <tr>\n",
 256 |        "      <th>4</th>\n",
 257 |        "      <td>rs116587930</td>\n",
 258 |        "      <td>1</td>\n",
 259 |        "      <td>727841</td>\n",
 260 |        "      <td>GG</td>\n",
 261 |        "    </tr>\n",
 262 |        "    <tr>\n",
 263 |        "      <th>5</th>\n",
 264 |        "      <td>rs3131972</td>\n",
 265 |        "      <td>1</td>\n",
 266 |        "      <td>752721</td>\n",
 267 |        "      <td>AG</td>\n",
 268 |        "    </tr>\n",
 269 |        "    <tr>\n",
 270 |        "      <th>6</th>\n",
 271 |        "      <td>rs12184325</td>\n",
 272 |        "      <td>1</td>\n",
 273 |        "      <td>754105</td>\n",
 274 |        "      <td>CC</td>\n",
 275 |        "    </tr>\n",
 276 |        "    <tr>\n",
 277 |        "      <th>7</th>\n",
 278 |        "      <td>rs12567639</td>\n",
 279 |        "      <td>1</td>\n",
 280 |        "      <td>756268</td>\n",
 281 |        "      <td>AA</td>\n",
 282 |        "    </tr>\n",
 283 |        "    <tr>\n",
 284 |        "      <th>8</th>\n",
 285 |        "      <td>rs114525117</td>\n",
 286 |        "      <td>1</td>\n",
 287 |        "      <td>759036</td>\n",
 288 |        "      <td>GG</td>\n",
 289 |        "    </tr>\n",
 290 |        "    <tr>\n",
 291 |        "      <th>9</th>\n",
 292 |        "      <td>rs12124819</td>\n",
 293 |        "      <td>1</td>\n",
 294 |        "      <td>776546</td>\n",
 295 |        "      <td>AA</td>\n",
 296 |        "    </tr>\n",
 297 |        "    <tr>\n",
 298 |        "      <th>10</th>\n",
 299 |        "      <td>rs12127425</td>\n",
 300 |        "      <td>1</td>\n",
 301 |        "      <td>794332</td>\n",
 302 |        "      <td>GG</td>\n",
 303 |        "    </tr>\n",
 304 |        "    <tr>\n",
 305 |        "      <th>11</th>\n",
 306 |        "      <td>rs79373928</td>\n",
 307 |        "      <td>1</td>\n",
 308 |        "      <td>801536</td>\n",
 309 |        "      <td>TT</td>\n",
 310 |        "    </tr>\n",
 311 |        "    <tr>\n",
 312 |        "      <th>12</th>\n",
 313 |        "      <td>rs72888853</td>\n",
 314 |        "      <td>1</td>\n",
 315 |        "      <td>815421</td>\n",
 316 |        "      <td>--</td>\n",
 317 |        "    </tr>\n",
 318 |        "    <tr>\n",
 319 |        "      <th>13</th>\n",
 320 |        "      <td>rs7538305</td>\n",
 321 |        "      <td>1</td>\n",
 322 |        "      <td>824398</td>\n",
 323 |        "      <td>AA</td>\n",
 324 |        "    </tr>\n",
 325 |        "    <tr>\n",
 326 |        "      <th>14</th>\n",
 327 |        "      <td>rs28444699</td>\n",
 328 |        "      <td>1</td>\n",
 329 |        "      <td>830181</td>\n",
 330 |        "      <td>AA</td>\n",
 331 |        "    </tr>\n",
 332 |        "    <tr>\n",
 333 |        "      <th>15</th>\n",
 334 |        "      <td>i713449</td>\n",
 335 |        "      <td>1</td>\n",
 336 |        "      <td>830731</td>\n",
 337 |        "      <td>--</td>\n",
 338 |        "    </tr>\n",
 339 |        "    <tr>\n",
 340 |        "      <th>16</th>\n",
 341 |        "      <td>rs116452738</td>\n",
 342 |        "      <td>1</td>\n",
 343 |        "      <td>834830</td>\n",
 344 |        "      <td>GG</td>\n",
 345 |        "    </tr>\n",
 346 |        "    <tr>\n",
 347 |        "      <th>17</th>\n",
 348 |        "      <td>rs72631887</td>\n",
 349 |        "      <td>1</td>\n",
 350 |        "      <td>835092</td>\n",
 351 |        "      <td>TT</td>\n",
 352 |        "    </tr>\n",
 353 |        "    <tr>\n",
 354 |        "      <th>18</th>\n",
 355 |        "      <td>rs28678693</td>\n",
 356 |        "      <td>1</td>\n",
 357 |        "      <td>838665</td>\n",
 358 |        "      <td>TT</td>\n",
 359 |        "    </tr>\n",
 360 |        "    <tr>\n",
 361 |        "      <th>19</th>\n",
 362 |        "      <td>rs4970382</td>\n",
 363 |        "      <td>1</td>\n",
 364 |        "      <td>840753</td>\n",
 365 |        "      <td>CT</td>\n",
 366 |        "    </tr>\n",
 367 |        "    <tr>\n",
 368 |        "      <th>20</th>\n",
 369 |        "      <td>rs4475691</td>\n",
 370 |        "      <td>1</td>\n",
 371 |        "      <td>846808</td>\n",
 372 |        "      <td>CC</td>\n",
 373 |        "    </tr>\n",
 374 |        "    <tr>\n",
 375 |        "      <th>21</th>\n",
 376 |        "      <td>rs72631889</td>\n",
 377 |        "      <td>1</td>\n",
 378 |        "      <td>851390</td>\n",
 379 |        "      <td>GG</td>\n",
 380 |        "    </tr>\n",
 381 |        "    <tr>\n",
 382 |        "      <th>22</th>\n",
 383 |        "      <td>rs7537756</td>\n",
 384 |        "      <td>1</td>\n",
 385 |        "      <td>854250</td>\n",
 386 |        "      <td>AA</td>\n",
 387 |        "    </tr>\n",
 388 |        "    <tr>\n",
 389 |        "      <th>23</th>\n",
 390 |        "      <td>rs13302982</td>\n",
 391 |        "      <td>1</td>\n",
 392 |        "      <td>861808</td>\n",
 393 |        "      <td>GG</td>\n",
 394 |        "    </tr>\n",
 395 |        "    <tr>\n",
 396 |        "      <th>24</th>\n",
 397 |        "      <td>rs376747791</td>\n",
 398 |        "      <td>1</td>\n",
 399 |        "      <td>863130</td>\n",
 400 |        "      <td>AA</td>\n",
 401 |        "    </tr>\n",
 402 |        "  </tbody>\n",
 403 |        "</table>\n",
 404 |        "</div>"
 405 |       ],
 406 |       "text/plain": [
 407 |        "           rsid chromosome  position genotype\n",
 408 |        "0   rs548049170          1     69869       TT\n",
 409 |        "1    rs13328684          1     74792       --\n",
 410 |        "2     rs9283150          1    565508       AA\n",
 411 |        "3       i713426          1    726912       --\n",
 412 |        "4   rs116587930          1    727841       GG\n",
 413 |        "5     rs3131972          1    752721       AG\n",
 414 |        "6    rs12184325          1    754105       CC\n",
 415 |        "7    rs12567639          1    756268       AA\n",
 416 |        "8   rs114525117          1    759036       GG\n",
 417 |        "9    rs12124819          1    776546       AA\n",
 418 |        "10   rs12127425          1    794332       GG\n",
 419 |        "11   rs79373928          1    801536       TT\n",
 420 |        "12   rs72888853          1    815421       --\n",
 421 |        "13    rs7538305          1    824398       AA\n",
 422 |        "14   rs28444699          1    830181       AA\n",
 423 |        "15      i713449          1    830731       --\n",
 424 |        "16  rs116452738          1    834830       GG\n",
 425 |        "17   rs72631887          1    835092       TT\n",
 426 |        "18   rs28678693          1    838665       TT\n",
 427 |        "19    rs4970382          1    840753       CT\n",
 428 |        "20    rs4475691          1    846808       CC\n",
 429 |        "21   rs72631889          1    851390       GG\n",
 430 |        "22    rs7537756          1    854250       AA\n",
 431 |        "23   rs13302982          1    861808       GG\n",
 432 |        "24  rs376747791          1    863130       AA"
 433 |       ]
 434 |      },
 435 |      "execution_count": 7,
 436 |      "metadata": {},
 437 |      "output_type": "execute_result"
 438 |     }
 439 |    ],
 440 |    "source": [
 441 |     "df.head(25)"
 442 |    ]
 443 |   },
 444 |   {
 445 |    "cell_type": "code",
 446 |    "execution_count": 8,
 447 |    "metadata": {},
 448 |    "outputs": [
 449 |     {
 450 |      "data": {
 451 |       "text/plain": [
 452 |        " rsid         False\n",
 453 |        "chromosome    False\n",
 454 |        "position      False\n",
 455 |        "genotype      False\n",
 456 |        "dtype: bool"
 457 |       ]
 458 |      },
 459 |      "execution_count": 8,
 460 |      "metadata": {},
 461 |      "output_type": "execute_result"
 462 |     }
 463 |    ],
 464 |    "source": [
 465 |     "df.isna().any()"
 466 |    ]
 467 |   },
 468 |   {
 469 |    "cell_type": "code",
 470 |    "execution_count": 9,
 471 |    "metadata": {
 472 |     "scrolled": true
 473 |    },
 474 |    "outputs": [
 475 |     {
 476 |      "data": {
 477 |       "text/plain": [
 478 |        " rsid         638531\n",
 479 |        "chromosome        25\n",
 480 |        "position      634934\n",
 481 |        "genotype          20\n",
 482 |        "dtype: int64"
 483 |       ]
 484 |      },
 485 |      "execution_count": 9,
 486 |      "metadata": {},
 487 |      "output_type": "execute_result"
 488 |     }
 489 |    ],
 490 |    "source": [
 491 |     "df.nunique()"
 492 |    ]
 493 |   },
 494 |   {
 495 |    "cell_type": "code",
 496 |    "execution_count": 10,
 497 |    "metadata": {},
 498 |    "outputs": [
 499 |     {
 500 |      "name": "stdout",
 501 |      "output_type": "stream",
 502 |      "text": [
 503 |       "<class 'pandas.core.frame.DataFrame'>\n",
 504 |       "RangeIndex: 638531 entries, 0 to 638530\n",
 505 |       "Data columns (total 4 columns):\n",
 506 |       " rsid         638531 non-null object\n",
 507 |       "chromosome    638531 non-null object\n",
 508 |       "position      638531 non-null int64\n",
 509 |       "genotype      638531 non-null object\n",
 510 |       "dtypes: int64(1), object(3)\n",
 511 |       "memory usage: 19.5+ MB\n"
 512 |      ]
 513 |     }
 514 |    ],
 515 |    "source": [
 516 |     "df.info()"
 517 |    ]
 518 |   },
 519 |   {
 520 |    "cell_type": "code",
 521 |    "execution_count": 11,
 522 |    "metadata": {},
 523 |    "outputs": [
 524 |     {
 525 |      "data": {
 526 |       "text/html": [
 527 |        "<div>\n",
 528 |        "<style scoped>\n",
 529 |        "    .dataframe tbody tr th:only-of-type {\n",
 530 |        "        vertical-align: middle;\n",
 531 |        "    }\n",
 532 |        "\n",
 533 |        "    .dataframe tbody tr th {\n",
 534 |        "        vertical-align: top;\n",
 535 |        "    }\n",
 536 |        "\n",
 537 |        "    .dataframe thead th {\n",
 538 |        "        text-align: right;\n",
 539 |        "    }\n",
 540 |        "</style>\n",
 541 |        "<table border=\"1\" class=\"dataframe\">\n",
 542 |        "  <thead>\n",
 543 |        "    <tr style=\"text-align: right;\">\n",
 544 |        "      <th></th>\n",
 545 |        "      <th>rsid</th>\n",
 546 |        "      <th>chromosome</th>\n",
 547 |        "      <th>position</th>\n",
 548 |        "      <th>genotype</th>\n",
 549 |        "    </tr>\n",
 550 |        "  </thead>\n",
 551 |        "  <tbody>\n",
 552 |        "    <tr>\n",
 553 |        "      <th>449</th>\n",
 554 |        "      <td>i6059967</td>\n",
 555 |        "      <td>1</td>\n",
 556 |        "      <td>2526746</td>\n",
 557 |        "      <td>AA</td>\n",
 558 |        "    </tr>\n",
 559 |        "    <tr>\n",
 560 |        "      <th>2816</th>\n",
 561 |        "      <td>i6052145</td>\n",
 562 |        "      <td>1</td>\n",
 563 |        "      <td>11009679</td>\n",
 564 |        "      <td>GG</td>\n",
 565 |        "    </tr>\n",
 566 |        "    <tr>\n",
 567 |        "      <th>5325</th>\n",
 568 |        "      <td>i6012699</td>\n",
 569 |        "      <td>1</td>\n",
 570 |        "      <td>19992513</td>\n",
 571 |        "      <td>CC</td>\n",
 572 |        "    </tr>\n",
 573 |        "    <tr>\n",
 574 |        "      <th>5339</th>\n",
 575 |        "      <td>i6059797</td>\n",
 576 |        "      <td>1</td>\n",
 577 |        "      <td>20020994</td>\n",
 578 |        "      <td>TT</td>\n",
 579 |        "    </tr>\n",
 580 |        "    <tr>\n",
 581 |        "      <th>5791</th>\n",
 582 |        "      <td>i6058167</td>\n",
 583 |        "      <td>1</td>\n",
 584 |        "      <td>21795388</td>\n",
 585 |        "      <td>GG</td>\n",
 586 |        "    </tr>\n",
 587 |        "  </tbody>\n",
 588 |        "</table>\n",
 589 |        "</div>"
 590 |       ],
 591 |       "text/plain": [
 592 |        "          rsid chromosome  position genotype\n",
 593 |        "449   i6059967          1   2526746       AA\n",
 594 |        "2816  i6052145          1  11009679       GG\n",
 595 |        "5325  i6012699          1  19992513       CC\n",
 596 |        "5339  i6059797          1  20020994       TT\n",
 597 |        "5791  i6058167          1  21795388       GG"
 598 |       ]
 599 |      },
 600 |      "metadata": {},
 601 |      "output_type": "display_data"
 602 |     },
 603 |     {
 604 |      "name": "stdout",
 605 |      "output_type": "stream",
 606 |      "text": [
 607 |       "<class 'pandas.core.frame.DataFrame'>\n",
 608 |       "Int64Index: 3597 entries, 449 to 638530\n",
 609 |       "Data columns (total 4 columns):\n",
 610 |       " rsid         3597 non-null object\n",
 611 |       "chromosome    3597 non-null object\n",
 612 |       "position      3597 non-null int64\n",
 613 |       "genotype      3597 non-null object\n",
 614 |       "dtypes: int64(1), object(3)\n",
 615 |       "memory usage: 140.5+ KB\n"
 616 |      ]
 617 |     },
 618 |     {
 619 |      "data": {
 620 |       "text/plain": [
 621 |        "None"
 622 |       ]
 623 |      },
 624 |      "metadata": {},
 625 |      "output_type": "display_data"
 626 |     }
 627 |    ],
 628 |    "source": [
 629 |     "duplicates = df[df.duplicated(subset='position')]\n",
 630 |     "display(duplicates.head())\n",
 631 |     "display(duplicates.info())"
 632 |    ]
 633 |   },
 634 |   {
 635 |    "cell_type": "code",
 636 |    "execution_count": 12,
 637 |    "metadata": {},
 638 |    "outputs": [],
 639 |    "source": [
 640 |     "# How many chromosomes am I missing by not having a Y chromosome?\n",
 641 |     "Y_chromosome = df[df.chromosome == 'Y']"
 642 |    ]
 643 |   },
 644 |   {
 645 |    "cell_type": "code",
 646 |    "execution_count": 13,
 647 |    "metadata": {
 648 |     "scrolled": true
 649 |    },
 650 |    "outputs": [
 651 |     {
 652 |      "data": {
 653 |       "text/plain": [
 654 |        "3733"
 655 |       ]
 656 |      },
 657 |      "execution_count": 13,
 658 |      "metadata": {},
 659 |      "output_type": "execute_result"
 660 |     }
 661 |    ],
 662 |    "source": [
 663 |     "len(Y_chromosome)"
 664 |    ]
 665 |   },
 666 |   {
 667 |    "cell_type": "markdown",
 668 |    "metadata": {},
 669 |    "source": [
 670 |     "Since I don't have this chromosome, I'll just drop it from the DataFrame."
 671 |    ]
 672 |   },
 673 |   {
 674 |    "cell_type": "code",
 675 |    "execution_count": 14,
 676 |    "metadata": {},
 677 |    "outputs": [
 678 |     {
 679 |      "name": "stdout",
 680 |      "output_type": "stream",
 681 |      "text": [
 682 |       "<class 'pandas.core.frame.DataFrame'>\n",
 683 |       "Int64Index: 634798 entries, 0 to 638530\n",
 684 |       "Data columns (total 4 columns):\n",
 685 |       " rsid         634798 non-null object\n",
 686 |       "chromosome    634798 non-null object\n",
 687 |       "position      634798 non-null int64\n",
 688 |       "genotype      634798 non-null object\n",
 689 |       "dtypes: int64(1), object(3)\n",
 690 |       "memory usage: 24.2+ MB\n"
 691 |      ]
 692 |     }
 693 |    ],
 694 |    "source": [
 695 |     "df = df[df.chromosome != 'Y']\n",
 696 |     "df.info()"
 697 |    ]
 698 |   },
 699 |   {
 700 |    "cell_type": "markdown",
 701 |    "metadata": {},
 702 |    "source": [
 703 |     "Most of the chromosomes are numeric; only X, Y, and mitochondrial are characters. I'll convert them to numbers, cast them to ints, and create a dictionary to translate back later so that the data will be more manipulable."
 704 |    ]
 705 |   },
 706 |   {
 707 |    "cell_type": "code",
 708 |    "execution_count": 15,
 709 |    "metadata": {
 710 |     "scrolled": true
 711 |    },
 712 |    "outputs": [
 713 |     {
 714 |      "data": {
 715 |       "text/plain": [
 716 |        "array(['1', '2', '3', '4', '5', '6', '7', '8', '9', '10', '11', '12',\n",
 717 |        "       '13', '14', '15', '16', '17', '18', '19', '20', '21', '22', 'X',\n",
 718 |        "       'MT'], dtype=object)"
 719 |       ]
 720 |      },
 721 |      "execution_count": 15,
 722 |      "metadata": {},
 723 |      "output_type": "execute_result"
 724 |     }
 725 |    ],
 726 |    "source": [
 727 |     "df['chromosome'].unique()"
 728 |    ]
 729 |   },
 730 |   {
 731 |    "cell_type": "code",
 732 |    "execution_count": 16,
 733 |    "metadata": {},
 734 |    "outputs": [],
 735 |    "source": [
 736 |     "df['chromosome'] = df['chromosome'].apply(lambda x: re.sub(r'X', r'23', x))\n",
 737 |     "df['chromosome'] = df['chromosome'].apply(lambda x: re.sub(r'MT', r'24', x))"
 738 |    ]
 739 |   },
 740 |   {
 741 |    "cell_type": "code",
 742 |    "execution_count": 17,
 743 |    "metadata": {},
 744 |    "outputs": [],
 745 |    "source": [
 746 |     "df['chromosome'] = df['chromosome'].apply(lambda x: int(x))"
 747 |    ]
 748 |   },
 749 |   {
 750 |    "cell_type": "code",
 751 |    "execution_count": 18,
 752 |    "metadata": {},
 753 |    "outputs": [],
 754 |    "source": [
 755 |     "chromosome_dict = {1:'1', 2:'2', 3:'3', 4:'4', 5:'5', 6:'6', 7:'7', 8:'8', 9:'9', 10:'10', 11:'11', 12:'12', 13:'13', \n",
 756 |     "                  14:'14', 15:'15', 16:'16', 17:'17', 18:'18', 19:'19', 20:'20', 21:'21', 22:'22', 23:'X', 24:'MT'}"
 757 |    ]
 758 |   },
 759 |   {
 760 |    "cell_type": "code",
 761 |    "execution_count": 19,
 762 |    "metadata": {},
 763 |    "outputs": [
 764 |     {
 765 |      "name": "stdout",
 766 |      "output_type": "stream",
 767 |      "text": [
 768 |       "{1: '1', 2: '2', 3: '3', 4: '4', 5: '5', 6: '6', 7: '7', 8: '8', 9: '9', 10: '10', 11: '11', 12: '12', 13: '13', 14: '14', 15: '15', 16: '16', 17: '17', 18: '18', 19: '19', 20: '20', 21: '21', 22: '22', 23: 'X', 24: 'MT'}\n",
 769 |       "<class 'pandas.core.frame.DataFrame'>\n",
 770 |       "Int64Index: 634798 entries, 0 to 638530\n",
 771 |       "Data columns (total 4 columns):\n",
 772 |       " rsid         634798 non-null object\n",
 773 |       "chromosome    634798 non-null int64\n",
 774 |       "position      634798 non-null int64\n",
 775 |       "genotype      634798 non-null object\n",
 776 |       "dtypes: int64(2), object(2)\n",
 777 |       "memory usage: 24.2+ MB\n"
 778 |      ]
 779 |     }
 780 |    ],
 781 |    "source": [
 782 |     "print(chromosome_dict)\n",
 783 |     "df.info()"
 784 |    ]
 785 |   },
 786 |   {
 787 |    "cell_type": "markdown",
 788 |    "metadata": {},
 789 |    "source": [
 790 |     "There are 16,005 genotypes that I simply do not have:"
 791 |    ]
 792 |   },
 793 |   {
 794 |    "cell_type": "code",
 795 |    "execution_count": 20,
 796 |    "metadata": {},
 797 |    "outputs": [
 798 |     {
 799 |      "data": {
 800 |       "text/plain": [
 801 |        "16005"
 802 |       ]
 803 |      },
 804 |      "execution_count": 20,
 805 |      "metadata": {},
 806 |      "output_type": "execute_result"
 807 |     }
 808 |    ],
 809 |    "source": [
 810 |     "genotype_na = df[df.genotype == '--']\n",
 811 |     "len(genotype_na)"
 812 |    ]
 813 |   },
 814 |   {
 815 |    "cell_type": "markdown",
 816 |    "metadata": {},
 817 |    "source": [
 818 |     "### Some visualizations"
 819 |    ]
 820 |   },
 821 |   {
 822 |    "cell_type": "code",
 823 |    "execution_count": 21,
 824 |    "metadata": {
 825 |     "scrolled": true
 826 |    },
 827 |    "outputs": [
 828 |     {
 829 |      "name": "stdout",
 830 |      "output_type": "stream",
 831 |      "text": [
 832 |       "<class 'pandas.core.frame.DataFrame'>\n",
 833 |       "Int64Index: 49514 entries, 0 to 49513\n",
 834 |       "Data columns (total 4 columns):\n",
 835 |       " rsid         49514 non-null object\n",
 836 |       "chromosome    49514 non-null int64\n",
 837 |       "position      49514 non-null int64\n",
 838 |       "genotype      49514 non-null object\n",
 839 |       "dtypes: int64(2), object(2)\n",
 840 |       "memory usage: 1.9+ MB\n"
 841 |      ]
 842 |     }
 843 |    ],
 844 |    "source": [
 845 |     "df[df.chromosome == 1].info()"
 846 |    ]
 847 |   },
 848 |   {
 849 |    "cell_type": "code",
 850 |    "execution_count": 22,
 851 |    "metadata": {},
 852 |    "outputs": [],
 853 |    "source": [
 854 |     "# Remove that pesky whitespace from the column name\n",
 855 |     "df.rename({' rsid': 'rsid'}, axis='columns', inplace=True)"
 856 |    ]
 857 |   },
 858 |   {
 859 |    "cell_type": "markdown",
 860 |    "metadata": {},
 861 |    "source": [
 862 |     "How many SNPs are there per chromosome?"
 863 |    ]
 864 |   },
 865 |   {
 866 |    "cell_type": "code",
 867 |    "execution_count": 23,
 868 |    "metadata": {},
 869 |    "outputs": [],
 870 |    "source": [
 871 |     "# We can do this manually with a for loop . . .\n",
 872 |     "x = []\n",
 873 |     "y = []\n",
 874 |     "for k in chromosome_dict:\n",
 875 |     "    x.append(k)\n",
 876 |     "    y.append(len(df[df.chromosome == k]))\n",
 877 |     "rsid_per_chromosome = dict(zip(x,y)) "
 878 |    ]
 879 |   },
 880 |   {
 881 |    "cell_type": "code",
 882 |    "execution_count": 24,
 883 |    "metadata": {
 884 |     "scrolled": false
 885 |    },
 886 |    "outputs": [
 887 |     {
 888 |      "data": {
 889 |       "text/plain": [
 890 |        "{1: 49514,\n",
 891 |        " 2: 51775,\n",
 892 |        " 3: 43024,\n",
 893 |        " 4: 39474,\n",
 894 |        " 5: 37032,\n",
 895 |        " 6: 44023,\n",
 896 |        " 7: 34357,\n",
 897 |        " 8: 31683,\n",
 898 |        " 9: 26446,\n",
 899 |        " 10: 30525,\n",
 900 |        " 11: 30942,\n",
 901 |        " 12: 29432,\n",
 902 |        " 13: 22080,\n",
 903 |        " 14: 19961,\n",
 904 |        " 15: 19006,\n",
 905 |        " 16: 20397,\n",
 906 |        " 17: 19401,\n",
 907 |        " 18: 17675,\n",
 908 |        " 19: 14917,\n",
 909 |        " 20: 14781,\n",
 910 |        " 21: 8607,\n",
 911 |        " 22: 8915,\n",
 912 |        " 23: 16530,\n",
 913 |        " 24: 4301}"
 914 |       ]
 915 |      },
 916 |      "execution_count": 24,
 917 |      "metadata": {},
 918 |      "output_type": "execute_result"
 919 |     }
 920 |    ],
 921 |    "source": [
 922 |     "rsid_per_chromosome"
 923 |    ]
 924 |   },
 925 |   {
 926 |    "cell_type": "code",
 927 |    "execution_count": 25,
 928 |    "metadata": {},
 929 |    "outputs": [],
 930 |    "source": [
 931 |     "# . . . but pandas makes it a lot easier!\n",
 932 |     "rsid_per_chromosome_series = df.groupby('chromosome')['rsid'].count()\n",
 933 |     "rsid_per_chromosome_series.columns = ['chromosome', 'count']"
 934 |    ]
 935 |   },
 936 |   {
 937 |    "cell_type": "code",
 938 |    "execution_count": 26,
 939 |    "metadata": {},
 940 |    "outputs": [
 941 |     {
 942 |      "data": {
 943 |       "image/png": "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\n",
 944 |       "text/plain": [
 945 |        "<Figure size 1152x648 with 1 Axes>"
 946 |       ]
 947 |      },
 948 |      "metadata": {
 949 |       "needs_background": "light"
 950 |      },
 951 |      "output_type": "display_data"
 952 |     }
 953 |    ],
 954 |    "source": [
 955 |     "rsid_per_chromosome_series.plot.barh(figsize=(16,9), fontsize=15)\n",
 956 |     "plt.show()"
 957 |    ]
 958 |   },
 959 |   {
 960 |    "cell_type": "markdown",
 961 |    "metadata": {},
 962 |    "source": [
 963 |     "## Getting data on SNPs from SNPedia\n",
 964 |     "\n",
 965 |     "To get some more info about my DNA, I pulled some information on clinically significant SNPs from SNPedia.\n",
 966 |     "\n",
 967 |     "The columns are:\n",
 968 |     "\n",
 969 |     "* Unnamed: 0 (actually the SNP name)\n",
 970 |     "* Magnitude (a subjective measure of interest)\n",
 971 |     "* Repute (a subjective measure of whether the genotype is \"good\" or \"bad\" to have based on research, and blank for things like ancestry and eye color)\n",
 972 |     "* Summary (a narrative description)"
 973 |    ]
 974 |   },
 975 |   {
 976 |    "cell_type": "code",
 977 |    "execution_count": 27,
 978 |    "metadata": {},
 979 |    "outputs": [
 980 |     {
 981 |      "data": {
 982 |       "text/html": [
 983 |        "<div>\n",
 984 |        "<style scoped>\n",
 985 |        "    .dataframe tbody tr th:only-of-type {\n",
 986 |        "        vertical-align: middle;\n",
 987 |        "    }\n",
 988 |        "\n",
 989 |        "    .dataframe tbody tr th {\n",
 990 |        "        vertical-align: top;\n",
 991 |        "    }\n",
 992 |        "\n",
 993 |        "    .dataframe thead th {\n",
 994 |        "        text-align: right;\n",
 995 |        "    }\n",
 996 |        "</style>\n",
 997 |        "<table border=\"1\" class=\"dataframe\">\n",
 998 |        "  <thead>\n",
 999 |        "    <tr style=\"text-align: right;\">\n",
1000 |        "      <th></th>\n",
1001 |        "      <th>Unnamed: 0</th>\n",
1002 |        "      <th>Magnitude</th>\n",
1003 |        "      <th>Repute</th>\n",
1004 |        "      <th>Summary</th>\n",
1005 |        "    </tr>\n",
1006 |        "  </thead>\n",
1007 |        "  <tbody>\n",
1008 |        "    <tr>\n",
1009 |        "      <th>0</th>\n",
1010 |        "      <td>Rs661(A;A)</td>\n",
1011 |        "      <td>9.0</td>\n",
1012 |        "      <td>Bad</td>\n",
1013 |        "      <td>early onset Alzheimer's disease</td>\n",
1014 |        "    </tr>\n",
1015 |        "    <tr>\n",
1016 |        "      <th>1</th>\n",
1017 |        "      <td>Rs6647(T;T)</td>\n",
1018 |        "      <td>0.0</td>\n",
1019 |        "      <td>Good</td>\n",
1020 |        "      <td>Normal; two copies of Pi-M1V allele</td>\n",
1021 |        "    </tr>\n",
1022 |        "    <tr>\n",
1023 |        "      <th>2</th>\n",
1024 |        "      <td>Rs6647(C;C)</td>\n",
1025 |        "      <td>0.0</td>\n",
1026 |        "      <td>Good</td>\n",
1027 |        "      <td>Normal; two copies of Pi-M1A allele</td>\n",
1028 |        "    </tr>\n",
1029 |        "    <tr>\n",
1030 |        "      <th>3</th>\n",
1031 |        "      <td>Rs1303(T;T)</td>\n",
1032 |        "      <td>0.0</td>\n",
1033 |        "      <td>Good</td>\n",
1034 |        "      <td>common in clinvar</td>\n",
1035 |        "    </tr>\n",
1036 |        "    <tr>\n",
1037 |        "      <th>4</th>\n",
1038 |        "      <td>Rs28929471(G;G)</td>\n",
1039 |        "      <td>0.0</td>\n",
1040 |        "      <td>Good</td>\n",
1041 |        "      <td>common in complete genomics</td>\n",
1042 |        "    </tr>\n",
1043 |        "  </tbody>\n",
1044 |        "</table>\n",
1045 |        "</div>"
1046 |       ],
1047 |       "text/plain": [
1048 |        "        Unnamed: 0  Magnitude Repute                              Summary\n",
1049 |        "0       Rs661(A;A)        9.0    Bad      early onset Alzheimer's disease\n",
1050 |        "1      Rs6647(T;T)        0.0   Good  Normal; two copies of Pi-M1V allele\n",
1051 |        "2      Rs6647(C;C)        0.0   Good  Normal; two copies of Pi-M1A allele\n",
1052 |        "3      Rs1303(T;T)        0.0   Good                    common in clinvar\n",
1053 |        "4  Rs28929471(G;G)        0.0   Good          common in complete genomics"
1054 |       ]
1055 |      },
1056 |      "execution_count": 27,
1057 |      "metadata": {},
1058 |      "output_type": "execute_result"
1059 |     }
1060 |    ],
1061 |    "source": [
1062 |     "snp_df = pd.read_csv('result.csv')\n",
1063 |     "snp_df.head()"
1064 |    ]
1065 |   },
1066 |   {
1067 |    "cell_type": "markdown",
1068 |    "metadata": {},
1069 |    "source": [
1070 |     "To match up with my original DataFrame, I'll create a genotype column and use regex to separate out the genotype, which is tacked onto the end of the SNP."
1071 |    ]
1072 |   },
1073 |   {
1074 |    "cell_type": "code",
1075 |    "execution_count": 28,
1076 |    "metadata": {},
1077 |    "outputs": [],
1078 |    "source": [
1079 |     "snp_df['genotype'] = snp_df['Unnamed: 0'].apply(lambda x: re.sub(r'.*([AGCT]);([AGCT])\\)', r'\\1\\2', x))"
1080 |    ]
1081 |   },
1082 |   {
1083 |    "cell_type": "code",
1084 |    "execution_count": 29,
1085 |    "metadata": {},
1086 |    "outputs": [
1087 |     {
1088 |      "data": {
1089 |       "text/html": [
1090 |        "<div>\n",
1091 |        "<style scoped>\n",
1092 |        "    .dataframe tbody tr th:only-of-type {\n",
1093 |        "        vertical-align: middle;\n",
1094 |        "    }\n",
1095 |        "\n",
1096 |        "    .dataframe tbody tr th {\n",
1097 |        "        vertical-align: top;\n",
1098 |        "    }\n",
1099 |        "\n",
1100 |        "    .dataframe thead th {\n",
1101 |        "        text-align: right;\n",
1102 |        "    }\n",
1103 |        "</style>\n",
1104 |        "<table border=\"1\" class=\"dataframe\">\n",
1105 |        "  <thead>\n",
1106 |        "    <tr style=\"text-align: right;\">\n",
1107 |        "      <th></th>\n",
1108 |        "      <th>Unnamed: 0</th>\n",
1109 |        "      <th>Magnitude</th>\n",
1110 |        "      <th>Repute</th>\n",
1111 |        "      <th>Summary</th>\n",
1112 |        "      <th>genotype</th>\n",
1113 |        "    </tr>\n",
1114 |        "  </thead>\n",
1115 |        "  <tbody>\n",
1116 |        "    <tr>\n",
1117 |        "      <th>0</th>\n",
1118 |        "      <td>Rs661(A;A)</td>\n",
1119 |        "      <td>9.0</td>\n",
1120 |        "      <td>Bad</td>\n",
1121 |        "      <td>early onset Alzheimer's disease</td>\n",
1122 |        "      <td>AA</td>\n",
1123 |        "    </tr>\n",
1124 |        "    <tr>\n",
1125 |        "      <th>1</th>\n",
1126 |        "      <td>Rs6647(T;T)</td>\n",
1127 |        "      <td>0.0</td>\n",
1128 |        "      <td>Good</td>\n",
1129 |        "      <td>Normal; two copies of Pi-M1V allele</td>\n",
1130 |        "      <td>TT</td>\n",
1131 |        "    </tr>\n",
1132 |        "    <tr>\n",
1133 |        "      <th>2</th>\n",
1134 |        "      <td>Rs6647(C;C)</td>\n",
1135 |        "      <td>0.0</td>\n",
1136 |        "      <td>Good</td>\n",
1137 |        "      <td>Normal; two copies of Pi-M1A allele</td>\n",
1138 |        "      <td>CC</td>\n",
1139 |        "    </tr>\n",
1140 |        "    <tr>\n",
1141 |        "      <th>3</th>\n",
1142 |        "      <td>Rs1303(T;T)</td>\n",
1143 |        "      <td>0.0</td>\n",
1144 |        "      <td>Good</td>\n",
1145 |        "      <td>common in clinvar</td>\n",
1146 |        "      <td>TT</td>\n",
1147 |        "    </tr>\n",
1148 |        "    <tr>\n",
1149 |        "      <th>4</th>\n",
1150 |        "      <td>Rs28929471(G;G)</td>\n",
1151 |        "      <td>0.0</td>\n",
1152 |        "      <td>Good</td>\n",
1153 |        "      <td>common in complete genomics</td>\n",
1154 |        "      <td>GG</td>\n",
1155 |        "    </tr>\n",
1156 |        "  </tbody>\n",
1157 |        "</table>\n",
1158 |        "</div>"
1159 |       ],
1160 |       "text/plain": [
1161 |        "        Unnamed: 0  Magnitude Repute                              Summary  \\\n",
1162 |        "0       Rs661(A;A)        9.0    Bad      early onset Alzheimer's disease   \n",
1163 |        "1      Rs6647(T;T)        0.0   Good  Normal; two copies of Pi-M1V allele   \n",
1164 |        "2      Rs6647(C;C)        0.0   Good  Normal; two copies of Pi-M1A allele   \n",
1165 |        "3      Rs1303(T;T)        0.0   Good                    common in clinvar   \n",
1166 |        "4  Rs28929471(G;G)        0.0   Good          common in complete genomics   \n",
1167 |        "\n",
1168 |        "  genotype  \n",
1169 |        "0       AA  \n",
1170 |        "1       TT  \n",
1171 |        "2       CC  \n",
1172 |        "3       TT  \n",
1173 |        "4       GG  "
1174 |       ]
1175 |      },
1176 |      "execution_count": 29,
1177 |      "metadata": {},
1178 |      "output_type": "execute_result"
1179 |     }
1180 |    ],
1181 |    "source": [
1182 |     "snp_df.head()"
1183 |    ]
1184 |   },
1185 |   {
1186 |    "cell_type": "markdown",
1187 |    "metadata": {},
1188 |    "source": [
1189 |     "For consistency's sake, I renamed the columns to match my original DataFrame and made sure the rsids were all lower-case."
1190 |    ]
1191 |   },
1192 |   {
1193 |    "cell_type": "code",
1194 |    "execution_count": 30,
1195 |    "metadata": {},
1196 |    "outputs": [],
1197 |    "source": [
1198 |     "new_cols = ['rsid', 'magnitude', 'repute', 'summary', 'genotype']\n",
1199 |     "snp_df.columns = new_cols"
1200 |    ]
1201 |   },
1202 |   {
1203 |    "cell_type": "markdown",
1204 |    "metadata": {},
1205 |    "source": [
1206 |     "I'll use regex to clean up the rsid a little more, too."
1207 |    ]
1208 |   },
1209 |   {
1210 |    "cell_type": "code",
1211 |    "execution_count": 31,
1212 |    "metadata": {},
1213 |    "outputs": [],
1214 |    "source": [
1215 |     "snp_df['rsid'] = snp_df['rsid'].map(lambda x : x.lower())\n",
1216 |     "snp_df['rsid'] = snp_df['rsid'].map(lambda x : re.sub(r'([a-z]{1,}[\\d]+)\\([agct];[agct]\\)', r'\\1', x))"
1217 |    ]
1218 |   },
1219 |   {
1220 |    "cell_type": "code",
1221 |    "execution_count": 32,
1222 |    "metadata": {
1223 |     "scrolled": false
1224 |    },
1225 |    "outputs": [
1226 |     {
1227 |      "data": {
1228 |       "text/html": [
1229 |        "<div>\n",
1230 |        "<style scoped>\n",
1231 |        "    .dataframe tbody tr th:only-of-type {\n",
1232 |        "        vertical-align: middle;\n",
1233 |        "    }\n",
1234 |        "\n",
1235 |        "    .dataframe tbody tr th {\n",
1236 |        "        vertical-align: top;\n",
1237 |        "    }\n",
1238 |        "\n",
1239 |        "    .dataframe thead th {\n",
1240 |        "        text-align: right;\n",
1241 |        "    }\n",
1242 |        "</style>\n",
1243 |        "<table border=\"1\" class=\"dataframe\">\n",
1244 |        "  <thead>\n",
1245 |        "    <tr style=\"text-align: right;\">\n",
1246 |        "      <th></th>\n",
1247 |        "      <th>rsid</th>\n",
1248 |        "      <th>magnitude</th>\n",
1249 |        "      <th>repute</th>\n",
1250 |        "      <th>summary</th>\n",
1251 |        "      <th>genotype</th>\n",
1252 |        "    </tr>\n",
1253 |        "  </thead>\n",
1254 |        "  <tbody>\n",
1255 |        "    <tr>\n",
1256 |        "      <th>0</th>\n",
1257 |        "      <td>rs661</td>\n",
1258 |        "      <td>9.0</td>\n",
1259 |        "      <td>Bad</td>\n",
1260 |        "      <td>early onset Alzheimer's disease</td>\n",
1261 |        "      <td>AA</td>\n",
1262 |        "    </tr>\n",
1263 |        "    <tr>\n",
1264 |        "      <th>1</th>\n",
1265 |        "      <td>rs6647</td>\n",
1266 |        "      <td>0.0</td>\n",
1267 |        "      <td>Good</td>\n",
1268 |        "      <td>Normal; two copies of Pi-M1V allele</td>\n",
1269 |        "      <td>TT</td>\n",
1270 |        "    </tr>\n",
1271 |        "    <tr>\n",
1272 |        "      <th>2</th>\n",
1273 |        "      <td>rs6647</td>\n",
1274 |        "      <td>0.0</td>\n",
1275 |        "      <td>Good</td>\n",
1276 |        "      <td>Normal; two copies of Pi-M1A allele</td>\n",
1277 |        "      <td>CC</td>\n",
1278 |        "    </tr>\n",
1279 |        "    <tr>\n",
1280 |        "      <th>3</th>\n",
1281 |        "      <td>rs1303</td>\n",
1282 |        "      <td>0.0</td>\n",
1283 |        "      <td>Good</td>\n",
1284 |        "      <td>common in clinvar</td>\n",
1285 |        "      <td>TT</td>\n",
1286 |        "    </tr>\n",
1287 |        "    <tr>\n",
1288 |        "      <th>4</th>\n",
1289 |        "      <td>rs28929471</td>\n",
1290 |        "      <td>0.0</td>\n",
1291 |        "      <td>Good</td>\n",
1292 |        "      <td>common in complete genomics</td>\n",
1293 |        "      <td>GG</td>\n",
1294 |        "    </tr>\n",
1295 |        "  </tbody>\n",
1296 |        "</table>\n",
1297 |        "</div>"
1298 |       ],
1299 |       "text/plain": [
1300 |        "         rsid  magnitude repute                              summary genotype\n",
1301 |        "0       rs661        9.0    Bad      early onset Alzheimer's disease       AA\n",
1302 |        "1      rs6647        0.0   Good  Normal; two copies of Pi-M1V allele       TT\n",
1303 |        "2      rs6647        0.0   Good  Normal; two copies of Pi-M1A allele       CC\n",
1304 |        "3      rs1303        0.0   Good                    common in clinvar       TT\n",
1305 |        "4  rs28929471        0.0   Good          common in complete genomics       GG"
1306 |       ]
1307 |      },
1308 |      "execution_count": 32,
1309 |      "metadata": {},
1310 |      "output_type": "execute_result"
1311 |     }
1312 |    ],
1313 |    "source": [
1314 |     "snp_df.head()"
1315 |    ]
1316 |   },
1317 |   {
1318 |    "cell_type": "code",
1319 |    "execution_count": 33,
1320 |    "metadata": {
1321 |     "scrolled": true
1322 |    },
1323 |    "outputs": [
1324 |     {
1325 |      "name": "stdout",
1326 |      "output_type": "stream",
1327 |      "text": [
1328 |       "<class 'pandas.core.frame.DataFrame'>\n",
1329 |       "RangeIndex: 100 entries, 0 to 99\n",
1330 |       "Data columns (total 5 columns):\n",
1331 |       "rsid         100 non-null object\n",
1332 |       "magnitude    100 non-null float64\n",
1333 |       "repute       91 non-null object\n",
1334 |       "summary      96 non-null object\n",
1335 |       "genotype     100 non-null object\n",
1336 |       "dtypes: float64(1), object(4)\n",
1337 |       "memory usage: 4.0+ KB\n"
1338 |      ]
1339 |     }
1340 |    ],
1341 |    "source": [
1342 |     "snp_df.info()"
1343 |    ]
1344 |   },
1345 |   {
1346 |    "cell_type": "markdown",
1347 |    "metadata": {},
1348 |    "source": [
1349 |     "Let's see what's going on with the null reputes and summaries and overwrite them if it's appropriate. (In this case, the answer seems to be yes.)"
1350 |    ]
1351 |   },
1352 |   {
1353 |    "cell_type": "code",
1354 |    "execution_count": 34,
1355 |    "metadata": {},
1356 |    "outputs": [
1357 |     {
1358 |      "data": {
1359 |       "text/html": [
1360 |        "<div>\n",
1361 |        "<style scoped>\n",
1362 |        "    .dataframe tbody tr th:only-of-type {\n",
1363 |        "        vertical-align: middle;\n",
1364 |        "    }\n",
1365 |        "\n",
1366 |        "    .dataframe tbody tr th {\n",
1367 |        "        vertical-align: top;\n",
1368 |        "    }\n",
1369 |        "\n",
1370 |        "    .dataframe thead th {\n",
1371 |        "        text-align: right;\n",
1372 |        "    }\n",
1373 |        "</style>\n",
1374 |        "<table border=\"1\" class=\"dataframe\">\n",
1375 |        "  <thead>\n",
1376 |        "    <tr style=\"text-align: right;\">\n",
1377 |        "      <th></th>\n",
1378 |        "      <th>rsid</th>\n",
1379 |        "      <th>magnitude</th>\n",
1380 |        "      <th>repute</th>\n",
1381 |        "      <th>summary</th>\n",
1382 |        "      <th>genotype</th>\n",
1383 |        "    </tr>\n",
1384 |        "  </thead>\n",
1385 |        "  <tbody>\n",
1386 |        "    <tr>\n",
1387 |        "      <th>0</th>\n",
1388 |        "      <td>rs28931569</td>\n",
1389 |        "      <td>4.0</td>\n",
1390 |        "      <td>NaN</td>\n",
1391 |        "      <td>high risk of emphysema</td>\n",
1392 |        "      <td>CC</td>\n",
1393 |        "    </tr>\n",
1394 |        "    <tr>\n",
1395 |        "      <th>1</th>\n",
1396 |        "      <td>rs28929473</td>\n",
1397 |        "      <td>0.0</td>\n",
1398 |        "      <td>NaN</td>\n",
1399 |        "      <td>NaN</td>\n",
1400 |        "      <td>TT</td>\n",
1401 |        "    </tr>\n",
1402 |        "    <tr>\n",
1403 |        "      <th>2</th>\n",
1404 |        "      <td>rs28931572</td>\n",
1405 |        "      <td>0.0</td>\n",
1406 |        "      <td>NaN</td>\n",
1407 |        "      <td>NaN</td>\n",
1408 |        "      <td>AA</td>\n",
1409 |        "    </tr>\n",
1410 |        "    <tr>\n",
1411 |        "      <th>3</th>\n",
1412 |        "      <td>rs1801252</td>\n",
1413 |        "      <td>3.0</td>\n",
1414 |        "      <td>NaN</td>\n",
1415 |        "      <td>NaN</td>\n",
1416 |        "      <td>GG</td>\n",
1417 |        "    </tr>\n",
1418 |        "    <tr>\n",
1419 |        "      <th>4</th>\n",
1420 |        "      <td>rs8192466</td>\n",
1421 |        "      <td>4.0</td>\n",
1422 |        "      <td>NaN</td>\n",
1423 |        "      <td>uncertain</td>\n",
1424 |        "      <td>TT</td>\n",
1425 |        "    </tr>\n",
1426 |        "    <tr>\n",
1427 |        "      <th>5</th>\n",
1428 |        "      <td>rs4986852</td>\n",
1429 |        "      <td>2.0</td>\n",
1430 |        "      <td>NaN</td>\n",
1431 |        "      <td>predisposition to breast cancer?</td>\n",
1432 |        "      <td>AA</td>\n",
1433 |        "    </tr>\n",
1434 |        "    <tr>\n",
1435 |        "      <th>6</th>\n",
1436 |        "      <td>rs1800709</td>\n",
1437 |        "      <td>2.0</td>\n",
1438 |        "      <td>NaN</td>\n",
1439 |        "      <td>predisposition to breast cancer?</td>\n",
1440 |        "      <td>TT</td>\n",
1441 |        "    </tr>\n",
1442 |        "    <tr>\n",
1443 |        "      <th>7</th>\n",
1444 |        "      <td>rs28931592</td>\n",
1445 |        "      <td>0.0</td>\n",
1446 |        "      <td>NaN</td>\n",
1447 |        "      <td>NaN</td>\n",
1448 |        "      <td>TT</td>\n",
1449 |        "    </tr>\n",
1450 |        "    <tr>\n",
1451 |        "      <th>8</th>\n",
1452 |        "      <td>rs4986893</td>\n",
1453 |        "      <td>2.1</td>\n",
1454 |        "      <td>NaN</td>\n",
1455 |        "      <td>poor metabolizer of several commonly prescribe...</td>\n",
1456 |        "      <td>AA</td>\n",
1457 |        "    </tr>\n",
1458 |        "  </tbody>\n",
1459 |        "</table>\n",
1460 |        "</div>"
1461 |       ],
1462 |       "text/plain": [
1463 |        "         rsid  magnitude repute  \\\n",
1464 |        "0  rs28931569        4.0    NaN   \n",
1465 |        "1  rs28929473        0.0    NaN   \n",
1466 |        "2  rs28931572        0.0    NaN   \n",
1467 |        "3   rs1801252        3.0    NaN   \n",
1468 |        "4   rs8192466        4.0    NaN   \n",
1469 |        "5   rs4986852        2.0    NaN   \n",
1470 |        "6   rs1800709        2.0    NaN   \n",
1471 |        "7  rs28931592        0.0    NaN   \n",
1472 |        "8   rs4986893        2.1    NaN   \n",
1473 |        "\n",
1474 |        "                                             summary genotype  \n",
1475 |        "0                             high risk of emphysema       CC  \n",
1476 |        "1                                                NaN       TT  \n",
1477 |        "2                                                NaN       AA  \n",
1478 |        "3                                                NaN       GG  \n",
1479 |        "4                                          uncertain       TT  \n",
1480 |        "5                   predisposition to breast cancer?       AA  \n",
1481 |        "6                   predisposition to breast cancer?       TT  \n",
1482 |        "7                                                NaN       TT  \n",
1483 |        "8  poor metabolizer of several commonly prescribe...       AA  "
1484 |       ]
1485 |      },
1486 |      "metadata": {},
1487 |      "output_type": "display_data"
1488 |     }
1489 |    ],
1490 |    "source": [
1491 |     "null_repute = snp_df[snp_df['repute'].isnull()]\n",
1492 |     "null_summaries = snp_df[snp_df['summary'].isnull()]\n",
1493 |     "null_repute_and_summaries = pd.concat([null_repute,null_summaries]).drop_duplicates().reset_index(drop=True)\n",
1494 |     "display(null_repute_and_summaries)"
1495 |    ]
1496 |   },
1497 |   {
1498 |    "cell_type": "code",
1499 |    "execution_count": 35,
1500 |    "metadata": {},
1501 |    "outputs": [],
1502 |    "source": [
1503 |     "snp_df['repute'].fillna(value='Neutral', inplace=True)\n",
1504 |     "snp_df['summary'].fillna(value='None', inplace=True)"
1505 |    ]
1506 |   },
1507 |   {
1508 |    "cell_type": "code",
1509 |    "execution_count": 36,
1510 |    "metadata": {},
1511 |    "outputs": [
1512 |     {
1513 |      "data": {
1514 |       "text/plain": [
1515 |        "rsid         False\n",
1516 |        "magnitude    False\n",
1517 |        "repute       False\n",
1518 |        "summary      False\n",
1519 |        "genotype     False\n",
1520 |        "dtype: bool"
1521 |       ]
1522 |      },
1523 |      "execution_count": 36,
1524 |      "metadata": {},
1525 |      "output_type": "execute_result"
1526 |     }
1527 |    ],
1528 |    "source": [
1529 |     "# No no NaNette\n",
1530 |     "snp_df.isna().any()"
1531 |    ]
1532 |   },
1533 |   {
1534 |    "cell_type": "markdown",
1535 |    "metadata": {},
1536 |    "source": [
1537 |     "# Merging my data with SNPedia\n",
1538 |     "\n",
1539 |     "Here, I've done an inner join of the SNPedia DataFrame on my DNA to see what data, if any, it has on my particular genotypes."
1540 |    ]
1541 |   },
1542 |   {
1543 |    "cell_type": "code",
1544 |    "execution_count": 37,
1545 |    "metadata": {},
1546 |    "outputs": [],
1547 |    "source": [
1548 |     "new_df = snp_df.merge(df, how='inner', on=['rsid', 'genotype'], suffixes=('_SNPedia', '_myDNA'))"
1549 |    ]
1550 |   },
1551 |   {
1552 |    "cell_type": "code",
1553 |    "execution_count": 38,
1554 |    "metadata": {},
1555 |    "outputs": [
1556 |     {
1557 |      "data": {
1558 |       "text/html": [
1559 |        "<div>\n",
1560 |        "<style scoped>\n",
1561 |        "    .dataframe tbody tr th:only-of-type {\n",
1562 |        "        vertical-align: middle;\n",
1563 |        "    }\n",
1564 |        "\n",
1565 |        "    .dataframe tbody tr th {\n",
1566 |        "        vertical-align: top;\n",
1567 |        "    }\n",
1568 |        "\n",
1569 |        "    .dataframe thead th {\n",
1570 |        "        text-align: right;\n",
1571 |        "    }\n",
1572 |        "</style>\n",
1573 |        "<table border=\"1\" class=\"dataframe\">\n",
1574 |        "  <thead>\n",
1575 |        "    <tr style=\"text-align: right;\">\n",
1576 |        "      <th></th>\n",
1577 |        "      <th>rsid</th>\n",
1578 |        "      <th>magnitude</th>\n",
1579 |        "      <th>repute</th>\n",
1580 |        "      <th>summary</th>\n",
1581 |        "      <th>genotype</th>\n",
1582 |        "      <th>chromosome</th>\n",
1583 |        "      <th>position</th>\n",
1584 |        "    </tr>\n",
1585 |        "  </thead>\n",
1586 |        "  <tbody>\n",
1587 |        "    <tr>\n",
1588 |        "      <th>0</th>\n",
1589 |        "      <td>rs1303</td>\n",
1590 |        "      <td>0.0</td>\n",
1591 |        "      <td>Good</td>\n",
1592 |        "      <td>common in clinvar</td>\n",
1593 |        "      <td>TT</td>\n",
1594 |        "      <td>14</td>\n",
1595 |        "      <td>94844843</td>\n",
1596 |        "    </tr>\n",
1597 |        "    <tr>\n",
1598 |        "      <th>1</th>\n",
1599 |        "      <td>rs17580</td>\n",
1600 |        "      <td>2.5</td>\n",
1601 |        "      <td>Bad</td>\n",
1602 |        "      <td>a slightly reduced functionality form of Alpha...</td>\n",
1603 |        "      <td>TT</td>\n",
1604 |        "      <td>14</td>\n",
1605 |        "      <td>94847262</td>\n",
1606 |        "    </tr>\n",
1607 |        "    <tr>\n",
1608 |        "      <th>2</th>\n",
1609 |        "      <td>rs28931580</td>\n",
1610 |        "      <td>0.0</td>\n",
1611 |        "      <td>Good</td>\n",
1612 |        "      <td>common in clinvar</td>\n",
1613 |        "      <td>AA</td>\n",
1614 |        "      <td>12</td>\n",
1615 |        "      <td>50344783</td>\n",
1616 |        "    </tr>\n",
1617 |        "    <tr>\n",
1618 |        "      <th>3</th>\n",
1619 |        "      <td>rs1042714</td>\n",
1620 |        "      <td>0.0</td>\n",
1621 |        "      <td>Good</td>\n",
1622 |        "      <td>normal</td>\n",
1623 |        "      <td>CC</td>\n",
1624 |        "      <td>5</td>\n",
1625 |        "      <td>148206473</td>\n",
1626 |        "    </tr>\n",
1627 |        "    <tr>\n",
1628 |        "      <th>4</th>\n",
1629 |        "      <td>rs1800888</td>\n",
1630 |        "      <td>0.0</td>\n",
1631 |        "      <td>Good</td>\n",
1632 |        "      <td>normal</td>\n",
1633 |        "      <td>CC</td>\n",
1634 |        "      <td>5</td>\n",
1635 |        "      <td>148206885</td>\n",
1636 |        "    </tr>\n",
1637 |        "    <tr>\n",
1638 |        "      <th>5</th>\n",
1639 |        "      <td>rs2303790</td>\n",
1640 |        "      <td>0.0</td>\n",
1641 |        "      <td>Good</td>\n",
1642 |        "      <td>common in clinvar</td>\n",
1643 |        "      <td>AA</td>\n",
1644 |        "      <td>16</td>\n",
1645 |        "      <td>57017292</td>\n",
1646 |        "    </tr>\n",
1647 |        "    <tr>\n",
1648 |        "      <th>6</th>\n",
1649 |        "      <td>rs5882</td>\n",
1650 |        "      <td>2.0</td>\n",
1651 |        "      <td>Bad</td>\n",
1652 |        "      <td>Faster aging. Increased risk for Dementia. Les...</td>\n",
1653 |        "      <td>AA</td>\n",
1654 |        "      <td>16</td>\n",
1655 |        "      <td>57016092</td>\n",
1656 |        "    </tr>\n",
1657 |        "    <tr>\n",
1658 |        "      <th>7</th>\n",
1659 |        "      <td>rs2230199</td>\n",
1660 |        "      <td>2.0</td>\n",
1661 |        "      <td>Bad</td>\n",
1662 |        "      <td>2.5x+ risk of ARMD</td>\n",
1663 |        "      <td>GG</td>\n",
1664 |        "      <td>19</td>\n",
1665 |        "      <td>6718387</td>\n",
1666 |        "    </tr>\n",
1667 |        "    <tr>\n",
1668 |        "      <th>8</th>\n",
1669 |        "      <td>rs28931608</td>\n",
1670 |        "      <td>0.0</td>\n",
1671 |        "      <td>Good</td>\n",
1672 |        "      <td>common in clinvar</td>\n",
1673 |        "      <td>GG</td>\n",
1674 |        "      <td>7</td>\n",
1675 |        "      <td>75614497</td>\n",
1676 |        "    </tr>\n",
1677 |        "    <tr>\n",
1678 |        "      <th>9</th>\n",
1679 |        "      <td>rs4986893</td>\n",
1680 |        "      <td>0.0</td>\n",
1681 |        "      <td>Good</td>\n",
1682 |        "      <td>normal</td>\n",
1683 |        "      <td>GG</td>\n",
1684 |        "      <td>10</td>\n",
1685 |        "      <td>96540410</td>\n",
1686 |        "    </tr>\n",
1687 |        "    <tr>\n",
1688 |        "      <th>10</th>\n",
1689 |        "      <td>rs28399504</td>\n",
1690 |        "      <td>0.0</td>\n",
1691 |        "      <td>Good</td>\n",
1692 |        "      <td>normal</td>\n",
1693 |        "      <td>AA</td>\n",
1694 |        "      <td>10</td>\n",
1695 |        "      <td>96522463</td>\n",
1696 |        "    </tr>\n",
1697 |        "    <tr>\n",
1698 |        "      <th>11</th>\n",
1699 |        "      <td>rs2234922</td>\n",
1700 |        "      <td>0.0</td>\n",
1701 |        "      <td>Good</td>\n",
1702 |        "      <td>common in clinvar</td>\n",
1703 |        "      <td>AA</td>\n",
1704 |        "      <td>1</td>\n",
1705 |        "      <td>226026406</td>\n",
1706 |        "    </tr>\n",
1707 |        "    <tr>\n",
1708 |        "      <th>12</th>\n",
1709 |        "      <td>rs28931614</td>\n",
1710 |        "      <td>0.0</td>\n",
1711 |        "      <td>Good</td>\n",
1712 |        "      <td>common in clinvar</td>\n",
1713 |        "      <td>GG</td>\n",
1714 |        "      <td>4</td>\n",
1715 |        "      <td>1806119</td>\n",
1716 |        "    </tr>\n",
1717 |        "    <tr>\n",
1718 |        "      <th>13</th>\n",
1719 |        "      <td>rs28933068</td>\n",
1720 |        "      <td>0.0</td>\n",
1721 |        "      <td>Good</td>\n",
1722 |        "      <td>common in clinvar</td>\n",
1723 |        "      <td>CC</td>\n",
1724 |        "      <td>4</td>\n",
1725 |        "      <td>1807371</td>\n",
1726 |        "    </tr>\n",
1727 |        "  </tbody>\n",
1728 |        "</table>\n",
1729 |        "</div>"
1730 |       ],
1731 |       "text/plain": [
1732 |        "          rsid  magnitude repute  \\\n",
1733 |        "0       rs1303        0.0   Good   \n",
1734 |        "1      rs17580        2.5    Bad   \n",
1735 |        "2   rs28931580        0.0   Good   \n",
1736 |        "3    rs1042714        0.0   Good   \n",
1737 |        "4    rs1800888        0.0   Good   \n",
1738 |        "5    rs2303790        0.0   Good   \n",
1739 |        "6       rs5882        2.0    Bad   \n",
1740 |        "7    rs2230199        2.0    Bad   \n",
1741 |        "8   rs28931608        0.0   Good   \n",
1742 |        "9    rs4986893        0.0   Good   \n",
1743 |        "10  rs28399504        0.0   Good   \n",
1744 |        "11   rs2234922        0.0   Good   \n",
1745 |        "12  rs28931614        0.0   Good   \n",
1746 |        "13  rs28933068        0.0   Good   \n",
1747 |        "\n",
1748 |        "                                              summary genotype  chromosome  \\\n",
1749 |        "0                                   common in clinvar       TT          14   \n",
1750 |        "1   a slightly reduced functionality form of Alpha...       TT          14   \n",
1751 |        "2                                   common in clinvar       AA          12   \n",
1752 |        "3                                              normal       CC           5   \n",
1753 |        "4                                              normal       CC           5   \n",
1754 |        "5                                   common in clinvar       AA          16   \n",
1755 |        "6   Faster aging. Increased risk for Dementia. Les...       AA          16   \n",
1756 |        "7                                  2.5x+ risk of ARMD       GG          19   \n",
1757 |        "8                                   common in clinvar       GG           7   \n",
1758 |        "9                                              normal       GG          10   \n",
1759 |        "10                                             normal       AA          10   \n",
1760 |        "11                                  common in clinvar       AA           1   \n",
1761 |        "12                                  common in clinvar       GG           4   \n",
1762 |        "13                                  common in clinvar       CC           4   \n",
1763 |        "\n",
1764 |        "     position  \n",
1765 |        "0    94844843  \n",
1766 |        "1    94847262  \n",
1767 |        "2    50344783  \n",
1768 |        "3   148206473  \n",
1769 |        "4   148206885  \n",
1770 |        "5    57017292  \n",
1771 |        "6    57016092  \n",
1772 |        "7     6718387  \n",
1773 |        "8    75614497  \n",
1774 |        "9    96540410  \n",
1775 |        "10   96522463  \n",
1776 |        "11  226026406  \n",
1777 |        "12    1806119  \n",
1778 |        "13    1807371  "
1779 |       ]
1780 |      },
1781 |      "execution_count": 38,
1782 |      "metadata": {},
1783 |      "output_type": "execute_result"
1784 |     }
1785 |    ],
1786 |    "source": [
1787 |     "new_df.head(20)"
1788 |    ]
1789 |   },
1790 |   {
1791 |    "cell_type": "markdown",
1792 |    "metadata": {},
1793 |    "source": [
1794 |     "### What's hiding in there?"
1795 |    ]
1796 |   },
1797 |   {
1798 |    "cell_type": "code",
1799 |    "execution_count": 39,
1800 |    "metadata": {},
1801 |    "outputs": [],
1802 |    "source": [
1803 |     "# Create a DataFrame for some subsets of genes\n",
1804 |     "good_genes = new_df[new_df.repute == 'Good']\n",
1805 |     "bad_genes = new_df[new_df.repute == 'Bad']\n",
1806 |     "interesting_genes = new_df[new_df.magnitude > 4] # 4 is the threshold for \"worth your time\" given by SNPedia"
1807 |    ]
1808 |   },
1809 |   {
1810 |    "cell_type": "markdown",
1811 |    "metadata": {},
1812 |    "source": [
1813 |     "I have plenty of \"good\" genotypes, but none with a nonzero magnitude."
1814 |    ]
1815 |   },
1816 |   {
1817 |    "cell_type": "code",
1818 |    "execution_count": 40,
1819 |    "metadata": {
1820 |     "scrolled": true
1821 |    },
1822 |    "outputs": [
1823 |     {
1824 |      "data": {
1825 |       "text/html": [
1826 |        "<div>\n",
1827 |        "<style scoped>\n",
1828 |        "    .dataframe tbody tr th:only-of-type {\n",
1829 |        "        vertical-align: middle;\n",
1830 |        "    }\n",
1831 |        "\n",
1832 |        "    .dataframe tbody tr th {\n",
1833 |        "        vertical-align: top;\n",
1834 |        "    }\n",
1835 |        "\n",
1836 |        "    .dataframe thead th {\n",
1837 |        "        text-align: right;\n",
1838 |        "    }\n",
1839 |        "</style>\n",
1840 |        "<table border=\"1\" class=\"dataframe\">\n",
1841 |        "  <thead>\n",
1842 |        "    <tr style=\"text-align: right;\">\n",
1843 |        "      <th></th>\n",
1844 |        "      <th>rsid</th>\n",
1845 |        "      <th>magnitude</th>\n",
1846 |        "      <th>repute</th>\n",
1847 |        "      <th>summary</th>\n",
1848 |        "      <th>genotype</th>\n",
1849 |        "      <th>chromosome</th>\n",
1850 |        "      <th>position</th>\n",
1851 |        "    </tr>\n",
1852 |        "  </thead>\n",
1853 |        "  <tbody>\n",
1854 |        "    <tr>\n",
1855 |        "      <th>0</th>\n",
1856 |        "      <td>rs1303</td>\n",
1857 |        "      <td>0.0</td>\n",
1858 |        "      <td>Good</td>\n",
1859 |        "      <td>common in clinvar</td>\n",
1860 |        "      <td>TT</td>\n",
1861 |        "      <td>14</td>\n",
1862 |        "      <td>94844843</td>\n",
1863 |        "    </tr>\n",
1864 |        "    <tr>\n",
1865 |        "      <th>2</th>\n",
1866 |        "      <td>rs28931580</td>\n",
1867 |        "      <td>0.0</td>\n",
1868 |        "      <td>Good</td>\n",
1869 |        "      <td>common in clinvar</td>\n",
1870 |        "      <td>AA</td>\n",
1871 |        "      <td>12</td>\n",
1872 |        "      <td>50344783</td>\n",
1873 |        "    </tr>\n",
1874 |        "    <tr>\n",
1875 |        "      <th>3</th>\n",
1876 |        "      <td>rs1042714</td>\n",
1877 |        "      <td>0.0</td>\n",
1878 |        "      <td>Good</td>\n",
1879 |        "      <td>normal</td>\n",
1880 |        "      <td>CC</td>\n",
1881 |        "      <td>5</td>\n",
1882 |        "      <td>148206473</td>\n",
1883 |        "    </tr>\n",
1884 |        "    <tr>\n",
1885 |        "      <th>4</th>\n",
1886 |        "      <td>rs1800888</td>\n",
1887 |        "      <td>0.0</td>\n",
1888 |        "      <td>Good</td>\n",
1889 |        "      <td>normal</td>\n",
1890 |        "      <td>CC</td>\n",
1891 |        "      <td>5</td>\n",
1892 |        "      <td>148206885</td>\n",
1893 |        "    </tr>\n",
1894 |        "    <tr>\n",
1895 |        "      <th>5</th>\n",
1896 |        "      <td>rs2303790</td>\n",
1897 |        "      <td>0.0</td>\n",
1898 |        "      <td>Good</td>\n",
1899 |        "      <td>common in clinvar</td>\n",
1900 |        "      <td>AA</td>\n",
1901 |        "      <td>16</td>\n",
1902 |        "      <td>57017292</td>\n",
1903 |        "    </tr>\n",
1904 |        "    <tr>\n",
1905 |        "      <th>8</th>\n",
1906 |        "      <td>rs28931608</td>\n",
1907 |        "      <td>0.0</td>\n",
1908 |        "      <td>Good</td>\n",
1909 |        "      <td>common in clinvar</td>\n",
1910 |        "      <td>GG</td>\n",
1911 |        "      <td>7</td>\n",
1912 |        "      <td>75614497</td>\n",
1913 |        "    </tr>\n",
1914 |        "    <tr>\n",
1915 |        "      <th>9</th>\n",
1916 |        "      <td>rs4986893</td>\n",
1917 |        "      <td>0.0</td>\n",
1918 |        "      <td>Good</td>\n",
1919 |        "      <td>normal</td>\n",
1920 |        "      <td>GG</td>\n",
1921 |        "      <td>10</td>\n",
1922 |        "      <td>96540410</td>\n",
1923 |        "    </tr>\n",
1924 |        "    <tr>\n",
1925 |        "      <th>10</th>\n",
1926 |        "      <td>rs28399504</td>\n",
1927 |        "      <td>0.0</td>\n",
1928 |        "      <td>Good</td>\n",
1929 |        "      <td>normal</td>\n",
1930 |        "      <td>AA</td>\n",
1931 |        "      <td>10</td>\n",
1932 |        "      <td>96522463</td>\n",
1933 |        "    </tr>\n",
1934 |        "    <tr>\n",
1935 |        "      <th>11</th>\n",
1936 |        "      <td>rs2234922</td>\n",
1937 |        "      <td>0.0</td>\n",
1938 |        "      <td>Good</td>\n",
1939 |        "      <td>common in clinvar</td>\n",
1940 |        "      <td>AA</td>\n",
1941 |        "      <td>1</td>\n",
1942 |        "      <td>226026406</td>\n",
1943 |        "    </tr>\n",
1944 |        "    <tr>\n",
1945 |        "      <th>12</th>\n",
1946 |        "      <td>rs28931614</td>\n",
1947 |        "      <td>0.0</td>\n",
1948 |        "      <td>Good</td>\n",
1949 |        "      <td>common in clinvar</td>\n",
1950 |        "      <td>GG</td>\n",
1951 |        "      <td>4</td>\n",
1952 |        "      <td>1806119</td>\n",
1953 |        "    </tr>\n",
1954 |        "    <tr>\n",
1955 |        "      <th>13</th>\n",
1956 |        "      <td>rs28933068</td>\n",
1957 |        "      <td>0.0</td>\n",
1958 |        "      <td>Good</td>\n",
1959 |        "      <td>common in clinvar</td>\n",
1960 |        "      <td>CC</td>\n",
1961 |        "      <td>4</td>\n",
1962 |        "      <td>1807371</td>\n",
1963 |        "    </tr>\n",
1964 |        "  </tbody>\n",
1965 |        "</table>\n",
1966 |        "</div>"
1967 |       ],
1968 |       "text/plain": [
1969 |        "          rsid  magnitude repute            summary genotype  chromosome  \\\n",
1970 |        "0       rs1303        0.0   Good  common in clinvar       TT          14   \n",
1971 |        "2   rs28931580        0.0   Good  common in clinvar       AA          12   \n",
1972 |        "3    rs1042714        0.0   Good             normal       CC           5   \n",
1973 |        "4    rs1800888        0.0   Good             normal       CC           5   \n",
1974 |        "5    rs2303790        0.0   Good  common in clinvar       AA          16   \n",
1975 |        "8   rs28931608        0.0   Good  common in clinvar       GG           7   \n",
1976 |        "9    rs4986893        0.0   Good             normal       GG          10   \n",
1977 |        "10  rs28399504        0.0   Good             normal       AA          10   \n",
1978 |        "11   rs2234922        0.0   Good  common in clinvar       AA           1   \n",
1979 |        "12  rs28931614        0.0   Good  common in clinvar       GG           4   \n",
1980 |        "13  rs28933068        0.0   Good  common in clinvar       CC           4   \n",
1981 |        "\n",
1982 |        "     position  \n",
1983 |        "0    94844843  \n",
1984 |        "2    50344783  \n",
1985 |        "3   148206473  \n",
1986 |        "4   148206885  \n",
1987 |        "5    57017292  \n",
1988 |        "8    75614497  \n",
1989 |        "9    96540410  \n",
1990 |        "10   96522463  \n",
1991 |        "11  226026406  \n",
1992 |        "12    1806119  \n",
1993 |        "13    1807371  "
1994 |       ]
1995 |      },
1996 |      "execution_count": 40,
1997 |      "metadata": {},
1998 |      "output_type": "execute_result"
1999 |     }
2000 |    ],
2001 |    "source": [
2002 |     "good_genes"
2003 |    ]
2004 |   },
2005 |   {
2006 |    "cell_type": "markdown",
2007 |    "metadata": {},
2008 |    "source": [
2009 |     "I have three \"bad\" genotypes with a nonzero magnitude."
2010 |    ]
2011 |   },
2012 |   {
2013 |    "cell_type": "code",
2014 |    "execution_count": 41,
2015 |    "metadata": {},
2016 |    "outputs": [
2017 |     {
2018 |      "data": {
2019 |       "text/html": [
2020 |        "<div>\n",
2021 |        "<style scoped>\n",
2022 |        "    .dataframe tbody tr th:only-of-type {\n",
2023 |        "        vertical-align: middle;\n",
2024 |        "    }\n",
2025 |        "\n",
2026 |        "    .dataframe tbody tr th {\n",
2027 |        "        vertical-align: top;\n",
2028 |        "    }\n",
2029 |        "\n",
2030 |        "    .dataframe thead th {\n",
2031 |        "        text-align: right;\n",
2032 |        "    }\n",
2033 |        "</style>\n",
2034 |        "<table border=\"1\" class=\"dataframe\">\n",
2035 |        "  <thead>\n",
2036 |        "    <tr style=\"text-align: right;\">\n",
2037 |        "      <th></th>\n",
2038 |        "      <th>rsid</th>\n",
2039 |        "      <th>magnitude</th>\n",
2040 |        "      <th>repute</th>\n",
2041 |        "      <th>summary</th>\n",
2042 |        "      <th>genotype</th>\n",
2043 |        "      <th>chromosome</th>\n",
2044 |        "      <th>position</th>\n",
2045 |        "    </tr>\n",
2046 |        "  </thead>\n",
2047 |        "  <tbody>\n",
2048 |        "    <tr>\n",
2049 |        "      <th>1</th>\n",
2050 |        "      <td>rs17580</td>\n",
2051 |        "      <td>2.5</td>\n",
2052 |        "      <td>Bad</td>\n",
2053 |        "      <td>a slightly reduced functionality form of Alpha...</td>\n",
2054 |        "      <td>TT</td>\n",
2055 |        "      <td>14</td>\n",
2056 |        "      <td>94847262</td>\n",
2057 |        "    </tr>\n",
2058 |        "    <tr>\n",
2059 |        "      <th>6</th>\n",
2060 |        "      <td>rs5882</td>\n",
2061 |        "      <td>2.0</td>\n",
2062 |        "      <td>Bad</td>\n",
2063 |        "      <td>Faster aging. Increased risk for Dementia. Les...</td>\n",
2064 |        "      <td>AA</td>\n",
2065 |        "      <td>16</td>\n",
2066 |        "      <td>57016092</td>\n",
2067 |        "    </tr>\n",
2068 |        "    <tr>\n",
2069 |        "      <th>7</th>\n",
2070 |        "      <td>rs2230199</td>\n",
2071 |        "      <td>2.0</td>\n",
2072 |        "      <td>Bad</td>\n",
2073 |        "      <td>2.5x+ risk of ARMD</td>\n",
2074 |        "      <td>GG</td>\n",
2075 |        "      <td>19</td>\n",
2076 |        "      <td>6718387</td>\n",
2077 |        "    </tr>\n",
2078 |        "  </tbody>\n",
2079 |        "</table>\n",
2080 |        "</div>"
2081 |       ],
2082 |       "text/plain": [
2083 |        "        rsid  magnitude repute  \\\n",
2084 |        "1    rs17580        2.5    Bad   \n",
2085 |        "6     rs5882        2.0    Bad   \n",
2086 |        "7  rs2230199        2.0    Bad   \n",
2087 |        "\n",
2088 |        "                                             summary genotype  chromosome  \\\n",
2089 |        "1  a slightly reduced functionality form of Alpha...       TT          14   \n",
2090 |        "6  Faster aging. Increased risk for Dementia. Les...       AA          16   \n",
2091 |        "7                                 2.5x+ risk of ARMD       GG          19   \n",
2092 |        "\n",
2093 |        "   position  \n",
2094 |        "1  94847262  \n",
2095 |        "6  57016092  \n",
2096 |        "7   6718387  "
2097 |       ]
2098 |      },
2099 |      "execution_count": 41,
2100 |      "metadata": {},
2101 |      "output_type": "execute_result"
2102 |     }
2103 |    ],
2104 |    "source": [
2105 |     "bad_genes"
2106 |    ]
2107 |   },
2108 |   {
2109 |    "cell_type": "markdown",
2110 |    "metadata": {},
2111 |    "source": [
2112 |     "Sadly I have no \"interesting\" genotypes above the threshold of 4, although I have some slightly interesting bad ones."
2113 |    ]
2114 |   },
2115 |   {
2116 |    "cell_type": "code",
2117 |    "execution_count": 42,
2118 |    "metadata": {},
2119 |    "outputs": [
2120 |     {
2121 |      "data": {
2122 |       "text/html": [
2123 |        "<div>\n",
2124 |        "<style scoped>\n",
2125 |        "    .dataframe tbody tr th:only-of-type {\n",
2126 |        "        vertical-align: middle;\n",
2127 |        "    }\n",
2128 |        "\n",
2129 |        "    .dataframe tbody tr th {\n",
2130 |        "        vertical-align: top;\n",
2131 |        "    }\n",
2132 |        "\n",
2133 |        "    .dataframe thead th {\n",
2134 |        "        text-align: right;\n",
2135 |        "    }\n",
2136 |        "</style>\n",
2137 |        "<table border=\"1\" class=\"dataframe\">\n",
2138 |        "  <thead>\n",
2139 |        "    <tr style=\"text-align: right;\">\n",
2140 |        "      <th></th>\n",
2141 |        "      <th>rsid</th>\n",
2142 |        "      <th>magnitude</th>\n",
2143 |        "      <th>repute</th>\n",
2144 |        "      <th>summary</th>\n",
2145 |        "      <th>genotype</th>\n",
2146 |        "      <th>chromosome</th>\n",
2147 |        "      <th>position</th>\n",
2148 |        "    </tr>\n",
2149 |        "  </thead>\n",
2150 |        "  <tbody>\n",
2151 |        "  </tbody>\n",
2152 |        "</table>\n",
2153 |        "</div>"
2154 |       ],
2155 |       "text/plain": [
2156 |        "Empty DataFrame\n",
2157 |        "Columns: [rsid, magnitude, repute, summary, genotype, chromosome, position]\n",
2158 |        "Index: []"
2159 |       ]
2160 |      },
2161 |      "execution_count": 42,
2162 |      "metadata": {},
2163 |      "output_type": "execute_result"
2164 |     }
2165 |    ],
2166 |    "source": [
2167 |     "interesting_genes"
2168 |    ]
2169 |   },
2170 |   {
2171 |    "cell_type": "markdown",
2172 |    "metadata": {},
2173 |    "source": [
2174 |     "# Scrape relevant articles with Selenium\n",
2175 |     "\n",
2176 |     "Now I'd like to read up on my bad genetics, so I'll use Selenium to grab the abstracts of some scientific papers for me from PubMed."
2177 |    ]
2178 |   },
2179 |   {
2180 |    "cell_type": "code",
2181 |    "execution_count": 43,
2182 |    "metadata": {},
2183 |    "outputs": [],
2184 |    "source": [
2185 |     "# Get the base URL from SNPedia\n",
2186 |     "base_url = 'https://www.snpedia.com/index.php/'"
2187 |    ]
2188 |   },
2189 |   {
2190 |    "cell_type": "code",
2191 |    "execution_count": 44,
2192 |    "metadata": {},
2193 |    "outputs": [
2194 |     {
2195 |      "name": "stdout",
2196 |      "output_type": "stream",
2197 |      "text": [
2198 |       "https://www.snpedia.com/index.php/rs17580 \n",
2199 |       "\n",
2200 |       "https://www.snpedia.com/index.php/rs5882 \n",
2201 |       "\n",
2202 |       "https://www.snpedia.com/index.php/rs2230199 \n",
2203 |       "\n"
2204 |      ]
2205 |     }
2206 |    ],
2207 |    "source": [
2208 |     "# Create URLs for each gene that I want to study\n",
2209 |     "gene_urls = [base_url + rsid for rsid in bad_genes['rsid']]\n",
2210 |     "for url in gene_urls:\n",
2211 |     "    print(url, '\\n')"
2212 |    ]
2213 |   },
2214 |   {
2215 |    "cell_type": "code",
2216 |    "execution_count": 45,
2217 |    "metadata": {},
2218 |    "outputs": [],
2219 |    "source": [
2220 |     "# Initialize Selenium\n",
2221 |     "browser = webdriver.Chrome()"
2222 |    ]
2223 |   },
2224 |   {
2225 |    "cell_type": "code",
2226 |    "execution_count": 46,
2227 |    "metadata": {},
2228 |    "outputs": [],
2229 |    "source": [
2230 |     "import time"
2231 |    ]
2232 |   },
2233 |   {
2234 |    "cell_type": "code",
2235 |    "execution_count": 47,
2236 |    "metadata": {
2237 |     "scrolled": false
2238 |    },
2239 |    "outputs": [],
2240 |    "source": [
2241 |     "# Write a function to visit the SNPedia URLs, click through to PubMed, \n",
2242 |     "# and retrieve the info on the articles for each gene\n",
2243 |     "\n",
2244 |     "def scrape_abstracts(urls):\n",
2245 |     "    \n",
2246 |     "    #all_df = pd.DataFrame()\n",
2247 |     "    rsid_list = []\n",
2248 |     "    all_article_links = []\n",
2249 |     "    all_article_title = []\n",
2250 |     "    all_article_citation = []\n",
2251 |     "    all_article_authors = []\n",
2252 |     "    all_article_abstract = []\n",
2253 |     "    \n",
2254 |     "    for url in urls:\n",
2255 |     "        browser.get(url) #load url\n",
2256 |     "        rsid = browser.find_element_by_css_selector('.firstHeading').text\n",
2257 |     "        links_elements = browser.find_elements_by_partial_link_text('PMID')\n",
2258 |     "        link_urls = []\n",
2259 |     "        \n",
2260 |     "        for link in links_elements:\n",
2261 |     "            link_urls.append(link.get_attribute('href')) # get the URLs to the PubMed pages\n",
2262 |     "    \n",
2263 |     "        for element in link_urls:\n",
2264 |     "            browser.get(element) # follow each link element to PubMed\n",
2265 |     "            time.sleep(.8)\n",
2266 |     "            article_title = browser.find_element_by_xpath(\"//div[@class='cit']/../h1\").text\n",
2267 |     "            article_citation = browser.find_element_by_class_name('cit').text\n",
2268 |     "            article_authors = browser.find_element_by_class_name('auths').text\n",
2269 |     "            article_abstract = browser.find_element_by_class_name('abstr').text\n",
2270 |     "\n",
2271 |     "            rsid_list.append(rsid)\n",
2272 |     "            all_article_title.append(article_title)\n",
2273 |     "            all_article_citation.append(article_citation)\n",
2274 |     "            all_article_authors.append(article_authors)\n",
2275 |     "            all_article_abstract.append(article_abstract)\n",
2276 |     "            all_article_links.append(element)\n",
2277 |     "            \n",
2278 |     "        print(len(rsid_list) == len(link_urls) == len(all_article_title) == len(all_article_citation) == len(all_article_authors) == len(all_article_abstract))\n",
2279 |     "     \n",
2280 |     "    df = pd.DataFrame() # store the information\n",
2281 |     "    df['rsid'] = rsid_list\n",
2282 |     "    df['article_title'] = all_article_title\n",
2283 |     "    df['article_citation'] = all_article_citation\n",
2284 |     "    df['article_authors'] = all_article_authors\n",
2285 |     "    df['article_abstract'] = all_article_abstract\n",
2286 |     "    df['link'] = all_article_links\n",
2287 |     "    df = df.drop_duplicates()\n",
2288 |     "\n",
2289 |     "    df.index = range(len(df.index))\n",
2290 |     "    \n",
2291 |     "    return df"
2292 |    ]
2293 |   },
2294 |   {
2295 |    "cell_type": "code",
2296 |    "execution_count": 52,
2297 |    "metadata": {},
2298 |    "outputs": [
2299 |     {
2300 |      "name": "stdout",
2301 |      "output_type": "stream",
2302 |      "text": [
2303 |       "True\n",
2304 |       "False\n",
2305 |       "False\n"
2306 |      ]
2307 |     }
2308 |    ],
2309 |    "source": [
2310 |     "abstracts_df = scrape_abstracts(gene_urls)"
2311 |    ]
2312 |   },
2313 |   {
2314 |    "cell_type": "code",
2315 |    "execution_count": 55,
2316 |    "metadata": {},
2317 |    "outputs": [
2318 |     {
2319 |      "data": {
2320 |       "text/html": [
2321 |        "<div>\n",
2322 |        "<style scoped>\n",
2323 |        "    .dataframe tbody tr th:only-of-type {\n",
2324 |        "        vertical-align: middle;\n",
2325 |        "    }\n",
2326 |        "\n",
2327 |        "    .dataframe tbody tr th {\n",
2328 |        "        vertical-align: top;\n",
2329 |        "    }\n",
2330 |        "\n",
2331 |        "    .dataframe thead th {\n",
2332 |        "        text-align: right;\n",
2333 |        "    }\n",
2334 |        "</style>\n",
2335 |        "<table border=\"1\" class=\"dataframe\">\n",
2336 |        "  <thead>\n",
2337 |        "    <tr style=\"text-align: right;\">\n",
2338 |        "      <th></th>\n",
2339 |        "      <th>rsid</th>\n",
2340 |        "      <th>article_title</th>\n",
2341 |        "      <th>article_citation</th>\n",
2342 |        "      <th>article_authors</th>\n",
2343 |        "      <th>article_abstract</th>\n",
2344 |        "      <th>link</th>\n",
2345 |        "    </tr>\n",
2346 |        "  </thead>\n",
2347 |        "  <tbody>\n",
2348 |        "    <tr>\n",
2349 |        "      <th>0</th>\n",
2350 |        "      <td>rs17580</td>\n",
2351 |        "      <td>Heterozygosity for the alpha1-antitrypsin Z al...</td>\n",
2352 |        "      <td>Aliment Pharmacol Ther. 2011 Feb;33(3):389-94....</td>\n",
2353 |        "      <td>Mihalache F1, Höblinger A, Grünhage F, Krawczy...</td>\n",
2354 |        "      <td>Abstract\\nBACKGROUND:\\nAlpha1-antitrypsin (α1A...</td>\n",
2355 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/21138453?d...</td>\n",
2356 |        "    </tr>\n",
2357 |        "    <tr>\n",
2358 |        "      <th>1</th>\n",
2359 |        "      <td>rs17580</td>\n",
2360 |        "      <td>Genetic polymorphisms and susceptibility to lu...</td>\n",
2361 |        "      <td>J Negat Results Biomed. 2006 Apr 11;5:5.</td>\n",
2362 |        "      <td>Lee PL1, West C, Crain K, Wang L.</td>\n",
2363 |        "      <td>Abstract\\nSusceptibility to infection by bacte...</td>\n",
2364 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/16608528?d...</td>\n",
2365 |        "    </tr>\n",
2366 |        "    <tr>\n",
2367 |        "      <th>2</th>\n",
2368 |        "      <td>rs17580</td>\n",
2369 |        "      <td>Prevalence of genetic polymorphisms in the pro...</td>\n",
2370 |        "      <td>BMC Gastroenterol. 2010 Feb 20;10:22. doi: 10....</td>\n",
2371 |        "      <td>Kok KF1, te Morsche RH, van Oijen MG, Drenth JP.</td>\n",
2372 |        "      <td>Abstract\\nBACKGROUND:\\nAlpha-1 antitrypsin (A1...</td>\n",
2373 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/20170533?d...</td>\n",
2374 |        "    </tr>\n",
2375 |        "    <tr>\n",
2376 |        "      <th>3</th>\n",
2377 |        "      <td>rs17580</td>\n",
2378 |        "      <td>Serum levels and genotype distribution of α1-a...</td>\n",
2379 |        "      <td>Thorax. 2012 Aug;67(8):669-74. doi: 10.1136/th...</td>\n",
2380 |        "      <td>Ferrarotti I1, Thun GA, Zorzetto M, Ottaviani ...</td>\n",
2381 |        "      <td>Abstract\\nRATIONALE:\\nα1-Antitrypsin (AAT) def...</td>\n",
2382 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/22426792?d...</td>\n",
2383 |        "    </tr>\n",
2384 |        "    <tr>\n",
2385 |        "      <th>4</th>\n",
2386 |        "      <td>rs17580</td>\n",
2387 |        "      <td>Molecular abnormality of PI S variant of human...</td>\n",
2388 |        "      <td>Am J Hum Genet. 1977 May;29(3):233-9.</td>\n",
2389 |        "      <td>Yoshida A, Ewing C, Wessels M, Lieberman J, Ga...</td>\n",
2390 |        "      <td>Abstract\\nAlpha1-antitrypsin variant protein w...</td>\n",
2391 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/301355?dop...</td>\n",
2392 |        "    </tr>\n",
2393 |        "    <tr>\n",
2394 |        "      <th>5</th>\n",
2395 |        "      <td>rs17580</td>\n",
2396 |        "      <td>Alpha 1-antitrypsin deficiency caused by the a...</td>\n",
2397 |        "      <td>J Clin Invest. 1989 Apr;83(4):1144-52.</td>\n",
2398 |        "      <td>Curiel D1, Brantly M, Curiel E, Stier L, Cryst...</td>\n",
2399 |        "      <td>Abstract\\nalpha 1-Antitrypsin (alpha 1AT) defi...</td>\n",
2400 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/2539391?do...</td>\n",
2401 |        "    </tr>\n",
2402 |        "    <tr>\n",
2403 |        "      <th>6</th>\n",
2404 |        "      <td>rs17580</td>\n",
2405 |        "      <td>SERPINA1 PiZ and PiS heterozygotes and lung fu...</td>\n",
2406 |        "      <td>PLoS One. 2012;7(8):e42728. doi: 10.1371/journ...</td>\n",
2407 |        "      <td>Thun GA1, Ferrarotti I, Imboden M, Rochat T, G...</td>\n",
2408 |        "      <td>Abstract\\nBACKGROUND:\\nSevere alpha1-antitryps...</td>\n",
2409 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/22912729?d...</td>\n",
2410 |        "    </tr>\n",
2411 |        "    <tr>\n",
2412 |        "      <th>7</th>\n",
2413 |        "      <td>rs17580</td>\n",
2414 |        "      <td>Prevalence of alpha-1 antitrypsin high-risk va...</td>\n",
2415 |        "      <td>Arch Bronconeumol. 2015 Feb;51(2):80-85. doi: ...</td>\n",
2416 |        "      <td>Pérez-Rubio G1, Jiménez-Valverde LO2, Ramírez-...</td>\n",
2417 |        "      <td>Abstract\\nINTRODUCTION:\\nChronic obstructive p...</td>\n",
2418 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/25454901?d...</td>\n",
2419 |        "    </tr>\n",
2420 |        "    <tr>\n",
2421 |        "      <th>8</th>\n",
2422 |        "      <td>rs5882</td>\n",
2423 |        "      <td>Association of a functional polymorphism in th...</td>\n",
2424 |        "      <td>JAMA. 2010 Jan 13;303(2):150-8. doi: 10.1001/j...</td>\n",
2425 |        "      <td>Sanders AE1, Wang C, Katz M, Derby CA, Barzila...</td>\n",
2426 |        "      <td>Abstract\\nCONTEXT:\\nPolymorphisms in the chole...</td>\n",
2427 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/20068209?d...</td>\n",
2428 |        "    </tr>\n",
2429 |        "    <tr>\n",
2430 |        "      <th>9</th>\n",
2431 |        "      <td>rs5882</td>\n",
2432 |        "      <td>Common genetic variation in multiple metabolic...</td>\n",
2433 |        "      <td>J Lipid Res. 2010 Dec;51(12):3524-32. doi: 10....</td>\n",
2434 |        "      <td>Peloso GM1, Demissie S, Collins D, Mirel DB, G...</td>\n",
2435 |        "      <td>Abstract\\nA low level of HDL-C is the most com...</td>\n",
2436 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/20855565?d...</td>\n",
2437 |        "    </tr>\n",
2438 |        "    <tr>\n",
2439 |        "      <th>10</th>\n",
2440 |        "      <td>rs5882</td>\n",
2441 |        "      <td>The CETP I405V polymorphism is associated with...</td>\n",
2442 |        "      <td>Aging Cell. 2012 Apr;11(2):228-33. doi: 10.111...</td>\n",
2443 |        "      <td>Yu L1, Shulman JM, Chibnik L, Leurgans S, Schn...</td>\n",
2444 |        "      <td>Abstract\\nThe cholesteryl ester transfer prote...</td>\n",
2445 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/22122979?d...</td>\n",
2446 |        "    </tr>\n",
2447 |        "    <tr>\n",
2448 |        "      <th>11</th>\n",
2449 |        "      <td>rs5882</td>\n",
2450 |        "      <td>Cholesteryl Ester Transfer Protein (CETP) poly...</td>\n",
2451 |        "      <td>PLoS One. 2012;7(3):e31930. doi: 10.1371/journ...</td>\n",
2452 |        "      <td>Papp AC1, Pinsonneault JK, Wang D, Newman LC, ...</td>\n",
2453 |        "      <td>Abstract\\nPolymorphisms in and around the Chol...</td>\n",
2454 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/22403620?d...</td>\n",
2455 |        "    </tr>\n",
2456 |        "    <tr>\n",
2457 |        "      <th>12</th>\n",
2458 |        "      <td>rs5882</td>\n",
2459 |        "      <td>Association testing by DNA pooling: an effecti...</td>\n",
2460 |        "      <td>Proc Natl Acad Sci U S A. 2002 Dec 24;99(26):1...</td>\n",
2461 |        "      <td>Bansal A1, van den Boom D, Kammerer S, Honisch...</td>\n",
2462 |        "      <td>Abstract\\nWith an ever-increasing resource of ...</td>\n",
2463 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/12475937?d...</td>\n",
2464 |        "    </tr>\n",
2465 |        "    <tr>\n",
2466 |        "      <th>13</th>\n",
2467 |        "      <td>rs5882</td>\n",
2468 |        "      <td>Direct molecular haplotyping of long-range gen...</td>\n",
2469 |        "      <td>Proc Natl Acad Sci U S A. 2003 Jun 24;100(13):...</td>\n",
2470 |        "      <td>Ding C1, Cantor CR.</td>\n",
2471 |        "      <td>Abstract\\nHaplotypes, combinations of several ...</td>\n",
2472 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/12802015?d...</td>\n",
2473 |        "    </tr>\n",
2474 |        "    <tr>\n",
2475 |        "      <th>14</th>\n",
2476 |        "      <td>rs5882</td>\n",
2477 |        "      <td>Effects of cholesterol ester transfer protein ...</td>\n",
2478 |        "      <td>Atherosclerosis. 2008 Jan;196(1):455-60. Epub ...</td>\n",
2479 |        "      <td>Terán-García M1, Després JP, Tremblay A, Bouch...</td>\n",
2480 |        "      <td>Abstract\\nCholesterol ester transfer protein (...</td>\n",
2481 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/17196207?d...</td>\n",
2482 |        "    </tr>\n",
2483 |        "    <tr>\n",
2484 |        "      <th>15</th>\n",
2485 |        "      <td>rs5882</td>\n",
2486 |        "      <td>No association of CETP genotype with cognitive...</td>\n",
2487 |        "      <td>Neurosci Lett. 2007 Jun 13;420(2):189-92. Epub...</td>\n",
2488 |        "      <td>Johnson W1, Harris SE, Collins P, Starr JM, Wh...</td>\n",
2489 |        "      <td>Abstract\\nA cholesteryl ester transfer protein...</td>\n",
2490 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/17531380?d...</td>\n",
2491 |        "    </tr>\n",
2492 |        "    <tr>\n",
2493 |        "      <th>16</th>\n",
2494 |        "      <td>rs5882</td>\n",
2495 |        "      <td>Lack of replication of genetic associations wi...</td>\n",
2496 |        "      <td>Biogerontology. 2008 Apr;9(2):85-92. Epub 2007...</td>\n",
2497 |        "      <td>Novelli V1, Viviani Anselmi C, Roncarati R, Gu...</td>\n",
2498 |        "      <td>Abstract\\nThe exceptional longevity of centena...</td>\n",
2499 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/18034366?d...</td>\n",
2500 |        "    </tr>\n",
2501 |        "    <tr>\n",
2502 |        "      <th>17</th>\n",
2503 |        "      <td>rs5882</td>\n",
2504 |        "      <td>A hierarchical and modular approach to the dis...</td>\n",
2505 |        "      <td>BMC Genet. 2008 Jan 14;9:6. doi: 10.1186/1471-...</td>\n",
2506 |        "      <td>Sebastiani P1, Zhao Z, Abad-Grau MM, Riva A, H...</td>\n",
2507 |        "      <td>Abstract\\nBACKGROUND:\\nOne of the challenges o...</td>\n",
2508 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/18194558?d...</td>\n",
2509 |        "    </tr>\n",
2510 |        "    <tr>\n",
2511 |        "      <th>18</th>\n",
2512 |        "      <td>rs5882</td>\n",
2513 |        "      <td>New application of intelligent agents in spora...</td>\n",
2514 |        "      <td>BMC Bioinformatics. 2008 May 30;9:254. doi: 10...</td>\n",
2515 |        "      <td>Penco S1, Buscema M, Patrosso MC, Marocchi A, ...</td>\n",
2516 |        "      <td>Abstract\\nBACKGROUND:\\nFew genetic factors pre...</td>\n",
2517 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/18513389?d...</td>\n",
2518 |        "    </tr>\n",
2519 |        "    <tr>\n",
2520 |        "      <th>19</th>\n",
2521 |        "      <td>rs5882</td>\n",
2522 |        "      <td>Cholesterol ester transfer protein, interleuki...</td>\n",
2523 |        "      <td>Am J Cardiol. 2008 Jun 15;101(12):1683-8. doi:...</td>\n",
2524 |        "      <td>Enquobahrie DA1, Smith NL, Bis JC, Carty CL, R...</td>\n",
2525 |        "      <td>Abstract\\nVariations in candidate genes partic...</td>\n",
2526 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/18549840?d...</td>\n",
2527 |        "    </tr>\n",
2528 |        "    <tr>\n",
2529 |        "      <th>20</th>\n",
2530 |        "      <td>rs5882</td>\n",
2531 |        "      <td>Cholesteryl ester transfer protein (CETP) gene...</td>\n",
2532 |        "      <td>Ann Hum Genet. 2008 Nov;72(Pt 6):732-41. doi: ...</td>\n",
2533 |        "      <td>Meiner V1, Friedlander Y, Milo H, Sharon N, Be...</td>\n",
2534 |        "      <td>Abstract\\nAlthough Cholesteryl Ester Transfer ...</td>\n",
2535 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/18637884?d...</td>\n",
2536 |        "    </tr>\n",
2537 |        "    <tr>\n",
2538 |        "      <th>21</th>\n",
2539 |        "      <td>rs5882</td>\n",
2540 |        "      <td>Multiple genetic variants along candidate path...</td>\n",
2541 |        "      <td>J Lipid Res. 2008 Dec;49(12):2582-9. doi: 10.1...</td>\n",
2542 |        "      <td>Lu Y1, Dollé ME, Imholz S, van 't Slot R, Vers...</td>\n",
2543 |        "      <td>Abstract\\nThe known genetic variants determini...</td>\n",
2544 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/18660489?d...</td>\n",
2545 |        "    </tr>\n",
2546 |        "    <tr>\n",
2547 |        "      <th>22</th>\n",
2548 |        "      <td>rs5882</td>\n",
2549 |        "      <td>Genetic-epidemiological evidence on genes asso...</td>\n",
2550 |        "      <td>Exp Gerontol. 2009 Mar;44(3):136-60. doi: 10.1...</td>\n",
2551 |        "      <td>Boes E1, Coassin S, Kollerits B, Heid IM, Kron...</td>\n",
2552 |        "      <td>Abstract\\nHigh-density lipoprotein (HDL) parti...</td>\n",
2553 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19041386?d...</td>\n",
2554 |        "    </tr>\n",
2555 |        "    <tr>\n",
2556 |        "      <th>23</th>\n",
2557 |        "      <td>rs5882</td>\n",
2558 |        "      <td>A meta-analysis of candidate gene polymorphism...</td>\n",
2559 |        "      <td>Stroke. 2009 Mar;40(3):683-95. doi: 10.1161/ST...</td>\n",
2560 |        "      <td>Wang X1, Cheng S, Brophy VH, Erlich HA, Mannha...</td>\n",
2561 |        "      <td>Abstract\\nBACKGROUND AND PURPOSE:\\nIschemic st...</td>\n",
2562 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19131662?d...</td>\n",
2563 |        "    </tr>\n",
2564 |        "    <tr>\n",
2565 |        "      <th>24</th>\n",
2566 |        "      <td>rs5882</td>\n",
2567 |        "      <td>Genetic risk factors in recurrent venous throm...</td>\n",
2568 |        "      <td>Clin Chim Acta. 2009 Apr;402(1-2):189-92.</td>\n",
2569 |        "      <td>Zee RY1, Bubes V, Shrivastava S, Ridker PM, Gl...</td>\n",
2570 |        "      <td>Abstract\\nBACKGROUND:\\nRecurrent venous thromb...</td>\n",
2571 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19263529?d...</td>\n",
2572 |        "    </tr>\n",
2573 |        "    <tr>\n",
2574 |        "      <th>25</th>\n",
2575 |        "      <td>rs5882</td>\n",
2576 |        "      <td>TagSNP transferability and relative loss of va...</td>\n",
2577 |        "      <td>J Biomed Sci. 2009 Aug 14;16:73. doi: 10.1186/...</td>\n",
2578 |        "      <td>Lins TC1, Abreu BS, Pereira RW.</td>\n",
2579 |        "      <td>Abstract\\nBACKGROUND:\\nThe application of a su...</td>\n",
2580 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19682379?d...</td>\n",
2581 |        "    </tr>\n",
2582 |        "    <tr>\n",
2583 |        "      <th>26</th>\n",
2584 |        "      <td>rs5882</td>\n",
2585 |        "      <td>Genetic loci associated with plasma concentrat...</td>\n",
2586 |        "      <td>Circ Cardiovasc Genet. 2008 Oct;1(1):21-30. do...</td>\n",
2587 |        "      <td>Chasman DI1, Paré G, Zee RY, Parker AN, Cook N...</td>\n",
2588 |        "      <td>Abstract\\nBACKGROUND:\\nGenome-wide genetic ass...</td>\n",
2589 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19802338?d...</td>\n",
2590 |        "    </tr>\n",
2591 |        "    <tr>\n",
2592 |        "      <th>27</th>\n",
2593 |        "      <td>rs5882</td>\n",
2594 |        "      <td>Polymorphism in the CETP gene region, HDL chol...</td>\n",
2595 |        "      <td>Circ Cardiovasc Genet. 2009 Feb;2(1):26-33. do...</td>\n",
2596 |        "      <td>Ridker PM1, Paré G, Parker AN, Zee RY, Miletic...</td>\n",
2597 |        "      <td>Abstract\\nBACKGROUND:\\nRecent trial data have ...</td>\n",
2598 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/20031564?d...</td>\n",
2599 |        "    </tr>\n",
2600 |        "    <tr>\n",
2601 |        "      <th>28</th>\n",
2602 |        "      <td>rs5882</td>\n",
2603 |        "      <td>Associations between common genetic polymorphi...</td>\n",
2604 |        "      <td>Atherosclerosis. 2011 May;216(1):166-9. doi: 1...</td>\n",
2605 |        "      <td>Legry V1, Bokor S, Beghin L, Galfo M, Gonzalez...</td>\n",
2606 |        "      <td>Abstract\\nOBJECTIVE:\\nGenetic variability in t...</td>\n",
2607 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/21316679?d...</td>\n",
2608 |        "    </tr>\n",
2609 |        "    <tr>\n",
2610 |        "      <th>29</th>\n",
2611 |        "      <td>rs5882</td>\n",
2612 |        "      <td>Gender and single nucleotide polymorphisms in ...</td>\n",
2613 |        "      <td>J Nutr. 2012 Sep;142(9):1764-71. doi: 10.3945/...</td>\n",
2614 |        "      <td>Clifford AJ1, Chen K, McWade L, Rincon G, Kim ...</td>\n",
2615 |        "      <td>Abstract\\nUsing linear regression models, we s...</td>\n",
2616 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/22833659?d...</td>\n",
2617 |        "    </tr>\n",
2618 |        "    <tr>\n",
2619 |        "      <th>...</th>\n",
2620 |        "      <td>...</td>\n",
2621 |        "      <td>...</td>\n",
2622 |        "      <td>...</td>\n",
2623 |        "      <td>...</td>\n",
2624 |        "      <td>...</td>\n",
2625 |        "      <td>...</td>\n",
2626 |        "    </tr>\n",
2627 |        "    <tr>\n",
2628 |        "      <th>58</th>\n",
2629 |        "      <td>rs2230199</td>\n",
2630 |        "      <td>A meta-analysis of candidate gene polymorphism...</td>\n",
2631 |        "      <td>Stroke. 2009 Mar;40(3):683-95. doi: 10.1161/ST...</td>\n",
2632 |        "      <td>Wang X1, Cheng S, Brophy VH, Erlich HA, Mannha...</td>\n",
2633 |        "      <td>Abstract\\nBACKGROUND AND PURPOSE:\\nIschemic st...</td>\n",
2634 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19131662?d...</td>\n",
2635 |        "    </tr>\n",
2636 |        "    <tr>\n",
2637 |        "      <th>59</th>\n",
2638 |        "      <td>rs2230199</td>\n",
2639 |        "      <td>Common variation in the SERPING1 gene is not a...</td>\n",
2640 |        "      <td>Mol Vis. 2009;15:200-7. Epub 2009 Jan 23.</td>\n",
2641 |        "      <td>Park KH1, Ryu E, Tosakulwong N, Wu Y, Edwards AO.</td>\n",
2642 |        "      <td>Abstract\\nPURPOSE:\\nCommon genetic variation i...</td>\n",
2643 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19169411?d...</td>\n",
2644 |        "    </tr>\n",
2645 |        "    <tr>\n",
2646 |        "      <th>60</th>\n",
2647 |        "      <td>rs2230199</td>\n",
2648 |        "      <td>Assessing susceptibility to age-related macula...</td>\n",
2649 |        "      <td>Mol Cell Proteomics. 2009 Jun;8(6):1338-49. do...</td>\n",
2650 |        "      <td>Gu J1, Pauer GJ, Yue X, Narendra U, Sturgill G...</td>\n",
2651 |        "      <td>Abstract\\nAge-related macular degeneration (AM...</td>\n",
2652 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19202148?d...</td>\n",
2653 |        "    </tr>\n",
2654 |        "    <tr>\n",
2655 |        "      <th>61</th>\n",
2656 |        "      <td>rs2230199</td>\n",
2657 |        "      <td>Multilocus analysis of age-related macular deg...</td>\n",
2658 |        "      <td>Eur J Hum Genet. 2009 Sep;17(9):1190-9. doi: 1...</td>\n",
2659 |        "      <td>Bergeron-Sawitzke J1, Gold B, Olsh A, Schlotte...</td>\n",
2660 |        "      <td>Abstract\\nAge-related macular degeneration (AM...</td>\n",
2661 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19259132?d...</td>\n",
2662 |        "    </tr>\n",
2663 |        "    <tr>\n",
2664 |        "      <th>62</th>\n",
2665 |        "      <td>rs2230199</td>\n",
2666 |        "      <td>Genetic risk factors in recurrent venous throm...</td>\n",
2667 |        "      <td>Clin Chim Acta. 2009 Apr;402(1-2):189-92.</td>\n",
2668 |        "      <td>Zee RY1, Bubes V, Shrivastava S, Ridker PM, Gl...</td>\n",
2669 |        "      <td>Abstract\\nBACKGROUND:\\nRecurrent venous thromb...</td>\n",
2670 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19263529?d...</td>\n",
2671 |        "    </tr>\n",
2672 |        "    <tr>\n",
2673 |        "      <th>63</th>\n",
2674 |        "      <td>rs2230199</td>\n",
2675 |        "      <td>Association of 77 polymorphisms in 52 candidat...</td>\n",
2676 |        "      <td>J Hypertens. 2009 Mar;27(3):476-83.</td>\n",
2677 |        "      <td>Conen D1, Cheng S, Steiner LL, Buring JE, Ridk...</td>\n",
2678 |        "      <td>Abstract\\nOBJECTIVE:\\nGenetic risk factors for...</td>\n",
2679 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19330901?d...</td>\n",
2680 |        "    </tr>\n",
2681 |        "    <tr>\n",
2682 |        "      <th>64</th>\n",
2683 |        "      <td>rs2230199</td>\n",
2684 |        "      <td>Single nucleotide polymorphisms of the tenomod...</td>\n",
2685 |        "      <td>Mol Vis. 2009;15:762-70. Epub 2009 Apr 15.</td>\n",
2686 |        "      <td>Tolppanen AM1, Nevalainen T, Kolehmainen M, Se...</td>\n",
2687 |        "      <td>Abstract\\nPURPOSE:\\nTenomodulin (TNMD) is loca...</td>\n",
2688 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19381347?d...</td>\n",
2689 |        "    </tr>\n",
2690 |        "    <tr>\n",
2691 |        "      <th>65</th>\n",
2692 |        "      <td>rs2230199</td>\n",
2693 |        "      <td>A candidate gene association study of 77 polym...</td>\n",
2694 |        "      <td>J Pain. 2009 Jul;10(7):759-66. doi: 10.1016/j....</td>\n",
2695 |        "      <td>Schürks M1, Kurth T, Buring JE, Zee RY.</td>\n",
2696 |        "      <td>Abstract\\nPopulation-based studies have establ...</td>\n",
2697 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19559392?d...</td>\n",
2698 |        "    </tr>\n",
2699 |        "    <tr>\n",
2700 |        "      <th>66</th>\n",
2701 |        "      <td>rs2230199</td>\n",
2702 |        "      <td>Plasma complement components and activation fr...</td>\n",
2703 |        "      <td>Invest Ophthalmol Vis Sci. 2009 Dec;50(12):581...</td>\n",
2704 |        "      <td>Reynolds R1, Hartnett ME, Atkinson JP, Giclas ...</td>\n",
2705 |        "      <td>Abstract\\nPURPOSE:\\nSeveral genes encoding com...</td>\n",
2706 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19661236?d...</td>\n",
2707 |        "    </tr>\n",
2708 |        "    <tr>\n",
2709 |        "      <th>67</th>\n",
2710 |        "      <td>rs2230199</td>\n",
2711 |        "      <td>CFH, C3 and ARMS2 are significant risk loci fo...</td>\n",
2712 |        "      <td>PLoS One. 2009 Oct 12;4(10):e7418. doi: 10.137...</td>\n",
2713 |        "      <td>Scholl HP1, Fleckenstein M, Fritsche LG, Schmi...</td>\n",
2714 |        "      <td>Abstract\\nBACKGROUND:\\nAge-related macular deg...</td>\n",
2715 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19823576?d...</td>\n",
2716 |        "    </tr>\n",
2717 |        "    <tr>\n",
2718 |        "      <th>68</th>\n",
2719 |        "      <td>rs2230199</td>\n",
2720 |        "      <td>Complement component 3 polymorphisms interact ...</td>\n",
2721 |        "      <td>Am J Clin Nutr. 2009 Dec;90(6):1665-73. doi: 1...</td>\n",
2722 |        "      <td>Phillips CM1, Goumidi L, Bertrais S, Ferguson ...</td>\n",
2723 |        "      <td>Abstract\\nBACKGROUND:\\nComplement component 3 ...</td>\n",
2724 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/19828715?d...</td>\n",
2725 |        "    </tr>\n",
2726 |        "    <tr>\n",
2727 |        "      <th>69</th>\n",
2728 |        "      <td>rs2230199</td>\n",
2729 |        "      <td>Genetic analysis of typical wet-type age-relat...</td>\n",
2730 |        "      <td>J Ocul Biol Dis Infor. 2009 Dec 22;2(4):164-175.</td>\n",
2731 |        "      <td>Goto A, Akahori M, Okamoto H, Minami M, Terauc...</td>\n",
2732 |        "      <td>Abstract\\nAge-related macular degeneration (AM...</td>\n",
2733 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/20157352?d...</td>\n",
2734 |        "    </tr>\n",
2735 |        "    <tr>\n",
2736 |        "      <th>70</th>\n",
2737 |        "      <td>rs2230199</td>\n",
2738 |        "      <td>R102G polymorphism of the C3 gene associated w...</td>\n",
2739 |        "      <td>Mol Vis. 2010 Jul 15;16:1324-30.</td>\n",
2740 |        "      <td>Zerbib J1, Richard F, Puche N, Leveziel N, Coh...</td>\n",
2741 |        "      <td>Abstract\\nPURPOSE:\\nMajor genetic factors for ...</td>\n",
2742 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/20664795?d...</td>\n",
2743 |        "    </tr>\n",
2744 |        "    <tr>\n",
2745 |        "      <th>71</th>\n",
2746 |        "      <td>rs2230199</td>\n",
2747 |        "      <td>Assessing susceptibility to age-related macula...</td>\n",
2748 |        "      <td>Arch Ophthalmol. 2011 Mar;129(3):344-51. doi: ...</td>\n",
2749 |        "      <td>Chen Y1, Zeng J, Zhao C, Wang K, Trood E, Bueh...</td>\n",
2750 |        "      <td>Abstract\\nOBJECTIVES:\\nTo evaluate the indepen...</td>\n",
2751 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/21402993?d...</td>\n",
2752 |        "    </tr>\n",
2753 |        "    <tr>\n",
2754 |        "      <th>72</th>\n",
2755 |        "      <td>rs2230199</td>\n",
2756 |        "      <td>Using genetic variation and environmental risk...</td>\n",
2757 |        "      <td>PLoS One. 2011 Mar 24;6(3):e17784. doi: 10.137...</td>\n",
2758 |        "      <td>Spencer KL1, Olson LM, Schnetz-Boutaud N, Gall...</td>\n",
2759 |        "      <td>Abstract\\nA major goal of personalized medicin...</td>\n",
2760 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/21455292?d...</td>\n",
2761 |        "    </tr>\n",
2762 |        "    <tr>\n",
2763 |        "      <th>73</th>\n",
2764 |        "      <td>rs2230199</td>\n",
2765 |        "      <td>Association of polymorphisms in C2, CFB and C3...</td>\n",
2766 |        "      <td>Exp Eye Res. 2012 Mar;96(1):42-7. doi: 10.1016...</td>\n",
2767 |        "      <td>Kim SJ1, Lee SJ, Kim NR, Chin HS.</td>\n",
2768 |        "      <td>Abstract\\nThis study was to investigate the as...</td>\n",
2769 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/22273503?d...</td>\n",
2770 |        "    </tr>\n",
2771 |        "    <tr>\n",
2772 |        "      <th>74</th>\n",
2773 |        "      <td>rs2230199</td>\n",
2774 |        "      <td>Complement C3 gene polymorphism in renal trans...</td>\n",
2775 |        "      <td>Gene. 2012 May 1;498(2):254-8. doi: 10.1016/j....</td>\n",
2776 |        "      <td>Bazyar N1, Azarpira N, Khatami SR, Galehdari H...</td>\n",
2777 |        "      <td>Abstract\\nThe C3 component of complement has d...</td>\n",
2778 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/22361228?d...</td>\n",
2779 |        "    </tr>\n",
2780 |        "    <tr>\n",
2781 |        "      <th>75</th>\n",
2782 |        "      <td>rs2230199</td>\n",
2783 |        "      <td>Heritability and genome-wide association study...</td>\n",
2784 |        "      <td>Ophthalmology. 2012 Sep;119(9):1874-85. doi: 1...</td>\n",
2785 |        "      <td>Sobrin L1, Ripke S, Yu Y, Fagerness J, Bhangal...</td>\n",
2786 |        "      <td>Abstract\\nPURPOSE:\\nTo investigate whether the...</td>\n",
2787 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/22705344?d...</td>\n",
2788 |        "    </tr>\n",
2789 |        "    <tr>\n",
2790 |        "      <th>76</th>\n",
2791 |        "      <td>rs2230199</td>\n",
2792 |        "      <td>Pharmacogenetics for genes associated with age...</td>\n",
2793 |        "      <td>Ophthalmology. 2013 Mar;120(3):593-599. doi: 1...</td>\n",
2794 |        "      <td>Hagstrom SA1, Ying GS2, Pauer GJT3, Sturgill-S...</td>\n",
2795 |        "      <td>Abstract\\nPURPOSE:\\nTo evaluate the pharmacoge...</td>\n",
2796 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/23337555?d...</td>\n",
2797 |        "    </tr>\n",
2798 |        "    <tr>\n",
2799 |        "      <th>77</th>\n",
2800 |        "      <td>rs2230199</td>\n",
2801 |        "      <td>Genetic influences on the outcome of anti-vasc...</td>\n",
2802 |        "      <td>Ophthalmology. 2013 Aug;120(8):1641-8. doi: 10...</td>\n",
2803 |        "      <td>Abedi F1, Wickremasinghe S, Richardson AJ, Isl...</td>\n",
2804 |        "      <td>Abstract\\nPURPOSE:\\nTo determine the associati...</td>\n",
2805 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/23582991?d...</td>\n",
2806 |        "    </tr>\n",
2807 |        "    <tr>\n",
2808 |        "      <th>78</th>\n",
2809 |        "      <td>rs2230199</td>\n",
2810 |        "      <td>Seven new loci associated with age-related mac...</td>\n",
2811 |        "      <td>Nat Genet. 2013 Apr;45(4):433-9, 439e1-2. doi:...</td>\n",
2812 |        "      <td>Fritsche LG1, Chen W, Schu M, Yaspan BL, Yu Y,...</td>\n",
2813 |        "      <td>Abstract\\nAge-related macular degeneration (AM...</td>\n",
2814 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/23455636?d...</td>\n",
2815 |        "    </tr>\n",
2816 |        "    <tr>\n",
2817 |        "      <th>79</th>\n",
2818 |        "      <td>rs2230199</td>\n",
2819 |        "      <td>Complement alternative pathway genetic variati...</td>\n",
2820 |        "      <td>Clin Exp Immunol. 2013 Nov;174(2):326-34. doi:...</td>\n",
2821 |        "      <td>Kraivong R1, Vasanawathana S, Limpitikul W, Ma...</td>\n",
2822 |        "      <td>Abstract\\nDengue disease is a mosquito-borne i...</td>\n",
2823 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/23919682?d...</td>\n",
2824 |        "    </tr>\n",
2825 |        "    <tr>\n",
2826 |        "      <th>80</th>\n",
2827 |        "      <td>rs2230199</td>\n",
2828 |        "      <td>Common polymorphisms in the complement system ...</td>\n",
2829 |        "      <td>J Infect. 2013 Mar;66(3):255-62. doi: 10.1016/...</td>\n",
2830 |        "      <td>Adriani KS1, Brouwer MC, Geldhoff M, Baas F, Z...</td>\n",
2831 |        "      <td>Abstract\\nOBJECTIVE:\\nRisk factors for suscept...</td>\n",
2832 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/23068452?d...</td>\n",
2833 |        "    </tr>\n",
2834 |        "    <tr>\n",
2835 |        "      <th>81</th>\n",
2836 |        "      <td>rs2230199</td>\n",
2837 |        "      <td>Association between polymorphisms of complemen...</td>\n",
2838 |        "      <td>Invest Ophthalmol Vis Sci. 2013 Jan 7;54(1):17...</td>\n",
2839 |        "      <td>Wu L1, Tao Q, Chen W, Wang Z, Song Y, Sheng S,...</td>\n",
2840 |        "      <td>Abstract\\nPURPOSE:\\nWe assessed the associatio...</td>\n",
2841 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/23233260?d...</td>\n",
2842 |        "    </tr>\n",
2843 |        "    <tr>\n",
2844 |        "      <th>82</th>\n",
2845 |        "      <td>rs2230199</td>\n",
2846 |        "      <td>Nonsynonymous single nucleotide polymorphisms ...</td>\n",
2847 |        "      <td>Gene. 2015 May 1;561(2):249-55. doi: 10.1016/j...</td>\n",
2848 |        "      <td>Qian-Qian Y1, Yong Y2, Jing Z1, Xin B1, Tian-H...</td>\n",
2849 |        "      <td>Abstract\\nNonsynonymous single nucleotide poly...</td>\n",
2850 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/25688879?d...</td>\n",
2851 |        "    </tr>\n",
2852 |        "    <tr>\n",
2853 |        "      <th>83</th>\n",
2854 |        "      <td>rs2230199</td>\n",
2855 |        "      <td>Impact of the common genetic associations of a...</td>\n",
2856 |        "      <td>PLoS One. 2014 Mar 27;9(3):e93459. doi: 10.137...</td>\n",
2857 |        "      <td>Ristau T1, Paun C2, Ersoy L1, Hahn M3, Lechant...</td>\n",
2858 |        "      <td>Abstract\\nAge-related macular degeneration (AM...</td>\n",
2859 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/24675670?d...</td>\n",
2860 |        "    </tr>\n",
2861 |        "    <tr>\n",
2862 |        "      <th>84</th>\n",
2863 |        "      <td>rs2230199</td>\n",
2864 |        "      <td>The genetic variant rs4073 A→T of the Interleu...</td>\n",
2865 |        "      <td>Acta Ophthalmol. 2015 Dec;93(8):726-33. doi: 1...</td>\n",
2866 |        "      <td>Hautamäki A1, Seitsonen S1, Holopainen JM1, Mo...</td>\n",
2867 |        "      <td>Abstract\\nPURPOSE:\\nTo study the association o...</td>\n",
2868 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/26154559?d...</td>\n",
2869 |        "    </tr>\n",
2870 |        "    <tr>\n",
2871 |        "      <th>85</th>\n",
2872 |        "      <td>rs2230199</td>\n",
2873 |        "      <td>Association between a functional genetic polym...</td>\n",
2874 |        "      <td>Genet Mol Res. 2015 Oct 16;14(4):12567-76. doi...</td>\n",
2875 |        "      <td>Zhang MX1, Zhao XF2, Ren YC1, Geng TT3, Yang H...</td>\n",
2876 |        "      <td>Abstract\\nThe association between the rs223019...</td>\n",
2877 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/26505407?d...</td>\n",
2878 |        "    </tr>\n",
2879 |        "    <tr>\n",
2880 |        "      <th>86</th>\n",
2881 |        "      <td>rs2230199</td>\n",
2882 |        "      <td>Single-Nucleotide Polymorphisms Associated Wit...</td>\n",
2883 |        "      <td>JAMA Ophthalmol. 2016 Jun 1;134(6):674-81. doi...</td>\n",
2884 |        "      <td>Maguire MG1, Ying GS1, Jaffe GJ2, Toth CA2, Da...</td>\n",
2885 |        "      <td>Abstract\\nIMPORTANCE:\\nSingle-nucleotide polym...</td>\n",
2886 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/27099955?d...</td>\n",
2887 |        "    </tr>\n",
2888 |        "    <tr>\n",
2889 |        "      <th>87</th>\n",
2890 |        "      <td>rs2230199</td>\n",
2891 |        "      <td>Effect of Risk Alleles in CFH, C3, and VEGFA o...</td>\n",
2892 |        "      <td>Klin Monbl Augenheilkd. 2016 Apr;233(4):465-70...</td>\n",
2893 |        "      <td>Habibi I1, Kort F2, Sfar I1, Chebil A2, Bourao...</td>\n",
2894 |        "      <td>Abstract\\nPURPOSE:\\nThe aim of this pharmacoge...</td>\n",
2895 |        "      <td>https://www.ncbi.nlm.nih.gov/pubmed/27116510?d...</td>\n",
2896 |        "    </tr>\n",
2897 |        "  </tbody>\n",
2898 |        "</table>\n",
2899 |        "<p>88 rows × 6 columns</p>\n",
2900 |        "</div>"
2901 |       ],
2902 |       "text/plain": [
2903 |        "         rsid                                      article_title  \\\n",
2904 |        "0     rs17580  Heterozygosity for the alpha1-antitrypsin Z al...   \n",
2905 |        "1     rs17580  Genetic polymorphisms and susceptibility to lu...   \n",
2906 |        "2     rs17580  Prevalence of genetic polymorphisms in the pro...   \n",
2907 |        "3     rs17580  Serum levels and genotype distribution of α1-a...   \n",
2908 |        "4     rs17580  Molecular abnormality of PI S variant of human...   \n",
2909 |        "5     rs17580  Alpha 1-antitrypsin deficiency caused by the a...   \n",
2910 |        "6     rs17580  SERPINA1 PiZ and PiS heterozygotes and lung fu...   \n",
2911 |        "7     rs17580  Prevalence of alpha-1 antitrypsin high-risk va...   \n",
2912 |        "8      rs5882  Association of a functional polymorphism in th...   \n",
2913 |        "9      rs5882  Common genetic variation in multiple metabolic...   \n",
2914 |        "10     rs5882  The CETP I405V polymorphism is associated with...   \n",
2915 |        "11     rs5882  Cholesteryl Ester Transfer Protein (CETP) poly...   \n",
2916 |        "12     rs5882  Association testing by DNA pooling: an effecti...   \n",
2917 |        "13     rs5882  Direct molecular haplotyping of long-range gen...   \n",
2918 |        "14     rs5882  Effects of cholesterol ester transfer protein ...   \n",
2919 |        "15     rs5882  No association of CETP genotype with cognitive...   \n",
2920 |        "16     rs5882  Lack of replication of genetic associations wi...   \n",
2921 |        "17     rs5882  A hierarchical and modular approach to the dis...   \n",
2922 |        "18     rs5882  New application of intelligent agents in spora...   \n",
2923 |        "19     rs5882  Cholesterol ester transfer protein, interleuki...   \n",
2924 |        "20     rs5882  Cholesteryl ester transfer protein (CETP) gene...   \n",
2925 |        "21     rs5882  Multiple genetic variants along candidate path...   \n",
2926 |        "22     rs5882  Genetic-epidemiological evidence on genes asso...   \n",
2927 |        "23     rs5882  A meta-analysis of candidate gene polymorphism...   \n",
2928 |        "24     rs5882  Genetic risk factors in recurrent venous throm...   \n",
2929 |        "25     rs5882  TagSNP transferability and relative loss of va...   \n",
2930 |        "26     rs5882  Genetic loci associated with plasma concentrat...   \n",
2931 |        "27     rs5882  Polymorphism in the CETP gene region, HDL chol...   \n",
2932 |        "28     rs5882  Associations between common genetic polymorphi...   \n",
2933 |        "29     rs5882  Gender and single nucleotide polymorphisms in ...   \n",
2934 |        "..        ...                                                ...   \n",
2935 |        "58  rs2230199  A meta-analysis of candidate gene polymorphism...   \n",
2936 |        "59  rs2230199  Common variation in the SERPING1 gene is not a...   \n",
2937 |        "60  rs2230199  Assessing susceptibility to age-related macula...   \n",
2938 |        "61  rs2230199  Multilocus analysis of age-related macular deg...   \n",
2939 |        "62  rs2230199  Genetic risk factors in recurrent venous throm...   \n",
2940 |        "63  rs2230199  Association of 77 polymorphisms in 52 candidat...   \n",
2941 |        "64  rs2230199  Single nucleotide polymorphisms of the tenomod...   \n",
2942 |        "65  rs2230199  A candidate gene association study of 77 polym...   \n",
2943 |        "66  rs2230199  Plasma complement components and activation fr...   \n",
2944 |        "67  rs2230199  CFH, C3 and ARMS2 are significant risk loci fo...   \n",
2945 |        "68  rs2230199  Complement component 3 polymorphisms interact ...   \n",
2946 |        "69  rs2230199  Genetic analysis of typical wet-type age-relat...   \n",
2947 |        "70  rs2230199  R102G polymorphism of the C3 gene associated w...   \n",
2948 |        "71  rs2230199  Assessing susceptibility to age-related macula...   \n",
2949 |        "72  rs2230199  Using genetic variation and environmental risk...   \n",
2950 |        "73  rs2230199  Association of polymorphisms in C2, CFB and C3...   \n",
2951 |        "74  rs2230199  Complement C3 gene polymorphism in renal trans...   \n",
2952 |        "75  rs2230199  Heritability and genome-wide association study...   \n",
2953 |        "76  rs2230199  Pharmacogenetics for genes associated with age...   \n",
2954 |        "77  rs2230199  Genetic influences on the outcome of anti-vasc...   \n",
2955 |        "78  rs2230199  Seven new loci associated with age-related mac...   \n",
2956 |        "79  rs2230199  Complement alternative pathway genetic variati...   \n",
2957 |        "80  rs2230199  Common polymorphisms in the complement system ...   \n",
2958 |        "81  rs2230199  Association between polymorphisms of complemen...   \n",
2959 |        "82  rs2230199  Nonsynonymous single nucleotide polymorphisms ...   \n",
2960 |        "83  rs2230199  Impact of the common genetic associations of a...   \n",
2961 |        "84  rs2230199  The genetic variant rs4073 A→T of the Interleu...   \n",
2962 |        "85  rs2230199  Association between a functional genetic polym...   \n",
2963 |        "86  rs2230199  Single-Nucleotide Polymorphisms Associated Wit...   \n",
2964 |        "87  rs2230199  Effect of Risk Alleles in CFH, C3, and VEGFA o...   \n",
2965 |        "\n",
2966 |        "                                     article_citation  \\\n",
2967 |        "0   Aliment Pharmacol Ther. 2011 Feb;33(3):389-94....   \n",
2968 |        "1            J Negat Results Biomed. 2006 Apr 11;5:5.   \n",
2969 |        "2   BMC Gastroenterol. 2010 Feb 20;10:22. doi: 10....   \n",
2970 |        "3   Thorax. 2012 Aug;67(8):669-74. doi: 10.1136/th...   \n",
2971 |        "4               Am J Hum Genet. 1977 May;29(3):233-9.   \n",
2972 |        "5              J Clin Invest. 1989 Apr;83(4):1144-52.   \n",
2973 |        "6   PLoS One. 2012;7(8):e42728. doi: 10.1371/journ...   \n",
2974 |        "7   Arch Bronconeumol. 2015 Feb;51(2):80-85. doi: ...   \n",
2975 |        "8   JAMA. 2010 Jan 13;303(2):150-8. doi: 10.1001/j...   \n",
2976 |        "9   J Lipid Res. 2010 Dec;51(12):3524-32. doi: 10....   \n",
2977 |        "10  Aging Cell. 2012 Apr;11(2):228-33. doi: 10.111...   \n",
2978 |        "11  PLoS One. 2012;7(3):e31930. doi: 10.1371/journ...   \n",
2979 |        "12  Proc Natl Acad Sci U S A. 2002 Dec 24;99(26):1...   \n",
2980 |        "13  Proc Natl Acad Sci U S A. 2003 Jun 24;100(13):...   \n",
2981 |        "14  Atherosclerosis. 2008 Jan;196(1):455-60. Epub ...   \n",
2982 |        "15  Neurosci Lett. 2007 Jun 13;420(2):189-92. Epub...   \n",
2983 |        "16  Biogerontology. 2008 Apr;9(2):85-92. Epub 2007...   \n",
2984 |        "17  BMC Genet. 2008 Jan 14;9:6. doi: 10.1186/1471-...   \n",
2985 |        "18  BMC Bioinformatics. 2008 May 30;9:254. doi: 10...   \n",
2986 |        "19  Am J Cardiol. 2008 Jun 15;101(12):1683-8. doi:...   \n",
2987 |        "20  Ann Hum Genet. 2008 Nov;72(Pt 6):732-41. doi: ...   \n",
2988 |        "21  J Lipid Res. 2008 Dec;49(12):2582-9. doi: 10.1...   \n",
2989 |        "22  Exp Gerontol. 2009 Mar;44(3):136-60. doi: 10.1...   \n",
2990 |        "23  Stroke. 2009 Mar;40(3):683-95. doi: 10.1161/ST...   \n",
2991 |        "24          Clin Chim Acta. 2009 Apr;402(1-2):189-92.   \n",
2992 |        "25  J Biomed Sci. 2009 Aug 14;16:73. doi: 10.1186/...   \n",
2993 |        "26  Circ Cardiovasc Genet. 2008 Oct;1(1):21-30. do...   \n",
2994 |        "27  Circ Cardiovasc Genet. 2009 Feb;2(1):26-33. do...   \n",
2995 |        "28  Atherosclerosis. 2011 May;216(1):166-9. doi: 1...   \n",
2996 |        "29  J Nutr. 2012 Sep;142(9):1764-71. doi: 10.3945/...   \n",
2997 |        "..                                                ...   \n",
2998 |        "58  Stroke. 2009 Mar;40(3):683-95. doi: 10.1161/ST...   \n",
2999 |        "59          Mol Vis. 2009;15:200-7. Epub 2009 Jan 23.   \n",
3000 |        "60  Mol Cell Proteomics. 2009 Jun;8(6):1338-49. do...   \n",
3001 |        "61  Eur J Hum Genet. 2009 Sep;17(9):1190-9. doi: 1...   \n",
3002 |        "62          Clin Chim Acta. 2009 Apr;402(1-2):189-92.   \n",
3003 |        "63                J Hypertens. 2009 Mar;27(3):476-83.   \n",
3004 |        "64         Mol Vis. 2009;15:762-70. Epub 2009 Apr 15.   \n",
3005 |        "65  J Pain. 2009 Jul;10(7):759-66. doi: 10.1016/j....   \n",
3006 |        "66  Invest Ophthalmol Vis Sci. 2009 Dec;50(12):581...   \n",
3007 |        "67  PLoS One. 2009 Oct 12;4(10):e7418. doi: 10.137...   \n",
3008 |        "68  Am J Clin Nutr. 2009 Dec;90(6):1665-73. doi: 1...   \n",
3009 |        "69   J Ocul Biol Dis Infor. 2009 Dec 22;2(4):164-175.   \n",
3010 |        "70                   Mol Vis. 2010 Jul 15;16:1324-30.   \n",
3011 |        "71  Arch Ophthalmol. 2011 Mar;129(3):344-51. doi: ...   \n",
3012 |        "72  PLoS One. 2011 Mar 24;6(3):e17784. doi: 10.137...   \n",
3013 |        "73  Exp Eye Res. 2012 Mar;96(1):42-7. doi: 10.1016...   \n",
3014 |        "74  Gene. 2012 May 1;498(2):254-8. doi: 10.1016/j....   \n",
3015 |        "75  Ophthalmology. 2012 Sep;119(9):1874-85. doi: 1...   \n",
3016 |        "76  Ophthalmology. 2013 Mar;120(3):593-599. doi: 1...   \n",
3017 |        "77  Ophthalmology. 2013 Aug;120(8):1641-8. doi: 10...   \n",
3018 |        "78  Nat Genet. 2013 Apr;45(4):433-9, 439e1-2. doi:...   \n",
3019 |        "79  Clin Exp Immunol. 2013 Nov;174(2):326-34. doi:...   \n",
3020 |        "80  J Infect. 2013 Mar;66(3):255-62. doi: 10.1016/...   \n",
3021 |        "81  Invest Ophthalmol Vis Sci. 2013 Jan 7;54(1):17...   \n",
3022 |        "82  Gene. 2015 May 1;561(2):249-55. doi: 10.1016/j...   \n",
3023 |        "83  PLoS One. 2014 Mar 27;9(3):e93459. doi: 10.137...   \n",
3024 |        "84  Acta Ophthalmol. 2015 Dec;93(8):726-33. doi: 1...   \n",
3025 |        "85  Genet Mol Res. 2015 Oct 16;14(4):12567-76. doi...   \n",
3026 |        "86  JAMA Ophthalmol. 2016 Jun 1;134(6):674-81. doi...   \n",
3027 |        "87  Klin Monbl Augenheilkd. 2016 Apr;233(4):465-70...   \n",
3028 |        "\n",
3029 |        "                                      article_authors  \\\n",
3030 |        "0   Mihalache F1, Höblinger A, Grünhage F, Krawczy...   \n",
3031 |        "1                   Lee PL1, West C, Crain K, Wang L.   \n",
3032 |        "2    Kok KF1, te Morsche RH, van Oijen MG, Drenth JP.   \n",
3033 |        "3   Ferrarotti I1, Thun GA, Zorzetto M, Ottaviani ...   \n",
3034 |        "4   Yoshida A, Ewing C, Wessels M, Lieberman J, Ga...   \n",
3035 |        "5   Curiel D1, Brantly M, Curiel E, Stier L, Cryst...   \n",
3036 |        "6   Thun GA1, Ferrarotti I, Imboden M, Rochat T, G...   \n",
3037 |        "7   Pérez-Rubio G1, Jiménez-Valverde LO2, Ramírez-...   \n",
3038 |        "8   Sanders AE1, Wang C, Katz M, Derby CA, Barzila...   \n",
3039 |        "9   Peloso GM1, Demissie S, Collins D, Mirel DB, G...   \n",
3040 |        "10  Yu L1, Shulman JM, Chibnik L, Leurgans S, Schn...   \n",
3041 |        "11  Papp AC1, Pinsonneault JK, Wang D, Newman LC, ...   \n",
3042 |        "12  Bansal A1, van den Boom D, Kammerer S, Honisch...   \n",
3043 |        "13                                Ding C1, Cantor CR.   \n",
3044 |        "14  Terán-García M1, Després JP, Tremblay A, Bouch...   \n",
3045 |        "15  Johnson W1, Harris SE, Collins P, Starr JM, Wh...   \n",
3046 |        "16  Novelli V1, Viviani Anselmi C, Roncarati R, Gu...   \n",
3047 |        "17  Sebastiani P1, Zhao Z, Abad-Grau MM, Riva A, H...   \n",
3048 |        "18  Penco S1, Buscema M, Patrosso MC, Marocchi A, ...   \n",
3049 |        "19  Enquobahrie DA1, Smith NL, Bis JC, Carty CL, R...   \n",
3050 |        "20  Meiner V1, Friedlander Y, Milo H, Sharon N, Be...   \n",
3051 |        "21  Lu Y1, Dollé ME, Imholz S, van 't Slot R, Vers...   \n",
3052 |        "22  Boes E1, Coassin S, Kollerits B, Heid IM, Kron...   \n",
3053 |        "23  Wang X1, Cheng S, Brophy VH, Erlich HA, Mannha...   \n",
3054 |        "24  Zee RY1, Bubes V, Shrivastava S, Ridker PM, Gl...   \n",
3055 |        "25                    Lins TC1, Abreu BS, Pereira RW.   \n",
3056 |        "26  Chasman DI1, Paré G, Zee RY, Parker AN, Cook N...   \n",
3057 |        "27  Ridker PM1, Paré G, Parker AN, Zee RY, Miletic...   \n",
3058 |        "28  Legry V1, Bokor S, Beghin L, Galfo M, Gonzalez...   \n",
3059 |        "29  Clifford AJ1, Chen K, McWade L, Rincon G, Kim ...   \n",
3060 |        "..                                                ...   \n",
3061 |        "58  Wang X1, Cheng S, Brophy VH, Erlich HA, Mannha...   \n",
3062 |        "59  Park KH1, Ryu E, Tosakulwong N, Wu Y, Edwards AO.   \n",
3063 |        "60  Gu J1, Pauer GJ, Yue X, Narendra U, Sturgill G...   \n",
3064 |        "61  Bergeron-Sawitzke J1, Gold B, Olsh A, Schlotte...   \n",
3065 |        "62  Zee RY1, Bubes V, Shrivastava S, Ridker PM, Gl...   \n",
3066 |        "63  Conen D1, Cheng S, Steiner LL, Buring JE, Ridk...   \n",
3067 |        "64  Tolppanen AM1, Nevalainen T, Kolehmainen M, Se...   \n",
3068 |        "65            Schürks M1, Kurth T, Buring JE, Zee RY.   \n",
3069 |        "66  Reynolds R1, Hartnett ME, Atkinson JP, Giclas ...   \n",
3070 |        "67  Scholl HP1, Fleckenstein M, Fritsche LG, Schmi...   \n",
3071 |        "68  Phillips CM1, Goumidi L, Bertrais S, Ferguson ...   \n",
3072 |        "69  Goto A, Akahori M, Okamoto H, Minami M, Terauc...   \n",
3073 |        "70  Zerbib J1, Richard F, Puche N, Leveziel N, Coh...   \n",
3074 |        "71  Chen Y1, Zeng J, Zhao C, Wang K, Trood E, Bueh...   \n",
3075 |        "72  Spencer KL1, Olson LM, Schnetz-Boutaud N, Gall...   \n",
3076 |        "73                  Kim SJ1, Lee SJ, Kim NR, Chin HS.   \n",
3077 |        "74  Bazyar N1, Azarpira N, Khatami SR, Galehdari H...   \n",
3078 |        "75  Sobrin L1, Ripke S, Yu Y, Fagerness J, Bhangal...   \n",
3079 |        "76  Hagstrom SA1, Ying GS2, Pauer GJT3, Sturgill-S...   \n",
3080 |        "77  Abedi F1, Wickremasinghe S, Richardson AJ, Isl...   \n",
3081 |        "78  Fritsche LG1, Chen W, Schu M, Yaspan BL, Yu Y,...   \n",
3082 |        "79  Kraivong R1, Vasanawathana S, Limpitikul W, Ma...   \n",
3083 |        "80  Adriani KS1, Brouwer MC, Geldhoff M, Baas F, Z...   \n",
3084 |        "81  Wu L1, Tao Q, Chen W, Wang Z, Song Y, Sheng S,...   \n",
3085 |        "82  Qian-Qian Y1, Yong Y2, Jing Z1, Xin B1, Tian-H...   \n",
3086 |        "83  Ristau T1, Paun C2, Ersoy L1, Hahn M3, Lechant...   \n",
3087 |        "84  Hautamäki A1, Seitsonen S1, Holopainen JM1, Mo...   \n",
3088 |        "85  Zhang MX1, Zhao XF2, Ren YC1, Geng TT3, Yang H...   \n",
3089 |        "86  Maguire MG1, Ying GS1, Jaffe GJ2, Toth CA2, Da...   \n",
3090 |        "87  Habibi I1, Kort F2, Sfar I1, Chebil A2, Bourao...   \n",
3091 |        "\n",
3092 |        "                                     article_abstract  \\\n",
3093 |        "0   Abstract\\nBACKGROUND:\\nAlpha1-antitrypsin (α1A...   \n",
3094 |        "1   Abstract\\nSusceptibility to infection by bacte...   \n",
3095 |        "2   Abstract\\nBACKGROUND:\\nAlpha-1 antitrypsin (A1...   \n",
3096 |        "3   Abstract\\nRATIONALE:\\nα1-Antitrypsin (AAT) def...   \n",
3097 |        "4   Abstract\\nAlpha1-antitrypsin variant protein w...   \n",
3098 |        "5   Abstract\\nalpha 1-Antitrypsin (alpha 1AT) defi...   \n",
3099 |        "6   Abstract\\nBACKGROUND:\\nSevere alpha1-antitryps...   \n",
3100 |        "7   Abstract\\nINTRODUCTION:\\nChronic obstructive p...   \n",
3101 |        "8   Abstract\\nCONTEXT:\\nPolymorphisms in the chole...   \n",
3102 |        "9   Abstract\\nA low level of HDL-C is the most com...   \n",
3103 |        "10  Abstract\\nThe cholesteryl ester transfer prote...   \n",
3104 |        "11  Abstract\\nPolymorphisms in and around the Chol...   \n",
3105 |        "12  Abstract\\nWith an ever-increasing resource of ...   \n",
3106 |        "13  Abstract\\nHaplotypes, combinations of several ...   \n",
3107 |        "14  Abstract\\nCholesterol ester transfer protein (...   \n",
3108 |        "15  Abstract\\nA cholesteryl ester transfer protein...   \n",
3109 |        "16  Abstract\\nThe exceptional longevity of centena...   \n",
3110 |        "17  Abstract\\nBACKGROUND:\\nOne of the challenges o...   \n",
3111 |        "18  Abstract\\nBACKGROUND:\\nFew genetic factors pre...   \n",
3112 |        "19  Abstract\\nVariations in candidate genes partic...   \n",
3113 |        "20  Abstract\\nAlthough Cholesteryl Ester Transfer ...   \n",
3114 |        "21  Abstract\\nThe known genetic variants determini...   \n",
3115 |        "22  Abstract\\nHigh-density lipoprotein (HDL) parti...   \n",
3116 |        "23  Abstract\\nBACKGROUND AND PURPOSE:\\nIschemic st...   \n",
3117 |        "24  Abstract\\nBACKGROUND:\\nRecurrent venous thromb...   \n",
3118 |        "25  Abstract\\nBACKGROUND:\\nThe application of a su...   \n",
3119 |        "26  Abstract\\nBACKGROUND:\\nGenome-wide genetic ass...   \n",
3120 |        "27  Abstract\\nBACKGROUND:\\nRecent trial data have ...   \n",
3121 |        "28  Abstract\\nOBJECTIVE:\\nGenetic variability in t...   \n",
3122 |        "29  Abstract\\nUsing linear regression models, we s...   \n",
3123 |        "..                                                ...   \n",
3124 |        "58  Abstract\\nBACKGROUND AND PURPOSE:\\nIschemic st...   \n",
3125 |        "59  Abstract\\nPURPOSE:\\nCommon genetic variation i...   \n",
3126 |        "60  Abstract\\nAge-related macular degeneration (AM...   \n",
3127 |        "61  Abstract\\nAge-related macular degeneration (AM...   \n",
3128 |        "62  Abstract\\nBACKGROUND:\\nRecurrent venous thromb...   \n",
3129 |        "63  Abstract\\nOBJECTIVE:\\nGenetic risk factors for...   \n",
3130 |        "64  Abstract\\nPURPOSE:\\nTenomodulin (TNMD) is loca...   \n",
3131 |        "65  Abstract\\nPopulation-based studies have establ...   \n",
3132 |        "66  Abstract\\nPURPOSE:\\nSeveral genes encoding com...   \n",
3133 |        "67  Abstract\\nBACKGROUND:\\nAge-related macular deg...   \n",
3134 |        "68  Abstract\\nBACKGROUND:\\nComplement component 3 ...   \n",
3135 |        "69  Abstract\\nAge-related macular degeneration (AM...   \n",
3136 |        "70  Abstract\\nPURPOSE:\\nMajor genetic factors for ...   \n",
3137 |        "71  Abstract\\nOBJECTIVES:\\nTo evaluate the indepen...   \n",
3138 |        "72  Abstract\\nA major goal of personalized medicin...   \n",
3139 |        "73  Abstract\\nThis study was to investigate the as...   \n",
3140 |        "74  Abstract\\nThe C3 component of complement has d...   \n",
3141 |        "75  Abstract\\nPURPOSE:\\nTo investigate whether the...   \n",
3142 |        "76  Abstract\\nPURPOSE:\\nTo evaluate the pharmacoge...   \n",
3143 |        "77  Abstract\\nPURPOSE:\\nTo determine the associati...   \n",
3144 |        "78  Abstract\\nAge-related macular degeneration (AM...   \n",
3145 |        "79  Abstract\\nDengue disease is a mosquito-borne i...   \n",
3146 |        "80  Abstract\\nOBJECTIVE:\\nRisk factors for suscept...   \n",
3147 |        "81  Abstract\\nPURPOSE:\\nWe assessed the associatio...   \n",
3148 |        "82  Abstract\\nNonsynonymous single nucleotide poly...   \n",
3149 |        "83  Abstract\\nAge-related macular degeneration (AM...   \n",
3150 |        "84  Abstract\\nPURPOSE:\\nTo study the association o...   \n",
3151 |        "85  Abstract\\nThe association between the rs223019...   \n",
3152 |        "86  Abstract\\nIMPORTANCE:\\nSingle-nucleotide polym...   \n",
3153 |        "87  Abstract\\nPURPOSE:\\nThe aim of this pharmacoge...   \n",
3154 |        "\n",
3155 |        "                                                 link  \n",
3156 |        "0   https://www.ncbi.nlm.nih.gov/pubmed/21138453?d...  \n",
3157 |        "1   https://www.ncbi.nlm.nih.gov/pubmed/16608528?d...  \n",
3158 |        "2   https://www.ncbi.nlm.nih.gov/pubmed/20170533?d...  \n",
3159 |        "3   https://www.ncbi.nlm.nih.gov/pubmed/22426792?d...  \n",
3160 |        "4   https://www.ncbi.nlm.nih.gov/pubmed/301355?dop...  \n",
3161 |        "5   https://www.ncbi.nlm.nih.gov/pubmed/2539391?do...  \n",
3162 |        "6   https://www.ncbi.nlm.nih.gov/pubmed/22912729?d...  \n",
3163 |        "7   https://www.ncbi.nlm.nih.gov/pubmed/25454901?d...  \n",
3164 |        "8   https://www.ncbi.nlm.nih.gov/pubmed/20068209?d...  \n",
3165 |        "9   https://www.ncbi.nlm.nih.gov/pubmed/20855565?d...  \n",
3166 |        "10  https://www.ncbi.nlm.nih.gov/pubmed/22122979?d...  \n",
3167 |        "11  https://www.ncbi.nlm.nih.gov/pubmed/22403620?d...  \n",
3168 |        "12  https://www.ncbi.nlm.nih.gov/pubmed/12475937?d...  \n",
3169 |        "13  https://www.ncbi.nlm.nih.gov/pubmed/12802015?d...  \n",
3170 |        "14  https://www.ncbi.nlm.nih.gov/pubmed/17196207?d...  \n",
3171 |        "15  https://www.ncbi.nlm.nih.gov/pubmed/17531380?d...  \n",
3172 |        "16  https://www.ncbi.nlm.nih.gov/pubmed/18034366?d...  \n",
3173 |        "17  https://www.ncbi.nlm.nih.gov/pubmed/18194558?d...  \n",
3174 |        "18  https://www.ncbi.nlm.nih.gov/pubmed/18513389?d...  \n",
3175 |        "19  https://www.ncbi.nlm.nih.gov/pubmed/18549840?d...  \n",
3176 |        "20  https://www.ncbi.nlm.nih.gov/pubmed/18637884?d...  \n",
3177 |        "21  https://www.ncbi.nlm.nih.gov/pubmed/18660489?d...  \n",
3178 |        "22  https://www.ncbi.nlm.nih.gov/pubmed/19041386?d...  \n",
3179 |        "23  https://www.ncbi.nlm.nih.gov/pubmed/19131662?d...  \n",
3180 |        "24  https://www.ncbi.nlm.nih.gov/pubmed/19263529?d...  \n",
3181 |        "25  https://www.ncbi.nlm.nih.gov/pubmed/19682379?d...  \n",
3182 |        "26  https://www.ncbi.nlm.nih.gov/pubmed/19802338?d...  \n",
3183 |        "27  https://www.ncbi.nlm.nih.gov/pubmed/20031564?d...  \n",
3184 |        "28  https://www.ncbi.nlm.nih.gov/pubmed/21316679?d...  \n",
3185 |        "29  https://www.ncbi.nlm.nih.gov/pubmed/22833659?d...  \n",
3186 |        "..                                                ...  \n",
3187 |        "58  https://www.ncbi.nlm.nih.gov/pubmed/19131662?d...  \n",
3188 |        "59  https://www.ncbi.nlm.nih.gov/pubmed/19169411?d...  \n",
3189 |        "60  https://www.ncbi.nlm.nih.gov/pubmed/19202148?d...  \n",
3190 |        "61  https://www.ncbi.nlm.nih.gov/pubmed/19259132?d...  \n",
3191 |        "62  https://www.ncbi.nlm.nih.gov/pubmed/19263529?d...  \n",
3192 |        "63  https://www.ncbi.nlm.nih.gov/pubmed/19330901?d...  \n",
3193 |        "64  https://www.ncbi.nlm.nih.gov/pubmed/19381347?d...  \n",
3194 |        "65  https://www.ncbi.nlm.nih.gov/pubmed/19559392?d...  \n",
3195 |        "66  https://www.ncbi.nlm.nih.gov/pubmed/19661236?d...  \n",
3196 |        "67  https://www.ncbi.nlm.nih.gov/pubmed/19823576?d...  \n",
3197 |        "68  https://www.ncbi.nlm.nih.gov/pubmed/19828715?d...  \n",
3198 |        "69  https://www.ncbi.nlm.nih.gov/pubmed/20157352?d...  \n",
3199 |        "70  https://www.ncbi.nlm.nih.gov/pubmed/20664795?d...  \n",
3200 |        "71  https://www.ncbi.nlm.nih.gov/pubmed/21402993?d...  \n",
3201 |        "72  https://www.ncbi.nlm.nih.gov/pubmed/21455292?d...  \n",
3202 |        "73  https://www.ncbi.nlm.nih.gov/pubmed/22273503?d...  \n",
3203 |        "74  https://www.ncbi.nlm.nih.gov/pubmed/22361228?d...  \n",
3204 |        "75  https://www.ncbi.nlm.nih.gov/pubmed/22705344?d...  \n",
3205 |        "76  https://www.ncbi.nlm.nih.gov/pubmed/23337555?d...  \n",
3206 |        "77  https://www.ncbi.nlm.nih.gov/pubmed/23582991?d...  \n",
3207 |        "78  https://www.ncbi.nlm.nih.gov/pubmed/23455636?d...  \n",
3208 |        "79  https://www.ncbi.nlm.nih.gov/pubmed/23919682?d...  \n",
3209 |        "80  https://www.ncbi.nlm.nih.gov/pubmed/23068452?d...  \n",
3210 |        "81  https://www.ncbi.nlm.nih.gov/pubmed/23233260?d...  \n",
3211 |        "82  https://www.ncbi.nlm.nih.gov/pubmed/25688879?d...  \n",
3212 |        "83  https://www.ncbi.nlm.nih.gov/pubmed/24675670?d...  \n",
3213 |        "84  https://www.ncbi.nlm.nih.gov/pubmed/26154559?d...  \n",
3214 |        "85  https://www.ncbi.nlm.nih.gov/pubmed/26505407?d...  \n",
3215 |        "86  https://www.ncbi.nlm.nih.gov/pubmed/27099955?d...  \n",
3216 |        "87  https://www.ncbi.nlm.nih.gov/pubmed/27116510?d...  \n",
3217 |        "\n",
3218 |        "[88 rows x 6 columns]"
3219 |       ]
3220 |      },
3221 |      "execution_count": 55,
3222 |      "metadata": {},
3223 |      "output_type": "execute_result"
3224 |     }
3225 |    ],
3226 |    "source": [
3227 |     "abstracts_df"
3228 |    ]
3229 |   },
3230 |   {
3231 |    "cell_type": "markdown",
3232 |    "metadata": {},
3233 |    "source": [
3234 |     "To save for later perusal, I'll export my web scrapings, complete with abstracts and hyperlinks, to a CSV file using the pandas DataFrame.to_csv method. "
3235 |    ]
3236 |   },
3237 |   {
3238 |    "cell_type": "code",
3239 |    "execution_count": 56,
3240 |    "metadata": {},
3241 |    "outputs": [],
3242 |    "source": [
3243 |     "#DataFrame to CSV\n",
3244 |     "export_csv = abstracts_df.to_csv(r'/Users/lorajohns/Documents/Python/DNA/DNA_articles.csv')"
3245 |    ]
3246 |   },
3247 |   {
3248 |    "cell_type": "markdown",
3249 |    "metadata": {},
3250 |    "source": [
3251 |     "## Reading up on the medical literature\n",
3252 |     "\n",
3253 |     "Now I have a handy CSV file, nicely formatted to read in Numbers, Excel, or PDF format, with citations to scientific articles analyzing and describing my genotypes with \"significant\" magnitudes and \"bad\" reputations. With the powerful tools Python provides, it's a great time to be alive for literal introspection. "
3254 |    ]
3255 |   }
3256 |  ],
3257 |  "metadata": {
3258 |   "kernelspec": {
3259 |    "display_name": "Python 3",
3260 |    "language": "python",
3261 |    "name": "python3"
3262 |   },
3263 |   "language_info": {
3264 |    "codemirror_mode": {
3265 |     "name": "ipython",
3266 |     "version": 3
3267 |    },
3268 |    "file_extension": ".py",
3269 |    "mimetype": "text/x-python",
3270 |    "name": "python",
3271 |    "nbconvert_exporter": "python",
3272 |    "pygments_lexer": "ipython3",
3273 |    "version": "3.7.2"
3274 |   }
3275 |  },
3276 |  "nbformat": 4,
3277 |  "nbformat_minor": 2
3278 | }
3279 | 


--------------------------------------------------------------------------------