|
a |
|
b/ipynb/embedding 3d NCBI 2019-04-07.ipynb |
|
|
1 |
{ |
|
|
2 |
"cells": [ |
|
|
3 |
{ |
|
|
4 |
"cell_type": "markdown", |
|
|
5 |
"metadata": {}, |
|
|
6 |
"source": [ |
|
|
7 |
"## Exploration of 100d space of genome vectors\n", |
|
|
8 |
"\n", |
|
|
9 |
"Genome vectors created by the Dna2VecDataBunch exhibit piculiar patterns. This notebook is dedicated to exploratoin \n", |
|
|
10 |
"of the bacterial genome space using dimensionality reduction techniques" |
|
|
11 |
] |
|
|
12 |
}, |
|
|
13 |
{ |
|
|
14 |
"cell_type": "code", |
|
|
15 |
"execution_count": 4, |
|
|
16 |
"metadata": {}, |
|
|
17 |
"outputs": [ |
|
|
18 |
{ |
|
|
19 |
"name": "stdout", |
|
|
20 |
"output_type": "stream", |
|
|
21 |
"text": [ |
|
|
22 |
"The autoreload extension is already loaded. To reload it, use:\n", |
|
|
23 |
" %reload_ext autoreload\n" |
|
|
24 |
] |
|
|
25 |
} |
|
|
26 |
], |
|
|
27 |
"source": [ |
|
|
28 |
"%load_ext autoreload\n", |
|
|
29 |
"%autoreload 2" |
|
|
30 |
] |
|
|
31 |
}, |
|
|
32 |
{ |
|
|
33 |
"cell_type": "code", |
|
|
34 |
"execution_count": 5, |
|
|
35 |
"metadata": {}, |
|
|
36 |
"outputs": [], |
|
|
37 |
"source": [ |
|
|
38 |
"import sys\n", |
|
|
39 |
"sys.path.append(\"../mylib/\")\n", |
|
|
40 |
"\n", |
|
|
41 |
"from genomic import sequence\n", |
|
|
42 |
"from genomic.sequence import regex_filter, count_filter\n", |
|
|
43 |
"from functools import partial\n", |
|
|
44 |
"import pandas as pd\n", |
|
|
45 |
"import numpy as np\n", |
|
|
46 |
"from sklearn.decomposition import PCA\n", |
|
|
47 |
"from sklearn import manifold,neighbors\n", |
|
|
48 |
"from scipy.cluster.hierarchy import dendrogram, linkage \n", |
|
|
49 |
"from matplotlib import pyplot as plt\n", |
|
|
50 |
"import seaborn as sns; sns.set(color_codes=True)\n", |
|
|
51 |
"import plotly.plotly as py\n", |
|
|
52 |
"import plotly.graph_objs as go" |
|
|
53 |
] |
|
|
54 |
}, |
|
|
55 |
{ |
|
|
56 |
"cell_type": "markdown", |
|
|
57 |
"metadata": {}, |
|
|
58 |
"source": [ |
|
|
59 |
"### Load Data" |
|
|
60 |
] |
|
|
61 |
}, |
|
|
62 |
{ |
|
|
63 |
"cell_type": "code", |
|
|
64 |
"execution_count": 6, |
|
|
65 |
"metadata": {}, |
|
|
66 |
"outputs": [], |
|
|
67 |
"source": [ |
|
|
68 |
"# DB=\"/data/genomes/GenSeq_fastas/train\"\n", |
|
|
69 |
"DB='/home/serge/development/genomes/ncbi-genomes-2019-04-07/bacterial genomes'" |
|
|
70 |
] |
|
|
71 |
}, |
|
|
72 |
{ |
|
|
73 |
"cell_type": "code", |
|
|
74 |
"execution_count": 7, |
|
|
75 |
"metadata": {}, |
|
|
76 |
"outputs": [], |
|
|
77 |
"source": [ |
|
|
78 |
"filters=[partial(regex_filter, rx=\"Escherichia|Klebsiella|Bacillus\"),partial(regex_filter, rx=\"plasmid?\\s\", keep=False),\n", |
|
|
79 |
" partial(count_filter,num_fastas=(1,1), keep=1)]\n", |
|
|
80 |
"data = sequence.Dna2VecList.from_folder(DB,filters=filters,agg=partial(np.mean, axis=0),n_cpus=7)" |
|
|
81 |
] |
|
|
82 |
}, |
|
|
83 |
{ |
|
|
84 |
"cell_type": "code", |
|
|
85 |
"execution_count": 8, |
|
|
86 |
"metadata": {}, |
|
|
87 |
"outputs": [ |
|
|
88 |
{ |
|
|
89 |
"data": { |
|
|
90 |
"text/plain": [ |
|
|
91 |
"1686" |
|
|
92 |
] |
|
|
93 |
}, |
|
|
94 |
"execution_count": 8, |
|
|
95 |
"metadata": {}, |
|
|
96 |
"output_type": "execute_result" |
|
|
97 |
} |
|
|
98 |
], |
|
|
99 |
"source": [ |
|
|
100 |
"len(data.items)" |
|
|
101 |
] |
|
|
102 |
}, |
|
|
103 |
{ |
|
|
104 |
"cell_type": "code", |
|
|
105 |
"execution_count": 9, |
|
|
106 |
"metadata": {}, |
|
|
107 |
"outputs": [ |
|
|
108 |
{ |
|
|
109 |
"name": "stdout", |
|
|
110 |
"output_type": "stream", |
|
|
111 |
"text": [ |
|
|
112 |
"CPU times: user 42min 11s, sys: 8min 41s, total: 50min 52s\n", |
|
|
113 |
"Wall time: 1h 25min 43s\n" |
|
|
114 |
] |
|
|
115 |
} |
|
|
116 |
], |
|
|
117 |
"source": [ |
|
|
118 |
"processors = [\n", |
|
|
119 |
" sequence.GSFileProcessor(),\n", |
|
|
120 |
" sequence.GSTokenizeProcessor(tokenizer=sequence.GSTokenizer(ngram=8, skip=0, n_cpus=4)),\n", |
|
|
121 |
" sequence.Dna2VecProcessor()]\n", |
|
|
122 |
"%time for p in processors: p.process(data)" |
|
|
123 |
] |
|
|
124 |
}, |
|
|
125 |
{ |
|
|
126 |
"cell_type": "code", |
|
|
127 |
"execution_count": 10, |
|
|
128 |
"metadata": {}, |
|
|
129 |
"outputs": [ |
|
|
130 |
{ |
|
|
131 |
"data": { |
|
|
132 |
"text/plain": [ |
|
|
133 |
"1686" |
|
|
134 |
] |
|
|
135 |
}, |
|
|
136 |
"execution_count": 10, |
|
|
137 |
"metadata": {}, |
|
|
138 |
"output_type": "execute_result" |
|
|
139 |
} |
|
|
140 |
], |
|
|
141 |
"source": [ |
|
|
142 |
"len(data.items)" |
|
|
143 |
] |
|
|
144 |
}, |
|
|
145 |
{ |
|
|
146 |
"cell_type": "markdown", |
|
|
147 |
"metadata": {}, |
|
|
148 |
"source": [ |
|
|
149 |
"### Genome vectors" |
|
|
150 |
] |
|
|
151 |
}, |
|
|
152 |
{ |
|
|
153 |
"cell_type": "code", |
|
|
154 |
"execution_count": 14, |
|
|
155 |
"metadata": {}, |
|
|
156 |
"outputs": [], |
|
|
157 |
"source": [ |
|
|
158 |
"def log_scale(X):\n", |
|
|
159 |
" x=np.asarray(X);e=1e-6\n", |
|
|
160 |
" return np.log10(x+np.abs(x.min())+e) \n", |
|
|
161 |
"\n", |
|
|
162 |
"\n", |
|
|
163 |
"x=np.asarray(data.items)\n", |
|
|
164 |
"bad_fastas = np.where(np.mean(x,axis=1) == 0.)[0]\n", |
|
|
165 |
"X = np.delete(x, bad_fastas,0)\n", |
|
|
166 |
"labelList=[\" \".join(i.split()[1:3]) for i in data.descriptions]\n", |
|
|
167 |
"labelList=np.delete(np.asarray(labelList), bad_fastas)\n", |
|
|
168 |
"vocab=list(np.unique(labelList))\n", |
|
|
169 |
"y=[vocab.index(x) for x in labelList]" |
|
|
170 |
] |
|
|
171 |
}, |
|
|
172 |
{ |
|
|
173 |
"cell_type": "markdown", |
|
|
174 |
"metadata": {}, |
|
|
175 |
"source": [ |
|
|
176 |
"## Correlation Distance in log-scaled space" |
|
|
177 |
] |
|
|
178 |
}, |
|
|
179 |
{ |
|
|
180 |
"cell_type": "markdown", |
|
|
181 |
"metadata": {}, |
|
|
182 |
"source": [ |
|
|
183 |
"### tSNE" |
|
|
184 |
] |
|
|
185 |
}, |
|
|
186 |
{ |
|
|
187 |
"cell_type": "code", |
|
|
188 |
"execution_count": 18, |
|
|
189 |
"metadata": { |
|
|
190 |
"scrolled": true |
|
|
191 |
}, |
|
|
192 |
"outputs": [ |
|
|
193 |
{ |
|
|
194 |
"name": "stdout", |
|
|
195 |
"output_type": "stream", |
|
|
196 |
"text": [ |
|
|
197 |
"CPU times: user 31.1 s, sys: 313 ms, total: 31.4 s\n", |
|
|
198 |
"Wall time: 30.9 s\n" |
|
|
199 |
] |
|
|
200 |
} |
|
|
201 |
], |
|
|
202 |
"source": [ |
|
|
203 |
"tsne = manifold.TSNE(n_components=3, init='pca', perplexity=10, metric=\"correlation\",random_state=0)\n", |
|
|
204 |
"%time X3 = tsne.fit_transform(log_scale(X))\n", |
|
|
205 |
"\n", |
|
|
206 |
"genus = [i.split()[0] for i in labelList]\n", |
|
|
207 |
"genus_vocab=list(np.unique(genus))\n", |
|
|
208 |
"y=[genus_vocab.index(x) for x in genus]\n", |
|
|
209 |
"genus_vocab\n", |
|
|
210 |
"\n", |
|
|
211 |
"X3_df = pd.DataFrame(data=X3, columns=[\"pc1\",'pc2','pc3'], index=labelList)\n", |
|
|
212 |
"\n", |
|
|
213 |
"X3_df[\"genus\"]=genus\n", |
|
|
214 |
"X3_df[\"y\"]=y\n", |
|
|
215 |
"\n", |
|
|
216 |
"genus_df=X3_df.groupby(\"genus\").agg({\"pc1\": list, \"pc2\":list,\"pc3\":list,\"y\":np.mean})" |
|
|
217 |
] |
|
|
218 |
}, |
|
|
219 |
{ |
|
|
220 |
"cell_type": "markdown", |
|
|
221 |
"metadata": {}, |
|
|
222 |
"source": [ |
|
|
223 |
"### Correlation Distance visualisation" |
|
|
224 |
] |
|
|
225 |
}, |
|
|
226 |
{ |
|
|
227 |
"cell_type": "code", |
|
|
228 |
"execution_count": 20, |
|
|
229 |
"metadata": {}, |
|
|
230 |
"outputs": [ |
|
|
231 |
{ |
|
|
232 |
"name": "stderr", |
|
|
233 |
"output_type": "stream", |
|
|
234 |
"text": [ |
|
|
235 |
"/home/serge/anaconda3/envs/bio/lib/python3.6/site-packages/IPython/core/display.py:689: UserWarning:\n", |
|
|
236 |
"\n", |
|
|
237 |
"Consider using IPython.display.IFrame instead\n", |
|
|
238 |
"\n" |
|
|
239 |
] |
|
|
240 |
}, |
|
|
241 |
{ |
|
|
242 |
"data": { |
|
|
243 |
"text/html": [ |
|
|
244 |
"<iframe id=\"igraph\" scrolling=\"no\" style=\"border:none;\" seamless=\"seamless\" src=\"https://plot.ly/~sergeman/12.embed\" height=\"1000px\" width=\"1000px\"></iframe>" |
|
|
245 |
], |
|
|
246 |
"text/plain": [ |
|
|
247 |
"<plotly.tools.PlotlyDisplay object>" |
|
|
248 |
] |
|
|
249 |
}, |
|
|
250 |
"execution_count": 20, |
|
|
251 |
"metadata": {}, |
|
|
252 |
"output_type": "execute_result" |
|
|
253 |
} |
|
|
254 |
], |
|
|
255 |
"source": [ |
|
|
256 |
"data=[]\n", |
|
|
257 |
"for g in genus_df.index:\n", |
|
|
258 |
" trace = go.Scatter3d(\n", |
|
|
259 |
" name = str(g),\n", |
|
|
260 |
" x=genus_df.loc[g,\"pc1\"],\n", |
|
|
261 |
" y=genus_df.loc[g,\"pc2\"],\n", |
|
|
262 |
" z=genus_df.loc[g,\"pc3\"],\n", |
|
|
263 |
" mode='markers',\n", |
|
|
264 |
" marker=dict(\n", |
|
|
265 |
" size=8,\n", |
|
|
266 |
" color=genus_df.loc[g,\"y\"], # set color to an array/list of desired values\n", |
|
|
267 |
" colorscale='Jet', # choose a colorscale\n", |
|
|
268 |
" opacity=0.5)\n", |
|
|
269 |
" )\n", |
|
|
270 |
"\n", |
|
|
271 |
" data.append(trace)\n", |
|
|
272 |
" \n", |
|
|
273 |
"\n", |
|
|
274 |
"layout = go.Layout(\n", |
|
|
275 |
" width=1000,\n", |
|
|
276 |
" height=1000,\n", |
|
|
277 |
" margin=dict(\n", |
|
|
278 |
" l=0,\n", |
|
|
279 |
" r=0,\n", |
|
|
280 |
" b=0,\n", |
|
|
281 |
" t=0\n", |
|
|
282 |
" )\n", |
|
|
283 |
")\n", |
|
|
284 |
"fig = go.Figure(data=data, layout=layout)\n", |
|
|
285 |
"py.iplot(fig, filename='correlation distance ncbi-genomes-2019-04-07 Escherichia,Klebsiella,Bacillus')" |
|
|
286 |
] |
|
|
287 |
}, |
|
|
288 |
{ |
|
|
289 |
"cell_type": "markdown", |
|
|
290 |
"metadata": {}, |
|
|
291 |
"source": [ |
|
|
292 |
"## Eucleadian Distance in log-scaled space" |
|
|
293 |
] |
|
|
294 |
}, |
|
|
295 |
{ |
|
|
296 |
"cell_type": "markdown", |
|
|
297 |
"metadata": {}, |
|
|
298 |
"source": [ |
|
|
299 |
"### tSNE" |
|
|
300 |
] |
|
|
301 |
}, |
|
|
302 |
{ |
|
|
303 |
"cell_type": "code", |
|
|
304 |
"execution_count": 21, |
|
|
305 |
"metadata": {}, |
|
|
306 |
"outputs": [ |
|
|
307 |
{ |
|
|
308 |
"name": "stdout", |
|
|
309 |
"output_type": "stream", |
|
|
310 |
"text": [ |
|
|
311 |
"CPU times: user 25.8 s, sys: 334 ms, total: 26.1 s\n", |
|
|
312 |
"Wall time: 25.5 s\n" |
|
|
313 |
] |
|
|
314 |
} |
|
|
315 |
], |
|
|
316 |
"source": [ |
|
|
317 |
"tsne = manifold.TSNE(n_components=3, init='pca', perplexity=30,random_state=0)\n", |
|
|
318 |
"%time X3 = tsne.fit_transform(log_scale(X))" |
|
|
319 |
] |
|
|
320 |
}, |
|
|
321 |
{ |
|
|
322 |
"cell_type": "code", |
|
|
323 |
"execution_count": 22, |
|
|
324 |
"metadata": {}, |
|
|
325 |
"outputs": [], |
|
|
326 |
"source": [ |
|
|
327 |
"genus = [i.split()[0] for i in labelList]\n", |
|
|
328 |
"genus_vocab=list(np.unique(genus))\n", |
|
|
329 |
"y=[genus_vocab.index(x) for x in genus]\n", |
|
|
330 |
"genus_vocab\n", |
|
|
331 |
"\n", |
|
|
332 |
"X3_df = pd.DataFrame(data=X3, columns=[\"pc1\",'pc2','pc3'], index=labelList)\n", |
|
|
333 |
"\n", |
|
|
334 |
"X3_df[\"genus\"]=genus\n", |
|
|
335 |
"X3_df[\"y\"]=y\n", |
|
|
336 |
"\n", |
|
|
337 |
"genus_df=X3_df.groupby(\"genus\").agg({\"pc1\": list, \"pc2\":list,\"pc3\":list,\"y\":np.mean})" |
|
|
338 |
] |
|
|
339 |
}, |
|
|
340 |
{ |
|
|
341 |
"cell_type": "markdown", |
|
|
342 |
"metadata": {}, |
|
|
343 |
"source": [ |
|
|
344 |
"### Eucleadian Distance Visualisation" |
|
|
345 |
] |
|
|
346 |
}, |
|
|
347 |
{ |
|
|
348 |
"cell_type": "code", |
|
|
349 |
"execution_count": 32, |
|
|
350 |
"metadata": {}, |
|
|
351 |
"outputs": [ |
|
|
352 |
{ |
|
|
353 |
"name": "stderr", |
|
|
354 |
"output_type": "stream", |
|
|
355 |
"text": [ |
|
|
356 |
"/home/serge/anaconda3/envs/bio/lib/python3.6/site-packages/IPython/core/display.py:689: UserWarning:\n", |
|
|
357 |
"\n", |
|
|
358 |
"Consider using IPython.display.IFrame instead\n", |
|
|
359 |
"\n" |
|
|
360 |
] |
|
|
361 |
}, |
|
|
362 |
{ |
|
|
363 |
"data": { |
|
|
364 |
"text/html": [ |
|
|
365 |
"<iframe id=\"igraph\" scrolling=\"no\" style=\"border:none;\" seamless=\"seamless\" src=\"https://plot.ly/~sergeman/14.embed\" height=\"1000px\" width=\"1000px\"></iframe>" |
|
|
366 |
], |
|
|
367 |
"text/plain": [ |
|
|
368 |
"<plotly.tools.PlotlyDisplay object>" |
|
|
369 |
] |
|
|
370 |
}, |
|
|
371 |
"execution_count": 32, |
|
|
372 |
"metadata": {}, |
|
|
373 |
"output_type": "execute_result" |
|
|
374 |
} |
|
|
375 |
], |
|
|
376 |
"source": [ |
|
|
377 |
"data=[]\n", |
|
|
378 |
"for g in genus_df.index:\n", |
|
|
379 |
" trace = go.Scatter3d(\n", |
|
|
380 |
" name = str(g),\n", |
|
|
381 |
" x=genus_df.loc[g,\"pc1\"],\n", |
|
|
382 |
" y=genus_df.loc[g,\"pc2\"],\n", |
|
|
383 |
" z=genus_df.loc[g,\"pc3\"],\n", |
|
|
384 |
" mode='markers',\n", |
|
|
385 |
" marker=dict(\n", |
|
|
386 |
" size=8,\n", |
|
|
387 |
" color=genus_df.loc[g,\"y\"]+1, # set color to an array/list of desired values\n", |
|
|
388 |
" colorscale='YlGnBu', # choose a colorscale\n", |
|
|
389 |
" opacity=0.5)\n", |
|
|
390 |
" )\n", |
|
|
391 |
"\n", |
|
|
392 |
" data.append(trace)\n", |
|
|
393 |
" \n", |
|
|
394 |
"\n", |
|
|
395 |
"layout = go.Layout(\n", |
|
|
396 |
" width=1000,\n", |
|
|
397 |
" height=1000,\n", |
|
|
398 |
" margin=dict(\n", |
|
|
399 |
" l=0,\n", |
|
|
400 |
" r=0,\n", |
|
|
401 |
" b=0,\n", |
|
|
402 |
" t=0\n", |
|
|
403 |
" )\n", |
|
|
404 |
")\n", |
|
|
405 |
"fig = go.Figure(data=data, layout=layout)\n", |
|
|
406 |
"py.iplot(fig, filename='eucledian distance metric by genus Escherichia|Klebsiella|Bacillus')" |
|
|
407 |
] |
|
|
408 |
}, |
|
|
409 |
{ |
|
|
410 |
"cell_type": "markdown", |
|
|
411 |
"metadata": {}, |
|
|
412 |
"source": [ |
|
|
413 |
"## Eucleadian Distance in unmodified space" |
|
|
414 |
] |
|
|
415 |
}, |
|
|
416 |
{ |
|
|
417 |
"cell_type": "markdown", |
|
|
418 |
"metadata": {}, |
|
|
419 |
"source": [ |
|
|
420 |
"### tSNE" |
|
|
421 |
] |
|
|
422 |
}, |
|
|
423 |
{ |
|
|
424 |
"cell_type": "code", |
|
|
425 |
"execution_count": 27, |
|
|
426 |
"metadata": {}, |
|
|
427 |
"outputs": [ |
|
|
428 |
{ |
|
|
429 |
"name": "stdout", |
|
|
430 |
"output_type": "stream", |
|
|
431 |
"text": [ |
|
|
432 |
"CPU times: user 41.5 s, sys: 313 ms, total: 41.8 s\n", |
|
|
433 |
"Wall time: 41.2 s\n" |
|
|
434 |
] |
|
|
435 |
} |
|
|
436 |
], |
|
|
437 |
"source": [ |
|
|
438 |
"tsne = manifold.TSNE(n_components=3, init='pca', perplexity=30,random_state=0)\n", |
|
|
439 |
"%time X3 = tsne.fit_transform(X)" |
|
|
440 |
] |
|
|
441 |
}, |
|
|
442 |
{ |
|
|
443 |
"cell_type": "code", |
|
|
444 |
"execution_count": 28, |
|
|
445 |
"metadata": {}, |
|
|
446 |
"outputs": [], |
|
|
447 |
"source": [ |
|
|
448 |
"genus = [i.split()[0] for i in labelList]\n", |
|
|
449 |
"genus_vocab=list(np.unique(genus))\n", |
|
|
450 |
"y=[genus_vocab.index(x) for x in genus]\n", |
|
|
451 |
"genus_vocab\n", |
|
|
452 |
"\n", |
|
|
453 |
"X3_df = pd.DataFrame(data=X3, columns=[\"pc1\",'pc2','pc3'], index=labelList)\n", |
|
|
454 |
"\n", |
|
|
455 |
"X3_df[\"genus\"]=genus\n", |
|
|
456 |
"X3_df[\"y\"]=y\n", |
|
|
457 |
"\n", |
|
|
458 |
"genus_df=X3_df.groupby(\"genus\").agg({\"pc1\": list, \"pc2\":list,\"pc3\":list,\"y\":np.mean})" |
|
|
459 |
] |
|
|
460 |
}, |
|
|
461 |
{ |
|
|
462 |
"cell_type": "markdown", |
|
|
463 |
"metadata": {}, |
|
|
464 |
"source": [ |
|
|
465 |
"### Eucleadian Distance Visualisation" |
|
|
466 |
] |
|
|
467 |
}, |
|
|
468 |
{ |
|
|
469 |
"cell_type": "code", |
|
|
470 |
"execution_count": 29, |
|
|
471 |
"metadata": {}, |
|
|
472 |
"outputs": [ |
|
|
473 |
{ |
|
|
474 |
"name": "stderr", |
|
|
475 |
"output_type": "stream", |
|
|
476 |
"text": [ |
|
|
477 |
"/home/serge/anaconda3/envs/bio/lib/python3.6/site-packages/IPython/core/display.py:689: UserWarning:\n", |
|
|
478 |
"\n", |
|
|
479 |
"Consider using IPython.display.IFrame instead\n", |
|
|
480 |
"\n" |
|
|
481 |
] |
|
|
482 |
}, |
|
|
483 |
{ |
|
|
484 |
"data": { |
|
|
485 |
"text/html": [ |
|
|
486 |
"<iframe id=\"igraph\" scrolling=\"no\" style=\"border:none;\" seamless=\"seamless\" src=\"https://plot.ly/~sergeman/16.embed\" height=\"1000px\" width=\"1000px\"></iframe>" |
|
|
487 |
], |
|
|
488 |
"text/plain": [ |
|
|
489 |
"<plotly.tools.PlotlyDisplay object>" |
|
|
490 |
] |
|
|
491 |
}, |
|
|
492 |
"execution_count": 29, |
|
|
493 |
"metadata": {}, |
|
|
494 |
"output_type": "execute_result" |
|
|
495 |
} |
|
|
496 |
], |
|
|
497 |
"source": [ |
|
|
498 |
"data=[]\n", |
|
|
499 |
"for g in genus_df.index:\n", |
|
|
500 |
" trace = go.Scatter3d(\n", |
|
|
501 |
" name = str(g),\n", |
|
|
502 |
" x=genus_df.loc[g,\"pc1\"],\n", |
|
|
503 |
" y=genus_df.loc[g,\"pc2\"],\n", |
|
|
504 |
" z=genus_df.loc[g,\"pc3\"],\n", |
|
|
505 |
" mode='markers',\n", |
|
|
506 |
" marker=dict(\n", |
|
|
507 |
" size=8,\n", |
|
|
508 |
" color=genus_df.loc[g,\"y\"], # set color to an array/list of desired values\n", |
|
|
509 |
" colorscale='Jet', # choose a colorscale\n", |
|
|
510 |
" opacity=0.5)\n", |
|
|
511 |
" )\n", |
|
|
512 |
"\n", |
|
|
513 |
" data.append(trace)\n", |
|
|
514 |
" \n", |
|
|
515 |
"\n", |
|
|
516 |
"layout = go.Layout(\n", |
|
|
517 |
" width=1000,\n", |
|
|
518 |
" height=1000,\n", |
|
|
519 |
" margin=dict(\n", |
|
|
520 |
" l=0,\n", |
|
|
521 |
" r=0,\n", |
|
|
522 |
" b=0,\n", |
|
|
523 |
" t=0\n", |
|
|
524 |
" )\n", |
|
|
525 |
")\n", |
|
|
526 |
"fig = go.Figure(data=data, layout=layout)\n", |
|
|
527 |
"py.iplot(fig, filename='eucledian distance in native space Escherichia|Klebsiella|Bacillus')" |
|
|
528 |
] |
|
|
529 |
}, |
|
|
530 |
{ |
|
|
531 |
"cell_type": "markdown", |
|
|
532 |
"metadata": {}, |
|
|
533 |
"source": [ |
|
|
534 |
"## Genome Inventory" |
|
|
535 |
] |
|
|
536 |
}, |
|
|
537 |
{ |
|
|
538 |
"cell_type": "code", |
|
|
539 |
"execution_count": 26, |
|
|
540 |
"metadata": {}, |
|
|
541 |
"outputs": [], |
|
|
542 |
"source": [ |
|
|
543 |
"inventory = pd.DataFrame(data=[l.split()[1:3] for l in all_fastas], columns=[\"genus\",\"species\" ])" |
|
|
544 |
] |
|
|
545 |
}, |
|
|
546 |
{ |
|
|
547 |
"cell_type": "code", |
|
|
548 |
"execution_count": 30, |
|
|
549 |
"metadata": { |
|
|
550 |
"scrolled": true |
|
|
551 |
}, |
|
|
552 |
"outputs": [ |
|
|
553 |
{ |
|
|
554 |
"data": { |
|
|
555 |
"text/html": [ |
|
|
556 |
"<div>\n", |
|
|
557 |
"<style scoped>\n", |
|
|
558 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
559 |
" vertical-align: middle;\n", |
|
|
560 |
" }\n", |
|
|
561 |
"\n", |
|
|
562 |
" .dataframe tbody tr th {\n", |
|
|
563 |
" vertical-align: top;\n", |
|
|
564 |
" }\n", |
|
|
565 |
"\n", |
|
|
566 |
" .dataframe thead th {\n", |
|
|
567 |
" text-align: right;\n", |
|
|
568 |
" }\n", |
|
|
569 |
"</style>\n", |
|
|
570 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
571 |
" <thead>\n", |
|
|
572 |
" <tr style=\"text-align: right;\">\n", |
|
|
573 |
" <th></th>\n", |
|
|
574 |
" <th>species</th>\n", |
|
|
575 |
" </tr>\n", |
|
|
576 |
" <tr>\n", |
|
|
577 |
" <th>genus</th>\n", |
|
|
578 |
" <th></th>\n", |
|
|
579 |
" </tr>\n", |
|
|
580 |
" </thead>\n", |
|
|
581 |
" <tbody>\n", |
|
|
582 |
" <tr>\n", |
|
|
583 |
" <th>Escherichia</th>\n", |
|
|
584 |
" <td>2239</td>\n", |
|
|
585 |
" </tr>\n", |
|
|
586 |
" <tr>\n", |
|
|
587 |
" <th>Klebsiella</th>\n", |
|
|
588 |
" <td>1718</td>\n", |
|
|
589 |
" </tr>\n", |
|
|
590 |
" <tr>\n", |
|
|
591 |
" <th>Salmonella</th>\n", |
|
|
592 |
" <td>1183</td>\n", |
|
|
593 |
" </tr>\n", |
|
|
594 |
" <tr>\n", |
|
|
595 |
" <th>Bacillus</th>\n", |
|
|
596 |
" <td>1172</td>\n", |
|
|
597 |
" </tr>\n", |
|
|
598 |
" <tr>\n", |
|
|
599 |
" <th>Lactobacillus</th>\n", |
|
|
600 |
" <td>953</td>\n", |
|
|
601 |
" </tr>\n", |
|
|
602 |
" <tr>\n", |
|
|
603 |
" <th>Staphylococcus</th>\n", |
|
|
604 |
" <td>889</td>\n", |
|
|
605 |
" </tr>\n", |
|
|
606 |
" <tr>\n", |
|
|
607 |
" <th>Burkholderia</th>\n", |
|
|
608 |
" <td>650</td>\n", |
|
|
609 |
" </tr>\n", |
|
|
610 |
" <tr>\n", |
|
|
611 |
" <th>Enterococcus</th>\n", |
|
|
612 |
" <td>626</td>\n", |
|
|
613 |
" </tr>\n", |
|
|
614 |
" <tr>\n", |
|
|
615 |
" <th>Pseudomonas</th>\n", |
|
|
616 |
" <td>613</td>\n", |
|
|
617 |
" </tr>\n", |
|
|
618 |
" <tr>\n", |
|
|
619 |
" <th>Streptococcus</th>\n", |
|
|
620 |
" <td>564</td>\n", |
|
|
621 |
" </tr>\n", |
|
|
622 |
" <tr>\n", |
|
|
623 |
" <th>Acinetobacter</th>\n", |
|
|
624 |
" <td>531</td>\n", |
|
|
625 |
" </tr>\n", |
|
|
626 |
" <tr>\n", |
|
|
627 |
" <th>Bordetella</th>\n", |
|
|
628 |
" <td>504</td>\n", |
|
|
629 |
" </tr>\n", |
|
|
630 |
" <tr>\n", |
|
|
631 |
" <th>Vibrio</th>\n", |
|
|
632 |
" <td>474</td>\n", |
|
|
633 |
" </tr>\n", |
|
|
634 |
" <tr>\n", |
|
|
635 |
" <th>Xanthomonas</th>\n", |
|
|
636 |
" <td>395</td>\n", |
|
|
637 |
" </tr>\n", |
|
|
638 |
" <tr>\n", |
|
|
639 |
" <th>Mycobacterium</th>\n", |
|
|
640 |
" <td>368</td>\n", |
|
|
641 |
" </tr>\n", |
|
|
642 |
" <tr>\n", |
|
|
643 |
" <th>Borrelia</th>\n", |
|
|
644 |
" <td>347</td>\n", |
|
|
645 |
" </tr>\n", |
|
|
646 |
" <tr>\n", |
|
|
647 |
" <th>Campylobacter</th>\n", |
|
|
648 |
" <td>339</td>\n", |
|
|
649 |
" </tr>\n", |
|
|
650 |
" <tr>\n", |
|
|
651 |
" <th>Rhizobium</th>\n", |
|
|
652 |
" <td>307</td>\n", |
|
|
653 |
" </tr>\n", |
|
|
654 |
" <tr>\n", |
|
|
655 |
" <th>Enterobacter</th>\n", |
|
|
656 |
" <td>298</td>\n", |
|
|
657 |
" </tr>\n", |
|
|
658 |
" <tr>\n", |
|
|
659 |
" <th>Mycoplasma</th>\n", |
|
|
660 |
" <td>290</td>\n", |
|
|
661 |
" </tr>\n", |
|
|
662 |
" <tr>\n", |
|
|
663 |
" <th>Corynebacterium</th>\n", |
|
|
664 |
" <td>258</td>\n", |
|
|
665 |
" </tr>\n", |
|
|
666 |
" <tr>\n", |
|
|
667 |
" <th>Phaeobacter</th>\n", |
|
|
668 |
" <td>256</td>\n", |
|
|
669 |
" </tr>\n", |
|
|
670 |
" <tr>\n", |
|
|
671 |
" <th>Yersinia</th>\n", |
|
|
672 |
" <td>243</td>\n", |
|
|
673 |
" </tr>\n", |
|
|
674 |
" <tr>\n", |
|
|
675 |
" <th>Brucella</th>\n", |
|
|
676 |
" <td>233</td>\n", |
|
|
677 |
" </tr>\n", |
|
|
678 |
" <tr>\n", |
|
|
679 |
" <th>Clostridium</th>\n", |
|
|
680 |
" <td>228</td>\n", |
|
|
681 |
" </tr>\n", |
|
|
682 |
" <tr>\n", |
|
|
683 |
" <th>Listeria</th>\n", |
|
|
684 |
" <td>227</td>\n", |
|
|
685 |
" </tr>\n", |
|
|
686 |
" <tr>\n", |
|
|
687 |
" <th>Streptomyces</th>\n", |
|
|
688 |
" <td>225</td>\n", |
|
|
689 |
" </tr>\n", |
|
|
690 |
" <tr>\n", |
|
|
691 |
" <th>Chlamydia</th>\n", |
|
|
692 |
" <td>202</td>\n", |
|
|
693 |
" </tr>\n", |
|
|
694 |
" <tr>\n", |
|
|
695 |
" <th>Helicobacter</th>\n", |
|
|
696 |
" <td>187</td>\n", |
|
|
697 |
" </tr>\n", |
|
|
698 |
" <tr>\n", |
|
|
699 |
" <th>Candidatus</th>\n", |
|
|
700 |
" <td>187</td>\n", |
|
|
701 |
" </tr>\n", |
|
|
702 |
" <tr>\n", |
|
|
703 |
" <th>...</th>\n", |
|
|
704 |
" <td>...</td>\n", |
|
|
705 |
" </tr>\n", |
|
|
706 |
" <tr>\n", |
|
|
707 |
" <th>'Deinococcus</th>\n", |
|
|
708 |
" <td>1</td>\n", |
|
|
709 |
" </tr>\n", |
|
|
710 |
" <tr>\n", |
|
|
711 |
" <th>Mariniflexile</th>\n", |
|
|
712 |
" <td>1</td>\n", |
|
|
713 |
" </tr>\n", |
|
|
714 |
" <tr>\n", |
|
|
715 |
" <th>Marinithermus</th>\n", |
|
|
716 |
" <td>1</td>\n", |
|
|
717 |
" </tr>\n", |
|
|
718 |
" <tr>\n", |
|
|
719 |
" <th>Lactobacillales</th>\n", |
|
|
720 |
" <td>1</td>\n", |
|
|
721 |
" </tr>\n", |
|
|
722 |
" <tr>\n", |
|
|
723 |
" <th>Marinobacterium</th>\n", |
|
|
724 |
" <td>1</td>\n", |
|
|
725 |
" </tr>\n", |
|
|
726 |
" <tr>\n", |
|
|
727 |
" <th>Megamonas</th>\n", |
|
|
728 |
" <td>1</td>\n", |
|
|
729 |
" </tr>\n", |
|
|
730 |
" <tr>\n", |
|
|
731 |
" <th>Melioribacter</th>\n", |
|
|
732 |
" <td>1</td>\n", |
|
|
733 |
" </tr>\n", |
|
|
734 |
" <tr>\n", |
|
|
735 |
" <th>Melittangium</th>\n", |
|
|
736 |
" <td>1</td>\n", |
|
|
737 |
" </tr>\n", |
|
|
738 |
" <tr>\n", |
|
|
739 |
" <th>Methylobacillus</th>\n", |
|
|
740 |
" <td>1</td>\n", |
|
|
741 |
" </tr>\n", |
|
|
742 |
" <tr>\n", |
|
|
743 |
" <th>Methylocaldum</th>\n", |
|
|
744 |
" <td>1</td>\n", |
|
|
745 |
" </tr>\n", |
|
|
746 |
" <tr>\n", |
|
|
747 |
" <th>Magnetococcus</th>\n", |
|
|
748 |
" <td>1</td>\n", |
|
|
749 |
" </tr>\n", |
|
|
750 |
" <tr>\n", |
|
|
751 |
" <th>Mageeibacillus</th>\n", |
|
|
752 |
" <td>1</td>\n", |
|
|
753 |
" </tr>\n", |
|
|
754 |
" <tr>\n", |
|
|
755 |
" <th>Lysinimonas</th>\n", |
|
|
756 |
" <td>1</td>\n", |
|
|
757 |
" </tr>\n", |
|
|
758 |
" <tr>\n", |
|
|
759 |
" <th>Luteitalea</th>\n", |
|
|
760 |
" <td>1</td>\n", |
|
|
761 |
" </tr>\n", |
|
|
762 |
" <tr>\n", |
|
|
763 |
" <th>Lacunisphaera</th>\n", |
|
|
764 |
" <td>1</td>\n", |
|
|
765 |
" </tr>\n", |
|
|
766 |
" <tr>\n", |
|
|
767 |
" <th>Lautropia</th>\n", |
|
|
768 |
" <td>1</td>\n", |
|
|
769 |
" </tr>\n", |
|
|
770 |
" <tr>\n", |
|
|
771 |
" <th>Leadbetterella</th>\n", |
|
|
772 |
" <td>1</td>\n", |
|
|
773 |
" </tr>\n", |
|
|
774 |
" <tr>\n", |
|
|
775 |
" <th>Leminorella</th>\n", |
|
|
776 |
" <td>1</td>\n", |
|
|
777 |
" </tr>\n", |
|
|
778 |
" <tr>\n", |
|
|
779 |
" <th>Lentibacillus</th>\n", |
|
|
780 |
" <td>1</td>\n", |
|
|
781 |
" </tr>\n", |
|
|
782 |
" <tr>\n", |
|
|
783 |
" <th>Lentzea</th>\n", |
|
|
784 |
" <td>1</td>\n", |
|
|
785 |
" </tr>\n", |
|
|
786 |
" <tr>\n", |
|
|
787 |
" <th>Leptothrix</th>\n", |
|
|
788 |
" <td>1</td>\n", |
|
|
789 |
" </tr>\n", |
|
|
790 |
" <tr>\n", |
|
|
791 |
" <th>Levyella</th>\n", |
|
|
792 |
" <td>1</td>\n", |
|
|
793 |
" </tr>\n", |
|
|
794 |
" <tr>\n", |
|
|
795 |
" <th>Limnobaculum</th>\n", |
|
|
796 |
" <td>1</td>\n", |
|
|
797 |
" </tr>\n", |
|
|
798 |
" <tr>\n", |
|
|
799 |
" <th>Limnochorda</th>\n", |
|
|
800 |
" <td>1</td>\n", |
|
|
801 |
" </tr>\n", |
|
|
802 |
" <tr>\n", |
|
|
803 |
" <th>Litorilituus</th>\n", |
|
|
804 |
" <td>1</td>\n", |
|
|
805 |
" </tr>\n", |
|
|
806 |
" <tr>\n", |
|
|
807 |
" <th>Lonsdalea</th>\n", |
|
|
808 |
" <td>1</td>\n", |
|
|
809 |
" </tr>\n", |
|
|
810 |
" <tr>\n", |
|
|
811 |
" <th>Luteibacter</th>\n", |
|
|
812 |
" <td>1</td>\n", |
|
|
813 |
" </tr>\n", |
|
|
814 |
" <tr>\n", |
|
|
815 |
" <th>Luteipulveratus</th>\n", |
|
|
816 |
" <td>1</td>\n", |
|
|
817 |
" </tr>\n", |
|
|
818 |
" <tr>\n", |
|
|
819 |
" <th>secondary</th>\n", |
|
|
820 |
" <td>1</td>\n", |
|
|
821 |
" </tr>\n", |
|
|
822 |
" <tr>\n", |
|
|
823 |
" <th>plasmid1</th>\n", |
|
|
824 |
" <td>0</td>\n", |
|
|
825 |
" </tr>\n", |
|
|
826 |
" </tbody>\n", |
|
|
827 |
"</table>\n", |
|
|
828 |
"<p>1120 rows × 1 columns</p>\n", |
|
|
829 |
"</div>" |
|
|
830 |
], |
|
|
831 |
"text/plain": [ |
|
|
832 |
" species\n", |
|
|
833 |
"genus \n", |
|
|
834 |
"Escherichia 2239\n", |
|
|
835 |
"Klebsiella 1718\n", |
|
|
836 |
"Salmonella 1183\n", |
|
|
837 |
"Bacillus 1172\n", |
|
|
838 |
"Lactobacillus 953\n", |
|
|
839 |
"Staphylococcus 889\n", |
|
|
840 |
"Burkholderia 650\n", |
|
|
841 |
"Enterococcus 626\n", |
|
|
842 |
"Pseudomonas 613\n", |
|
|
843 |
"Streptococcus 564\n", |
|
|
844 |
"Acinetobacter 531\n", |
|
|
845 |
"Bordetella 504\n", |
|
|
846 |
"Vibrio 474\n", |
|
|
847 |
"Xanthomonas 395\n", |
|
|
848 |
"Mycobacterium 368\n", |
|
|
849 |
"Borrelia 347\n", |
|
|
850 |
"Campylobacter 339\n", |
|
|
851 |
"Rhizobium 307\n", |
|
|
852 |
"Enterobacter 298\n", |
|
|
853 |
"Mycoplasma 290\n", |
|
|
854 |
"Corynebacterium 258\n", |
|
|
855 |
"Phaeobacter 256\n", |
|
|
856 |
"Yersinia 243\n", |
|
|
857 |
"Brucella 233\n", |
|
|
858 |
"Clostridium 228\n", |
|
|
859 |
"Listeria 227\n", |
|
|
860 |
"Streptomyces 225\n", |
|
|
861 |
"Chlamydia 202\n", |
|
|
862 |
"Helicobacter 187\n", |
|
|
863 |
"Candidatus 187\n", |
|
|
864 |
"... ...\n", |
|
|
865 |
"'Deinococcus 1\n", |
|
|
866 |
"Mariniflexile 1\n", |
|
|
867 |
"Marinithermus 1\n", |
|
|
868 |
"Lactobacillales 1\n", |
|
|
869 |
"Marinobacterium 1\n", |
|
|
870 |
"Megamonas 1\n", |
|
|
871 |
"Melioribacter 1\n", |
|
|
872 |
"Melittangium 1\n", |
|
|
873 |
"Methylobacillus 1\n", |
|
|
874 |
"Methylocaldum 1\n", |
|
|
875 |
"Magnetococcus 1\n", |
|
|
876 |
"Mageeibacillus 1\n", |
|
|
877 |
"Lysinimonas 1\n", |
|
|
878 |
"Luteitalea 1\n", |
|
|
879 |
"Lacunisphaera 1\n", |
|
|
880 |
"Lautropia 1\n", |
|
|
881 |
"Leadbetterella 1\n", |
|
|
882 |
"Leminorella 1\n", |
|
|
883 |
"Lentibacillus 1\n", |
|
|
884 |
"Lentzea 1\n", |
|
|
885 |
"Leptothrix 1\n", |
|
|
886 |
"Levyella 1\n", |
|
|
887 |
"Limnobaculum 1\n", |
|
|
888 |
"Limnochorda 1\n", |
|
|
889 |
"Litorilituus 1\n", |
|
|
890 |
"Lonsdalea 1\n", |
|
|
891 |
"Luteibacter 1\n", |
|
|
892 |
"Luteipulveratus 1\n", |
|
|
893 |
"secondary 1\n", |
|
|
894 |
"plasmid1 0\n", |
|
|
895 |
"\n", |
|
|
896 |
"[1120 rows x 1 columns]" |
|
|
897 |
] |
|
|
898 |
}, |
|
|
899 |
"execution_count": 30, |
|
|
900 |
"metadata": {}, |
|
|
901 |
"output_type": "execute_result" |
|
|
902 |
} |
|
|
903 |
], |
|
|
904 |
"source": [ |
|
|
905 |
"inventory.groupby(\"genus\").agg({\"species\":\"count\"}).sort_values(\"species\",ascending=False)" |
|
|
906 |
] |
|
|
907 |
}, |
|
|
908 |
{ |
|
|
909 |
"cell_type": "code", |
|
|
910 |
"execution_count": 24, |
|
|
911 |
"metadata": { |
|
|
912 |
"scrolled": false |
|
|
913 |
}, |
|
|
914 |
"outputs": [ |
|
|
915 |
{ |
|
|
916 |
"data": { |
|
|
917 |
"text/html": [ |
|
|
918 |
"<div>\n", |
|
|
919 |
"<style scoped>\n", |
|
|
920 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
921 |
" vertical-align: middle;\n", |
|
|
922 |
" }\n", |
|
|
923 |
"\n", |
|
|
924 |
" .dataframe tbody tr th {\n", |
|
|
925 |
" vertical-align: top;\n", |
|
|
926 |
" }\n", |
|
|
927 |
"\n", |
|
|
928 |
" .dataframe thead th {\n", |
|
|
929 |
" text-align: right;\n", |
|
|
930 |
" }\n", |
|
|
931 |
"</style>\n", |
|
|
932 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
933 |
" <thead>\n", |
|
|
934 |
" <tr style=\"text-align: right;\">\n", |
|
|
935 |
" <th></th>\n", |
|
|
936 |
" <th></th>\n", |
|
|
937 |
" <th>count</th>\n", |
|
|
938 |
" </tr>\n", |
|
|
939 |
" <tr>\n", |
|
|
940 |
" <th>genus</th>\n", |
|
|
941 |
" <th>species</th>\n", |
|
|
942 |
" <th></th>\n", |
|
|
943 |
" </tr>\n", |
|
|
944 |
" </thead>\n", |
|
|
945 |
" <tbody>\n", |
|
|
946 |
" <tr>\n", |
|
|
947 |
" <th>'Catharanthus</th>\n", |
|
|
948 |
" <th>roseus'</th>\n", |
|
|
949 |
" <td>2</td>\n", |
|
|
950 |
" </tr>\n", |
|
|
951 |
" <tr>\n", |
|
|
952 |
" <th>'Deinococcus</th>\n", |
|
|
953 |
" <th>soli'</th>\n", |
|
|
954 |
" <td>1</td>\n", |
|
|
955 |
" </tr>\n", |
|
|
956 |
" <tr>\n", |
|
|
957 |
" <th>'Nostoc</th>\n", |
|
|
958 |
" <th>azollae'</th>\n", |
|
|
959 |
" <td>3</td>\n", |
|
|
960 |
" </tr>\n", |
|
|
961 |
" <tr>\n", |
|
|
962 |
" <th>18,711,729</th>\n", |
|
|
963 |
" <th>reads</th>\n", |
|
|
964 |
" <td>1</td>\n", |
|
|
965 |
" </tr>\n", |
|
|
966 |
" <tr>\n", |
|
|
967 |
" <th>Acaryochloris</th>\n", |
|
|
968 |
" <th>marina</th>\n", |
|
|
969 |
" <td>10</td>\n", |
|
|
970 |
" </tr>\n", |
|
|
971 |
" <tr>\n", |
|
|
972 |
" <th rowspan=\"10\" valign=\"top\">Acetobacter</th>\n", |
|
|
973 |
" <th>aceti</th>\n", |
|
|
974 |
" <td>1</td>\n", |
|
|
975 |
" </tr>\n", |
|
|
976 |
" <tr>\n", |
|
|
977 |
" <th>ascendens</th>\n", |
|
|
978 |
" <td>1</td>\n", |
|
|
979 |
" </tr>\n", |
|
|
980 |
" <tr>\n", |
|
|
981 |
" <th>orientalis</th>\n", |
|
|
982 |
" <td>2</td>\n", |
|
|
983 |
" </tr>\n", |
|
|
984 |
" <tr>\n", |
|
|
985 |
" <th>oryzifermentans</th>\n", |
|
|
986 |
" <td>1</td>\n", |
|
|
987 |
" </tr>\n", |
|
|
988 |
" <tr>\n", |
|
|
989 |
" <th>pasteurianus</th>\n", |
|
|
990 |
" <td>91</td>\n", |
|
|
991 |
" </tr>\n", |
|
|
992 |
" <tr>\n", |
|
|
993 |
" <th>persici</th>\n", |
|
|
994 |
" <td>2</td>\n", |
|
|
995 |
" </tr>\n", |
|
|
996 |
" <tr>\n", |
|
|
997 |
" <th>pomorum</th>\n", |
|
|
998 |
" <td>7</td>\n", |
|
|
999 |
" </tr>\n", |
|
|
1000 |
" <tr>\n", |
|
|
1001 |
" <th>senegalensis</th>\n", |
|
|
1002 |
" <td>2</td>\n", |
|
|
1003 |
" </tr>\n", |
|
|
1004 |
" <tr>\n", |
|
|
1005 |
" <th>sp.</th>\n", |
|
|
1006 |
" <td>7</td>\n", |
|
|
1007 |
" </tr>\n", |
|
|
1008 |
" <tr>\n", |
|
|
1009 |
" <th>tropicalis</th>\n", |
|
|
1010 |
" <td>2</td>\n", |
|
|
1011 |
" </tr>\n", |
|
|
1012 |
" <tr>\n", |
|
|
1013 |
" <th>Acetobacterium</th>\n", |
|
|
1014 |
" <th>woodii</th>\n", |
|
|
1015 |
" <td>1</td>\n", |
|
|
1016 |
" </tr>\n", |
|
|
1017 |
" <tr>\n", |
|
|
1018 |
" <th>Acetohalobium</th>\n", |
|
|
1019 |
" <th>arabaticum</th>\n", |
|
|
1020 |
" <td>1</td>\n", |
|
|
1021 |
" </tr>\n", |
|
|
1022 |
" <tr>\n", |
|
|
1023 |
" <th>Acetomicrobium</th>\n", |
|
|
1024 |
" <th>mobile</th>\n", |
|
|
1025 |
" <td>1</td>\n", |
|
|
1026 |
" </tr>\n", |
|
|
1027 |
" <tr>\n", |
|
|
1028 |
" <th rowspan=\"4\" valign=\"top\">Acholeplasma</th>\n", |
|
|
1029 |
" <th>axanthum</th>\n", |
|
|
1030 |
" <td>1</td>\n", |
|
|
1031 |
" </tr>\n", |
|
|
1032 |
" <tr>\n", |
|
|
1033 |
" <th>hippikon</th>\n", |
|
|
1034 |
" <td>2</td>\n", |
|
|
1035 |
" </tr>\n", |
|
|
1036 |
" <tr>\n", |
|
|
1037 |
" <th>laidlawii</th>\n", |
|
|
1038 |
" <td>2</td>\n", |
|
|
1039 |
" </tr>\n", |
|
|
1040 |
" <tr>\n", |
|
|
1041 |
" <th>oculi</th>\n", |
|
|
1042 |
" <td>1</td>\n", |
|
|
1043 |
" </tr>\n", |
|
|
1044 |
" <tr>\n", |
|
|
1045 |
" <th rowspan=\"5\" valign=\"top\">Achromobacter</th>\n", |
|
|
1046 |
" <th>denitrificans</th>\n", |
|
|
1047 |
" <td>3</td>\n", |
|
|
1048 |
" </tr>\n", |
|
|
1049 |
" <tr>\n", |
|
|
1050 |
" <th>insolitus</th>\n", |
|
|
1051 |
" <td>4</td>\n", |
|
|
1052 |
" </tr>\n", |
|
|
1053 |
" <tr>\n", |
|
|
1054 |
" <th>sp.</th>\n", |
|
|
1055 |
" <td>2</td>\n", |
|
|
1056 |
" </tr>\n", |
|
|
1057 |
" <tr>\n", |
|
|
1058 |
" <th>spanius</th>\n", |
|
|
1059 |
" <td>4</td>\n", |
|
|
1060 |
" </tr>\n", |
|
|
1061 |
" <tr>\n", |
|
|
1062 |
" <th>xylosoxidans</th>\n", |
|
|
1063 |
" <td>11</td>\n", |
|
|
1064 |
" </tr>\n", |
|
|
1065 |
" <tr>\n", |
|
|
1066 |
" <th rowspan=\"2\" valign=\"top\">Acidaminococcus</th>\n", |
|
|
1067 |
" <th>fermentans</th>\n", |
|
|
1068 |
" <td>1</td>\n", |
|
|
1069 |
" </tr>\n", |
|
|
1070 |
" <tr>\n", |
|
|
1071 |
" <th>intestini</th>\n", |
|
|
1072 |
" <td>1</td>\n", |
|
|
1073 |
" </tr>\n", |
|
|
1074 |
" <tr>\n", |
|
|
1075 |
" <th>Acidiferrobacter</th>\n", |
|
|
1076 |
" <th>sp.</th>\n", |
|
|
1077 |
" <td>1</td>\n", |
|
|
1078 |
" </tr>\n", |
|
|
1079 |
" <tr>\n", |
|
|
1080 |
" <th>...</th>\n", |
|
|
1081 |
" <th>...</th>\n", |
|
|
1082 |
" <td>...</td>\n", |
|
|
1083 |
" </tr>\n", |
|
|
1084 |
" <tr>\n", |
|
|
1085 |
" <th>Zymobacter</th>\n", |
|
|
1086 |
" <th>palmae</th>\n", |
|
|
1087 |
" <td>2</td>\n", |
|
|
1088 |
" </tr>\n", |
|
|
1089 |
" <tr>\n", |
|
|
1090 |
" <th>Zymomonas</th>\n", |
|
|
1091 |
" <th>mobilis</th>\n", |
|
|
1092 |
" <td>49</td>\n", |
|
|
1093 |
" </tr>\n", |
|
|
1094 |
" <tr>\n", |
|
|
1095 |
" <th>[Arcobacter]</th>\n", |
|
|
1096 |
" <th>porcinus</th>\n", |
|
|
1097 |
" <td>1</td>\n", |
|
|
1098 |
" </tr>\n", |
|
|
1099 |
" <tr>\n", |
|
|
1100 |
" <th>[Bacillus</th>\n", |
|
|
1101 |
" <th>thuringiensis]</th>\n", |
|
|
1102 |
" <td>2</td>\n", |
|
|
1103 |
" </tr>\n", |
|
|
1104 |
" <tr>\n", |
|
|
1105 |
" <th rowspan=\"2\" valign=\"top\">[Bacillus]</th>\n", |
|
|
1106 |
" <th>caldolyticus</th>\n", |
|
|
1107 |
" <td>2</td>\n", |
|
|
1108 |
" </tr>\n", |
|
|
1109 |
" <tr>\n", |
|
|
1110 |
" <th>selenitireducens</th>\n", |
|
|
1111 |
" <td>1</td>\n", |
|
|
1112 |
" </tr>\n", |
|
|
1113 |
" <tr>\n", |
|
|
1114 |
" <th rowspan=\"2\" valign=\"top\">[Brevibacterium]</th>\n", |
|
|
1115 |
" <th>flavum</th>\n", |
|
|
1116 |
" <td>2</td>\n", |
|
|
1117 |
" </tr>\n", |
|
|
1118 |
" <tr>\n", |
|
|
1119 |
" <th>frigoritolerans</th>\n", |
|
|
1120 |
" <td>1</td>\n", |
|
|
1121 |
" </tr>\n", |
|
|
1122 |
" <tr>\n", |
|
|
1123 |
" <th rowspan=\"8\" valign=\"top\">[Clostridium]</th>\n", |
|
|
1124 |
" <th>bolteae</th>\n", |
|
|
1125 |
" <td>2</td>\n", |
|
|
1126 |
" </tr>\n", |
|
|
1127 |
" <tr>\n", |
|
|
1128 |
" <th>cellulolyticum</th>\n", |
|
|
1129 |
" <td>1</td>\n", |
|
|
1130 |
" </tr>\n", |
|
|
1131 |
" <tr>\n", |
|
|
1132 |
" <th>cellulosi</th>\n", |
|
|
1133 |
" <td>1</td>\n", |
|
|
1134 |
" </tr>\n", |
|
|
1135 |
" <tr>\n", |
|
|
1136 |
" <th>clariflavum</th>\n", |
|
|
1137 |
" <td>1</td>\n", |
|
|
1138 |
" </tr>\n", |
|
|
1139 |
" <tr>\n", |
|
|
1140 |
" <th>propionicum</th>\n", |
|
|
1141 |
" <td>1</td>\n", |
|
|
1142 |
" </tr>\n", |
|
|
1143 |
" <tr>\n", |
|
|
1144 |
" <th>saccharolyticum</th>\n", |
|
|
1145 |
" <td>1</td>\n", |
|
|
1146 |
" </tr>\n", |
|
|
1147 |
" <tr>\n", |
|
|
1148 |
" <th>scindens</th>\n", |
|
|
1149 |
" <td>1</td>\n", |
|
|
1150 |
" </tr>\n", |
|
|
1151 |
" <tr>\n", |
|
|
1152 |
" <th>stercorarium</th>\n", |
|
|
1153 |
" <td>4</td>\n", |
|
|
1154 |
" </tr>\n", |
|
|
1155 |
" <tr>\n", |
|
|
1156 |
" <th>[Enterobacter]</th>\n", |
|
|
1157 |
" <th>lignolyticus</th>\n", |
|
|
1158 |
" <td>1</td>\n", |
|
|
1159 |
" </tr>\n", |
|
|
1160 |
" <tr>\n", |
|
|
1161 |
" <th rowspan=\"3\" valign=\"top\">[Eubacterium]</th>\n", |
|
|
1162 |
" <th>eligens</th>\n", |
|
|
1163 |
" <td>3</td>\n", |
|
|
1164 |
" </tr>\n", |
|
|
1165 |
" <tr>\n", |
|
|
1166 |
" <th>hallii</th>\n", |
|
|
1167 |
" <td>1</td>\n", |
|
|
1168 |
" </tr>\n", |
|
|
1169 |
" <tr>\n", |
|
|
1170 |
" <th>rectale</th>\n", |
|
|
1171 |
" <td>1</td>\n", |
|
|
1172 |
" </tr>\n", |
|
|
1173 |
" <tr>\n", |
|
|
1174 |
" <th rowspan=\"2\" valign=\"top\">[Haemophilus]</th>\n", |
|
|
1175 |
" <th>ducreyi</th>\n", |
|
|
1176 |
" <td>14</td>\n", |
|
|
1177 |
" </tr>\n", |
|
|
1178 |
" <tr>\n", |
|
|
1179 |
" <th>parasuis</th>\n", |
|
|
1180 |
" <td>4</td>\n", |
|
|
1181 |
" </tr>\n", |
|
|
1182 |
" <tr>\n", |
|
|
1183 |
" <th>[Mycobacterium]</th>\n", |
|
|
1184 |
" <th>chelonae</th>\n", |
|
|
1185 |
" <td>2</td>\n", |
|
|
1186 |
" </tr>\n", |
|
|
1187 |
" <tr>\n", |
|
|
1188 |
" <th>[Pasteurella]</th>\n", |
|
|
1189 |
" <th>aerogenes</th>\n", |
|
|
1190 |
" <td>1</td>\n", |
|
|
1191 |
" </tr>\n", |
|
|
1192 |
" <tr>\n", |
|
|
1193 |
" <th>[Polyangium]</th>\n", |
|
|
1194 |
" <th>brachysporum</th>\n", |
|
|
1195 |
" <td>1</td>\n", |
|
|
1196 |
" </tr>\n", |
|
|
1197 |
" <tr>\n", |
|
|
1198 |
" <th>[Pseudomonas</th>\n", |
|
|
1199 |
" <th>syringae]</th>\n", |
|
|
1200 |
" <td>3</td>\n", |
|
|
1201 |
" </tr>\n", |
|
|
1202 |
" <tr>\n", |
|
|
1203 |
" <th>[Pseudomonas]</th>\n", |
|
|
1204 |
" <th>mesoacidophila</th>\n", |
|
|
1205 |
" <td>4</td>\n", |
|
|
1206 |
" </tr>\n", |
|
|
1207 |
" <tr>\n", |
|
|
1208 |
" <th>complete</th>\n", |
|
|
1209 |
" <th>chromosome</th>\n", |
|
|
1210 |
" <td>2</td>\n", |
|
|
1211 |
" </tr>\n", |
|
|
1212 |
" <tr>\n", |
|
|
1213 |
" <th>gamma</th>\n", |
|
|
1214 |
" <th>proteobacterium</th>\n", |
|
|
1215 |
" <td>1</td>\n", |
|
|
1216 |
" </tr>\n", |
|
|
1217 |
" <tr>\n", |
|
|
1218 |
" <th>secondary</th>\n", |
|
|
1219 |
" <th>endosymbiont</th>\n", |
|
|
1220 |
" <td>1</td>\n", |
|
|
1221 |
" </tr>\n", |
|
|
1222 |
" </tbody>\n", |
|
|
1223 |
"</table>\n", |
|
|
1224 |
"<p>3186 rows × 1 columns</p>\n", |
|
|
1225 |
"</div>" |
|
|
1226 |
], |
|
|
1227 |
"text/plain": [ |
|
|
1228 |
" count\n", |
|
|
1229 |
"genus species \n", |
|
|
1230 |
"'Catharanthus roseus' 2\n", |
|
|
1231 |
"'Deinococcus soli' 1\n", |
|
|
1232 |
"'Nostoc azollae' 3\n", |
|
|
1233 |
"18,711,729 reads 1\n", |
|
|
1234 |
"Acaryochloris marina 10\n", |
|
|
1235 |
"Acetobacter aceti 1\n", |
|
|
1236 |
" ascendens 1\n", |
|
|
1237 |
" orientalis 2\n", |
|
|
1238 |
" oryzifermentans 1\n", |
|
|
1239 |
" pasteurianus 91\n", |
|
|
1240 |
" persici 2\n", |
|
|
1241 |
" pomorum 7\n", |
|
|
1242 |
" senegalensis 2\n", |
|
|
1243 |
" sp. 7\n", |
|
|
1244 |
" tropicalis 2\n", |
|
|
1245 |
"Acetobacterium woodii 1\n", |
|
|
1246 |
"Acetohalobium arabaticum 1\n", |
|
|
1247 |
"Acetomicrobium mobile 1\n", |
|
|
1248 |
"Acholeplasma axanthum 1\n", |
|
|
1249 |
" hippikon 2\n", |
|
|
1250 |
" laidlawii 2\n", |
|
|
1251 |
" oculi 1\n", |
|
|
1252 |
"Achromobacter denitrificans 3\n", |
|
|
1253 |
" insolitus 4\n", |
|
|
1254 |
" sp. 2\n", |
|
|
1255 |
" spanius 4\n", |
|
|
1256 |
" xylosoxidans 11\n", |
|
|
1257 |
"Acidaminococcus fermentans 1\n", |
|
|
1258 |
" intestini 1\n", |
|
|
1259 |
"Acidiferrobacter sp. 1\n", |
|
|
1260 |
"... ...\n", |
|
|
1261 |
"Zymobacter palmae 2\n", |
|
|
1262 |
"Zymomonas mobilis 49\n", |
|
|
1263 |
"[Arcobacter] porcinus 1\n", |
|
|
1264 |
"[Bacillus thuringiensis] 2\n", |
|
|
1265 |
"[Bacillus] caldolyticus 2\n", |
|
|
1266 |
" selenitireducens 1\n", |
|
|
1267 |
"[Brevibacterium] flavum 2\n", |
|
|
1268 |
" frigoritolerans 1\n", |
|
|
1269 |
"[Clostridium] bolteae 2\n", |
|
|
1270 |
" cellulolyticum 1\n", |
|
|
1271 |
" cellulosi 1\n", |
|
|
1272 |
" clariflavum 1\n", |
|
|
1273 |
" propionicum 1\n", |
|
|
1274 |
" saccharolyticum 1\n", |
|
|
1275 |
" scindens 1\n", |
|
|
1276 |
" stercorarium 4\n", |
|
|
1277 |
"[Enterobacter] lignolyticus 1\n", |
|
|
1278 |
"[Eubacterium] eligens 3\n", |
|
|
1279 |
" hallii 1\n", |
|
|
1280 |
" rectale 1\n", |
|
|
1281 |
"[Haemophilus] ducreyi 14\n", |
|
|
1282 |
" parasuis 4\n", |
|
|
1283 |
"[Mycobacterium] chelonae 2\n", |
|
|
1284 |
"[Pasteurella] aerogenes 1\n", |
|
|
1285 |
"[Polyangium] brachysporum 1\n", |
|
|
1286 |
"[Pseudomonas syringae] 3\n", |
|
|
1287 |
"[Pseudomonas] mesoacidophila 4\n", |
|
|
1288 |
"complete chromosome 2\n", |
|
|
1289 |
"gamma proteobacterium 1\n", |
|
|
1290 |
"secondary endosymbiont 1\n", |
|
|
1291 |
"\n", |
|
|
1292 |
"[3186 rows x 1 columns]" |
|
|
1293 |
] |
|
|
1294 |
}, |
|
|
1295 |
"execution_count": 24, |
|
|
1296 |
"metadata": {}, |
|
|
1297 |
"output_type": "execute_result" |
|
|
1298 |
} |
|
|
1299 |
], |
|
|
1300 |
"source": [ |
|
|
1301 |
"inventory.groupby([\"genus\", \"species\"]).agg({\"species\": \"count\"})\n", |
|
|
1302 |
"inventory.columns=[\"count\"]\n", |
|
|
1303 |
"inventory" |
|
|
1304 |
] |
|
|
1305 |
}, |
|
|
1306 |
{ |
|
|
1307 |
"cell_type": "code", |
|
|
1308 |
"execution_count": 117, |
|
|
1309 |
"metadata": {}, |
|
|
1310 |
"outputs": [ |
|
|
1311 |
{ |
|
|
1312 |
"data": { |
|
|
1313 |
"text/html": [ |
|
|
1314 |
"<div>\n", |
|
|
1315 |
"<style scoped>\n", |
|
|
1316 |
" .dataframe tbody tr th:only-of-type {\n", |
|
|
1317 |
" vertical-align: middle;\n", |
|
|
1318 |
" }\n", |
|
|
1319 |
"\n", |
|
|
1320 |
" .dataframe tbody tr th {\n", |
|
|
1321 |
" vertical-align: top;\n", |
|
|
1322 |
" }\n", |
|
|
1323 |
"\n", |
|
|
1324 |
" .dataframe thead th {\n", |
|
|
1325 |
" text-align: right;\n", |
|
|
1326 |
" }\n", |
|
|
1327 |
"</style>\n", |
|
|
1328 |
"<table border=\"1\" class=\"dataframe\">\n", |
|
|
1329 |
" <thead>\n", |
|
|
1330 |
" <tr style=\"text-align: right;\">\n", |
|
|
1331 |
" <th></th>\n", |
|
|
1332 |
" <th>n_sequences</th>\n", |
|
|
1333 |
" <th>species</th>\n", |
|
|
1334 |
" </tr>\n", |
|
|
1335 |
" <tr>\n", |
|
|
1336 |
" <th>genus</th>\n", |
|
|
1337 |
" <th></th>\n", |
|
|
1338 |
" <th></th>\n", |
|
|
1339 |
" </tr>\n", |
|
|
1340 |
" </thead>\n", |
|
|
1341 |
" <tbody>\n", |
|
|
1342 |
" <tr>\n", |
|
|
1343 |
" <th>Bacillus</th>\n", |
|
|
1344 |
" <td>1132</td>\n", |
|
|
1345 |
" <td>11</td>\n", |
|
|
1346 |
" </tr>\n", |
|
|
1347 |
" <tr>\n", |
|
|
1348 |
" <th>Streptomyces</th>\n", |
|
|
1349 |
" <td>743</td>\n", |
|
|
1350 |
" <td>5</td>\n", |
|
|
1351 |
" </tr>\n", |
|
|
1352 |
" <tr>\n", |
|
|
1353 |
" <th>Vibrio</th>\n", |
|
|
1354 |
" <td>468</td>\n", |
|
|
1355 |
" <td>5</td>\n", |
|
|
1356 |
" </tr>\n", |
|
|
1357 |
" <tr>\n", |
|
|
1358 |
" <th>Rhizobium</th>\n", |
|
|
1359 |
" <td>325</td>\n", |
|
|
1360 |
" <td>6</td>\n", |
|
|
1361 |
" </tr>\n", |
|
|
1362 |
" <tr>\n", |
|
|
1363 |
" <th>Pseudomonas</th>\n", |
|
|
1364 |
" <td>304</td>\n", |
|
|
1365 |
" <td>8</td>\n", |
|
|
1366 |
" </tr>\n", |
|
|
1367 |
" <tr>\n", |
|
|
1368 |
" <th>Staphylococcus</th>\n", |
|
|
1369 |
" <td>301</td>\n", |
|
|
1370 |
" <td>6</td>\n", |
|
|
1371 |
" </tr>\n", |
|
|
1372 |
" <tr>\n", |
|
|
1373 |
" <th>Clostridium</th>\n", |
|
|
1374 |
" <td>259</td>\n", |
|
|
1375 |
" <td>5</td>\n", |
|
|
1376 |
" </tr>\n", |
|
|
1377 |
" <tr>\n", |
|
|
1378 |
" <th>Streptococcus</th>\n", |
|
|
1379 |
" <td>222</td>\n", |
|
|
1380 |
" <td>6</td>\n", |
|
|
1381 |
" </tr>\n", |
|
|
1382 |
" <tr>\n", |
|
|
1383 |
" <th>Planktothrix</th>\n", |
|
|
1384 |
" <td>179</td>\n", |
|
|
1385 |
" <td>5</td>\n", |
|
|
1386 |
" </tr>\n", |
|
|
1387 |
" <tr>\n", |
|
|
1388 |
" <th>Stenotrophomonas</th>\n", |
|
|
1389 |
" <td>176</td>\n", |
|
|
1390 |
" <td>5</td>\n", |
|
|
1391 |
" </tr>\n", |
|
|
1392 |
" <tr>\n", |
|
|
1393 |
" <th>Escherichia</th>\n", |
|
|
1394 |
" <td>133</td>\n", |
|
|
1395 |
" <td>3</td>\n", |
|
|
1396 |
" </tr>\n", |
|
|
1397 |
" <tr>\n", |
|
|
1398 |
" <th>Paenibacillus</th>\n", |
|
|
1399 |
" <td>127</td>\n", |
|
|
1400 |
" <td>3</td>\n", |
|
|
1401 |
" </tr>\n", |
|
|
1402 |
" <tr>\n", |
|
|
1403 |
" <th>Listeria</th>\n", |
|
|
1404 |
" <td>104</td>\n", |
|
|
1405 |
" <td>4</td>\n", |
|
|
1406 |
" </tr>\n", |
|
|
1407 |
" <tr>\n", |
|
|
1408 |
" <th>Corynebacterium</th>\n", |
|
|
1409 |
" <td>103</td>\n", |
|
|
1410 |
" <td>7</td>\n", |
|
|
1411 |
" </tr>\n", |
|
|
1412 |
" <tr>\n", |
|
|
1413 |
" <th>Klebsiella</th>\n", |
|
|
1414 |
" <td>16</td>\n", |
|
|
1415 |
" <td>3</td>\n", |
|
|
1416 |
" </tr>\n", |
|
|
1417 |
" <tr>\n", |
|
|
1418 |
" <th>Shigella</th>\n", |
|
|
1419 |
" <td>14</td>\n", |
|
|
1420 |
" <td>3</td>\n", |
|
|
1421 |
" </tr>\n", |
|
|
1422 |
" <tr>\n", |
|
|
1423 |
" <th>Salmonella</th>\n", |
|
|
1424 |
" <td>4</td>\n", |
|
|
1425 |
" <td>2</td>\n", |
|
|
1426 |
" </tr>\n", |
|
|
1427 |
" <tr>\n", |
|
|
1428 |
" <th>Enterobacter</th>\n", |
|
|
1429 |
" <td>1</td>\n", |
|
|
1430 |
" <td>1</td>\n", |
|
|
1431 |
" </tr>\n", |
|
|
1432 |
" </tbody>\n", |
|
|
1433 |
"</table>\n", |
|
|
1434 |
"</div>" |
|
|
1435 |
], |
|
|
1436 |
"text/plain": [ |
|
|
1437 |
" n_sequences species\n", |
|
|
1438 |
"genus \n", |
|
|
1439 |
"Bacillus 1132 11\n", |
|
|
1440 |
"Streptomyces 743 5\n", |
|
|
1441 |
"Vibrio 468 5\n", |
|
|
1442 |
"Rhizobium 325 6\n", |
|
|
1443 |
"Pseudomonas 304 8\n", |
|
|
1444 |
"Staphylococcus 301 6\n", |
|
|
1445 |
"Clostridium 259 5\n", |
|
|
1446 |
"Streptococcus 222 6\n", |
|
|
1447 |
"Planktothrix 179 5\n", |
|
|
1448 |
"Stenotrophomonas 176 5\n", |
|
|
1449 |
"Escherichia 133 3\n", |
|
|
1450 |
"Paenibacillus 127 3\n", |
|
|
1451 |
"Listeria 104 4\n", |
|
|
1452 |
"Corynebacterium 103 7\n", |
|
|
1453 |
"Klebsiella 16 3\n", |
|
|
1454 |
"Shigella 14 3\n", |
|
|
1455 |
"Salmonella 4 2\n", |
|
|
1456 |
"Enterobacter 1 1" |
|
|
1457 |
] |
|
|
1458 |
}, |
|
|
1459 |
"execution_count": 117, |
|
|
1460 |
"metadata": {}, |
|
|
1461 |
"output_type": "execute_result" |
|
|
1462 |
} |
|
|
1463 |
], |
|
|
1464 |
"source": [ |
|
|
1465 |
"counts = inventory.reset_index().groupby(\"genus\").agg({\"count\", sum}).drop((\"species\"), axis=1)\n", |
|
|
1466 |
"counts.columns=[\"n_sequences\",\"species\"]\n", |
|
|
1467 |
"counts.sort_values(\"n_sequences\", ascending=False)" |
|
|
1468 |
] |
|
|
1469 |
}, |
|
|
1470 |
{ |
|
|
1471 |
"cell_type": "code", |
|
|
1472 |
"execution_count": null, |
|
|
1473 |
"metadata": {}, |
|
|
1474 |
"outputs": [], |
|
|
1475 |
"source": [] |
|
|
1476 |
} |
|
|
1477 |
], |
|
|
1478 |
"metadata": { |
|
|
1479 |
"kernelspec": { |
|
|
1480 |
"display_name": "Python 3", |
|
|
1481 |
"language": "python", |
|
|
1482 |
"name": "python3" |
|
|
1483 |
}, |
|
|
1484 |
"language_info": { |
|
|
1485 |
"codemirror_mode": { |
|
|
1486 |
"name": "ipython", |
|
|
1487 |
"version": 3 |
|
|
1488 |
}, |
|
|
1489 |
"file_extension": ".py", |
|
|
1490 |
"mimetype": "text/x-python", |
|
|
1491 |
"name": "python", |
|
|
1492 |
"nbconvert_exporter": "python", |
|
|
1493 |
"pygments_lexer": "ipython3", |
|
|
1494 |
"version": "3.6.8" |
|
|
1495 |
}, |
|
|
1496 |
"varInspector": { |
|
|
1497 |
"cols": { |
|
|
1498 |
"lenName": 16, |
|
|
1499 |
"lenType": 16, |
|
|
1500 |
"lenVar": 40 |
|
|
1501 |
}, |
|
|
1502 |
"kernels_config": { |
|
|
1503 |
"python": { |
|
|
1504 |
"delete_cmd_postfix": "", |
|
|
1505 |
"delete_cmd_prefix": "del ", |
|
|
1506 |
"library": "var_list.py", |
|
|
1507 |
"varRefreshCmd": "print(var_dic_list())" |
|
|
1508 |
}, |
|
|
1509 |
"r": { |
|
|
1510 |
"delete_cmd_postfix": ") ", |
|
|
1511 |
"delete_cmd_prefix": "rm(", |
|
|
1512 |
"library": "var_list.r", |
|
|
1513 |
"varRefreshCmd": "cat(var_dic_list()) " |
|
|
1514 |
} |
|
|
1515 |
}, |
|
|
1516 |
"types_to_exclude": [ |
|
|
1517 |
"module", |
|
|
1518 |
"function", |
|
|
1519 |
"builtin_function_or_method", |
|
|
1520 |
"instance", |
|
|
1521 |
"_Feature" |
|
|
1522 |
], |
|
|
1523 |
"window_display": false |
|
|
1524 |
} |
|
|
1525 |
}, |
|
|
1526 |
"nbformat": 4, |
|
|
1527 |
"nbformat_minor": 2 |
|
|
1528 |
} |