larisa / gene-disease-embeddings

Go to a project
Toggle navigation Toggle navigation pinning
Larisa Morales Soto
72371e02 2 parents 9970f04e 81a87e9b

Merge branch 'master' of pakal.ccg.unam.mx:larisams/gene-disease-embeddings

Inline Side-by-side
Showing 6 changed files with 936 additions and 0 deletions
#Cluster: 1
3_s 3
17_s 17
33_s 33
42_s 42
43_s 43
59_s 59
66_s 66
82_s 82
84_s 84
100_s 100
123_s 123
124_s 124
132_s 131
136_s 135
137_s 136
148_s 147
188_s 186
196_s 194
216_s 214
219_s 217
226_s 224
227_s 225
229_s 227
230_s 228
234_s 232
238_s 236
244_s 242
245_s 243
269_s 266
275_s 272
281_s 278
287_s 284
290_s 287
301_s 297
302_s 298
303_s 299
315_s 311
332_s 328
350_s 346
361_s 357
366_s 362
379_s 375
415_s 411
421_s 417
444_s 440
445_s 441
446_s 442
453_s 449
#Cluster: 2
6_s 6
18_s 18
24_s 24
25_s 25
29_s 29
37_s 37
38_s 38
44_s 44
47_s 47
55_s 55
65_s 65
69_s 69
70_s 70
71_s 71
72_s 72
79_s 79
81_s 81
86_s 86
92_s 92
94_s 94
101_s 101
102_s 102
104_s 104
110_s 110
112_s 112
115_s 115
118_s 118
120_s 120
127_s 126
128_s 127
130_s 129
144_s 143
146_s 145
156_s 155
161_s 160
164_s 163
166_s 165
169_s 168
179_s 177
182_s 180
186_s 184
189_s 187
192_s 190
195_s 193
204_s 202
205_s 203
208_s 206
217_s 215
221_s 219
222_s 220
223_s 221
225_s 223
233_s 231
236_s 234
241_s 239
242_s 240
247_s 245
260_s 257
262_s 259
265_s 262
272_s 269
278_s 275
279_s 276
280_s 277
284_s 281
289_s 286
297_s 293
300_s 296
307_s 303
308_s 304
310_s 306
316_s 312
318_s 314
320_s 316
326_s 322
330_s 326
335_s 331
336_s 332
340_s 336
348_s 344
352_s 348
353_s 349
355_s 351
357_s 353
371_s 367
383_s 379
384_s 380
392_s 388
399_s 395
402_s 398
408_s 404
411_s 407
413_s 409
414_s 410
418_s 414
419_s 415
424_s 420
428_s 424
429_s 425
433_s 429
438_s 434
440_s 436
447_s 443
450_s 446
#Cluster: 3
1_s 1
5_s 5
7_s 7
8_s 8
10_s 10
12_s 12
13_s 13
14_s 14
16_s 16
20_s 20
22_s 22
23_s 23
28_s 28
31_s 31
34_s 34
48_s 48
49_s 49
54_s 54
58_s 58
64_s 64
67_s 67
74_s 74
75_s 75
80_s 80
83_s 83
87_s 87
88_s 88
89_s 89
90_s 90
91_s 91
93_s 93
98_s 98
106_s 106
109_s 109
117_s 117
138_s 137
141_s 140
142_s 141
147_s 146
149_s 148
150_s 149
159_s 158
162_s 161
163_s 162
165_s 164
171_s 169
174_s 172
177_s 175
184_s 182
190_s 188
197_s 195
198_s 196
199_s 197
203_s 201
210_s 208
214_s 212
215_s 213
220_s 218
237_s 235
239_s 237
240_s 238
243_s 241
246_s 244
248_s 246
250_s 248
251_s 249
253_s 250
254_s 251
255_s 252
256_s 253
264_s 261
268_s 265
273_s 270
286_s 283
291_s 288
293_s 289
295_s 291
298_s 294
299_s 295
305_s 301
313_s 309
314_s 310
317_s 313
322_s 318
325_s 321
328_s 324
333_s 329
343_s 339
345_s 341
347_s 343
349_s 345
354_s 350
356_s 352
360_s 356
362_s 358
363_s 359
364_s 360
365_s 361
367_s 363
368_s 364
372_s 368
374_s 370
375_s 371
376_s 372
377_s 373
378_s 374
380_s 376
387_s 383
388_s 384
390_s 386
391_s 387
398_s 394
401_s 397
403_s 399
407_s 403
409_s 405
416_s 412
420_s 416
431_s 427
437_s 433
442_s 438
443_s 439
448_s 444
451_s 447
452_s 448
#Cluster: 4
9_s 9
19_s 19
21_s 21
26_s 26
32_s 32
39_s 39
52_s 52
73_s 73
77_s 77
95_s 95
107_s 107
113_s 113
125_s 125
129_s 128
131_s 130
145_s 144
153_s 152
158_s 157
172_s 170
175_s 173
180_s 178
200_s 198
202_s 200
207_s 205
224_s 222
228_s 226
231_s 229
259_s 256
263_s 260
274_s 271
283_s 280
288_s 285
306_s 302
321_s 317
323_s 319
334_s 330
359_s 355
382_s 378
395_s 391
417_s 413
434_s 430
454_s 450
#Cluster: 5
2_s 2
4_s 4
11_s 11
15_s 15
27_s 27
30_s 30
35_s 35
36_s 36
40_s 40
41_s 41
45_s 45
46_s 46
50_s 50
51_s 51
53_s 53
56_s 56
57_s 57
60_s 60
61_s 61
62_s 62
63_s 63
68_s 68
76_s 76
78_s 78
85_s 85
96_s 96
97_s 97
99_s 99
103_s 103
105_s 105
108_s 108
111_s 111
114_s 114
116_s 116
119_s 119
121_s 121
122_s 122
133_s 132
134_s 133
135_s 134
139_s 138
140_s 139
143_s 142
151_s 150
152_s 151
154_s 153
155_s 154
157_s 156
160_s 159
167_s 166
168_s 167
173_s 171
176_s 174
178_s 176
181_s 179
183_s 181
185_s 183
187_s 185
191_s 189
193_s 191
194_s 192
201_s 199
206_s 204
209_s 207
211_s 209
212_s 210
213_s 211
218_s 216
232_s 230
235_s 233
249_s 247
257_s 254
258_s 255
261_s 258
266_s 263
267_s 264
270_s 267
271_s 268
276_s 273
277_s 274
282_s 279
285_s 282
294_s 290
296_s 292
304_s 300
309_s 305
311_s 307
312_s 308
319_s 315
324_s 320
327_s 323
329_s 325
331_s 327
337_s 333
338_s 334
339_s 335
341_s 337
342_s 338
344_s 340
346_s 342
351_s 347
358_s 354
369_s 365
370_s 366
373_s 369
381_s 377
385_s 381
386_s 382
389_s 385
393_s 389
394_s 390
396_s 392
397_s 393
400_s 396
404_s 400
405_s 401
406_s 402
410_s 406
412_s 408
422_s 418
423_s 419
425_s 421
426_s 422
427_s 423
430_s 426
432_s 428
435_s 431
436_s 432
439_s 435
441_s 437
449_s 445
455_s 451
#Cluster: 1
3_s 3
17_s 17
33_s 33
42_s 42
43_s 43
59_s 59
66_s 66
82_s 82
84_s 84
100_s 100
123_s 123
124_s 124
132_s 131
136_s 135
137_s 136
148_s 147
188_s 186
196_s 194
216_s 214
219_s 217
226_s 224
227_s 225
229_s 227
230_s 228
234_s 232
238_s 236
244_s 242
245_s 243
269_s 266
275_s 272
281_s 278
287_s 284
290_s 287
301_s 297
302_s 298
303_s 299
315_s 311
332_s 328
350_s 346
361_s 357
366_s 362
379_s 375
415_s 411
421_s 417
444_s 440
445_s 441
446_s 442
453_s 449
#Cluster: 2
6_s 6
18_s 18
24_s 24
25_s 25
29_s 29
37_s 37
38_s 38
44_s 44
47_s 47
55_s 55
65_s 65
69_s 69
70_s 70
71_s 71
72_s 72
79_s 79
81_s 81
86_s 86
92_s 92
94_s 94
101_s 101
102_s 102
104_s 104
110_s 110
112_s 112
115_s 115
118_s 118
120_s 120
127_s 126
128_s 127
130_s 129
144_s 143
146_s 145
156_s 155
161_s 160
164_s 163
166_s 165
169_s 168
179_s 177
182_s 180
186_s 184
189_s 187
192_s 190
195_s 193
204_s 202
205_s 203
208_s 206
217_s 215
221_s 219
222_s 220
223_s 221
225_s 223
233_s 231
236_s 234
241_s 239
242_s 240
247_s 245
260_s 257
262_s 259
265_s 262
272_s 269
278_s 275
279_s 276
280_s 277
284_s 281
289_s 286
297_s 293
300_s 296
307_s 303
308_s 304
310_s 306
316_s 312
318_s 314
320_s 316
326_s 322
330_s 326
335_s 331
336_s 332
340_s 336
348_s 344
352_s 348
353_s 349
355_s 351
357_s 353
371_s 367
383_s 379
384_s 380
392_s 388
399_s 395
402_s 398
408_s 404
411_s 407
413_s 409
414_s 410
418_s 414
419_s 415
424_s 420
428_s 424
429_s 425
433_s 429
438_s 434
440_s 436
447_s 443
450_s 446
#Cluster: 3
1_s 1
5_s 5
7_s 7
8_s 8
10_s 10
12_s 12
13_s 13
14_s 14
16_s 16
20_s 20
22_s 22
23_s 23
28_s 28
31_s 31
34_s 34
48_s 48
49_s 49
54_s 54
58_s 58
64_s 64
67_s 67
74_s 74
75_s 75
80_s 80
83_s 83
87_s 87
88_s 88
89_s 89
90_s 90
91_s 91
93_s 93
98_s 98
106_s 106
109_s 109
117_s 117
138_s 137
141_s 140
142_s 141
147_s 146
149_s 148
150_s 149
159_s 158
162_s 161
163_s 162
165_s 164
171_s 169
174_s 172
177_s 175
184_s 182
190_s 188
197_s 195
198_s 196
199_s 197
203_s 201
210_s 208
214_s 212
215_s 213
220_s 218
237_s 235
239_s 237
240_s 238
243_s 241
246_s 244
248_s 246
250_s 248
251_s 249
253_s 250
254_s 251
255_s 252
256_s 253
264_s 261
268_s 265
273_s 270
286_s 283
291_s 288
293_s 289
295_s 291
298_s 294
299_s 295
305_s 301
313_s 309
314_s 310
317_s 313
322_s 318
325_s 321
328_s 324
333_s 329
343_s 339
345_s 341
347_s 343
349_s 345
354_s 350
356_s 352
360_s 356
362_s 358
363_s 359
364_s 360
365_s 361
367_s 363
368_s 364
372_s 368
374_s 370
375_s 371
376_s 372
377_s 373
378_s 374
380_s 376
387_s 383
388_s 384
390_s 386
391_s 387
398_s 394
401_s 397
403_s 399
407_s 403
409_s 405
416_s 412
420_s 416
431_s 427
437_s 433
442_s 438
443_s 439
448_s 444
451_s 447
452_s 448
#Cluster: 4
9_s 9
19_s 19
21_s 21
26_s 26
32_s 32
39_s 39
52_s 52
73_s 73
77_s 77
95_s 95
107_s 107
113_s 113
125_s 125
129_s 128
131_s 130
145_s 144
153_s 152
158_s 157
172_s 170
175_s 173
180_s 178
200_s 198
202_s 200
207_s 205
224_s 222
228_s 226
231_s 229
259_s 256
263_s 260
274_s 271
283_s 280
288_s 285
306_s 302
321_s 317
323_s 319
334_s 330
359_s 355
382_s 378
395_s 391
417_s 413
434_s 430
454_s 450
#Cluster: 5
11_s 11
27_s 27
30_s 30
36_s 36
40_s 40
46_s 46
53_s 53
57_s 57
60_s 60
62_s 62
63_s 63
78_s 78
96_s 96
99_s 99
114_s 114
122_s 122
134_s 133
135_s 134
154_s 153
155_s 154
160_s 159
167_s 166
168_s 167
173_s 171
187_s 185
194_s 192
206_s 204
211_s 209
213_s 211
249_s 247
257_s 254
258_s 255
267_s 264
271_s 268
276_s 273
282_s 279
285_s 282
296_s 292
319_s 315
346_s 342
351_s 347
358_s 354
385_s 381
386_s 382
389_s 385
396_s 392
405_s 401
423_s 419
427_s 423
430_s 426
449_s 445
455_s 451
#Cluster: 6
2_s 2
4_s 4
15_s 15
35_s 35
41_s 41
45_s 45
50_s 50
51_s 51
56_s 56
61_s 61
68_s 68
76_s 76
85_s 85
97_s 97
103_s 103
105_s 105
108_s 108
111_s 111
116_s 116
119_s 119
121_s 121
133_s 132
139_s 138
140_s 139
143_s 142
151_s 150
152_s 151
157_s 156
176_s 174
178_s 176
181_s 179
183_s 181
185_s 183
191_s 189
193_s 191
201_s 199
209_s 207
212_s 210
218_s 216
232_s 230
235_s 233
261_s 258
266_s 263
270_s 267
277_s 274
294_s 290
304_s 300
309_s 305
311_s 307
312_s 308
324_s 320
327_s 323
329_s 325
331_s 327
337_s 333
338_s 334
339_s 335
341_s 337
342_s 338
344_s 340
369_s 365
370_s 366
373_s 369
381_s 377
393_s 389
394_s 390
397_s 393
400_s 396
404_s 400
406_s 402
410_s 406
412_s 408
422_s 418
425_s 421
426_s 422
432_s 428
435_s 431
436_s 432
439_s 435
441_s 437
......@@ -66,3 +66,21 @@ print_cluster(cls4, "SentenceMembership_4clusters.txt")
####
# 5 clusters
png("Dendogram_5clusters.png", height = 600, width = 975)
plot(senclus, hang=-1)
cls5 <- rect.hclust(senclus, k=5, border = 3:4)
dev.off()
print_cluster(cls5, "SentenceMembership_5clusters.txt")
###
# 6 clusters
png("Dendogram_6clusters.png", height = 600, width = 975)
plot(senclus, hang=-1)
cls6 <- rect.hclust(senclus, k=6, border = 3:4)
dev.off()
print_cluster(cls6, "SentenceMembership_6clusters.txt")
......
......@@ -5,3 +5,8 @@ grep -E "\|t\|" ../corpora/full-sentences.txt | perl -ne 'if(/(\d+\|t\|)(.*)/){p
# Run wisse
python3.4 wisse_example.py --input ../corpora/articles-titles.txt --idfmodel local --embedmodel /export/space1/users/compu2/bionlp/word-embeddings/w2v/almac/ignacio/data/word2vec/indexed_w2v_En_vector_space_H300 --localw binary --output ../embeddings/articles-titles.vec --format wisse &
# Within cluster sentence analysis
grep -c -E '<g>.*<d>|<d>.*<g>' cluster1_tagged.txt cluster2_tagged.txt cluster3_tagged.txt cluster4_tagged.txt
wc -l cluster1_tagged.txt cluster2_tagged.txt cluster3_tagged.txt cluster4_tagged.txt
......