ribesstefano commited on
Commit
1ee75b1
1 Parent(s): e874ff5

Double checking E3 ligase knockouts

Browse files
notebooks/double_check_knockouts.ipynb ADDED
@@ -0,0 +1,447 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "cells": [
3
+ {
4
+ "cell_type": "markdown",
5
+ "metadata": {},
6
+ "source": [
7
+ "# Double Check Cell Knockouts\n",
8
+ "\n",
9
+ "Double check that there are no E3 ligase knockouts, like CRBN-/- cell lines, in the dataset.\n",
10
+ "\n",
11
+ "NOTE: It requires the downloaded file \"cellosaurus.txt\" from the Cellosaurus database to be stored in the `data` directory."
12
+ ]
13
+ },
14
+ {
15
+ "cell_type": "code",
16
+ "execution_count": 1,
17
+ "metadata": {},
18
+ "outputs": [],
19
+ "source": [
20
+ "import pandas as pd\n",
21
+ "import pickle"
22
+ ]
23
+ },
24
+ {
25
+ "cell_type": "code",
26
+ "execution_count": 4,
27
+ "metadata": {},
28
+ "outputs": [
29
+ {
30
+ "data": {
31
+ "text/plain": [
32
+ "{'MOLT-4': 'MOLT-4',\n",
33
+ " 'H1975': 'H1975/WR',\n",
34
+ " 'PBMCs': 'PH1-PBMCs-hiPSC4F1',\n",
35
+ " 'THP-1': 'THP-1',\n",
36
+ " 'K562': 'EGFP-K562',\n",
37
+ " 'MCF-7': 'MCF-7',\n",
38
+ " 'Hs578t': 'Hs578T-Dox',\n",
39
+ " 'THP': 'THP-1',\n",
40
+ " 'HCC827': 'HCC827',\n",
41
+ " 'MOLM14': 'MOLM-14',\n",
42
+ " 'HeLa': 'HeLa',\n",
43
+ " 'HCT116': 'HCT116-53BPI(+/-)',\n",
44
+ " 'Human THP-1 monocytes': 'THP-1',\n",
45
+ " 'MCF-7 breast cancer cells': 'MCF-7',\n",
46
+ " 'NAMALWA': 'Namalwa',\n",
47
+ " 'K562 CML': 'K562/GM-CSF',\n",
48
+ " 'MOLM-13': 'MOLM-13',\n",
49
+ " 'MOLT4': 'MOLT4/P',\n",
50
+ " 'OPM2': 'OPM-2',\n",
51
+ " 'MV-4-11': 'MV4-11',\n",
52
+ " 'MDA-MB-468': 'MDA-MB-468',\n",
53
+ " 'PC-3': 'PC-3',\n",
54
+ " 'Jurkat': 'Jurkat',\n",
55
+ " 'LNCaP': 'LNCaP',\n",
56
+ " 'MCF7': 'MCF7 AREc32',\n",
57
+ " '22Rv1': '22Rv1',\n",
58
+ " 'AML cells': 'OCI-AML-1',\n",
59
+ " 'H661': 'NCI-H661',\n",
60
+ " 'Hela': 'HeLa',\n",
61
+ " 'VCaP': 'VCaP',\n",
62
+ " 'THP1': 'PSC-THP1',\n",
63
+ " 'PC3': 'HNC PC3',\n",
64
+ " 'hela': 'HeLa',\n",
65
+ " 'Karpas422': 'Karpas-422',\n",
66
+ " 'U251': 'U251-TR3',\n",
67
+ " 'MM1S': 'MM1.S',\n",
68
+ " 'Ramos': 'Ramos',\n",
69
+ " 'MDA-MB-231': 'MDA-MB-231',\n",
70
+ " 'LnCap': 'LNCaP',\n",
71
+ " 'HEK293': 'HEK293',\n",
72
+ " 'MiaPaCa2': 'MIA PaCa-2',\n",
73
+ " 'SR': 'SR',\n",
74
+ " 'OVCAR8': 'OVCAR-8',\n",
75
+ " 'Hella': 'IH-1',\n",
76
+ " 'RS4;11': 'RS4;11',\n",
77
+ " 'HEK293T': 'HEK293T',\n",
78
+ " 'RAMOS': 'Ramos',\n",
79
+ " 'A375': 'A375-C5',\n",
80
+ " 'KYSE520 esophageal cancer cell line': 'KYSE-520',\n",
81
+ " 'NCI-H2030': 'NCI-H2030',\n",
82
+ " 'SW1573': 'SW1573',\n",
83
+ " 'SU-DHL-1': 'SU-DHL-1',\n",
84
+ " 'PA1': 'PA1',\n",
85
+ " 'Ba/F3': 'Ba/F3',\n",
86
+ " 'HT1080': 'HT1080 EGFP',\n",
87
+ " 'HepG2': 'HepG2 hALR',\n",
88
+ " 'MyLa1929': 'MyLa 1929',\n",
89
+ " 'A549': 'A549 Cas9',\n",
90
+ " 'Huh7': 'Huh7 IFITM2-/-',\n",
91
+ " 'RI-1': 'Ri-1',\n",
92
+ " 'EOL-1': 'EoL-1',\n",
93
+ " 'A-204': 'A-204',\n",
94
+ " 'T47D': 'T47D Ad12',\n",
95
+ " 'VCaP AR+': 'VCaP AR-V7/pHag',\n",
96
+ " 'NCI-H661': 'NCI-H661',\n",
97
+ " 'NCI-H838': 'NCI-H838',\n",
98
+ " 'NCI-H2228': 'NCI-H2228',\n",
99
+ " '22RV1': '22Rv1',\n",
100
+ " 'HBL-1': 'HBL-1 [Human AIDS-related non-Hodgkin lymphoma]',\n",
101
+ " 'Mino': 'Mino',\n",
102
+ " 'H3255': 'NCI-H3255',\n",
103
+ " 'XLA': 'XLA-07',\n",
104
+ " 'LnCaP95': 'LNCaP95 clone A7',\n",
105
+ " 'Namalwa': 'Namalwa',\n",
106
+ " 'CA-46': 'CA46',\n",
107
+ " 'SUM149': 'SUM149-Luc',\n",
108
+ " 'MV4-11': 'MV4-11',\n",
109
+ " 'HD-MB03': 'HD-MB03',\n",
110
+ " 'Molm-16': 'MOLM-16',\n",
111
+ " '293T': '293T FOXP3',\n",
112
+ " 'H3122': 'NCI-H3122',\n",
113
+ " 'Karpas 299': 'Karpas-299',\n",
114
+ " 'Kelly': 'Kelly',\n",
115
+ " 'RS4; 11': 'RS4;11',\n",
116
+ " 'A431': 'A431 siYAP',\n",
117
+ " 'HCC-827': 'HCC827-Luc [JCRB]',\n",
118
+ " 'platelets': '2T60',\n",
119
+ " 'Panc Tu-I': 'PancTu-I',\n",
120
+ " 'MM.1S': 'MM.1S-luc',\n",
121
+ " 'NCI-H1568': 'NCI-H1568',\n",
122
+ " 'PBMC': 'BSS1-PBMC-iPS4F4',\n",
123
+ " 'DB': 'DB',\n",
124
+ " 'HT-29': 'HT-29',\n",
125
+ " 'SK-MEL-28': 'SK-MEL-28',\n",
126
+ " 'COLO 205': 'COLO 205',\n",
127
+ " 'PC9': 'PC9-BrM3',\n",
128
+ " 'Huh7.5': 'Huh-7.5',\n",
129
+ " 'WI38': 'WI-38 VA13 subline 2RA',\n",
130
+ " 'KYSE520': 'KYSE-520',\n",
131
+ " 'MV4;11': 'MV4-11',\n",
132
+ " 'TM3': 'TM3',\n",
133
+ " 'MDA-MB-436': 'MDA-MB-436',\n",
134
+ " 'germ': 'G1 [Mouse germ stem cell]',\n",
135
+ " 'SW480': 'SW480',\n",
136
+ " 'MB-MDA-231': 'MDA-MB-231',\n",
137
+ " 'HLE': 'HLE',\n",
138
+ " 'HuH-7': 'Huh-7',\n",
139
+ " 'SNU-423': 'SNU-423',\n",
140
+ " 'HUH-1': 'HuH-1',\n",
141
+ " 'SK-Hep-1': 'SK-HEP-1',\n",
142
+ " 'SNU-387': 'SNU-387',\n",
143
+ " 'HLF': 'HLF',\n",
144
+ " 'SNU-398': 'SNU-398',\n",
145
+ " 'HUCCT1': 'HuCC-T1-G10',\n",
146
+ " 'NCI-H23': 'NCI-H23',\n",
147
+ " 'NCI-H358': 'NCI-H358',\n",
148
+ " 'MIA PaCa-2': 'MIA PaCa-2',\n",
149
+ " 'HCC1937': 'HCC1937',\n",
150
+ " 'Capan-1': 'Capan-1',\n",
151
+ " 'SW620': 'SW620',\n",
152
+ " 'KM12': 'KM12',\n",
153
+ " 'HEL': 'HEL',\n",
154
+ " 'Sk-Mel-28': 'SK-MEL-28',\n",
155
+ " 'RAW 264.7': 'RAW 264.7',\n",
156
+ " 'Pfeiffer': 'Pfeiffer',\n",
157
+ " 'DOHH2': 'DoHH2',\n",
158
+ " 'U937': 'U937(CD59+)',\n",
159
+ " 'Z138': 'Z-138',\n",
160
+ " 'OCI-AML2': 'OCI-AML-2',\n",
161
+ " 'OCI-AML3': 'OCI-AML-3',\n",
162
+ " 'Kasumi-1': 'Kasumi-1',\n",
163
+ " 'NB4': 'NB4',\n",
164
+ " 'H1666': 'NCI-H1666',\n",
165
+ " 'CAL-12T': 'CAL-12T',\n",
166
+ " 'SK-MEL-246': 'SK-MEL-246',\n",
167
+ " 'MOLM-14': 'MOLM-14',\n",
168
+ " 'KYSE-270': 'KYSE-270',\n",
169
+ " 'HCT-116': 'HCT 116',\n",
170
+ " 'COLO-205': 'COLO 205',\n",
171
+ " 'Calu-1': 'Calu-1',\n",
172
+ " 'KU812': 'Ku812',\n",
173
+ " 'BT474': 'BT474 A3',\n",
174
+ " 'MIA PaCa2': 'MIA PaCa-2',\n",
175
+ " 'AsPC-1': 'AsPC-1',\n",
176
+ " 'SK-LU-1': 'SK-LU-1',\n",
177
+ " 'HEI-OC1': 'HEI-OC1',\n",
178
+ " 'Bel-7402': 'BEL-7402',\n",
179
+ " 'SH-SY5Y': 'SH-SY5Y',\n",
180
+ " 'H358': 'NCI-H358',\n",
181
+ " 'H23': 'NCI-H23',\n",
182
+ " 'JeKo-1': 'JeKo-1',\n",
183
+ " 'TMD8': 'TMD8',\n",
184
+ " 'MHH-CALL-4': 'MHH-CALL-4',\n",
185
+ " 'KOPN49': 'KOPN-49',\n",
186
+ " 'MOLM-16': 'MOLM-16',\n",
187
+ " 'SUP-M2': 'SUP-M2',\n",
188
+ " 'CCLP1': 'CC-LP-1',\n",
189
+ " 'KATO III': 'KATO III',\n",
190
+ " 'BaF3 FLT3-ITD': 'Ba/F3',\n",
191
+ " 'HEK293A': 'HEK293A mRFP-ATG9',\n",
192
+ " 'HAP1': 'HAP1',\n",
193
+ " 'ER-positive breast cancer cell lines': 'CGBC 01'}"
194
+ ]
195
+ },
196
+ "execution_count": 4,
197
+ "metadata": {},
198
+ "output_type": "execute_result"
199
+ }
200
+ ],
201
+ "source": [
202
+ "with open('../data/processed/cell2identifier.pkl', 'rb') as f:\n",
203
+ " cell2identifier = pickle.load(f)\n",
204
+ "cell2identifier"
205
+ ]
206
+ },
207
+ {
208
+ "cell_type": "code",
209
+ "execution_count": 5,
210
+ "metadata": {},
211
+ "outputs": [
212
+ {
213
+ "data": {
214
+ "text/plain": [
215
+ "array(['MOLT-4', 'H1975/WR', 'PH1-PBMCs-hiPSC4F1', 'THP-1', 'EGFP-K562',\n",
216
+ " 'MCF-7', 'Hs578T-Dox', 'HCC827', 'MOLM-14', nan, 'HeLa',\n",
217
+ " 'HCT116-53BPI(+/-)', 'Namalwa', 'K562/GM-CSF', 'MOLM-13',\n",
218
+ " 'MOLT4/P', 'OPM-2', 'MV4-11', 'MDA-MB-468', 'PC-3', 'Jurkat',\n",
219
+ " 'LNCaP', 'MCF7 AREc32', '22Rv1', 'OCI-AML-1', 'NCI-H661', 'VCaP',\n",
220
+ " 'PSC-THP1', 'HNC PC3', 'Karpas-422', 'U251-TR3', 'MM1.S', 'Ramos',\n",
221
+ " 'MDA-MB-231', 'HEK293', 'MIA PaCa-2', 'SR', 'OVCAR-8', 'IH-1',\n",
222
+ " 'RS4;11', 'HEK293T', 'A375-C5', 'KYSE-520', 'NCI-H2030', 'SW1573',\n",
223
+ " 'SU-DHL-1', 'PA1', 'HT1080 EGFP', 'HepG2 hALR', 'MyLa 1929',\n",
224
+ " 'A549 Cas9', 'Huh7 IFITM2-/-', 'Ri-1', 'EoL-1', 'A-204',\n",
225
+ " 'T47D Ad12', 'VCaP AR-V7/pHag', 'NCI-H838', 'NCI-H2228',\n",
226
+ " 'HBL-1 [Human AIDS-related non-Hodgkin lymphoma]', 'Mino',\n",
227
+ " 'NCI-H3255', 'XLA-07', 'LNCaP95 clone A7', 'CA46', 'SUM149-Luc',\n",
228
+ " 'HD-MB03', 'MOLM-16', '293T FOXP3', 'NCI-H3122', 'Karpas-299',\n",
229
+ " 'Kelly', 'A431 siYAP', 'HCC827-Luc [JCRB]', '2T60', 'PancTu-I',\n",
230
+ " 'MM.1S-luc', 'NCI-H1568', 'BSS1-PBMC-iPS4F4', 'DB', 'HT-29',\n",
231
+ " 'SK-MEL-28', 'COLO 205', 'PC9-BrM3', 'Huh-7.5',\n",
232
+ " 'WI-38 VA13 subline 2RA', 'TM3', 'MDA-MB-436',\n",
233
+ " 'G1 [Mouse germ stem cell]', 'SW480', 'HLE', 'Huh-7', 'SNU-423',\n",
234
+ " 'HuH-1', 'SK-HEP-1', 'SNU-387', 'HLF', 'SNU-398', 'HuCC-T1-G10',\n",
235
+ " 'NCI-H23', 'NCI-H358', 'HCC1937', 'Capan-1', 'SW620', 'KM12',\n",
236
+ " 'HEL', 'RAW 264.7', 'Pfeiffer', 'DoHH2', 'U937(CD59+)', 'Z-138',\n",
237
+ " 'OCI-AML-2', 'OCI-AML-3', 'Kasumi-1', 'NB4', 'NCI-H1666',\n",
238
+ " 'CAL-12T', 'SK-MEL-246', 'Ba/F3', 'KYSE-270', 'HCT 116', 'Calu-1',\n",
239
+ " 'Ku812', 'BT474 A3', 'AsPC-1', 'SK-LU-1', 'HEI-OC1', 'BEL-7402',\n",
240
+ " 'SH-SY5Y', 'JeKo-1', 'TMD8', 'MHH-CALL-4', 'KOPN-49', 'SUP-M2',\n",
241
+ " 'CC-LP-1', 'KATO III', 'HEK293A mRFP-ATG9', 'HAP1', 'CGBC 01'],\n",
242
+ " dtype=object)"
243
+ ]
244
+ },
245
+ "execution_count": 5,
246
+ "metadata": {},
247
+ "output_type": "execute_result"
248
+ }
249
+ ],
250
+ "source": [
251
+ "protac_df = pd.read_csv('../data/PROTAC-Degradation-DB.csv')\n",
252
+ "cell_lines = protac_df['Cell Line Identifier'].unique()\n",
253
+ "cell_lines"
254
+ ]
255
+ },
256
+ {
257
+ "cell_type": "markdown",
258
+ "metadata": {},
259
+ "source": [
260
+ "Each entry in cellosaurus looks as the following:\n",
261
+ "\n",
262
+ "```\n",
263
+ "ID #W7079\n",
264
+ "AC CVCL_E549\n",
265
+ "SY #W7079 REM; REMUS; W7079\n",
266
+ "DR dbMHC; 48440\n",
267
+ "DR ECACC; 94022552\n",
268
+ "DR IHW; IHW09223\n",
269
+ "DR IPD-IMGT/HLA; 11548\n",
270
+ "DR Wikidata; Q54480892\n",
271
+ "RX PubMed=30844424;\n",
272
+ "CC Part of: 12th International Histocompatibility Workshop (12IHW) cell line panel.\n",
273
+ "CC Population: Caucasian.\n",
274
+ "CC HLA typing: A*02:01,02:06; B*40:01:02:01,67:01:01; C*03,07; DPB1*04:01,05:01 (IPD-IMGT/HLA=11548).\n",
275
+ "CC Transformant: NCBI_TaxID; 10376; Epstein-Barr virus (EBV).\n",
276
+ "CC Derived from site: In situ; Peripheral blood; UBERON=UBERON_0000178.\n",
277
+ "CC Cell type: B-cell; CL=CL_0000236.\n",
278
+ "OX NCBI_TaxID=9606; ! Homo sapiens (Human)\n",
279
+ "SX Sex unspecified\n",
280
+ "AG Age unspecified\n",
281
+ "CA Transformed cell line\n",
282
+ "DT Created: 22-10-12; Last updated: 30-01-24; Version: 17\n",
283
+ "//\n",
284
+ "```"
285
+ ]
286
+ },
287
+ {
288
+ "cell_type": "code",
289
+ "execution_count": null,
290
+ "metadata": {},
291
+ "outputs": [],
292
+ "source": [
293
+ "# Load cellosaurus data into a string file\n",
294
+ "with open('data/cellosaurus.txt', 'r') as f:\n",
295
+ " cellosaurus = f.read()"
296
+ ]
297
+ },
298
+ {
299
+ "cell_type": "code",
300
+ "execution_count": 14,
301
+ "metadata": {},
302
+ "outputs": [],
303
+ "source": [
304
+ "cell2cellosaurus = {}\n",
305
+ "for cell_line in cell_lines:\n",
306
+ " cell2cellosaurus[cell_line] = None\n",
307
+ " for i, entry in enumerate(cellosaurus.split('//\\n')):\n",
308
+ " # print(entry)\n",
309
+ " # print('-' * 80)\n",
310
+ " if f'ID {cell_line}' in entry:\n",
311
+ " cell2cellosaurus[cell_line] = entry\n",
312
+ "\n",
313
+ " if 'E3' in entry or 'ligase' in entry.lower():\n",
314
+ " print(cell_line)\n",
315
+ " print(entry)\n",
316
+ " print('-' * 80)\n",
317
+ " break"
318
+ ]
319
+ },
320
+ {
321
+ "cell_type": "code",
322
+ "execution_count": 22,
323
+ "metadata": {},
324
+ "outputs": [
325
+ {
326
+ "name": "stdout",
327
+ "output_type": "stream",
328
+ "text": [
329
+ "ID HCT116-53BPI(+/-)\n",
330
+ "AC CVCL_1R00\n",
331
+ "DR cancercelllines; CVCL_1R00\n",
332
+ "DR RCB; RCB2996\n",
333
+ "DR Wikidata; Q54882028\n",
334
+ "CC Population: Caucasian.\n",
335
+ "CC Knockout cell: Method=Homologous recombination; HGNC; 11999; TP53BP1 (Note=1 of 2 alleles).\n",
336
+ "CC Sequence variation: Mutation; HGNC; 173; ACVR2A; Simple; p.Lys437Argfs*5 (c.1310delA); dbSNP=rs764719749; Zygosity=Homozygous (from parent cell line).\n",
337
+ "CC Sequence variation: Mutation; HGNC; 1101; BRCA2; Simple; p.Ile2675Aspfs*6 (c.8021dupA) (c.8021_8022insA); ClinVar=VCV000267050; Zygosity=Heterozygous (from parent cell line).\n",
338
+ "CC Sequence variation: Mutation; HGNC; 1787; CDKN2A; Simple; p.Arg24Serfs*20 (c.68dupG) (c.68_69insG) (p.G23fs); Zygosity=Heterozygous (from parent cell line).\n",
339
+ "CC Sequence variation: Mutation; HGNC; 2514; CTNNB1; Simple; p.Ser45del (c.133_135delTCT); ClinVar=VCV000017576; Zygosity=Heterozygous (from parent cell line).\n",
340
+ "CC Sequence variation: Mutation; HGNC; 3373; EP300; Simple; p.Met1470Cysfs*22 (c.4408delA); Zygosity=Heterozygous (from parent cell line).\n",
341
+ "CC Sequence variation: Mutation; HGNC; 3373; EP300; Simple; p.Asn1700Thrfs*9 (c.5099delA); Zygosity=Heterozygous (from parent cell line).\n",
342
+ "CC Sequence variation: Mutation; HGNC; 6407; KRAS; Simple; p.Gly13Asp (c.38G>A); ClinVar=VCV000012580; Zygosity=Heterozygous (from parent cell line).\n",
343
+ "CC Sequence variation: Mutation; HGNC; 8975; PIK3CA; Simple; p.His1047Arg (c.3140A>G); ClinVar=VCV000013652; Zygosity=Heterozygous (from parent cell line).\n",
344
+ "CC Sequence variation: Mutation; HGNC; 9277; PPM1D; Simple; p.Leu450Ter (c.1349delT) (p.Leu450fs) (c.1344delT); Zygosity=Heterozygous (from parent cell line).\n",
345
+ "CC Sequence variation: Mutation; HGNC; 11773; TGFBR2; Simple; p.Lys128Serfs*35 (c.383delA); ClinVar=VCV000477546; Zygosity=Homozygous (from parent cell line).\n",
346
+ "CC Derived from site: In situ; Colon; UBERON=UBERON_0001155.\n",
347
+ "DI NCIt; C4910; Colon carcinoma\n",
348
+ "OX NCBI_TaxID=9606; ! Homo sapiens (Human)\n",
349
+ "HI CVCL_0291 ! HCT 116\n",
350
+ "SX Male\n",
351
+ "AG 48Y\n",
352
+ "CA Cancer cell line\n",
353
+ "DT Created: 08-07-15; Last updated: 30-01-24; Version: 13\n",
354
+ "\n",
355
+ "--------------------------------------------------------------------------------\n",
356
+ "ID Huh7 IFITM2-/-\n",
357
+ "AC CVCL_UZ56\n",
358
+ "DR cancercelllines; CVCL_UZ56\n",
359
+ "DR Wikidata; Q94308822\n",
360
+ "RX PubMed=30723923;\n",
361
+ "CC Population: Japanese.\n",
362
+ "CC Knockout cell: Method=CRISPR/Cas9; HGNC; 5413; IFITM2.\n",
363
+ "CC Sequence variation: Mutation; HGNC; 6307; KDR; Simple; p.Gln472His (c.1416A>T); ClinVar=VCV000134603; Zygosity=Homozygous (from parent cell line).\n",
364
+ "CC Sequence variation: Mutation; HGNC; 20932; POLD3; Simple; p.Lys109Arg (c.326A>G) (p.Lys70Arg, c.209A>G); Zygosity=Unspecified (from parent cell line).\n",
365
+ "CC Sequence variation: Mutation; HGNC; 11730; TERT; Simple; c.1-124C>T (c.228C>T) (C228T); Zygosity=Unspecified; Note=In promoter (from parent cell line).\n",
366
+ "CC Sequence variation: Mutation; HGNC; 11998; TP53; Simple; p.Tyr220Cys (c.659A>G); ClinVar=VCV000127819; Zygosity=Homozygous (from parent cell line).\n",
367
+ "CC Derived from site: In situ; Liver; UBERON=UBERON_0002107.\n",
368
+ "DI NCIt; C7956; Adult hepatocellular carcinoma\n",
369
+ "DI ORDO; Orphanet_210159; Adult hepatocellular carcinoma\n",
370
+ "OX NCBI_TaxID=9606; ! Homo sapiens (Human)\n",
371
+ "HI CVCL_0336 ! Huh-7\n",
372
+ "SX Male\n",
373
+ "AG 57Y\n",
374
+ "CA Cancer cell line\n",
375
+ "DT Created: 25-02-19; Last updated: 05-10-23; Version: 10\n",
376
+ "\n",
377
+ "--------------------------------------------------------------------------------\n"
378
+ ]
379
+ }
380
+ ],
381
+ "source": [
382
+ "for cell_line, cellosaurus_entry in cell2cellosaurus.items():\n",
383
+ " if pd.isna(cell_line):\n",
384
+ " continue\n",
385
+ " if '-/-' in cell_line or '+/-' in cell_line or '+/+' in cell_line or '-/-' in cellosaurus_entry or '+/-' in cellosaurus_entry or '+/+' in cellosaurus_entry:\n",
386
+ " print(cellosaurus_entry)\n",
387
+ " print('-' * 80)\n"
388
+ ]
389
+ },
390
+ {
391
+ "cell_type": "code",
392
+ "execution_count": 23,
393
+ "metadata": {},
394
+ "outputs": [
395
+ {
396
+ "name": "stdout",
397
+ "output_type": "stream",
398
+ "text": [
399
+ "HCT116\n",
400
+ "HCT116-53BPI(+/-)\n",
401
+ "--------------------------------------------------------------------------------\n",
402
+ "Huh7\n",
403
+ "Huh7 IFITM2-/-\n",
404
+ "--------------------------------------------------------------------------------\n"
405
+ ]
406
+ }
407
+ ],
408
+ "source": [
409
+ "for cell_synonym, cell_id in cell2identifier.items():\n",
410
+ " if pd.isna(cell_line):\n",
411
+ " continue\n",
412
+ " if '-/-' in cell_synonym or '+/-' in cell_synonym or '+/+' in cell_synonym or '-/-' in cell_id or '+/-' in cell_id or '+/+' in cell_id:\n",
413
+ " print(cell_synonym)\n",
414
+ " print(cell_id)\n",
415
+ " print('-' * 80)"
416
+ ]
417
+ },
418
+ {
419
+ "cell_type": "code",
420
+ "execution_count": null,
421
+ "metadata": {},
422
+ "outputs": [],
423
+ "source": []
424
+ }
425
+ ],
426
+ "metadata": {
427
+ "kernelspec": {
428
+ "display_name": "paroutes-env",
429
+ "language": "python",
430
+ "name": "python3"
431
+ },
432
+ "language_info": {
433
+ "codemirror_mode": {
434
+ "name": "ipython",
435
+ "version": 3
436
+ },
437
+ "file_extension": ".py",
438
+ "mimetype": "text/x-python",
439
+ "name": "python",
440
+ "nbconvert_exporter": "python",
441
+ "pygments_lexer": "ipython3",
442
+ "version": "3.8.19"
443
+ }
444
+ },
445
+ "nbformat": 4,
446
+ "nbformat_minor": 2
447
+ }