@datagrok/sequence-translator 0.0.3 → 0.0.6

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (15) hide show
  1. package/.eslintrc.json +39 -0
  2. package/detectors.js +10 -14
  3. package/package.json +8 -2
  4. package/setup.cmd +11 -0
  5. package/src/axolabsMap.ts +101 -99
  6. package/src/defineAxolabsPattern.ts +242 -207
  7. package/src/drawAxolabsPattern.ts +127 -92
  8. package/src/map.ts +538 -353
  9. package/src/package-test.ts +12 -0
  10. package/src/package.ts +619 -293
  11. package/src/save-sense-antisense.ts +44 -0
  12. package/src/tests/smiles-tests.ts +454 -0
  13. package/webpack.config.js +7 -1
  14. package/scripts/convertFastaToSmiles +0 -24
  15. package/scripts/drawAxolabsPattern +0 -50
package/src/map.ts CHANGED
@@ -1,355 +1,540 @@
1
- export const stadardPhosphateLinkSMILES = 'OP(=O)(O)O';
2
- export const map: {[synthesizer: string]: {[technology: string]: {[code: string]: {"name": string, "weight": number, "normalized": string, "SMILES": string}}}} = {
3
- "BioSpring Codes": {
4
- "For ASO Gapmers": {
5
- "5": {
6
- "name": "2'MOE-5Me-rU",
7
- "weight": 378.27,
8
- "normalized": "rU",
9
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))[C@H](OCCOC)[C@@H]1O"
10
- },
11
- "6": {
12
- "name": "2'MOE-rA",
13
- "weight": 387.29,
14
- "normalized": "rA",
15
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OCCOC)[C@@H]1O"
16
- },
17
- "7": {
18
- "name": "2'MOE-5Me-rC",
19
- "weight": 377.29,
20
- "normalized": "rC",
21
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))[C@H](OCCOC)[C@@H]1O"
22
- },
23
- "8": {
24
- "name": "2'MOE-rG",
25
- "weight": 403.28,
26
- "normalized": "rG",
27
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OCCOC)[C@@H]1O"
28
- },
29
- "9": {
30
- "name": "5-Methyl-dC",
31
- "weight": 303.21,
32
- "normalized": "dC",
33
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))C[C@@H]1O"
34
- },
35
- "*": {
36
- "name": "ps linkage",
37
- "weight": 16.07,
38
- "normalized": "",
39
- "SMILES": "OP(=O)(O)S"
40
- },
41
- "A": {
42
- "name": "Adenine",
43
- "weight": 313.21,
44
- "normalized": "dA",
45
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O"
46
- },
47
- "C": {
48
- "name": "Cytosine",
49
- "weight": 289.18,
50
- "normalized": "dC",
51
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O"
52
- },
53
- "G": {
54
- "name": "Guanine",
55
- "weight": 329.21,
56
- "normalized": "dG",
57
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O"
58
- },
59
- "T": {
60
- "name": "Tyrosine",
61
- "weight": 304.2,
62
- "normalized": "dT",
63
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O"
64
- }
65
- },
66
- "For 2'-OMe and 2'-F modified siRNA": {
67
- "1": {
68
- "name": "2'-fluoro-U",
69
- "weight": 308.16,
70
- "normalized": "rU",
71
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O"
72
- },
73
- "2": {
74
- "name": "2'-fluoro-A",
75
- "weight": 331.2,
76
- "normalized": "rA",
77
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O"
78
- },
79
- "3": {
80
- "name": "2'-fluoro-C",
81
- "weight": 307.18,
82
- "normalized": "rC",
83
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O"
84
- },
85
- "4": {
86
- "name": "2'-fluoro-G",
87
- "weight": 347.19,
88
- "normalized": "rG",
89
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1O"
90
- },
91
- "5": {
92
- "name": "2'OMe-rU",
93
- "weight": 320.2,
94
- "normalized": "rU",
95
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O"
96
- },
97
- "6": {
98
- "name": "2'OMe-rA",
99
- "weight": 343.24,
100
- "normalized": "rA",
101
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O"
102
- },
103
- "7": {
104
- "name": "2'OMe-rC",
105
- "weight": 319.21,
106
- "normalized": "rC",
107
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O"
108
- },
109
- "8": {
110
- "name": "2'OMe-rG",
111
- "weight": 359.24,
112
- "normalized": "rG",
113
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O"
114
- },
115
- "*": {
116
- "name": "ps linkage",
117
- "weight": 16.07,
118
- "normalized": "",
119
- "SMILES": "OP(=O)(O)S"
120
- }
121
- }
1
+ export const SYNTHESIZERS = {
2
+ RAW_NUCLEOTIDES: 'Raw Nucleotides',
3
+ BIOSPRING: 'BioSpring Codes',
4
+ GCRS: 'Janssen GCRS Codes',
5
+ AXOLABS: 'Axolabs Codes',
6
+ MERMADE_12: 'Mermade 12',
7
+ };
8
+ export const TECHNOLOGIES = {
9
+ DNA: 'DNA',
10
+ RNA: 'RNA',
11
+ ASO_GAPMERS: 'For ASO Gapmers',
12
+ SI_RNA: 'For 2\'-OMe and 2\'-F modified siRNA',
13
+ };
14
+ // interface CODES {
15
+ // }
16
+ export const MODIFICATIONS: {[index: string]: {left: string, right: string}} = {
17
+ '(invabasic)': {
18
+ left: 'O[C@@H]1C[C@@H]O[C@H]1CO',
19
+ right: 'O[C@@H]1C[C@@H]O[C@H]1CO',
122
20
  },
123
- "Axolabs Codes": {
124
- "For 2'-OMe and 2'-F modified siRNA": {
125
- "Uf": {
126
- "name": "2'-fluoro-U",
127
- "weight": 308.16,
128
- "normalized": "rU",
129
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O"
130
- },
131
- "Af": {
132
- "name": "2'-fluoro-A",
133
- "weight": 331.2,
134
- "normalized": "rA",
135
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O"
136
- },
137
- "Cf": {
138
- "name": "2'-fluoro-C",
139
- "weight": 307.18,
140
- "normalized": "rC",
141
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O"
142
- },
143
- "Gf": {
144
- "name": "2'-fluoro-G",
145
- "weight": 347.19,
146
- "normalized": "rG",
147
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1O"
148
- },
149
- "u": {
150
- "name": "2'OMe-rU",
151
- "weight": 320.2,
152
- "normalized": "rU",
153
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O"
154
- },
155
- "a": {
156
- "name": "2'OMe-rA",
157
- "weight": 343.24,
158
- "normalized": "rA",
159
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O"
160
- },
161
- "c": {
162
- "name": "2'OMe-rC",
163
- "weight": 319.21,
164
- "normalized": "rC",
165
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O"
166
- },
167
- "g": {
168
- "name": "2'OMe-rG",
169
- "weight": 359.,
170
- "normalized": "rG",
171
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O"
172
- },
173
- "s": {
174
- "name": "ps linkage",
175
- "weight": 16.07,
176
- "normalized": "",
177
- "SMILES": "OP(=O)(O)S"
178
- }
179
- }
21
+ '(GalNAc-2-JNJ)': {
22
+ left: 'C(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)' +
23
+ '(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)' +
24
+ '(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)NC(=O)CCCC(=O)NCC(O)CO',
25
+ right: 'OCC(O)CNC(=O)CCCC(=O)NC(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)' +
26
+ '(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)'+
27
+ '(COCCC(=O)NCCCNC(=O)CCCCOC2OC(CO)C(O)C(O)C2NC(=O)C)',
180
28
  },
181
- "Janssen GCRS Codes": {
182
- "For ASO Gapmers": {
183
- "moeT": {
184
- "name": "2'MOE-5Me-rU",
185
- "weight": 378.27,
186
- "normalized": "rU",
187
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))[C@H](OCCOC)[C@@H]1O"
188
- },
189
- "moeA": {
190
- "name": "2'MOE-rA",
191
- "weight": 387.29,
192
- "normalized": "rA",
193
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OCCOC)[C@@H]1O"
194
- },
195
- "moe5mC": {
196
- "name": "2'MOE-5Me-rC",
197
- "weight": 377.29,
198
- "normalized": "rC",
199
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))[C@H](OCCOC)[C@@H]1O"
200
- },
201
- "(5m)moeC": {
202
- "name": "2'MOE-5Me-rC",
203
- "weight": 377.29,
204
- "normalized": "rC",
205
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))[C@H](OCCOC)[C@@H]1O"
206
- },
207
- "moeG": {
208
- "name": "2'MOE-rG",
209
- "weight": 403.28,
210
- "normalized": "rG",
211
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OCCOC)[C@@H]1O"
212
- },
213
- "5mC": {
214
- "name": "5-Methyl-dC",
215
- "weight": 303.28,
216
- "normalized": "dC",
217
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))C[C@@H]1O"
218
- },
219
- "(5m)C": {
220
- "name": "5-Methyl-dC",
221
- "weight": 303.28,
222
- "normalized": "dC",
223
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))C[C@@H]1O"
224
- },
225
- "ps": {
226
- "name": "ps linkage",
227
- "weight": 16.07,
228
- "normalized": "",
229
- "SMILES": "OP(=O)(O)S"
230
- },
231
- "A": {
232
- "name": "Adenine",
233
- "weight": 313.21,
234
- "normalized": "dA",
235
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O"
236
- },
237
- "dA": {
238
- "name": "Adenine",
239
- "weight": 313.21,
240
- "normalized": "dA",
241
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O"
242
- },
243
- "C": {
244
- "name": "Cytosine",
245
- "weight": 289.18,
246
- "normalized": "dC",
247
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O"
248
- },
249
- "dC": {
250
- "name": "Cytosine",
251
- "weight": 289.18,
252
- "normalized": "dC",
253
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O"
254
- },
255
- "G": {
256
- "name": "Guanine",
257
- "weight": 329.21,
258
- "normalized": "dG",
259
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O"
260
- },
261
- "dG": {
262
- "name": "Guanine",
263
- "weight": 329.21,
264
- "normalized": "dG",
265
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O"
266
- },
267
- "T": {
268
- "name": "Tyrosine",
269
- "weight": 304.2,
270
- "normalized": "dT",
271
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O"
272
- },
273
- "dT": {
274
- "name": "Tyrosine",
275
- "weight": 304.2,
276
- "normalized": "dT",
277
- "SMILES": "OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O"
278
- },
279
- "rA": {
280
- "name": "Adenine",
281
- "weight": 329.21,
282
- "normalized": "rA",
283
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](O)[C@@H]1O"
284
- },
285
- "rC": {
286
- "name": "Cytosine",
287
- "weight": 305.18,
288
- "normalized": "rC",
289
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](O)[C@@H]1O"
290
- },
291
- "rG": {
292
- "name": "Guanine",
293
- "weight": 345.21,
294
- "normalized": "rG",
295
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](O)[C@@H]1O"
296
- },
297
- "rU": {
298
- "name": "Uracil",
299
- "weight": 306.17,
300
- "normalized": "rU",
301
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](O)[C@@H]1O"
302
- }
303
- },
304
- "For 2'-OMe and 2'-F modified siRNA": {
305
- "fU": {
306
- "name": "2'-fluoro-U",
307
- "weight": 308.16,
308
- "normalized": "rU",
309
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O"
310
- },
311
- "fA": {
312
- "name": "2'-fluoro-A",
313
- "weight": 331.2,
314
- "normalized": "rA",
315
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O"
316
- },
317
- "fC": {
318
- "name": "2'-fluoro-C",
319
- "weight": 307.18,
320
- "normalized": "rC",
321
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O"
322
- },
323
- "fG": {
324
- "name": "2'-fluoro-G",
325
- "weight": 347.19,
326
- "normalized": "rG",
327
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1O"
328
- },
329
- "mU": {
330
- "name": "2'OMe-rU",
331
- "weight": 320.2,
332
- "normalized": "rU",
333
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O"
334
- },
335
- "mA": {
336
- "name": "2'OMe-rA",
337
- "weight": 343.24,
338
- "normalized": "rA",
339
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O"
340
- },
341
- "mC": {
342
- "name": "2'OMe-rC",
343
- "weight": 319.21,
344
- "normalized": "rC",
345
- "SMILES": "OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O"
346
- },
347
- "mG": {
348
- "name": "2'OMe-rG",
349
- "weight": 359.24,
350
- "normalized": "rG",
351
- "SMILES": "OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O"
352
- }
353
- }
354
- }
355
- };
29
+ };
30
+ export const stadardPhosphateLinkSmiles = 'OP(=O)(O)O';
31
+ export const map: {[synthesizer: string]:
32
+ {[technology: string]: {[code: string]:
33
+ {'name': string, 'weight': number, 'normalized': string, 'SMILES': string}}}} = {
34
+ 'Raw Nucleotides': {
35
+ 'DNA': {
36
+ 'A': {
37
+ 'name': 'Adenine',
38
+ 'weight': 313.21,
39
+ 'normalized': 'dA',
40
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O',
41
+ },
42
+ 'T': {
43
+ 'name': 'Tyrosine',
44
+ 'weight': 304.2,
45
+ 'normalized': 'dT',
46
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O',
47
+ },
48
+ 'G': {
49
+ 'name': 'Guanine',
50
+ 'weight': 329.21,
51
+ 'normalized': 'dG',
52
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
53
+ },
54
+ 'C': {
55
+ 'name': 'Cytosine',
56
+ 'weight': 289.18,
57
+ 'normalized': 'dC',
58
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O',
59
+ },
60
+ },
61
+ 'RNA': {
62
+ 'A': {
63
+ 'name': 'Adenine',
64
+ 'weight': 313.21,
65
+ 'normalized': 'dA',
66
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O',
67
+ },
68
+ 'U': {
69
+ 'name': 'Uracil',
70
+ 'weight': 306.17,
71
+ 'normalized': 'rU',
72
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](O)[C@@H]1O',
73
+ },
74
+ 'G': {
75
+ 'name': 'Guanine',
76
+ 'weight': 329.21,
77
+ 'normalized': 'dG',
78
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
79
+ },
80
+ 'C': {
81
+ 'name': 'Cytosine',
82
+ 'weight': 289.18,
83
+ 'normalized': 'dC',
84
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O',
85
+ },
86
+ },
87
+ },
88
+ 'BioSpring Codes': {
89
+ 'For ASO Gapmers': {
90
+ '5': {
91
+ 'name': '2\'MOE-5Me-rU',
92
+ 'weight': 378.27,
93
+ 'normalized': 'rU',
94
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))[C@H](OCCOC)[C@@H]1O',
95
+ },
96
+ '6': {
97
+ 'name': '2\'MOE-rA',
98
+ 'weight': 387.29,
99
+ 'normalized': 'rA',
100
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OCCOC)[C@@H]1O',
101
+ },
102
+ '7': {
103
+ 'name': '2\'MOE-5Me-rC',
104
+ 'weight': 377.29,
105
+ 'normalized': 'rC',
106
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))[C@H](OCCOC)[C@@H]1O',
107
+ },
108
+ '8': {
109
+ 'name': '2\'MOE-rG',
110
+ 'weight': 403.28,
111
+ 'normalized': 'rG',
112
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OCCOC)[C@@H]1O',
113
+ },
114
+ '9': {
115
+ 'name': '5-Methyl-dC',
116
+ 'weight': 303.21,
117
+ 'normalized': 'dC',
118
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))C[C@@H]1O',
119
+ },
120
+ '*': {
121
+ 'name': 'ps linkage',
122
+ 'weight': 16.07,
123
+ 'normalized': '',
124
+ 'SMILES': 'OP(=O)(S)O',
125
+ },
126
+ 'A': {
127
+ 'name': 'Adenine',
128
+ 'weight': 313.21,
129
+ 'normalized': 'dA',
130
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O',
131
+ },
132
+ 'C': {
133
+ 'name': 'Cytosine',
134
+ 'weight': 289.18,
135
+ 'normalized': 'dC',
136
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O',
137
+ },
138
+ 'G': {
139
+ 'name': 'Guanine',
140
+ 'weight': 329.21,
141
+ 'normalized': 'dG',
142
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
143
+ },
144
+ 'T': {
145
+ 'name': 'Tyrosine',
146
+ 'weight': 304.2,
147
+ 'normalized': 'dT',
148
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O',
149
+ },
150
+ },
151
+ 'For 2\'-OMe and 2\'-F modified siRNA': {
152
+ '1': {
153
+ 'name': '2\'-fluoro-U',
154
+ 'weight': 308.16,
155
+ 'normalized': 'rU',
156
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O',
157
+ },
158
+ '2': {
159
+ 'name': '2\'-fluoro-A',
160
+ 'weight': 331.2,
161
+ 'normalized': 'rA',
162
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O',
163
+ },
164
+ '3': {
165
+ 'name': '2\'-fluoro-C',
166
+ 'weight': 307.18,
167
+ 'normalized': 'rC',
168
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O',
169
+ },
170
+ '4': {
171
+ 'name': '2\'-fluoro-G',
172
+ 'weight': 347.19,
173
+ 'normalized': 'rG',
174
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1O',
175
+ },
176
+ '5': {
177
+ 'name': '2\'OMe-rU',
178
+ 'weight': 320.2,
179
+ 'normalized': 'rU',
180
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O',
181
+ },
182
+ '6': {
183
+ 'name': '2\'OMe-rA',
184
+ 'weight': 343.24,
185
+ 'normalized': 'rA',
186
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O',
187
+ },
188
+ '7': {
189
+ 'name': '2\'OMe-rC',
190
+ 'weight': 319.21,
191
+ 'normalized': 'rC',
192
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O',
193
+ },
194
+ '8': {
195
+ 'name': '2\'OMe-rG',
196
+ 'weight': 359.24,
197
+ 'normalized': 'rG',
198
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O',
199
+ },
200
+ '*': {
201
+ 'name': 'ps linkage',
202
+ 'weight': 16.07,
203
+ 'normalized': '',
204
+ 'SMILES': 'OP(=O)(S)O',
205
+ },
206
+ },
207
+ },
208
+ 'Axolabs Codes': {
209
+ 'For 2\'-OMe and 2\'-F modified siRNA': {
210
+ 'Uf': {
211
+ 'name': '2\'-fluoro-U',
212
+ 'weight': 308.16,
213
+ 'normalized': 'rU',
214
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O',
215
+ },
216
+ 'Af': {
217
+ 'name': '2\'-fluoro-A',
218
+ 'weight': 331.2,
219
+ 'normalized': 'rA',
220
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O',
221
+ },
222
+ 'Cf': {
223
+ 'name': '2\'-fluoro-C',
224
+ 'weight': 307.18,
225
+ 'normalized': 'rC',
226
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O',
227
+ },
228
+ 'Gf': {
229
+ 'name': '2\'-fluoro-G',
230
+ 'weight': 347.19,
231
+ 'normalized': 'rG',
232
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1O',
233
+ },
234
+ 'u': {
235
+ 'name': '2\'OMe-rU',
236
+ 'weight': 320.2,
237
+ 'normalized': 'rU',
238
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O',
239
+ },
240
+ 'a': {
241
+ 'name': '2\'OMe-rA',
242
+ 'weight': 343.24,
243
+ 'normalized': 'rA',
244
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O',
245
+ },
246
+ 'c': {
247
+ 'name': '2\'OMe-rC',
248
+ 'weight': 319.21,
249
+ 'normalized': 'rC',
250
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O',
251
+ },
252
+ 'g': {
253
+ 'name': '2\'OMe-rG',
254
+ 'weight': 359.,
255
+ 'normalized': 'rG',
256
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O',
257
+ },
258
+ 's': {
259
+ 'name': 'ps linkage',
260
+ 'weight': 16.07,
261
+ 'normalized': '',
262
+ 'SMILES': 'OP(=O)(S)O',
263
+ },
264
+ },
265
+ },
266
+ 'Janssen GCRS Codes': {
267
+ 'For ASO Gapmers': {
268
+ 'moeT': {
269
+ 'name': '2\'MOE-5Me-rU',
270
+ 'weight': 378.27,
271
+ 'normalized': 'rU',
272
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))[C@H](OCCOC)[C@@H]1O',
273
+ },
274
+ 'moeA': {
275
+ 'name': '2\'MOE-rA',
276
+ 'weight': 387.29,
277
+ 'normalized': 'rA',
278
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OCCOC)[C@@H]1O',
279
+ },
280
+ 'moe5mC': {
281
+ 'name': '2\'MOE-5Me-rC',
282
+ 'weight': 377.29,
283
+ 'normalized': 'rC',
284
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))[C@H](OCCOC)[C@@H]1O',
285
+ },
286
+ '(5m)moeC': {
287
+ 'name': '2\'MOE-5Me-rC',
288
+ 'weight': 377.29,
289
+ 'normalized': 'rC',
290
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))[C@H](OCCOC)[C@@H]1O',
291
+ },
292
+ 'moeG': {
293
+ 'name': '2\'MOE-rG',
294
+ 'weight': 403.28,
295
+ 'normalized': 'rG',
296
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OCCOC)[C@@H]1O',
297
+ },
298
+ '5mC': {
299
+ 'name': '5-Methyl-dC',
300
+ 'weight': 303.28,
301
+ 'normalized': 'dC',
302
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))C[C@@H]1O',
303
+ },
304
+ '(5m)C': {
305
+ 'name': '5-Methyl-dC',
306
+ 'weight': 303.28,
307
+ 'normalized': 'dC',
308
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(N)=NC2(=O))C[C@@H]1O',
309
+ },
310
+ 'ps': {
311
+ 'name': 'ps linkage',
312
+ 'weight': 16.07,
313
+ 'normalized': '',
314
+ 'SMILES': 'OP(=O)(S)O',
315
+ },
316
+ 'A': {
317
+ 'name': 'Adenine',
318
+ 'weight': 313.21,
319
+ 'normalized': 'dA',
320
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O',
321
+ },
322
+ 'dA': {
323
+ 'name': 'Adenine',
324
+ 'weight': 313.21,
325
+ 'normalized': 'dA',
326
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)C[C@@H]1O',
327
+ },
328
+ 'C': {
329
+ 'name': 'Cytosine',
330
+ 'weight': 289.18,
331
+ 'normalized': 'dC',
332
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O',
333
+ },
334
+ 'dC': {
335
+ 'name': 'Cytosine',
336
+ 'weight': 289.18,
337
+ 'normalized': 'dC',
338
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))C[C@@H]1O',
339
+ },
340
+ 'G': {
341
+ 'name': 'Guanine',
342
+ 'weight': 329.21,
343
+ 'normalized': 'dG',
344
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
345
+ },
346
+ 'dG': {
347
+ 'name': 'Guanine',
348
+ 'weight': 329.21,
349
+ 'normalized': 'dG',
350
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)C)[C@@H]1O',
351
+ },
352
+ 'T': {
353
+ 'name': 'Tyrosine',
354
+ 'weight': 304.2,
355
+ 'normalized': 'dT',
356
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O',
357
+ },
358
+ 'dT': {
359
+ 'name': 'Tyrosine',
360
+ 'weight': 304.2,
361
+ 'normalized': 'dT',
362
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=C(C)C(=O)NC2(=O))C[C@@H]1O',
363
+ },
364
+ 'rA': {
365
+ 'name': 'Adenine',
366
+ 'weight': 329.21,
367
+ 'normalized': 'rA',
368
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](O)[C@@H]1O',
369
+ },
370
+ 'rC': {
371
+ 'name': 'Cytosine',
372
+ 'weight': 305.18,
373
+ 'normalized': 'rC',
374
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](O)[C@@H]1O',
375
+ },
376
+ 'rG': {
377
+ 'name': 'Guanine',
378
+ 'weight': 345.21,
379
+ 'normalized': 'rG',
380
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](O)[C@@H]1O',
381
+ },
382
+ 'rU': {
383
+ 'name': 'Uracil',
384
+ 'weight': 306.17,
385
+ 'normalized': 'rU',
386
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](O)[C@@H]1O',
387
+ },
388
+ },
389
+ 'For 2\'-OMe and 2\'-F modified siRNA': {
390
+ 'fU': {
391
+ 'name': '2\'-fluoro-U',
392
+ 'weight': 308.16,
393
+ 'normalized': 'rU',
394
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O',
395
+ },
396
+ 'fA': {
397
+ 'name': '2\'-fluoro-A',
398
+ 'weight': 331.2,
399
+ 'normalized': 'rA',
400
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O',
401
+ },
402
+ 'fC': {
403
+ 'name': '2\'-fluoro-C',
404
+ 'weight': 307.18,
405
+ 'normalized': 'rC',
406
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O',
407
+ },
408
+ 'fG': {
409
+ 'name': '2\'-fluoro-G',
410
+ 'weight': 347.19,
411
+ 'normalized': 'rG',
412
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1O',
413
+ },
414
+ 'mU': {
415
+ 'name': '2\'OMe-rU',
416
+ 'weight': 320.2,
417
+ 'normalized': 'rU',
418
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O',
419
+ },
420
+ 'mA': {
421
+ 'name': '2\'OMe-rA',
422
+ 'weight': 343.24,
423
+ 'normalized': 'rA',
424
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O',
425
+ },
426
+ 'mC': {
427
+ 'name': '2\'OMe-rC',
428
+ 'weight': 319.21,
429
+ 'normalized': 'rC',
430
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O',
431
+ },
432
+ 'mG': {
433
+ 'name': '2\'OMe-rG',
434
+ 'weight': 359.24,
435
+ 'normalized': 'rG',
436
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O',
437
+ },
438
+ },
439
+ },
440
+ 'Mermade 12': {
441
+ 'For 2\'-OMe and 2\'-F modified siRNA': {
442
+ 'e': {
443
+ 'name': '2\'OMe-rA-ps',
444
+ 'weight': 359.31,
445
+ 'normalized': 'rA',
446
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(S)O',
447
+ },
448
+ 'h': {
449
+ 'name': '2\'OMe-rU-ps',
450
+ 'weight': 336.27,
451
+ 'normalized': 'rU',
452
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1OP(=O)(S)O',
453
+ },
454
+ 'g': {
455
+ 'name': '2\'OMe-rG-ps',
456
+ 'weight': 375.31,
457
+ 'normalized': 'rG',
458
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1OP(=O)(S)O',
459
+ },
460
+ 'f': {
461
+ 'name': '2\'OMe-rC-ps',
462
+ 'weight': 335.28,
463
+ 'normalized': 'rC',
464
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1OP(=O)(S)O',
465
+ },
466
+ 'i': {
467
+ 'name': '2\'-fluoro-A-ps',
468
+ 'weight': 347.27,
469
+ 'normalized': 'rA',
470
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1OP(=O)(S)O',
471
+ },
472
+ 'l': {
473
+ 'name': '2\'-fluoro-U-ps',
474
+ 'weight': 324.23,
475
+ 'normalized': 'rU',
476
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1OP(=O)(S)O',
477
+ },
478
+ 'k': {
479
+ 'name': '2\'-fluoro-G-ps',
480
+ 'weight': 363.26,
481
+ 'normalized': 'rG',
482
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1OP(=O)(S)O',
483
+ },
484
+ 'j': {
485
+ 'name': '2\'-fluoro-C-ps',
486
+ 'weight': 323.25,
487
+ 'normalized': 'rC',
488
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1OP(=O)(S)O',
489
+ },
490
+ 'L': {
491
+ 'name': '2\'-fluoro-U',
492
+ 'weight': 308.16,
493
+ 'normalized': 'rU',
494
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](F)[C@@H]1O',
495
+ },
496
+ 'I': {
497
+ 'name': '2\'-fluoro-A',
498
+ 'weight': 331.2,
499
+ 'normalized': 'rA',
500
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](F)[C@@H]1O',
501
+ },
502
+ 'J': {
503
+ 'name': '2\'-fluoro-C',
504
+ 'weight': 307.18,
505
+ 'normalized': 'rC',
506
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](F)[C@@H]1O',
507
+ },
508
+ 'K': {
509
+ 'name': '2\'-fluoro-G',
510
+ 'weight': 347.19,
511
+ 'normalized': 'rG',
512
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](F)[C@@H]1O',
513
+ },
514
+ 'H': {
515
+ 'name': '2\'OMe-rU',
516
+ 'weight': 320.2,
517
+ 'normalized': 'rU',
518
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(=O)NC2(=O))[C@H](OC)[C@@H]1O',
519
+ },
520
+ 'E': {
521
+ 'name': '2\'OMe-rA',
522
+ 'weight': 343.24,
523
+ 'normalized': 'rA',
524
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=CN=C(N)C=3N=C2)[C@H](OC)[C@@H]1O',
525
+ },
526
+ 'F': {
527
+ 'name': '2\'OMe-rC',
528
+ 'weight': 319.21,
529
+ 'normalized': 'rC',
530
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C=CC(N)=NC2(=O))[C@H](OC)[C@@H]1O',
531
+ },
532
+ 'G': {
533
+ 'name': '2\'OMe-rG',
534
+ 'weight': 359.24,
535
+ 'normalized': 'rG',
536
+ 'SMILES': 'OC[C@H]1O[C@@H](N2C3N=C(N)NC(=O)C=3N=C2)[C@H](OC)[C@@H]1O',
537
+ },
538
+ },
539
+ },
540
+ };