File size: 12,871 Bytes
bc7aaea |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 70,
"id": "c7317218",
"metadata": {},
"outputs": [],
"source": [
"import requests\n",
"from copy import copy as cp\n"
]
},
{
"cell_type": "markdown",
"id": "c022e07b",
"metadata": {},
"source": [
"## Authorize with the endpoint"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "f1272e3f",
"metadata": {},
"outputs": [],
"source": [
"API_URL = \"https://YOUR.ENDPOINT.aws.endpoints.huggingface.cloud\"\n",
"headers = {\n",
" \"Accept\" : \"application/json\",\n",
" \"Authorization\": \"Bearer hf_YOUR_TOKEN\",\n",
" \"Content-Type\": \"application/json\"\n",
"}\n",
"\n",
"def query(payload):\n",
" response = requests.post(API_URL, headers=headers, json=payload)\n",
" return response.json()"
]
},
{
"cell_type": "markdown",
"id": "082c3300",
"metadata": {},
"source": [
"## Construct the query\n",
"Instructions define what type of experiment you are trying to simulate with P3GPT.<br>\n",
"Key instructions enabled at this endpoint include:\n",
"- <font size=\"4\">**`disease2diff2disease`**</font>: For tasks that are equivalent to case-control cross-sectional settings. E.g. the generation of DEGs for a medical condition;\n",
"- <font size=\"4\">**`compound2diff2compound `**</font>: For compound screening tasks. E.g. propose a compound that can selectively methylate certain gene promoters;\n",
"- <font size=\"4\">**`age_group2diff2age_group`**</font>: For task on aging-related omics dynamics. E.g. identify genes that are up-/down-regulated in older vs younger adults. \n"
]
},
{
"cell_type": "code",
"execution_count": 139,
"id": "fd84fc60",
"metadata": {},
"outputs": [],
"source": [
"prompt = {'instruction': ['age_group2diff2age_group','compound2diff2compound'], \n",
" # This is a chemical screening experiment in a particular age group, \n",
" # so you'll need to use 2 intructions\n",
" 'tissue': 'lung',\n",
" 'age': 70,\n",
" 'cell': '',\n",
" 'efo': 'EFO_0000768', #pulmonary fibrosis\n",
" 'datatype': 'expression', # we want to get DEGs\n",
" 'drug': 'curcumin',\n",
" 'dose': '',\n",
" 'time': '',\n",
" 'case': ['70.0-80.0', '80.0-90.0'], # define the age groups of interest\n",
" 'control': '', # left blank since no healthy controls participate in this experiment\n",
" 'dataset_type': '',\n",
" 'gender': 'm',\n",
" 'species': 'human',\n",
" 'up': [], # left blank to be filled in by P3GPT\n",
" 'down': []\n",
" }\n",
"\n"
]
},
{
"cell_type": "markdown",
"id": "609bd3c0",
"metadata": {},
"source": [
"## Execution modes\n",
"- <font size=\"4\">**`meta2diff`**</font>: `compound2diff2compound` can be executed either way. This mode tells P3GPT to return differentially expressed genes and not compounds;\n",
"- <font size=\"4\">**`diff2compound`**</font>: The reverse of the `meta2diff` mode. Make sure to fill in 'up' and 'down' in the prompt first!\n",
"- <font size=\"4\">**`meta2diff2compound`**</font>: Runs `meta2diff` first and applies `diff2compound` to its output. This is mostly for utility reasons — you get to run P3GPT twice with one call.\n",
"\n",
"As an LLM, P3GPT is trained to fill in the blanks in its prompt pointed at by the instructions. Its native output has the same structure as the input prompt.<br>\n",
"Modes do not belong in the prompt and are used for parsing P3GPT's output so that only the expected part of the completed prompt is presented to the user."
]
},
{
"cell_type": "code",
"execution_count": 140,
"id": "c6280337",
"metadata": {},
"outputs": [],
"source": [
"config_sample = {'inputs': prompt,\n",
" 'mode': 'meta2diff', # this is a chemical screening experiment \n",
" 'parameters': {'temperature': 0.4,\n",
" 'top_p': 0.8,\n",
" 'top_k': 3550,\n",
" 'n_next_tokens': 20}\n",
" }\n",
"output = query(config_sample) # send request to Hugging Face"
]
},
{
"cell_type": "code",
"execution_count": 141,
"id": "47a3f882",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"dict_keys(['output', 'mode', 'message', 'input'])\n"
]
}
],
"source": [
"print(output.keys())"
]
},
{
"cell_type": "code",
"execution_count": 142,
"id": "5408079c",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'Done!'"
]
},
"execution_count": 142,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# successful generation\n",
"output['message']"
]
},
{
"cell_type": "code",
"execution_count": 143,
"id": "f51d4314",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"'[BOS]<age_group2diff2age_group><compound2diff2compound><tissue>lung </tissue><age_individ>70 </age_individ><cell></cell><efo>EFO_0000768 </efo><datatype>expression </datatype><drug>curcumin </drug><dose></dose><time></time><case>70.0-80.0 80.0-90.0 </case><control></control><dataset_type></dataset_type><gender>m </gender><species>human </species>'"
]
},
"execution_count": 143,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# this is what actual P3GPT input looks like\n",
"# NB: there is no 'mode' in the prompt. \n",
"output['input']"
]
},
{
"cell_type": "code",
"execution_count": 144,
"id": "08c9f49a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Up-regulated genes:\n",
"MUC5B; AHSP; ALAS2; SLC4A1; CDHR5; NXF2B; CYP4F3; LGALS7B; FBN3; NTS; CYSTM1; ORM2; ASL; CD177; GLRX5; H4C3; NDUFA3; TUBA4B; EPB42; GCHFR\n",
"\n",
"Down-regulated genes:\n",
"KRT6A; KRT5; KRT15; KRT14; KRT6B; DSG3; CALML3; S100A7; SERPINB5; SPRR2A; SPRR3; LY6D; TMEM45A; KRT16; S100A9; GOLGA8A; SPINK6; CXCL10; CXCL9; CSTA\n",
"\n"
]
}
],
"source": [
"# output gene symbols\n",
"genes_up, genes_dn = output['output']['up'][0], output['output']['down'][0]\n",
"print(\"Up-regulated genes:\")\n",
"print(*genes_up[:20], sep = \"; \",end='\\n\\n')\n",
"print(\"Down-regulated genes:\")\n",
"print(*genes_dn[:20], sep = \"; \",end='\\n\\n')\n"
]
},
{
"cell_type": "code",
"execution_count": 145,
"id": "f6910a3d",
"metadata": {},
"outputs": [],
"source": [
"# now, let's do the opposite and get a compounds based on these DEG lists\n",
"# to do that, we only need a couple changes to the original prompt\n",
"prompt2 = cp(prompt)\n",
"prompt2.update({\n",
" 'drug':'',\n",
" 'up':genes_up,\n",
" 'down':genes_dn\n",
" })\n",
"# remember to reverse meta2diff!\n",
"config_sample.update({'mode':'diff2compound',\n",
" 'inputs':prompt2})"
]
},
{
"cell_type": "code",
"execution_count": 146,
"id": "e791e285",
"metadata": {},
"outputs": [],
"source": [
"output = query(config_sample) # send request to Hugging Face"
]
},
{
"cell_type": "code",
"execution_count": 127,
"id": "8ae15313",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"dict_keys(['output', 'compounds', 'raw_output', 'mode', 'message', 'input'])"
]
},
"execution_count": 127,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"output.keys()"
]
},
{
"cell_type": "code",
"execution_count": 147,
"id": "5f35f00c",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"artemisinin; todralazine; dyphylline; esmolol; formestane; z160; netupitant; brd-k89304341; isoprenaline\n"
]
}
],
"source": [
"print(*output['compounds'][0], sep='; ')"
]
},
{
"cell_type": "code",
"execution_count": 175,
"id": "5d883cf8",
"metadata": {},
"outputs": [],
"source": [
"# alternatively, use the meta2diff2compound to get straigth to compounds\n",
"prompt3 = cp(prompt)\n",
"prompt3.update({'instruction':['compound2diff2compound']})\n",
"config_sample.update({'mode':'meta2diff2compound',\n",
" 'inputs':prompt3})"
]
},
{
"cell_type": "code",
"execution_count": 176,
"id": "c2adb995",
"metadata": {},
"outputs": [],
"source": [
"output = query(config_sample)"
]
},
{
"cell_type": "code",
"execution_count": 178,
"id": "99da6eb8",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'instruction': ['compound2diff2compound'],\n",
" 'tissue': 'lung',\n",
" 'age': 70,\n",
" 'cell': '',\n",
" 'efo': 'EFO_0000768',\n",
" 'datatype': 'expression',\n",
" 'drug': '',\n",
" 'dose': '',\n",
" 'time': '',\n",
" 'case': ['70.0-80.0', '80.0-90.0'],\n",
" 'control': '',\n",
" 'dataset_type': '',\n",
" 'gender': 'm',\n",
" 'species': 'human',\n",
" 'up': [],\n",
" 'down': []}"
]
},
"execution_count": 178,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"prompt3"
]
},
{
"cell_type": "code",
"execution_count": 177,
"id": "ac9c4890",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'output': [None],\n",
" 'mode': 'meta2diff2compound',\n",
" 'message': '62149 is not in list',\n",
" 'input': '[BOS]<compound2diff2compound><tissue>lung </tissue><age_individ>70 </age_individ><cell></cell><efo>EFO_0000768 </efo><datatype>expression </datatype><drug></drug><dose></dose><time></time><case>70.0-80.0 80.0-90.0 </case><control></control><dataset_type></dataset_type><gender>m </gender><species>human </species>'}"
]
},
"execution_count": 177,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"output"
]
},
{
"cell_type": "code",
"execution_count": 167,
"id": "09ec4fe2",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Up-regulated genes:\n",
"MUC5B; AHSP; ALAS2; SLC4A1; CDHR5; NXF2B; CYP4F3; LGALS7B; FBN3; NTS; CYSTM1; ORM2; ASL; CD177; GLRX5; H4C3; NDUFA3; TUBA4B; EPB42; GCHFR; KLF1; CFAP119; TRAPPC2L; DMTN; PDZK1IP1; SEM1; PCYT2; SERF2; CDC20; DAD1; MPC2; EMC3; BOLA1; CMTM5; PGD; EBP; GUK1; NDUFB7; UQCR11; LGALS9C; KEL; HBQ1; TUBB2A; RBX1; TMEM141; F8A1; COX7B; TMEM258; NDUFA7; MYL6; UQCRQ; MRPS24; HPGD; BOLA2B; KRTAP19-4; ATP5MF; RPL29; RPP25L; WDR83OS; FAU; UXT; ZNHIT1; SLC6A8\n",
"\n",
"Down-regulated genes:\n",
"KRT6A; KRT5; KRT15; KRT14; KRT6B; DSG3; CALML3; S100A7; SERPINB5; SPRR2A; SPRR3; LY6D; TMEM45A; KRT16; S100A9; GOLGA8A; SPINK6; CXCL10; CXCL9; CSTA; DSC3; APOL1; CXCL8; PKIA; MYBL1; CYP26B1; POSTN; THBS1; ARL14; UPK1B; CXCL13; CXCL6; C1R; COL14A1; TNFAIP2; TIMP1; VEGFC; C1QB; COL15A1; MGP; BICC1; S100A2; XIST; MARCKS; TLR2; TYMP; RPS4Y1; COL1A1; KLF6; KRT17; FBN1; STK32B; KDM5D; SPP1; APOD; THBS2; EIF1AY; CD163; CCL8; SYNM; CD44; HSPA9; CD14; SOCS3; HSPA6; MCL1; ALOX5AP; PBX3; DDX21; IRF8; HMGA1; MAFB; RGS1; SERPINE1; FKBP5; NOVA1; GFPT2; RRP12; AGTR1; C3AR1; GBP1; CCL18; TLR4; IGSF6; MSMB; SERPINA3; HLA-DQA1; HSPB8; SLC2A1; FOXD1; MS4A14; NAMPT; FYB1; TCAF1; NCF2; SERPINA1; F13A1; GBP3; FHL2; VSIG4; IFI16; MRC1\n",
"\n"
]
}
],
"source": [
"\n",
"print(\"Up-regulated genes:\")\n",
"print(*output['output']['up'][0], sep='; ', end=\"\\n\\n\")\n",
"print(\"Down-regulated genes:\")\n",
"print(*output['output']['down'][0], sep='; ', end=\"\\n\\n\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.5"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|