File size: 13,291 Bytes
d766458 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 | {
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/sokrypton/ColabDesign/blob/v1.1.1/af/design.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "OA2k3sAYuiXe"
},
"source": [
"#AfDesign (v1.1.1)\n",
"Backprop through AlphaFold for protein design.\n",
"\n",
"**WARNING**\n",
"1. This notebook is in active development and was designed for demonstration purposes only.\n",
"2. Using AfDesign as the only \"loss\" function for design might be a bad idea, you may find adversarial sequences (aka. sequences that trick AlphaFold)."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "-AXy0s_4cKaK"
},
"outputs": [],
"source": [
"#@title setup\n",
"%%time\n",
"import os\n",
"if not os.path.isdir(\"params\"):\n",
" # get code\n",
" os.system(\"pip -q install git+https://github.com/sokrypton/ColabDesign.git@v1.1.1\")\n",
" # for debugging\n",
" os.system(\"ln -s /usr/local/lib/python3.*/dist-packages/colabdesign colabdesign\")\n",
" # download params\n",
" os.system(\"mkdir params\")\n",
" os.system(\"apt-get install aria2 -qq\")\n",
" os.system(\"aria2c -q -x 16 https://storage.googleapis.com/alphafold/alphafold_params_2022-12-06.tar\")\n",
" os.system(\"tar -xf alphafold_params_2022-12-06.tar -C params\")\n",
"\n",
"import warnings\n",
"warnings.simplefilter(action='ignore', category=FutureWarning)\n",
"\n",
"import os\n",
"from colabdesign import mk_afdesign_model, clear_mem\n",
"from IPython.display import HTML\n",
"from google.colab import files\n",
"import numpy as np\n",
"\n",
"def get_pdb(pdb_code=\"\"):\n",
" if pdb_code is None or pdb_code == \"\":\n",
" upload_dict = files.upload()\n",
" pdb_string = upload_dict[list(upload_dict.keys())[0]]\n",
" with open(\"tmp.pdb\",\"wb\") as out: out.write(pdb_string)\n",
" return \"tmp.pdb\"\n",
" elif os.path.isfile(pdb_code):\n",
" return pdb_code\n",
" elif len(pdb_code) == 4:\n",
" os.system(f\"wget -qnc https://files.rcsb.org/view/{pdb_code}.pdb\")\n",
" return f\"{pdb_code}.pdb\"\n",
" else:\n",
" os.system(f\"wget -qnc https://alphafold.ebi.ac.uk/files/AF-{pdb_code}-F1-model_v3.pdb\")\n",
" return f\"AF-{pdb_code}-F1-model_v3.pdb\""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "UUfKrOzT0gOS"
},
"source": [
"# fixed backbone design (fixbb)\n",
"For a given protein backbone, generate/design a new sequence that AlphaFold thinks folds into that conformation. "
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "qLd1DsnKzxBJ"
},
"outputs": [],
"source": [
"clear_mem()\n",
"af_model = mk_afdesign_model(protocol=\"fixbb\")\n",
"af_model.prep_inputs(pdb_filename=get_pdb(\"1TEN\"), chain=\"A\")\n",
"\n",
"print(\"length\", af_model._len)\n",
"print(\"weights\", af_model.opt[\"weights\"])"
]
},
{
"cell_type": "code",
"source": [
"af_model.restart()\n",
"af_model.design_3stage()"
],
"metadata": {
"id": "u0AwskJ84NGx"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"af_model.plot_traj() "
],
"metadata": {
"id": "8FB1v7dn1LL6"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "YEApO8YzBoS0"
},
"outputs": [],
"source": [
"af_model.save_pdb(f\"{af_model.protocol}.pdb\")\n",
"af_model.plot_pdb()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "cW1KQiHKJpfp"
},
"outputs": [],
"source": [
"HTML(af_model.animate())"
]
},
{
"cell_type": "code",
"source": [
"af_model.get_seqs()"
],
"metadata": {
"id": "YDrChASGVUUx"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"# hallucination\n",
"For a given length, generate/hallucinate a protein sequence that AlphaFold thinks folds into a well structured protein (high plddt, low pae, many contacts)."
],
"metadata": {
"id": "qLwS2s_xcjRI"
}
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "sZnYfCbfEvol"
},
"outputs": [],
"source": [
"clear_mem()\n",
"af_model = mk_afdesign_model(protocol=\"hallucination\")\n",
"af_model.prep_inputs(length=100)\n",
"\n",
"print(\"length\",af_model._len)\n",
"print(\"weights\",af_model.opt[\"weights\"])"
]
},
{
"cell_type": "code",
"source": [
"# pre-design with gumbel initialization and softmax activation\n",
"af_model.restart(mode=\"gumbel\")\n",
"af_model.design_soft(50)\n",
"\n",
"# three stage design \n",
"af_model.set_seq(af_model.aux[\"seq\"][\"pseudo\"])\n",
"af_model.design_3stage(50,50,10)"
],
"metadata": {
"id": "f76xqCkw0vj9"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "A1GxeLZdTTya"
},
"outputs": [],
"source": [
"af_model.save_pdb(f\"{af_model.protocol}.pdb\")\n",
"af_model.plot_pdb()"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "L2E9Tn2Acchj"
},
"outputs": [],
"source": [
"HTML(af_model.animate())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "YSKWYu0_GlUH"
},
"outputs": [],
"source": [
"af_model.get_seqs()"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "dXfm4B8ISLuL"
},
"source": [
"# binder hallucination\n",
"For a given protein target and protein binder length, generate/hallucinate a protein binder sequence AlphaFold thinks will bind to the target structure.\n",
"To do this, we minimize PAE and maximize number of contacts at the interface and within the binder, and we maximize pLDDT of the binder.\n",
"By default, AlphaFold-ptm with residue index offset hack is used. To enable AlphaFold-multimer set: mk_afdesign_model(use_multimer=True).\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "3XLJPiRKx5Mw"
},
"outputs": [],
"source": [
"clear_mem()\n",
"af_model = mk_afdesign_model(protocol=\"binder\")\n",
"af_model.prep_inputs(pdb_filename=get_pdb(\"4MZK\"), chain=\"A\", binder_len=19)\n",
"\n",
"print(\"target_length\",af_model._target_len)\n",
"print(\"binder_length\",af_model._binder_len)\n",
"print(\"weights\",af_model.opt[\"weights\"])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "u6VxjuinyCZa"
},
"outputs": [],
"source": [
"af_model.restart()\n",
"af_model.design_3stage(100,100,10)"
]
},
{
"cell_type": "code",
"source": [
"af_model.save_pdb(f\"{af_model.protocol}.pdb\")\n",
"af_model.plot_pdb()"
],
"metadata": {
"id": "sTlS7_L8Zfwf"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "9cARoviGyIKb"
},
"outputs": [],
"source": [
"HTML(af_model.animate())"
]
},
{
"cell_type": "code",
"source": [
"af_model.get_seqs()"
],
"metadata": {
"id": "RzE137NDZdZc"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"#**ADVANCED**"
],
"metadata": {
"id": "SK0IJLoen_EC"
}
},
{
"cell_type": "markdown",
"source": [
"## partial hallucination + custom Radius of Gyration (rg) loss\n",
"mix supervised (fixbb) and unsupervised (hallucination) losses to constrain the halluciation process."
],
"metadata": {
"id": "zl6JGTUzXRnk"
}
},
{
"cell_type": "code",
"source": [
"import jax\n",
"import jax.numpy as jnp\n",
"from colabdesign.af.alphafold.common import residue_constants\n",
"\n",
"# first off, let's implement a custom Radius of Gyration loss function\n",
"def rg_loss(inputs, outputs):\n",
" positions = outputs[\"structure_module\"][\"final_atom_positions\"]\n",
" ca = positions[:,residue_constants.atom_order[\"CA\"]]\n",
" center = ca.mean(0)\n",
" rg = jnp.sqrt(jnp.square(ca - center).sum(-1).mean() + 1e-8)\n",
" rg_th = 2.38 * ca.shape[0] ** 0.365\n",
" rg = jax.nn.elu(rg - rg_th)\n",
" return {\"rg\":rg}"
],
"metadata": {
"id": "spec3m8BlGer"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"clear_mem()\n",
"af_model = mk_afdesign_model(protocol=\"partial\",\n",
" loss_callback=rg_loss, # add rg_loss\n",
" use_templates=False) # set True to constrain positions using template input\n",
"\n",
"af_model.opt[\"weights\"][\"rg\"] = 0.1 # optional: specify weight for rg_loss\n",
"\n",
"af_model.prep_inputs(pdb_filename=get_pdb(\"6MRR\"),\n",
" chain=\"A\",\n",
" pos=\"3-30,33-68\", # define positions to contrain\n",
" length=100) # total length if different from input pdb\n",
"\n",
"af_model.rewire(loops=[36]) # set loop length between segments "
],
"metadata": {
"id": "h_BvzwbAKo6V"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# initialize with wildtype seq, fill in the rest with soft_gumbel distribution\n",
"af_model.restart(mode=[\"soft\",\"gumbel\",\"wildtype\"])\n",
"af_model.design_3stage(100, 100, 10)"
],
"metadata": {
"id": "5Unr9u2GYKRD"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"af_model.save_pdb(f\"{af_model.protocol}.pdb\")\n",
"af_model.plot_pdb()"
],
"metadata": {
"id": "BFweaqNWYuF0"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"HTML(af_model.animate())"
],
"metadata": {
"id": "GSu2lB9HYw-t"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"af_model.get_seqs()"
],
"metadata": {
"id": "2EG2t2_KY4Td"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "rTGKbhsI0t8k"
},
"execution_count": null,
"outputs": []
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [
"q4qiU9I0QHSz"
],
"name": "design.ipynb",
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |