File size: 16,984 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 | {
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU",
"gpuClass": "standard"
},
"cells": [
{
"cell_type": "markdown",
"metadata": {
"id": "view-in-github",
"colab_type": "text"
},
"source": [
"<a href=\"https://colab.research.google.com/github/sokrypton/ColabDesign/blob/main/rf/examples/diffusion_ori.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"source": [
"#**RFdiffusion**\n",
"RFdiffusion is a method for structure generation, with or without conditional information (a motif, target etc). It can perform a whole range of protein design challenges as we have outlined in the RFdiffusion [manuscript](https://www.biorxiv.org/content/10.1101/2022.12.09.519842v2).\n",
"\n",
"**<font color=\"red\">WARNING</font>** This notebook is in development, we are still working on adding all the options from the manuscript above.\n",
"\n",
"---\n",
"Use `contigs` to define continious chains. Use a `:` to define multiple contigs and a `/` to define mutliple segments within a contig. \n",
"For example:\n",
"\n",
"**unconditional**\n",
"- `contigs='100'` - diffuse **monomer** of length 100\n",
"- `contigs='50:100'` - diffuse **hetero-oligomer** of lengths 50 and 100\n",
"- `contigs='50'` `copies=2` - make two copies of the defined contig(s) and add a symmetry constraint, for **homo-oligomeric** diffusion.\n",
"\n",
"**binder design**\n",
"- `contigs='A:50'` `pdb='4N5T'` - diffuse a **binder** of length 50 to chain A of defined PDB.\n",
"- `contigs='E6-155:70-100'` `pdb='5KQV'` `hotspot='E64,E88,E96'` - diffuse a **binder** of length 70 to 100 (sampled randomly) to chain E and defined hotspot(s).\n",
"\n",
"**motif scaffolding**\n",
" - `contigs='40/A163-181/40'` `pdb='5TPN'`\n",
" - `contigs='A3-30/36/A33-68'` `pdb='6MRR'` - diffuse a loop of length 36 between two segments of defined PDB ranges.\n",
"\n",
"**partial diffusion**\n",
"- `contigs=''` `pdb='6MRR'` - noise all coordinates\n",
"- `contigs='A1-10'` `pdb='6MRR'` - keep first 10 positions fixed, noise the rest\n",
"- `contigs='A'` `pdb='1SSC'` - fix chain A, noise the rest\n",
"\n",
"*hints and tips*\n",
"- `pdb=''` leave blank to get an upload prompt\n",
"- `contigs='50-100'` use dash to specify a range of lengths to sample from\n",
"\n"
],
"metadata": {
"id": "tSgCPxIZ1T_A"
}
},
{
"cell_type": "code",
"source": [
"#@title setup **RFdiffusion** (~2m30S)\n",
"%%time\n",
"import os, time\n",
"if not os.path.isdir(\"params\"):\n",
" os.system(\"apt-get install aria2\")\n",
" os.system(\"mkdir params\")\n",
" # send param download into background\n",
" os.system(\"(\\\n",
" aria2c -q -x 16 http://files.ipd.uw.edu/pub/RFdiffusion/6f5902ac237024bdd0c176cb93063dc4/Base_ckpt.pt; \\\n",
" aria2c -q -x 16 http://files.ipd.uw.edu/pub/RFdiffusion/e29311f6f1bf1af907f9ef9f44b8328b/Complex_base_ckpt.pt; \\\n",
" aria2c -q -x 16 https://storage.googleapis.com/alphafold/alphafold_params_2022-12-06.tar; \\\n",
" tar -xf alphafold_params_2022-12-06.tar -C params; \\\n",
" touch params/done.txt) &\")\n",
"\n",
"if not os.path.isdir(\"RFdiffusion\"):\n",
" print(\"installing RFdiffusion...\")\n",
" os.system(\"git clone https://github.com/sokrypton/RFdiffusion.git\")\n",
" os.system(\"pip -q install jedi omegaconf hydra-core icecream\")\n",
" os.system(\"pip install dgl==1.0.2+cu116 -f https://data.dgl.ai/wheels/cu116/repo.html\")\n",
" os.system(\"cd RFdiffusion/env/SE3Transformer; pip -q install --no-cache-dir -r requirements.txt; pip -q install .\")\n",
"\n",
"if not os.path.isdir(\"colabdesign\"):\n",
" print(\"installing ColabDesign...\")\n",
" os.system(\"pip -q install git+https://github.com/sokrypton/ColabDesign.git\")\n",
" os.system(\"ln -s /usr/local/lib/python3.*/dist-packages/colabdesign colabdesign\")\n",
"\n",
"if not os.path.isdir(\"RFdiffusion/models\"):\n",
" print(\"downloading RFdiffusion params...\")\n",
" os.system(\"mkdir RFdiffusion/models\")\n",
" models = [\"Base_ckpt.pt\",\"Complex_base_ckpt.pt\"]\n",
" for m in models:\n",
" while os.path.isfile(f\"{m}.aria2\"):\n",
" time.sleep(5)\n",
" os.system(f\"mv {' '.join(models)} RFdiffusion/models\")\n",
"\n",
"import sys, random, string, re\n",
"if 'RFdiffusion' not in sys.path:\n",
" os.environ[\"DGLBACKEND\"] = \"pytorch\"\n",
" sys.path.append('RFdiffusion')\n",
"\n",
"from google.colab import files\n",
"from colabdesign.rf.utils import fix_contigs, fix_partial_contigs, fix_pdb\n",
"from inference.utils import parse_pdb\n",
"\n",
"def get_pdb(pdb_code=None):\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\"\n",
"\n",
"def run_diffusion(contigs, path, pdb=None, iterations=50,\n",
" symmetry=\"cyclic\", copies=1, hotspot=None):\n",
" # determine mode\n",
" contigs = contigs.replace(\",\",\" \").replace(\":\",\" \").split()\n",
" is_fixed, is_free = False, False\n",
" for contig in contigs:\n",
" for x in contig.split(\"/\"):\n",
" a = x.split(\"-\")[0]\n",
" if a[0].isalpha():\n",
" is_fixed = True\n",
" if a.isnumeric():\n",
" is_free = True\n",
" if len(contigs) == 0 or not is_free:\n",
" mode = \"partial\"\n",
" elif is_fixed:\n",
" mode = \"fixed\"\n",
" else:\n",
" mode = \"free\"\n",
"\n",
" # fix input contigs\n",
" if mode in [\"partial\",\"fixed\"]:\n",
" pdb_filename = get_pdb(pdb)\n",
" parsed_pdb = parse_pdb(pdb_filename)\n",
" opts = f\" inference.input_pdb={pdb_filename}\"\n",
" if mode in [\"partial\"]:\n",
" partial_T = int(80 * (iterations / 200))\n",
" opts += f\" diffuser.partial_T={partial_T}\"\n",
" contigs = fix_partial_contigs(contigs, parsed_pdb)\n",
" else:\n",
" opts += f\" diffuser.T={iterations}\"\n",
" contigs = fix_contigs(contigs, parsed_pdb)\n",
" else:\n",
" opts = f\" diffuser.T={iterations}\"\n",
" parsed_pdb = None \n",
" contigs = fix_contigs(contigs, parsed_pdb)\n",
"\n",
" if hotspot is not None and hotspot != \"\":\n",
" opts += f\" ppi.hotspot_res=[{hotspot}]\"\n",
"\n",
" # setup symmetry\n",
" if copies > 1:\n",
" sym = {\"cyclic\":\"c\",\"dihedral\":\"d\"}[symmetry] + str(copies)\n",
" sym_opts = f\"--config-name symmetry inference.symmetry={sym} \\\n",
" 'potentials.guiding_potentials=[\\\"type:olig_contacts,weight_intra:1,weight_inter:0.1\\\"]' \\\n",
" potentials.olig_intra_all=True potentials.olig_inter_all=True \\\n",
" potentials.guide_scale=2 potentials.guide_decay=quadratic\"\n",
" opts = f\"{sym_opts} {opts}\"\n",
" if symmetry == \"dihedral\": copies *= 2\n",
" contigs = sum([contigs] * copies,[])\n",
"\n",
" opts = f\"{opts} 'contigmap.contigs=[{' '.join(contigs)}]'\"\n",
"\n",
" print(\"mode:\", mode)\n",
" print(\"output:\", f\"outputs/{path}\")\n",
" print(\"contigs:\", contigs)\n",
"\n",
" cmd = f\"./RFdiffusion/run_inference.py {opts} inference.output_prefix=outputs/{path} inference.num_designs=1\"\n",
" print(cmd)\n",
" !{cmd}\n",
"\n",
" # fix pdbs\n",
" pdbs = [f\"outputs/traj/{path}_0_pX0_traj.pdb\",\n",
" f\"outputs/traj/{path}_0_Xt-1_traj.pdb\",\n",
" f\"outputs/{path}_0.pdb\"]\n",
" for pdb in pdbs:\n",
" with open(pdb,\"r\") as handle: pdb_str = handle.read()\n",
" with open(pdb,\"w\") as handle: handle.write(fix_pdb(pdb_str, contigs))\n",
" return contigs, copies"
],
"metadata": {
"cellView": "form",
"id": "pZQnHLuDCsZm"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#@title run **RFdiffusion** to generate a backbone\n",
"name = \"test\" #@param {type:\"string\"}\n",
"contigs = \"100\" #@param {type:\"string\"}\n",
"pdb = \"\" #@param {type:\"string\"}\n",
"copies = 1 #@param [\"1\", \"2\", \"3\", \"4\", \"5\", \"6\", \"7\", \"8\", \"9\", \"10\", \"11\", \"12\"] {type:\"raw\"}\n",
"#@markdown ---\n",
"#@markdown **advanced** settings\n",
"iterations = 50 #@param [\"50\", \"100\", \"150\", \"200\"] {type:\"raw\"}\n",
"symmetry = \"cyclic\" #@param [\"cyclic\", \"dihedral\"]\n",
"hotspot = \"\" #@param {type:\"string\"}\n",
"\n",
"# determine where to save\n",
"path = name\n",
"while os.path.exists(f\"outputs/{path}_0.pdb\"):\n",
" path = name + \"_\" + ''.join(random.choices(string.ascii_lowercase + string.digits, k=5))\n",
"\n",
"flags = {\"contigs\":contigs,\n",
" \"pdb\":pdb,\n",
" \"copies\":copies,\n",
" \"iterations\":iterations,\n",
" \"symmetry\":symmetry,\n",
" \"hotspot\":hotspot,\n",
" \"path\":path}\n",
"\n",
"for k,v in flags.items():\n",
" if isinstance(v,str):\n",
" flags[k] = v.replace(\"'\",\"\").replace('\"','')\n",
" \n",
"contigs, copies = run_diffusion(**flags)"
],
"metadata": {
"id": "TuRUfQJZ4vkM",
"cellView": "form"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#@title Display 3D structure {run: \"auto\"}\n",
"import py3Dmol\n",
"from colabdesign.shared.plot import pymol_color_list\n",
"\n",
"from string import ascii_uppercase,ascii_lowercase\n",
"alphabet_list = list(ascii_uppercase+ascii_lowercase)\n",
"\n",
"show_mainchains = False \n",
"animate = False #@param {type:\"boolean\"}\n",
"color = \"chain\" #@param [\"rainbow\", \"chain\"]\n",
"hbondCutoff = 4.0\n",
"view = py3Dmol.view(js='https://3dmol.org/build/3Dmol.js')\n",
"\n",
"if animate:\n",
" pdb = f\"/content/outputs/traj/{path}_0_pX0_traj.pdb\"\n",
" pdb_str = open(pdb,'r').read()\n",
" view.addModelsAsFrames(pdb_str,'pdb',{'hbondCutoff':hbondCutoff})\n",
"else:\n",
" pdb = f\"/content/outputs/{path}_0.pdb\"\n",
" pdb_str = open(pdb,'r').read()\n",
" view.addModel(pdb_str,'pdb',{'hbondCutoff':hbondCutoff})\n",
"\n",
"if color == \"rainbow\":\n",
" view.setStyle({'cartoon': {'color':'spectrum'}})\n",
"elif color == \"chain\":\n",
" for n,chain,color in zip(range(len(contigs)),\n",
" alphabet_list,\n",
" pymol_color_list):\n",
" view.setStyle({'chain':chain},{'cartoon': {'color':color}})\n",
"\n",
"view.zoomTo()\n",
"if animate:\n",
" view.animate({'loop': 'backAndForth'})\n",
"view.show()"
],
"metadata": {
"id": "wqEi03_qi_g2",
"cellView": "form"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"%%time\n",
"#@title run **ProteinMPNN** to generate a sequence and **AlphaFold** to validate\n",
"num_seqs = 8 #@param [\"8\", \"16\", \"32\", \"64\"] {type:\"raw\"}\n",
"initial_guess = False #@param {type:\"boolean\"}\n",
"num_recycles = 1 #@param [\"0\", \"1\", \"2\", \"3\", \"6\", \"12\"] {type:\"raw\"}\n",
"use_multimer = False #@param {type:\"boolean\"}\n",
"rm_aa = \"C\" #@param {type:\"string\"}\n",
"#@markdown - for **binder** design, we recommend `initial_guess=True num_recycles=3`\n",
"\n",
"if not os.path.isfile(\"params/done.txt\"):\n",
" print(\"downloading AlphaFold params...\")\n",
" while not os.path.isfile(\"params/done.txt\"):\n",
" time.sleep(5)\n",
"\n",
"contigs_str = \":\".join(contigs)\n",
"opts = [f\"--pdb=outputs/{path}_0.pdb\",\n",
" f\"--loc=outputs/{path}\",\n",
" f\"--contig={contigs_str}\",\n",
" f\"--copies={copies}\",\n",
" f\"--num_seqs={num_seqs}\",\n",
" f\"--num_recycles={num_recycles}\",\n",
" f\"--rm_aa={rm_aa}\"]\n",
"if initial_guess: opts.append(\"--initial_guess\")\n",
"if use_multimer: opts.append(\"--use_multimer\")\n",
"opts = ' '.join(opts)\n",
"!python colabdesign/rf/designability_test.py {opts}"
],
"metadata": {
"id": "rES3p-q6j4tc",
"cellView": "form"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#@title Display best result\n",
"import py3Dmol\n",
"hbondCutoff = 4.0\n",
"view = py3Dmol.view(js='https://3dmol.org/build/3Dmol.js')\n",
"\n",
"pdb_str = open(f\"outputs/{path}_0.pdb\",'r').read()\n",
"view.addModel(pdb_str,'pdb',{'hbondCutoff':hbondCutoff})\n",
"pdb_str = open(f\"outputs/{path}/best.pdb\",'r').read()\n",
"view.addModel(pdb_str,'pdb',{'hbondCutoff':hbondCutoff})\n",
"\n",
"view.setStyle({\"model\":0},{'cartoon':{}}) #: {'colorscheme': {'prop':'b','gradient': 'roygb','min':0,'max':100}}})\n",
"view.setStyle({\"model\":1},{'cartoon':{'colorscheme': {'prop':'b','gradient': 'roygb','min':0,'max':100}}})\n",
"view.zoomTo()\n",
"view.show()"
],
"metadata": {
"cellView": "form",
"id": "DUNKRBNSvk6_"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#@title Package and download results\n",
"#@markdown If you are having issues downloading the result archive, \n",
"#@markdown try disabling your adblocker and run this cell again. \n",
"#@markdown If that fails click on the little folder icon to the \n",
"#@markdown left, navigate to file: `name.result.zip`, \n",
"#@markdown right-click and select \\\"Download\\\" \n",
"#@markdown (see [screenshot](https://pbs.twimg.com/media/E6wRW2lWUAEOuoe?format=jpg&name=small)).\n",
"!zip -r {path}.result.zip outputs/{path}* outputs/traj/{path}*\n",
"files.download(f\"{path}.result.zip\")"
],
"metadata": {
"cellView": "form",
"id": "tVAE0BrnZoRR"
},
"execution_count": null,
"outputs": []
}
]
} |