File size: 13,389 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 | {
"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/examples/peptide_binder_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 - peptide binder design\n",
"For a given protein target and protein binder length, generate/hallucinate a protein binder sequence AlphaFold thinks will bind to the target structure. To do this, we maximize number of contacts at the interface and maximize pLDDT of the binder.\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",
"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 colabdesign.shared.utils import copy_dict\n",
"from colabdesign.af.alphafold.common import residue_constants\n",
"\n",
"from IPython.display import HTML\n",
"from google.colab import files\n",
"import numpy as np\n",
"\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": "code",
"source": [
"#@title **prep inputs**\n",
"import re\n",
"#@markdown ---\n",
"#@markdown **target info**\n",
"pdb = \"4N5T\" #@param {type:\"string\"}\n",
"#@markdown - enter PDB code or UniProt code (to fetch AlphaFoldDB model) or leave blink to upload your own\n",
"target_chain = \"A\" #@param {type:\"string\"}\n",
"target_hotspot = \"\" #@param {type:\"string\"}\n",
"if target_hotspot == \"\": target_hotspot = None\n",
"#@markdown - restrict loss to predefined positions on target (eg. \"1-10,12,15\")\n",
"target_flexible = False #@param {type:\"boolean\"}\n",
"#@markdown - allow backbone of target structure to be flexible\n",
"\n",
"#@markdown ---\n",
"#@markdown **binder info**\n",
"binder_len = 14 #@param {type:\"integer\"}\n",
"#@markdown - length of binder to hallucination\n",
"binder_seq = \"\" #@param {type:\"string\"}\n",
"binder_seq = re.sub(\"[^A-Z]\", \"\", binder_seq.upper())\n",
"if len(binder_seq) > 0:\n",
" binder_len = len(binder_seq)\n",
"else:\n",
" binder_seq = None\n",
"#@markdown - if defined, will initialize design with this sequence\n",
"\n",
"binder_chain = \"\" #@param {type:\"string\"}\n",
"if binder_chain == \"\": binder_chain = None\n",
"#@markdown - if defined, supervised loss is used (binder_len is ignored)\n",
"\n",
"#@markdown ---\n",
"#@markdown **model config**\n",
"use_multimer = False #@param {type:\"boolean\"}\n",
"#@markdown - use alphafold-multimer for design\n",
"num_recycles = 0 #@param [\"0\", \"1\", \"3\", \"6\"] {type:\"raw\"}\n",
"num_models = \"2\" #@param [\"1\", \"2\", \"3\", \"4\", \"5\", \"all\"]\n",
"num_models = 5 if num_models == \"all\" else int(num_models)\n",
"#@markdown - number of trained models to use during optimization\n",
"\n",
"\n",
"x = {\"pdb_filename\":pdb,\n",
" \"chain\":target_chain,\n",
" \"binder_len\":binder_len,\n",
" \"binder_chain\":binder_chain,\n",
" \"hotspot\":target_hotspot,\n",
" \"use_multimer\":use_multimer,\n",
" \"rm_target_seq\":target_flexible}\n",
" \n",
"x[\"pdb_filename\"] = get_pdb(x[\"pdb_filename\"]) \n",
"\n",
"if \"x_prev\" not in dir() or x != x_prev:\n",
" clear_mem()\n",
" model = mk_afdesign_model(protocol=\"binder\",\n",
" use_multimer=x[\"use_multimer\"],\n",
" num_recycles=num_recycles,\n",
" recycle_mode=\"sample\")\n",
" model.prep_inputs(**x,\n",
" ignore_missing=False)\n",
" x_prev = copy_dict(x)\n",
" print(\"target length:\", model._target_len)\n",
" print(\"binder length:\", model._binder_len)\n",
" binder_len = model._binder_len"
],
"metadata": {
"id": "HSgE99WALOE-",
"cellView": "form"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"#@title **run AfDesign**\n",
"from scipy.special import softmax\n",
"\n",
"optimizer = \"pssm_semigreedy\" #@param [\"pssm_semigreedy\", \"3stage\", \"semigreedy\", \"pssm\", \"logits\", \"soft\", \"hard\"]\n",
"#@markdown - `pssm_semigreedy` - uses the designed PSSM to bias semigreedy opt. (Recommended)\n",
"#@markdown - `3stage` - gradient based optimization (GD) (logits → soft → hard)\n",
"#@markdown - `pssm` - GD optimize (logits → soft) to get a sequence profile (PSSM).\n",
"#@markdown - `semigreedy` - tries X random mutations, accepts those that decrease loss\n",
"#@markdown - `logits` - GD optimize logits inputs (continious)\n",
"#@markdown - `soft` - GD optimize softmax(logits) inputs (probabilities)\n",
"#@markdown - `hard` - GD optimize one_hot(logits) inputs (discrete)\n",
"\n",
"#@markdown WARNING: The output sequence from `pssm`,`logits`,`soft` is not one_hot. To get a valid sequence use the other optimizers, or redesign the output backbone with another protocol like ProteinMPNN.\n",
"\n",
"#@markdown ----\n",
"#@markdown #### advanced GD settings\n",
"GD_method = \"sgd\" #@param [\"adabelief\", \"adafactor\", \"adagrad\", \"adam\", \"adamw\", \"fromage\", \"lamb\", \"lars\", \"noisy_sgd\", \"dpsgd\", \"radam\", \"rmsprop\", \"sgd\", \"sm3\", \"yogi\"]\n",
"learning_rate = 0.1 #@param {type:\"raw\"}\n",
"norm_seq_grad = True #@param {type:\"boolean\"}\n",
"dropout = True #@param {type:\"boolean\"}\n",
"\n",
"model.restart(seq=binder_seq)\n",
"model.set_optimizer(optimizer=GD_method,\n",
" learning_rate=learning_rate,\n",
" norm_seq_grad=norm_seq_grad)\n",
"models = model._model_names[:num_models]\n",
"\n",
"flags = {\"num_recycles\":num_recycles,\n",
" \"models\":models,\n",
" \"dropout\":dropout}\n",
"\n",
"if optimizer == \"3stage\":\n",
" model.design_3stage(120, 60, 10, **flags)\n",
" pssm = softmax(model._tmp[\"seq_logits\"],-1)\n",
"\n",
"if optimizer == \"pssm_semigreedy\":\n",
" model.design_pssm_semigreedy(120, 32, **flags)\n",
" pssm = softmax(model._tmp[\"seq_logits\"],1)\n",
"\n",
"if optimizer == \"semigreedy\":\n",
" model.design_pssm_semigreedy(0, 32, **flags)\n",
" pssm = None\n",
"\n",
"if optimizer == \"pssm\":\n",
" model.design_logits(120, e_soft=1.0, num_models=1, ramp_recycles=True, **flags)\n",
" model.design_soft(32, num_models=1, **flags)\n",
" flags.update({\"dropout\":False,\"save_best\":True})\n",
" model.design_soft(10, num_models=num_models, **flags)\n",
" pssm = softmax(model.aux[\"seq\"][\"logits\"],-1)\n",
"\n",
"O = {\"logits\":model.design_logits,\n",
" \"soft\":model.design_soft,\n",
" \"hard\":model.design_hard}\n",
"\n",
"if optimizer in O:\n",
" O[optimizer](120, num_models=1, ramp_recycles=True, **flags)\n",
" flags.update({\"dropout\":False,\"save_best\":True})\n",
" O[optimizer](10, num_models=num_models, **flags)\n",
" pssm = softmax(model.aux[\"seq\"][\"logits\"],-1)\n",
"\n",
"model.save_pdb(f\"{model.protocol}.pdb\")"
],
"metadata": {
"cellView": "form",
"id": "60qmxpzno0yV"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "A1GxeLZdTTya",
"cellView": "form"
},
"outputs": [],
"source": [
"#@title display hallucinated protein {run: \"auto\"}\n",
"color = \"pLDDT\" #@param [\"chain\", \"pLDDT\", \"rainbow\"]\n",
"show_sidechains = False #@param {type:\"boolean\"}\n",
"show_mainchains = False #@param {type:\"boolean\"}\n",
"color_HP = False #@param {type:\"boolean\"}\n",
"animate = True #@param {type:\"boolean\"}\n",
"model.plot_pdb(show_sidechains=show_sidechains,\n",
" show_mainchains=show_mainchains,\n",
" color=color, color_HP=color_HP, animate=animate)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "L2E9Tn2Acchj"
},
"outputs": [],
"source": [
"HTML(model.animate(dpi=100))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "YSKWYu0_GlUH"
},
"outputs": [],
"source": [
"model.save_pdb(f\"{model.protocol}.pdb\")\n",
"model.get_seqs()"
]
},
{
"cell_type": "code",
"source": [
"#@markdown ### Amino acid probabilties\n",
"import plotly.express as px\n",
"alphabet = \"ACDEFGHIKLMNPQRSTVWY\"\n",
"if \"pssm\" in dir() and pssm is not None:\n",
" fig = px.imshow(pssm.mean(0).T,\n",
" labels=dict(x=\"positions\", y=\"amino acids\", color=\"probability\"),\n",
" y=residue_constants.restypes,\n",
" zmin=0,\n",
" zmax=1,\n",
" template=\"simple_white\",\n",
" )\n",
" fig.update_xaxes(side=\"top\")\n",
" fig.show()"
],
"metadata": {
"cellView": "form",
"id": "3pvptBM55GHU"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# log\n",
"model._tmp[\"best\"][\"aux\"][\"log\"]"
],
"metadata": {
"id": "1SGmdJKLNKvb"
},
"execution_count": null,
"outputs": []
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"collapsed_sections": [],
"provenance": [],
"include_colab_link": true
},
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |