File size: 10,602 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 | {
"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/af_pseudo_diffusion.ipynb\" target=\"_parent\"><img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/></a>"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "VD9K5H2cnFxL"
},
"source": [
"#AF_pseudo_diffusion + proteinMPNN\n",
"Hacking AlphaFold to be a diffusion model (for backbone generation). At each step add logits from proteinMPNN.\n",
"\n",
"\n",
"**WARNING**: This notebook is experimental, designed as a control. Not intended for practical use at this stage.\n",
"\n",
"---\n",
"**NEW**\n",
"For latest version of notebook (reconfigured to work in distogram space) go here:\n",
"[af_pseudo_diffusion_dgram.ipynb](https://colab.research.google.com/github/sokrypton/ColabDesign/blob/v1.1.1/af/examples/af_pseudo_diffusion_dgram.ipynb)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "YCRzPGdTZfEe"
},
"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, re\n",
"from colabdesign import mk_afdesign_model, clear_mem\n",
"from colabdesign.mpnn import mk_mpnn_model\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\"\n",
"\n",
"def sample_gumbel(shape, eps=1e-20): \n",
" \"\"\"Sample from Gumbel(0, 1)\"\"\"\n",
" U = np.random.uniform(size=shape)\n",
" return -np.log(-np.log(U + eps) + eps)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "wxYMB4A9Zmrf",
"cellView": "form"
},
"outputs": [],
"source": [
"#@title initialize the model\n",
"length = 100 #@param {type:\"integer\"}\n",
"#@markdown Provide a starting point (optional)\n",
"starting_seq = \"\" #@param {type:\"string\"}\n",
"starting_seq = re.sub(\"[^A-Z]\", \"\", starting_seq.upper())\n",
"#@markdown - if `starting_seq` provided the `length` option will be overwritten by length of starting sequence.\n",
"use_starting_pdb = False #@param {type:\"boolean\"}\n",
"pdb = \"\" #@param {type:\"string\"}\n",
"#@markdown - specify PDB or Uniprot code or leave pdb blank for upload prompt\n",
"chains = \"A\" #@param {type:\"string\"}\n",
"#@markdown - (example `A` or `A,B` for complexes)\n",
"fix_pos = \"\" #@param {type:\"string\"}\n",
"#@markdown - specify which positions to keep fixed in the sequence (example: `1,2-10`)\n",
"#@markdown - you can also specify chain specific constraints (example: `A1-10,B1-20`)\n",
"#@markdown - you can also specify to fix entire chain(s) (example: `A`)\n",
"\n",
"if len(starting_seq) > 0:\n",
" length = len(starting_seq)\n",
"\n",
"clear_mem()\n",
"if use_starting_pdb:\n",
" af_model = mk_afdesign_model(protocol=\"fixbb\", use_templates=True)\n",
" af_model.prep_inputs(get_pdb(pdb), chains, fix_pos=fix_pos) \n",
"else:\n",
" af_model = mk_afdesign_model(protocol=\"hallucination\", use_templates=True)\n",
" af_model.prep_inputs(length=length)\n",
"mpnn_model = mk_mpnn_model()\n",
"print(\"lengths\",af_model._lengths)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "3Dt8i00UbxtW",
"cellView": "form"
},
"outputs": [],
"source": [
"#@title run protocol\n",
"#@markdown Optimization options\n",
"iterations = 100 #@param [\"50\", \"100\"] {type:\"raw\"}\n",
"use_xyz_noise = True #@param {type:\"boolean\"}\n",
"use_seq_noise = True #@param {type:\"boolean\"}\n",
"use_dropout = True #@param {type:\"boolean\"}\n",
"use_plddt = True #@param {type:\"boolean\"}\n",
"store_denoised = True #@param {type:\"boolean\"}\n",
"#@markdown - this does not change results, but toggle between storing noised vs denoised coordinates for animation.\n",
"\n",
"#@markdown AlphaFold options\n",
"sample_models = False #@param {type:\"boolean\"}\n",
"rm_template_seq = True #@param {type:\"boolean\"}\n",
"\n",
"#@markdown proteinMPNN options (disable to keep sequence the same)\n",
"use_mpnn = True #@param {type:\"boolean\"}\n",
"mpnn_mode = \"conditional\" #@param [\"conditional\", \"unconditional\"]\n",
"\n",
"af_model.restart(mode=\"gumbel\")\n",
"\n",
"if len(starting_seq) > 1:\n",
" af_model.set_seq(seq=starting_seq)\n",
"elif use_starting_pdb:\n",
" af_model.set_seq(mode=\"wildtype\")\n",
"\n",
"af_model._inputs[\"rm_template_seq\"] = rm_template_seq\n",
"L = sum(af_model._lengths)\n",
"\n",
"af_model._inputs[\"bias\"] = np.zeros((L,20))\n",
"\n",
"if not use_starting_pdb:\n",
" af_model._inputs[\"batch\"] = {\"aatype\":np.zeros(L).astype(int),\n",
" \"all_atom_mask\":np.zeros((L,37)),\n",
" \"all_atom_positions\":np.zeros((L,37,3))}\n",
"\n",
"for k in range(iterations):\n",
" # add noise\n",
" if use_seq_noise:\n",
" af_model._inputs[\"bias\"] = 0.1 * sample_gumbel((L,20))\n",
"\n",
" if use_xyz_noise:\n",
" n = np.random.normal(size=(L,37,3)) * (1-k/iterations)\n",
" af_model._inputs[\"batch\"][\"all_atom_positions\"] += n\n",
" if not store_denoised and k > 0:\n",
" af_model._tmp[\"traj\"][\"xyz\"][-1] += n[:,1]\n",
"\n",
" # denoise\n",
" aux = af_model.predict(return_aux=True, verbose=False,\n",
" sample_models=sample_models, dropout=use_dropout)\n",
" plddt = af_model.aux[\"plddt\"]\n",
" # update inputs\n",
" af_model._inputs[\"batch\"][\"aatype\"] = af_model.aux[\"seq\"][\"hard\"].argmax(-1)[0]\n",
" af_model._inputs[\"batch\"][\"all_atom_mask\"][:,:4] = 1\n",
" if use_plddt:\n",
" af_model._inputs[\"batch\"][\"all_atom_mask\"][:,(1,3)] = np.sqrt(plddt)[:,None]\n",
" af_model._inputs[\"batch\"][\"all_atom_positions\"] = af_model.aux[\"atom_positions\"].copy()\n",
"\n",
" # add logits from proteinmpnn at each stage\n",
" if use_mpnn:\n",
" mpnn_model.get_af_inputs(af_model)\n",
" opt = {} if mpnn_mode == \"conditional\" else {\"ar_mask\":np.zeros((L,L))}\n",
" mpnn_out = mpnn_model.score(**opt)\n",
" aux[\"log\"][\"mpnn\"] = mpnn_out[\"score\"]\n",
" mpnn_logits = mpnn_out[\"logits\"][:,:20]\n",
" m = (k/iterations)\n",
" af_model._params[\"seq\"] = (1-m) * af_model._params[\"seq\"] + m * mpnn_logits\n",
"\n",
" # save results\n",
" af_model._save_results(aux)\n",
" af_model._k += 1"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "v3dPQeEQcAcT"
},
"outputs": [],
"source": [
"af_model.plot_pdb()"
]
},
{
"cell_type": "code",
"source": [
"af_model.save_pdb(\"tmp.pdb\")\n",
"af_model.get_seqs()"
],
"metadata": {
"id": "6Ck-ME5_99qE"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "6cJhizcYcUxm"
},
"outputs": [],
"source": [
"HTML(af_model.animate(dpi=100))"
]
},
{
"cell_type": "code",
"source": [],
"metadata": {
"id": "aVS6VC7wKyhD"
},
"execution_count": null,
"outputs": []
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"provenance": [],
"include_colab_link": true
},
"gpuClass": "standard",
"kernelspec": {
"display_name": "Python 3",
"name": "python3"
},
"language_info": {
"name": "python"
}
},
"nbformat": 4,
"nbformat_minor": 0
} |