File size: 61,895 Bytes
de2c4f3 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 | {
"nbformat": 4,
"nbformat_minor": 0,
"metadata": {
"colab": {
"provenance": [],
"gpuType": "T4"
},
"kernelspec": {
"name": "python3",
"display_name": "Python 3"
},
"language_info": {
"name": "python"
},
"accelerator": "GPU"
},
"cells": [
{
"cell_type": "markdown",
"source": [
"# P2PXML - Deep Geometric Framework to Predict Antibody-Antigen Binding Affinity"
],
"metadata": {
"id": "N47Ue-53WqAG"
}
},
{
"cell_type": "markdown",
"source": [
"List of resources:\n",
"\n",
"* Paper: https://www.biorxiv.org/content/10.1101/2024.06.09.598103v1\n",
"* Project Page: https://drug-discovery-entc.github.io/p2pxml/\n",
"* Codes: https://github.com/Drug-Discovery-ENTC/p2pxml/\n",
"* Our dataset: https://zenodo.org/records/11531319\n",
"\n",
"The codes, including this notebook, are released under MIT license (https://github.com/Drug-Discovery-ENTC/p2pxml/blob/main/LICENSE) and the dataset is released under Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License (https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en)."
],
"metadata": {
"id": "35qWIH9dWzu7"
}
},
{
"cell_type": "markdown",
"source": [
"Citation:\n",
"\n",
"```bibtex\n",
"@article{bandara2024deep,\n",
" title={Deep Geometric Framework to Predict Antibody-Antigen Binding Affinity},\n",
" author={Bandara, Nuwan Sriyantha and Premathilaka, Dasun and Chandanayake, Sachini and Hettiarachchi, Sahan and Varenthirarajah, Vithurshan and Munasinghe, Aravinda and Madhawa, Kaushalya and Charles, Subodha},\n",
" journal={bioRxiv},\n",
" pages={2024--06},\n",
" year={2024},\n",
" publisher={Cold Spring Harbor Laboratory}\n",
"}\n",
"```"
],
"metadata": {
"id": "sA_FHFqAY25r"
}
},
{
"cell_type": "markdown",
"source": [
"*Disclaimer: This is a minimal working demonstration and the results may be inaccurate. Even though our models are trained on our curated dataset, which is the largest and most generalized publicly-available dataset for antibody-antigen binding affinity prediction to-date in the literature (to the best of our knowledge), it is still biased towards certain antigen variants such as HIV and SARS-CoV-2 due to their abundance in terms of number of data points in the dataset.*"
],
"metadata": {
"id": "VnvPPD74XZBK"
}
},
{
"cell_type": "markdown",
"source": [
"### Run all the cells"
],
"metadata": {
"id": "3Yam7nw1w2vB"
}
},
{
"cell_type": "code",
"source": [
"# Dependencies are already installed in the evo_bio environment.\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"cellView": "form",
"id": "0LGtmIUycmB_",
"outputId": "2d00a0bd-9a18-4f2f-9b5d-5d4cd2dd481d"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Collecting torchmetrics\n",
" Downloading torchmetrics-1.4.0.post0-py3-none-any.whl (868 kB)\n",
"\u001b[?25l \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/868.8 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K \u001b[91m━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.9/868.8 kB\u001b[0m \u001b[31m2.5 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[91m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[91m╸\u001b[0m\u001b[90m━━━━━━━━━━\u001b[0m \u001b[32m645.1/868.8 kB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m868.8/868.8 kB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: numpy>1.20.0 in /usr/local/lib/python3.10/dist-packages (from torchmetrics) (1.25.2)\n",
"Requirement already satisfied: packaging>17.1 in /usr/local/lib/python3.10/dist-packages (from torchmetrics) (24.1)\n",
"Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from torchmetrics) (2.3.0+cu121)\n",
"Collecting lightning-utilities>=0.8.0 (from torchmetrics)\n",
" Downloading lightning_utilities-0.11.2-py3-none-any.whl (26 kB)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from lightning-utilities>=0.8.0->torchmetrics) (67.7.2)\n",
"Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from lightning-utilities>=0.8.0->torchmetrics) (4.12.2)\n",
"Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->torchmetrics) (3.14.0)\n",
"Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->torchmetrics) (1.12.1)\n",
"Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->torchmetrics) (3.3)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->torchmetrics) (3.1.4)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->torchmetrics) (2023.6.0)\n",
"Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n",
"Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n",
"Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n",
"Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n",
"Collecting nvidia-cublas-cu12==12.1.3.1 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n",
"Collecting nvidia-cufft-cu12==11.0.2.54 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n",
"Collecting nvidia-curand-cu12==10.3.2.106 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n",
"Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n",
"Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n",
"Collecting nvidia-nccl-cu12==2.20.5 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_nccl_cu12-2.20.5-py3-none-manylinux2014_x86_64.whl (176.2 MB)\n",
"Collecting nvidia-nvtx-cu12==12.1.105 (from torch>=1.10.0->torchmetrics)\n",
" Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n",
"Requirement already satisfied: triton==2.3.0 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->torchmetrics) (2.3.0)\n",
"Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch>=1.10.0->torchmetrics)\n",
" Downloading nvidia_nvjitlink_cu12-12.5.40-py3-none-manylinux2014_x86_64.whl (21.3 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.3/21.3 MB\u001b[0m \u001b[31m46.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->torchmetrics) (2.1.5)\n",
"Requirement already satisfied: mpmath<1.4.0,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->torch>=1.10.0->torchmetrics) (1.3.0)\n",
"Installing collected packages: nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, lightning-utilities, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, torchmetrics\n",
"Successfully installed lightning-utilities-0.11.2 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.20.5 nvidia-nvjitlink-cu12-12.5.40 nvidia-nvtx-cu12-12.1.105 torchmetrics-1.4.0.post0\n",
"Collecting torch_geometric\n",
" Downloading torch_geometric-2.5.3-py3-none-any.whl (1.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.1/1.1 MB\u001b[0m \u001b[31m25.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (4.66.4)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (1.25.2)\n",
"Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (1.11.4)\n",
"Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (2023.6.0)\n",
"Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (3.1.4)\n",
"Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (3.9.5)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (2.31.0)\n",
"Requirement already satisfied: pyparsing in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (3.1.2)\n",
"Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (1.2.2)\n",
"Requirement already satisfied: psutil>=5.8.0 in /usr/local/lib/python3.10/dist-packages (from torch_geometric) (5.9.5)\n",
"Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->torch_geometric) (1.3.1)\n",
"Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->torch_geometric) (23.2.0)\n",
"Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->torch_geometric) (1.4.1)\n",
"Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->torch_geometric) (6.0.5)\n",
"Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->torch_geometric) (1.9.4)\n",
"Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->torch_geometric) (4.0.3)\n",
"Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch_geometric) (2.1.5)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->torch_geometric) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->torch_geometric) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->torch_geometric) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->torch_geometric) (2024.6.2)\n",
"Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->torch_geometric) (1.4.2)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn->torch_geometric) (3.5.0)\n",
"Installing collected packages: torch_geometric\n",
"Successfully installed torch_geometric-2.5.3\n",
"Collecting Biopandas\n",
" Downloading biopandas-0.4.1-py2.py3-none-any.whl (878 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m879.0/879.0 kB\u001b[0m \u001b[31m18.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hRequirement already satisfied: numpy>=1.16.2 in /usr/local/lib/python3.10/dist-packages (from Biopandas) (1.25.2)\n",
"Requirement already satisfied: pandas>=0.24.2 in /usr/local/lib/python3.10/dist-packages (from Biopandas) (2.0.3)\n",
"Requirement already satisfied: setuptools in /usr/local/lib/python3.10/dist-packages (from Biopandas) (67.7.2)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->Biopandas) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->Biopandas) (2023.4)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas>=0.24.2->Biopandas) (2024.1)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas>=0.24.2->Biopandas) (1.16.0)\n",
"Installing collected packages: Biopandas\n",
"Successfully installed Biopandas-0.4.1\n",
"Collecting Bio\n",
" Downloading bio-1.7.1-py3-none-any.whl (280 kB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m281.0/281.0 kB\u001b[0m \u001b[31m8.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting biopython>=1.80 (from Bio)\n",
" Downloading biopython-1.83-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (3.1 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.1/3.1 MB\u001b[0m \u001b[31m84.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25hCollecting gprofiler-official (from Bio)\n",
" Downloading gprofiler_official-1.0.0-py3-none-any.whl (9.3 kB)\n",
"Collecting mygene (from Bio)\n",
" Downloading mygene-3.2.2-py2.py3-none-any.whl (5.4 kB)\n",
"Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from Bio) (2.0.3)\n",
"Requirement already satisfied: pooch in /usr/local/lib/python3.10/dist-packages (from Bio) (1.8.2)\n",
"Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from Bio) (2.31.0)\n",
"Requirement already satisfied: tqdm in /usr/local/lib/python3.10/dist-packages (from Bio) (4.66.4)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from biopython>=1.80->Bio) (1.25.2)\n",
"Collecting biothings-client>=0.2.6 (from mygene->Bio)\n",
" Downloading biothings_client-0.3.1-py2.py3-none-any.whl (29 kB)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->Bio) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->Bio) (2023.4)\n",
"Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->Bio) (2024.1)\n",
"Requirement already satisfied: platformdirs>=2.5.0 in /usr/local/lib/python3.10/dist-packages (from pooch->Bio) (4.2.2)\n",
"Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from pooch->Bio) (24.1)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->Bio) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->Bio) (3.7)\n",
"Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->Bio) (2.0.7)\n",
"Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->Bio) (2024.6.2)\n",
"Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->Bio) (1.16.0)\n",
"Installing collected packages: biopython, gprofiler-official, biothings-client, mygene, Bio\n",
"Successfully installed Bio-1.7.1 biopython-1.83 biothings-client-0.3.1 gprofiler-official-1.0.0 mygene-3.2.2\n",
"Collecting periodictable\n",
" Downloading periodictable-1.7.0.tar.gz (1.0 MB)\n",
"\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.0/1.0 MB\u001b[0m \u001b[31m21.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
"\u001b[?25h Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
"Requirement already satisfied: pyparsing in /usr/local/lib/python3.10/dist-packages (from periodictable) (3.1.2)\n",
"Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (from periodictable) (1.25.2)\n",
"Building wheels for collected packages: periodictable\n",
" Building wheel for periodictable (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
" Created wheel for periodictable: filename=periodictable-1.7.0-py3-none-any.whl size=752513 sha256=1eb56758363adbb2061156246a94af1e3606f299807b00cce152f7027d875432\n",
" Stored in directory: /root/.cache/pip/wheels/7e/19/a2/fef5d0ca2b1ad2b199e863a6e796ad9d5efc86563d80c91a0c\n",
"Successfully built periodictable\n",
"Installing collected packages: periodictable\n",
"Successfully installed periodictable-1.7.0\n"
]
}
]
},
{
"cell_type": "code",
"source": [
"# @title\n",
"import pandas as pd\n",
"import numpy as np\n",
"from tqdm import tqdm\n",
"import math\n",
"\n",
"import torch\n",
"import torch.nn as nn\n",
"from torch.optim import AdamW\n",
"from torch import Tensor\n",
"import torch.nn.functional as F\n",
"from torch.nn import Parameter\n",
"from torch.nn import Sequential, Linear, ReLU, MultiheadAttention, Dropout, LayerNorm, AvgPool1d\n",
"from torchmetrics.functional import mean_absolute_error\n",
"import torch.optim as optim\n",
"from torch.utils.data import Dataset, DataLoader\n",
"from torch.optim.lr_scheduler import LambdaLR\n",
"from tqdm import tqdm\n",
"\n",
"from torch.nn.init import zeros_,xavier_normal_\n",
"\n",
"import os\n",
"\n",
"import networkx as nx\n",
"import torch_geometric.data as Data\n",
"from torch_geometric.loader import DataLoader\n",
"from torch_geometric.nn import GCNConv, global_mean_pool, GATConv\n",
"from torch_geometric.transforms import NormalizeScale\n",
"from torch_geometric.data import Batch\n",
"from torchmetrics.functional import mean_absolute_error\n",
"from torch.utils.data import random_split\n",
"\n",
"import matplotlib.pyplot as plt\n",
"\n",
"from biopandas.pdb import PandasPdb\n",
"import periodictable\n",
"from Bio import SeqIO\n",
"from Bio.PDB import PDBParser\n",
"from Bio.SeqUtils import seq1\n",
"\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"import warnings\n",
"warnings.filterwarnings(\"ignore\")\n",
"\n",
"import logging, sys"
],
"metadata": {
"cellView": "form",
"id": "z72fVm0ybIX5"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "markdown",
"source": [
"**Note**\n",
"\n",
"Here, input the **.pdb** files for both antibody and antigen. *Note that the current maximum FASTA sequence lengths for antibody and antigen are 669 and 3102 respectively.*\n",
"\n",
"Example PDB files for an antibody-antigen pair can be found at https://github.com/Drug-Discovery-ENTC/p2pxml/tree/main/data"
],
"metadata": {
"id": "Yyu_GMViwOen"
}
},
{
"cell_type": "code",
"source": [
"import os\n",
"import shutil\n",
"import pandas as pd\n",
"\n",
"ROOT = os.environ[\"P2PXML_ROOT\"]\n",
"SMOKE_DIR = os.path.join(ROOT, \"scripts\", \"smoke\")\n",
"\n",
"os.makedirs(os.path.join(SMOKE_DIR, \"antibodies\"), exist_ok=True)\n",
"os.makedirs(os.path.join(SMOKE_DIR, \"antigens\"), exist_ok=True)\n",
"os.makedirs(os.path.join(SMOKE_DIR, \"graph_data\"), exist_ok=True)\n",
"\n",
"antibody_name = \"10-1074\"\n",
"antigen_name = \"0013095_2_11\"\n",
"\n",
"shutil.copy2(\n",
" os.path.join(ROOT, \"conf\", \"data\", antibody_name + \".pdb\"),\n",
" os.path.join(SMOKE_DIR, \"antibodies\", antibody_name + \".pdb\"),\n",
")\n",
"shutil.copy2(\n",
" os.path.join(ROOT, \"conf\", \"data\", antigen_name + \".pdb\"),\n",
" os.path.join(SMOKE_DIR, \"antigens\", antigen_name + \".pdb\"),\n",
")\n",
"\n",
"test_df = pd.DataFrame({\n",
" \"Ab\": [antibody_name],\n",
" \"Ag\": [antigen_name],\n",
" \"log(IC50)\": [0.0],\n",
"})\n",
"\n",
"print(test_df)"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/",
"height": 184
},
"cellView": "form",
"id": "vJY-76IGngwE",
"outputId": "6da824c5-99a0-462c-cc6f-0f54752321c8"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Please upload the antibody .pdb file.\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"\n",
" <input type=\"file\" id=\"files-726cd675-eace-48d3-a066-db99c7b38db1\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-726cd675-eace-48d3-a066-db99c7b38db1\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script>// Copyright 2017 Google LLC\n",
"//\n",
"// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"// you may not use this file except in compliance with the License.\n",
"// You may obtain a copy of the License at\n",
"//\n",
"// http://www.apache.org/licenses/LICENSE-2.0\n",
"//\n",
"// Unless required by applicable law or agreed to in writing, software\n",
"// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"// See the License for the specific language governing permissions and\n",
"// limitations under the License.\n",
"\n",
"/**\n",
" * @fileoverview Helpers for google.colab Python module.\n",
" */\n",
"(function(scope) {\n",
"function span(text, styleAttributes = {}) {\n",
" const element = document.createElement('span');\n",
" element.textContent = text;\n",
" for (const key of Object.keys(styleAttributes)) {\n",
" element.style[key] = styleAttributes[key];\n",
" }\n",
" return element;\n",
"}\n",
"\n",
"// Max number of bytes which will be uploaded at a time.\n",
"const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
"\n",
"function _uploadFiles(inputId, outputId) {\n",
" const steps = uploadFilesStep(inputId, outputId);\n",
" const outputElement = document.getElementById(outputId);\n",
" // Cache steps on the outputElement to make it available for the next call\n",
" // to uploadFilesContinue from Python.\n",
" outputElement.steps = steps;\n",
"\n",
" return _uploadFilesContinue(outputId);\n",
"}\n",
"\n",
"// This is roughly an async generator (not supported in the browser yet),\n",
"// where there are multiple asynchronous steps and the Python side is going\n",
"// to poll for completion of each step.\n",
"// This uses a Promise to block the python side on completion of each step,\n",
"// then passes the result of the previous step as the input to the next step.\n",
"function _uploadFilesContinue(outputId) {\n",
" const outputElement = document.getElementById(outputId);\n",
" const steps = outputElement.steps;\n",
"\n",
" const next = steps.next(outputElement.lastPromiseValue);\n",
" return Promise.resolve(next.value.promise).then((value) => {\n",
" // Cache the last promise value to make it available to the next\n",
" // step of the generator.\n",
" outputElement.lastPromiseValue = value;\n",
" return next.value.response;\n",
" });\n",
"}\n",
"\n",
"/**\n",
" * Generator function which is called between each async step of the upload\n",
" * process.\n",
" * @param {string} inputId Element ID of the input file picker element.\n",
" * @param {string} outputId Element ID of the output display.\n",
" * @return {!Iterable<!Object>} Iterable of next steps.\n",
" */\n",
"function* uploadFilesStep(inputId, outputId) {\n",
" const inputElement = document.getElementById(inputId);\n",
" inputElement.disabled = false;\n",
"\n",
" const outputElement = document.getElementById(outputId);\n",
" outputElement.innerHTML = '';\n",
"\n",
" const pickedPromise = new Promise((resolve) => {\n",
" inputElement.addEventListener('change', (e) => {\n",
" resolve(e.target.files);\n",
" });\n",
" });\n",
"\n",
" const cancel = document.createElement('button');\n",
" inputElement.parentElement.appendChild(cancel);\n",
" cancel.textContent = 'Cancel upload';\n",
" const cancelPromise = new Promise((resolve) => {\n",
" cancel.onclick = () => {\n",
" resolve(null);\n",
" };\n",
" });\n",
"\n",
" // Wait for the user to pick the files.\n",
" const files = yield {\n",
" promise: Promise.race([pickedPromise, cancelPromise]),\n",
" response: {\n",
" action: 'starting',\n",
" }\n",
" };\n",
"\n",
" cancel.remove();\n",
"\n",
" // Disable the input element since further picks are not allowed.\n",
" inputElement.disabled = true;\n",
"\n",
" if (!files) {\n",
" return {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
" }\n",
"\n",
" for (const file of files) {\n",
" const li = document.createElement('li');\n",
" li.append(span(file.name, {fontWeight: 'bold'}));\n",
" li.append(span(\n",
" `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
" `last modified: ${\n",
" file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
" 'n/a'} - `));\n",
" const percent = span('0% done');\n",
" li.appendChild(percent);\n",
"\n",
" outputElement.appendChild(li);\n",
"\n",
" const fileDataPromise = new Promise((resolve) => {\n",
" const reader = new FileReader();\n",
" reader.onload = (e) => {\n",
" resolve(e.target.result);\n",
" };\n",
" reader.readAsArrayBuffer(file);\n",
" });\n",
" // Wait for the data to be ready.\n",
" let fileData = yield {\n",
" promise: fileDataPromise,\n",
" response: {\n",
" action: 'continue',\n",
" }\n",
" };\n",
"\n",
" // Use a chunked sending to avoid message size limits. See b/62115660.\n",
" let position = 0;\n",
" do {\n",
" const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
" const chunk = new Uint8Array(fileData, position, length);\n",
" position += length;\n",
"\n",
" const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
" yield {\n",
" response: {\n",
" action: 'append',\n",
" file: file.name,\n",
" data: base64,\n",
" },\n",
" };\n",
"\n",
" let percentDone = fileData.byteLength === 0 ?\n",
" 100 :\n",
" Math.round((position / fileData.byteLength) * 100);\n",
" percent.textContent = `${percentDone}% done`;\n",
"\n",
" } while (position < fileData.byteLength);\n",
" }\n",
"\n",
" // All done.\n",
" yield {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
"}\n",
"\n",
"scope.google = scope.google || {};\n",
"scope.google.colab = scope.google.colab || {};\n",
"scope.google.colab._files = {\n",
" _uploadFiles,\n",
" _uploadFilesContinue,\n",
"};\n",
"})(self);\n",
"</script> "
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Saving 0.5γ.pdb to 0.5γ.pdb\n",
" \n",
"Please upload the antigen .pdb file.\n"
]
},
{
"output_type": "display_data",
"data": {
"text/plain": [
"<IPython.core.display.HTML object>"
],
"text/html": [
"\n",
" <input type=\"file\" id=\"files-dbe4ccc2-7c30-42c9-9d5c-74425ea6f0f7\" name=\"files[]\" multiple disabled\n",
" style=\"border:none\" />\n",
" <output id=\"result-dbe4ccc2-7c30-42c9-9d5c-74425ea6f0f7\">\n",
" Upload widget is only available when the cell has been executed in the\n",
" current browser session. Please rerun this cell to enable.\n",
" </output>\n",
" <script>// Copyright 2017 Google LLC\n",
"//\n",
"// Licensed under the Apache License, Version 2.0 (the \"License\");\n",
"// you may not use this file except in compliance with the License.\n",
"// You may obtain a copy of the License at\n",
"//\n",
"// http://www.apache.org/licenses/LICENSE-2.0\n",
"//\n",
"// Unless required by applicable law or agreed to in writing, software\n",
"// distributed under the License is distributed on an \"AS IS\" BASIS,\n",
"// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\n",
"// See the License for the specific language governing permissions and\n",
"// limitations under the License.\n",
"\n",
"/**\n",
" * @fileoverview Helpers for google.colab Python module.\n",
" */\n",
"(function(scope) {\n",
"function span(text, styleAttributes = {}) {\n",
" const element = document.createElement('span');\n",
" element.textContent = text;\n",
" for (const key of Object.keys(styleAttributes)) {\n",
" element.style[key] = styleAttributes[key];\n",
" }\n",
" return element;\n",
"}\n",
"\n",
"// Max number of bytes which will be uploaded at a time.\n",
"const MAX_PAYLOAD_SIZE = 100 * 1024;\n",
"\n",
"function _uploadFiles(inputId, outputId) {\n",
" const steps = uploadFilesStep(inputId, outputId);\n",
" const outputElement = document.getElementById(outputId);\n",
" // Cache steps on the outputElement to make it available for the next call\n",
" // to uploadFilesContinue from Python.\n",
" outputElement.steps = steps;\n",
"\n",
" return _uploadFilesContinue(outputId);\n",
"}\n",
"\n",
"// This is roughly an async generator (not supported in the browser yet),\n",
"// where there are multiple asynchronous steps and the Python side is going\n",
"// to poll for completion of each step.\n",
"// This uses a Promise to block the python side on completion of each step,\n",
"// then passes the result of the previous step as the input to the next step.\n",
"function _uploadFilesContinue(outputId) {\n",
" const outputElement = document.getElementById(outputId);\n",
" const steps = outputElement.steps;\n",
"\n",
" const next = steps.next(outputElement.lastPromiseValue);\n",
" return Promise.resolve(next.value.promise).then((value) => {\n",
" // Cache the last promise value to make it available to the next\n",
" // step of the generator.\n",
" outputElement.lastPromiseValue = value;\n",
" return next.value.response;\n",
" });\n",
"}\n",
"\n",
"/**\n",
" * Generator function which is called between each async step of the upload\n",
" * process.\n",
" * @param {string} inputId Element ID of the input file picker element.\n",
" * @param {string} outputId Element ID of the output display.\n",
" * @return {!Iterable<!Object>} Iterable of next steps.\n",
" */\n",
"function* uploadFilesStep(inputId, outputId) {\n",
" const inputElement = document.getElementById(inputId);\n",
" inputElement.disabled = false;\n",
"\n",
" const outputElement = document.getElementById(outputId);\n",
" outputElement.innerHTML = '';\n",
"\n",
" const pickedPromise = new Promise((resolve) => {\n",
" inputElement.addEventListener('change', (e) => {\n",
" resolve(e.target.files);\n",
" });\n",
" });\n",
"\n",
" const cancel = document.createElement('button');\n",
" inputElement.parentElement.appendChild(cancel);\n",
" cancel.textContent = 'Cancel upload';\n",
" const cancelPromise = new Promise((resolve) => {\n",
" cancel.onclick = () => {\n",
" resolve(null);\n",
" };\n",
" });\n",
"\n",
" // Wait for the user to pick the files.\n",
" const files = yield {\n",
" promise: Promise.race([pickedPromise, cancelPromise]),\n",
" response: {\n",
" action: 'starting',\n",
" }\n",
" };\n",
"\n",
" cancel.remove();\n",
"\n",
" // Disable the input element since further picks are not allowed.\n",
" inputElement.disabled = true;\n",
"\n",
" if (!files) {\n",
" return {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
" }\n",
"\n",
" for (const file of files) {\n",
" const li = document.createElement('li');\n",
" li.append(span(file.name, {fontWeight: 'bold'}));\n",
" li.append(span(\n",
" `(${file.type || 'n/a'}) - ${file.size} bytes, ` +\n",
" `last modified: ${\n",
" file.lastModifiedDate ? file.lastModifiedDate.toLocaleDateString() :\n",
" 'n/a'} - `));\n",
" const percent = span('0% done');\n",
" li.appendChild(percent);\n",
"\n",
" outputElement.appendChild(li);\n",
"\n",
" const fileDataPromise = new Promise((resolve) => {\n",
" const reader = new FileReader();\n",
" reader.onload = (e) => {\n",
" resolve(e.target.result);\n",
" };\n",
" reader.readAsArrayBuffer(file);\n",
" });\n",
" // Wait for the data to be ready.\n",
" let fileData = yield {\n",
" promise: fileDataPromise,\n",
" response: {\n",
" action: 'continue',\n",
" }\n",
" };\n",
"\n",
" // Use a chunked sending to avoid message size limits. See b/62115660.\n",
" let position = 0;\n",
" do {\n",
" const length = Math.min(fileData.byteLength - position, MAX_PAYLOAD_SIZE);\n",
" const chunk = new Uint8Array(fileData, position, length);\n",
" position += length;\n",
"\n",
" const base64 = btoa(String.fromCharCode.apply(null, chunk));\n",
" yield {\n",
" response: {\n",
" action: 'append',\n",
" file: file.name,\n",
" data: base64,\n",
" },\n",
" };\n",
"\n",
" let percentDone = fileData.byteLength === 0 ?\n",
" 100 :\n",
" Math.round((position / fileData.byteLength) * 100);\n",
" percent.textContent = `${percentDone}% done`;\n",
"\n",
" } while (position < fileData.byteLength);\n",
" }\n",
"\n",
" // All done.\n",
" yield {\n",
" response: {\n",
" action: 'complete',\n",
" }\n",
" };\n",
"}\n",
"\n",
"scope.google = scope.google || {};\n",
"scope.google.colab = scope.google.colab || {};\n",
"scope.google.colab._files = {\n",
" _uploadFiles,\n",
" _uploadFilesContinue,\n",
"};\n",
"})(self);\n",
"</script> "
]
},
"metadata": {}
},
{
"output_type": "stream",
"name": "stdout",
"text": [
"Saving AC10_29.pdb to AC10_29.pdb\n"
]
}
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"cellView": "form",
"id": "kigJrq_0XkxU"
},
"outputs": [],
"source": [
"# @title\n",
"max_antibody_sequence_length = 669\n",
"max_antigen_sequence_length = 3102\n",
"\n",
"class ProteinDataset(Dataset):\n",
" def __init__(self, df, max_antibody_sequence_length, max_antigen_sequence_length, save_dir=os.path.join(SMOKE_DIR, 'graph_data')):\n",
" self.sequences = df['Ab'].values\n",
" self.viruses = df['Ag'].values\n",
" self.labels = df['log(IC50)'].values\n",
" self.max_antibody_sequence_length = max_antibody_sequence_length\n",
" self.max_antigen_sequence_length = max_antigen_sequence_length\n",
" self.save_dir = save_dir\n",
" os.makedirs(save_dir, exist_ok=True)\n",
"\n",
" def __len__(self):\n",
" return len(self.sequences)\n",
"\n",
" def __getitem__(self, idx):\n",
" sequence = self.sequences[idx]\n",
" virus = self.viruses[idx]\n",
" label = self.labels[idx]\n",
" label = torch.tensor(label, dtype=torch.float64)\n",
"\n",
" antibody = self.load_or_generate_graph(sequence, self.max_antibody_sequence_length, 'antibodies')\n",
" antigen = self.load_or_generate_graph(virus, self.max_antigen_sequence_length, 'antigens')\n",
"\n",
" if antibody is not None and antigen is not None:\n",
" return antibody, antigen, label\n",
" else:\n",
" return self.__getitem__((idx + 1) % len(self)) # Ensure idx is within bounds\n",
"\n",
" def load_or_generate_graph(self, pdb_file, max_sequence_length, graph_type):\n",
" graph_path = os.path.join(self.save_dir, f'{graph_type}_{pdb_file}.pt')\n",
"\n",
" if os.path.exists(graph_path):\n",
" return torch.load(graph_path)\n",
"\n",
" if graph_type == 'antigens':\n",
" graph_constructed = self.pdb_to_graph_virus(pdb_file, max_sequence_length)\n",
" else:\n",
" graph_constructed = self.pdb_to_graph_antibody(pdb_file, max_sequence_length)\n",
"\n",
" if graph_constructed is not None:\n",
" torch.save(graph_constructed, graph_path)\n",
" return graph_constructed\n",
"\n",
" def pdb_to_graph_virus(self, pdb_file, max_antigen_sequence_length):\n",
" return self.pdb_to_graph(pdb_file, max_antigen_sequence_length, 'antigens')\n",
"\n",
" def pdb_to_graph_antibody(self, pdb_file, max_antibody_sequence_length):\n",
" return self.pdb_to_graph(pdb_file, max_antibody_sequence_length, 'antibodies')\n",
"\n",
" def pdb_to_graph(self, pdb_file, max_sequence_length, graph_type):\n",
" seq_length = max_sequence_length\n",
" amino_acids = list(\"ACDEFGHIKLMNPQRSTVWY\")\n",
" aa_to_index = {aa: i for i, aa in enumerate(amino_acids)}\n",
" pdbparser = PDBParser()\n",
"\n",
" try:\n",
" structure = pdbparser.get_structure(pdb_file, os.path.join(SMOKE_DIR, graph_type, pdb_file + '.pdb'))\n",
" chains = {chain.id: seq1(''.join(residue.resname for residue in chain)) for chain in structure.get_chains()}\n",
" full_sequence = ''\n",
" for value in chains.values():\n",
" full_sequence += value\n",
" full_sequence = full_sequence.replace(\"X\", \"\")\n",
"\n",
" if len(full_sequence) > seq_length:\n",
" print(f\"Exceeds max length {graph_type}\")\n",
" return None\n",
"\n",
" indices = [aa_to_index[aa] for aa in full_sequence]\n",
" encoded = F.one_hot(torch.tensor(indices), num_classes=len(amino_acids)).float()\n",
" padded_encoded = F.pad(encoded.flatten(), (0, max(seq_length * len(amino_acids) - encoded.flatten().shape[0], 0)))\n",
"\n",
" ppdb = PandasPdb()\n",
" ppdb.read_pdb(os.path.join(SMOKE_DIR, graph_type, pdb_file + '.pdb'))\n",
" coords = ppdb.df['ATOM'][['x_coord', 'y_coord', 'z_coord']].values\n",
" atomic_nums = ppdb.df['ATOM']['element_symbol'].apply(lambda symbol: periodictable.elements.symbol(symbol).number).values\n",
"\n",
" graph = nx.Graph()\n",
" num_atoms = len(coords)\n",
" for i in range(num_atoms):\n",
" graph.add_node(i, x=coords[i][0], y=coords[i][1], z=coords[i][2], atomic_number=atomic_nums[i])\n",
" for i in range(num_atoms):\n",
" for j in range(i + 1, num_atoms):\n",
" dist = ((coords[i] - coords[j]) ** 2).sum() ** 0.5\n",
" if dist < 5:\n",
" bond_strength = 1 / dist\n",
" graph.add_edge(i, j, distance=dist, bond_strength=bond_strength)\n",
"\n",
" edge_attrs = {}\n",
"\n",
" for u, v, data in graph.edges(data=True):\n",
" edge_attrs[(u, v)] = [data['distance'], data['bond_strength']]\n",
" edge_attrs[(v, u)] = [data['distance'], data['bond_strength']]\n",
"\n",
" data = Data.Data(\n",
" x=torch.tensor(list(nx.get_node_attributes(graph, 'x').values())).to(torch.float64),\n",
" y_coord=torch.tensor(list(nx.get_node_attributes(graph, 'y').values())).to(torch.float64),\n",
" z_coord=torch.tensor(list(nx.get_node_attributes(graph, 'z').values())).to(torch.float64),\n",
" pos=torch.tensor(coords).to(torch.float64),\n",
" edge_index=torch.tensor(list(graph.edges)).to(torch.float64).t().contiguous(),\n",
" edge_attr=torch.tensor([edge_attrs[e] for e in graph.edges()]).to(torch.float64),\n",
" z=torch.tensor(list(nx.get_node_attributes(graph, 'atomic_number').values())).to(torch.float64),\n",
" seq=padded_encoded.to(torch.float64),\n",
" y = torch.tensor([0.0]).to(torch.float64)\n",
" )\n",
" return data\n",
"\n",
" except Exception as e:\n",
" print(e)\n",
" return None\n",
"\n",
"test_ds = ProteinDataset(test_df, max_antibody_sequence_length, max_antigen_sequence_length)\n",
"test_loader = DataLoader(test_ds, batch_size=1, shuffle=False)"
]
},
{
"cell_type": "code",
"source": [
"# @title\n",
"class SelfAttention(nn.Module):\n",
" def __init__(self, embed_dim, num_heads=16):\n",
" super(SelfAttention, self).__init__()\n",
" self.embed_dim = embed_dim\n",
" self.num_heads = num_heads\n",
" if embed_dim % num_heads != 0:\n",
" raise ValueError(f\"embedding dimension = {embed_dim} should be divisible by number of heads = {num_heads}\")\n",
" self.head_dim = embed_dim // num_heads\n",
" self.query_dense = nn.Linear(embed_dim, embed_dim)\n",
" self.key_dense = nn.Linear(embed_dim, embed_dim)\n",
" self.value_dense = nn.Linear(embed_dim, embed_dim)\n",
" self.combine_heads = nn.Linear(embed_dim, embed_dim)\n",
"\n",
" def forward(self, inputs):\n",
" query = self.query_dense(inputs)\n",
" key = self.key_dense(inputs)\n",
" value = self.value_dense(inputs)\n",
" query = query.view(-1, self.num_heads, self.head_dim)\n",
" key = key.view(-1, self.num_heads, self.head_dim)\n",
" value = value.view(-1, self.num_heads, self.head_dim)\n",
" query = query.permute(1, 0, 2)\n",
" key = key.permute(1, 0, 2)\n",
" value = value.permute(1, 0, 2)\n",
" dot_product = torch.matmul(query, key.permute(0, 2, 1))\n",
" scaled_dot_product = dot_product / torch.sqrt(torch.tensor(self.head_dim, dtype=torch.float32))\n",
" attention_weights = torch.softmax(scaled_dot_product, dim=-1)\n",
" output = torch.matmul(attention_weights, value)\n",
" output = output.permute(1, 0, 2)\n",
" output = output.view(-1, self.embed_dim)\n",
" output = self.combine_heads(output)\n",
" return output\n",
"\n",
"class TransformerBlock(nn.Module):\n",
" def __init__(self, embed_dim, num_heads, dense_dim=1024, dropout_rate=0.1):\n",
" super(TransformerBlock, self).__init__()\n",
" self.attention = SelfAttention(embed_dim, num_heads)\n",
" self.dropout1 = nn.Dropout(dropout_rate)\n",
" self.norm1 = nn.LayerNorm(embed_dim, eps=1e-6)\n",
" self.dense1 = nn.Linear(embed_dim, dense_dim)\n",
" self.dropout2 = nn.Dropout(dropout_rate)\n",
" self.norm2 = nn.LayerNorm(embed_dim, eps=1e-6)\n",
" self.dense2 = nn.Linear(dense_dim, embed_dim)\n",
"\n",
" def forward(self, inputs):\n",
" attention_output = self.attention(inputs)\n",
" attention_output = self.dropout1(attention_output)\n",
" output1 = self.norm1(inputs + attention_output)\n",
" dense_output = self.dense1(output1)\n",
" dense_output = self.dropout2(dense_output)\n",
" output2 = self.norm2(output1 + dense_output)\n",
" output = self.dense2(output2)\n",
" return output\n",
"\n",
"class CrossAttention(nn.Module):\n",
" def __init__(self, dim, input_shape):\n",
" super(CrossAttention, self).__init__()\n",
" self.dim = dim\n",
" self.input_shape = input_shape\n",
"\n",
" self.Wq = nn.Parameter(torch.Tensor(input_shape[0][-1], self.dim))\n",
" self.Wk = nn.Parameter(torch.Tensor(input_shape[1][-1], self.dim))\n",
" self.Wv = nn.Parameter(torch.Tensor(input_shape[1][-1], self.dim))\n",
"\n",
" nn.init.xavier_uniform_(self.Wq)\n",
" nn.init.xavier_uniform_(self.Wk)\n",
" nn.init.xavier_uniform_(self.Wv)\n",
"\n",
" def forward(self, inputs):\n",
" x, y = inputs\n",
"\n",
" Q = torch.matmul(x, self.Wq)\n",
" K = torch.matmul(y, self.Wk)\n",
" V = torch.matmul(y, self.Wv)\n",
"\n",
" attn_weights = torch.matmul(Q, K.t()) / torch.sqrt(torch.tensor(self.dim, dtype=torch.float64))\n",
" attn_weights = F.softmax(attn_weights, dim=-1)\n",
" attn_output = attn_weights * V\n",
" output = torch.cat([x, attn_output], dim=-1)\n",
"\n",
" return output\n",
"\n",
"class CombinedModel(nn.Module):\n",
" def __init__(self, hidden_channels=128, num_layers=16):\n",
" super(CombinedModel, self).__init__()\n",
"\n",
" self.cross_attn_1 = CrossAttention(128, [(1024,),(1024,)])\n",
" self.cross_attn_2 = CrossAttention(128,[(1024,),(1024,)])\n",
" self.cross_attn = CrossAttention(128,[(1152,),(1152,)])\n",
" self.self_atten_1 = nn.AdaptiveAvgPool1d(1)\n",
" self.self_atten_2 = nn.AdaptiveAvgPool1d(1)\n",
" self.cross_pooling = nn.AdaptiveAvgPool1d(1)\n",
" self.dense = nn.Linear(1280, 256)\n",
" self.output_layer1 = nn.Linear(2816, 128)\n",
" self.output_layer = nn.Linear(128, 1)\n",
"\n",
" self.input_1 = nn.Linear(input_shape_1[0], 1024)\n",
" self.self_attn_1 = SelfAttention(1024)\n",
" self.transformer_1 = TransformerBlock(1024, 4)\n",
" self.pooling_1 = nn.AdaptiveAvgPool1d(1)\n",
" self.dense_1 = nn.Linear(1024, 1024)\n",
" self.dropout_1 = nn.Dropout(p=0.05)\n",
"\n",
" self.input_2 = nn.Linear(input_shape_2[0], 1024)\n",
" self.self_attn_2 = SelfAttention(1024)\n",
" self.transformer_2 = TransformerBlock(1024, 4)\n",
" self.pooling_2 = nn.AdaptiveAvgPool1d(1)\n",
" self.dense_2 = nn.Linear(1024, 1024)\n",
" self.dropout_2 = nn.Dropout(p=0.05)\n",
"\n",
" self.num_layers = num_layers\n",
"\n",
" self.convs1 = nn.ModuleList()\n",
" self.convs1.append(GCNConv(4, hidden_channels))\n",
" for _ in range(num_layers - 1):\n",
" self.convs1.append(GCNConv(hidden_channels, hidden_channels))\n",
"\n",
" self.convs2 = nn.ModuleList()\n",
" self.convs2.append(GCNConv(4, hidden_channels))\n",
" for _ in range(num_layers - 1):\n",
" self.convs2.append(GCNConv(hidden_channels, hidden_channels))\n",
"\n",
" self.cross_att = GATConv(hidden_channels, hidden_channels, heads=2)\n",
"\n",
" self.lin1 = nn.Linear(2816, hidden_channels)\n",
" self.lin2 = nn.Linear(hidden_channels, 1)\n",
"\n",
" self.transform = NormalizeScale()\n",
"\n",
" def forward(self, data_batch_1, data_batch_2):\n",
" x1 = data_batch_1.x.double()\n",
" edge_index_1 = data_batch_1.edge_index\n",
" z1 = data_batch_1.z\n",
" y1_coord = data_batch_1.y_coord\n",
" z1_coord = data_batch_1.z_coord\n",
"\n",
" concatenated_x1 = torch.stack([x1, z1, y1_coord, z1_coord], dim=1)\n",
"\n",
" # Apply graph normalization\n",
" data_batch_1 = self.transform(data_batch_1)\n",
" x1 = data_batch_1.x\n",
"\n",
" for i in range(self.num_layers):\n",
" concatenated_x1 = self.convs1[i](concatenated_x1, edge_index_1.to(torch.int64))\n",
" concatenated_x1 = F.relu(concatenated_x1.double())\n",
"\n",
" # Process second graph\n",
" x2 = data_batch_2.x\n",
" edge_index_2 = data_batch_2.edge_index\n",
" z2 = data_batch_2.z\n",
" y2_coord = data_batch_2.y_coord\n",
" z2_coord = data_batch_2.z_coord\n",
"\n",
" concatenated_x2 = torch.stack([x2, z2, y2_coord, z2_coord], dim=1)\n",
"\n",
" # Apply graph normalization\n",
" data_batch_2 = self.transform(data_batch_2)\n",
" x2 = data_batch_2.x\n",
"\n",
" for i in range(self.num_layers):\n",
" concatenated_x2 = self.convs2[i](concatenated_x2, edge_index_2.to(torch.int64))\n",
" concatenated_x2 = F.relu(concatenated_x2)\n",
"\n",
" # Cross-attention block\n",
" x1 = self.cross_att(concatenated_x1, edge_index_1.to(torch.int64))\n",
" x2 = self.cross_att(concatenated_x2, edge_index_2.to(torch.int64))\n",
"\n",
" # Concatenate all tensors along the last dimension\n",
" x = torch.cat([\n",
" global_mean_pool(x1, data_batch_1.batch),\n",
" global_mean_pool(x2, data_batch_2.batch)], dim=1)\n",
"\n",
" input_11 = self.input_1(data_batch_1.seq)\n",
" self_attn_1 = self.self_attn_1(input_11)\n",
" transformer_1 = self.transformer_1(self_attn_1)\n",
" pooling_1 = self.pooling_1(transformer_1.transpose(0, 1)).squeeze(dim=1)\n",
" dense_1 = self.dense_1(pooling_1)\n",
" dropout_1 = self.dropout_1(dense_1)\n",
"\n",
" input_22 = self.input_2(data_batch_2.seq)\n",
" self_attn_2 = self.self_attn_2(input_22)\n",
" transformer_2 = self.transformer_2(self_attn_2)\n",
" pooling_2 = self.pooling_2(transformer_2.transpose(0, 1)).squeeze(dim=1)\n",
" dense_2 = self.dense_2(pooling_2)\n",
" dropout_2 = self.dropout_2(dense_2)\n",
"\n",
" input_shape = [(dropout_1.shape[-1],), (dropout_2.shape[-1],)]\n",
" cross_attn_1 = self.cross_attn_1([dropout_1, dropout_2])\n",
" cross_attn_2 = self.cross_attn_2([self.self_attn_1(input_11), self.self_attn_2(input_22)])\n",
" cross_pooling = self.cross_pooling(cross_attn_2.transpose(0, 1)).squeeze(dim=1)\n",
" cross_attn = self.cross_attn([cross_attn_1, cross_pooling])\n",
" cross_atten = F.tanh(self.dense(cross_attn))\n",
"\n",
" self_atten_1 = self.self_atten_1(self_attn_1.transpose(0, 1)).squeeze(dim=1)\n",
" self_atten_2 = self.self_atten_2(self_attn_2.transpose(0, 1)).squeeze(dim=1)\n",
" attention_scores = torch.cat([self_atten_1, self_atten_2, cross_atten], dim=-1)\n",
"\n",
" x_2 = torch.cat([self.pooling_2(x.transpose(0, 1)).squeeze(dim=1), attention_scores], dim = -1)\n",
"\n",
" attention_scores = torch.cat([attention_scores, self.pooling_2(x.transpose(0, 1)).squeeze(dim=1)], dim = -1)\n",
"\n",
" output_layer1 = F.tanh(self.output_layer1(attention_scores)) #transformer\n",
" output_layer = self.output_layer(output_layer1)\n",
"\n",
" x = F.relu(self.lin1(x_2))\n",
" x = self.lin2(x)\n",
"\n",
" return x, output_layer"
],
"metadata": {
"cellView": "form",
"id": "apGATVycfjcM"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Use the local weight/model_weights.pth file.\n"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"cellView": "form",
"id": "wWCGMOsynHU8",
"outputId": "dc83398f-ea31-4e0e-93ce-c0460ebd7fe5"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"--2024-06-20 14:59:31-- https://uniofmora-my.sharepoint.com/:u:/g/personal/180066f_uom_lk/EY2Q0k-ghI1Hs6iZfCUwF6gBJZacOak9XEwzmPd6SK9uAQ?e=yHk23u&download=1\n",
"Resolving uniofmora-my.sharepoint.com (uniofmora-my.sharepoint.com)... 13.107.136.10, 13.107.138.10, 2620:1ec:8f8::10, ...\n",
"Connecting to uniofmora-my.sharepoint.com (uniofmora-my.sharepoint.com)|13.107.136.10|:443... connected.\n",
"HTTP request sent, awaiting response... 302 Found\n",
"Location: /personal/180066f_uom_lk/Documents/FYP/model_weights/28_best_model.pth?ga=1 [following]\n",
"--2024-06-20 14:59:31-- https://uniofmora-my.sharepoint.com/personal/180066f_uom_lk/Documents/FYP/model_weights/28_best_model.pth?ga=1\n",
"Reusing existing connection to uniofmora-my.sharepoint.com:443.\n",
"HTTP request sent, awaiting response... 200 OK\n",
"Length: 2475531770 (2.3G) [application/octet-stream]\n",
"Saving to: ‘EY2Q0k-ghI1Hs6iZfCUwF6gBJZacOak9XEwzmPd6SK9uAQ?e=yHk23u&download=1’\n",
"\n",
"EY2Q0k-ghI1Hs6iZfCU 100%[===================>] 2.30G 142MB/s in 24s \n",
"\n",
"2024-06-20 14:59:55 (98.5 MB/s) - ‘EY2Q0k-ghI1Hs6iZfCUwF6gBJZacOak9XEwzmPd6SK9uAQ?e=yHk23u&download=1’ saved [2475531770/2475531770]\n",
"\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"Running on GPU (\"cuda\") device is advised"
],
"metadata": {
"id": "FtQaxzI349rF"
}
},
{
"cell_type": "code",
"source": [
"# @title\n",
"input_shape_1 = (int(max_antibody_sequence_length*20),)\n",
"input_shape_2 = (int(max_antigen_sequence_length*20),)\n",
"\n",
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
"print(\"Inference device:\", device)\n",
"com_model = CombinedModel().to(device)\n",
"com_model = com_model.to(torch.float64)\n",
"\n",
"alpha = 0.45\n",
"beta = 0.55\n",
"gamma = 0.05\n",
"\n",
"com_model_cp = torch.load(os.path.join(ROOT, 'weight', 'model_weights.pth'), map_location=device, weights_only=False)\n",
"com_model_epoch = com_model_cp['epoch']\n",
"com_model.load_state_dict(com_model_cp['model_state_dict'])\n",
"\n",
"# Evaluate the model\n",
"com_model.eval()\n",
"test_loss = 0.0\n",
"test_mae = 0.0\n",
"total_samples = 0\n",
"\n",
"with torch.no_grad():\n",
" for input in test_loader:\n",
" input_1 = input[0].to(device)\n",
" input_2 = input[1].to(device)\n",
" target = input[2].to(device)\n",
" batch_size = input_1.size(0)\n",
"\n",
" if input_1.pos is not None:\n",
" input_1 = NormalizeScale()(input_1)\n",
" else:\n",
" print(\"Data does not have position information, skipping normalization.\")\n",
"\n",
" if input_2.pos is not None:\n",
" input_2 = NormalizeScale()(input_2)\n",
" else:\n",
" print(\"Data does not have position information, skipping normalization.\")\n",
"\n",
" output_gnn, output_tranf = com_model(input_1, input_2)\n",
" print(f\"Predicted binding affinity for the uploaded antibody-antigen pair (in IC50): {10**(alpha*output_gnn.item()+beta*output_tranf.item()+gamma*np.abs(output_gnn.item() - output_tranf.item()))}\") #"
],
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"cellView": "form",
"id": "Sdn3Mq5PbxRb",
"outputId": "66b69bc7-fe5b-424c-ebae-4995c9cf2011"
},
"execution_count": null,
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"Predicted binding affinity for the uploaded antibody-antigen pair (in IC50): 22.93421825850764\n"
]
}
]
},
{
"cell_type": "markdown",
"source": [
"**Notes:**\n",
"\n",
"- Check that the runtime type is set to GPU at \"Runtime\" -> \"Change runtime type\".\n",
"- Try to restart the session \"Runtime\" -> \"Restart session and run all\".\n",
"- Check your input PDB files.\n",
"- Our current model only supports proteins with amino-acid sequence lengths upto 669 (for antibodies) and 3102 (for antigens).\n",
"- If you encounter any bugs, please report the issue to https://github.com/Drug-Discovery-ENTC/p2pxml/issues or email the corresponding author (Nuwan) at pmnsribandara@gmail.com"
],
"metadata": {
"id": "SUyJQvdLMI3j"
}
}
]
}
|