1 2<!doctype html> 3<html lang="en" class="no-js"> 4 <head> 5 6 <meta charset="utf-8"> 7 <meta name="viewport" content="width=device-width,initial-scale=1"> 8 9 10 11 <link rel="canonical" href="https://chasemc.github.io/nodes_and_relationships/about_the_database/"> 12 13 14 <link rel="prev" href="../../nextflow/docker_images/"> 15 16 17 <link rel="next" href="../schema/"> 18 19 20 <link rel="icon" href="../../media/single.png"> 21 <meta name="generator" content="mkdocs-1.6.1, mkdocs-material-9.5.44"> 22 23 24 25 <title>Identifiers - SocialGene</title> 26 27 28 29 <link rel="stylesheet" href="../../assets/stylesheets/main.0253249f.min.css"> 30 31 32 33 34 35 36 37 38 39 40 41 42 <link rel="preconnect" href="https://fonts.gstatic.com" crossorigin> 43 <link rel="stylesheet" href="https://fonts.googleapis.com/css?family=Roboto:300,300i,400,400i,700,700i%7CRoboto+Mono:400,400i,700,700i&display=fallback"> 44 <style>:root{--md-text-font:"Roboto";--md-code-font:"Roboto Mono"}</style> 45 46 47 48 <link rel="stylesheet" href="../../assets/_mkdocstrings.css"> 49 50 <link rel="stylesheet" href="../../stylesheets/extra.css"> 51 52
52<script>__md_scope=new URL("../..",location),__md_hash=e=>[...e].reduce(((e,_)=>(e<<5)-e+_.charCodeAt(0)),0),__md_get=(e,_=localStorage,t=__md_scope)=>JSON.parse(_.getItem(t.pathname+"."+e)),__md_set=(e,_,t=localStorage,a=__md_scope)=>{try{t.setItem(a.pathname+"."+e,JSON.stringify(_))}catch(e){}}</script>
52 53 54 55 56 57 58 59 60
61<script id="__analytics">function __md_analytics(){function e(){dataLayer.push(arguments)}window.dataLayer=window.dataLayer||[],e("js",new Date),e("config","G-YSRY3GE6B5"),document.addEventListener("DOMContentLoaded",(function(){document.forms.search&&document.forms.search.query.addEventListener("blur",(function(){this.value&&e("event","search",{search_term:this.value})}));document$.subscribe((function(){var t=document.forms.feedback;if(void 0!==t)for(var a of t.querySelectorAll("[type=submit]"))a.addEventListener("click",(function(a){a.preventDefault();var n=document.location.pathname,d=this.getAttribute("data-md-value");e("event","feedback",{page:n,data:d}),t.firstElementChild.disabled=!0;var r=t.querySelector(".md-feedback__note [data-md-value='"+d+"']");r&&(r.hidden=!1)})),t.hidden=!1})),location$.subscribe((function(t){e("config","G-YSRY3GE6B5",{page_path:t.pathname})}))}));var t=document.createElement("script");t.async=!0,t.src="https://www.googletagmanager.com/gtag/js?id=G-YSRY3GE6B5",document.getElementById("__analytics").insertAdjacentElement("afterEnd",t)}</script>
61 62 63
63<script>"undefined"!=typeof __md_analytics&&__md_analytics()</script>
63 64 65 66 67 68 69 </head> 70 71 72 <body dir="ltr"> 73 74 75 <input class="md-toggle" data-md-toggle="drawer" type="checkbox" id="__drawer" autocomplete="off"> 76 <input class="md-toggle" data-md-toggle="search" type="checkbox" id="__search" autocomplete="off"> 77 <label class="md-overlay" for="__drawer"></label> 78 <div data-md-component="skip"> 79 80 81 <a href="#uids" class="md-skip"> 82 Skip to content 83 </a> 84 85 </div> 86 <div data-md-component="announce"> 87 88 </div> 89 90 91 92 93 94 95<header class="md-header md-header--shadow" data-md-component="header"> 96 <nav class="md-header__inner md-grid" aria-label="Header"> 97 <a href="../.." title="SocialGene" class="md-header__button md-logo" aria-label="SocialGene" data-md-component="logo"> 98 99 100 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg> 101 102 </a> 103 <label class="md-header__button md-icon" for="__drawer"> 104 105 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M3 6h18v2H3zm0 5h18v2H3zm0 5h18v2H3z"/></svg> 106 </label> 107 <div class="md-header__title" data-md-component="header-title"> 108 <div class="md-header__ellipsis"> 109 <div class="md-header__topic"> 110 <span class="md-ellipsis"> 111 SocialGene 112 </span> 113 </div> 114 <div class="md-header__topic" data-md-component="header-topic"> 115 <span class="md-ellipsis"> 116 117 Identifiers 118 119 </span> 120 </div> 121 </div> 122 </div> 123 124 125
125<script>var palette=__md_get("__palette");if(palette&&palette.color){if("(prefers-color-scheme)"===palette.color.media){var media=matchMedia("(prefers-color-scheme: light)"),input=document.querySelector(media.matches?"[data-md-color-media='(prefers-color-scheme: light)']":"[data-md-color-media='(prefers-color-scheme: dark)']");palette.color.media=input.getAttribute("data-md-color-media"),palette.color.scheme=input.getAttribute("data-md-color-scheme"),palette.color.primary=input.getAttribute("data-md-color-primary"),palette.color.accent=input.getAttribute("data-md-color-accent")}for(var[key,value]of Object.entries(palette.color))document.body.setAttribute("data-md-color-"+key,value)}</script>
125 126 127 128 129 <label class="md-header__button md-icon" for="__search"> 130 131 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg> 132 </label> 133 <div class="md-search" data-md-component="search" role="dialog"> 134 <label class="md-search__overlay" for="__search"></label> 135 <div class="md-search__inner" role="search"> 136 <form class="md-search__form" name="search"> 137 <input type="text" class="md-search__input" name="query" aria-label="Search" placeholder="Search" autocapitalize="off" autocorrect="off" autocomplete="off" spellcheck="false" data-md-component="search-query" required> 138 <label class="md-search__icon md-icon" for="__search"> 139 140 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M9.5 3A6.5 6.5 0 0 1 16 9.5c0 1.61-.59 3.09-1.56 4.23l.27.27h.79l5 5-1.5 1.5-5-5v-.79l-.27-.27A6.52 6.52 0 0 1 9.5 16 6.5 6.5 0 0 1 3 9.5 6.5 6.5 0 0 1 9.5 3m0 2C7 5 5 7 5 9.5S7 14 9.5 14 14 12 14 9.5 12 5 9.5 5"/></svg> 141 142 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 11v2H8l5.5 5.5-1.42 1.42L4.16 12l7.92-7.92L13.5 5.5 8 11z"/></svg> 143 </label> 144 <nav class="md-search__options" aria-label="Search"> 145 146 <button type="reset" class="md-search__icon md-icon" title="Clear" aria-label="Clear" tabindex="-1"> 147 148 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M19 6.41 17.59 5 12 10.59 6.41 5 5 6.41 10.59 12 5 17.59 6.41 19 12 13.41 17.59 19 19 17.59 13.41 12z"/></svg> 149 </button> 150 </nav> 151 152 </form> 153 <div class="md-search__output"> 154 <div class="md-search__scrollwrap" tabindex="0" data-md-scrollfix> 155 <div class="md-search-result" data-md-component="search-result"> 156 <div class="md-search-result__meta"> 157 Initializing search 158 </div> 159 <ol class="md-search-result__list" role="presentation"></ol> 160 </div> 161 </div> 162 </div> 163 </div> 164</div> 165 166 167 <div class="md-header__source"> 168 <a href="https://github.com/socialgene/socialgene.github.io" title="Go to repository" class="md-source" data-md-component="source"> 169 <div class="md-source__icon md-icon"> 170 171 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg> 172 </div> 173 <div class="md-source__repository"> 174 GitHub 175 </div> 176</a> 177 </div> 178 179 </nav> 180 181</header> 182 183 <div class="md-container" data-md-component="container"> 184 185 186 187 188 189 190 <main class="md-main" data-md-component="main"> 191 <div class="md-main__inner md-grid"> 192 193 194 195 <div class="md-sidebar md-sidebar--primary" data-md-component="sidebar" data-md-type="navigation" > 196 <div class="md-sidebar__scrollwrap"> 197 <div class="md-sidebar__inner"> 198 199 200 201 202<nav class="md-nav md-nav--primary" aria-label="Navigation" data-md-level="0"> 203 <label class="md-nav__title" for="__drawer"> 204 <a href="../.." title="SocialGene" class="md-nav__button md-logo" aria-label="SocialGene" data-md-component="logo"> 205 206 207 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
207<path d="M12 8a3 3 0 0 0 3-3 3 3 0 0 0-3-3 3 3 0 0 0-3 3 3 3 0 0 0 3 3m0 3.54C9.64 9.35 6.5 8 3 8v11c3.5 0 6.64 1.35 9 3.54 2.36-2.19 5.5-3.54 9-3.54V8c-3.5 0-6.64 1.35-9 3.54"/></svg> 208 209 </a> 210 SocialGene 211 </label> 212 213 <div class="md-nav__source"> 214 <a href="https://github.com/socialgene/socialgene.github.io" title="Go to repository" class="md-source" data-md-component="source"> 215 <div class="md-source__icon md-icon"> 216 217 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 448 512"><!--! Font Awesome Free 6.6.0 by @fontawesome - https://fontawesome.com License - https://fontawesome.com/license/free (Icons: CC BY 4.0, Fonts: SIL OFL 1.1, Code: MIT License) Copyright 2024 Fonticons, Inc.--><path d="M439.55 236.05 244 40.45a28.87 28.87 0 0 0-40.81 0l-40.66 40.63 51.52 51.52c27.06-9.14 52.68 16.77 43.39 43.68l49.66 49.66c34.23-11.8 61.18 31 35.47 56.69-26.49 26.49-70.21-2.87-56-37.34L240.22 199v121.85c25.3 12.54 22.26 41.85 9.08 55a34.34 34.34 0 0 1-48.55 0c-17.57-17.6-11.07-46.91 11.25-56v-123c-20.8-8.51-24.6-30.74-18.64-45L142.57 101 8.45 235.14a28.86 28.86 0 0 0 0 40.81l195.61 195.6a28.86 28.86 0 0 0 40.8 0l194.69-194.69a28.86 28.86 0 0 0 0-40.81"/></svg> 218 </div> 219 <div class="md-source__repository"> 220 GitHub 221 </div> 222</a> 223 </div> 224 225 <ul class="md-nav__list" data-md-scrollfix> 226 227 228 229 230 231 232 233 <li class="md-nav__item"> 234 <a href="../.." class="md-nav__link"> 235 236 237 <span class="md-ellipsis"> 238 Overview 239 </span> 240 241 242 </a> 243 </li> 244 245 246 247 248 249 250 251 252 253 <li class="md-nav__item"> 254 <a href="../../system_requirements/" class="md-nav__link"> 255 256 257 <span class="md-ellipsis"> 258 System Requirements 259 </span> 260 261 262 </a> 263 </li> 264 265 266 267 268 269 270 271 272 273 <li class="md-nav__item"> 274 <a href="../../ultraquickstart/ultraquickstart/" class="md-nav__link"> 275 276 277 <span class="md-ellipsis"> 278 Ultra-Quickstart! 279 </span> 280 281 282 </a> 283 </li> 284 285 286 287 288 289 290 291 292 293 294 295 296 297 <li class="md-nav__item md-nav__item--nested"> 298 299 300 301 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4" > 302 303 304 <label class="md-nav__link" for="__nav_4" id="__nav_4_label" tabindex="0"> 305 306 307 <span class="md-ellipsis"> 308 Building a Database (Nextflow) 309 </span> 310 311 312 <span class="md-nav__icon md-icon"></span> 313 </label> 314 315 <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_4_label" aria-expanded="false"> 316 <label class="md-nav__title" for="__nav_4"> 317 <span class="md-nav__icon md-icon"></span> 318 Building a Database (Nextflow) 319 </label> 320 <ul class="md-nav__list" data-md-scrollfix> 321 322 323 324 325 326 327 328 <li class="md-nav__item"> 329 <a href="../../nextflow/installation/" class="md-nav__link"> 330 331 332 <span class="md-ellipsis"> 333 Installation 334 </span> 335 336 337 </a> 338 </li> 339 340 341 342 343 344 345 346 347 348 349 <li class="md-nav__item"> 350 <a href="../../nextflow/inputs/" class="md-nav__link"> 351 352 353 <span class="md-ellipsis"> 354 Inputs 355 </span> 356 357 358 </a> 359 </li> 360 361 362 363 364 365 366 367 368 369 370 <li class="md-nav__item"> 371 <a href="../../nextflow/parameters/" class="md-nav__link"> 372 373 374 <span class="md-ellipsis"> 375 Parameters 376 </span> 377 378 379 </a> 380 </li> 381 382 383 384 385 386 387 388 389 390 391 <li class="md-nav__item"> 392 <a href="../../nextflow/outputs/" class="md-nav__link"> 393 394 395 <span class="md-ellipsis"> 396 Outputs 397 </span> 398 399 400 </a> 401 </li> 402 403 404 405 406 407 408 409 410 411 412 <li class="md-nav__item"> 413 <a href="../../nextflow/running_the_pipeline/" class="md-nav__link"> 414 415 416 <span class="md-ellipsis"> 417 Running the Workflow 418 </span> 419 420 421 </a> 422 </li> 423 424 425 426 427 428 429 430 431 432 433 <li class="md-nav__item"> 434 <a href="../../nextflow/examples/" class="md-nav__link"> 435 436 437 <span class="md-ellipsis"> 438 Examples 439 </span> 440 441 442 </a> 443 </li> 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 <li class="md-nav__item md-nav__item--nested"> 459 460 461 462 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_4_7" > 463 464 465 <label class="md-nav__link" for="__nav_4_7" id="__nav_4_7_label" tabindex="0"> 466 467 468 <span class="md-ellipsis"> 469 Advanced 470 </span> 471 472
473 <span class="md-nav__icon md-icon"></span> 474 </label> 475 476 <nav class="md-nav" data-md-level="2" aria-labelledby="__nav_4_7_label" aria-expanded="false"> 477 <label class="md-nav__title" for="__nav_4_7"> 478 <span class="md-nav__icon md-icon"></span> 479 Advanced 480 </label> 481 <ul class="md-nav__list" data-md-scrollfix> 482 483 484 485 486 487 488 489 <li class="md-nav__item"> 490 <a href="../../nextflow/docker_images/" class="md-nav__link"> 491 492 493 <span class="md-ellipsis"> 494 Docker Images 495 </span> 496 497 498 </a> 499 </li> 500 501 502 503 504 </ul> 505 </nav> 506 507 </li> 508 509 510 511 512 </ul> 513 </nav> 514 515 </li> 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 <li class="md-nav__item md-nav__item--active md-nav__item--nested"> 532 533 534 535 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_5" checked> 536 537 538 <label class="md-nav__link" for="__nav_5" id="__nav_5_label" tabindex="0"> 539 540 541 <span class="md-ellipsis"> 542 Nodes and Relationships 543 </span> 544 545 546 <span class="md-nav__icon md-icon"></span> 547 </label> 548 549 <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_5_label" aria-expanded="true"> 550 <label class="md-nav__title" for="__nav_5"> 551 <span class="md-nav__icon md-icon"></span> 552 Nodes and Relationships 553 </label> 554 <ul class="md-nav__list" data-md-scrollfix> 555 556 557 558 559 560 561 562 563 564 <li class="md-nav__item md-nav__item--active"> 565 566 <input class="md-nav__toggle md-toggle" type="checkbox" id="__toc"> 567 568 569 570 <label class="md-nav__link md-nav__link--active" for="__toc"> 571 572 573 <span class="md-ellipsis"> 574 Identifiers 575 </span> 576 577 578 <span class="md-nav__icon md-icon"></span> 579 </label> 580 581 <a href="./" class="md-nav__link md-nav__link--active"> 582 583 584 <span class="md-ellipsis"> 585 Identifiers 586 </span> 587 588 589 </a> 590 591 592 593<nav class="md-nav md-nav--secondary" aria-label="Table of contents"> 594 595 596 597 598 <label class="md-nav__title" for="__toc"> 599 <span class="md-nav__icon md-icon"></span> 600 Table of contents 601 </label> 602 <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix> 603 604 <li class="md-nav__item"> 605 <a href="#uids" class="md-nav__link"> 606 <span class="md-ellipsis"> 607 UIDs 608 </span> 609 </a> 610 611</li> 612 613 <li class="md-nav__item"> 614 <a href="#proteins" class="md-nav__link"> 615 <span class="md-ellipsis"> 616 Proteins 617 </span> 618 </a> 619 620</li> 621 622 <li class="md-nav__item"> 623 <a href="#assemblies" class="md-nav__link"> 624 <span class="md-ellipsis"> 625 Assemblies 626 </span> 627 </a> 628 629</li> 630 631 <li class="md-nav__item"> 632 <a href="#nucleotides" class="md-nav__link"> 633 <span class="md-ellipsis"> 634 Nucleotides 635 </span> 636 </a> 637 638</li> 639 640 </ul> 641 642</nav> 643 644 </li> 645 646 647 648 649 650 651 652 653 654 655 <li class="md-nav__item"> 656 <a href="../schema/" class="md-nav__link"> 657 658 659 <span class="md-ellipsis"> 660 Schema 661 </span> 662 663 664 </a> 665 </li> 666 667 668 669 670 </ul> 671 </nav> 672 673 </li> 674 675 676 677 678 679 680 681 682 683 684 685 686 687 <li class="md-nav__item md-nav__item--nested"> 688 689 690 691 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_6" > 692 693 694 <label class="md-nav__link" for="__nav_6" id="__nav_6_label" tabindex="0"> 695 696 697 <span class="md-ellipsis"> 698 Interacting with a Database (Neo4j) 699 </span> 700 701 702 <span class="md-nav__icon md-icon"></span> 703 </label> 704 705 <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_6_label" aria-expanded="false"> 706 <label class="md-nav__title" for="__nav_6">
707 <span class="md-nav__icon md-icon"></span> 708 Interacting with a Database (Neo4j) 709 </label> 710 <ul class="md-nav__list" data-md-scrollfix> 711 712 713 714 715 716 717 718 <li class="md-nav__item"> 719 <a href="../../neo4j/database_launch/" class="md-nav__link"> 720 721 722 <span class="md-ellipsis"> 723 Database Launch 724 </span> 725 726 727 </a> 728 </li> 729 730 731 732 733 734 735 736 737 738 739 <li class="md-nav__item"> 740 <a href="../../neo4j/database_backups/" class="md-nav__link"> 741 742 743 <span class="md-ellipsis"> 744 Database Backups 745 </span> 746 747 748 </a> 749 </li> 750 751 752 753 754 755 756 757 758 759 760 <li class="md-nav__item"> 761 <a href="../../neo4j/interacting/" class="md-nav__link"> 762 763 764 <span class="md-ellipsis"> 765 Interacting 766 </span> 767 768 769 </a> 770 </li> 771 772 773 774 775 776 777 778 779 780 781 <li class="md-nav__item"> 782 <a href="../../neo4j/slurm/" class="md-nav__link"> 783 784 785 <span class="md-ellipsis"> 786 Running the Database with Slurm 787 </span> 788 789 790 </a> 791 </li> 792 793 794 795 796 </ul> 797 </nav> 798 799 </li> 800 801 802 803 804 805 806 807 808 809 810 811 812 813 <li class="md-nav__item md-nav__item--nested"> 814 815 816 817 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7" > 818 819 820 <label class="md-nav__link" for="__nav_7" id="__nav_7_label" tabindex="0"> 821 822 823 <span class="md-ellipsis"> 824 Developing 825 </span> 826 827 828 <span class="md-nav__icon md-icon"></span> 829 </label> 830 831 <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_7_label" aria-expanded="false"> 832 <label class="md-nav__title" for="__nav_7"> 833 <span class="md-nav__icon md-icon"></span> 834 Developing 835 </label> 836 <ul class="md-nav__list" data-md-scrollfix> 837 838 839 840 841 842 843 844 845 846 847 848 <li class="md-nav__item md-nav__item--nested"> 849 850 851 852 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_7_1" > 853 854 855 <label class="md-nav__link" for="__nav_7_1" id="__nav_7_1_label" tabindex="0"> 856 857 858 <span class="md-ellipsis"> 859 Python 860 </span> 861 862 863 <span class="md-nav__icon md-icon"></span> 864 </label> 865 866 <nav class="md-nav" data-md-level="2" aria-labelledby="__nav_7_1_label" aria-expanded="false"> 867 <label class="md-nav__title" for="__nav_7_1"> 868 <span class="md-nav__icon md-icon"></span> 869 Python 870 </label> 871 <ul class="md-nav__list" data-md-scrollfix> 872 873 874 875 876 877 878 879 <li class="md-nav__item"> 880 <a href="../../developing/python/setup/" class="md-nav__link"> 881 882 883 <span class="md-ellipsis"> 884 Setup 885 </span> 886 887 888 </a> 889 </li> 890 891 892 893 894 895 896 897 898 899 900 <li class="md-nav__item"> 901 <a href="../../developing/python/classes/" class="md-nav__link"> 902 903 904 <span class="md-ellipsis"> 905 Classes 906 </span> 907 908 909 </a> 910 </li> 911 912 913 914 915 916 917 918 919 920 921 <li class="md-nav__item"> 922 <a href="../../developing/python/testing/" class="md-nav__link"> 923 924 925 <span class="md-ellipsis"> 926 Testing 927 </span> 928 929 930 </a> 931 </li> 932 933 934 935 936 937 938 939 940 941 942 <li class="md-nav__item"> 943 <a href="../../reference" class="md-nav__link"> 944 945 946 <span class="md-ellipsis"> 947 Auto-Generated Reference 948 </span> 949 950 951 </a> 952 </li> 953 954 955 956 957 </ul> 958 </nav> 959 960 </li> 961 962 963 964 965 </ul> 966 </nav> 967 968 </li> 969 970 971 972 973 974 975 976 977 978 979 980 981 982 <li class="md-nav__item md-nav__item--nested"> 983 984 985 986 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8" > 987 988 989 <label class="md-nav__link" for="__nav_8" id="__nav_8_label" tabindex="0"> 990 991 992 <span class="md-ellipsis"> 993 Precomputed Databases 994 </span> 995 996
997 <span class="md-nav__icon md-icon"></span> 998 </label> 999 1000 <nav class="md-nav" data-md-level="1" aria-labelledby="__nav_8_label" aria-expanded="false"> 1001 <label class="md-nav__title" for="__nav_8"> 1002 <span class="md-nav__icon md-icon"></span> 1003 Precomputed Databases 1004 </label> 1005 <ul class="md-nav__list" data-md-scrollfix> 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 <li class="md-nav__item md-nav__item--nested"> 1018 1019 1020 1021 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8_1" > 1022 1023 1024 <label class="md-nav__link" for="__nav_8_1" id="__nav_8_1_label" tabindex="0"> 1025 1026 1027 <span class="md-ellipsis"> 1028 Version: 2023_v0.4.1 1029 </span> 1030 1031 1032 <span class="md-nav__icon md-icon"></span> 1033 </label> 1034 1035 <nav class="md-nav" data-md-level="2" aria-labelledby="__nav_8_1_label" aria-expanded="false"> 1036 <label class="md-nav__title" for="__nav_8_1"> 1037 <span class="md-nav__icon md-icon"></span> 1038 Version: 2023_v0.4.1 1039 </label> 1040 <ul class="md-nav__list" data-md-scrollfix> 1041 1042 1043 1044 1045 1046 1047 1048 <li class="md-nav__item"> 1049 <a href="../../precomputed_databases/2023_v0.4.1/general/" class="md-nav__link"> 1050 1051 1052 <span class="md-ellipsis"> 1053 general 1054 </span> 1055 1056 1057 </a> 1058 </li> 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 <li class="md-nav__item md-nav__item--nested"> 1074 1075 1076 1077 <input class="md-nav__toggle md-toggle " type="checkbox" id="__nav_8_1_2" > 1078 1079 1080 <label class="md-nav__link" for="__nav_8_1_2" id="__nav_8_1_2_label" tabindex="0"> 1081 1082 1083 <span class="md-ellipsis"> 1084 aws 1085 </span> 1086 1087 1088 <span class="md-nav__icon md-icon"></span> 1089 </label> 1090 1091 <nav class="md-nav" data-md-level="3" aria-labelledby="__nav_8_1_2_label" aria-expanded="false"> 1092 <label class="md-nav__title" for="__nav_8_1_2"> 1093 <span class="md-nav__icon md-icon"></span> 1094 aws 1095 </label> 1096 <ul class="md-nav__list" data-md-scrollfix> 1097 1098 1099 1100 1101 1102 1103 1104 <li class="md-nav__item"> 1105 <a href="../../precomputed_databases/2023_v0.4.1/aws/aws/" class="md-nav__link"> 1106 1107 1108 <span class="md-ellipsis"> 1109 data 1110 </span> 1111 1112 1113 </a> 1114 </li> 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 <li class="md-nav__item"> 1126 <a href="../../precomputed_databases/2023_v0.4.1/aws/aws_instructions/" class="md-nav__link"> 1127 1128 1129 <span class="md-ellipsis"> 1130 instructions 1131 </span> 1132 1133 1134 </a> 1135 </li> 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 <li class="md-nav__item"> 1147 <a href="../../precomputed_databases/2023_v0.4.1/aws/local_use/" class="md-nav__link"> 1148 1149 1150 <span class="md-ellipsis"> 1151 local use 1152 </span> 1153 1154 1155 </a> 1156 </li> 1157 1158 1159 1160 1161 </ul> 1162 </nav> 1163 1164 </li> 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 <li class="md-nav__item"> 1176 <a href="../../precomputed_databases/2023_v0.4.1/dryad/dryad/" class="md-nav__link"> 1177 1178 1179 <span class="md-ellipsis"> 1180 dryad 1181 </span> 1182 1183 1184 </a> 1185 </li> 1186 1187 1188 1189 1190 </ul> 1191 </nav> 1192 1193 </li> 1194 1195 1196 1197 1198 </ul> 1199 </nav> 1200 1201 </li> 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 <li class="md-nav__item"> 1212 <a href="../../presentations/presentations/" class="md-nav__link"> 1213 1214 1215 <span class="md-ellipsis"> 1216 Presentations 1217 </span> 1218 1219 1220 </a> 1221 </li> 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 <li class="md-nav__item"> 1232 <a href="../../hasher/hasher/" class="md-nav__link"> 1233 1234 1235 <span class="md-ellipsis"> 1236 hasher 1237 </span> 1238 1239 1240 </a> 1241 </li> 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 <li class="md-nav__item"> 1252 <a href="../../feedback/" class="md-nav__link"> 1253 1254 1255 <span class="md-ellipsis"> 1256 Give Feedback 1257 </span> 1258 1259 1260 </a> 1261 </li> 1262 1263 1264 1265 </ul> 1266</nav> 1267 </div> 1268 </div> 1269 </div> 1270 1271 1272 1273 <div class="md-sidebar md-sidebar--secondary" data-md-component="sidebar" data-md-type="toc" > 1274 <div class="md-sidebar__scrollwrap"> 1275 <div class="md-sidebar__inner"> 1276 1277 1278<nav class="md-nav md-nav--secondary" aria-label="Table of contents"> 1279 1280
1281 1282 1283 <label class="md-nav__title" for="__toc"> 1284 <span class="md-nav__icon md-icon"></span> 1285 Table of contents 1286 </label> 1287 <ul class="md-nav__list" data-md-component="toc" data-md-scrollfix> 1288 1289 <li class="md-nav__item"> 1290 <a href="#uids" class="md-nav__link"> 1291 <span class="md-ellipsis"> 1292 UIDs 1293 </span> 1294 </a> 1295 1296</li> 1297 1298 <li class="md-nav__item"> 1299 <a href="#proteins" class="md-nav__link"> 1300 <span class="md-ellipsis"> 1301 Proteins 1302 </span> 1303 </a> 1304 1305</li> 1306 1307 <li class="md-nav__item"> 1308 <a href="#assemblies" class="md-nav__link"> 1309 <span class="md-ellipsis"> 1310 Assemblies 1311 </span> 1312 </a> 1313 1314</li> 1315 1316 <li class="md-nav__item"> 1317 <a href="#nucleotides" class="md-nav__link"> 1318 <span class="md-ellipsis"> 1319 Nucleotides 1320 </span> 1321 </a> 1322 1323</li> 1324 1325 </ul> 1326 1327</nav> 1328 </div> 1329 </div> 1330 </div> 1331 1332 1333 1334 <div class="md-content" data-md-component="content"> 1335 <article class="md-content__inner md-typeset"> 1336 1337 1338 1339 1340 <a href="https://github.com/socialgene/socialgene.github.io/edit/main/docs/nodes_and_relationships/about_the_database.md" title="Edit this page" class="md-content__button md-icon"> 1341 1342 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M10 20H6V4h7v5h5v3.1l2-2V8l-6-6H6c-1.1 0-2 .9-2 2v16c0 1.1.9 2 2 2h4zm10.2-7c.1 0 .3.1.4.2l1.3 1.3c.2.2.2.6 0 .8l-1 1-2.1-2.1 1-1c.1-.1.2-.2.4-.2m0 3.9L14.1 23H12v-2.1l6.1-6.1z"/></svg> 1343 </a> 1344 1345 1346 1347 1348 <h1>Identifiers</h1> 1349 1350<h2 id="uids">UIDs</h2> 1351<p>Most nodes have a "uid" property which stand for unique identifier. It is unique, but only within the same Node label; e.g. only one uid will be present across all "protein" nodes.</p> 1352<h2 id="proteins">Proteins</h2> 1353<p>For proteins the uid is the sha512t24u hash of the protein sequence, this means proteins with identical amino acid sequences are stored only once and referenced by this uid.</p> 1354<p>Protein nodes also have a CRC64 hash which can be used to cross-reference UniProt. The original protein ID from the input FASTA/Genome is found not on the redundant protein nodes but on the relationship between the node representing the nucleotide sequence the protein was found on, and the non-redundant protein.</p> 1355<p>An example of retrieving an input protein's original ID:</p> 1356<div class="tabbed-set tabbed-alternate" data-tabs="1:1"><input checked="checked" id="__tabbed_1_1" name="__tabbed_1" type="radio" /><div class="tabbed-labels"><label for="__tabbed_1_1">Cypher</label></div> 1357<div class="tabbed-content"> 1358<div class="tabbed-block"></div> 1359</div> 1360</div> 1361<div class="highlight"><pre><span></span><code><span class="k">MATCH</span><span class="w"> </span><span class="p">()</span><span class="o">-[</span><span class="n">e1</span><span class="p">:</span><span class="n">ENCODES</span><span class="o">]-></span><span class="p">(</span><span class="n">p1</span><span class="p">:</span><span class="n">protein</span><span class="w"> </span><span class="p">{</span><span class="n">uid</span><span class="p">:</span><span class="s">"bnI__-NwnuHiyLRDrRcUdrPyYyIjfONy"</span><span class="p">})</span><span class="w"> </span> 1362<span class="k">RETURN</span><span class="w"> </span><span class="n">e1</span><span class="p">.</span><span class="n">protein_id</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="n">protein_id</span><span class="p">,</span><span class="w"> </span><span class="n">p1</span><span class="p">.</span><span class="n">uid</span><span class="w"> </span><span class="k">as</span><span class="w"> </span><span class="n">uid</span> 1363<span class="k">LIMIT</span><span class="w"> </span><span class="m">2</span> 1364</code></pre></div> 1365<p>Results in:</p> 1366<table> 1367<thead> 1368<tr> 1369<th>protein_id</th> 1370<th>protein_uid</th> 1371</tr> 1372</thead> 1373<tbody> 1374<tr> 1375<td>ALC45_RS09175</td> 1376<td>bnI__-NwnuHiyLRDrRcUdrPyYyIjfONy</td> 1377</tr> 1378<tr> 1379<td>ALT75_RS12645</td> 1380<td>bnI__-NwnuHiyLRDrRcUdrPyYyIjfONy</td> 1381</tr> 1382</tbody> 1383</table> 1384<h2 id="assemblies">Assemblies</h2> 1385<p>For assemblies SocialGene tries to assign a uid in preference of:</p> 1386<p>1) extract the <code>
1386Assembly:</code> identifier from the <code>dbxrefs</code> section of a genbank file and use it as the uid</p> 1387<p>2) use the name of the input file as the uid (assumption that a single file contains a single assembly/genome)</p> 1388<p>3) assign a random string as the uid</p> 1389<div class="admonition note"> 1390<p class="admonition-title">Note</p> 1391<p>If a FASTA file was used as input the nucleotide and assembly node uids will be the FASTA file's name.</p> 1392</div> 1393<h2 id="nucleotides">Nucleotides</h2> 1394<p>Nucleotide sequences ("Locus" in GBK files) are assigned a unique id by hashing the assembly uid they come from, and the external nucleotide identifier. See the example below. The original nucleotide identifier is stored on the nucleotide node as the property <code>external_id</code>. </p> 1395<div class="tabbed-set tabbed-alternate" data-tabs="2:1"><input checked="checked" id="__tabbed_2_1" name="__tabbed_2" type="radio" /><div class="tabbed-labels"><label for="__tabbed_2_1">Cypher</label></div> 1396<div class="tabbed-content"> 1397<div class="tabbed-block"></div> 1398</div> 1399</div> 1400<div class="highlight"><pre><span></span><code><span class="k">MATCH</span><span class="w"> </span><span class="p">(</span><span class="n">n1</span><span class="p">:</span><span class="n">nucleotide</span><span class="w"> </span><span class="p">{</span><span class="n">external_id</span><span class="p">:</span><span class="s">"NZ_CXED01000052.1"</span><span class="p">})</span> 1401<span class="k">RETURN</span><span class="w"> </span><span class="n">n1</span> 1402<span class="k">LIMIT</span><span class="w"> </span><span class="m">1</span> 1403</code></pre></div> 1404<p>Returns the node and its properties:</p> 1405<div class="highlight"><pre><span></span><code>{ 1406 "identity": 43109979, 1407 "labels": [ 1408 "nucleotide" 1409 ], 1410 "properties": { 1411 "strain": "20051272_1361367", 1412 "collection_date": "2005-01-01", 1413 "country": "Egypt", 1414 "db_xref": "taxon:624", 1415 "uid": "zzGRoTd7WPwP8XCrEzdEmnbWtvJvCsap", 1416 "serovar": "NA", 1417 "external_id": "NZ_CXED01000052.1", 1418 "mol_type": "genomic DNA", 1419 "isolation_source": "feces" 1420 }, 1421 "elementId": "43109979" 1422} 1423</code></pre></div> 1424<p>In this case the uid of the nucleotide node is <code>zzGRoTd7WPwP8XCrEzdEmnbWtvJvCsap</code>, which is the hash of assembly uid "GCF_001246015.1" and the nucleotide external_id "NZ_CXED01000052.1".</p> 1425<p>This can be verified in the SocialGene python library:</p> 1426<div class="tabbed-set tabbed-alternate" data-tabs="3:1"><input checked="checked" id="__tabbed_3_1" name="__tabbed_3" type="radio" /><div class="tabbed-labels"><label for="__tabbed_3_1">Python</label></div> 1427<div class="tabbed-content"> 1428<div class="tabbed-block"></div> 1429</div> 1430</div> 1431<div class="highlight"><pre><span></span><code><span class="kn">from</span> <span class="nn">socialgene.hashing.hashing</span> <span class="kn">import</span> <span class="n">hasher</span> 1432<span class="n">hasher</span><span class="p">(</span><span class="s2">"GCF_001246015.1___NZ_CXED01000052.1"</span><span class="p">)</span> 1433 1434<span class="c1"># 'zzGRoTd7WPwP8XCrEzdEmnbWtvJvCsap'</span> 1435</code></pre></div> 1436<div class="admonition note"> 1437<p class="admonition-title">Note</p> 1438<p>If a FASTA file was used as input the nucleotide and assembly node uids will be the FASTA file's name.</p> 1439</div> 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 <form class="md-feedback" name="feedback" hidden> 1454 <fieldset> 1455 <legend class="md-feedback__title"> 1456 Was this page helpful? 1457 </legend> 1458 <div class="md-feedback__inner"> 1459 <div class="md-feedback__list"> 1460 1461 <button class="md-feedback__icon md-icon" type="submit" title="This page was helpful" data-md-value="1"> 1462 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path d="M20 12a8 8 0 0 0-8-8 8 8 0 0 0-8 8 8 8 0 0 0 8 8 8 8 0 0 0 8-8m2 0a10 10 0 0 1-10 10A10 10 0 0 1 2 12 10 10 0 0 1 12 2a10 10 0 0 1 10 10M10 9.5c0 .8-.7 1.5-1.5 1.5S7 10.3 7 9.5 7.7 8 8.5 8s1.5.7 1.5 1.5m7 0c0 .8-.7 1.5-1.5 1.5S14 10.3 14 9.5 14.7 8 15.5 8s1.5.7 1.5 1.5m-5 7.73c-1.75 0-3.29-.73-4.19-1.81L9.23 14c.45.72 1.52 1.23 2.77 1.23s2.32-.51 2.77-1.23l1.42 1.42c-.9 1.08-2.44 1.81-4.19 1.81"/></svg> 1463 </button> 1464 1465 <button class="md-feedback__icon md-icon" type="submit" title="This page could be improved" data-md-value="0"> 1466 <svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24">
1466<path d="M20 12a8 8 0 0 0-8-8 8 8 0 0 0-8 8 8 8 0 0 0 8 8 8 8 0 0 0 8-8m2 0a10 10 0 0 1-10 10A10 10 0 0 1 2 12 10 10 0 0 1 12 2a10 10 0 0 1 10 10m-6.5-4c.8 0 1.5.7 1.5 1.5s-.7 1.5-1.5 1.5-1.5-.7-1.5-1.5.7-1.5 1.5-1.5M10 9.5c0 .8-.7 1.5-1.5 1.5S7 10.3 7 9.5 7.7 8 8.5 8s1.5.7 1.5 1.5m2 4.5c1.75 0 3.29.72 4.19 1.81l-1.42 1.42C14.32 16.5 13.25 16 12 16s-2.32.5-2.77 1.23l-1.42-1.42C8.71 14.72 10.25 14 12 14"/></svg> 1467 </button> 1468 1469 </div> 1470 <div class="md-feedback__note"> 1471 1472 <div data-md-value="1" hidden> 1473 1474 1475 1476 1477 Thanks for your feedback! 1478 </div> 1479 1480 <div data-md-value="0" hidden> 1481 1482 1483 1484 1485 Thanks for your feedback! Help us improve this page by using our <a href="..." target="_blank" rel="noopener">feedback form</a>. 1486 </div> 1487 1488 </div> 1489 </div> 1490 </fieldset> 1491 </form> 1492 1493 1494 1495 </article> 1496 </div> 1497 1498
1499<script>var target=document.getElementById(location.hash.slice(1));target&&target.name&&(target.checked=target.name.startsWith("__tabbed_"))</script>
1499 1500 </div> 1501 1502 </main> 1503 1504 <footer class="md-footer"> 1505 1506 <div class="md-footer-meta md-typeset"> 1507 <div class="md-footer-meta__inner md-grid"> 1508 <div class="md-copyright"> 1509 1510 1511 Made with 1512 <a href="https://squidfunk.github.io/mkdocs-material/" target="_blank" rel="noopener"> 1513 Material for MkDocs 1514 </a> 1515 1516</div> 1517 1518 </div> 1519 </div> 1520</footer> 1521 1522 </div> 1523 <div class="md-dialog" data-md-component="dialog"> 1524 <div class="md-dialog__inner md-typeset"></div> 1525 </div> 1526 1527 1528
1528<script id="__config" type="application/json">{"base": "../..", "features": ["content.action.edit", "content.code.copy"], "search": "../../assets/javascripts/workers/search.6ce7567c.min.js", "translations": {"clipboard.copied": "Copied to clipboard", "clipboard.copy": "Copy to clipboard", "search.result.more.one": "1 more on this page", "search.result.more.other": "# more on this page", "search.result.none": "No matching documents", "search.result.one": "1 matching document", "search.result.other": "# matching documents", "search.result.placeholder": "Type to start searching", "search.result.term.missing": "Missing", "select.version": "Select version"}}</script>
1528 1529 1530 1531
1531<script src="../../assets/javascripts/bundle.83f73b43.min.js"></script>
1531 1532 1533 1534 </body> 1535</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.