1920 lines
64 KiB
HTML
1920 lines
64 KiB
HTML
<!DOCTYPE html>
|
|
<html lang="en-us" dir="ltr">
|
|
<head>
|
|
<meta charset="UTF-8">
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
|
<meta name="description" content="
|
|
Prepare a local copy of Genbank
|
|
#
|
|
|
|
|
|
|
|
|
|
|
|
A local copy of the GenBank database requires a lot of disk space.
|
|
|
|
|
|
A whole copy of GenBank stored as compressed
|
|
fasta
|
|
files takes up about 1TB of disk
|
|
space.">
|
|
<meta name="theme-color" media="(prefers-color-scheme: light)" content="#ffffff">
|
|
<meta name="theme-color" media="(prefers-color-scheme: dark)" content="#343a40">
|
|
<meta name="color-scheme" content="light dark"><meta property="og:url" content="http://metabar:8888/obidoc/docs/cookbook/local_genbank/">
|
|
<meta property="og:site_name" content="OBITools4 documentation">
|
|
<meta property="og:title" content="Prepare a local copy of Genbank">
|
|
<meta property="og:description" content="Prepare a local copy of Genbank # A local copy of the GenBank database requires a lot of disk space. A whole copy of GenBank stored as compressed fasta files takes up about 1TB of disk space.">
|
|
<meta property="og:locale" content="en_us">
|
|
<meta property="og:type" content="website">
|
|
<title>Prepare a local copy of Genbank | OBITools4 documentation</title>
|
|
<link rel="icon" href="/obidoc/favicon.png" >
|
|
<link rel="manifest" href="/obidoc/manifest.json">
|
|
<link rel="canonical" href="http://metabar:8888/obidoc/docs/cookbook/local_genbank/">
|
|
<link rel="stylesheet" href="/obidoc/book.min.5fd7b8e2d1c0ae15da279c52ff32731130386f71b58f011468f20d0056fe6b78.css" integrity="sha256-X9e44tHArhXaJ5xS/zJzETA4b3G1jwEUaPINAFb+a3g=" crossorigin="anonymous">
|
|
<script defer src="/obidoc/fuse.min.js"></script>
|
|
<script defer src="/obidoc/en.search.min.4da51bdd2d833922fdbc0e19df517221387fc625ffb68ee140d605b3c5b68058.js" integrity="sha256-TaUb3S2DOSL9vA4Z31FyITh/xiX/to7hQNYFs8W2gFg=" crossorigin="anonymous"></script>
|
|
|
|
<script defer src="/obidoc/sw.min.32af8eafce4180aa1c5dea66d99fb26ba9043ea7c7a4c706138c91d9051b285e.js" integrity="sha256-Mq+Or85BgKocXepm2Z+ya6kEPqfHpMcGE4yR2QUbKF4=" crossorigin="anonymous"></script>
|
|
<link rel="alternate" type="application/rss+xml" href="http://metabar:8888/obidoc/docs/cookbook/local_genbank/index.xml" title="OBITools4 documentation" />
|
|
<!--
|
|
Made with Book Theme
|
|
https://github.com/alex-shpak/hugo-book
|
|
-->
|
|
<link rel="stylesheet" type="text/css" href="http://metabar:8888/obidoc/hugo-cite.css" />
|
|
</head>
|
|
<body dir="ltr">
|
|
<input type="checkbox" class="hidden toggle" id="menu-control" />
|
|
<input type="checkbox" class="hidden toggle" id="toc-control" />
|
|
<main class="container flex">
|
|
<aside class="book-menu">
|
|
<div class="book-menu-content">
|
|
|
|
<nav>
|
|
<h2 class="book-brand">
|
|
<a class="flex align-center" href="/obidoc/"><img src="/obidoc/obitools_logo.jpg" alt="Logo" class="book-icon" /><span>OBITools4 documentation</span>
|
|
</a>
|
|
</h2>
|
|
|
|
|
|
<div class="book-search hidden">
|
|
<input type="text" id="book-search-input" placeholder="Search" aria-label="Search" maxlength="64" data-hotkeys="s/" />
|
|
<div class="book-search-spinner hidden"></div>
|
|
<ul id="book-search-results"></ul>
|
|
</div>
|
|
<script>document.querySelector(".book-search").classList.remove("hidden")</script>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<span>Docs</span>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/about/" class="">About</a>
|
|
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/installation/" class="">Installation</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/principles/" class="">General operating principles</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-08756b4c1f14be6ee584ece005b9f621" class="toggle" />
|
|
<label for="section-08756b4c1f14be6ee584ece005b9f621" class="flex justify-between">
|
|
<a role="button" class="">File formats</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-933c2e64b905b84e22aa5273cea2d0bd" class="toggle" />
|
|
<label for="section-933c2e64b905b84e22aa5273cea2d0bd" class="flex justify-between">
|
|
<a role="button" class="">Sequence file formats</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/formats/fasta/" class="">FASTA file format</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/formats/fastq/" class="">FASTQ file format</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/formats/genbank/" class="">GenBank Flat File format</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/formats/embl/" class="">EMBL Flat File format</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/file_format/sequence_files/csv/" class="">CSV format</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/formats/json/" class="">JSON format</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/file_format/sequence_files/annotations/" class="">Annotation of sequences</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-0258ae1c222f9a38cc1b75254c93b0f4" class="toggle" />
|
|
<label for="section-0258ae1c222f9a38cc1b75254c93b0f4" class="flex justify-between">
|
|
<a role="button" class="">Taxonomy file formats</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/file_format/taxonomy_file/csv_taxdump/" class="">CSV formatted taxdump</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/file_format/taxonomy_file/ncbi_taxdump/" class="">NCBI taxdump</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/formats/csv/" class="">The CSV format</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-70b1e6e5ec7f3ccab643155fa50659b6" class="toggle" />
|
|
<label for="section-70b1e6e5ec7f3ccab643155fa50659b6" class="flex justify-between">
|
|
<a role="button" class="">Patterns</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/patterns/regular/" class="">Regular Expressions</a>
|
|
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/patterns/dnagrep/" class="">DNA Patterns</a>
|
|
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-8223f464911a1fe6c655972143684e93" class="toggle" />
|
|
<label for="section-8223f464911a1fe6c655972143684e93" class="flex justify-between">
|
|
<a role="button" class="">The OBITools4 commands</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/commands/options/" class="">Shared command options</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-8921ea65523c266b128dd4263232b0fc" class="toggle" />
|
|
<label for="section-8921ea65523c266b128dd4263232b0fc" class="flex justify-between">
|
|
<a role="button" class="">Basics</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obiannotate/" class="">obiannotate</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obicomplement/" class="">obicomplement</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obiconvert/" class="">obiconvert</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obicount/" class="">obicount</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obicsv/" class="">obicsv</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obidemerge/" class="">obidemerge</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obidistribute/" class="">obidistribute</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obigrep/" class="">obigrep</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obijoin/" class="">obijoin</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obimatrix/" class="">obimatrix</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obisplit/" class="">obisplit</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obisummary/" class="">obisummary</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obiuniq/" class="">obiuniq</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-dbdf1bb5377572439394e60e08c30f50" class="toggle" />
|
|
<label for="section-dbdf1bb5377572439394e60e08c30f50" class="flex justify-between">
|
|
<a role="button" class="">Demultiplexing samples</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obimultiplex/" class="">obimultiplex</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obitagpcr/" class="">obitagpcr</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-aa98fedd067b51150db59691a8ea8edd" class="toggle" />
|
|
<label for="section-aa98fedd067b51150db59691a8ea8edd" class="flex justify-between">
|
|
<a role="button" class="">Sequence alignments</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obiclean/" class="">obiclean</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-7433746525d8c2b29b033f765c869acd" class="toggle" />
|
|
<label for="section-7433746525d8c2b29b033f765c869acd" class="flex justify-between">
|
|
<a href="/obidoc/obitools/obipairing/" class="">obipairing</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/commands/alignments/obipairing/fasta-like/" class="">The FASTA-like alignment</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/commands/alignments/obipairing/exact-alignment/" class="">Exact alignment</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obipcr/" class="">obipcr</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obirefidx/" class="">obirefidx</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obitag/" class="">obitag</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-5746f699d10490780dec8e30ab2dd3ce" class="toggle" />
|
|
<label for="section-5746f699d10490780dec8e30ab2dd3ce" class="flex justify-between">
|
|
<a role="button" class="">Taxonomy</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obitaxonomy/" class="">obitaxonomy</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-3f50c4fe7ab436a56ae92897d5444956" class="toggle" />
|
|
<label for="section-3f50c4fe7ab436a56ae92897d5444956" class="flex justify-between">
|
|
<a role="button" class="">Advanced tools</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obiscript/" class="">obiscript</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-549be3934679fcb82a232f6bd5435563" class="toggle" />
|
|
<label for="section-549be3934679fcb82a232f6bd5435563" class="flex justify-between">
|
|
<a role="button" class="">Others</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obimicrosat/" class="">obimicrosat</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-ceca4455173761e30cbc0a6dc2327167" class="toggle" />
|
|
<label for="section-ceca4455173761e30cbc0a6dc2327167" class="flex justify-between">
|
|
<a role="button" class="">Experimentals</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obicleandb/" class="">obicleandb</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obiconsensus/" class="">obiconsensus</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/obitools/obilandmark/" class="">obilandmark</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/commands/tags/" class="">Glossary of tags</a>
|
|
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-9b1bcd52530c59dc4819b1f61c128f54" class="toggle" checked />
|
|
<label for="section-9b1bcd52530c59dc4819b1f61c128f54" class="flex justify-between">
|
|
<a role="button" class="">Cookbook</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/cookbook/illumina/" class="">Analysing an Illumina data set</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/cookbook/ecoprimers/" class="">Designing new barcodes</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/cookbook/local_genbank/" class="active">Prepare a local copy of Genbank</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/cookbook/reference_db/" class="">Build a reference database</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/cookbook/minion/" class="">Oxford Nanopore data analysis</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<span>Programming OBITools</span>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/programming/expression/" class="">Expression language</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-6d580829a667b5cca790b286d99a10fe" class="toggle" />
|
|
<label for="section-6d580829a667b5cca790b286d99a10fe" class="flex justify-between">
|
|
<a href="/obidoc/docs/programming/lua/" class="">Lua: for scripting OBITools</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<input type="checkbox" id="section-2fb081dac812d624eea5f4268fca9e26" class="toggle" />
|
|
<label for="section-2fb081dac812d624eea5f4268fca9e26" class="flex justify-between">
|
|
<a role="button" class="">Obitools Classes</a>
|
|
</label>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/programming/lua/obitools_classes/biosequence/" class="">BioSequence</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/programming/lua/obitools_classes/biosequenceslice/" class="">BioSequenceSlice</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/programming/lua/obitools_classes/taxonomy/" class="">Taxonomy</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/programming/lua/obitools_classes/taxon/" class="">Taxon</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
|
|
<li>
|
|
|
|
|
|
|
|
|
|
|
|
<a href="/obidoc/docs/programming/lua/obitools_classes/mutex/" class="">Mutex</a>
|
|
|
|
|
|
|
|
<ul>
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
</li>
|
|
|
|
|
|
</ul>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
</nav>
|
|
|
|
|
|
|
|
|
|
<script>(function(){var e=document.querySelector("aside .book-menu-content");addEventListener("beforeunload",function(){localStorage.setItem("menu.scrollTop",e.scrollTop)}),e.scrollTop=localStorage.getItem("menu.scrollTop")})()</script>
|
|
|
|
|
|
|
|
</div>
|
|
</aside>
|
|
|
|
<div class="book-page">
|
|
<header class="book-header">
|
|
|
|
<div class="flex align-center justify-between">
|
|
<label for="menu-control">
|
|
<img src="/obidoc/svg/menu.svg" class="book-icon" alt="Menu" />
|
|
</label>
|
|
|
|
<h3>Prepare a local copy of Genbank</h3>
|
|
|
|
<label for="toc-control">
|
|
|
|
<img src="/obidoc/svg/toc.svg" class="book-icon" alt="Table of Contents" />
|
|
|
|
</label>
|
|
</div>
|
|
|
|
|
|
|
|
<aside class="hidden clearfix">
|
|
|
|
|
|
<nav id="TableOfContents">
|
|
<ul>
|
|
<li><a href="#prepare-a-local-copy-of-genbank">Prepare a local copy of Genbank</a>
|
|
<ul>
|
|
<li><a href="#download-genbank">Download GenBank</a></li>
|
|
<li><a href="#the-makefile-script-for-downloading-genbank">The Makefile script for downloading Genbank</a></li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</nav>
|
|
|
|
|
|
|
|
</aside>
|
|
|
|
|
|
</header>
|
|
|
|
|
|
|
|
<article class="markdown book-article"><h1 id="prepare-a-local-copy-of-genbank">
|
|
Prepare a local copy of Genbank
|
|
<a class="anchor" href="#prepare-a-local-copy-of-genbank">#</a>
|
|
</h1>
|
|
|
|
<link rel="stylesheet" href="/obidoc/css/vendors/admonitions.5c73bad2903e7d2d44ad118370ebd8c2cf5f239d4d93c283e55c00f2f8d30746.css" integrity="sha256-XHO60pA+fS1ErRGDcOvYws9fI51Nk8KD5VwA8vjTB0Y=" crossorigin="anonymous">
|
|
<div class="admonition caution">
|
|
<div class="admonition-header"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path d="M256 32c14.2 0 27.3 7.5 34.5 19.8l216 368c7.3 12.4 7.3 27.7 .2 40.1S486.3 480 472 480L40 480c-14.3 0-27.6-7.7-34.7-20.1s-7-27.8 .2-40.1l216-368C228.7 39.5 241.8 32 256 32zm0 128c-13.3 0-24 10.7-24 24l0 112c0 13.3 10.7 24 24 24s24-10.7 24-24l0-112c0-13.3-10.7-24-24-24zm32 224a32 32 0 1 0 -64 0 32 32 0 1 0 64 0z"/></svg>
|
|
<span>A local copy of the GenBank database requires a lot of disk space.</span>
|
|
</div>
|
|
<div class="admonition-content">
|
|
<p>A whole copy of GenBank stored as compressed
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
files takes up about 1TB of disk
|
|
space.</p>
|
|
</div>
|
|
</div><p>Three bioinformatics centres distribute all publicly available DNA sequences worldwide. They are</p>
|
|
<ul>
|
|
<li>
|
|
<a href="https://www.ncbi.nlm.nih.gov/genome/">NCBI</a>: distributes GenBank</li>
|
|
<li>
|
|
<a href="https://www.ebi.ac.uk/ena/browser/home">EMBL-EBI</a>: distributes EMBL</li>
|
|
<li>
|
|
<a href="https://www.ddbj.nig.ac.jp/ddbj/index-e.html">DDBJ</a>: distributes DDBJ</li>
|
|
</ul>
|
|
<p>The three centres are associated in an international agreement, the
|
|
<a href="https://www.insdc.org/">International Nucleotide Sequence Database Collaboration (INSDC)</a>. This agreement allows the three centres to share the sequences submitted by biologists. As a result, all sequences are available in the three databases, where they are identified by the same accession number.</p>
|
|
<p>The content of these databases is available via a web interface, but can also be downloaded to have a local copy.
|
|
The
|
|
<a href="https://www.ncbi.nlm.nih.gov/genome/">NCBI</a> and the
|
|
<a href="https://www.ebi.ac.uk/ena/browser/home">EMBL-EBI</a> have two different strategies for distributing data. The
|
|
<a href="https://www.ebi.ac.uk/ena/browser/home">EMBL-EBI</a> distributes fewer large files, whereas the
|
|
<a href="https://www.ncbi.nlm.nih.gov/genome/">NCBI</a> platform prefers to distribute many small files. This is why we choose to download the sequences from GenBank here.</p>
|
|
<p>Each of these databases is divided into several taxonomic divisions. The main GenBank divisions useful for metabarcoding are:</p>
|
|
<ul>
|
|
<li><code>bct</code>: <em>Bacteria</em></li>
|
|
<li><code>inv</code>: <em>Invertebrates</em></li>
|
|
<li><code>mam</code>: <em>Mammals</em></li>
|
|
<li><code>phg</code>: <em>Phages</em></li>
|
|
<li><code>pln</code>: <em>Plants</em></li>
|
|
<li><code>pri</code>: <em>Primates</em></li>
|
|
<li><code>rod</code>: <em>Rodents</em></li>
|
|
<li><code>vrl</code>: <em>Viruses</em></li>
|
|
<li><code>vrt</code>: <em>Vertebrates</em></li>
|
|
</ul>
|
|
<p>Other divisions exist, but are less useful for metabarcoding (
|
|
<a href="https://www.ncbi.nlm.nih.gov/genbank/htgs/divisions/">click here more information</a>).</p>
|
|
<h2 id="download-genbank">
|
|
Download GenBank
|
|
<a class="anchor" href="#download-genbank">#</a>
|
|
</h2>
|
|
<p>GenBank is distributed in two main formats:
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
and
|
|
<a href="http://metabar:8888/obidoc/formats/genbank/">GenBank</a>
|
|
. The
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
format has the advantage of being smaller than the
|
|
<a href="http://metabar:8888/obidoc/formats/genbank/">GenBank</a>
|
|
format because all the sequence annotations stored in the
|
|
<a href="http://metabar:8888/obidoc/formats/genbank/">GenBank</a>
|
|
format are not present in the
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
format. For metabarcoding, however, the disadvantage is that the
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
format does not contain the sequence taxonomic information stored as a taxon identifier (taxid).</p>
|
|
<p>To combine the advantages of both formats, you can download the
|
|
<a href="http://metabar:8888/obidoc/formats/genbank/">GenBank</a>
|
|
format and convert it to the
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
format using the <a href="http://metabar:8888/obidoc/obitools/obiconvert/">
|
|
<abbr title="obiconvert: convert format of a sequence file"><code>obiconvert</code></abbr>
|
|
</a> command. The <a href="http://metabar:8888/obidoc/obitools/obiconvert/">
|
|
<abbr title="obiconvert: convert format of a sequence file"><code>obiconvert</code></abbr>
|
|
</a> command ensures that taxonomic information is preserved during conversion.</p>
|
|
<p>Network interruptions can occur quite frequently during the process of downloading all these files, so there is a risk of the download failing. To solve this problem, here is a <code>make</code> script that downloads the GenBank files and converts them in
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
files.
|
|
The choice of
|
|
<a href="https://en.wikipedia.org/wiki/Make_%28software%29"><code>make</code></a> allows the download process to be restarted at the point of failure if it fails.</p>
|
|
<p>To download GenBank, copy the <a href="Makefile" type="text/x-makefile" download="Makefile"><code>Makefile</code></a> file to your local computer in the directory where you want to store the GenBank files.</p>
|
|
|
|
<div class="admonition caution">
|
|
<div class="admonition-header"><svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><path d="M256 32c14.2 0 27.3 7.5 34.5 19.8l216 368c7.3 12.4 7.3 27.7 .2 40.1S486.3 480 472 480L40 480c-14.3 0-27.6-7.7-34.7-20.1s-7-27.8 .2-40.1l216-368C228.7 39.5 241.8 32 256 32zm0 128c-13.3 0-24 10.7-24 24l0 112c0 13.3 10.7 24 24 24s24-10.7 24-24l0-112c0-13.3-10.7-24-24-24zm32 224a32 32 0 1 0 -64 0 32 32 0 1 0 64 0z"/></svg>
|
|
<span>The Makefile script must be called <code>Makefile</code> without any extension.</span>
|
|
</div>
|
|
</div><p>Then, execute the following command:</p>
|
|
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-bash" data-lang="bash"><span style="display:flex;"><span>make
|
|
</span></span></code></pre></div><p>By default, the script download the divisions of GenBank listed above. To download one or more specific divisions of GenBank, you can use the <code>GBDIV</code> variable. For example, to download only the <code>mam</code> division, enter the following command:</p>
|
|
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-bash" data-lang="bash"><span style="display:flex;"><span>make GBDIV<span style="color:#f92672">=</span>mam
|
|
</span></span></code></pre></div><p>To download several divisions like <code>mam</code> and <code>rod</code>, separate the names by a space:</p>
|
|
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-bash" data-lang="bash"><span style="display:flex;"><span>make GBDIV<span style="color:#f92672">=</span><span style="color:#e6db74">"mam rod"</span>
|
|
</span></span></code></pre></div><p>If the download fails, restart the download process by using the <code>make</code> command again, without specifying the <code>GBDIV</code> variable again:</p>
|
|
<div class="highlight"><pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-bash" data-lang="bash"><span style="display:flex;"><span>make
|
|
</span></span></code></pre></div><p>The <code>Makefile</code> will create a directory called <code>Release_###</code>, where <strong>###</strong> is the number of the current release. This directory will contain the following files:</p>
|
|
<pre tabindex="0"><code>. 📂 Release_264
|
|
└── 📂 depends/
|
|
│ ├── 📄 gbfiles.d
|
|
│ ├── 📄 gbfiles.d.full
|
|
└── 📂 fasta/
|
|
│ └── 📂 mam/
|
|
│ ├── 📄 gbmam1.fasta.gz
|
|
│ ├── 📄 gbmam10.fasta.gz
|
|
│ └── 📄 ...
|
|
│ └── 📂 rod/
|
|
│ ├── 📄 gbrod1.fasta.gz
|
|
│ └── 📄 ...
|
|
└── 📂 stamp/
|
|
│ ├── 📄 gbmam1.seq.gz.stamp
|
|
│ ├── 📄 gbmam10.seq.gz.stamp
|
|
│ ├── 📄 gbrod1.seq.gz.stamp
|
|
└── 📂 taxonomy/
|
|
├── 📄 citations.dmp
|
|
├── 📄 delnodes.dmp
|
|
├── 📄 division.dmp
|
|
├── 📄 gc.prt
|
|
├── 📄 gencode.dmp
|
|
├── 📄 images.dmp
|
|
├── 📄 merged.dmp
|
|
├── 📄 names.dmp
|
|
├── 📄 nodes.dmp
|
|
└── 📄 readme.txt
|
|
</code></pre><ul>
|
|
<li>The <code>taxonomy</code> directory contains a copy of the NCBI taxonomy database at the time of download.</li>
|
|
<li>The <code>fasta</code> directory contains the
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
files sorted by taxonomic division in subdirectories, here <code>mam</code> and <code>rod</code>.</li>
|
|
<li>The <code>stamp</code> directory allows the <code>Makefile</code> script to restart the download process if it fails, without having to download the whole GenBank database again. To free up space, the <code>stamp</code> directory can be deleted at the end of the download process.</li>
|
|
<li>The <code>depends</code> directory contains a <code>make</code> script with all the instructions for downloading the GenBank files. It is first created by the <code>Makefile</code> script. It contains instructions for downloading the files that need to be downloaded according to the specified GenBank division. To free up space, the <code>depends</code> directory can be deleted at the end of the download process.</li>
|
|
<li>The <code>tmp</code> directory is used to store the downloaded GenBank files before they are converted into
|
|
<a href="http://metabar:8888/obidoc/formats/fasta/">fasta</a>
|
|
. It does not normally persist after the download process. To free up space, the <code>tmp</code> directory can be deleted at the end of the download process if it persists.</li>
|
|
</ul>
|
|
<h2 id="the-makefile-script-for-downloading-genbank">
|
|
The Makefile script for downloading Genbank
|
|
<a class="anchor" href="#the-makefile-script-for-downloading-genbank">#</a>
|
|
</h2>
|
|
<p><a style="padding: 10px 20px; background-color: #cacaca; border: 1px solid #8e8080; border-bottom: none; border-radius: 5px 5px 0 0; box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1)"
|
|
href="Makefile" download="Makefile">📄 Makefile</a></p>
|
|
<DIV style="border: 2px solid #8e8080; border-radius: 0 0 5px 5px; padding: 20px; background-color: white; ">
|
|
<div class="highlight"><div style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;">
|
|
<table style="border-spacing:0;padding:0;margin:0;border:0;"><tr><td style="vertical-align:top;padding:0;margin:0;border:0;">
|
|
<pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 1
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 2
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 3
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 4
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 5
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 6
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 7
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 8
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 9
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 10
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 11
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 12
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 13
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 14
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 15
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 16
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 17
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 18
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 19
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 20
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 21
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 22
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 23
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 24
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 25
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 26
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 27
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 28
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 29
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 30
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 31
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 32
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 33
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 34
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 35
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 36
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 37
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 38
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 39
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 40
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 41
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 42
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 43
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 44
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 45
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 46
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 47
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 48
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 49
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 50
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 51
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 52
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 53
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 54
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 55
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 56
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 57
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 58
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 59
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 60
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 61
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 62
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 63
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 64
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 65
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 66
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 67
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 68
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 69
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 70
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 71
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 72
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 73
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 74
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 75
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 76
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 77
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 78
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 79
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 80
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 81
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 82
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 83
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 84
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 85
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 86
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 87
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 88
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 89
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 90
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 91
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 92
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 93
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 94
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 95
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 96
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 97
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 98
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f"> 99
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f">100
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f">101
|
|
</span><span style="white-space:pre;-webkit-user-select:none;user-select:none;margin-right:0.4em;padding:0 0.4em 0 0.4em;color:#7f7f7f">102
|
|
</span></code></pre></td>
|
|
<td style="vertical-align:top;padding:0;margin:0;border:0;;width:100%">
|
|
<pre tabindex="0" style="color:#f8f8f2;background-color:#272822;-moz-tab-size:4;-o-tab-size:4;tab-size:4;"><code class="language-make" data-lang="make"><span style="display:flex;"><span>SHELL <span style="color:#f92672">:=</span> /bin/bash
|
|
</span></span><span style="display:flex;"><span>FTPNCBI<span style="color:#f92672">=</span>ftp.ncbi.nlm.nih.gov
|
|
</span></span><span style="display:flex;"><span>GBURL<span style="color:#f92672">=</span>https://<span style="color:#66d9ef">$(</span>FTPNCBI<span style="color:#66d9ef">)</span>/genbank
|
|
</span></span><span style="display:flex;"><span>GBRELEASE_URL<span style="color:#f92672">=</span><span style="color:#66d9ef">$(</span>GBURL<span style="color:#66d9ef">)</span>/GB_Release_Number
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span>TAXOURL<span style="color:#f92672">=</span>https://<span style="color:#66d9ef">$(</span>FTPNCBI<span style="color:#66d9ef">)</span>/pub/taxonomy/taxdump.tar.gz
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span>GBRELEASE<span style="color:#f92672">:=</span><span style="color:#66d9ef">$(</span>shell curl <span style="color:#66d9ef">$(</span>GBRELEASE_URL<span style="color:#66d9ef">))</span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span>GBDIV_ALL<span style="color:#f92672">:=</span><span style="color:#66d9ef">$(</span>shell curl -L <span style="color:#e6db74">${</span>GBURL<span style="color:#e6db74">}</span> <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> | grep -E <span style="color:#e6db74">'gb.+\.seq\.gz'</span> <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> | sed -E <span style="color:#e6db74">'s@^.*<a href="gb([^0-9]+)[0-9]+\.seq.gz.*$$@\1@'</span> <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> | sort <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> | uniq<span style="color:#f92672">)</span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span>GBDIV<span style="color:#f92672">=</span>bct inv mam phg pln pri rod vrl vrt
|
|
</span></span><span style="display:flex;"><span>DIRECTORIES<span style="color:#f92672">=</span>fasta fasta_fgs
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span>GBFILE_ALL<span style="color:#f92672">:=</span><span style="color:#66d9ef">$(</span>shell curl -L <span style="color:#e6db74">${</span>GBURL<span style="color:#e6db74">}</span> <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> | grep -E <span style="color:#e6db74">"gb(</span>$$<span style="color:#e6db74">(tr ' ' '|' <<< "</span><span style="color:#e6db74">${</span>GBDIV<span style="color:#e6db74">}</span><span style="color:#e6db74">"))[0-9]+"</span> <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> | sed -E <span style="color:#e6db74">'s@^<a href="(gb.+.seq.gz)">.*$$@\1@'</span><span style="color:#f92672">)</span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span>SUFFIXES <span style="color:#f92672">+=</span> .d
|
|
</span></span><span style="display:flex;"><span>NODEPS<span style="color:#f92672">:=</span>clean taxonomy
|
|
</span></span><span style="display:flex;"><span>DEPFILES<span style="color:#f92672">:=</span><span style="color:#66d9ef">$(</span>wildcard Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>/depends/*.d<span style="color:#66d9ef">)</span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#960050;background-color:#1e0010">ifeq</span> <span style="color:#960050;background-color:#1e0010">(0,</span> <span style="color:#66d9ef">$(</span>words <span style="color:#66d9ef">$(</span>findstring <span style="color:#66d9ef">$(</span>MAKECMDGOALS<span style="color:#66d9ef">)</span>, <span style="color:#66d9ef">$(</span>NODEPS<span style="color:#66d9ef">)))</span><span style="color:#960050;background-color:#1e0010">)</span>
|
|
</span></span><span style="display:flex;"><span> <span style="color:#75715e">#Chances are, these files don't exist. GMake will create them and
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#75715e"></span> <span style="color:#75715e">#clean up automatically afterwards</span>
|
|
</span></span><span style="display:flex;"><span> -include <span style="color:#66d9ef">$(</span>DEPFILES<span style="color:#66d9ef">)</span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#960050;background-color:#1e0010">endif</span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">all</span><span style="color:#f92672">:</span> depends directories FORCE
|
|
</span></span><span style="display:flex;"><span> @make downloads
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">downloads</span><span style="color:#f92672">:</span> taxonomy fasta_files
|
|
</span></span><span style="display:flex;"><span> @echo Genbank Release number <span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>
|
|
</span></span><span style="display:flex;"><span> @echo all divisions : <span style="color:#66d9ef">$(</span>GBDIV_ALL<span style="color:#66d9ef">)</span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">FORCE</span><span style="color:#f92672">:</span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">.PHONY</span><span style="color:#f92672">:</span> all directories depends taxonomy fasta_files FORCE
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">depends</span><span style="color:#f92672">:</span> directories Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>/depends/gbfiles.d Makefile
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">division</span><span style="color:#f92672">:</span> <span style="color:#66d9ef">$(</span>GBDIV<span style="color:#66d9ef">)</span>
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">taxonomy</span><span style="color:#f92672">:</span> directories Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>/taxonomy
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">directories</span><span style="color:#f92672">:</span> Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>/fasta Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>/stamp Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>/tmp
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">Release_$(GBRELEASE)</span><span style="color:#f92672">:</span>
|
|
</span></span><span style="display:flex;"><span> @mkdir -p $@
|
|
</span></span><span style="display:flex;"><span> @echo Create $@ directory
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">Release_$(GBRELEASE)/fasta</span><span style="color:#f92672">:</span> Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>
|
|
</span></span><span style="display:flex;"><span> @mkdir -p $@
|
|
</span></span><span style="display:flex;"><span> @echo Create $@ directory
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">Release_$(GBRELEASE)/stamp</span><span style="color:#f92672">:</span> Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>
|
|
</span></span><span style="display:flex;"><span> @mkdir -p $@
|
|
</span></span><span style="display:flex;"><span> @echo Create $@ directory
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">Release_$(GBRELEASE)/tmp</span><span style="color:#f92672">:</span> Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>
|
|
</span></span><span style="display:flex;"><span> @mkdir -p $@
|
|
</span></span><span style="display:flex;"><span> @echo Create $@ directory
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">Release_$(GBRELEASE)/depends/gbfiles.d</span><span style="color:#f92672">:</span> Makefile
|
|
</span></span><span style="display:flex;"><span> @echo Create depends directory
|
|
</span></span><span style="display:flex;"><span> @mkdir -p Release_<span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span>/depends
|
|
</span></span><span style="display:flex;"><span> @for f in <span style="color:#e6db74">${</span>GBFILE_ALL<span style="color:#e6db74">}</span> ; <span style="color:#66d9ef">do</span> <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/stamp/</span>$$<span style="color:#e6db74">f.stamp:"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t@echo Downloading file : </span>$$<span style="color:#e6db74">f..."</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t@mkdir -p Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/tmp"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t@mkdir -p Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/stamp"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t@curl -L </span><span style="color:#e6db74">${</span>GBURL<span style="color:#e6db74">}</span><span style="color:#e6db74">/</span>$$<span style="color:#e6db74">f > Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/tmp/</span>$$<span style="color:#e6db74">f && touch \$</span>$@<span style="color:#e6db74">"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> div<span style="color:#f92672">=</span>$$<span style="color:#f92672">(</span>sed -E <span style="color:#e6db74">'s@^gb(...).*$$@\1@'</span> <span style="color:#f92672"><<<</span> $$f<span style="color:#f92672">)</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> fasta<span style="color:#f92672">=</span><span style="color:#e6db74">"Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/fasta/</span>$$<span style="color:#e6db74">div/</span>$$<span style="color:#e6db74">{f/.seq.gz/.fasta.gz}"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> fasta_fgs<span style="color:#f92672">=</span><span style="color:#e6db74">"Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/fasta_fgs/</span>$$<span style="color:#e6db74">div/</span>$$<span style="color:#e6db74">{f/.seq.gz/.fasta.gz}"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> fasta_files<span style="color:#f92672">=</span><span style="color:#e6db74">"</span>$$<span style="color:#e6db74">fasta_files </span>$$<span style="color:#e6db74">fasta"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> fasta_fgs_files<span style="color:#f92672">=</span><span style="color:#e6db74">"</span>$$<span style="color:#e6db74">fasta_fgs_files </span>$$<span style="color:#e6db74">fasta_fgs"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"</span>$$<span style="color:#e6db74">fasta: Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/stamp/</span>$$<span style="color:#e6db74">f.stamp"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t@echo converting file : \$</span>$<span style="color:#e6db74">< in fasta"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t@mkdir -p Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/fasta/</span>$$<span style="color:#e6db74">div"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t@obiconvert -Z --fasta-output --skip-empty \\"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/tmp/</span>$$<span style="color:#e6db74">f > Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/tmp/</span>$$<span style="color:#e6db74">{f/.seq.gz/.fasta.gz} \\"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t && mv Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/tmp/</span>$$<span style="color:#e6db74">{f/.seq.gz/.fasta.gz} \$</span>$@<span style="color:#e6db74"> \\"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t && rm -f Release_</span><span style="color:#66d9ef">$(</span>GBRELEASE<span style="color:#66d9ef">)</span><span style="color:#e6db74">/tmp/</span>$$<span style="color:#e6db74">f \\"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t || rm -f \$</span>$@<span style="color:#e6db74">"</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo -e <span style="color:#e6db74">"\t@echo conversion of </span>$$<span style="color:#e6db74">@ done."</span> ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> <span style="color:#66d9ef">done</span> > $@ ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo >> $@ ; <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> echo <span style="color:#e6db74">"fasta_files: </span>$$<span style="color:#e6db74">fasta_files"</span> >> $@ ;
|
|
</span></span><span style="display:flex;"><span>
|
|
</span></span><span style="display:flex;"><span><span style="color:#a6e22e">Release_$(GBRELEASE)/taxonomy</span><span style="color:#f92672">:</span>
|
|
</span></span><span style="display:flex;"><span> mkdir -p $@
|
|
</span></span><span style="display:flex;"><span> curl -iL <span style="color:#66d9ef">$(</span>TAXOURL<span style="color:#66d9ef">)</span> <span style="color:#ae81ff">\
|
|
</span></span></span><span style="display:flex;"><span><span style="color:#ae81ff"></span> | tar -C $@ -zxf -
|
|
</span></span></code></pre></td></tr></table>
|
|
</div>
|
|
</div></td>
|
|
</DIV>
|
|
</article>
|
|
|
|
|
|
|
|
<footer class="book-footer">
|
|
|
|
<div class="flex flex-wrap justify-between">
|
|
|
|
|
|
|
|
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<script>(function(){function e(e){const t=window.getSelection(),n=document.createRange();n.selectNodeContents(e),t.removeAllRanges(),t.addRange(n)}document.querySelectorAll("pre code").forEach(t=>{t.addEventListener("click",function(){if(window.getSelection().toString())return;e(t.parentElement),navigator.clipboard&&navigator.clipboard.writeText(t.parentElement.textContent)})})})()</script>
|
|
|
|
|
|
|
|
|
|
</footer>
|
|
|
|
|
|
|
|
<div class="book-comments">
|
|
|
|
</div>
|
|
|
|
|
|
|
|
<label for="menu-control" class="hidden book-menu-overlay"></label>
|
|
</div>
|
|
|
|
|
|
<aside class="book-toc">
|
|
<div class="book-toc-content">
|
|
|
|
|
|
<nav id="TableOfContents">
|
|
<ul>
|
|
<li><a href="#prepare-a-local-copy-of-genbank">Prepare a local copy of Genbank</a>
|
|
<ul>
|
|
<li><a href="#download-genbank">Download GenBank</a></li>
|
|
<li><a href="#the-makefile-script-for-downloading-genbank">The Makefile script for downloading Genbank</a></li>
|
|
</ul>
|
|
</li>
|
|
</ul>
|
|
</nav>
|
|
|
|
|
|
|
|
</div>
|
|
</aside>
|
|
|
|
</main>
|
|
|
|
|
|
</body>
|
|
</html>
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|