Files
obitools4/doc/_book/commands.html

712 lines
44 KiB
HTML
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!DOCTYPE html>
<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"><head>
<meta charset="utf-8">
<meta name="generator" content="quarto-1.2.256">
<meta name="viewport" content="width=device-width, initial-scale=1.0, user-scalable=yes">
<title>OBITools V4 - 4&nbsp; The OBITools V4 commands</title>
<style>
code{white-space: pre-wrap;}
span.smallcaps{font-variant: small-caps;}
div.columns{display: flex; gap: min(4vw, 1.5em);}
div.column{flex: auto; overflow-x: auto;}
div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
ul.task-list{list-style: none;}
ul.task-list li input[type="checkbox"] {
width: 0.8em;
margin: 0 0.8em 0.2em -1.6em;
vertical-align: middle;
}
pre > code.sourceCode { white-space: pre; position: relative; }
pre > code.sourceCode > span { display: inline-block; line-height: 1.25; }
pre > code.sourceCode > span:empty { height: 1.2em; }
.sourceCode { overflow: visible; }
code.sourceCode > span { color: inherit; text-decoration: inherit; }
div.sourceCode { margin: 1em 0; }
pre.sourceCode { margin: 0; }
@media screen {
div.sourceCode { overflow: auto; }
}
@media print {
pre > code.sourceCode { white-space: pre-wrap; }
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
}
pre.numberSource code
{ counter-reset: source-line 0; }
pre.numberSource code > span
{ position: relative; left: -4em; counter-increment: source-line; }
pre.numberSource code > span > a:first-child::before
{ content: counter(source-line);
position: relative; left: -1em; text-align: right; vertical-align: baseline;
border: none; display: inline-block;
-webkit-touch-callout: none; -webkit-user-select: none;
-khtml-user-select: none; -moz-user-select: none;
-ms-user-select: none; user-select: none;
padding: 0 4px; width: 4em;
color: #aaaaaa;
}
pre.numberSource { margin-left: 3em; border-left: 1px solid #aaaaaa; padding-left: 4px; }
div.sourceCode
{ }
@media screen {
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
}
code span.al { color: #ff0000; font-weight: bold; } /* Alert */
code span.an { color: #60a0b0; font-weight: bold; font-style: italic; } /* Annotation */
code span.at { color: #7d9029; } /* Attribute */
code span.bn { color: #40a070; } /* BaseN */
code span.bu { color: #008000; } /* BuiltIn */
code span.cf { color: #007020; font-weight: bold; } /* ControlFlow */
code span.ch { color: #4070a0; } /* Char */
code span.cn { color: #880000; } /* Constant */
code span.co { color: #60a0b0; font-style: italic; } /* Comment */
code span.cv { color: #60a0b0; font-weight: bold; font-style: italic; } /* CommentVar */
code span.do { color: #ba2121; font-style: italic; } /* Documentation */
code span.dt { color: #902000; } /* DataType */
code span.dv { color: #40a070; } /* DecVal */
code span.er { color: #ff0000; font-weight: bold; } /* Error */
code span.ex { } /* Extension */
code span.fl { color: #40a070; } /* Float */
code span.fu { color: #06287e; } /* Function */
code span.im { color: #008000; font-weight: bold; } /* Import */
code span.in { color: #60a0b0; font-weight: bold; font-style: italic; } /* Information */
code span.kw { color: #007020; font-weight: bold; } /* Keyword */
code span.op { color: #666666; } /* Operator */
code span.ot { color: #007020; } /* Other */
code span.pp { color: #bc7a00; } /* Preprocessor */
code span.sc { color: #4070a0; } /* SpecialChar */
code span.ss { color: #bb6688; } /* SpecialString */
code span.st { color: #4070a0; } /* String */
code span.va { color: #19177c; } /* Variable */
code span.vs { color: #4070a0; } /* VerbatimString */
code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warning */
div.csl-bib-body { }
div.csl-entry {
clear: both;
}
.hanging div.csl-entry {
margin-left:2em;
text-indent:-2em;
}
div.csl-left-margin {
min-width:2em;
float:left;
}
div.csl-right-inline {
margin-left:2em;
padding-left:1em;
}
div.csl-indent {
margin-left: 2em;
}
</style>
<script src="site_libs/quarto-nav/quarto-nav.js"></script>
<script src="site_libs/quarto-nav/headroom.min.js"></script>
<script src="site_libs/clipboard/clipboard.min.js"></script>
<script src="site_libs/quarto-search/autocomplete.umd.js"></script>
<script src="site_libs/quarto-search/fuse.min.js"></script>
<script src="site_libs/quarto-search/quarto-search.js"></script>
<meta name="quarto:offset" content="./">
<link href="./library.html" rel="next">
<link href="./tutorial.html" rel="prev">
<script src="site_libs/quarto-html/quarto.js"></script>
<script src="site_libs/quarto-html/popper.min.js"></script>
<script src="site_libs/quarto-html/tippy.umd.min.js"></script>
<script src="site_libs/quarto-html/anchor.min.js"></script>
<link href="site_libs/quarto-html/tippy.css" rel="stylesheet">
<link href="site_libs/quarto-html/quarto-syntax-highlighting.css" rel="stylesheet" id="quarto-text-highlighting-styles">
<script src="site_libs/bootstrap/bootstrap.min.js"></script>
<link href="site_libs/bootstrap/bootstrap-icons.css" rel="stylesheet">
<link href="site_libs/bootstrap/bootstrap.min.css" rel="stylesheet" id="quarto-bootstrap" data-mode="light">
<script id="quarto-search-options" type="application/json">{
"location": "sidebar",
"copy-button": false,
"collapse-after": 3,
"panel-placement": "start",
"type": "textbox",
"limit": 20,
"language": {
"search-no-results-text": "No results",
"search-matching-documents-text": "matching documents",
"search-copy-link-title": "Copy link to search",
"search-hide-matches-text": "Hide additional matches",
"search-more-match-text": "more match in this document",
"search-more-matches-text": "more matches in this document",
"search-clear-button-title": "Clear",
"search-detached-cancel-button-title": "Cancel",
"search-submit-button-title": "Submit"
}
}</script>
<script src="https://cdn.jsdelivr.net/npm/mathjax@3/es5/tex-chtml-full.js" type="text/javascript"></script>
</head>
<body class="nav-sidebar floating">
<div id="quarto-search-results"></div>
<header id="quarto-header" class="headroom fixed-top">
<nav class="quarto-secondary-nav" data-bs-toggle="collapse" data-bs-target="#quarto-sidebar" aria-controls="quarto-sidebar" aria-expanded="false" aria-label="Toggle sidebar navigation" onclick="if (window.quartoToggleHeadroom) { window.quartoToggleHeadroom(); }">
<div class="container-fluid d-flex justify-content-between">
<h1 class="quarto-secondary-nav-title"><span class="chapter-number">4</span>&nbsp; <span class="chapter-title">The <em>OBITools V4</em> commands</span></h1>
<button type="button" class="quarto-btn-toggle btn" aria-label="Show secondary navigation">
<i class="bi bi-chevron-right"></i>
</button>
</div>
</nav>
</header>
<!-- content -->
<div id="quarto-content" class="quarto-container page-columns page-rows-contents page-layout-article">
<!-- sidebar -->
<nav id="quarto-sidebar" class="sidebar collapse sidebar-navigation floating overflow-auto">
<div class="pt-lg-2 mt-2 text-left sidebar-header">
<div class="sidebar-title mb-0 py-0">
<a href="./">OBITools V4</a>
</div>
</div>
<div class="mt-2 flex-shrink-0 align-items-center">
<div class="sidebar-search">
<div id="quarto-search" class="" title="Search"></div>
</div>
</div>
<div class="sidebar-menu-container">
<ul class="list-unstyled mt-1">
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="./index.html" class="sidebar-item-text sidebar-link">Preface</a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="./intro.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">1</span>&nbsp; <span class="chapter-title">The OBITools</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="./formats.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">2</span>&nbsp; <span class="chapter-title">File formats usable with <em>OBITools</em></span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="./tutorial.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">3</span>&nbsp; <span class="chapter-title">OBITools V4 Tutorial</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="./commands.html" class="sidebar-item-text sidebar-link active"><span class="chapter-number">4</span>&nbsp; <span class="chapter-title">The <em>OBITools V4</em> commands</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="./library.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">5</span>&nbsp; <span class="chapter-title">The GO <em>OBITools</em> library</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="./annexes.html" class="sidebar-item-text sidebar-link"><span class="chapter-number">6</span>&nbsp; <span class="chapter-title">Annexes</span></a>
</div>
</li>
<li class="sidebar-item">
<div class="sidebar-item-container">
<a href="./references.html" class="sidebar-item-text sidebar-link">References</a>
</div>
</li>
</ul>
</div>
</nav>
<!-- margin-sidebar -->
<div id="quarto-margin-sidebar" class="sidebar margin-sidebar">
<nav id="TOC" role="doc-toc" class="toc-active">
<h2 id="toc-title">Table of contents</h2>
<ul>
<li><a href="#specifying-the-input-files-to-obitools-commands" id="toc-specifying-the-input-files-to-obitools-commands" class="nav-link active" data-scroll-target="#specifying-the-input-files-to-obitools-commands"><span class="toc-section-number">4.1</span> Specifying the input files to <em>OBITools</em> commands</a></li>
<li><a href="#options-common-to-most-of-the-obitools-commands" id="toc-options-common-to-most-of-the-obitools-commands" class="nav-link" data-scroll-target="#options-common-to-most-of-the-obitools-commands"><span class="toc-section-number">4.2</span> Options common to most of the <em>OBITools</em> commands</a>
<ul class="collapse">
<li><a href="#specifying-input-format" id="toc-specifying-input-format" class="nav-link" data-scroll-target="#specifying-input-format"><span class="toc-section-number">4.2.1</span> Specifying input format</a></li>
<li><a href="#specifying-output-format" id="toc-specifying-output-format" class="nav-link" data-scroll-target="#specifying-output-format"><span class="toc-section-number">4.2.2</span> Specifying output format</a></li>
<li><a href="#the-fasta-and-fastq-annotations-format" id="toc-the-fasta-and-fastq-annotations-format" class="nav-link" data-scroll-target="#the-fasta-and-fastq-annotations-format"><span class="toc-section-number">4.2.3</span> The Fasta and Fastq annotations format</a></li>
</ul></li>
<li><a href="#obitools-expression-language" id="toc-obitools-expression-language" class="nav-link" data-scroll-target="#obitools-expression-language"><span class="toc-section-number">4.3</span> OBITools expression language</a>
<ul class="collapse">
<li><a href="#variables-usable-in-the-expression" id="toc-variables-usable-in-the-expression" class="nav-link" data-scroll-target="#variables-usable-in-the-expression"><span class="toc-section-number">4.3.1</span> Variables usable in the expression</a></li>
<li><a href="#function-defined-in-the-language" id="toc-function-defined-in-the-language" class="nav-link" data-scroll-target="#function-defined-in-the-language"><span class="toc-section-number">4.3.2</span> Function defined in the language</a></li>
<li><a href="#accessing-to-the-sequence-annotations" id="toc-accessing-to-the-sequence-annotations" class="nav-link" data-scroll-target="#accessing-to-the-sequence-annotations"><span class="toc-section-number">4.3.3</span> Accessing to the sequence annotations</a></li>
</ul></li>
<li><a href="#metabarcode-design-and-quality-assessment" id="toc-metabarcode-design-and-quality-assessment" class="nav-link" data-scroll-target="#metabarcode-design-and-quality-assessment"><span class="toc-section-number">4.4</span> Metabarcode design and quality assessment</a>
<ul class="collapse">
<li><a href="#obipcr" id="toc-obipcr" class="nav-link" data-scroll-target="#obipcr"><span class="toc-section-number">4.4.1</span> <code>obipcr</code></a></li>
</ul></li>
<li><a href="#file-format-conversions" id="toc-file-format-conversions" class="nav-link" data-scroll-target="#file-format-conversions"><span class="toc-section-number">4.5</span> File format conversions</a>
<ul class="collapse">
<li><a href="#obiconvert" id="toc-obiconvert" class="nav-link" data-scroll-target="#obiconvert"><span class="toc-section-number">4.5.1</span> <code>obiconvert</code></a></li>
</ul></li>
<li><a href="#sequence-annotations" id="toc-sequence-annotations" class="nav-link" data-scroll-target="#sequence-annotations"><span class="toc-section-number">4.6</span> Sequence annotations</a>
<ul class="collapse">
<li><a href="#obiannotate" id="toc-obiannotate" class="nav-link" data-scroll-target="#obiannotate"><span class="toc-section-number">4.6.1</span> <code>obiannotate</code></a></li>
<li><a href="#obitag" id="toc-obitag" class="nav-link" data-scroll-target="#obitag"><span class="toc-section-number">4.6.2</span> <code>obitag</code></a></li>
</ul></li>
<li><a href="#computations-on-sequences" id="toc-computations-on-sequences" class="nav-link" data-scroll-target="#computations-on-sequences"><span class="toc-section-number">4.7</span> Computations on sequences</a>
<ul class="collapse">
<li><a href="#obipairing" id="toc-obipairing" class="nav-link" data-scroll-target="#obipairing"><span class="toc-section-number">4.7.1</span> <code>obipairing</code></a></li>
<li><a href="#obimultiplex" id="toc-obimultiplex" class="nav-link" data-scroll-target="#obimultiplex"><span class="toc-section-number">4.7.2</span> <code>obimultiplex</code></a></li>
<li><a href="#obicomplement" id="toc-obicomplement" class="nav-link" data-scroll-target="#obicomplement"><span class="toc-section-number">4.7.3</span> <code>obicomplement</code></a></li>
<li><a href="#obiclean" id="toc-obiclean" class="nav-link" data-scroll-target="#obiclean"><span class="toc-section-number">4.7.4</span> <code>obiclean</code></a></li>
<li><a href="#obiuniq" id="toc-obiuniq" class="nav-link" data-scroll-target="#obiuniq"><span class="toc-section-number">4.7.5</span> <code>obiuniq</code></a></li>
</ul></li>
<li><a href="#sequence-sampling-and-filtering" id="toc-sequence-sampling-and-filtering" class="nav-link" data-scroll-target="#sequence-sampling-and-filtering"><span class="toc-section-number">4.8</span> Sequence sampling and filtering</a>
<ul class="collapse">
<li><a href="#obigrep" id="toc-obigrep" class="nav-link" data-scroll-target="#obigrep"><span class="toc-section-number">4.8.1</span> <code>obigrep</code></a></li>
</ul></li>
<li><a href="#utilities" id="toc-utilities" class="nav-link" data-scroll-target="#utilities"><span class="toc-section-number">4.9</span> Utilities</a>
<ul class="collapse">
<li><a href="#obicount" id="toc-obicount" class="nav-link" data-scroll-target="#obicount"><span class="toc-section-number">4.9.1</span> <code>obicount</code></a></li>
<li><a href="#obidistribute" id="toc-obidistribute" class="nav-link" data-scroll-target="#obidistribute"><span class="toc-section-number">4.9.2</span> <code>obidistribute</code></a></li>
<li><a href="#obifind" id="toc-obifind" class="nav-link" data-scroll-target="#obifind"><span class="toc-section-number">4.9.3</span> <code>obifind</code></a></li>
</ul></li>
</ul>
</nav>
</div>
<!-- main -->
<main class="content" id="quarto-document-content">
<header id="title-block-header" class="quarto-title-block default">
<div class="quarto-title">
<h1 class="title d-none d-lg-block"><span class="chapter-number">4</span>&nbsp; <span class="chapter-title">The <em>OBITools V4</em> commands</span></h1>
</div>
<div class="quarto-title-meta">
</div>
</header>
<section id="specifying-the-input-files-to-obitools-commands" class="level2" data-number="4.1">
<h2 data-number="4.1" class="anchored" data-anchor-id="specifying-the-input-files-to-obitools-commands"><span class="header-section-number">4.1</span> Specifying the input files to <em>OBITools</em> commands</h2>
</section>
<section id="options-common-to-most-of-the-obitools-commands" class="level2" data-number="4.2">
<h2 data-number="4.2" class="anchored" data-anchor-id="options-common-to-most-of-the-obitools-commands"><span class="header-section-number">4.2</span> Options common to most of the <em>OBITools</em> commands</h2>
<section id="specifying-input-format" class="level3" data-number="4.2.1">
<h3 data-number="4.2.1" class="anchored" data-anchor-id="specifying-input-format"><span class="header-section-number">4.2.1</span> Specifying input format</h3>
<p>Five sequence formats are accepted for input files. <em>Fasta</em> (<a href="formats.html#sec-fasta"><span>Section&nbsp;2.1.2</span></a>) and <em>Fastq</em> (<a href="formats.html#sec-fastq"><span>Section&nbsp;2.1.3</span></a>) are the main ones, EMBL and Genbank allow the use of flat files produced by these two international databases. The last one, ecoPCR, is maintained for compatibility with previous <em>OBITools</em> and allows to read <em>ecoPCR</em> outputs as sequence files.</p>
<ul>
<li><code>--ecopcr</code> : Read data following the <em>ecoPCR</em> output format.</li>
<li><code>--embl</code> Read data following the <em>EMBL</em> flatfile format.</li>
<li><code>--genbank</code> Read data following the <em>Genbank</em> flatfile format.</li>
</ul>
<p>Several encoding schemes have been proposed for quality scores in <em>Fastq</em> format. Currently, <em>OBITools</em> considers Sanger encoding as the standard. For reasons of compatibility with older datasets produced with <em>Solexa</em> sequencers, it is possible, by using the following option, to force the use of the corresponding quality encoding scheme when reading these older files.</p>
<ul>
<li><code>--solexa</code> Decodes quality string according to the Solexa specification. (default: false)</li>
</ul>
</section>
<section id="specifying-output-format" class="level3" data-number="4.2.2">
<h3 data-number="4.2.2" class="anchored" data-anchor-id="specifying-output-format"><span class="header-section-number">4.2.2</span> Specifying output format</h3>
<p>Only two output sequence formats are supported by OBITools, Fasta and Fastq. Fastq is used when output sequences are associated with quality information. Otherwise, Fasta is the default format. However, it is possible to force the output format by using one of the following two options. Forcing the use of Fasta results in the loss of quality information. Conversely, when the Fastq format is forced with sequences that have no quality data, dummy qualities set to 40 for each nucleotide are added.</p>
<ul>
<li><code>--fasta-output</code> Read data following the ecoPCR output format.</li>
<li><code>--fastq-output</code> Read data following the EMBL flatfile format.</li>
</ul>
<p>OBITools allows multiple input files to be specified for a single command.</p>
<ul>
<li><code>--no-order</code> When several input files are provided, indicates that there is no order among them. (default: false). Using such option can increase a lot the processing of the data.</li>
</ul>
</section>
<section id="the-fasta-and-fastq-annotations-format" class="level3" data-number="4.2.3">
<h3 data-number="4.2.3" class="anchored" data-anchor-id="the-fasta-and-fastq-annotations-format"><span class="header-section-number">4.2.3</span> The Fasta and Fastq annotations format</h3>
<p>OBITools extend the <a href="#the-fasta-sequence-format">Fasta</a> and <a href="#the-fastq-sequence-format">Fastq</a> formats by introducing a format for the title lines of these formats allowing to annotate every sequence. While the previous version of OBITools used an <em>ad-hoc</em> format for these annotation, this new version introduce the usage of the standard JSON format to store them.</p>
<p>On input, OBITools automatically recognize the format of the annotations, but two options allows to force the parsing following one of them. You should normally not need to use these options.</p>
<ul>
<li><p><code>--input-OBI-header</code> FASTA/FASTQ title line annotations follow OBI format. (default: false)</p></li>
<li><p><code>--input-json-header</code> FASTA/FASTQ title line annotations follow json format. (default: false)</p></li>
</ul>
<p>On output, by default annotation are formatted using the new JSON format. For compatibility with previous version of OBITools and with external scripts and software, it is possible to force the usage of the previous OBITools format.</p>
<ul>
<li><p><code>--output-OBI-header|-O</code> output FASTA/FASTQ title line annotations follow OBI format. (default: false)</p></li>
<li><p><code>--output-json-header</code> output FASTA/FASTQ title line annotations follow json format. (default: false)</p></li>
</ul>
<section id="system-related-options" class="level4" data-number="4.2.3.1">
<h4 data-number="4.2.3.1" class="anchored" data-anchor-id="system-related-options"><span class="header-section-number">4.2.3.1</span> System related options</h4>
<ul>
<li><code>--debug</code> (default: false)</li>
<li><code>--help\|-h\|-?</code> (default: false)</li>
<li><code>--max-cpu &lt;int&gt;</code> Number of parallele threads computing the result (default: 10)</li>
<li><code>--workers\|-w &lt;int&gt;</code> Number of parallele threads computing the result (default: 9)</li>
</ul>
</section>
</section>
</section>
<section id="obitools-expression-language" class="level2" data-number="4.3">
<h2 data-number="4.3" class="anchored" data-anchor-id="obitools-expression-language"><span class="header-section-number">4.3</span> OBITools expression language</h2>
<p>Several OBITools (<em>e.g.</em> obigrep, obiannotate) allow the user to specify some simple expressions to compute values or define predicates. This expressions are parsed and evaluated using the <a href="https://pkg.go.dev/github.com/PaesslerAG/gval" title="Gval (Go eVALuate) for evaluating arbitrary expressions Go-like expressions.">gval</a> go package, which allows for evaluating go-Like expression.</p>
<section id="variables-usable-in-the-expression" class="level3" data-number="4.3.1">
<h3 data-number="4.3.1" class="anchored" data-anchor-id="variables-usable-in-the-expression"><span class="header-section-number">4.3.1</span> Variables usable in the expression</h3>
<ul>
<li><code>sequence</code> is the sequence object on which the expression is evaluated.</li>
<li><code>annotations</code>is a map object containing every annotations associated to the currently processed sequence.</li>
</ul>
</section>
<section id="function-defined-in-the-language" class="level3" data-number="4.3.2">
<h3 data-number="4.3.2" class="anchored" data-anchor-id="function-defined-in-the-language"><span class="header-section-number">4.3.2</span> Function defined in the language</h3>
<section id="instrospection-functions" class="level4 unnumbered">
<h4 class="unnumbered anchored" data-anchor-id="instrospection-functions">Instrospection functions</h4>
<ul>
<li><code>len(x)</code>is a generic function allowing to retreive the size of a object. It returns the length of a sequences, the number of element in a map like <code>annotations</code>, the number of elements in an array. The reurned value is an <code>int</code>.</li>
</ul>
</section>
<section id="cast-functions" class="level4 unnumbered">
<h4 class="unnumbered anchored" data-anchor-id="cast-functions">Cast functions</h4>
<ul>
<li><code>int(x)</code> converts if possible the <code>x</code> value to an integer value. The function returns an <code>int</code>.</li>
<li><code>numeric(x)</code> converts if possible the <code>x</code> value to a float value. The function returns a <code>float</code>.</li>
<li><code>bool(x)</code> converts if possible the <code>x</code> value to a boolean value. The function returns a <code>bool</code>.</li>
</ul>
</section>
<section id="string-related-functions" class="level4 unnumbered">
<h4 class="unnumbered anchored" data-anchor-id="string-related-functions">String related functions</h4>
<ul>
<li><code>printf(format,...)</code> allows to combine several values to build a string. <code>format</code> follows the classical C <code>printf</code> syntax. The function returns a <code>string</code>.</li>
<li><code>subspc(x)</code> substitutes every space in the <code>x</code> string by the underscore (<code>_</code>) character. The function returns a <code>string</code>.</li>
</ul>
</section>
</section>
<section id="accessing-to-the-sequence-annotations" class="level3" data-number="4.3.3">
<h3 data-number="4.3.3" class="anchored" data-anchor-id="accessing-to-the-sequence-annotations"><span class="header-section-number">4.3.3</span> Accessing to the sequence annotations</h3>
<p>The <code>annotations</code> variable is a map object containing all the annotations associated to the currently processed sequence. Index of the map are the attribute names. It exists to possibillities to retreive an annotation. It is possible to use the classical <code>[]</code> indexing operator, putting the attribute name quoted by double quotes between them.</p>
<div class="sourceCode" id="cb1"><pre class="sourceCode go code-with-copy"><code class="sourceCode go"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a>annotations<span class="op">[</span><span class="st">"direction"</span><span class="op">]</span></span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>The above code retreives the <code>direction</code> annotation. A second notation using the dot (<code>.</code>) is often more convenient.</p>
<div class="sourceCode" id="cb2"><pre class="sourceCode go code-with-copy"><code class="sourceCode go"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>annotations<span class="op">.</span>direction</span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Special attributes of the sequence are accessible only by dedicated methods of the <code>sequence</code> object.</p>
<ul>
<li>The sequence identifier : <code>Id()</code></li>
<li>THe sequence definition : <code>Definition()</code></li>
</ul>
</section>
</section>
<section id="metabarcode-design-and-quality-assessment" class="level2" data-number="4.4">
<h2 data-number="4.4" class="anchored" data-anchor-id="metabarcode-design-and-quality-assessment"><span class="header-section-number">4.4</span> Metabarcode design and quality assessment</h2>
<section id="obipcr" class="level3" data-number="4.4.1">
<h3 data-number="4.4.1" class="anchored" data-anchor-id="obipcr"><span class="header-section-number">4.4.1</span> <code>obipcr</code></h3>
<blockquote class="blockquote">
<p>Replace the <code>ecoPCR</code> original <em>OBITools</em></p>
</blockquote>
</section>
</section>
<section id="file-format-conversions" class="level2" data-number="4.5">
<h2 data-number="4.5" class="anchored" data-anchor-id="file-format-conversions"><span class="header-section-number">4.5</span> File format conversions</h2>
<section id="obiconvert" class="level3" data-number="4.5.1">
<h3 data-number="4.5.1" class="anchored" data-anchor-id="obiconvert"><span class="header-section-number">4.5.1</span> <code>obiconvert</code></h3>
</section>
</section>
<section id="sequence-annotations" class="level2" data-number="4.6">
<h2 data-number="4.6" class="anchored" data-anchor-id="sequence-annotations"><span class="header-section-number">4.6</span> Sequence annotations</h2>
<section id="obiannotate" class="level3" data-number="4.6.1">
<h3 data-number="4.6.1" class="anchored" data-anchor-id="obiannotate"><span class="header-section-number">4.6.1</span> <code>obiannotate</code></h3>
</section>
<section id="obitag" class="level3" data-number="4.6.2">
<h3 data-number="4.6.2" class="anchored" data-anchor-id="obitag"><span class="header-section-number">4.6.2</span> <code>obitag</code></h3>
</section>
</section>
<section id="computations-on-sequences" class="level2" data-number="4.7">
<h2 data-number="4.7" class="anchored" data-anchor-id="computations-on-sequences"><span class="header-section-number">4.7</span> Computations on sequences</h2>
<section id="obipairing" class="level3" data-number="4.7.1">
<h3 data-number="4.7.1" class="anchored" data-anchor-id="obipairing"><span class="header-section-number">4.7.1</span> <code>obipairing</code></h3>
<blockquote class="blockquote">
<p>Replace the <code>illuminapairedends</code> original <em>OBITools</em></p>
</blockquote>
<section id="alignment-procedure" class="level4 unnumbered">
<h4 class="unnumbered anchored" data-anchor-id="alignment-procedure">Alignment procedure</h4>
<p><code>obipairing</code> is introducing a new alignment algorithm compared to the <code>illuminapairedend</code> command of the <code>OBITools V2</code>. Nethertheless this new algorithm has been design to produce the same results than the previous, except in very few cases.</p>
<p>The new algorithm is a two-step procedure. First, a FASTN-type algorithm <span class="citation" data-cites="Lipman1985-hw">(<a href="references.html#ref-Lipman1985-hw" role="doc-biblioref">Lipman and Pearson 1985</a>)</span> identifies the best offset between the two matched readings. This identifies the region of overlap.</p>
<p>In the second step, the matching regions of the two reads are extracted along with a flanking sequence of <span class="math inline">\(\Delta\)</span> base pairs. The two subsequences are then aligned using a “one side free end-gap” dynamic programming algorithm. This latter step is only called if at least one mismatch is detected by the FASTP step.</p>
<p>Unless the similarity between the two reads at their overlap region is very low, the addition of the flanking regions in the second step of the alignment ensures the same alignment as if the dynamic programming alignment was performed on the full reads.</p>
</section>
<section id="the-scoring-system" class="level4 unnumbered">
<h4 class="unnumbered anchored" data-anchor-id="the-scoring-system">The scoring system</h4>
<p>In the dynamic programming step, the match and mismatch scores take into account the quality scores of the two aligned nucleotides. By taking these into account, the probability of a true match can be calculated for each aligned base pair.</p>
<p>If we consider a nucleotide read with a quality score <span class="math inline">\(Q\)</span>, the probability of misreading this base (<span class="math inline">\(P_E\)</span>) is : <span class="math display">\[
P_E = 10^{-\frac{Q}{10}}
\]</span></p>
<p>Thus, when a given nucleotide <span class="math inline">\(X\)</span> is observed with the quality score <span class="math inline">\(Q\)</span>. The probability that <span class="math inline">\(X\)</span> is really an <span class="math inline">\(X\)</span> is :</p>
<p><span class="math display">\[
P(X=X) = 1 - P_E
\]</span></p>
<p>Otherwise, <span class="math inline">\(X\)</span> is actually one of the three other possible nucleotides (<span class="math inline">\(X_{E1}\)</span>, <span class="math inline">\(X_{E2}\)</span> or <span class="math inline">\(X_{E3}\)</span>). If we suppose that the three reading error have the same probability :</p>
<p><span class="math display">\[
P(X=X_{E1}) = P(X=X_{E3}) = P(X=X_{E3}) = \frac{P_E}{3}
\]</span></p>
<p>At each position in an alignment where the two nucleotides <span class="math inline">\(X_1\)</span> and <span class="math inline">\(X_2\)</span> face each other (not a gapped position), the probability of a true match varies depending on whether <span class="math inline">\(X_1=X_2\)</span>, an observed match, or <span class="math inline">\(X_1 \neq X_2\)</span>, an observed mismatch.</p>
<p><strong>Probability of a true match when <span class="math inline">\(X_1=X_2\)</span></strong></p>
<p>That probability can be divided in two parts. First <span class="math inline">\(X_1\)</span> and <span class="math inline">\(X_2\)</span> have been correctly read. The corresponding probability is :</p>
<p><span class="math display">\[
\begin{aligned}
P_{TM} &amp;= (1- PE_1)(1-PE_2)\\
&amp;=(1 - 10^{-\frac{Q_1}{10} } )(1 - 10^{-\frac{Q_2}{10}} )
\end{aligned}
\]</span></p>
<p>Secondly, a match can occure if the true nucleotides read as <span class="math inline">\(X_1\)</span> and <span class="math inline">\(X_2\)</span> are not <span class="math inline">\(X_1\)</span> and <span class="math inline">\(X_2\)</span> but identical.</p>
<p><span class="math display">\[
\begin{aligned}
P(X_1==X_{E1}) \cap P(X_2==X_{E1}) &amp;= \frac{P_{E1} P_{E2}}{9} \\
P(X_1==X_{Ex}) \cap P(X_2==X_{Ex}) &amp; = \frac{P_{E1} P_{E2}}{3}
\end{aligned}
\]</span></p>
<p>The probability of a true match between <span class="math inline">\(X_1\)</span> and <span class="math inline">\(X_2\)</span> when <span class="math inline">\(X_1 = X_2\)</span> an observed match :</p>
<p><span class="math display">\[
\begin{aligned}
P(MATCH | X_1 = X_2) = (1- PE_1)(1-PE_2) + \frac{P_{E1} P_{E2}}{3}
\end{aligned}
\]</span></p>
<p><strong>Probability of a true match when <span class="math inline">\(X_1 \neq X_2\)</span></strong></p>
<p>That probability can be divided in three parts.</p>
<ol type="a">
<li><span class="math inline">\(X_1\)</span> has been correctly read and <span class="math inline">\(X_2\)</span> is a sequencing error and is actually equal to <span class="math inline">\(X_1\)</span>. <span class="math display">\[
P_a = (1-P_{E1})\frac{P_{E2}}{3}
\]</span></li>
<li><span class="math inline">\(X_2\)</span> has been correctly read and <span class="math inline">\(X_1\)</span> is a sequencing error and is actually equal to <span class="math inline">\(X_2\)</span>. <span class="math display">\[
P_b = (1-P_{E2})\frac{P_{E1}}{3}
\]</span></li>
<li><span class="math inline">\(X_1\)</span> and <span class="math inline">\(X_2\)</span> corresponds to sequencing error but are actually the same base <span class="math inline">\(X_{Ex}\)</span> <span class="math display">\[
P_c = 2\frac{P_{E1} P_{E2}}{9}
\]</span></li>
</ol>
<p>Consequently : <span class="math display">\[
\begin{aligned}
P(MATCH | X_1 \neq X_2) = (1-P_{E1})\frac{P_{E2}}{3} + (1-P_{E2})\frac{P_{E1}}{3} + 2\frac{P_{E1} P_{E2}}{9}
\end{aligned}
\]</span></p>
<p><strong>Probability of a match under the random model</strong></p>
<p>The second considered model is a pure random model where every base is equiprobable, hence having a probability of occurrence of a nucleotide equals <span class="math inline">\(0.25\)</span>. Under that hypothesis</p>
<p><span class="math display">\[
P(MATCH | \text{Random model}) = 0.25
\]</span></p>
<p><strong>The score is a log ration of likelyhood</strong></p>
<p>Score is define as the logarithm of the ratio between the likelyhood of the observations considering the sequencer error model over tha likelyhood u</p>
<div class="cell">
<div class="cell-output-display">
<div class="quarto-figure quarto-figure-center">
<figure class="figure">
<p><img src="commands_files/figure-html/unnamed-chunk-1-1.png" class="img-fluid figure-img" width="672"></p>
<p></p><figcaption class="figure-caption">Evolution of the match and mismatch scores when the quality of base is 20 while the second range from 10 to 40.</figcaption><p></p>
</figure>
</div>
</div>
</div>
</section>
</section>
<section id="obimultiplex" class="level3" data-number="4.7.2">
<h3 data-number="4.7.2" class="anchored" data-anchor-id="obimultiplex"><span class="header-section-number">4.7.2</span> <code>obimultiplex</code></h3>
<blockquote class="blockquote">
<p>Replace the <code>ngsfilter</code> original <em>OBITools</em></p>
</blockquote>
</section>
<section id="obicomplement" class="level3" data-number="4.7.3">
<h3 data-number="4.7.3" class="anchored" data-anchor-id="obicomplement"><span class="header-section-number">4.7.3</span> <code>obicomplement</code></h3>
</section>
<section id="obiclean" class="level3" data-number="4.7.4">
<h3 data-number="4.7.4" class="anchored" data-anchor-id="obiclean"><span class="header-section-number">4.7.4</span> <code>obiclean</code></h3>
</section>
<section id="obiuniq" class="level3" data-number="4.7.5">
<h3 data-number="4.7.5" class="anchored" data-anchor-id="obiuniq"><span class="header-section-number">4.7.5</span> <code>obiuniq</code></h3>
</section>
</section>
<section id="sequence-sampling-and-filtering" class="level2" data-number="4.8">
<h2 data-number="4.8" class="anchored" data-anchor-id="sequence-sampling-and-filtering"><span class="header-section-number">4.8</span> Sequence sampling and filtering</h2>
<section id="obigrep" class="level3" data-number="4.8.1">
<h3 data-number="4.8.1" class="anchored" data-anchor-id="obigrep"><span class="header-section-number">4.8.1</span> <code>obigrep</code></h3>
</section>
</section>
<section id="utilities" class="level2" data-number="4.9">
<h2 data-number="4.9" class="anchored" data-anchor-id="utilities"><span class="header-section-number">4.9</span> Utilities</h2>
<section id="obicount" class="level3" data-number="4.9.1">
<h3 data-number="4.9.1" class="anchored" data-anchor-id="obicount"><span class="header-section-number">4.9.1</span> <code>obicount</code></h3>
<p><code>obicount</code> counts the number of sequence records, the sum of the <code>count</code> attributes, and the sum of the length of all the sequences.</p>
<p><em>Example:</em></p>
<div class="sourceCode" id="cb3"><pre class="sourceCode bash code-with-copy"><code class="sourceCode bash"><span id="cb3-1"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a><span class="ex">obicount</span> seq.fasta </span></code><button title="Copy to Clipboard" class="code-copy-button"><i class="bi"></i></button></pre></div>
<p>Prints the number of sequence records contained in the <code>seq.fasta</code> file and the sum of their <code>count</code> attributes.</p>
<p><em>Options specific to the command</em></p>
<ul>
<li><code>--reads|-r</code> Prints read counts.</li>
<li><code>--symbols|-s</code> Prints symbol counts.</li>
<li><code>--variants|-v</code> Prints variant counts.</li>
</ul>
</section>
<section id="obidistribute" class="level3" data-number="4.9.2">
<h3 data-number="4.9.2" class="anchored" data-anchor-id="obidistribute"><span class="header-section-number">4.9.2</span> <code>obidistribute</code></h3>
</section>
<section id="obifind" class="level3" data-number="4.9.3">
<h3 data-number="4.9.3" class="anchored" data-anchor-id="obifind"><span class="header-section-number">4.9.3</span> <code>obifind</code></h3>
<blockquote class="blockquote">
<p>Replace the <code>ecofind</code> original <em>OBITools.</em></p>
</blockquote>
<div id="refs" class="references csl-bib-body hanging-indent" role="doc-bibliography" style="display: none">
<div id="ref-Lipman1985-hw" class="csl-entry" role="doc-biblioentry">
Lipman, D J, and W R Pearson. 1985. <span><span class="nocase">Rapid and sensitive protein similarity searches</span>.”</span> <em>Science</em> 227 (4693): 143541. <a href="http://www.ncbi.nlm.nih.gov/pubmed/2983426">http://www.ncbi.nlm.nih.gov/pubmed/2983426</a>.
</div>
</div>
</section>
</section>
</main> <!-- /main -->
<script id="quarto-html-after-body" type="application/javascript">
window.document.addEventListener("DOMContentLoaded", function (event) {
const toggleBodyColorMode = (bsSheetEl) => {
const mode = bsSheetEl.getAttribute("data-mode");
const bodyEl = window.document.querySelector("body");
if (mode === "dark") {
bodyEl.classList.add("quarto-dark");
bodyEl.classList.remove("quarto-light");
} else {
bodyEl.classList.add("quarto-light");
bodyEl.classList.remove("quarto-dark");
}
}
const toggleBodyColorPrimary = () => {
const bsSheetEl = window.document.querySelector("link#quarto-bootstrap");
if (bsSheetEl) {
toggleBodyColorMode(bsSheetEl);
}
}
toggleBodyColorPrimary();
const icon = "";
const anchorJS = new window.AnchorJS();
anchorJS.options = {
placement: 'right',
icon: icon
};
anchorJS.add('.anchored');
const clipboard = new window.ClipboardJS('.code-copy-button', {
target: function(trigger) {
return trigger.previousElementSibling;
}
});
clipboard.on('success', function(e) {
// button target
const button = e.trigger;
// don't keep focus
button.blur();
// flash "checked"
button.classList.add('code-copy-button-checked');
var currentTitle = button.getAttribute("title");
button.setAttribute("title", "Copied!");
let tooltip;
if (window.bootstrap) {
button.setAttribute("data-bs-toggle", "tooltip");
button.setAttribute("data-bs-placement", "left");
button.setAttribute("data-bs-title", "Copied!");
tooltip = new bootstrap.Tooltip(button,
{ trigger: "manual",
customClass: "code-copy-button-tooltip",
offset: [0, -8]});
tooltip.show();
}
setTimeout(function() {
if (tooltip) {
tooltip.hide();
button.removeAttribute("data-bs-title");
button.removeAttribute("data-bs-toggle");
button.removeAttribute("data-bs-placement");
}
button.setAttribute("title", currentTitle);
button.classList.remove('code-copy-button-checked');
}, 1000);
// clear code selection
e.clearSelection();
});
function tippyHover(el, contentFn) {
const config = {
allowHTML: true,
content: contentFn,
maxWidth: 500,
delay: 100,
arrow: false,
appendTo: function(el) {
return el.parentElement;
},
interactive: true,
interactiveBorder: 10,
theme: 'quarto',
placement: 'bottom-start'
};
window.tippy(el, config);
}
const noterefs = window.document.querySelectorAll('a[role="doc-noteref"]');
for (var i=0; i<noterefs.length; i++) {
const ref = noterefs[i];
tippyHover(ref, function() {
// use id or data attribute instead here
let href = ref.getAttribute('data-footnote-href') || ref.getAttribute('href');
try { href = new URL(href).hash; } catch {}
const id = href.replace(/^#\/?/, "");
const note = window.document.getElementById(id);
return note.innerHTML;
});
}
const findCites = (el) => {
const parentEl = el.parentElement;
if (parentEl) {
const cites = parentEl.dataset.cites;
if (cites) {
return {
el,
cites: cites.split(' ')
};
} else {
return findCites(el.parentElement)
}
} else {
return undefined;
}
};
var bibliorefs = window.document.querySelectorAll('a[role="doc-biblioref"]');
for (var i=0; i<bibliorefs.length; i++) {
const ref = bibliorefs[i];
const citeInfo = findCites(ref);
if (citeInfo) {
tippyHover(citeInfo.el, function() {
var popup = window.document.createElement('div');
citeInfo.cites.forEach(function(cite) {
var citeDiv = window.document.createElement('div');
citeDiv.classList.add('hanging-indent');
citeDiv.classList.add('csl-entry');
var biblioDiv = window.document.getElementById('ref-' + cite);
if (biblioDiv) {
citeDiv.innerHTML = biblioDiv.innerHTML;
}
popup.appendChild(citeDiv);
});
return popup.innerHTML;
});
}
}
});
</script>
<nav class="page-navigation">
<div class="nav-page nav-page-previous">
<a href="./tutorial.html" class="pagination-link">
<i class="bi bi-arrow-left-short"></i> <span class="nav-page-text"><span class="chapter-number">3</span>&nbsp; <span class="chapter-title">OBITools V4 Tutorial</span></span>
</a>
</div>
<div class="nav-page nav-page-next">
<a href="./library.html" class="pagination-link">
<span class="nav-page-text"><span class="chapter-number">5</span>&nbsp; <span class="chapter-title">The GO <em>OBITools</em> library</span></span> <i class="bi bi-arrow-right-short"></i>
</a>
</div>
</nav>
</div> <!-- /content -->
</body></html>