|
|
|
|
|
<!DOCTYPE html> |
|
<html class="writer-html5" lang="en" > |
|
<head> |
|
<meta charset="utf-8"> |
|
|
|
<meta name="viewport" content="width=device-width, initial-scale=1.0"> |
|
|
|
<title>dscript.alphabets — D-SCRIPT v1.0-beta documentation</title> |
|
|
|
|
|
|
|
<link rel="stylesheet" href="../../_static/css/theme.css" type="text/css" /> |
|
<link rel="stylesheet" href="../../_static/pygments.css" type="text/css" /> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<script type="text/javascript" id="documentation_options" data-url_root="../../" src="../../_static/documentation_options.js"></script> |
|
<script src="../../_static/jquery.js"></script> |
|
<script src="../../_static/underscore.js"></script> |
|
<script src="../../_static/doctools.js"></script> |
|
<script src="../../_static/language_data.js"></script> |
|
<script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
|
|
|
<script type="text/javascript" src="../../_static/js/theme.js"></script> |
|
|
|
|
|
<link rel="index" title="Index" href="../../genindex.html" /> |
|
<link rel="search" title="Search" href="../../search.html" /> |
|
</head> |
|
|
|
<body class="wy-body-for-nav"> |
|
|
|
|
|
<div class="wy-grid-for-nav"> |
|
|
|
<nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
|
<div class="wy-side-scroll"> |
|
<div class="wy-side-nav-search" > |
|
|
|
|
|
|
|
<a href="../../index.html" class="icon icon-home" alt="Documentation Home"> D-SCRIPT |
|
|
|
|
|
|
|
</a> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="search"> |
|
<form id="rtd-search-form" class="wy-form" action="../../search.html" method="get"> |
|
<input type="text" name="q" placeholder="Search docs" /> |
|
<input type="hidden" name="check_keywords" value="yes" /> |
|
<input type="hidden" name="area" value="default" /> |
|
</form> |
|
</div> |
|
|
|
|
|
</div> |
|
|
|
|
|
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
|
|
|
|
|
|
|
|
|
|
|
|
|
<ul> |
|
<li class="toctree-l1"><a class="reference internal" href="../../installation.html">Installation</a></li> |
|
<li class="toctree-l1"><a class="reference internal" href="../../usage.html">Usage</a></li> |
|
<li class="toctree-l1"><a class="reference internal" href="../../data.html">Data</a></li> |
|
<li class="toctree-l1"><a class="reference internal" href="../../api/index.html">API</a></li> |
|
</ul> |
|
|
|
|
|
|
|
</div> |
|
|
|
</div> |
|
</nav> |
|
|
|
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
|
|
|
|
|
<nav class="wy-nav-top" aria-label="top navigation"> |
|
|
|
<i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
|
<a href="../../index.html">D-SCRIPT</a> |
|
|
|
</nav> |
|
|
|
|
|
<div class="wy-nav-content"> |
|
|
|
<div class="rst-content"> |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
<div role="navigation" aria-label="breadcrumbs navigation"> |
|
|
|
<ul class="wy-breadcrumbs"> |
|
|
|
<li><a href="../../index.html" class="icon icon-home"></a> »</li> |
|
|
|
<li><a href="../index.html">Module code</a> »</li> |
|
|
|
<li>dscript.alphabets</li> |
|
|
|
|
|
<li class="wy-breadcrumbs-aside"> |
|
|
|
</li> |
|
|
|
</ul> |
|
|
|
|
|
<hr/> |
|
</div> |
|
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
|
<div itemprop="articleBody"> |
|
|
|
<h1>Source code for dscript.alphabets</h1><div class="highlight"><pre> |
|
<span></span><span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span><span class="p">,</span> <span class="n">division</span> |
|
|
|
<span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
|
|
|
|
|
<div class="viewcode-block" id="Alphabet"><a class="viewcode-back" href="../../api/index.html#dscript.alphabets.Alphabet">[docs]</a><span class="k">class</span> <span class="nc">Alphabet</span><span class="p">:</span> |
|
<span class="sd">"""</span> |
|
<span class="sd"> From `Bepler & Berger <https://github.com/tbepler/protein-sequence-embedding-iclr2019>`_.</span> |
|
|
|
<span class="sd"> :param chars: List of characters in alphabet</span> |
|
<span class="sd"> :type chars: byte str</span> |
|
<span class="sd"> :param encoding: Mapping of characters to numbers [default: encoding]</span> |
|
<span class="sd"> :type encoding: np.ndarray</span> |
|
<span class="sd"> :param mask: Set encoding mask [default: False]</span> |
|
<span class="sd"> :type mask: bool</span> |
|
<span class="sd"> :param missing: Number to use for a value outside the alphabet [default: 255]</span> |
|
<span class="sd"> :type missing: int</span> |
|
<span class="sd"> """</span> |
|
|
|
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">chars</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">mask</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">missing</span><span class="o">=</span><span class="mi">255</span><span class="p">):</span> |
|
<span class="bp">self</span><span class="o">.</span><span class="n">chars</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">frombuffer</span><span class="p">(</span><span class="n">chars</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span> |
|
<span class="bp">self</span><span class="o">.</span><span class="n">encoding</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="mi">256</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span> <span class="o">+</span> <span class="n">missing</span> |
|
<span class="k">if</span> <span class="n">encoding</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
|
<span class="bp">self</span><span class="o">.</span><span class="n">encoding</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">chars</span><span class="p">]</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">chars</span><span class="p">))</span> |
|
<span class="bp">self</span><span class="o">.</span><span class="n">size</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">chars</span><span class="p">)</span> |
|
<span class="k">else</span><span class="p">:</span> |
|
<span class="bp">self</span><span class="o">.</span><span class="n">encoding</span><span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">chars</span><span class="p">]</span> <span class="o">=</span> <span class="n">encoding</span> |
|
<span class="bp">self</span><span class="o">.</span><span class="n">size</span> <span class="o">=</span> <span class="n">encoding</span><span class="o">.</span><span class="n">max</span><span class="p">()</span> <span class="o">+</span> <span class="mi">1</span> |
|
<span class="bp">self</span><span class="o">.</span><span class="n">mask</span> <span class="o">=</span> <span class="n">mask</span> |
|
<span class="k">if</span> <span class="n">mask</span><span class="p">:</span> |
|
<span class="bp">self</span><span class="o">.</span><span class="n">size</span> <span class="o">-=</span> <span class="mi">1</span> |
|
|
|
<span class="k">def</span> <span class="fm">__len__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">size</span> |
|
|
|
<span class="k">def</span> <span class="fm">__getitem__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">i</span><span class="p">):</span> |
|
<span class="k">return</span> <span class="nb">chr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">chars</span><span class="p">[</span><span class="n">i</span><span class="p">])</span> |
|
|
|
<div class="viewcode-block" id="Alphabet.encode"><a class="viewcode-back" href="../../api/index.html#dscript.alphabets.Alphabet.encode">[docs]</a> <span class="k">def</span> <span class="nf">encode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span> |
|
<span class="sd">"""</span> |
|
<span class="sd"> Encode a byte string into alphabet indices</span> |
|
<span class="sd"> </span> |
|
<span class="sd"> :param x: Amino acid string</span> |
|
<span class="sd"> :type x: byte str</span> |
|
<span class="sd"> :return: Numeric encoding</span> |
|
<span class="sd"> :rtype: np.ndarray</span> |
|
<span class="sd"> """</span> |
|
<span class="n">x</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">frombuffer</span><span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="n">dtype</span><span class="o">=</span><span class="n">np</span><span class="o">.</span><span class="n">uint8</span><span class="p">)</span> |
|
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">encoding</span><span class="p">[</span><span class="n">x</span><span class="p">]</span></div> |
|
|
|
<div class="viewcode-block" id="Alphabet.decode"><a class="viewcode-back" href="../../api/index.html#dscript.alphabets.Alphabet.decode">[docs]</a> <span class="k">def</span> <span class="nf">decode</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">x</span><span class="p">):</span> |
|
<span class="sd">"""</span> |
|
<span class="sd"> Decode numeric encoding to byte string of this alphabet</span> |
|
|
|
<span class="sd"> :param x: Numeric encoding</span> |
|
<span class="sd"> :type x: np.ndarray</span> |
|
<span class="sd"> :return: Amino acid string</span> |
|
<span class="sd"> :rtype: byte str</span> |
|
<span class="sd"> """</span> |
|
<span class="n">string</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">chars</span><span class="p">[</span><span class="n">x</span><span class="p">]</span> |
|
<span class="k">return</span> <span class="n">string</span><span class="o">.</span><span class="n">tobytes</span><span class="p">()</span></div></div> |
|
|
|
|
|
<div class="viewcode-block" id="Uniprot21"><a class="viewcode-back" href="../../api/index.html#dscript.alphabets.Uniprot21">[docs]</a><span class="k">class</span> <span class="nc">Uniprot21</span><span class="p">(</span><span class="n">Alphabet</span><span class="p">):</span> |
|
<span class="sd">"""</span> |
|
<span class="sd"> Uniprot 21 Amino Acid Encoding.</span> |
|
|
|
<span class="sd"> From `Bepler & Berger <https://github.com/tbepler/protein-sequence-embedding-iclr2019>`_.</span> |
|
<span class="sd"> """</span> |
|
|
|
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">mask</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
|
<span class="n">chars</span> <span class="o">=</span> <span class="sa">b</span><span class="s2">"ARNDCQEGHILKMFPSTWYVXOUBZ"</span> |
|
<span class="n">encoding</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">arange</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">chars</span><span class="p">))</span> |
|
<span class="n">encoding</span><span class="p">[</span><span class="mi">21</span><span class="p">:]</span> <span class="o">=</span> <span class="p">[</span><span class="mi">11</span><span class="p">,</span> <span class="mi">4</span><span class="p">,</span> <span class="mi">20</span><span class="p">,</span> <span class="mi">20</span><span class="p">]</span> <span class="c1"># encode 'OUBZ' as synonyms</span> |
|
<span class="nb">super</span><span class="p">(</span><span class="n">Uniprot21</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">chars</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">,</span> <span class="n">mask</span><span class="o">=</span><span class="n">mask</span><span class="p">,</span> <span class="n">missing</span><span class="o">=</span><span class="mi">20</span><span class="p">)</span></div> |
|
</pre></div> |
|
|
|
</div> |
|
|
|
</div> |
|
<footer> |
|
|
|
|
|
<hr/> |
|
|
|
<div role="contentinfo"> |
|
<p> |
|
|
|
© Copyright 2020, Samuel Sledzieski, Rohit Singh |
|
|
|
</p> |
|
</div> |
|
|
|
|
|
|
|
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a |
|
|
|
<a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> |
|
|
|
provided by <a href="https://readthedocs.org">Read the Docs</a>. |
|
|
|
</footer> |
|
|
|
</div> |
|
</div> |
|
|
|
</section> |
|
|
|
</div> |
|
|
|
|
|
<script type="text/javascript"> |
|
jQuery(function () { |
|
SphinxRtdTheme.Navigation.enable(true); |
|
}); |
|
</script> |
|
|
|
|
|
|
|
|
|
|
|
|
|
</body> |
|
</html> |