<?xml version="1.0" encoding="ascii"?>
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"DTD/xhtml1-transitional.dtd">
<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
<head>
<title>Bio.NeuralNetwork.Gene.Motif</title>
<link rel="stylesheet" href="epydoc.css" type="text/css" />
<script type="text/javascript" src="epydoc.js"></script>
</head>
<body bgcolor="white" text="black" link="blue" vlink="#204080"
alink="#204080">
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
bgcolor="#a0c0ff" cellspacing="0">
<tr valign="middle">
<!-- Tree link -->
<th> <a
href="module-tree.html">Trees</a> </th>
<!-- Index link -->
<th> <a
href="identifier-index.html">Indices</a> </th>
<!-- Help link -->
<th> <a
href="help.html">Help</a> </th>
<th class="navbar" width="100%"></th>
</tr>
</table>
<table width="100%" cellpadding="0" cellspacing="0">
<tr valign="top">
<td width="100%">
<span class="breadcrumbs">
<a href="Bio-module.html">Package Bio</a> ::
<a href="Bio.NeuralNetwork-module.html">Package NeuralNetwork</a> ::
<a href="Bio.NeuralNetwork.Gene-module.html">Package Gene</a> ::
Module Motif
</span>
</td>
<td>
<table cellpadding="0" cellspacing="0">
<!-- hide/show private -->
<tr><td align="right"><span class="options">[<a href="javascript:void(0);" class="privatelink"
onclick="toggle_private();">hide private</a>]</span></td></tr>
<tr><td align="right"><span class="options"
>[<a href="frames.html" target="_top">frames</a
>] | <a href="Bio.NeuralNetwork.Gene.Motif-pysrc.html"
target="_top">no frames</a>]</span></td></tr>
</table>
</td>
</tr>
</table>
<h1 class="epydoc">Source Code for <a href="Bio.NeuralNetwork.Gene.Motif-module.html">Module Bio.NeuralNetwork.Gene.Motif</a></h1>
<pre class="py-src">
<a name="L1"></a><tt class="py-lineno"> 1</tt> <tt class="py-line"><tt class="py-docstring">"""Find and deal with motifs in biological sequence data.</tt> </tt>
<a name="L2"></a><tt class="py-lineno"> 2</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L3"></a><tt class="py-lineno"> 3</tt> <tt class="py-line"><tt class="py-docstring">Representing DNA (or RNA or proteins) in a neural network can be difficult</tt> </tt>
<a name="L4"></a><tt class="py-lineno"> 4</tt> <tt class="py-line"><tt class="py-docstring">since input sequences can have different lengths. One way to get around</tt> </tt>
<a name="L5"></a><tt class="py-lineno"> 5</tt> <tt class="py-line"><tt class="py-docstring">this problem is to deal with sequences by finding common motifs, and counting</tt> </tt>
<a name="L6"></a><tt class="py-lineno"> 6</tt> <tt class="py-line"><tt class="py-docstring">the number of times those motifs occur in a sequence. This information can</tt> </tt>
<a name="L7"></a><tt class="py-lineno"> 7</tt> <tt class="py-line"><tt class="py-docstring">then be used for creating the neural networks, with occurances of motifs</tt> </tt>
<a name="L8"></a><tt class="py-lineno"> 8</tt> <tt class="py-line"><tt class="py-docstring">going into the network instead of raw sequence data.</tt> </tt>
<a name="L9"></a><tt class="py-lineno"> 9</tt> <tt class="py-line"><tt class="py-docstring">"""</tt> </tt>
<a name="L10"></a><tt class="py-lineno"> 10</tt> <tt class="py-line"><tt class="py-comment"># biopython</tt> </tt>
<a name="L11"></a><tt class="py-lineno"> 11</tt> <tt class="py-line"><tt class="py-keyword">from</tt> <tt id="link-0" class="py-name" targets="Package Bio=Bio-module.html"><a title="Bio" class="py-name" href="#" onclick="return doclink('link-0', 'Bio', 'link-0');">Bio</a></tt><tt class="py-op">.</tt><tt id="link-1" class="py-name" targets="Package Bio.Alphabet=Bio.Alphabet-module.html,Class Bio.Alphabet.Alphabet=Bio.Alphabet.Alphabet-class.html"><a title="Bio.Alphabet
Bio.Alphabet.Alphabet" class="py-name" href="#" onclick="return doclink('link-1', 'Alphabet', 'link-1');">Alphabet</a></tt> <tt class="py-keyword">import</tt> <tt id="link-2" class="py-name" targets="Function Bio.Alphabet._verify_alphabet()=Bio.Alphabet-module.html#_verify_alphabet"><a title="Bio.Alphabet._verify_alphabet" class="py-name" href="#" onclick="return doclink('link-2', '_verify_alphabet', 'link-2');">_verify_alphabet</a></tt> </tt>
<a name="L12"></a><tt class="py-lineno"> 12</tt> <tt class="py-line"><tt class="py-keyword">from</tt> <tt id="link-3" class="py-name"><a title="Bio" class="py-name" href="#" onclick="return doclink('link-3', 'Bio', 'link-0');">Bio</a></tt><tt class="py-op">.</tt><tt id="link-4" class="py-name" targets="Module Bio.Seq=Bio.Seq-module.html,Class Bio.Seq.Seq=Bio.Seq.Seq-class.html"><a title="Bio.Seq
Bio.Seq.Seq" class="py-name" href="#" onclick="return doclink('link-4', 'Seq', 'link-4');">Seq</a></tt> <tt class="py-keyword">import</tt> <tt id="link-5" class="py-name"><a title="Bio.Seq
Bio.Seq.Seq" class="py-name" href="#" onclick="return doclink('link-5', 'Seq', 'link-4');">Seq</a></tt> </tt>
<a name="L13"></a><tt class="py-lineno"> 13</tt> <tt class="py-line"> </tt>
<a name="L14"></a><tt class="py-lineno"> 14</tt> <tt class="py-line"><tt class="py-comment"># local modules</tt> </tt>
<a name="L15"></a><tt class="py-lineno"> 15</tt> <tt class="py-line"><tt class="py-keyword">from</tt> <tt id="link-6" class="py-name" targets="Module Bio.NeuralNetwork.Gene.Pattern=Bio.NeuralNetwork.Gene.Pattern-module.html"><a title="Bio.NeuralNetwork.Gene.Pattern" class="py-name" href="#" onclick="return doclink('link-6', 'Pattern', 'link-6');">Pattern</a></tt> <tt class="py-keyword">import</tt> <tt id="link-7" class="py-name" targets="Class Bio.NeuralNetwork.Gene.Pattern.PatternRepository=Bio.NeuralNetwork.Gene.Pattern.PatternRepository-class.html"><a title="Bio.NeuralNetwork.Gene.Pattern.PatternRepository" class="py-name" href="#" onclick="return doclink('link-7', 'PatternRepository', 'link-7');">PatternRepository</a></tt> </tt>
<a name="L16"></a><tt class="py-lineno"> 16</tt> <tt class="py-line"> </tt>
<a name="MotifFinder"></a><div id="MotifFinder-def"><a name="L17"></a><tt class="py-lineno"> 17</tt> <a class="py-toggle" href="#" id="MotifFinder-toggle" onclick="return toggle('MotifFinder');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifFinder-class.html">MotifFinder</a><tt class="py-op">(</tt><tt class="py-base-class">object</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifFinder-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="MotifFinder-expanded"><a name="L18"></a><tt class="py-lineno"> 18</tt> <tt class="py-line"> <tt class="py-docstring">"""Find motifs in a set of Sequence Records.</tt> </tt>
<a name="L19"></a><tt class="py-lineno"> 19</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="MotifFinder.__init__"></a><div id="MotifFinder.__init__-def"><a name="L20"></a><tt class="py-lineno"> 20</tt> <a class="py-toggle" href="#" id="MotifFinder.__init__-toggle" onclick="return toggle('MotifFinder.__init__');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifFinder-class.html#__init__">__init__</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">alphabet_strict</tt> <tt class="py-op">=</tt> <tt class="py-number">1</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifFinder.__init__-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="MotifFinder.__init__-expanded"><a name="L21"></a><tt class="py-lineno"> 21</tt> <tt class="py-line"> <tt class="py-docstring">"""Initialize a finder to get motifs.</tt> </tt>
<a name="L22"></a><tt class="py-lineno"> 22</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L23"></a><tt class="py-lineno"> 23</tt> <tt class="py-line"><tt class="py-docstring"> Arguments:</tt> </tt>
<a name="L24"></a><tt class="py-lineno"> 24</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L25"></a><tt class="py-lineno"> 25</tt> <tt class="py-line"><tt class="py-docstring"> o alphabet_strict - Whether or not motifs should be</tt> </tt>
<a name="L26"></a><tt class="py-lineno"> 26</tt> <tt class="py-line"><tt class="py-docstring"> restricted to having all of there elements within the alphabet</tt> </tt>
<a name="L27"></a><tt class="py-lineno"> 27</tt> <tt class="py-line"><tt class="py-docstring"> of the sequences. This requires that the Sequences have a real</tt> </tt>
<a name="L28"></a><tt class="py-lineno"> 28</tt> <tt class="py-line"><tt class="py-docstring"> alphabet, and that all sequences have the same alphabet.</tt> </tt>
<a name="L29"></a><tt class="py-lineno"> 29</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="L30"></a><tt class="py-lineno"> 30</tt> <tt class="py-line"> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">alphabet_strict</tt> <tt class="py-op">=</tt> <tt class="py-name">alphabet_strict</tt> </tt>
</div><a name="L31"></a><tt class="py-lineno"> 31</tt> <tt class="py-line"> </tt>
<a name="MotifFinder.find"></a><div id="MotifFinder.find-def"><a name="L32"></a><tt class="py-lineno"> 32</tt> <a class="py-toggle" href="#" id="MotifFinder.find-toggle" onclick="return toggle('MotifFinder.find');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifFinder-class.html#find">find</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">seq_records</tt><tt class="py-op">,</tt> <tt class="py-param">motif_size</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifFinder.find-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="MotifFinder.find-expanded"><a name="L33"></a><tt class="py-lineno"> 33</tt> <tt class="py-line"> <tt class="py-docstring">"""Find all motifs of the given size in the passed SeqRecords.</tt> </tt>
<a name="L34"></a><tt class="py-lineno"> 34</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L35"></a><tt class="py-lineno"> 35</tt> <tt class="py-line"><tt class="py-docstring"> Arguments:</tt> </tt>
<a name="L36"></a><tt class="py-lineno"> 36</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L37"></a><tt class="py-lineno"> 37</tt> <tt class="py-line"><tt class="py-docstring"> o seq_records - A list of SeqRecord objects which the motifs</tt> </tt>
<a name="L38"></a><tt class="py-lineno"> 38</tt> <tt class="py-line"><tt class="py-docstring"> will be found from.</tt> </tt>
<a name="L39"></a><tt class="py-lineno"> 39</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L40"></a><tt class="py-lineno"> 40</tt> <tt class="py-line"><tt class="py-docstring"> o motif_size - The size of the motifs we want to look for.</tt> </tt>
<a name="L41"></a><tt class="py-lineno"> 41</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L42"></a><tt class="py-lineno"> 42</tt> <tt class="py-line"><tt class="py-docstring"> Returns:</tt> </tt>
<a name="L43"></a><tt class="py-lineno"> 43</tt> <tt class="py-line"><tt class="py-docstring"> A PatternRepository object that contains all of the motifs (and their</tt> </tt>
<a name="L44"></a><tt class="py-lineno"> 44</tt> <tt class="py-line"><tt class="py-docstring"> counts) found in the training sequences).</tt> </tt>
<a name="L45"></a><tt class="py-lineno"> 45</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="L46"></a><tt class="py-lineno"> 46</tt> <tt class="py-line"> <tt class="py-name">motif_info</tt> <tt class="py-op">=</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-8" class="py-name" targets="Method Bio.NeuralNetwork.Gene.Motif.MotifFinder._get_motif_dict()=Bio.NeuralNetwork.Gene.Motif.MotifFinder-class.html#_get_motif_dict"><a title="Bio.NeuralNetwork.Gene.Motif.MotifFinder._get_motif_dict" class="py-name" href="#" onclick="return doclink('link-8', '_get_motif_dict', 'link-8');">_get_motif_dict</a></tt><tt class="py-op">(</tt><tt class="py-name">seq_records</tt><tt class="py-op">,</tt> <tt class="py-name">motif_size</tt><tt class="py-op">)</tt> </tt>
<a name="L47"></a><tt class="py-lineno"> 47</tt> <tt class="py-line"> </tt>
<a name="L48"></a><tt class="py-lineno"> 48</tt> <tt class="py-line"> <tt class="py-keyword">return</tt> <tt id="link-9" class="py-name"><a title="Bio.NeuralNetwork.Gene.Pattern.PatternRepository" class="py-name" href="#" onclick="return doclink('link-9', 'PatternRepository', 'link-7');">PatternRepository</a></tt><tt class="py-op">(</tt><tt class="py-name">motif_info</tt><tt class="py-op">)</tt> </tt>
</div><a name="L49"></a><tt class="py-lineno"> 49</tt> <tt class="py-line"> </tt>
<a name="MotifFinder._get_motif_dict"></a><div id="MotifFinder._get_motif_dict-def"><a name="L50"></a><tt class="py-lineno"> 50</tt> <a class="py-toggle" href="#" id="MotifFinder._get_motif_dict-toggle" onclick="return toggle('MotifFinder._get_motif_dict');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifFinder-class.html#_get_motif_dict">_get_motif_dict</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">seq_records</tt><tt class="py-op">,</tt> <tt class="py-param">motif_size</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifFinder._get_motif_dict-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="MotifFinder._get_motif_dict-expanded"><a name="L51"></a><tt class="py-lineno"> 51</tt> <tt class="py-line"> <tt class="py-docstring">"""Return a dictionary with information on motifs.</tt> </tt>
<a name="L52"></a><tt class="py-lineno"> 52</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L53"></a><tt class="py-lineno"> 53</tt> <tt class="py-line"><tt class="py-docstring"> This internal function essentially does all of the hard work for</tt> </tt>
<a name="L54"></a><tt class="py-lineno"> 54</tt> <tt class="py-line"><tt class="py-docstring"> finding motifs, and returns a dictionary containing the found motifs</tt> </tt>
<a name="L55"></a><tt class="py-lineno"> 55</tt> <tt class="py-line"><tt class="py-docstring"> and their counts. This is internal so it can be reused by</tt> </tt>
<a name="L56"></a><tt class="py-lineno"> 56</tt> <tt class="py-line"><tt class="py-docstring"> find_motif_differences.</tt> </tt>
<a name="L57"></a><tt class="py-lineno"> 57</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="L58"></a><tt class="py-lineno"> 58</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">alphabet_strict</tt><tt class="py-op">:</tt> </tt>
<a name="L59"></a><tt class="py-lineno"> 59</tt> <tt class="py-line"> <tt class="py-name">alphabet</tt> <tt class="py-op">=</tt> <tt class="py-name">seq_records</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-10" class="py-name" targets="Variable Bio.SeqRecord.SeqRecord.seq=Bio.SeqRecord.SeqRecord-class.html#seq,Variable BioSQL.BioSeq.DBSeqRecord.seq=BioSQL.BioSeq.DBSeqRecord-class.html#seq"><a title="Bio.SeqRecord.SeqRecord.seq
BioSQL.BioSeq.DBSeqRecord.seq" class="py-name" href="#" onclick="return doclink('link-10', 'seq', 'link-10');">seq</a></tt><tt class="py-op">.</tt><tt class="py-name">alphabet</tt> </tt>
<a name="L60"></a><tt class="py-lineno"> 60</tt> <tt class="py-line"> <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L61"></a><tt class="py-lineno"> 61</tt> <tt class="py-line"> <tt class="py-name">alphabet</tt> <tt class="py-op">=</tt> <tt class="py-name">None</tt> </tt>
<a name="L62"></a><tt class="py-lineno"> 62</tt> <tt class="py-line"> </tt>
<a name="L63"></a><tt class="py-lineno"> 63</tt> <tt class="py-line"> <tt class="py-comment"># loop through all records to find the motifs in the sequences</tt> </tt>
<a name="L64"></a><tt class="py-lineno"> 64</tt> <tt class="py-line"> <tt class="py-name">all_motifs</tt> <tt class="py-op">=</tt> <tt class="py-op">{</tt><tt class="py-op">}</tt> </tt>
<a name="L65"></a><tt class="py-lineno"> 65</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt class="py-name">seq_record</tt> <tt class="py-keyword">in</tt> <tt class="py-name">seq_records</tt><tt class="py-op">:</tt> </tt>
<a name="L66"></a><tt class="py-lineno"> 66</tt> <tt class="py-line"> <tt class="py-comment"># if we are working with alphabets, make sure we are consistent</tt> </tt>
<a name="L67"></a><tt class="py-lineno"> 67</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">alphabet</tt> <tt class="py-keyword">is</tt> <tt class="py-keyword">not</tt> <tt class="py-name">None</tt><tt class="py-op">:</tt> </tt>
<a name="L68"></a><tt class="py-lineno"> 68</tt> <tt class="py-line"> <tt class="py-keyword">assert</tt> <tt class="py-name">seq_record</tt><tt class="py-op">.</tt><tt id="link-11" class="py-name"><a title="Bio.SeqRecord.SeqRecord.seq
BioSQL.BioSeq.DBSeqRecord.seq" class="py-name" href="#" onclick="return doclink('link-11', 'seq', 'link-10');">seq</a></tt><tt class="py-op">.</tt><tt class="py-name">alphabet</tt> <tt class="py-op">==</tt> <tt class="py-name">alphabet</tt><tt class="py-op">,</tt> \ </tt>
<a name="L69"></a><tt class="py-lineno"> 69</tt> <tt class="py-line"> <tt class="py-string">"Working with alphabet %s and got %s"</tt> <tt class="py-op">%</tt> \ </tt>
<a name="L70"></a><tt class="py-lineno"> 70</tt> <tt class="py-line"> <tt class="py-op">(</tt><tt class="py-name">alphabet</tt><tt class="py-op">,</tt> <tt class="py-name">seq_record</tt><tt class="py-op">.</tt><tt id="link-12" class="py-name"><a title="Bio.SeqRecord.SeqRecord.seq
BioSQL.BioSeq.DBSeqRecord.seq" class="py-name" href="#" onclick="return doclink('link-12', 'seq', 'link-10');">seq</a></tt><tt class="py-op">.</tt><tt class="py-name">alphabet</tt><tt class="py-op">)</tt> </tt>
<a name="L71"></a><tt class="py-lineno"> 71</tt> <tt class="py-line"> </tt>
<a name="L72"></a><tt class="py-lineno"> 72</tt> <tt class="py-line"> <tt class="py-comment"># now start finding motifs in the sequence</tt> </tt>
<a name="L73"></a><tt class="py-lineno"> 73</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt id="link-13" class="py-name" targets="Variable Bio.Restriction._Update.RestrictionCompiler.start=Bio.Restriction._Update.RestrictionCompiler-module.html#start,Variable Bio.SeqFeature.FeatureLocation.start=Bio.SeqFeature.FeatureLocation-class.html#start"><a title="Bio.Restriction._Update.RestrictionCompiler.start
Bio.SeqFeature.FeatureLocation.start" class="py-name" href="#" onclick="return doclink('link-13', 'start', 'link-13');">start</a></tt> <tt class="py-keyword">in</tt> <tt id="link-14" class="py-name" targets="Method Bio.Graphics.GenomeDiagram._Diagram.Diagram.range()=Bio.Graphics.GenomeDiagram._Diagram.Diagram-class.html#range,Method Bio.Graphics.GenomeDiagram._FeatureSet.FeatureSet.range()=Bio.Graphics.GenomeDiagram._FeatureSet.FeatureSet-class.html#range,Method Bio.Graphics.GenomeDiagram._Graph.GraphData.range()=Bio.Graphics.GenomeDiagram._Graph.GraphData-class.html#range,Method Bio.Graphics.GenomeDiagram._GraphSet.GraphSet.range()=Bio.Graphics.GenomeDiagram._GraphSet.GraphSet-class.html#range,Method Bio.Graphics.GenomeDiagram._Track.Track.range()=Bio.Graphics.GenomeDiagram._Track.Track-class.html#range"><a title="Bio.Graphics.GenomeDiagram._Diagram.Diagram.range
Bio.Graphics.GenomeDiagram._FeatureSet.FeatureSet.range
Bio.Graphics.GenomeDiagram._Graph.GraphData.range
Bio.Graphics.GenomeDiagram._GraphSet.GraphSet.range
Bio.Graphics.GenomeDiagram._Track.Track.range" class="py-name" href="#" onclick="return doclink('link-14', 'range', 'link-14');">range</a></tt><tt class="py-op">(</tt><tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">seq_record</tt><tt class="py-op">.</tt><tt id="link-15" class="py-name"><a title="Bio.SeqRecord.SeqRecord.seq
BioSQL.BioSeq.DBSeqRecord.seq" class="py-name" href="#" onclick="return doclink('link-15', 'seq', 'link-10');">seq</a></tt><tt class="py-op">)</tt> <tt class="py-op">-</tt> <tt class="py-op">(</tt><tt class="py-name">motif_size</tt> <tt class="py-op">-</tt> <tt class="py-number">1</tt><tt class="py-op">)</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L74"></a><tt class="py-lineno"> 74</tt> <tt class="py-line"> <tt class="py-name">motif</tt> <tt class="py-op">=</tt> <tt class="py-name">seq_record</tt><tt class="py-op">.</tt><tt id="link-16" class="py-name"><a title="Bio.SeqRecord.SeqRecord.seq
BioSQL.BioSeq.DBSeqRecord.seq" class="py-name" href="#" onclick="return doclink('link-16', 'seq', 'link-10');">seq</a></tt><tt class="py-op">[</tt><tt id="link-17" class="py-name"><a title="Bio.Restriction._Update.RestrictionCompiler.start
Bio.SeqFeature.FeatureLocation.start" class="py-name" href="#" onclick="return doclink('link-17', 'start', 'link-13');">start</a></tt><tt class="py-op">:</tt><tt id="link-18" class="py-name"><a title="Bio.Restriction._Update.RestrictionCompiler.start
Bio.SeqFeature.FeatureLocation.start" class="py-name" href="#" onclick="return doclink('link-18', 'start', 'link-13');">start</a></tt> <tt class="py-op">+</tt> <tt class="py-name">motif_size</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-19" class="py-name" targets="Method Bio.Crystal.Crystal.tostring()=Bio.Crystal.Crystal-class.html#tostring,Method Bio.Seq.MutableSeq.tostring()=Bio.Seq.MutableSeq-class.html#tostring,Method Bio.Seq.Seq.tostring()=Bio.Seq.Seq-class.html#tostring,Method BioSQL.BioSeq.DBSeq.tostring()=BioSQL.BioSeq.DBSeq-class.html#tostring"><a title="Bio.Crystal.Crystal.tostring
Bio.Seq.MutableSeq.tostring
Bio.Seq.Seq.tostring
BioSQL.BioSeq.DBSeq.tostring" class="py-name" href="#" onclick="return doclink('link-19', 'tostring', 'link-19');">tostring</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L75"></a><tt class="py-lineno"> 75</tt> <tt class="py-line"> </tt>
<a name="L76"></a><tt class="py-lineno"> 76</tt> <tt class="py-line"> <tt class="py-comment"># if we are being alphabet strict, make sure the motif</tt> </tt>
<a name="L77"></a><tt class="py-lineno"> 77</tt> <tt class="py-line"> <tt class="py-comment"># falls within the specified alphabet</tt> </tt>
<a name="L78"></a><tt class="py-lineno"> 78</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">alphabet</tt> <tt class="py-keyword">is</tt> <tt class="py-keyword">not</tt> <tt class="py-name">None</tt><tt class="py-op">:</tt> </tt>
<a name="L79"></a><tt class="py-lineno"> 79</tt> <tt class="py-line"> <tt class="py-name">motif_seq</tt> <tt class="py-op">=</tt> <tt id="link-20" class="py-name"><a title="Bio.Seq
Bio.Seq.Seq" class="py-name" href="#" onclick="return doclink('link-20', 'Seq', 'link-4');">Seq</a></tt><tt class="py-op">(</tt><tt class="py-name">motif</tt><tt class="py-op">,</tt> <tt class="py-name">alphabet</tt><tt class="py-op">)</tt> </tt>
<a name="L80"></a><tt class="py-lineno"> 80</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt id="link-21" class="py-name"><a title="Bio.Alphabet._verify_alphabet" class="py-name" href="#" onclick="return doclink('link-21', '_verify_alphabet', 'link-2');">_verify_alphabet</a></tt><tt class="py-op">(</tt><tt class="py-name">motif_seq</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L81"></a><tt class="py-lineno"> 81</tt> <tt class="py-line"> <tt class="py-name">all_motifs</tt> <tt class="py-op">=</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-22" class="py-name" targets="Method Bio.NeuralNetwork.Gene.Motif.MotifFinder._add_motif()=Bio.NeuralNetwork.Gene.Motif.MotifFinder-class.html#_add_motif"><a title="Bio.NeuralNetwork.Gene.Motif.MotifFinder._add_motif" class="py-name" href="#" onclick="return doclink('link-22', '_add_motif', 'link-22');">_add_motif</a></tt><tt class="py-op">(</tt><tt class="py-name">all_motifs</tt><tt class="py-op">,</tt> <tt class="py-name">motif</tt><tt class="py-op">)</tt> </tt>
<a name="L82"></a><tt class="py-lineno"> 82</tt> <tt class="py-line"> </tt>
<a name="L83"></a><tt class="py-lineno"> 83</tt> <tt class="py-line"> <tt class="py-comment"># if we are not being strict, just add the motif</tt> </tt>
<a name="L84"></a><tt class="py-lineno"> 84</tt> <tt class="py-line"> <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L85"></a><tt class="py-lineno"> 85</tt> <tt class="py-line"> <tt class="py-name">all_motifs</tt> <tt class="py-op">=</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-23" class="py-name"><a title="Bio.NeuralNetwork.Gene.Motif.MotifFinder._add_motif" class="py-name" href="#" onclick="return doclink('link-23', '_add_motif', 'link-22');">_add_motif</a></tt><tt class="py-op">(</tt><tt class="py-name">all_motifs</tt><tt class="py-op">,</tt> <tt class="py-name">motif</tt><tt class="py-op">)</tt> </tt>
<a name="L86"></a><tt class="py-lineno"> 86</tt> <tt class="py-line"> </tt>
<a name="L87"></a><tt class="py-lineno"> 87</tt> <tt class="py-line"> <tt class="py-keyword">return</tt> <tt class="py-name">all_motifs</tt> </tt>
</div><a name="L88"></a><tt class="py-lineno"> 88</tt> <tt class="py-line"> </tt>
<a name="MotifFinder.find_differences"></a><div id="MotifFinder.find_differences-def"><a name="L89"></a><tt class="py-lineno"> 89</tt> <a class="py-toggle" href="#" id="MotifFinder.find_differences-toggle" onclick="return toggle('MotifFinder.find_differences');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifFinder-class.html#find_differences">find_differences</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">first_records</tt><tt class="py-op">,</tt> <tt class="py-param">second_records</tt><tt class="py-op">,</tt> <tt class="py-param">motif_size</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifFinder.find_differences-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="MotifFinder.find_differences-expanded"><a name="L90"></a><tt class="py-lineno"> 90</tt> <tt class="py-line"> <tt class="py-docstring">"""Find motifs in two sets of records and return the differences.</tt> </tt>
<a name="L91"></a><tt class="py-lineno"> 91</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L92"></a><tt class="py-lineno"> 92</tt> <tt class="py-line"><tt class="py-docstring"> This is used for finding motifs, but instead of just counting up all</tt> </tt>
<a name="L93"></a><tt class="py-lineno"> 93</tt> <tt class="py-line"><tt class="py-docstring"> of the motifs in a set of records, this returns the differences</tt> </tt>
<a name="L94"></a><tt class="py-lineno"> 94</tt> <tt class="py-line"><tt class="py-docstring"> between two listings of seq_records.</tt> </tt>
<a name="L95"></a><tt class="py-lineno"> 95</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L96"></a><tt class="py-lineno"> 96</tt> <tt class="py-line"><tt class="py-docstring"> o first_records, second_records - Two listings of SeqRecord objects</tt> </tt>
<a name="L97"></a><tt class="py-lineno"> 97</tt> <tt class="py-line"><tt class="py-docstring"> to have their motifs compared.</tt> </tt>
<a name="L98"></a><tt class="py-lineno"> 98</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L99"></a><tt class="py-lineno"> 99</tt> <tt class="py-line"><tt class="py-docstring"> o motif_size - The size of the motifs we are looking for.</tt> </tt>
<a name="L100"></a><tt class="py-lineno">100</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L101"></a><tt class="py-lineno">101</tt> <tt class="py-line"><tt class="py-docstring"> Returns:</tt> </tt>
<a name="L102"></a><tt class="py-lineno">102</tt> <tt class="py-line"><tt class="py-docstring"> A PatternRepository object that has motifs, but instead of their</tt> </tt>
<a name="L103"></a><tt class="py-lineno">103</tt> <tt class="py-line"><tt class="py-docstring"> raw counts, this has the counts in the first set of records</tt> </tt>
<a name="L104"></a><tt class="py-lineno">104</tt> <tt class="py-line"><tt class="py-docstring"> subtracted from the counts in the second set.</tt> </tt>
<a name="L105"></a><tt class="py-lineno">105</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="L106"></a><tt class="py-lineno">106</tt> <tt class="py-line"> <tt class="py-name">first_motifs</tt> <tt class="py-op">=</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-24" class="py-name"><a title="Bio.NeuralNetwork.Gene.Motif.MotifFinder._get_motif_dict" class="py-name" href="#" onclick="return doclink('link-24', '_get_motif_dict', 'link-8');">_get_motif_dict</a></tt><tt class="py-op">(</tt><tt class="py-name">first_records</tt><tt class="py-op">,</tt> <tt class="py-name">motif_size</tt><tt class="py-op">)</tt> </tt>
<a name="L107"></a><tt class="py-lineno">107</tt> <tt class="py-line"> <tt class="py-name">second_motifs</tt> <tt class="py-op">=</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt id="link-25" class="py-name"><a title="Bio.NeuralNetwork.Gene.Motif.MotifFinder._get_motif_dict" class="py-name" href="#" onclick="return doclink('link-25', '_get_motif_dict', 'link-8');">_get_motif_dict</a></tt><tt class="py-op">(</tt><tt class="py-name">second_records</tt><tt class="py-op">,</tt> <tt class="py-name">motif_size</tt><tt class="py-op">)</tt> </tt>
<a name="L108"></a><tt class="py-lineno">108</tt> <tt class="py-line"> </tt>
<a name="L109"></a><tt class="py-lineno">109</tt> <tt class="py-line"> <tt class="py-name">motif_diffs</tt> <tt class="py-op">=</tt> <tt class="py-op">{</tt><tt class="py-op">}</tt> </tt>
<a name="L110"></a><tt class="py-lineno">110</tt> <tt class="py-line"> </tt>
<a name="L111"></a><tt class="py-lineno">111</tt> <tt class="py-line"> <tt class="py-comment"># first deal with all of the keys from the first motif</tt> </tt>
<a name="L112"></a><tt class="py-lineno">112</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt class="py-name">cur_key</tt> <tt class="py-keyword">in</tt> <tt class="py-name">first_motifs</tt><tt class="py-op">:</tt> </tt>
<a name="L113"></a><tt class="py-lineno">113</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">cur_key</tt> <tt class="py-keyword">in</tt> <tt class="py-name">second_motifs</tt><tt class="py-op">:</tt> </tt>
<a name="L114"></a><tt class="py-lineno">114</tt> <tt class="py-line"> <tt class="py-name">motif_diffs</tt><tt class="py-op">[</tt><tt class="py-name">cur_key</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-name">first_motifs</tt><tt class="py-op">[</tt><tt class="py-name">cur_key</tt><tt class="py-op">]</tt> <tt class="py-op">-</tt> \ </tt>
<a name="L115"></a><tt class="py-lineno">115</tt> <tt class="py-line"> <tt class="py-name">second_motifs</tt><tt class="py-op">[</tt><tt class="py-name">cur_key</tt><tt class="py-op">]</tt> </tt>
<a name="L116"></a><tt class="py-lineno">116</tt> <tt class="py-line"> <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L117"></a><tt class="py-lineno">117</tt> <tt class="py-line"> <tt class="py-name">motif_diffs</tt><tt class="py-op">[</tt><tt class="py-name">cur_key</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-name">first_motifs</tt><tt class="py-op">[</tt><tt class="py-name">cur_key</tt><tt class="py-op">]</tt> </tt>
<a name="L118"></a><tt class="py-lineno">118</tt> <tt class="py-line"> </tt>
<a name="L119"></a><tt class="py-lineno">119</tt> <tt class="py-line"> <tt class="py-comment"># now see if there are any keys from the second motif</tt> </tt>
<a name="L120"></a><tt class="py-lineno">120</tt> <tt class="py-line"> <tt class="py-comment"># that we haven't got yet.</tt> </tt>
<a name="L121"></a><tt class="py-lineno">121</tt> <tt class="py-line"> <tt class="py-name">missing_motifs</tt> <tt class="py-op">=</tt> <tt id="link-26" class="py-name" targets="Method Bio.Pathway.Rep.HashSet.HashSet.list()=Bio.Pathway.Rep.HashSet.HashSet-class.html#list"><a title="Bio.Pathway.Rep.HashSet.HashSet.list" class="py-name" href="#" onclick="return doclink('link-26', 'list', 'link-26');">list</a></tt><tt class="py-op">(</tt><tt class="py-name">second_motifs</tt><tt class="py-op">)</tt> </tt>
<a name="L122"></a><tt class="py-lineno">122</tt> <tt class="py-line"> </tt>
<a name="L123"></a><tt class="py-lineno">123</tt> <tt class="py-line"> <tt class="py-comment"># remove all of the motifs we've already added</tt> </tt>
<a name="L124"></a><tt class="py-lineno">124</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt class="py-name">added_motif</tt> <tt class="py-keyword">in</tt> <tt class="py-name">motif_diffs</tt><tt class="py-op">:</tt> </tt>
<a name="L125"></a><tt class="py-lineno">125</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">added_motif</tt> <tt class="py-keyword">in</tt> <tt class="py-name">missing_motifs</tt><tt class="py-op">:</tt> </tt>
<a name="L126"></a><tt class="py-lineno">126</tt> <tt class="py-line"> <tt class="py-name">missing_motifs</tt><tt class="py-op">.</tt><tt id="link-27" class="py-name" targets="Method Bio.Crystal.Chain.remove()=Bio.Crystal.Chain-class.html#remove,Method Bio.Graphics.BasicChromosome._ChromosomeComponent.remove()=Bio.Graphics.BasicChromosome._ChromosomeComponent-class.html#remove,Method Bio.Pathway.Rep.HashSet.HashSet.remove()=Bio.Pathway.Rep.HashSet.HashSet-class.html#remove,Method Bio.Restriction.Restriction.RestrictionBatch.remove()=Bio.Restriction.Restriction.RestrictionBatch-class.html#remove,Method Bio.Seq.MutableSeq.remove()=Bio.Seq.MutableSeq-class.html#remove,Method BioSQL.Loader.DatabaseRemover.remove()=BioSQL.Loader.DatabaseRemover-class.html#remove"><a title="Bio.Crystal.Chain.remove
Bio.Graphics.BasicChromosome._ChromosomeComponent.remove
Bio.Pathway.Rep.HashSet.HashSet.remove
Bio.Restriction.Restriction.RestrictionBatch.remove
Bio.Seq.MutableSeq.remove
BioSQL.Loader.DatabaseRemover.remove" class="py-name" href="#" onclick="return doclink('link-27', 'remove', 'link-27');">remove</a></tt><tt class="py-op">(</tt><tt class="py-name">added_motif</tt><tt class="py-op">)</tt> </tt>
<a name="L127"></a><tt class="py-lineno">127</tt> <tt class="py-line"> </tt>
<a name="L128"></a><tt class="py-lineno">128</tt> <tt class="py-line"> <tt class="py-comment"># now put in all of the motifs we didn't get</tt> </tt>
<a name="L129"></a><tt class="py-lineno">129</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt class="py-name">cur_key</tt> <tt class="py-keyword">in</tt> <tt class="py-name">missing_motifs</tt><tt class="py-op">:</tt> </tt>
<a name="L130"></a><tt class="py-lineno">130</tt> <tt class="py-line"> <tt class="py-name">motif_diffs</tt><tt class="py-op">[</tt><tt class="py-name">cur_key</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-number">0</tt> <tt class="py-op">-</tt> <tt class="py-name">second_motifs</tt><tt class="py-op">[</tt><tt class="py-name">cur_key</tt><tt class="py-op">]</tt> </tt>
<a name="L131"></a><tt class="py-lineno">131</tt> <tt class="py-line"> </tt>
<a name="L132"></a><tt class="py-lineno">132</tt> <tt class="py-line"> <tt class="py-keyword">return</tt> <tt id="link-28" class="py-name"><a title="Bio.NeuralNetwork.Gene.Pattern.PatternRepository" class="py-name" href="#" onclick="return doclink('link-28', 'PatternRepository', 'link-7');">PatternRepository</a></tt><tt class="py-op">(</tt><tt class="py-name">motif_diffs</tt><tt class="py-op">)</tt> </tt>
</div><a name="L133"></a><tt class="py-lineno">133</tt> <tt class="py-line"> </tt>
<a name="MotifFinder._add_motif"></a><div id="MotifFinder._add_motif-def"><a name="L134"></a><tt class="py-lineno">134</tt> <a class="py-toggle" href="#" id="MotifFinder._add_motif-toggle" onclick="return toggle('MotifFinder._add_motif');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifFinder-class.html#_add_motif">_add_motif</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">motif_dict</tt><tt class="py-op">,</tt> <tt class="py-param">motif_to_add</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifFinder._add_motif-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="MotifFinder._add_motif-expanded"><a name="L135"></a><tt class="py-lineno">135</tt> <tt class="py-line"> <tt class="py-docstring">"""Add a motif to the given dictionary.</tt> </tt>
<a name="L136"></a><tt class="py-lineno">136</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="L137"></a><tt class="py-lineno">137</tt> <tt class="py-line"> <tt class="py-comment"># incrememt the count of the motif if it is already present</tt> </tt>
<a name="L138"></a><tt class="py-lineno">138</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">motif_to_add</tt> <tt class="py-keyword">in</tt> <tt class="py-name">motif_dict</tt><tt class="py-op">:</tt> </tt>
<a name="L139"></a><tt class="py-lineno">139</tt> <tt class="py-line"> <tt class="py-name">motif_dict</tt><tt class="py-op">[</tt><tt class="py-name">motif_to_add</tt><tt class="py-op">]</tt> <tt class="py-op">+=</tt> <tt class="py-number">1</tt> </tt>
<a name="L140"></a><tt class="py-lineno">140</tt> <tt class="py-line"> <tt class="py-comment"># otherwise add it to the dictionary</tt> </tt>
<a name="L141"></a><tt class="py-lineno">141</tt> <tt class="py-line"> <tt class="py-keyword">else</tt><tt class="py-op">:</tt> </tt>
<a name="L142"></a><tt class="py-lineno">142</tt> <tt class="py-line"> <tt class="py-name">motif_dict</tt><tt class="py-op">[</tt><tt class="py-name">motif_to_add</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-number">1</tt> </tt>
<a name="L143"></a><tt class="py-lineno">143</tt> <tt class="py-line"> </tt>
<a name="L144"></a><tt class="py-lineno">144</tt> <tt class="py-line"> <tt class="py-keyword">return</tt> <tt class="py-name">motif_dict</tt> </tt>
</div></div><a name="L145"></a><tt class="py-lineno">145</tt> <tt class="py-line"> </tt>
<a name="MotifCoder"></a><div id="MotifCoder-def"><a name="L146"></a><tt class="py-lineno">146</tt> <a class="py-toggle" href="#" id="MotifCoder-toggle" onclick="return toggle('MotifCoder');">-</a><tt class="py-line"><tt class="py-keyword">class</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifCoder-class.html">MotifCoder</a><tt class="py-op">(</tt><tt class="py-base-class">object</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifCoder-collapsed" style="display:none;" pad="+++" indent="++++"></div><div id="MotifCoder-expanded"><a name="L147"></a><tt class="py-lineno">147</tt> <tt class="py-line"> <tt class="py-docstring">"""Convert motifs and a sequence into neural network representations.</tt> </tt>
<a name="L148"></a><tt class="py-lineno">148</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L149"></a><tt class="py-lineno">149</tt> <tt class="py-line"><tt class="py-docstring"> This is designed to convert a sequence into a representation that</tt> </tt>
<a name="L150"></a><tt class="py-lineno">150</tt> <tt class="py-line"><tt class="py-docstring"> can be fed as an input into a neural network. It does this by</tt> </tt>
<a name="L151"></a><tt class="py-lineno">151</tt> <tt class="py-line"><tt class="py-docstring"> representing a sequence based the motifs present.</tt> </tt>
<a name="L152"></a><tt class="py-lineno">152</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="MotifCoder.__init__"></a><div id="MotifCoder.__init__-def"><a name="L153"></a><tt class="py-lineno">153</tt> <a class="py-toggle" href="#" id="MotifCoder.__init__-toggle" onclick="return toggle('MotifCoder.__init__');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifCoder-class.html#__init__">__init__</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">motifs</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifCoder.__init__-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="MotifCoder.__init__-expanded"><a name="L154"></a><tt class="py-lineno">154</tt> <tt class="py-line"> <tt class="py-docstring">"""Initialize an input producer with motifs to look for.</tt> </tt>
<a name="L155"></a><tt class="py-lineno">155</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L156"></a><tt class="py-lineno">156</tt> <tt class="py-line"><tt class="py-docstring"> Arguments:</tt> </tt>
<a name="L157"></a><tt class="py-lineno">157</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L158"></a><tt class="py-lineno">158</tt> <tt class="py-line"><tt class="py-docstring"> o motifs - A complete list of motifs, in order, that are to be</tt> </tt>
<a name="L159"></a><tt class="py-lineno">159</tt> <tt class="py-line"><tt class="py-docstring"> searched for in a sequence.</tt> </tt>
<a name="L160"></a><tt class="py-lineno">160</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="L161"></a><tt class="py-lineno">161</tt> <tt class="py-line"> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motifs</tt> <tt class="py-op">=</tt> <tt class="py-name">motifs</tt> </tt>
<a name="L162"></a><tt class="py-lineno">162</tt> <tt class="py-line"> </tt>
<a name="L163"></a><tt class="py-lineno">163</tt> <tt class="py-line"> <tt class="py-comment"># check to be sure the motifs make sense (all the same size)</tt> </tt>
<a name="L164"></a><tt class="py-lineno">164</tt> <tt class="py-line"> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motif_size</tt> <tt class="py-op">=</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motifs</tt><tt class="py-op">[</tt><tt class="py-number">0</tt><tt class="py-op">]</tt><tt class="py-op">)</tt> </tt>
<a name="L165"></a><tt class="py-lineno">165</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt class="py-name">motif</tt> <tt class="py-keyword">in</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motifs</tt><tt class="py-op">:</tt> </tt>
<a name="L166"></a><tt class="py-lineno">166</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">len</tt><tt class="py-op">(</tt><tt class="py-name">motif</tt><tt class="py-op">)</tt> <tt class="py-op">!=</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motif_size</tt><tt class="py-op">:</tt> </tt>
<a name="L167"></a><tt class="py-lineno">167</tt> <tt class="py-line"> <tt class="py-keyword">raise</tt> <tt class="py-name">ValueError</tt><tt class="py-op">(</tt><tt class="py-string">"Motif %s given, expected motif size %s"</tt> </tt>
<a name="L168"></a><tt class="py-lineno">168</tt> <tt class="py-line"> <tt class="py-op">%</tt> <tt class="py-op">(</tt><tt class="py-name">motif</tt><tt class="py-op">,</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motif_size</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
</div><a name="L169"></a><tt class="py-lineno">169</tt> <tt class="py-line"> </tt>
<a name="MotifCoder.representation"></a><div id="MotifCoder.representation-def"><a name="L170"></a><tt class="py-lineno">170</tt> <a class="py-toggle" href="#" id="MotifCoder.representation-toggle" onclick="return toggle('MotifCoder.representation');">-</a><tt class="py-line"> <tt class="py-keyword">def</tt> <a class="py-def-name" href="Bio.NeuralNetwork.Gene.Motif.MotifCoder-class.html#representation">representation</a><tt class="py-op">(</tt><tt class="py-param">self</tt><tt class="py-op">,</tt> <tt class="py-param">sequence</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
</div><div id="MotifCoder.representation-collapsed" style="display:none;" pad="+++" indent="++++++++"></div><div id="MotifCoder.representation-expanded"><a name="L171"></a><tt class="py-lineno">171</tt> <tt class="py-line"> <tt class="py-docstring">"""Represent a sequence as a set of motifs.</tt> </tt>
<a name="L172"></a><tt class="py-lineno">172</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L173"></a><tt class="py-lineno">173</tt> <tt class="py-line"><tt class="py-docstring"> Arguments:</tt> </tt>
<a name="L174"></a><tt class="py-lineno">174</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L175"></a><tt class="py-lineno">175</tt> <tt class="py-line"><tt class="py-docstring"> o sequence - A Bio.Seq object to represent as a motif.</tt> </tt>
<a name="L176"></a><tt class="py-lineno">176</tt> <tt class="py-line"><tt class="py-docstring"></tt> </tt>
<a name="L177"></a><tt class="py-lineno">177</tt> <tt class="py-line"><tt class="py-docstring"> This converts a sequence into a representation based on the motifs.</tt> </tt>
<a name="L178"></a><tt class="py-lineno">178</tt> <tt class="py-line"><tt class="py-docstring"> The representation is returned as a list of the relative amount of</tt> </tt>
<a name="L179"></a><tt class="py-lineno">179</tt> <tt class="py-line"><tt class="py-docstring"> each motif (number of times a motif occured divided by the total</tt> </tt>
<a name="L180"></a><tt class="py-lineno">180</tt> <tt class="py-line"><tt class="py-docstring"> number of motifs in the sequence). The values in the list correspond</tt> </tt>
<a name="L181"></a><tt class="py-lineno">181</tt> <tt class="py-line"><tt class="py-docstring"> to the input order of the motifs specified in the initializer.</tt> </tt>
<a name="L182"></a><tt class="py-lineno">182</tt> <tt class="py-line"><tt class="py-docstring"> """</tt> </tt>
<a name="L183"></a><tt class="py-lineno">183</tt> <tt class="py-line"> <tt class="py-comment"># initialize a dictionary to hold the motifs in this sequence</tt> </tt>
<a name="L184"></a><tt class="py-lineno">184</tt> <tt class="py-line"> <tt class="py-name">seq_motifs</tt> <tt class="py-op">=</tt> <tt class="py-op">{</tt><tt class="py-op">}</tt> </tt>
<a name="L185"></a><tt class="py-lineno">185</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt class="py-name">motif</tt> <tt class="py-keyword">in</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motifs</tt><tt class="py-op">:</tt> </tt>
<a name="L186"></a><tt class="py-lineno">186</tt> <tt class="py-line"> <tt class="py-name">seq_motifs</tt><tt class="py-op">[</tt><tt class="py-name">motif</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-number">0</tt> </tt>
<a name="L187"></a><tt class="py-lineno">187</tt> <tt class="py-line"> </tt>
<a name="L188"></a><tt class="py-lineno">188</tt> <tt class="py-line"> <tt class="py-comment"># count all of the motifs we are looking for in the sequence</tt> </tt>
<a name="L189"></a><tt class="py-lineno">189</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt id="link-29" class="py-name"><a title="Bio.Restriction._Update.RestrictionCompiler.start
Bio.SeqFeature.FeatureLocation.start" class="py-name" href="#" onclick="return doclink('link-29', 'start', 'link-13');">start</a></tt> <tt class="py-keyword">in</tt> <tt id="link-30" class="py-name"><a title="Bio.Graphics.GenomeDiagram._Diagram.Diagram.range
Bio.Graphics.GenomeDiagram._FeatureSet.FeatureSet.range
Bio.Graphics.GenomeDiagram._Graph.GraphData.range
Bio.Graphics.GenomeDiagram._GraphSet.GraphSet.range
Bio.Graphics.GenomeDiagram._Track.Track.range" class="py-name" href="#" onclick="return doclink('link-30', 'range', 'link-14');">range</a></tt><tt class="py-op">(</tt><tt class="py-name">len</tt><tt class="py-op">(</tt><tt id="link-31" class="py-name" targets="Method Bio.FSSP.FSSPAlignDict.sequence()=Bio.FSSP.FSSPAlignDict-class.html#sequence,Method Bio.GenBank._FeatureConsumer.sequence()=Bio.GenBank._FeatureConsumer-class.html#sequence,Method Bio.GenBank._RecordConsumer.sequence()=Bio.GenBank._RecordConsumer-class.html#sequence,Method Bio.Phylo.PhyloXMLIO.Writer.sequence()=Bio.Phylo.PhyloXMLIO.Writer-class.html#sequence"><a title="Bio.FSSP.FSSPAlignDict.sequence
Bio.GenBank._FeatureConsumer.sequence
Bio.GenBank._RecordConsumer.sequence
Bio.Phylo.PhyloXMLIO.Writer.sequence" class="py-name" href="#" onclick="return doclink('link-31', 'sequence', 'link-31');">sequence</a></tt><tt class="py-op">)</tt> <tt class="py-op">-</tt> <tt class="py-op">(</tt><tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motif_size</tt> <tt class="py-op">-</tt> <tt class="py-number">1</tt><tt class="py-op">)</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L190"></a><tt class="py-lineno">190</tt> <tt class="py-line"> <tt class="py-name">motif</tt> <tt class="py-op">=</tt> <tt id="link-32" class="py-name"><a title="Bio.FSSP.FSSPAlignDict.sequence
Bio.GenBank._FeatureConsumer.sequence
Bio.GenBank._RecordConsumer.sequence
Bio.Phylo.PhyloXMLIO.Writer.sequence" class="py-name" href="#" onclick="return doclink('link-32', 'sequence', 'link-31');">sequence</a></tt><tt class="py-op">[</tt><tt id="link-33" class="py-name"><a title="Bio.Restriction._Update.RestrictionCompiler.start
Bio.SeqFeature.FeatureLocation.start" class="py-name" href="#" onclick="return doclink('link-33', 'start', 'link-13');">start</a></tt><tt class="py-op">:</tt><tt id="link-34" class="py-name"><a title="Bio.Restriction._Update.RestrictionCompiler.start
Bio.SeqFeature.FeatureLocation.start" class="py-name" href="#" onclick="return doclink('link-34', 'start', 'link-13');">start</a></tt> <tt class="py-op">+</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motif_size</tt><tt class="py-op">]</tt><tt class="py-op">.</tt><tt id="link-35" class="py-name"><a title="Bio.Crystal.Crystal.tostring
Bio.Seq.MutableSeq.tostring
Bio.Seq.Seq.tostring
BioSQL.BioSeq.DBSeq.tostring" class="py-name" href="#" onclick="return doclink('link-35', 'tostring', 'link-19');">tostring</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt> </tt>
<a name="L191"></a><tt class="py-lineno">191</tt> <tt class="py-line"> </tt>
<a name="L192"></a><tt class="py-lineno">192</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">motif</tt> <tt class="py-keyword">in</tt> <tt class="py-name">seq_motifs</tt><tt class="py-op">:</tt> </tt>
<a name="L193"></a><tt class="py-lineno">193</tt> <tt class="py-line"> <tt class="py-name">seq_motifs</tt><tt class="py-op">[</tt><tt class="py-name">motif</tt><tt class="py-op">]</tt> <tt class="py-op">+=</tt> <tt class="py-number">1</tt> </tt>
<a name="L194"></a><tt class="py-lineno">194</tt> <tt class="py-line"> </tt>
<a name="L195"></a><tt class="py-lineno">195</tt> <tt class="py-line"> <tt class="py-comment"># normalize the motifs to go between zero and one</tt> </tt>
<a name="L196"></a><tt class="py-lineno">196</tt> <tt class="py-line"> <tt class="py-name">min_count</tt> <tt class="py-op">=</tt> <tt class="py-name">min</tt><tt class="py-op">(</tt><tt class="py-name">seq_motifs</tt><tt class="py-op">.</tt><tt id="link-36" class="py-name" targets="Method Bio.Crystal.Crystal.values()=Bio.Crystal.Crystal-class.html#values,Method Bio.Phylo.PhyloXML.Events.values()=Bio.Phylo.PhyloXML.Events-class.html#values,Method Bio.SeqIO._index._IndexedSeqFileDict.values()=Bio.SeqIO._index._IndexedSeqFileDict-class.html#values,Method BioSQL.BioSeqDatabase.BioSeqDatabase.values()=BioSQL.BioSeqDatabase.BioSeqDatabase-class.html#values,Method BioSQL.BioSeqDatabase.DBServer.values()=BioSQL.BioSeqDatabase.DBServer-class.html#values"><a title="Bio.Crystal.Crystal.values
Bio.Phylo.PhyloXML.Events.values
Bio.SeqIO._index._IndexedSeqFileDict.values
BioSQL.BioSeqDatabase.BioSeqDatabase.values
BioSQL.BioSeqDatabase.DBServer.values" class="py-name" href="#" onclick="return doclink('link-36', 'values', 'link-36');">values</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L197"></a><tt class="py-lineno">197</tt> <tt class="py-line"> <tt class="py-name">max_count</tt> <tt class="py-op">=</tt> <tt class="py-name">max</tt><tt class="py-op">(</tt><tt class="py-name">seq_motifs</tt><tt class="py-op">.</tt><tt id="link-37" class="py-name"><a title="Bio.Crystal.Crystal.values
Bio.Phylo.PhyloXML.Events.values
Bio.SeqIO._index._IndexedSeqFileDict.values
BioSQL.BioSeqDatabase.BioSeqDatabase.values
BioSQL.BioSeqDatabase.DBServer.values" class="py-name" href="#" onclick="return doclink('link-37', 'values', 'link-36');">values</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L198"></a><tt class="py-lineno">198</tt> <tt class="py-line"> </tt>
<a name="L199"></a><tt class="py-lineno">199</tt> <tt class="py-line"> <tt class="py-comment"># as long as we have some motifs present, normalize them</tt> </tt>
<a name="L200"></a><tt class="py-lineno">200</tt> <tt class="py-line"> <tt class="py-comment"># otherwise we'll just return 0 for everything </tt> </tt>
<a name="L201"></a><tt class="py-lineno">201</tt> <tt class="py-line"> <tt class="py-keyword">if</tt> <tt class="py-name">max_count</tt> <tt class="py-op">></tt> <tt class="py-number">0</tt><tt class="py-op">:</tt> </tt>
<a name="L202"></a><tt class="py-lineno">202</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt class="py-name">motif</tt> <tt class="py-keyword">in</tt> <tt class="py-name">seq_motifs</tt><tt class="py-op">.</tt><tt id="link-38" class="py-name" targets="Method Bio.Crystal.Crystal.keys()=Bio.Crystal.Crystal-class.html#keys,Method Bio.PDB.AbstractPropertyMap.AbstractPropertyMap.keys()=Bio.PDB.AbstractPropertyMap.AbstractPropertyMap-class.html#keys,Method Bio.Phylo.PhyloXML.Events.keys()=Bio.Phylo.PhyloXML.Events-class.html#keys,Method Bio.SeqIO._index._IndexedSeqFileDict.keys()=Bio.SeqIO._index._IndexedSeqFileDict-class.html#keys,Method Bio.SeqIO._index._SQLiteManySeqFilesDict.keys()=Bio.SeqIO._index._SQLiteManySeqFilesDict-class.html#keys,Method BioSQL.BioSeqDatabase.BioSeqDatabase.keys()=BioSQL.BioSeqDatabase.BioSeqDatabase-class.html#keys,Method BioSQL.BioSeqDatabase.DBServer.keys()=BioSQL.BioSeqDatabase.DBServer-class.html#keys"><a title="Bio.Crystal.Crystal.keys
Bio.PDB.AbstractPropertyMap.AbstractPropertyMap.keys
Bio.Phylo.PhyloXML.Events.keys
Bio.SeqIO._index._IndexedSeqFileDict.keys
Bio.SeqIO._index._SQLiteManySeqFilesDict.keys
BioSQL.BioSeqDatabase.BioSeqDatabase.keys
BioSQL.BioSeqDatabase.DBServer.keys" class="py-name" href="#" onclick="return doclink('link-38', 'keys', 'link-38');">keys</a></tt><tt class="py-op">(</tt><tt class="py-op">)</tt><tt class="py-op">:</tt> </tt>
<a name="L203"></a><tt class="py-lineno">203</tt> <tt class="py-line"> <tt class="py-name">seq_motifs</tt><tt class="py-op">[</tt><tt class="py-name">motif</tt><tt class="py-op">]</tt> <tt class="py-op">=</tt> <tt class="py-op">(</tt><tt class="py-name">float</tt><tt class="py-op">(</tt><tt class="py-name">seq_motifs</tt><tt class="py-op">[</tt><tt class="py-name">motif</tt><tt class="py-op">]</tt> <tt class="py-op">-</tt> <tt class="py-name">min_count</tt><tt class="py-op">)</tt> </tt>
<a name="L204"></a><tt class="py-lineno">204</tt> <tt class="py-line"> <tt class="py-op">/</tt> <tt class="py-name">float</tt><tt class="py-op">(</tt><tt class="py-name">max_count</tt><tt class="py-op">)</tt><tt class="py-op">)</tt> </tt>
<a name="L205"></a><tt class="py-lineno">205</tt> <tt class="py-line"> </tt>
<a name="L206"></a><tt class="py-lineno">206</tt> <tt class="py-line"> <tt class="py-comment"># return the relative motif counts in the specified order</tt> </tt>
<a name="L207"></a><tt class="py-lineno">207</tt> <tt class="py-line"> <tt class="py-name">motif_amounts</tt> <tt class="py-op">=</tt> <tt class="py-op">[</tt><tt class="py-op">]</tt> </tt>
<a name="L208"></a><tt class="py-lineno">208</tt> <tt class="py-line"> <tt class="py-keyword">for</tt> <tt class="py-name">motif</tt> <tt class="py-keyword">in</tt> <tt class="py-name">self</tt><tt class="py-op">.</tt><tt class="py-name">_motifs</tt><tt class="py-op">:</tt> </tt>
<a name="L209"></a><tt class="py-lineno">209</tt> <tt class="py-line"> <tt class="py-name">motif_amounts</tt><tt class="py-op">.</tt><tt id="link-39" class="py-name" targets="Method Bio.Align.MultipleSeqAlignment.append()=Bio.Align.MultipleSeqAlignment-class.html#append,Method Bio.Crystal.Chain.append()=Bio.Crystal.Chain-class.html#append,Method Bio.SCOP.Raf.SeqMap.append()=Bio.SCOP.Raf.SeqMap-class.html#append,Method Bio.Seq.MutableSeq.append()=Bio.Seq.MutableSeq-class.html#append,Method Bio.Wise.psw.Alignment.append()=Bio.Wise.psw.Alignment-class.html#append,Method Bio.Wise.psw.AlignmentColumn.append()=Bio.Wise.psw.AlignmentColumn-class.html#append"><a title="Bio.Align.MultipleSeqAlignment.append
Bio.Crystal.Chain.append
Bio.SCOP.Raf.SeqMap.append
Bio.Seq.MutableSeq.append
Bio.Wise.psw.Alignment.append
Bio.Wise.psw.AlignmentColumn.append" class="py-name" href="#" onclick="return doclink('link-39', 'append', 'link-39');">append</a></tt><tt class="py-op">(</tt><tt class="py-name">seq_motifs</tt><tt class="py-op">[</tt><tt class="py-name">motif</tt><tt class="py-op">]</tt><tt class="py-op">)</tt> </tt>
<a name="L210"></a><tt class="py-lineno">210</tt> <tt class="py-line"> </tt>
<a name="L211"></a><tt class="py-lineno">211</tt> <tt class="py-line"> <tt class="py-keyword">return</tt> <tt class="py-name">motif_amounts</tt> </tt>
</div></div><a name="L212"></a><tt class="py-lineno">212</tt> <tt class="py-line"> </tt><script type="text/javascript">
<!--
expandto(location.href);
// -->
</script>
</pre>
<br />
<!-- ==================== NAVIGATION BAR ==================== -->
<table class="navbar" border="0" width="100%" cellpadding="0"
bgcolor="#a0c0ff" cellspacing="0">
<tr valign="middle">
<!-- Tree link -->
<th> <a
href="module-tree.html">Trees</a> </th>
<!-- Index link -->
<th> <a
href="identifier-index.html">Indices</a> </th>
<!-- Help link -->
<th> <a
href="help.html">Help</a> </th>
<th class="navbar" width="100%"></th>
</tr>
</table>
<table border="0" cellpadding="0" cellspacing="0" width="100%%">
<tr>
<td align="left" class="footer">
Generated by Epydoc 3.0.1 on Thu Aug 18 18:22:27 2011
</td>
<td align="right" class="footer">
<a target="mainFrame" href="http://epydoc.sourceforge.net"
>http://epydoc.sourceforge.net</a>
</td>
</tr>
</table>
<script type="text/javascript">
<!--
// Private objects are initially displayed (because if
// javascript is turned off then we want them to be
// visible); but by default, we want to hide them. So hide
// them unless we have a cookie that says to show them.
checkCookie();
// -->
</script>
</body>
</html>
