PageRenderTime 65ms CodeModel.GetById 21ms RepoModel.GetById 0ms app.codeStats 0ms

/BioLiteManual/_modules/biolite/workflows.html

https://bitbucket.org/aguang/biolite
HTML | 399 lines | 348 code | 51 blank | 0 comment | 0 complexity | 2454942d32297449f7d74b3e3f60bf62 MD5 | raw file
    

  1. 

  2. 

  3. <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
    4. 

  4.   "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
    5. 

  5. 

  6. 

  7. <html xmlns="http://www.w3.org/1999/xhtml">
    8. 

  8.   <head>
    9. 

  9.     <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
    10. 

  10.     
    11. 

  11.     <title>biolite.workflows &mdash; BioLite 0.3.3 documentation</title>
    12. 

  12.     
    13. 

  13.     <link rel="stylesheet" href="../../_static/default.css" type="text/css" />
    14. 

  14.     <link rel="stylesheet" href="../../_static/pygments.css" type="text/css" />
    15. 

  15.     
    16. 

  16.     <script type="text/javascript">
    17. 

  17.       var DOCUMENTATION_OPTIONS = {
    18. 

  18.         URL_ROOT:    '../../',
    19. 

  19.         VERSION:     '0.3.3',
    20. 

  20.         COLLAPSE_INDEX: false,
    21. 

  21.         FILE_SUFFIX: '.html',
    22. 

  22.         HAS_SOURCE:  true
    23. 

  23.       };
    24. 

  24.     </script>
    25. 

  25.     <script type="text/javascript" src="../../_static/jquery.js"></script>
    26. 

  26.     <script type="text/javascript" src="../../_static/underscore.js"></script>
    27. 

  27.     <script type="text/javascript" src="../../_static/doctools.js"></script>
    28. 

  28.     <link rel="top" title="BioLite 0.3.3 documentation" href="../../index.html" />
    29. 

  29.     <link rel="up" title="Module code" href="../index.html" /> 
    30. 

  30.   </head>
    31. 

  31.   <body>
    32. 

  32.     <div class="related">
    33. 

  33.       <h3>Navigation</h3>
    34. 

  34.       <ul>
    35. 

  35.         <li class="right" style="margin-right: 10px">
    36. 

  36.           <a href="../../genindex.html" title="General Index"
    37. 

  37.              accesskey="I">index</a></li>
    38. 

  38.         <li class="right" >
    39. 

  39.           <a href="../../py-modindex.html" title="Python Module Index"
    40. 

  40.              >modules</a> |</li>
    41. 

  41.         <li><a href="../../index.html">BioLite 0.3.3 documentation</a> &raquo;</li>
    42. 

  42.           <li><a href="../index.html" accesskey="U">Module code</a> &raquo;</li> 
    43. 

  43.       </ul>
    44. 

  44.     </div>  
    45. 

  45. 

  46.     <div class="document">
    47. 

  47.       <div class="documentwrapper">
    48. 

  48.         <div class="bodywrapper">
    49. 

  49.           <div class="body">
    50. 

  50.             
    51. 

  51.   <h1>Source code for biolite.workflows</h1><div class="highlight"><pre>
    52. 

  52. <span class="c"># BioLite - Tools for processing gene sequence data and automating workflows</span>
    53. 

  53. <span class="c"># Copyright (c) 2012-2013 Brown University. All rights reserved.</span>
    54. 

  54. <span class="c"># </span>
    55. 

  55. <span class="c"># This file is part of BioLite.</span>
    56. 

  56. <span class="c"># </span>
    57. 

  57. <span class="c"># BioLite is free software: you can redistribute it and/or modify</span>
    58. 

  58. <span class="c"># it under the terms of the GNU General Public License as published by</span>
    59. 

  59. <span class="c"># the Free Software Foundation, either version 3 of the License, or</span>
    60. 

  60. <span class="c"># (at your option) any later version.</span>
    61. 

  61. <span class="c"># </span>
    62. 

  62. <span class="c"># BioLite is distributed in the hope that it will be useful,</span>
    63. 

  63. <span class="c"># but WITHOUT ANY WARRANTY; without even the implied warranty of</span>
    64. 

  64. <span class="c"># MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the</span>
    65. 

  65. <span class="c"># GNU General Public License for more details.</span>
    66. 

  66. <span class="c"># </span>
    67. 

  67. <span class="c"># You should have received a copy of the GNU General Public License</span>
    68. 

  68. <span class="c"># along with BioLite.  If not, see &lt;http://www.gnu.org/licenses/&gt;.</span>
    69. 

  69. 

  70. <span class="sd">&quot;&quot;&quot;</span>
    71. 

  71. <span class="sd">Provides a collection of helper functions that coordinate multiple wrappers</span>
    72. 

  72. <span class="sd">from the :ref:`wrappers` to accomplish a unified goal or automate a common</span>
    73. 

  73. <span class="sd">analysis task.</span>
    74. 

  74. 

  75. <span class="sd">Workflows are available for the following groups of tasks:</span>
    76. 

  76. 

  77. <span class="sd">* Assembly statistics and sweeps</span>
    78. 

  78. <span class="sd">* Contig parsing</span>
    79. 

  79. <span class="sd">* Blast result parsing</span>
    80. 

  80. <span class="sd">* SamTools automation</span>
    81. 

  81. <span class="sd">* Transcript cleaning</span>
    82. 

  82. <span class="sd">&quot;&quot;&quot;</span>
    83. 

  83. 

  84. <span class="kn">import</span> <span class="nn">os</span>
    85. 

  85. <span class="kn">import</span> <span class="nn">re</span>
    86. 

  86. <span class="kn">import</span> <span class="nn">shutil</span>
    87. 

  87. <span class="kn">import</span> <span class="nn">sys</span>
    88. 

  88. 

  89. <span class="kn">from</span> <span class="nn">Bio.Blast</span> <span class="kn">import</span> <span class="n">NCBIXML</span>
    90. 

  90. <span class="kn">from</span> <span class="nn">Bio</span> <span class="kn">import</span> <span class="n">SeqIO</span>
    91. 

  91. <span class="kn">from</span> <span class="nn">collections</span> <span class="kn">import</span> <span class="n">namedtuple</span><span class="p">,</span> <span class="n">OrderedDict</span>
    92. 

  92. 

  93. <span class="kn">from</span> <span class="nn">biolite</span> <span class="kn">import</span> <span class="n">config</span>
    94. 

  94. <span class="kn">from</span> <span class="nn">biolite</span> <span class="kn">import</span> <span class="n">diagnostics</span>
    95. 

  95. <span class="kn">from</span> <span class="nn">biolite</span> <span class="kn">import</span> <span class="n">utils</span>
    96. 

  96. <span class="kn">from</span> <span class="nn">biolite</span> <span class="kn">import</span> <span class="n">wrappers</span>
    97. 

  97. 

  98. <span class="kn">import</span> <span class="nn">blast</span>
    99. 

  99. <span class="kn">import</span> <span class="nn">phylogeny</span>
    100. 

  100. 

  101. <span class="n">ContigHeader</span> <span class="o">=</span> <span class="n">namedtuple</span><span class="p">(</span><span class="s">&#39;ContigHeader&#39;</span><span class="p">,</span> <span class="s">&quot;locus transcript confidence length&quot;</span><span class="p">)</span>
    102. 

  102. <span class="sd">&quot;&quot;&quot;</span>
    103. 

  103. <span class="sd">A namedtuple for storing the information from a transcript header.</span>
    104. 

  104. <span class="sd">&quot;&quot;&quot;</span>
    105. 

  105. 

  106. <span class="n">standard_contig_header</span> <span class="o">=</span> \
    107. 

  107. 	<span class="s">&quot;Locus_{0}_Transcript_{1}/0_Confidence_{2}_Length_{3}</span><span class="se">\n</span><span class="s">&quot;</span>
    108. 

  108. 

  109. <span class="n">oases_header_pattern</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>\
    110. 

  110. 	<span class="s">r&#39;Locus_([\d\.]+)_Transcript_(\d+)/\d+_Confidence_([\.\d]+)_Length_(\d+)$&#39;</span><span class="p">)</span>
    111. 

  111. 

  112. <span class="n">trinity_header_pattern</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">compile</span><span class="p">(</span>\
    113. 

  113. 	<span class="s">r&#39;comp(\d+)_c(\d+)_seq(\d+) len=(\d+) path=\[([-: \d]+)\]$&#39;</span><span class="p">)</span>
    114. 

  114. 

  115. <div class="viewcode-block" id="unpack_oases_header"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.unpack_oases_header">[docs]</a><span class="k">def</span> <span class="nf">unpack_oases_header</span><span class="p">(</span><span class="n">header</span><span class="p">):</span>
    116. 

  116. 	<span class="sd">&quot;&quot;&quot;</span>
    117. 

  117. <span class="sd">	Unpacks an Oases contig header into a ContigHeader object.</span>
    118. 

  118. 

  119. <span class="sd">	Example header:</span>
    120. 

  120. <span class="sd">	</span>
    121. 

  121. <span class="sd">	&gt;Locus_9919_Transcript_1/1_Confidence_1.000_Length_160</span>
    122. 

  122. <span class="sd">	&quot;&quot;&quot;</span>
    123. 

  123. 	<span class="n">match</span> <span class="o">=</span> <span class="n">oases_header_pattern</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">header</span><span class="p">)</span>
    124. 

  124. 	<span class="k">if</span> <span class="n">match</span><span class="p">:</span>
    125. 

  125. 		<span class="k">return</span> <span class="n">ContigHeader</span><span class="p">(</span><span class="o">*</span><span class="n">match</span><span class="o">.</span><span class="n">groups</span><span class="p">())</span>
    126. 

  126. 	<span class="k">else</span><span class="p">:</span>
    127. 

  127. 		<span class="n">utils</span><span class="o">.</span><span class="n">die</span><span class="p">(</span><span class="s">&quot;bad oases header: </span><span class="si">%s</span><span class="s">&quot;</span> <span class="o">%</span> <span class="n">header</span><span class="p">)</span>
    128. 

  128. </div>
    129. 

  129. <div class="viewcode-block" id="contig_stats"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.contig_stats">[docs]</a><span class="k">def</span> <span class="nf">contig_stats</span><span class="p">(</span><span class="n">fasta_path</span><span class="p">,</span> <span class="n">hist_path</span><span class="p">):</span>
    130. 

  130. 	<span class="sd">&quot;&quot;&quot;</span>
    131. 

  131. <span class="sd">	Parses the assembled contigs in `fasta_path` and writes a histogram of</span>
    132. 

  132. <span class="sd">	contig length to `hist_path`.</span>
    133. 

  133. <span class="sd">	</span>
    134. 

  134. <span class="sd">	Writes the total contig count, mean length, and N50 length to</span>
    135. 

  135. <span class="sd">	the diagnostics.</span>
    136. 

  136. <span class="sd">	&quot;&quot;&quot;</span>
    137. 

  137. 	<span class="n">count</span> <span class="o">=</span> <span class="mi">0</span>
    138. 

  138. 	<span class="n">mean</span> <span class="o">=</span> <span class="mf">0.0</span>
    139. 

  139. 	<span class="n">n50</span> <span class="o">=</span> <span class="mi">0</span>
    140. 

  140. 

  141. 	<span class="c"># Parse the fasta file to construct a histogram, stored as a dictionary</span>
    142. 

  142. 	<span class="c"># {contig_length: frequency}, and to calculate total contig count and</span>
    143. 

  143. 	<span class="c"># mean length.</span>
    144. 

  144. 	<span class="n">hist</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span>
    145. 

  145. 	<span class="n">total_length</span> <span class="o">=</span> <span class="mi">0</span>
    146. 

  146. 	<span class="n">lengths</span> <span class="o">=</span> <span class="nb">list</span><span class="p">()</span>
    147. 

  147. 	<span class="k">for</span> <span class="n">record</span> <span class="ow">in</span> <span class="n">SeqIO</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">fasta_path</span><span class="p">,</span> <span class="s">&#39;fasta&#39;</span><span class="p">):</span>
    148. 

  148. 		<span class="n">count</span> <span class="o">+=</span> <span class="mi">1</span>
    149. 

  149. 		<span class="n">length</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">record</span><span class="o">.</span><span class="n">seq</span><span class="p">)</span>
    150. 

  150. 		<span class="n">lengths</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">length</span><span class="p">)</span>
    151. 

  151. 		<span class="n">hist</span><span class="p">[</span><span class="n">length</span><span class="p">]</span> <span class="o">=</span> <span class="n">hist</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">length</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span>
    152. 

  152. 	
    153. 

  153. 	<span class="n">lengths</span><span class="o">.</span><span class="n">sort</span><span class="p">()</span>
    154. 

  154. 	<span class="n">total_length</span> <span class="o">=</span> <span class="nb">sum</span><span class="p">(</span><span class="n">lengths</span><span class="p">)</span>
    155. 

  155. 	
    156. 

  156. 	<span class="k">if</span> <span class="n">count</span><span class="p">:</span>
    157. 

  157. 		<span class="n">mean</span> <span class="o">=</span> <span class="n">total_length</span> <span class="o">/</span> <span class="nb">float</span><span class="p">(</span><span class="n">count</span><span class="p">)</span>
    158. 

  158. 

  159. 	<span class="c"># Find the n50 value</span>
    160. 

  160. 	<span class="n">cum_length</span> <span class="o">=</span> <span class="mi">0</span>
    161. 

  161. 	<span class="k">for</span> <span class="n">length</span> <span class="ow">in</span> <span class="n">lengths</span><span class="p">:</span>
    162. 

  162. 		<span class="n">cum_length</span> <span class="o">+=</span> <span class="n">length</span>
    163. 

  163. 		<span class="k">if</span> <span class="n">cum_length</span> <span class="o">&gt;=</span> <span class="p">(</span><span class="n">total_length</span> <span class="o">/</span> <span class="mi">2</span><span class="p">):</span>
    164. 

  164. 			<span class="n">n50</span> <span class="o">=</span> <span class="n">length</span>
    165. 

  165. 			<span class="k">break</span>
    166. 

  166. 

  167. 	<span class="c"># Loop through the histogram to dump it to a text file.</span>
    168. 

  168. 	<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">hist_path</span><span class="p">,</span> <span class="s">&#39;w&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
    169. 

  169. 		<span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">hist</span><span class="o">.</span><span class="n">keys</span><span class="p">()):</span>
    170. 

  170. 			<span class="k">print</span> <span class="o">&gt;&gt;</span><span class="n">f</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">hist</span><span class="p">[</span><span class="n">key</span><span class="p">]</span>
    171. 

  171. 

  172. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">prefix</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s">&#39;contig_stats&#39;</span><span class="p">)</span>
    173. 

  173. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="s">&#39;count&#39;</span><span class="p">,</span> <span class="n">count</span><span class="p">)</span>
    174. 

  174. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="s">&#39;mean&#39;</span><span class="p">,</span> <span class="n">mean</span><span class="p">)</span>
    175. 

  175. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="s">&#39;n50&#39;</span><span class="p">,</span> <span class="n">n50</span><span class="p">)</span>
    176. 

  176. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">log_path</span><span class="p">(</span><span class="n">hist_path</span><span class="p">)</span>
    177. 

  177. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">prefix</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
    178. 

  178. </div>
    179. 

  179. <div class="viewcode-block" id="oases_clean"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.oases_clean">[docs]</a><span class="k">def</span> <span class="nf">oases_clean</span><span class="p">(</span><span class="n">workdir</span><span class="o">=</span><span class="s">&#39;./&#39;</span><span class="p">):</span>
    180. 

  180. 	<span class="sd">&quot;&quot;&quot;</span>
    181. 

  181. <span class="sd">	Cleans up a work directory that was used for an Oases assembly.</span>
    182. 

  182. <span class="sd">	&quot;&quot;&quot;</span>
    183. 

  183. 	<span class="n">files</span> <span class="o">=</span> <span class="p">(</span><span class="s">&#39;Sequences&#39;</span><span class="p">,</span> <span class="s">&#39;Roadmaps&#39;</span><span class="p">,</span> <span class="s">&#39;PreGraph&#39;</span><span class="p">,</span> <span class="s">&#39;Graph2&#39;</span><span class="p">,</span> <span class="s">&#39;LastGraph&#39;</span><span class="p">,</span> <span class="s">&#39;contigs.fa&#39;</span><span class="p">,</span> <span class="s">&#39;Log&#39;</span><span class="p">)</span>
    184. 

  184. 	<span class="k">for</span> <span class="n">f</span> <span class="ow">in</span> <span class="n">files</span><span class="p">:</span>
    185. 

  185. 		<span class="n">utils</span><span class="o">.</span><span class="n">safe_remove</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">workdir</span><span class="p">,</span> <span class="n">f</span><span class="p">))</span>
    186. 

  186. </div>
    187. 

  187. <div class="viewcode-block" id="oases_assemblies"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.oases_assemblies">[docs]</a><span class="k">def</span> <span class="nf">oases_assemblies</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">kmers</span><span class="o">=</span><span class="p">[</span><span class="mi">61</span><span class="p">],</span> <span class="n">workdir</span><span class="o">=</span><span class="s">&#39;./&#39;</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">ins_length</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
    188. 

  188. 	<span class="sd">&quot;&quot;&quot;</span>
    189. 

  189. <span class="sd">	Automates Oases assemblies that sweep multiple `kmers`.</span>
    190. 

  190. 

  191. <span class="sd">	If `inputs` is a list of FASTQ files, they are automatically shuffled</span>
    192. 

  192. <span class="sd">	together. Or, provide a singleton list with the path to a pre-shuffled</span>
    193. 

  193. <span class="sd">	FASTQ file.</span>
    194. 

  194. <span class="sd">	&quot;&quot;&quot;</span>
    195. 

  195. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">prefix</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s">&#39;oases_assemblies&#39;</span><span class="p">)</span>
    196. 

  196. 

  197. 	<span class="n">contig_list</span> <span class="o">=</span> <span class="nb">list</span><span class="p">()</span>
    198. 

  198. 

  199. 	<span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="n">kmers</span><span class="p">:</span>
    200. 

  200. 		<span class="n">diagnostics</span><span class="o">.</span><span class="n">prefix</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s">&#39;k</span><span class="si">%d</span><span class="s">&#39;</span> <span class="o">%</span> <span class="n">k</span><span class="p">)</span>
    201. 

  201. 		<span class="n">subdir</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">workdir</span><span class="p">,</span> <span class="s">&#39;k</span><span class="si">%d</span><span class="s">&#39;</span> <span class="o">%</span> <span class="n">k</span><span class="p">)</span>
    202. 

  202. 		<span class="c"># clear out any previous runs</span>
    203. 

  203. 		<span class="n">shutil</span><span class="o">.</span><span class="n">rmtree</span><span class="p">(</span><span class="n">subdir</span><span class="p">,</span> <span class="n">ignore_errors</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
    204. 

  204. 		<span class="n">utils</span><span class="o">.</span><span class="n">safe_mkdir</span><span class="p">(</span><span class="n">subdir</span><span class="p">)</span>
    205. 

  205. 		<span class="c">#oases_clean(subdir)</span>
    206. 

  206. 		<span class="n">wrappers</span><span class="o">.</span><span class="n">VelvetH</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">subdir</span><span class="p">,</span> <span class="n">kmer</span><span class="o">=</span><span class="n">k</span><span class="p">)</span>
    207. 

  207. 		<span class="n">wrappers</span><span class="o">.</span><span class="n">VelvetG</span><span class="p">(</span><span class="n">subdir</span><span class="p">,</span> <span class="n">ins_length</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="n">min_length</span><span class="p">)</span>
    208. 

  208. 		<span class="c"># makes transcripts.fa</span>
    209. 

  209. 		<span class="n">wrappers</span><span class="o">.</span><span class="n">Oases</span><span class="p">(</span><span class="n">subdir</span><span class="p">,</span> <span class="n">ins_length</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="n">min_length</span><span class="p">)</span>
    210. 

  210. 		<span class="n">contigs</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">subdir</span><span class="p">,</span> <span class="s">&#39;transcripts.fa&#39;</span><span class="p">)</span>
    211. 

  211. 		<span class="n">contigs_k</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">workdir</span><span class="p">,</span> <span class="s">&#39;transcripts-k</span><span class="si">%d</span><span class="s">.fa&#39;</span> <span class="o">%</span> <span class="n">k</span><span class="p">)</span>
    212. 

  212. 		<span class="n">shutil</span><span class="o">.</span><span class="n">move</span><span class="p">(</span><span class="n">contigs</span><span class="p">,</span> <span class="n">contigs_k</span><span class="p">)</span>
    213. 

  213. 		<span class="n">contig_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">contigs_k</span><span class="p">)</span>
    214. 

  214. 		<span class="n">diagnostics</span><span class="o">.</span><span class="n">prefix</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
    215. 

  215. 

  216. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">prefix</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
    217. 

  217. 	<span class="k">return</span> <span class="n">contig_list</span>
    218. 

  218. </div>
    219. 

  219. <div class="viewcode-block" id="oases_concat_assembly"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.oases_concat_assembly">[docs]</a><span class="k">def</span> <span class="nf">oases_concat_assembly</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">concat_path</span><span class="p">,</span> <span class="n">kmers</span><span class="p">,</span> <span class="n">workdir</span><span class="o">=</span><span class="s">&#39;./&#39;</span><span class="p">,</span> <span class="n">ins_length</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
    220. 

  220. 	<span class="sd">&quot;&quot;&quot;</span>
    221. 

  221. <span class="sd">	Performs Oases assemblies sweeping over the provided `kmers` list, and</span>
    222. 

  222. <span class="sd">	concatenates all contigs to `concat_path`.</span>
    223. 

  223. 

  224. <span class="sd">	If `inputs` is a list of FASTQ files, they are automatically shuffled</span>
    225. 

  225. <span class="sd">	together. Or, provide a singleton list with the path to a pre-shuffled</span>
    226. 

  226. <span class="sd">	FASTQ file.</span>
    227. 

  227. <span class="sd">	&quot;&quot;&quot;</span>
    228. 

  228. 	<span class="n">utils</span><span class="o">.</span><span class="n">truncate_file</span><span class="p">(</span><span class="n">concat_path</span><span class="p">)</span>
    229. 

  229. 	<span class="k">for</span> <span class="n">contigs</span> <span class="ow">in</span> <span class="n">oases_assemblies</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">kmers</span><span class="p">,</span> <span class="n">workdir</span><span class="p">,</span> <span class="n">ins_length</span><span class="p">):</span>
    230. 

  230. 		<span class="n">utils</span><span class="o">.</span><span class="n">cat_to_file</span><span class="p">(</span><span class="n">contigs</span><span class="p">,</span> <span class="n">concat_path</span><span class="p">)</span>
    231. 

  231. </div>
    232. 

  232. <div class="viewcode-block" id="oases_merge_assembly"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.oases_merge_assembly">[docs]</a><span class="k">def</span> <span class="nf">oases_merge_assembly</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">merge_path</span><span class="p">,</span> <span class="n">merge_kmer</span><span class="p">,</span> <span class="n">kmers</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="n">workdir</span><span class="o">=</span><span class="s">&#39;./&#39;</span><span class="p">,</span> <span class="n">ins_length</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
    233. 

  233. 	<span class="sd">&quot;&quot;&quot;</span>
    234. 

  234. <span class="sd">	Implements the Oases-M protocol for merging several Oases assemblies, as</span>
    235. 

  235. <span class="sd">	described in:</span>
    236. 

  236. 

  237. <span class="sd">	Schulz, M. H., Zerbino, D. R., Vingron, M., &amp; Birney, E. (2012). Oases:</span>
    238. 

  238. <span class="sd">	Robust de novo RNA-seq assembly across the dynamic range of expression</span>
    239. 

  239. <span class="sd">	levels.  Bioinformatics (Oxford, England), 1-7.</span>
    240. 

  240. <span class="sd">	doi:10.1093/bioinformatics/bts094</span>
    241. 

  241. 

  242. <span class="sd">	Performs Oases assemblies sweeping over the provided `kmers` list, then</span>
    243. 

  243. <span class="sd">	performs a Oases merge assembly with `merge_kmer`.</span>
    244. 

  244. <span class="sd">	&quot;&quot;&quot;</span>
    245. 

  245. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">prefix</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="s">&#39;oases_merge_assembly&#39;</span><span class="p">)</span>
    246. 

  246. 	<span class="n">oases_clean</span><span class="p">(</span><span class="n">workdir</span><span class="p">)</span>
    247. 

  247. 	<span class="n">contig_list</span> <span class="o">=</span> <span class="n">oases_assemblies</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">kmers</span><span class="p">,</span> <span class="n">workdir</span><span class="p">,</span> <span class="n">min_length</span><span class="p">,</span> <span class="n">ins_length</span><span class="p">)</span>
    248. 

  248. 	<span class="n">wrappers</span><span class="o">.</span><span class="n">VelvetH</span><span class="p">(</span><span class="n">contig_list</span><span class="p">,</span> <span class="n">workdir</span><span class="p">,</span> <span class="n">kmer</span><span class="o">=</span><span class="n">merge_kmer</span><span class="p">,</span> <span class="n">merge</span><span class="o">=</span><span class="bp">True</span><span class="p">)</span>
    249. 

  249. 	<span class="n">wrappers</span><span class="o">.</span><span class="n">VelvetG</span><span class="p">(</span><span class="n">workdir</span><span class="p">,</span> <span class="n">merge</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="n">min_length</span><span class="p">)</span>
    250. 

  250. 	<span class="n">wrappers</span><span class="o">.</span><span class="n">Oases</span><span class="p">(</span><span class="n">workdir</span><span class="p">,</span> <span class="n">merge</span><span class="o">=</span><span class="bp">True</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="n">min_length</span><span class="p">)</span>
    251. 

  251. 	<span class="n">contigs</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">workdir</span><span class="p">,</span> <span class="s">&#39;transcripts.fa&#39;</span><span class="p">)</span>
    252. 

  252. 	<span class="n">shutil</span><span class="o">.</span><span class="n">move</span><span class="p">(</span><span class="n">contigs</span><span class="p">,</span> <span class="n">merge_path</span><span class="p">)</span>
    253. 

  253. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">log</span><span class="p">(</span><span class="s">&#39;kmer&#39;</span><span class="p">,</span> <span class="n">merge_kmer</span><span class="p">)</span>
    254. 

  254. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">log_path</span><span class="p">(</span><span class="n">merge_path</span><span class="p">)</span>
    255. 

  255. 	<span class="n">diagnostics</span><span class="o">.</span><span class="n">prefix</span><span class="o">.</span><span class="n">pop</span><span class="p">()</span>
    256. 

  256. </div>
    257. 

  257. <div class="viewcode-block" id="trinity_assembly"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.trinity_assembly">[docs]</a><span class="k">def</span> <span class="nf">trinity_assembly</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">inputs</span><span class="p">,</span> <span class="n">workdir</span><span class="o">=</span><span class="s">&#39;./&#39;</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="mi">100</span><span class="p">):</span>
    258. 

  258. 	<span class="n">wrappers</span><span class="o">.</span><span class="n">Trinity</span><span class="p">(</span><span class="n">inputs</span><span class="p">,</span> <span class="n">workdir</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="n">min_length</span><span class="p">,</span> <span class="n">seq_type</span><span class="o">=</span><span class="s">&#39;fq&#39;</span><span class="p">)</span>
    259. 

  259. 	<span class="n">commands</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">workdir</span><span class="p">,</span> <span class="s">&#39;chrysalis&#39;</span><span class="p">,</span> <span class="s">&#39;butterfly_commands.adj&#39;</span><span class="p">)</span>
    260. 

  260. 	<span class="n">contigs</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">workdir</span><span class="p">,</span> <span class="s">&#39;Trinity.fasta&#39;</span><span class="p">)</span>
    261. 

  261. 	<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">commands</span><span class="p">):</span>
    262. 

  262. 		<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">commands</span><span class="o">+</span><span class="s">&#39;.biolite&#39;</span><span class="p">,</span> <span class="s">&#39;w&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
    263. 

  263. 			<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="nb">open</span><span class="p">(</span><span class="n">commands</span><span class="p">):</span>
    264. 

  264. 				<span class="n">line</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">rstrip</span><span class="p">()</span>
    265. 

  265. 				<span class="n">comp</span> <span class="o">=</span> <span class="n">line</span><span class="p">[</span><span class="n">line</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="s">&#39;-C&#39;</span><span class="p">)</span><span class="o">+</span><span class="mi">3</span><span class="p">:]</span><span class="o">.</span><span class="n">partition</span><span class="p">(</span><span class="s">&#39; &#39;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span>
    266. 

  266. 				<span class="k">if</span> <span class="n">utils</span><span class="o">.</span><span class="n">count_lines</span><span class="p">(</span><span class="n">comp</span><span class="o">+</span><span class="s">&#39;.out&#39;</span><span class="p">)</span> <span class="o">&gt;</span> <span class="n">min_length</span><span class="p">:</span>
    267. 

  267. 					<span class="k">print</span> <span class="o">&gt;&gt;</span><span class="n">f</span><span class="p">,</span> <span class="n">line</span><span class="p">,</span> <span class="s">&#39;&amp;&amp; cat </span><span class="si">%s</span><span class="s">.allProbPaths.fasta &gt;&gt;</span><span class="si">%s</span><span class="s">&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">comp</span><span class="p">,</span> <span class="n">contigs</span><span class="p">)</span>
    268. 

  268. 		<span class="n">wrappers</span><span class="o">.</span><span class="n">ParallelButterfly</span><span class="p">(</span>
    269. 

  269. 			<span class="n">commands</span><span class="o">+</span><span class="s">&#39;.biolite&#39;</span><span class="p">,</span> <span class="s">&#39;--joblog&#39;</span><span class="p">,</span> <span class="s">&#39;butterfly.joblog.txt&#39;</span><span class="p">,</span>
    270. 

  270. 			<span class="n">threads</span><span class="o">=</span><span class="nb">max</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="nb">int</span><span class="p">(</span><span class="n">config</span><span class="o">.</span><span class="n">get_resource</span><span class="p">(</span><span class="s">&#39;threads&#39;</span><span class="p">))</span><span class="o">/</span><span class="mi">2</span><span class="p">),</span>
    271. 

  271. 			<span class="n">return_ok</span><span class="o">=</span><span class="bp">None</span><span class="p">)</span>
    272. 

  272. 	<span class="k">else</span><span class="p">:</span>
    273. 

  273. 		<span class="n">utils</span><span class="o">.</span><span class="n">die</span><span class="p">(</span><span class="s">&quot;no butterfly command output from Trinity&quot;</span><span class="p">)</span>
    274. 

  274. 	<span class="k">if</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">contigs</span><span class="p">):</span>
    275. 

  275. 		<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">contigs</span><span class="p">,</span> <span class="s">&#39;r&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f1</span><span class="p">,</span> <span class="nb">open</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="s">&#39;w&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f2</span><span class="p">:</span>
    276. 

  276. 			<span class="k">for</span> <span class="n">record</span> <span class="ow">in</span> <span class="n">SeqIO</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">f1</span><span class="p">,</span> <span class="s">&#39;fasta&#39;</span><span class="p">):</span>
    277. 

  277. 				<span class="n">match</span> <span class="o">=</span> <span class="n">trinity_header_pattern</span><span class="o">.</span><span class="n">match</span><span class="p">(</span><span class="n">record</span><span class="o">.</span><span class="n">description</span><span class="p">)</span>
    278. 

  278. 				<span class="k">if</span> <span class="n">match</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
    279. 

  279. 					<span class="n">num</span><span class="p">,</span> <span class="n">sub</span><span class="p">,</span> <span class="n">seq</span><span class="p">,</span> <span class="n">length</span><span class="p">,</span> <span class="n">path</span> <span class="o">=</span> <span class="n">match</span><span class="o">.</span><span class="n">groups</span><span class="p">()</span>
    280. 

  280. 					<span class="n">record</span><span class="o">.</span><span class="n">name</span> <span class="o">=</span> <span class="s">&#39;&#39;</span>
    281. 

  281. 					<span class="n">record</span><span class="o">.</span><span class="n">description</span> <span class="o">=</span> <span class="s">&#39;&#39;</span>
    282. 

  282. 					<span class="n">record</span><span class="o">.</span><span class="n">id</span> <span class="o">=</span> <span class="n">standard_contig_header</span><span class="o">.</span><span class="n">format</span><span class="p">(</span>
    283. 

  283. 						<span class="s">&quot;</span><span class="si">%s</span><span class="s">.</span><span class="si">%s</span><span class="s">&quot;</span> <span class="o">%</span> <span class="p">(</span><span class="n">num</span><span class="p">,</span> <span class="n">sub</span><span class="p">),</span> <span class="n">seq</span><span class="p">,</span>
    284. 

  284. 						<span class="nb">sum</span><span class="p">(</span><span class="n">c</span> <span class="o">==</span> <span class="s">&#39; &#39;</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">path</span><span class="p">),</span> <span class="n">length</span><span class="p">)</span>
    285. 

  285. 					<span class="n">SeqIO</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">record</span><span class="p">,</span> <span class="n">f2</span><span class="p">,</span> <span class="s">&#39;fasta&#39;</span><span class="p">)</span>
    286. 

  286. 	<span class="k">else</span><span class="p">:</span>
    287. 

  287. 		<span class="n">utils</span><span class="o">.</span><span class="n">die</span><span class="p">(</span><span class="s">&quot;no contig output from Trinity&quot;</span><span class="p">)</span>
    288. 

  288. </div>
    289. 

  289. <div class="viewcode-block" id="extract_oases_exemplars"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.extract_oases_exemplars">[docs]</a><span class="k">def</span> <span class="nf">extract_oases_exemplars</span><span class="p">(</span><span class="n">input_path</span><span class="p">,</span> <span class="n">output_path</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="mi">0</span><span class="p">):</span>
    290. 

  290. 	<span class="sd">&quot;&quot;&quot;</span>
    291. 

  291. <span class="sd">	Extracts a single exemplar transcript for each locus in an Oases assembly</span>
    292. 

  292. <span class="sd">	at `input_path` and writes it to `output_path`. Only transcripts longer</span>
    293. 

  293. <span class="sd">	than `min_length` are considered.</span>
    294. 

  294. 

  295. <span class="sd">	The exemplar is chosen as the transcript with the highest confidence score.</span>
    296. 

  296. <span class="sd">	&quot;&quot;&quot;</span>
    297. 

  297. 	<span class="c"># Dictionary with key locus and value sequence record</span>
    298. 

  298. 	<span class="n">exemplars</span> <span class="o">=</span> <span class="n">OrderedDict</span><span class="p">()</span>
    299. 

  299. 

  300. 	<span class="c"># Parse transcripts</span>
    301. 

  301. 	<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">input_path</span><span class="p">,</span> <span class="s">&#39;rU&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
    302. 

  302. 		<span class="k">for</span> <span class="n">record</span> <span class="ow">in</span> <span class="n">SeqIO</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">f</span><span class="p">,</span> <span class="s">&#39;fasta&#39;</span><span class="p">):</span>
    303. 

  303. 			<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">record</span><span class="o">.</span><span class="n">seq</span><span class="p">)</span> <span class="o">&lt;</span> <span class="n">min_length</span><span class="p">:</span>
    304. 

  304. 				<span class="k">continue</span>
    305. 

  305. 			<span class="n">header</span> <span class="o">=</span> <span class="n">unpack_oases_header</span><span class="p">(</span><span class="n">record</span><span class="o">.</span><span class="n">id</span><span class="p">)</span>
    306. 

  306. 			<span class="k">if</span> <span class="n">header</span><span class="o">.</span><span class="n">locus</span> <span class="ow">in</span> <span class="n">exemplars</span><span class="p">:</span>
    307. 

  307. 				<span class="n">old_header</span> <span class="o">=</span> <span class="n">unpack_oases_header</span><span class="p">(</span><span class="n">exemplars</span><span class="p">[</span><span class="n">header</span><span class="o">.</span><span class="n">locus</span><span class="p">]</span><span class="o">.</span><span class="n">id</span><span class="p">)</span>
    308. 

  308. 				<span class="c"># If the new confidence is higher, replace the current record</span>
    309. 

  309. 				<span class="k">if</span> <span class="nb">float</span><span class="p">(</span><span class="n">header</span><span class="o">.</span><span class="n">confidence</span><span class="p">)</span> <span class="o">&gt;</span> <span class="nb">float</span><span class="p">(</span><span class="n">old_header</span><span class="o">.</span><span class="n">confidence</span><span class="p">):</span>
    310. 

  310. 					<span class="n">exemplars</span><span class="p">[</span><span class="n">header</span><span class="o">.</span><span class="n">locus</span><span class="p">]</span> <span class="o">=</span> <span class="n">record</span>
    311. 

  311. 

  312. 				<span class="c"># If the confidences are the same, then replace the old record</span>
    313. 

  313. 				<span class="c"># if the new length is greater</span>
    314. 

  314. 				<span class="k">elif</span> <span class="nb">float</span><span class="p">(</span><span class="n">header</span><span class="o">.</span><span class="n">confidence</span><span class="p">)</span> <span class="o">==</span> <span class="nb">float</span><span class="p">(</span><span class="n">old_header</span><span class="o">.</span><span class="n">confidence</span><span class="p">):</span>
    315. 

  315. 					<span class="k">if</span> <span class="nb">int</span><span class="p">(</span><span class="n">header</span><span class="o">.</span><span class="n">length</span><span class="p">)</span> <span class="o">&gt;</span> <span class="nb">int</span><span class="p">(</span><span class="n">old_header</span><span class="o">.</span><span class="n">length</span><span class="p">):</span>
    316. 

  316. 						<span class="n">exemplars</span><span class="p">[</span><span class="n">header</span><span class="o">.</span><span class="n">locus</span><span class="p">]</span> <span class="o">=</span> <span class="n">record</span>
    317. 

  317. 			<span class="c"># Create an entry for the record of it didn&#39;t exist</span>
    318. 

  318. 			<span class="k">else</span><span class="p">:</span>
    319. 

  319. 				<span class="n">exemplars</span><span class="p">[</span><span class="n">header</span><span class="o">.</span><span class="n">locus</span><span class="p">]</span> <span class="o">=</span> <span class="n">record</span>
    320. 

  320. 

  321. 	<span class="c"># Write out the exemplars in the order of the loci</span>
    322. 

  322. 	<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">output_path</span><span class="p">,</span> <span class="s">&#39;w&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
    323. 

  323. 		<span class="n">SeqIO</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">exemplars</span><span class="o">.</span><span class="n">itervalues</span><span class="p">(),</span> <span class="n">f</span><span class="p">,</span> <span class="s">&quot;fasta&quot;</span><span class="p">)</span>
    324. 

  324. 

  325. </div>
    326. 

  326. <span class="n">BlastHit</span> <span class="o">=</span> <span class="n">namedtuple</span><span class="p">(</span><span class="s">&#39;BlastHit&#39;</span><span class="p">,</span> <span class="s">&quot;query title definition id evalue rank orient mask score bitscore length percent&quot;</span><span class="p">)</span>
    327. 

  327. 

  328. <span class="sd">&quot;&quot;&quot;</span>
    329. 

  329. <span class="sd">A namedtuple for storing several fields of a Blast hit.</span>
    330. 

  330. <span class="sd">&quot;&quot;&quot;</span>
    331. 

  331. 

  332. <div class="viewcode-block" id="blast_hits"><a class="viewcode-back" href="../../workflows.html#biolite.workflows.blast_hits">[docs]</a><span class="k">def</span> <span class="nf">blast_hits</span><span class="p">(</span><span class="n">xml_path</span><span class="p">,</span> <span class="n">nlimit</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
    333. 

  333. 	<span class="sd">&quot;&quot;&quot;</span>
    334. 

  334. <span class="sd">	Reads an XML formatted BLAST report, and yields one named tuple per</span>
    335. 

  335. <span class="sd">	alignment, i.e.  per hit between a query and a subject. Each named tuple</span>
    336. 

  336. <span class="sd">	has the following elements:</span>
    337. 

  337. <span class="sd">	</span>
    338. 

  338. <span class="sd">	query title definition id evalue rank orient mask score bitscore length percent</span>
    339. 

  339. 

  340. <span class="sd">	where:</span>
    341. 

  341. 

  342. <span class="sd">	* orient is 1 if query and subject are in the same direction, 2 if they are</span>
    343. 

  343. <span class="sd">	  in the opposite direction, and 0 if direction is inconsistent across hsp&#39;s</span>
    344. 

  344. <span class="sd">	* evalue is the minimum evalue across hsp&#39;s</span>
    345. 

  345. <span class="sd">	* score, bitcore and length are maximal across hsp&#39;s</span>
    346. 

  346. <span class="sd">	&quot;&quot;&quot;</span>
    347. 

  347. 	<span class="k">with</span> <span class="nb">open</span><span class="p">(</span><span class="n">xml_path</span><span class="p">,</span> <span class="s">&#39;r&#39;</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
    348. 

  348. 		<span class="c"># Loop over the blast records.</span>
    349. 

  349. 		<span class="k">for</span> <span class="n">entry</span> <span class="ow">in</span> <span class="n">NCBIXML</span><span class="o">.</span><span class="n">parse</span><span class="p">(</span><span class="n">f</span><span class="p">):</span>
    350. 

  350. 			<span class="c"># Limit the number of alignments per query, if nlimit is set.</span>
    351. 

  351. 			<span class="k">if</span> <span class="n">nlimit</span><span class="p">:</span>
    352. 

  352. 				<span class="n">alignments</span> <span class="o">=</span> <span class="n">entry</span><span class="o">.</span><span class="n">alignments</span><span class="p">[:</span><span class="n">nlimit</span><span class="p">]</span>
    353. 

  353. 			<span class="k">else</span><span class="p">:</span>
    354. 

  354. 				<span class="n">alignments</span> <span class="o">=</span> <span class="n">entry</span><span class="o">.</span><span class="n">alignments</span>
    355. 

  355. 			<span class="n">rank</span> <span class="o">=</span> <span class="mi">0</span>
    356. 

  356. 			
    357. 

  357. 			<span class="c"># Loop over the alignments.</span>
    358. 

  358. 			<span class="k">for</span> <span class="n">alignment</span> <span class="ow">in</span> <span class="n">alignments</span><span class="p">:</span>
    359. 

  359. 				<span class="n">rank</span> <span class="o">=</span> <span class="n">rank</span> <span class="o">+</span> <span class="mi">1</span>
    360. 

  360. 				<span class="n">evalue</span> <span class="o">=</span> <span class="n">sys</span><span class="o">.</span><span class="n">maxint</span>
    361. 

  361. 				<span class="n">score</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span>
    362. 

  362. 				<span class="n">bitscore</span> <span class="o">=</span> <span class="o">-</span><span class="mf">1.0</span>
    363. 

  363. 				<span class="n">length</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span>
    364. 

  364. 				<span class="n">orient</span> <span class="o">=</span> <span class="mi">0</span>
    365. 

  365. 				
    366. 

  366. 				<span class="c"># Initialize a string to hold the sites that are within hsp&#39;s</span>
    367. 

  367. 				<span class="c"># String has the same length as the query Sites with 0 are not</span>
    368. 

  368. 				<span class="c"># in any hsp, sites that are nonzero are in hsps</span>
    369. 

  369. 				<span class="n">mask</span> <span class="o">=</span> <span class="p">[</span><span class="s">&#39;0&#39;</span><span class="p">]</span> <span class="o">*</span> <span class="n">entry</span><span class="o">.</span><span class="n">query_length</span>
    370. 

  370. 				
    371. 

  371. 				<span class="c"># Loop over the hsp&#39;s to get the lowest evalue and the</span>
    372. 

  372. 				<span class="c"># orientation.</span>
    373. 

  373. 				<span class="k">for</span> <span class="n">hsp</span> <span class="ow">in</span> <span class="n">alignment</span><span class="o">.</span><span class="n">hsps</span><span class="p">:</span>
    374. 

  374. 					<span class="c"># Check if the orient is the same by comparing</span>
    375. 

  375. 					<span class="c"># orientation of query and subject.</span>
    376. 

  376. 					<span class="k">if</span> <span class="p">(</span><span class="n">hsp</span><span class="o">.</span><span class="n">query_start</span> <span class="o">&lt;</span> <span class="n">hsp</span><span class="o">.</span><span class="n">query_end</span><span class="p">)</span> <span class="o">==</span> \
    377. 

  377. 					   <span class="p">(</span><span class="n">hsp</span><span class="o">.</span><span class="n">sbjct_start</span> <span class="o">&lt;</span> <span class="n">hsp</span><span class="o">.</span><span class="n">sbjct_end</span><span class="p">):</span>
    378. 

  378. 						<span class="n">orient</span> <span class="o">|=</span> <span class="mi">1</span>
    379. 

  379. 					<span class="c"># Or different.</span>
    380. 

  380. 					<span class="k">else</span><span class="p">:</span>
    381. 

  381. 						<span class="n">orient</span> <span class="o">|=</span> <span class="mi">2</span>
    382. 

  382. 					<span class="c"># Record the lowest e-value.</span>
    383. 

  383. 					<span class="n">evalue</span> <span class="o">=</span> <span class="nb">min</span><span class="p">(</span><span class="n">evalue</span><span class="p">,</span> <span class="n">hsp</span><span class="o">.</span><span class="n">expect</span><span class="p">)</span>
    384. 

  384. 					
    385. 

  385. 					<span class="c"># Create a 2 element list with the starting and end point</span>
    386. 

  386. 					<span class="c"># of the hsp, adjusted to be 0 offset rather than 1 offset</span>
    387. 

  387. 					<span class="n">ends</span> <span class="o">=</span> <span class="p">[</span><span class="n">hsp</span><span class="o">.</span><span class="n">query_start</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="n">hsp</span><span class="o">.</span><span class="n">query_end</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span>
    388. 

  388. 					
    389. 

  389. 					<span class="c"># Sort the list to orient it so that start is less then</span>
    390. 

  390. 					<span class="c"># finish, then loop over the string and set the sites in</span>
    391. 

  391. 					<span class="c"># the hsp range to &#39;1&#39;</span>
    392. 

  392. 					<span class="n">ends</span><span class="o">.</span><span class="n">sort</span><span class="p">()</span>
    393. 

  393. 					<span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">ends</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="n">ends</span><span class="p">[</span><span class="mi">1</span><span class="p">]</span> <span class="o">+</span> <span class="mi">1</span><span class="p">):</span>
    394. 

  394. 						<span class="n">mask</span><span class="p">[</span><span class="n">i</span><span class="p">]</span> <span class="o">=</span> <span class="s">&#39;1&#39;</span>
    395. 

  395. 					
    396. 

  396. 					<span class="c"># Convert list to string</span>
    397. 

  397. 					<span class="n">mask_string</span> <span class="o">=</span> <span class="s">&#39;&#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">mask</span><span class="p">)</span>
    398. 

  398. 

  399. 					<span class="c"># Record the highest score.</span>
    400. 

  400.