GENEPI 2.0.4

Author: chester

CHANGELOG.md

@@ -2,6 +2,10 @@
 
 All notable changes to this project will be documented in this file.
 
+## [2.0.4] - 2019-12-12
+### Added
+- Add sliding windows scanning to deal with mega genes
+
 ## [2.0.3] - 2019-10-13
 ### Added
 - Add GenEpi's documentation to Read the Docs

docs/build/doctrees/api.doctree

@@ -1,4 +1,4 @@
 # Sphinx build info version 1
 # This file hashes the configuration used when building these files. When it is not found, a full rebuild will be done.
-config: bdde69301557972f7da667f1cf6b26c5
+config: 4070760631a128e8fb06e9c0d07ff53d
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/build/doctrees/environment.pickle

@@ -362,6 +362,14 @@ <h1>Source code for genepi.step5_crossGeneEpistasis_Lasso</h1><div class="highli
     <span class="c1">#-------------------------</span>
     <span class="c1"># preprocess data</span>
     <span class="c1">#-------------------------</span>
+    <span class="c1">### f regression feature selection</span>
+    <span class="n">np_fRegression</span> <span class="o">=</span> <span class="o">-</span><span class="n">np</span><span class="o">.</span><span class="n">log10</span><span class="p">(</span><span class="n">f_regression</span><span class="p">(</span><span class="n">np_genotype</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">int</span><span class="p">),</span> <span class="n">np_phenotype</span><span class="p">[:,</span> <span class="o">-</span><span class="mi">1</span><span class="p">]</span><span class="o">.</span><span class="n">astype</span><span class="p">(</span><span class="nb">float</span><span class="p">))[</span><span class="mi">1</span><span class="p">])</span>
+    <span class="n">np_selectedIdx</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">x</span> <span class="o">&gt;</span> <span class="mi">5</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">np_fRegression</span><span class="p">])</span>
+    <span class="n">np_genotype</span> <span class="o">=</span> <span class="n">np_genotype</span><span class="p">[:,</span> <span class="n">np_selectedIdx</span><span class="p">]</span>
+    <span class="n">np_genotype_rsid</span> <span class="o">=</span> <span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">np_selectedIdx</span><span class="p">]</span>
+    <span class="k">if</span> <span class="n">np_genotype_rsid</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span>
+        <span class="k">return</span> <span class="mf">0.0</span>
+
     <span class="c1">### select degree 1 feature</span>
     <span class="n">np_genotype_rsid_degree</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">x</span><span class="p">)</span><span class="o">.</span><span class="n">count</span><span class="p">(</span><span class="s1">&#39;*&#39;</span><span class="p">)</span> <span class="o">+</span> <span class="mi">1</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">np_genotype_rsid</span><span class="p">])</span>
     <span class="n">np_selectedIdx</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">x</span> <span class="o">==</span> <span class="mi">1</span> <span class="k">for</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">np_genotype_rsid_degree</span><span class="p">])</span>
@@ -429,11 +437,11 @@ <h1>Source code for genepi.step5_crossGeneEpistasis_Lasso</h1><div class="highli
         <span class="k">for</span> <span class="n">idx_feature</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">np_genotype_rsid</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]):</span>
             <span class="c1">### if this feature is single gene epistasis</span>
             <span class="k">if</span> <span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]</span> <span class="ow">in</span> <span class="n">dict_geneMap</span><span class="o">.</span><span class="n">keys</span><span class="p">():</span>
-                <span class="n">str_thisOutput</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_weight</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_fRegression</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_genotypeFreq</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">dict_geneMap</span><span class="p">[</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">dict_score</span><span class="p">[</span><span class="n">dict_geneMap</span><span class="p">[</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]]])</span> <span class="o">+</span> <span class="s2">&quot;</span><span class="se">\n</span><span class="s2">&quot;</span>
+                <span class="n">str_thisOutput</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_weight</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_fRegression</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_genotypeFreq</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">dict_geneMap</span><span class="p">[</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]])</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;@&quot;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">dict_score</span><span class="p">[</span><span class="n">dict_geneMap</span><span class="p">[</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]]])</span> <span class="o">+</span> <span class="s2">&quot;</span><span class="se">\n</span><span class="s2">&quot;</span>
                 <span class="n">file_outputFile</span><span class="o">.</span><span class="n">writelines</span><span class="p">(</span><span class="n">str_thisOutput</span><span class="p">)</span>
             <span class="c1">### else this feature is cross gene epistasis</span>
             <span class="k">else</span><span class="p">:</span>
-                <span class="n">str_thisOutput</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_weight</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_fRegression</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_genotypeFreq</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">dict_geneMap</span><span class="p">[</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;*&quot;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]])</span> <span class="o">+</span> <span class="s2">&quot;*&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">dict_geneMap</span><span class="p">[</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;*&quot;</span><span class="p">)[</span><span class="mi">1</span><span class="p">]])</span> <span class="o">+</span> <span class="s2">&quot;, &quot;</span> <span class="o">+</span> <span class="s2">&quot;</span><span class="se">\n</span><span class="s2">&quot;</span>
+                <span class="n">str_thisOutput</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_weight</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_fRegression</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">np_genotypeFreq</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">])</span> <span class="o">+</span> <span class="s2">&quot;,&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">dict_geneMap</span><span class="p">[</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;*&quot;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]])</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;@&quot;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="s2">&quot;*&quot;</span> <span class="o">+</span> <span class="nb">str</span><span class="p">(</span><span class="n">dict_geneMap</span><span class="p">[</span><span class="n">np_genotype_rsid</span><span class="p">[</span><span class="n">idx_feature</span><span class="p">,]</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;*&quot;</span><span class="p">)[</span><span class="mi">1</span><span class="p">]])</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s2">&quot;@&quot;</span><span class="p">)[</span><span class="mi">0</span><span class="p">]</span> <span class="o">+</span> <span class="s2">&quot;, &quot;</span> <span class="o">+</span> <span class="s2">&quot;</span><span class="se">\n</span><span class="s2">&quot;</span>
                 <span class="n">file_outputFile</span><span class="o">.</span><span class="n">writelines</span><span class="p">(</span><span class="n">str_thisOutput</span><span class="p">)</span>
 
     <span class="c1">### output feature</span>