refactoring module docstring

docs/build/.buildinfo

@@ -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: 88dee1dfb417bc401516c5f62c9b42d9
+config: 6ef85c61a07ec8e9f0ed07676e851c59
 tags: 645f666f9bcd5a90fca523b33c5a78b7

docs/build/_modules/ensembl/tools/anno/protein_annotation/genblast.html

@@ -57,7 +57,6 @@ <h1>Source code for ensembl.tools.anno.protein_annotation.genblast</h1><div clas
 <span class="sd">the sequences have undergone significant evolutionary changes.</span>
 <span class="sd">This capability makes it a valuable resource for researchers studying gene</span>
 <span class="sd">evolution, gene families, and gene function across diverse species.</span>
-
 <span class="sd">GenBlast has been widely used in various genomic analyses and is available as</span>
 <span class="sd">a standalone command-line tool or as part of different bioinformatics pipelines.</span>
 <span class="sd">Researchers in the field of comparative genomics and gene function analysis</span>
@@ -110,17 +109,31 @@ <h1>Source code for ensembl.tools.anno.protein_annotation.genblast</h1><div clas
 <span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Executes GenBlast on genomic slices</span>
-<span class="sd">    Args:</span>
-<span class="sd">            masked_genome : Masked genome file path.</span>
-<span class="sd">            output_dir: Working directory path.</span>
-<span class="sd">            protein_dataset: Protein dataset (Uniprot/OrthoDb) path.</span>
-<span class="sd">            genblast_timeout_secs: Time for timeout (sec).</span>
-<span class="sd">            max_intron_length: Maximum intron length.</span>
-<span class="sd">            genblast_bin : Software path.</span>
-<span class="sd">            convert2blastmask_bin: Software path.</span>
-<span class="sd">            makeblastdb_bin : Software path.</span>
-<span class="sd">            genblast_timeout: seconds</span>
-<span class="sd">            num_threads: int, number of threads.</span>
+<span class="sd">            :param masked_genome: Masked genome file path.</span>
+<span class="sd">            :type masked_genome: Path</span>
+<span class="sd">            :param output_dir: Working directory path.</span>
+<span class="sd">            :type output_dir: Path</span>
+<span class="sd">            :param protein_dataset: Protein dataset (Uniprot/OrthoDb) path.</span>
+<span class="sd">            :type protein_dataset: Path</span>
+<span class="sd">            :param genblast_timeout_secs: Time for timeout (sec).</span>
+<span class="sd">            :type genblast_timeout_secs: int, default 10800</span>
+<span class="sd">            :param max_intron_length: Maximum intron length.</span>
+<span class="sd">            :type max_intron_length: int </span>
+<span class="sd">            :param genblast_bin: Software path.</span>
+<span class="sd">            :type genblast_bin: Path, default genblast</span>
+<span class="sd">            :param convert2blastmask_bin: Software path.</span>
+<span class="sd">            :type convert2blastmask_bin: Path, default convert2blastmask</span>
+<span class="sd">            :param makeblastdb_bin: Software path.</span>
+<span class="sd">            :type makeblastdb_bin: Path, default makeblastdb</span>
+<span class="sd">            :param genblast_timeout: seconds</span>
+<span class="sd">            :type genblast_timeout: int, default 1</span>
+<span class="sd">            :param num_threads: int, number of threads.</span>
+<span class="sd">            :type num_threads:int, default 1 </span>
+<span class="sd">            :param protein_set: Source </span>
+<span class="sd">            :type str: [&quot;uniprot&quot;, &quot;orthodb&quot;]</span>
+<span class="sd">                            </span>
+<span class="sd">            :return: None</span>
+<span class="sd">            :rtype: None</span>
 <span class="sd">    &quot;&quot;&quot;</span>
 
     <span class="n">check_exe</span><span class="p">(</span><span class="n">genblast_bin</span><span class="p">)</span>

docs/build/_modules/ensembl/tools/anno/repeat_annotation/dust.html

@@ -95,11 +95,17 @@ <h1>Source code for ensembl.tools.anno.repeat_annotation.dust</h1><div class="hi
 <span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Run Dust on genomic slices with mutiprocessing</span>
-<span class="sd">    Args:</span>
-<span class="sd">        genome_file : Genome file path.</span>
-<span class="sd">        output_dir : Working directory path.</span>
-<span class="sd">        dust_bin : Dust software path.</span>
-<span class="sd">        num_threads: Number of threads.</span>
+<span class="sd">        :param genome_file: Genome file path.</span>
+<span class="sd">        :type genome_file: PathLike</span>
+<span class="sd">        :param output_dir: Working directory path.</span>
+<span class="sd">        :type output_dir: Path</span>
+<span class="sd">        :param dust_bin: Dust software path.</span>
+<span class="sd">        :type dust_bin: Path, default dustmasker</span>
+<span class="sd">        :param num_threads: Number of threads.</span>
+<span class="sd">        :type num_threads: int, default 1</span>
+<span class="sd">                </span>
+<span class="sd">        :return: None</span>
+<span class="sd">        :rtype: None</span>
 <span class="sd">    &quot;&quot;&quot;</span>
 
     <span class="n">check_exe</span><span class="p">(</span><span class="n">dust_bin</span><span class="p">)</span>
@@ -113,9 +119,7 @@ <h1>Source code for ensembl.tools.anno.repeat_annotation.dust</h1><div class="hi
             <span class="k">return</span>
     <span class="n">logger</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s2">&quot;Creating list of genomic slices&quot;</span><span class="p">)</span>
     <span class="n">seq_region_to_length</span> <span class="o">=</span> <span class="n">get_seq_region_length</span><span class="p">(</span><span class="n">genome_file</span><span class="p">,</span> <span class="mi">5000</span><span class="p">)</span>
-    <span class="n">slice_ids_per_region</span> <span class="o">=</span> <span class="n">get_slice_id</span><span class="p">(</span>
-        <span class="n">seq_region_to_length</span><span class="p">,</span> <span class="n">slice_size</span><span class="o">=</span><span class="mi">1000000</span><span class="p">,</span> <span class="n">overlap</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="mi">5000</span>
-    <span class="p">)</span>
+    <span class="n">slice_ids_per_region</span> <span class="o">=</span> <span class="n">get_slice_id</span><span class="p">(</span><span class="n">seq_region_to_length</span><span class="p">,</span> <span class="n">slice_size</span><span class="o">=</span><span class="mi">1000000</span><span class="p">,</span> <span class="n">overlap</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span> <span class="n">min_length</span><span class="o">=</span><span class="mi">5000</span><span class="p">)</span>
     <span class="n">dust_cmd</span> <span class="o">=</span> <span class="p">[</span><span class="n">dust_bin</span><span class="p">,</span> <span class="s2">&quot;-in&quot;</span><span class="p">]</span>
     <span class="n">pool</span> <span class="o">=</span> <span class="n">multiprocessing</span><span class="o">.</span><span class="n">Pool</span><span class="p">(</span><span class="n">num_threads</span><span class="p">)</span>  <span class="c1"># pylint: disable=consider-using-with</span>
     <span class="k">for</span> <span class="n">slice_id</span> <span class="ow">in</span> <span class="n">slice_ids_per_region</span><span class="p">:</span>
@@ -197,8 +201,7 @@ <h1>Source code for ensembl.tools.anno.repeat_annotation.dust</h1><div class="hi
                 <span class="n">start</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">result_match</span><span class="o">.</span><span class="n">group</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="n">end</span> <span class="o">=</span> <span class="nb">int</span><span class="p">(</span><span class="n">result_match</span><span class="o">.</span><span class="n">group</span><span class="p">(</span><span class="mi">2</span><span class="p">))</span> <span class="o">+</span> <span class="mi">1</span>
                 <span class="n">gtf_line</span> <span class="o">=</span> <span class="p">(</span>
-                    <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">region_name</span><span class="si">}</span><span class="se">\t</span><span class="s2">Dust</span><span class="se">\t</span><span class="s2">repeat</span><span class="se">\t</span><span class="si">{</span><span class="n">start</span><span class="si">}</span><span class="se">\t</span><span class="s2">&quot;</span>
-                    <span class="sa">f</span><span class="s1">&#39;</span><span class="si">{</span><span class="n">end</span><span class="si">}</span><span class="se">\t</span><span class="s1">.</span><span class="se">\t</span><span class="s1">+</span><span class="se">\t</span><span class="s1">.</span><span class="se">\t</span><span class="s1">repeat_id &quot;</span><span class="si">{</span><span class="n">repeat_count</span><span class="si">}</span><span class="s1">&quot;;</span><span class="se">\n</span><span class="s1">&#39;</span>
+                    <span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">region_name</span><span class="si">}</span><span class="se">\t</span><span class="s2">Dust</span><span class="se">\t</span><span class="s2">repeat</span><span class="se">\t</span><span class="si">{</span><span class="n">start</span><span class="si">}</span><span class="se">\t</span><span class="s2">&quot;</span> <span class="sa">f</span><span class="s1">&#39;</span><span class="si">{</span><span class="n">end</span><span class="si">}</span><span class="se">\t</span><span class="s1">.</span><span class="se">\t</span><span class="s1">+</span><span class="se">\t</span><span class="s1">.</span><span class="se">\t</span><span class="s1">repeat_id &quot;</span><span class="si">{</span><span class="n">repeat_count</span><span class="si">}</span><span class="s1">&quot;;</span><span class="se">\n</span><span class="s1">&#39;</span>
                 <span class="p">)</span>
                 <span class="n">dust_out</span><span class="o">.</span><span class="n">write</span><span class="p">(</span><span class="n">gtf_line</span><span class="p">)</span>
                 <span class="n">repeat_count</span> <span class="o">+=</span> <span class="mi">1</span>
@@ -207,20 +210,14 @@ <h1>Source code for ensembl.tools.anno.repeat_annotation.dust</h1><div class="hi
 <span class="k">class</span> <span class="nc">InputSchema</span><span class="p">(</span><span class="n">argschema</span><span class="o">.</span><span class="n">ArgSchema</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Input arguments expected to run DustMasker.&quot;&quot;&quot;</span>
 
-    <span class="n">genome_file</span> <span class="o">=</span> <span class="n">argschema</span><span class="o">.</span><span class="n">fields</span><span class="o">.</span><span class="n">InputFile</span><span class="p">(</span>
-        <span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">description</span><span class="o">=</span><span class="s2">&quot;Genome file path&quot;</span>
-    <span class="p">)</span>
-    <span class="n">output_dir</span> <span class="o">=</span> <span class="n">argschema</span><span class="o">.</span><span class="n">fields</span><span class="o">.</span><span class="n">OutputDir</span><span class="p">(</span>
-        <span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">description</span><span class="o">=</span><span class="s2">&quot;Output directory path&quot;</span>
-    <span class="p">)</span>
+    <span class="n">genome_file</span> <span class="o">=</span> <span class="n">argschema</span><span class="o">.</span><span class="n">fields</span><span class="o">.</span><span class="n">InputFile</span><span class="p">(</span><span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">description</span><span class="o">=</span><span class="s2">&quot;Genome file path&quot;</span><span class="p">)</span>
+    <span class="n">output_dir</span> <span class="o">=</span> <span class="n">argschema</span><span class="o">.</span><span class="n">fields</span><span class="o">.</span><span class="n">OutputDir</span><span class="p">(</span><span class="n">required</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="n">description</span><span class="o">=</span><span class="s2">&quot;Output directory path&quot;</span><span class="p">)</span>
     <span class="n">dust_bin</span> <span class="o">=</span> <span class="n">argschema</span><span class="o">.</span><span class="n">fields</span><span class="o">.</span><span class="n">String</span><span class="p">(</span>
         <span class="n">required</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
         <span class="n">default</span><span class="o">=</span><span class="s2">&quot;dustmasker&quot;</span><span class="p">,</span>
         <span class="n">description</span><span class="o">=</span><span class="s2">&quot;Dust executable path&quot;</span><span class="p">,</span>
     <span class="p">)</span>
-    <span class="n">num_threads</span> <span class="o">=</span> <span class="n">argschema</span><span class="o">.</span><span class="n">fields</span><span class="o">.</span><span class="n">Integer</span><span class="p">(</span>
-        <span class="n">required</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">description</span><span class="o">=</span><span class="s2">&quot;Number of threads&quot;</span>
-    <span class="p">)</span>
+    <span class="n">num_threads</span> <span class="o">=</span> <span class="n">argschema</span><span class="o">.</span><span class="n">fields</span><span class="o">.</span><span class="n">Integer</span><span class="p">(</span><span class="n">required</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">description</span><span class="o">=</span><span class="s2">&quot;Number of threads&quot;</span><span class="p">)</span>
 
 
 <span class="k">def</span> <span class="nf">main</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>

docs/build/_modules/ensembl/tools/anno/repeat_annotation/red.html

@@ -80,14 +80,15 @@ <h1>Source code for ensembl.tools.anno.repeat_annotation.red</h1><div class="hig
 <span class="k">def</span> <span class="nf">run_red</span><span class="p">(</span><span class="n">genome_file</span><span class="p">:</span> <span class="n">Path</span><span class="p">,</span> <span class="n">output_dir</span><span class="p">:</span> <span class="n">Path</span><span class="p">,</span> <span class="n">red_bin</span><span class="p">:</span> <span class="n">Path</span> <span class="o">=</span> <span class="n">Path</span><span class="p">(</span><span class="s2">&quot;Red&quot;</span><span class="p">),)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Run Red on genome file</span>
-
-<span class="sd">    Args:</span>
-<span class="sd">        genome_file : Genome file path.</span>
-<span class="sd">        output_dir : Working directory path.</span>
-<span class="sd">        red_bin : Red software path.</span>
-
-<span class="sd">    Return:</span>
-<span class="sd">        masked genome file</span>
+<span class="sd">        :param genome_file: Genome file path.</span>
+<span class="sd">        :type genome_file: Path</span>
+<span class="sd">        :param output_dir: Working directory path.</span>
+<span class="sd">        :type output_dir: Path</span>
+<span class="sd">        :param red_bin: Red software path.</span>
+<span class="sd">        :type red_bin: Path, default Red</span>
+<span class="sd">        </span>
+<span class="sd">        :return: Masked genome file</span>
+<span class="sd">        :rtype: str</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="n">check_exe</span><span class="p">(</span><span class="n">red_bin</span><span class="p">)</span>
     <span class="n">red_dir</span> <span class="o">=</span> <span class="n">create_dir</span><span class="p">(</span><span class="n">output_dir</span><span class="p">,</span> <span class="s2">&quot;red_output&quot;</span><span class="p">)</span>

docs/build/_modules/ensembl/tools/anno/repeat_annotation/repeatmasker.html

@@ -96,14 +96,24 @@ <h1>Source code for ensembl.tools.anno.repeat_annotation.repeatmasker</h1><div c
 
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Executes RepeatMasker on the genome slices and stores the final annotation.gtf in repeatmasker_output</span>
-<span class="sd">    Args:</span>
-<span class="sd">        genome_file : Genome file path.</span>
-<span class="sd">        repeatmasker_path : RepeatMasker executable path.</span>
-<span class="sd">        library : Custom repeat library.</span>
-<span class="sd">        species :Species name.</span>
-<span class="sd">        output_dir : Output directory path.</span>
-<span class="sd">        num_threads: Number of threads.</span>
 
+<span class="sd">        :param genome_file: Genome file path.</span>
+<span class="sd">        :type genome_file: PathLike</span>
+<span class="sd">        :param output_dir: Output directory path.</span>
+<span class="sd">        :type output_dir: Path</span>
+<span class="sd">        :param repeatmasker_bin: RepeatMasker executable path.</span>
+<span class="sd">        :type repeatmasker_bin: Path, default RepeatMasker</span>
+<span class="sd">        :param library: Custom repeat library.</span>
+<span class="sd">        :type library: str</span>
+<span class="sd">        :param repeatmasker_engine: RepeatMasker engine.</span>
+<span class="sd">        :type repeatmasker_engine: str, default rmblast</span>
+<span class="sd">        :param species: Species name.</span>
+<span class="sd">        :type species: str</span>
+<span class="sd">        :param num_threads: Number of threads.</span>
+<span class="sd">        :type num_threads: int, default 1</span>
+<span class="sd">        </span>
+<span class="sd">        :return: None</span>
+<span class="sd">        :rtype: None</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="n">check_exe</span><span class="p">(</span><span class="n">repeatmasker_bin</span><span class="p">)</span>
     <span class="n">repeatmasker_dir</span> <span class="o">=</span> <span class="n">create_dir</span><span class="p">(</span><span class="n">output_dir</span><span class="p">,</span> <span class="s2">&quot;repeatmasker_output&quot;</span><span class="p">)</span>