Deploying to gh-pages from @ 0a4765c 🚀

_modules/pandasaurus_cxg/anndata_analyzer.html

@@ -259,7 +259,9 @@ <h1>Source code for pandasaurus_cxg.anndata_analyzer</h1><div class="highlight">
         <span class="n">enriched_df</span> <span class="o">=</span> <span class="n">enricher</span><span class="o">.</span><span class="n">enricher</span><span class="o">.</span><span class="n">enriched_df</span>
         <span class="k">if</span> <span class="n">enriched_df</span><span class="o">.</span><span class="n">empty</span><span class="p">:</span>
             <span class="k">return</span> <span class="n">enriched_df</span>
-        <span class="k">return</span> <span class="n">enriched_df</span><span class="p">[</span><span class="n">enriched_df</span><span class="p">[</span><span class="s2">&quot;o&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="n">enricher</span><span class="o">.</span><span class="n">seed_list</span><span class="p">)][[</span><span class="s2">&quot;s_label&quot;</span><span class="p">,</span> <span class="s2">&quot;o_label&quot;</span><span class="p">]]</span>
+        <span class="k">return</span> <span class="n">enriched_df</span><span class="p">[</span><span class="n">enriched_df</span><span class="p">[</span><span class="s2">&quot;o&quot;</span><span class="p">]</span><span class="o">.</span><span class="n">isin</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">enricher</span><span class="o">.</span><span class="n">seed_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">()))][</span>
+            <span class="p">[</span><span class="s2">&quot;s_label&quot;</span><span class="p">,</span> <span class="s2">&quot;o_label&quot;</span><span class="p">]</span>
+        <span class="p">]</span>
 
     <span class="k">def</span> <span class="nf">_filter_data_and_drop_duplicates</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">field_name_1</span><span class="p">,</span> <span class="n">field_name_2</span><span class="p">,</span> <span class="n">disease</span><span class="p">):</span>
         <span class="c1"># Filter the data based on the disease condition</span>

_modules/pandasaurus_cxg/anndata_enricher.html

@@ -121,8 +121,12 @@ <h1>Source code for pandasaurus_cxg.anndata_enricher</h1><div class="highlight">
             <span class="n">ontology_list_for_slims</span> <span class="o">=</span> <span class="p">[</span><span class="s2">&quot;Cell Ontology&quot;</span><span class="p">]</span>
         <span class="c1"># TODO Do we need to keep whole anndata? Would it be enough to keep the obs only?</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">anndata</span> <span class="o">=</span> <span class="n">anndata</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">seed_list</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">anndata</span><span class="o">.</span><span class="n">obs</span><span class="p">[</span><span class="n">cell_type_field</span><span class="p">]</span><span class="o">.</span><span class="n">unique</span><span class="p">()</span><span class="o">.</span><span class="n">tolist</span><span class="p">()</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">enricher</span> <span class="o">=</span> <span class="n">Query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed_list</span><span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">seed_dict</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span>
+            <span class="bp">self</span><span class="o">.</span><span class="n">anndata</span><span class="o">.</span><span class="n">obs</span><span class="o">.</span><span class="n">drop_duplicates</span><span class="p">(</span><span class="n">subset</span><span class="o">=</span><span class="p">[</span><span class="n">cell_type_field</span><span class="p">,</span> <span class="s2">&quot;cell_type&quot;</span><span class="p">])[</span>
+                <span class="p">[</span><span class="n">cell_type_field</span><span class="p">,</span> <span class="s2">&quot;cell_type&quot;</span><span class="p">]</span>
+            <span class="p">]</span><span class="o">.</span><span class="n">values</span>
+        <span class="p">)</span>
+        <span class="bp">self</span><span class="o">.</span><span class="n">enricher</span> <span class="o">=</span> <span class="n">Query</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">()))</span>
         <span class="k">try</span><span class="p">:</span>
             <span class="n">unique_context</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">anndata</span><span class="o">.</span><span class="n">obs</span><span class="p">[</span>
                 <span class="p">[</span><span class="n">context_field</span><span class="p">,</span> <span class="n">context_field_label</span><span class="p">]</span>
@@ -324,7 +328,7 @@ <h1>Source code for pandasaurus_cxg.anndata_enricher</h1><div class="highlight">
 <span class="sd">        Args:</span>
 <span class="sd">            property_list (List[str]): The list of properties to include in the enrichment analysis.</span>
 <span class="sd">        &quot;&quot;&quot;</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">enricher</span> <span class="o">=</span> <span class="n">Query</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed_list</span><span class="p">,</span> <span class="n">property_list</span><span class="p">)</span></div>
+        <span class="bp">self</span><span class="o">.</span><span class="n">enricher</span> <span class="o">=</span> <span class="n">Query</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">seed_dict</span><span class="o">.</span><span class="n">keys</span><span class="p">()),</span> <span class="n">property_list</span><span class="p">)</span></div>
 
 
 <div class="viewcode-block" id="AnndataEnricher.validate_slim_list">

_modules/pandasaurus_cxg/graph_generator/graph_generator.html

@@ -222,43 +222,13 @@ <h1>Source code for pandasaurus_cxg.graph_generator.graph_generator</h1><div cla
                     <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">resource</span><span class="p">,</span> <span class="n">subcluster</span><span class="p">,</span> <span class="n">s</span><span class="p">))</span>
 
         <span class="c1"># transitive reduction step</span>
-        <span class="bp">self</span><span class="o">.</span><span class="n">graph</span> <span class="o">=</span> <span class="n">graphgen</span><span class="o">.</span><span class="n">apply_transitive_reduction</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="p">,</span> <span class="p">[</span><span class="n">subcluster</span><span class="o">.</span><span class="n">toPython</span><span class="p">()])</span></div>
+        <span class="bp">self</span><span class="o">.</span><span class="n">graph</span> <span class="o">=</span> <span class="n">graphgen</span><span class="o">.</span><span class="n">apply_transitive_reduction</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="p">,</span> <span class="p">[</span><span class="n">subcluster</span><span class="o">.</span><span class="n">toPython</span><span class="p">()])</span>
 
-
-<div class="viewcode-block" id="GraphGenerator.enrich_rdf_graph">
-<a class="viewcode-back" href="../../../pandasaurus_cxg/graph_generator/graph_generator.html#pandasaurus_cxg.graph_generator.graph_generator.GraphGenerator.enrich_rdf_graph">[docs]</a>
-    <span class="k">def</span> <span class="nf">enrich_rdf_graph</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
-<span class="w">        </span><span class="sd">&quot;&quot;&quot;</span>
-<span class="sd">        Enrich RDF graph with enriched DataFrame from AnndataEnricher</span>
-
-<span class="sd">        Returns:</span>
-
-<span class="sd">        &quot;&quot;&quot;</span>
-        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">ea</span><span class="o">.</span><span class="n">enricher_manager</span><span class="o">.</span><span class="n">enricher</span><span class="o">.</span><span class="n">enriched_df</span><span class="o">.</span><span class="n">empty</span><span class="p">:</span>
-            <span class="c1"># TODO or we can just call simple_enrichment method</span>
-            <span class="n">enrichment_methods</span> <span class="o">=</span> <span class="p">[</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">dir</span><span class="p">(</span><span class="n">AnndataEnricher</span><span class="p">)</span> <span class="k">if</span> <span class="s2">&quot;_enrichment&quot;</span> <span class="ow">in</span> <span class="n">i</span><span class="p">]</span>
-            <span class="n">enrichment_methods</span><span class="o">.</span><span class="n">sort</span><span class="p">()</span>
-            <span class="k">raise</span> <span class="n">MissingEnrichmentProcess</span><span class="p">(</span><span class="n">enrichment_methods</span><span class="p">)</span>
-        <span class="n">cell_type_dict</span> <span class="o">=</span> <span class="p">(</span>
-            <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span>
-                <span class="p">[</span>
-                    <span class="bp">self</span><span class="o">.</span><span class="n">ea</span><span class="o">.</span><span class="n">enricher_manager</span><span class="o">.</span><span class="n">enricher</span><span class="o">.</span><span class="n">enriched_df</span><span class="p">[[</span><span class="s2">&quot;s&quot;</span><span class="p">,</span> <span class="s2">&quot;s_label&quot;</span><span class="p">]],</span>
-                    <span class="bp">self</span><span class="o">.</span><span class="n">ea</span><span class="o">.</span><span class="n">enricher_manager</span><span class="o">.</span><span class="n">enricher</span><span class="o">.</span><span class="n">enriched_df</span><span class="p">[[</span><span class="s2">&quot;o&quot;</span><span class="p">,</span> <span class="s2">&quot;o_label&quot;</span><span class="p">]]</span><span class="o">.</span><span class="n">rename</span><span class="p">(</span>
-                        <span class="n">columns</span><span class="o">=</span><span class="p">{</span><span class="s2">&quot;o&quot;</span><span class="p">:</span> <span class="s2">&quot;s&quot;</span><span class="p">,</span> <span class="s2">&quot;o_label&quot;</span><span class="p">:</span> <span class="s2">&quot;s_label&quot;</span><span class="p">}</span>
-                    <span class="p">),</span>
-                <span class="p">],</span>
-                <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">,</span>
-                <span class="n">ignore_index</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span>
-            <span class="p">)</span>
-            <span class="o">.</span><span class="n">drop_duplicates</span><span class="p">()</span>
-            <span class="o">.</span><span class="n">set_index</span><span class="p">(</span><span class="s2">&quot;s&quot;</span><span class="p">)[</span><span class="s2">&quot;s_label&quot;</span><span class="p">]</span>
-            <span class="o">.</span><span class="n">to_dict</span><span class="p">()</span>
-        <span class="p">)</span>
         <span class="c1"># add cell_type nodes and consists_of relations</span>
         <span class="n">cl_namespace</span> <span class="o">=</span> <span class="n">Namespace</span><span class="p">(</span><span class="s2">&quot;http://purl.obolibrary.org/obo/CL_&quot;</span><span class="p">)</span>
         <span class="n">consist_of</span> <span class="o">=</span> <span class="n">URIRef</span><span class="p">(</span><span class="n">CONSIST_OF</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;iri&quot;</span><span class="p">))</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">consist_of</span><span class="p">,</span> <span class="n">RDFS</span><span class="o">.</span><span class="n">label</span><span class="p">,</span> <span class="n">Literal</span><span class="p">(</span><span class="n">CONSIST_OF</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s2">&quot;label&quot;</span><span class="p">))))</span>
-        <span class="k">for</span> <span class="n">curie</span><span class="p">,</span> <span class="n">label</span> <span class="ow">in</span> <span class="n">cell_type_dict</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
+        <span class="k">for</span> <span class="n">curie</span><span class="p">,</span> <span class="n">label</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">ea</span><span class="o">.</span><span class="n">enricher_manager</span><span class="o">.</span><span class="n">seed_dict</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
             <span class="n">resource</span> <span class="o">=</span> <span class="n">cl_namespace</span><span class="p">[</span><span class="n">curie</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="o">-</span><span class="mi">1</span><span class="p">]]</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">resource</span><span class="p">,</span> <span class="n">RDFS</span><span class="o">.</span><span class="n">label</span><span class="p">,</span> <span class="n">Literal</span><span class="p">(</span><span class="n">label</span><span class="p">)))</span>
             <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">resource</span><span class="p">,</span> <span class="n">RDF</span><span class="o">.</span><span class="n">type</span><span class="p">,</span> <span class="n">OWL</span><span class="o">.</span><span class="n">Class</span><span class="p">))</span>
@@ -270,9 +240,24 @@ <h1>Source code for pandasaurus_cxg.graph_generator.graph_generator</h1><div cla
                 <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">class_expression_bnode</span><span class="p">,</span> <span class="n">OWL</span><span class="o">.</span><span class="n">onProperty</span><span class="p">,</span> <span class="n">consist_of</span><span class="p">))</span>
                 <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">class_expression_bnode</span><span class="p">,</span> <span class="n">OWL</span><span class="o">.</span><span class="n">someValuesFrom</span><span class="p">,</span> <span class="n">resource</span><span class="p">))</span>
                 <span class="c1"># Add the restriction</span>
-                <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">s</span><span class="p">,</span> <span class="n">RDF</span><span class="o">.</span><span class="n">type</span><span class="p">,</span> <span class="n">class_expression_bnode</span><span class="p">))</span>
+                <span class="bp">self</span><span class="o">.</span><span class="n">graph</span><span class="o">.</span><span class="n">add</span><span class="p">((</span><span class="n">s</span><span class="p">,</span> <span class="n">RDF</span><span class="o">.</span><span class="n">type</span><span class="p">,</span> <span class="n">class_expression_bnode</span><span class="p">))</span></div>
+
+
+<div class="viewcode-block" id="GraphGenerator.enrich_rdf_graph">
+<a class="viewcode-back" href="../../../pandasaurus_cxg/graph_generator/graph_generator.html#pandasaurus_cxg.graph_generator.graph_generator.GraphGenerator.enrich_rdf_graph">[docs]</a>
+    <span class="k">def</span> <span class="nf">enrich_rdf_graph</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
+<span class="w">        </span><span class="sd">&quot;&quot;&quot;</span>
+<span class="sd">        Enrich RDF graph with enriched DataFrame from AnndataEnricher</span>
 
-        <span class="c1"># add enrichment graph</span>
+<span class="sd">        Returns:</span>
+
+<span class="sd">        &quot;&quot;&quot;</span>
+        <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">ea</span><span class="o">.</span><span class="n">enricher_manager</span><span class="o">.</span><span class="n">enricher</span><span class="o">.</span><span class="n">enriched_df</span><span class="o">.</span><span class="n">empty</span><span class="p">:</span>
+            <span class="c1"># TODO or we can just call simple_enrichment method</span>
+            <span class="n">enrichment_methods</span> <span class="o">=</span> <span class="p">[</span><span class="n">i</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">dir</span><span class="p">(</span><span class="n">AnndataEnricher</span><span class="p">)</span> <span class="k">if</span> <span class="s2">&quot;_enrichment&quot;</span> <span class="ow">in</span> <span class="n">i</span><span class="p">]</span>
+            <span class="n">enrichment_methods</span><span class="o">.</span><span class="n">sort</span><span class="p">()</span>
+            <span class="k">raise</span> <span class="n">MissingEnrichmentProcess</span><span class="p">(</span><span class="n">enrichment_methods</span><span class="p">)</span>
+        <span class="c1"># add enrichment graph, subClassOf relations</span>
         <span class="bp">self</span><span class="o">.</span><span class="n">graph</span> <span class="o">+=</span> <span class="bp">self</span><span class="o">.</span><span class="n">ea</span><span class="o">.</span><span class="n">enricher_manager</span><span class="o">.</span><span class="n">enricher</span><span class="o">.</span><span class="n">graph</span></div>