Update dash_plotly_QC_scRNA.py

dash_plotly_QC_scRNA.py

@@ -77,8 +77,8 @@ max_value_3 = round(max_value_3, 1)
 # Add Sliders for three QC params: N genes by counts, total amount of reads and pct MT reads
 
 tab1_content = html.Div([
-    #dcc.Dropdown(id='dpdn2', value=conditions, multi=True,
-    #             options=conditions),
+    dcc.Dropdown(id='dpdn2', value="batch", multi=False,
+                 options=df.columns),
     html.Label("N Genes by Counts"),
     dcc.RangeSlider(
         id='range-slider-1',
@@ -287,7 +287,7 @@ def update_slider_values(min_1, max_1, min_2, max_2, min_3, max_3):
     Output(component_id='scatter-plot-11', component_property='figure'),
     Output(component_id='scatter-plot-12', component_property='figure'),
     Output(component_id='my-graph2', component_property='figure'),
-    #Input(component_id='dpdn2', component_property='value'),
+    Input(component_id='dpdn2', component_property='value'),
     Input(component_id='dpdn3', component_property='value'),
     Input(component_id='dpdn4', component_property='value'),
     Input(component_id='dpdn5', component_property='value'),
@@ -298,10 +298,10 @@ def update_slider_values(min_1, max_1, min_2, max_2, min_3, max_3):
     Input(component_id='range-slider-3', component_property='value')
 )
 
-def update_graph_and_pie_chart(s_chosen, g2m_chosen, condition1_chosen, condition2_chosen, condition3_chosen, range_value_1, range_value_2, range_value_3): #batch_chosen, 
-    batch_chosen = df[condition1_chosen].unique().to_list()
+def update_graph_and_pie_chart(col_chosen, s_chosen, g2m_chosen, condition1_chosen, condition2_chosen, condition3_chosen, range_value_1, range_value_2, range_value_3): #batch_chosen, 
+    batch_chosen = df[col_chosen].unique().to_list()
     dff = df.filter(
-        (pl.col(condition1_chosen).cast(str).is_in(batch_chosen)) &
+        (pl.col(col_chosen).cast(str).is_in(batch_chosen)) &
         (pl.col(col_features) >= range_value_1[0]) &
         (pl.col(col_features) <= range_value_1[1]) &
         (pl.col(col_counts) >= range_value_2[0]) &
@@ -311,19 +311,19 @@ def update_graph_and_pie_chart(s_chosen, g2m_chosen, condition1_chosen, conditio
 )
     
     #Drop categories that are not in the filtered data
-    dff = dff.with_columns(dff[condition1_chosen].cast(pl.Categorical))
+    dff = dff.with_columns(dff[col_chosen].cast(pl.Categorical))
 
     # Plot figures
-    fig_violin = px.violin(data_frame=dff, x=condition1_chosen, y=col_features, box=True, points="all",
-                            color=condition1_chosen, hover_name=condition1_chosen,template="seaborn")
+    fig_violin = px.violin(data_frame=dff, x=col_chosen, y=col_features, box=True, points="all",
+                            color=col_chosen, hover_name=col_chosen,template="seaborn")
 
     # Cache commonly used subexpressions
     total_count = pl.lit(len(dff))
-    category_counts = dff.group_by(condition1_chosen).agg(pl.col(condition1_chosen).count().alias("count"))
+    category_counts = dff.group_by(col_chosen).agg(pl.col(col_chosen).count().alias("count"))
     category_counts = category_counts.with_columns(((pl.col("count") / total_count * 100).round(decimals=2)).alias("normalized_count"))
 
     # Display the result
-    labels = category_counts[condition1_chosen].to_list()
+    labels = category_counts[col_chosen].to_list()
     values = category_counts["normalized_count"].to_list()
 
     total_cells = total_count  # Calculate total number of cells
@@ -334,22 +334,22 @@ def update_graph_and_pie_chart(s_chosen, g2m_chosen, condition1_chosen, conditio
     # Melt wide format DataFrame into long format
     # Specify batch column as string type and gene columns as float type
     list_conds = condition3_chosen
-    list_conds += [condition1_chosen]
+    list_conds += [col_chosen]
     dff_pre = dff.select(list_conds)
     
     # Melt wide format DataFrame into long format
-    dff_long = dff_pre.melt(id_vars=condition1_chosen, variable_name="Gene", value_name="Mean expression")
+    dff_long = dff_pre.melt(id_vars=col_chosen, variable_name="Gene", value_name="Mean expression")
 
     # Calculate the mean expression levels for each gene in each region
-    expression_means = dff_long.lazy().group_by([condition1_chosen, "Gene"]).agg(pl.mean("Mean expression")).collect()
+    expression_means = dff_long.lazy().group_by([col_chosen, "Gene"]).agg(pl.mean("Mean expression")).collect()
     
     # Calculate the percentage total expressed
-    dff_long1 = dff_pre.melt(id_vars=condition1_chosen, variable_name="Gene")#.group_by(pl.all()).agg(pl.len())
+    dff_long1 = dff_pre.melt(id_vars=col_chosen, variable_name="Gene")#.group_by(pl.all()).agg(pl.len())
     count = 1
     dff_long2 = dff_long1.with_columns(pl.lit(count).alias("len"))
-    dff_long3 = dff_long2.filter(pl.col("value") > 0).group_by([condition1_chosen, "Gene"]).agg(pl.sum("len").alias("len"))
-    dff_long4 = dff_long2.group_by([condition1_chosen, "Gene"]).agg(pl.sum("len").alias("total"))
-    dff_5 = dff_long4.join(dff_long3, on=[condition1_chosen,"Gene"], how="outer")
+    dff_long3 = dff_long2.filter(pl.col("value") > 0).group_by([col_chosen, "Gene"]).agg(pl.sum("len").alias("len"))
+    dff_long4 = dff_long2.group_by([col_chosen, "Gene"]).agg(pl.sum("len").alias("total"))
+    dff_5 = dff_long4.join(dff_long3, on=[col_chosen,"Gene"], how="outer")
     result = dff_5.select([
         pl.when((pl.col('len').is_not_null()) & (pl.col('total').is_not_null()))
               .then(pl.col('len') / pl.col('total')*100)
@@ -357,11 +357,11 @@ def update_graph_and_pie_chart(s_chosen, g2m_chosen, condition1_chosen, conditio
     ])
     result = result.with_columns(pl.col("%").fill_null(100))
     dff_5[["percentage"]] = result[["%"]]
-    dff_5 = dff_5.select(pl.col(condition1_chosen,"Gene","percentage"))
+    dff_5 = dff_5.select(pl.col(col_chosen,"Gene","percentage"))
 
     # Final part to join the percentage expressed and mean expression levels
     # TO DO
-    expression_means = expression_means.join(dff_5, on=[condition1_chosen,"Gene"], how="inner")
+    expression_means = expression_means.join(dff_5, on=[col_chosen,"Gene"], how="inner")
     
     #expression_means = expression_means.select(["batch", "Gene", "Expression"] + condition3_chosen)
     
@@ -418,7 +418,7 @@ def update_graph_and_pie_chart(s_chosen, g2m_chosen, condition1_chosen, conditio
                             #labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
                             hover_name='batch',template="seaborn")
     
-    fig_violin2 = px.violin(data_frame=dff, x=condition1_chosen, y=condition2_chosen, box=True, points="all",
+    fig_violin2 = px.violin(data_frame=dff, x=col_chosen, y=condition2_chosen, box=True, points="all",
                             color=condition1_chosen, hover_name=condition1_chosen,template="seaborn")