Update pages/Cornea_v1_integrated_scVI.py

pages/Cornea_v1_integrated_scVI.py

@@ -86,18 +86,18 @@ df = pl.read_parquet(f"./data/{dataset}.parquet")
 #    return
 
 #df = pl.read_parquet(filepath, storage_options=storage_options)
-min_value = df[col_features].min()
-max_value = df[col_features].max()
+#min_value = df[col_features].min()
+#max_value = df[col_features].max()
 
-min_value_2 = df[col_counts].min()
-min_value_2 = round(min_value_2)
-max_value_2 = df[col_counts].max()
-max_value_2 = round(max_value_2)
+#min_value_2 = df[col_counts].min()
+#min_value_2 = round(min_value_2)
+#max_value_2 = df[col_counts].max()
+#max_value_2 = round(max_value_2)
 
-min_value_3 = df[col_mt].min()
-min_value_3 = round(min_value_3, 1)
-max_value_3 = df[col_mt].max()
-max_value_3 = round(max_value_3, 1)
+#min_value_3 = df[col_mt].min()
+#min_value_3 = round(min_value_3, 1)
+#max_value_3 = df[col_mt].max()
+#max_value_3 = round(max_value_3, 1)
 
 # Loads in the conditions specified in the yaml file
 
@@ -107,55 +107,55 @@ max_value_3 = round(max_value_3, 1)
 # Create the first tab content
 # Add Sliders for three QC params: N genes by counts, total amount of reads and pct MT reads
 
-tab1_content = html.Div([
-    html.Label("Column chosen"),    
-    dcc.Dropdown(id='dpdn2', value="batch", multi=False,
-                 options=df.columns),
-    html.Label("N Genes by Counts"),
-    dcc.RangeSlider(
-        id='range-slider_db2-1',
-        step=250,
-        value=[min_value, max_value],
-        marks={i: str(i) for i in range(min_value, max_value + 1, 250)},
-    ),
-    dcc.Input(id='min-slider_db2-1', type='number', value=min_value, debounce=True),
-    dcc.Input(id='max-slider_db2-1', type='number', value=max_value, debounce=True),
-    html.Label("Total Counts"),
-    dcc.RangeSlider(
-        id='range-slider_db2-2',
-        step=7500,
-        value=[min_value_2, max_value_2],
-        marks={i: str(i) for i in range(min_value_2, max_value_2 + 1, 7500)},
-    ),
-    dcc.Input(id='min-slider_db2-2', type='number', value=min_value_2, debounce=True),
-    dcc.Input(id='max-slider_db2-2', type='number', value=max_value_2, debounce=True),
-    html.Label("Percent Mitochondrial Genes"),
-    dcc.RangeSlider(
-        id='range-slider_db2-3',
-        step=5,
-        min=0,
-        max=100,
-        value=[min_value_3, max_value_3],
-    ),
-    dcc.Input(id='min-slider_db2-3', type='number', value=min_value_3, debounce=True),
-    dcc.Input(id='max-slider_db2-3', type='number', value=max_value_3, debounce=True),
-    html.Div([
-        dcc.Graph(id='pie-graph_db2', figure={}, className='four columns',config=config_fig),
-        dcc.Graph(id='my-graph_db2', figure={}, clickData=None, hoverData=None,
-                  className='four columns',config=config_fig
-                  ),
-        dcc.Graph(id='scatter-plot_db2', figure={}, className='four columns',config=config_fig)
-    ]),
-    html.Div([
-        dcc.Graph(id='scatter-plot_db2-2', figure={}, className='four columns',config=config_fig)
-    ]),
-    html.Div([
-        dcc.Graph(id='scatter-plot_db2-3', figure={}, className='four columns',config=config_fig)
-    ]),
-    html.Div([
-        dcc.Graph(id='scatter-plot_db2-4', figure={}, className='four columns',config=config_fig)
-    ]),
-])
+#  tab1_content = html.Div([
+#     html.Label("Column chosen"),    
+#     dcc.Dropdown(id='dpdn2', value="batch", multi=False,
+#                  options=df.columns),
+#     html.Label("N Genes by Counts"),
+#     dcc.RangeSlider(
+#         id='range-slider_db2-1',
+#         step=250,
+#         value=[min_value, max_value],
+#         marks={i: str(i) for i in range(min_value, max_value + 1, 250)},
+#     ),
+#     dcc.Input(id='min-slider_db2-1', type='number', value=min_value, debounce=True),
+#     dcc.Input(id='max-slider_db2-1', type='number', value=max_value, debounce=True),
+#     html.Label("Total Counts"),
+#     dcc.RangeSlider(
+#         id='range-slider_db2-2',
+#         step=7500,
+#         value=[min_value_2, max_value_2],
+#         marks={i: str(i) for i in range(min_value_2, max_value_2 + 1, 7500)},
+#     ),
+#     dcc.Input(id='min-slider_db2-2', type='number', value=min_value_2, debounce=True),
+#     dcc.Input(id='max-slider_db2-2', type='number', value=max_value_2, debounce=True),
+#     html.Label("Percent Mitochondrial Genes"),
+#     dcc.RangeSlider(
+#         id='range-slider_db2-3',
+#         step=5,
+#         min=0,
+#         max=100,
+#         value=[min_value_3, max_value_3],
+#     ),
+#     dcc.Input(id='min-slider_db2-3', type='number', value=min_value_3, debounce=True),
+#     dcc.Input(id='max-slider_db2-3', type='number', value=max_value_3, debounce=True),
+#     html.Div([
+#         dcc.Graph(id='pie-graph_db2', figure={}, className='four columns',config=config_fig),
+#         dcc.Graph(id='my-graph_db2', figure={}, clickData=None, hoverData=None,
+#                   className='four columns',config=config_fig
+#                   ),
+#         dcc.Graph(id='scatter-plot_db2', figure={}, className='four columns',config=config_fig)
+#     ]),
+#     html.Div([
+#         dcc.Graph(id='scatter-plot_db2-2', figure={}, className='four columns',config=config_fig)
+#     ]),
+#     html.Div([
+#         dcc.Graph(id='scatter-plot_db2-3', figure={}, className='four columns',config=config_fig)
+#     ]),
+#     html.Div([
+#         dcc.Graph(id='scatter-plot_db2-4', figure={}, className='four columns',config=config_fig)
+#     ]),
+# ])
 
 # Create the second tab content with scatter-plot_db2-5 and scatter-plot_db2-6
 tab2_content = html.Div([
@@ -259,6 +259,9 @@ tab3_content = html.Div([
 
 
 tab4_content = html.Div([
+     html.Label("Column chosen"),    
+     dcc.Dropdown(id='dpdn2', value="batch", multi=False,
+                  options=df.columns),
     html.Div([
             html.Label("Multi gene"),
             dcc.Dropdown(id='dpdn7', value=["PAX6","TP63","S100A9","KRT5","KRT14","KRT10"], multi=True,
@@ -276,54 +279,54 @@ layout = html.Div([
         'font-size': '100%',
         'height': 50}, value='tab1',children=[
         #dcc.Tab(label='Dataset', value='tab0', children=tab0_content),
-        dcc.Tab(label='QC', value='tab1', children=tab1_content),
+        #dcc.Tab(label='QC', value='tab1', children=tab1_content),
+        dcc.Tab(label='Multi dot', value='tab4', children=tab4_content),
         dcc.Tab(label='Cell cycle', value='tab2', children=tab2_content),
         dcc.Tab(label='Custom', value='tab3', children=tab3_content),
-        dcc.Tab(label='Multi dot', value='tab4', children=tab4_content),
     ]),
 ])
 
 # Define the circular callback
-@callback(
-    Output("min-slider_db2-1", "value"),
-    Output("max-slider_db2-1", "value"),
-    Output("min-slider_db2-2", "value"),
-    Output("max-slider_db2-2", "value"),
-    Output("min-slider_db2-3", "value"),
-    Output("max-slider_db2-3", "value"),
-    Input("min-slider_db2-1", "value"),
-    Input("max-slider_db2-1", "value"),
-    Input("min-slider_db2-2", "value"),
-    Input("max-slider_db2-2", "value"),
-    Input("min-slider_db2-3", "value"),
-    Input("max-slider_db2-3", "value"),
+#@callback(
+    #Output("min-slider_db2-1", "value"),
+    #Output("max-slider_db2-1", "value"),
+    #Output("min-slider_db2-2", "value"),
+    #Output("max-slider_db2-2", "value"),
+    #Output("min-slider_db2-3", "value"),
+    #Output("max-slider_db2-3", "value"),
+    #Input("min-slider_db2-1", "value"),
+    #Input("max-slider_db2-1", "value"),
+    #Input("min-slider_db2-2", "value"),
+    #Input("max-slider_db2-2", "value"),
+    #Input("min-slider_db2-3", "value"),
+    #Input("max-slider_db2-3", "value"),
      
-)
-def circular_callback(min_1, max_1, min_2, max_2, min_3, max_3):
-    return min_1, max_1, min_2, max_2, min_3, max_3
-
-@callback(
-    Output('range-slider_db2-1', 'value'),
-    Output('range-slider_db2-2', 'value'),
-    Output('range-slider_db2-3', 'value'),
-    Input('min-slider_db2-1', 'value'),
-    Input('max-slider_db2-1', 'value'),
-    Input('min-slider_db2-2', 'value'),
-    Input('max-slider_db2-2', 'value'),
-    Input('min-slider_db2-3', 'value'),
-    Input('max-slider_db2-3', 'value'),
+#)
+# def circular_callback(min_1, max_1, min_2, max_2, min_3, max_3):
+#     return min_1, max_1, min_2, max_2, min_3, max_3
+
+# @callback(
+#     Output('range-slider_db2-1', 'value'),
+#     Output('range-slider_db2-2', 'value'),
+#     Output('range-slider_db2-3', 'value'),
+#     Input('min-slider_db2-1', 'value'),
+#     Input('max-slider_db2-1', 'value'),
+#     Input('min-slider_db2-2', 'value'),
+#     Input('max-slider_db2-2', 'value'),
+#     Input('min-slider_db2-3', 'value'),
+#     Input('max-slider_db2-3', 'value'),
      
-)
-def update_slider_values(min_1, max_1, min_2, max_2, min_3, max_3):
-    return [min_1, max_1], [min_2, max_2], [min_3, max_3]
+# )
+# def update_slider_values(min_1, max_1, min_2, max_2, min_3, max_3):
+#     return [min_1, max_1], [min_2, max_2], [min_3, max_3]
 
 @callback(
-    Output(component_id='my-graph_db2', component_property='figure'),
-    Output(component_id='pie-graph_db2', component_property='figure'),
-    Output(component_id='scatter-plot_db2', component_property='figure'),
-    Output(component_id='scatter-plot_db2-2', component_property='figure'),
-    Output(component_id='scatter-plot_db2-3', component_property='figure'),
-    Output(component_id='scatter-plot_db2-4', component_property='figure'),  # Add this new scatter plot
+    #Output(component_id='my-graph_db2', component_property='figure'),
+    #Output(component_id='pie-graph_db2', component_property='figure'),
+    #Output(component_id='scatter-plot_db2', component_property='figure'),
+    #Output(component_id='scatter-plot_db2-2', component_property='figure'),
+    #Output(component_id='scatter-plot_db2-3', component_property='figure'),
+    #Output(component_id='scatter-plot_db2-4', component_property='figure'),  # Add this new scatter plot
     Output(component_id='scatter-plot_db2-5', component_property='figure'),
     Output(component_id='scatter-plot_db2-6', component_property='figure'),
     Output(component_id='scatter-plot_db2-7', component_property='figure'),
@@ -339,44 +342,44 @@ def update_slider_values(min_1, max_1, min_2, max_2, min_3, max_3):
     Input(component_id='dpdn5', component_property='value'),
     Input(component_id='dpdn6', component_property='value'),
     Input(component_id='dpdn7', component_property='value'),
-    Input(component_id='range-slider_db2-1', component_property='value'),
-    Input(component_id='range-slider_db2-2', component_property='value'),
-    Input(component_id='range-slider_db2-3', component_property='value'),
+    #Input(component_id='range-slider_db2-1', component_property='value'),
+    #Input(component_id='range-slider_db2-2', component_property='value'),
+    #Input(component_id='range-slider_db2-3', component_property='value'),
      
 )
 
-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, 
+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(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]) &
-        (pl.col(col_counts) <= range_value_2[1]) &
-        (pl.col(col_mt) >= range_value_3[0]) &
-        (pl.col(col_mt) <= range_value_3[1])
+        (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]) &
+        #(pl.col(col_counts) <= range_value_2[1]) &
+        #(pl.col(col_mt) >= range_value_3[0]) &
+        #(pl.col(col_mt) <= range_value_3[1])
 )
     
-    #Drop categories that are not in the filtered data
-    dff = dff.with_columns(dff[col_chosen].cast(pl.Categorical))
+    # #Drop categories that are not in the filtered data
+    # dff = dff.with_columns(dff[col_chosen].cast(pl.Categorical))
 
-    dff = dff.sort(col_chosen)
+    # dff = dff.sort(col_chosen)
     
-    # Plot figures
-    fig_violin_db2 = px.violin(data_frame=dff, x=col_chosen, y=col_features, box=True, points="all",
-                            color=col_chosen, hover_name=col_chosen,template="seaborn")
+    # # Plot figures
+    # fig_violin_db2 = 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(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"))
+    # # Cache commonly used subexpressions
+    # total_count = pl.lit(len(dff))
+    # 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"))
 
-    # Sort the dataframe
-    #category_counts = category_counts.sort(col_chosen) does not work check if the names are different ...
+    # # Sort the dataframe
+    # #category_counts = category_counts.sort(col_chosen) does not work check if the names are different ...
     
-    # Display the result
-    total_cells = total_count  # Calculate total number of cells
-    pie_title = f'Percentage of Total Cells: {total_cells}'  # Include total cells in the title
+    # # Display the result
+    # total_cells = total_count  # Calculate total number of cells
+    # pie_title = f'Percentage of Total Cells: {total_cells}'  # Include total cells in the title
 
     # Calculate the mean expression
     
@@ -416,30 +419,30 @@ def update_graph_and_pie_chart(col_chosen, s_chosen, g2m_chosen, condition1_chos
     expression_means = expression_means.sort(col_chosen, descending=True)
     
     #expression_means = expression_means.select(["batch", "Gene", "Expression"] + condition3_chosen)
-    category_counts = category_counts.sort(col_chosen)
+    # category_counts = category_counts.sort(col_chosen)
     
-    fig_pie_db2 = px.pie(category_counts, values="normalized_count", names=col_chosen, labels=col_chosen, hole=.3, title=pie_title, template="seaborn")
+    # fig_pie_db2 = px.pie(category_counts, values="normalized_count", names=col_chosen, labels=col_chosen, hole=.3, title=pie_title, template="seaborn")
 
-    #labels = category_counts[col_chosen].to_list()
-    #values = category_counts["normalized_count"].to_list()
+    # #labels = category_counts[col_chosen].to_list()
+    # #values = category_counts["normalized_count"].to_list()
 
-    # Create the scatter plots
-    fig_scatter_db2 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=col_chosen,
-                             labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
-                             hover_name='batch',template="seaborn")
+    # # Create the scatter plots
+    # fig_scatter_db2 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=col_chosen,
+    #                          labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+    #                          hover_name='batch',template="seaborn")
 
-    fig_scatter_db2_2 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=col_mt,
-                             labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
-                             hover_name='batch',template="seaborn")
+    # fig_scatter_db2_2 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=col_mt,
+    #                          labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+    #                          hover_name='batch',template="seaborn")
 
-    fig_scatter_db2_3 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=col_features,
-                             labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
-                             hover_name='batch',template="seaborn")
+    # fig_scatter_db2_3 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=col_features,
+    #                          labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+    #                          hover_name='batch',template="seaborn")
 
 
-    fig_scatter_db2_4 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=col_counts,
-                             labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
-                             hover_name='batch',template="seaborn")
+    # fig_scatter_db2_4 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=col_counts,
+    #                          labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+    #                          hover_name='batch',template="seaborn")
     
     fig_scatter_db2_5 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=s_chosen,
                             labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
@@ -481,7 +484,7 @@ def update_graph_and_pie_chart(col_chosen, s_chosen, g2m_chosen, condition1_chos
                             color=condition1_chosen, hover_name=condition1_chosen,template="seaborn")
 
 
-    return fig_violin_db2, fig_pie_db2, fig_scatter_db2, fig_scatter_db2_2, fig_scatter_db2_3, fig_scatter_db2_4, fig_scatter_db2_5, fig_scatter_db2_6, fig_scatter_db2_7, fig_scatter_db2_8, fig_scatter_db2_9, fig_scatter_db2_10, fig_scatter_db2_11, fig_scatter_db2_12, fig_violin_db22
+    return fig_scatter_db2_5, fig_scatter_db2_6, fig_scatter_db2_7, fig_scatter_db2_8, fig_scatter_db2_9, fig_scatter_db2_10, fig_scatter_db2_11, fig_scatter_db2_12, fig_violin_db22 #fig_violin_db2, fig_pie_db2, fig_scatter_db2, fig_scatter_db2_2, fig_scatter_db2_3, fig_scatter_db2_4, 
 
 # Set http://localhost:5000/ in web browser
 # Now create your regular FASTAPI application