Update dash_plotly_QC_scRNA.py

dash_plotly_QC_scRNA.py

@@ -36,18 +36,16 @@ def read_config(filename):
     return config
 
 config = read_config(config_path)
-path_parquet = config.get("path_parquet")
+#path_parquet = config.get("path_parquet")
 col_batch = config.get("col_batch")
 col_features = config.get("col_features")
 col_counts = config.get("col_counts")
 col_mt = config.get("col_mt")
 
-filepath = f"az://{path_parquet}"
-
 storage_options={'account_name': AZURE_STORAGE_ACCOUNT, 'account_key': AZURE_STORAGE_ACCESS_KEY,'anon': False}
 #azfs = AzureBlobFileSystem(**storage_options )
 
-df = pl.read_parquet(filepath,storage_options=storage_options)
+
 #abfs = AzureBlobFileSystem(account_name=accountname,account_key=accountkey)
 #df = df.rename({"__index_level_0__": "Unnamed: 0"})
 
@@ -55,18 +53,11 @@ df = pl.read_parquet(filepath,storage_options=storage_options)
 external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
 app = dash.Dash(__name__, external_stylesheets=external_stylesheets) #, requests_pathname_prefix='/dashboard1/'
 
-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_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)
+tab0_content = html.Div([
+    html.Label("Dataset chosen"),    
+    dcc.Dropdown(id='dpdn1', value="d1011/10xflexd1011_umap_clusres", multi=False,
+                 options=["corg/10xflexcorg_umap_clusres","d1011/10xflexd1011_umap_clusres"])
+])
 
 # Loads in the conditions specified in the yaml file
 
@@ -243,6 +234,7 @@ app.layout = html.Div([
     dcc.Tabs(id='tabs', style= {'width': 600,
         '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='Cell cycle', value='tab2', children=tab2_content),
         dcc.Tab(label='Custom', value='tab3', children=tab3_content),
@@ -298,6 +290,7 @@ 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='dpdn1', component_property='value'),
     Input(component_id='dpdn2', component_property='value'),
     Input(component_id='dpdn3', component_property='value'),
     Input(component_id='dpdn4', component_property='value'),
@@ -309,7 +302,23 @@ 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(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(dataset_chosen, col_chosen, s_chosen, g2m_chosen, condition1_chosen, condition2_chosen, condition3_chosen, range_value_1, range_value_2, range_value_3): #batch_chosen, 
+    filepath = f"az://data10xflex/{dataset_chosen}"
+    df = pl.read_parquet(filepath,storage_options=storage_options)
+    
+    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_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)    
+    
     batch_chosen = df[col_chosen].unique().to_list()
     dff = df.filter(
         (pl.col(col_chosen).cast(str).is_in(batch_chosen)) &