Update pages/Cornea_v1_integrated_scVI.py

pages/Cornea_v1_integrated_scVI.py

@@ -50,128 +50,26 @@ 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 )
 
-# Load in multiple dataframes
 # Load in multiple dataframes
 df = pl.scan_parquet(f"./data/{dataset}.parquet", storage_options=storage_options).collect()
 
-# Setup the app
-#external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
-#app = dash.Dash(__name__, use_pages=True) #, requests_pathname_prefix='/dashboard1/'
-
-#df = pl.read_parquet(filepath,storage_options=storage_options)
-#df = pl.DataFrame()
-#abfs = AzureBlobFileSystem(account_name=accountname,account_key=accountkey)
-#df = df.rename({"__index_level_0__": "Unnamed: 0"})
-
-#df1 = pl.read_parquet(filepath, storage_options=storage_options)
-
-#df2 = pl.read_parquet(f"az://data10xflex/{dataset_chosen}.parquet", storage_options=storage_options)
-
-#tab0_content = html.Div([
-#    html.Label("Dataset chosen"),    
-#    dcc.Dropdown(id='dpdn1', value="corg/10xflexcorg_umap_clusres", multi=False,
-#                 options=["corg/10xflexcorg_umap_clusres","d1011/10xflexd1011_umap_clusres"])
-#])
-
-#@app.callback(
-#    Input(component_id='dpdn1', component_property='value')
-#)
-
-#def update_filepath(dpdn1):
-#    global df
-#    if str(f"az://data10xflex/{dpdn1}.parquet") != str(filepath):
-#        print("not identical filepath, chosing other")
-#        df2 = pl.read_parquet(f"az://data10xflex/{dpdn1}.parquet", storage_options=storage_options)
-#        df = df2
-#    return
-
-#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)
-
-# Loads in the conditions specified in the yaml file
-
-# Note: Future version perhaps all values from a column in the dataframe of the parquet file
-# Note 2: This could also be a tsv of the categories and own specified colors
-#conditions = df[col_batch].unique().to_list()
-# 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)
-#     ]),
-# ])
-
 # Create the second tab content with scatter-plot_db2-5 and scatter-plot_db2-6
 tab2_content = html.Div([
     html.Div([
             html.Label("S-cycle genes"),
-            dcc.Dropdown(id='dpdn3', value="PAX6", multi=False,
-                 options=[
-    "PAX6"
-]),
+            dcc.Dropdown(id='dpdn3', value="MCM5", multi=False,
+                 options=["MCM5","PCNA","TYMS","FEN1","MCM2","MCM4","RRM1","UNG","GINS2","MCM6","CDCA7","DTL",
+                          "PRIM1","UHRF1","HELLS","RFC2","RPA2","NASP","RAD51AP1","GMNN","WDR76","SLBP","CCNE2","UBR7",
+                          "POLD3","MSH2","ATAD2","RAD51","RRM2","CDC45","CDC6","EXO1","TIPIN","DSCC1","BLM","CASP8AP2",
+                          "USP1","CLSPN","POLA1","CHAF1B","BRIP1","E2F8"]),
             html.Label("G2M-cycle genes"),
-            dcc.Dropdown(id='dpdn4', value="PAX6", multi=False,
-                 options=[
-    "PAX6"
-]),
+            dcc.Dropdown(id='dpdn4', value="TOP2A", multi=False,
+                 options=["HMGB2","CDK1","NUSAP1","UBE2C","BIRC5","TPX2","TOP2A","NDC80","CKS2","NUF2","CKS1B","MKI67",
+                          "TMPO","CENPF","TACC3","SMC4","CCNB2","CKAP2L","CKAP2","AURKB","BUB1","KIF11","ANP32E","TUBB4B",
+                          "GTSE1","KIF20B","HJURP","CDCA3","CDC20","TTK","CDC25C","KIF2C","RANGAP1","NCAPD2","DLGAP5","CDCA2",
+                          "CDCA8","ECT2","KIF23","HMMR","AURKA","PSRC1","ANLN","LBR","CKAP5","CENPE","CTCF","NEK2","G2E3",
+                          "GAS2L3","CBX5","CENPA"]),
     ]),
     html.Div([
         dcc.Graph(id='scatter-plot_db2-5', figure={}, className='three columns',config=config_fig)
@@ -212,10 +110,6 @@ tab3_content = html.Div([
     ]),
     ]),
 ])
-#    html.Div([
-#        dcc.Graph(id='scatter-plot_db2-12', figure={}, className='four columns',config=config_fig)
-#    ]),
-
 
 tab4_content = html.Div([
      html.Label("Column chosen"),    
@@ -245,47 +139,7 @@ layout = html.Div([
     ]),
 ])
 
-# 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"),
-     
-#)
-# 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]
-
 @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='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'),
@@ -301,9 +155,6 @@ layout = html.Div([
     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'),
      
 )
 
@@ -311,12 +162,6 @@ def update_graph_and_pie_chart(col_chosen, s_chosen, g2m_chosen, condition1_chos
     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])
 )
     # Select ordering of plots
     if condition1_chosen == "integrated_cell_states":
@@ -355,7 +200,6 @@ def update_graph_and_pie_chart(col_chosen, s_chosen, g2m_chosen, condition1_chos
     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=[col_chosen,"Gene"], how="inner")
     
     fig_scatter_db2_5 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=s_chosen,
@@ -389,6 +233,7 @@ def update_graph_and_pie_chart(col_chosen, s_chosen, g2m_chosen, condition1_chos
                             #labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
                             hover_name='studies',template="seaborn",category_orders=cat_ord)
 
+    # Reorder categories on natural sorting or on the integrated cell state order of the paper
     if col_chosen == "integrated_cell_states":
         fig_scatter_db2_12 = px.scatter(data_frame=expression_means, x="Gene", y=col_chosen, color="Mean expression",
                                     size="percentage", size_max = 20,