Create DLC_epi.py

pages/DLC_epi.py

@@ -0,0 +1,258 @@
+# Dash app to visualize scRNA-seq data quality control metrics from scanpy objects
+# Shoutout to Coding-with-Adam for the initial template of the project: 
+# https://github.com/Coding-with-Adam/Dash-by-Plotly/blob/master/Dash%20Components/Graph/dash-graph.py
+
+import dash
+from dash import dcc, html, Output, Input, callback
+import plotly.express as px
+import dash_callback_chain
+import yaml
+import polars as pl
+import os
+from natsort import natsorted
+#pl.enable_string_cache(False)
+
+dash.register_page(__name__, location="sidebar")
+
+dataset = "corg/DLC_epi_nopluri_clusres_scVI_polars"
+
+# Set custom resolution for plots:
+config_fig = {
+  'toImageButtonOptions': {
+    'format': 'svg',
+    'filename': 'custom_image',
+    'height': 600,
+    'width': 700,
+    'scale': 1,
+  }
+}
+from adlfs import AzureBlobFileSystem
+mountpount=os.environ['AZURE_MOUNT_POINT'],
+AZURE_STORAGE_ACCESS_KEY=os.getenv('AZURE_STORAGE_ACCESS_KEY')
+AZURE_STORAGE_ACCOUNT=os.getenv('AZURE_STORAGE_ACCOUNT')
+
+# Load in config file
+config_path = "./data/config.yaml"
+
+# Add the read-in data from the yaml file
+def read_config(filename):
+    with open(filename, 'r') as yaml_file:
+        config = yaml.safe_load(yaml_file)
+    return config
+
+config = read_config(config_path)
+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")
+interesting_genes = ["LIN28A", "KRT8", "ABCG2", "S100A9", "COL1A2", "AQP1", "LUM", "TEK", "PAX6", "PMEL"]
+
+#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
+df = pl.scan_parquet(f"az://{dataset}.parquet", storage_options=storage_options).collect()
+
+# Create the second tab content with scatter-plot_db30-5 and scatter-plot_db30-6
+tab2_content = html.Div([
+    html.Div([
+            html.Label("S-cycle genes"),
+            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="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_db30-5', figure={}, className='three columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db30-6', figure={}, className='three columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db30-7', figure={}, className='three columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db30-8', figure={}, className='three columns',config=config_fig)
+    ]),
+])
+
+# Create the second tab content with scatter-plot_db30-5 and scatter-plot_db30-6
+tab3_content = html.Div([
+    html.Div([
+            html.Label("UMAP condition 1"),
+            dcc.Dropdown(id='dpdn5', value="sample", multi=False,
+                 options=df.columns),
+            html.Label("UMAP condition 2"),
+            dcc.Dropdown(id='dpdn6', value="PAX6", multi=False,
+                 options=df.columns),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db30-9', figure={}, className='four columns', hoverData=None ,config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db30-10', figure={}, className='four columns', hoverData=None, config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db30-11', figure={}, className='four columns',config=config_fig)
+    ]),
+    html.Div([
+            dcc.Graph(id='my-graph_db302', figure={}, clickData=None, hoverData=None,
+                  className='four columns',config=config_fig
+                  )
+    ]),
+    ]),
+])
+
+tab4_content = html.Div([
+     html.Label("Column chosen"),    
+     dcc.Dropdown(id='dpdn2', value="leiden_res_0.95_r3", multi=False,
+                  options=df.columns),
+    html.Div([
+            html.Label("Multi gene"),
+            dcc.Dropdown(id='dpdn7', value=interesting_genes, multi=True,
+                 options=df.columns),
+]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db30-12', figure={}, className='row',style={'width': '100vh', 'height': '90vh'})
+    ]),
+])
+
+# Define the tabs layout
+layout = html.Div([
+    html.H1(f'Dataset analysis dashboard: {dataset}'),
+    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='UMAP visualisation', value='tab3', children=tab3_content),
+        dcc.Tab(label='Multi dot', value='tab4', children=tab4_content),
+        dcc.Tab(label='Cell cycle', value='tab2', children=tab2_content),
+    ]),
+])
+
+@callback(
+    Output(component_id='scatter-plot_db30-5', component_property='figure'),
+    Output(component_id='scatter-plot_db30-6', component_property='figure'),
+    Output(component_id='scatter-plot_db30-7', component_property='figure'),
+    Output(component_id='scatter-plot_db30-8', component_property='figure'),
+    Output(component_id='scatter-plot_db30-9', component_property='figure'),
+    Output(component_id='scatter-plot_db30-10', component_property='figure'),
+    Output(component_id='scatter-plot_db30-11', component_property='figure'),
+    Output(component_id='scatter-plot_db30-12', component_property='figure'),
+    Output(component_id='my-graph_db302', component_property='figure'),
+    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'),
+    Input(component_id='dpdn6', component_property='value'),
+    Input(component_id='dpdn7', 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, 
+    batch_chosen = df[col_chosen].unique().to_list()
+    dff = df.filter(
+        (pl.col(col_chosen).cast(str).is_in(batch_chosen)) #&
+)
+    # Select ordering of plots
+    if condition1_chosen == "integrated_cell_states":
+        cat_ord= {condition1_chosen: natsorted(dff[condition1_chosen].unique())}
+    else:
+        cat_ord= {condition1_chosen: natsorted(dff[condition1_chosen].unique())}
+
+    # Calculate the mean expression
+    
+    # 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 += [col_chosen]
+    dff_pre = dff.select(list_conds)
+    
+    # Melt wide format DataFrame into long format
+    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([col_chosen, "Gene"]).agg(pl.mean("Mean expression")).collect() #
+    
+    # Calculate the percentage total expressed
+    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([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)
+              .otherwise(None).alias("%"),
+    ])
+    result = result.with_columns(pl.col("%").fill_null(0))
+    dff_5[["percentage"]] = result[["%"]]
+    dff_5 = dff_5.select(pl.col(col_chosen,"Gene","percentage"))
+
+    # Final part to join the percentage expressed and mean expression levels
+    expression_means = expression_means.join(dff_5, on=[col_chosen,"Gene"], how="inner")
+    
+    fig_scatter_db30_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'},
+                            hover_name=None, title="S-cycle gene:",template="seaborn")
+
+    fig_scatter_db30_6 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=g2m_chosen,
+                            labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+                            hover_name='sample', title="G2M-cycle gene:",template="seaborn")
+    
+    fig_scatter_db30_7 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color="S_score",
+                            labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+                            hover_name='sample', title="S score:",template="seaborn")
+    
+    fig_scatter_db30_8 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color="G2M_score",
+                            labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+                            hover_name='sample', title="G2M score:",template="seaborn")
+
+    # Sort values of custom in-between
+    dff = dff.sort(condition1_chosen)
+    
+    fig_scatter_db30_9 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=condition1_chosen,
+                            labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+                            hover_name=None,hover_data = None, template="seaborn",category_orders=cat_ord)
+    fig_scatter_db30_9.update_traces(hoverinfo='none', hovertemplate=None)
+    fig_scatter_db30_9.update_layout(hovermode=False)
+    
+    fig_scatter_db30_10 = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color=condition2_chosen,
+                            labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+                            hover_name='sample',template="seaborn")
+    
+    fig_scatter_db30_11 = px.scatter(data_frame=dff, x=condition1_chosen, y=condition2_chosen, color=condition1_chosen,
+                            #labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+                            hover_name='sample',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_db30_12 = px.scatter(data_frame=expression_means, x="Gene", y=col_chosen, color="Mean expression",
+                                    size="percentage", size_max = 20,
+                                #labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+                                hover_name=col_chosen,template="seaborn",category_orders={col_chosen: natsorted(expression_means[col_chosen].unique()),"Gene": condition3_chosen})
+    else:                                                                                
+        fig_scatter_db30_12 = px.scatter(data_frame=expression_means, x="Gene", y=col_chosen, color="Mean expression",
+                                    size="percentage", size_max = 20,
+                                #labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
+                                hover_name=col_chosen,template="seaborn",category_orders={col_chosen: natsorted(expression_means[col_chosen].unique()),"Gene": condition3_chosen})
+    
+    fig_violin_db302 = px.violin(data_frame=dff, x=condition1_chosen, y=condition2_chosen, box=True, points="all",
+                            color=condition1_chosen, hover_name=condition1_chosen,template="seaborn",category_orders=cat_ord)
+
+
+    return fig_scatter_db30_5, fig_scatter_db30_6, fig_scatter_db30_7, fig_scatter_db30_8, fig_scatter_db30_9, fig_scatter_db30_10, fig_scatter_db30_11, fig_scatter_db30_12, fig_violin_db302 #fig_violin_db30, fig_pie_db30, fig_scatter_db30, fig_scatter_db30_2, fig_scatter_db30_3, fig_scatter_db30_4, 
+
+# Set http://localhost:5000/ in web browser