Create DLC_corg_week16.py

pages/DLC_corg_week16.py

@@ -0,0 +1,493 @@
+# 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
+pl.enable_string_cache(False)
+
+dash.register_page(__name__, location="sidebar")
+
+dataset = "data10xflex/corg/DLC_corg_w16"
+
+# 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")
+
+#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.read_parquet(f"az://{dataset}.parquet", storage_options=storage_options)
+
+# 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_db4-1',
+        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_db4-1', type='number', value=min_value, debounce=True),
+    dcc.Input(id='max-slider_db4-1', type='number', value=max_value, debounce=True),
+    html.Label("Total Counts"),
+    dcc.RangeSlider(
+        id='range-slider_db4-2',
+        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_db4-2', type='number', value=min_value_2, debounce=True),
+    dcc.Input(id='max-slider_db4-2', type='number', value=max_value_2, debounce=True),
+    html.Label("Percent Mitochondrial Genes"),
+    dcc.RangeSlider(
+        id='range-slider_db4-3',
+        step=5,
+        min=0,
+        max=100,
+        value=[min_value_3, max_value_3],
+    ),
+    dcc.Input(id='min-slider_db4-3', type='number', value=min_value_3, debounce=True),
+    dcc.Input(id='max-slider_db4-3', type='number', value=max_value_3, debounce=True),
+    html.Div([
+        dcc.Graph(id='pie-graph_db4', figure={}, className='four columns',config=config_fig),
+        dcc.Graph(id='my-graph_db4', figure={}, clickData=None, hoverData=None,
+                  className='four columns',config=config_fig
+                  ),
+        dcc.Graph(id='scatter-plot_db4', figure={}, className='four columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-2', figure={}, className='four columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-3', figure={}, className='four columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-4', figure={}, className='four columns',config=config_fig)
+    ]),
+])
+
+# Create the second tab content with scatter-plot_db4-5 and scatter-plot_db4-6
+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",
+    "MLF1IP",
+    "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', 'FAM64A', 'SMC4', 'CCNB2', 'CKAP2L', 'CKAP2', 'AURKB', 'BUB1', 'KIF11', 'ANP32E', 'TUBB4B', 'GTSE1', 'KIF20B', 'HJURP', 'CDCA3', 'HN1', '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_db4-5', figure={}, className='three columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-6', figure={}, className='three columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-7', figure={}, className='three columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-8', figure={}, className='three columns',config=config_fig)
+    ]),
+])
+
+# Create the second tab content with scatter-plot_db4-5 and scatter-plot_db4-6
+tab3_content = html.Div([
+    html.Div([
+            html.Label("UMAP condition 1"),
+            dcc.Dropdown(id='dpdn5', value="batch", multi=False,
+                 options=df.columns),
+            html.Label("UMAP condition 2"),
+            dcc.Dropdown(id='dpdn6', value="n_genes_by_counts", multi=False,
+                 options=df.columns),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-9', figure={}, className='four columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-10', figure={}, className='four columns',config=config_fig)
+    ]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-11', figure={}, className='four columns',config=config_fig)
+    ]),
+    html.Div([
+            dcc.Graph(id='my-graph_db42', figure={}, clickData=None, hoverData=None,
+                  className='four columns',config=config_fig
+                  )
+    ]),
+    ]),
+])
+#    html.Div([
+#        dcc.Graph(id='scatter-plot_db4-12', figure={}, className='four columns',config=config_fig)
+#    ]),
+
+
+tab4_content = html.Div([
+    html.Div([
+            html.Label("Multi gene"),
+            dcc.Dropdown(id='dpdn7', value=['PAX6', 'TP63', 'OTX2', 'SIX3', 'LHX2', 'SIX6', 'SOX2', 'PMEL', 
+                                            'RAX', 'SOX2', 'LIN28A', 'ABCG2', 'KRT8', 'KRT18', 'KRT7', 
+                                            'KRT19', 'COL1A2', 'AQP1', 'LUM', 'TFAP2A', 'HAND1', 'S100A9', 
+                                            'SPP1', 'TEK', 'FOXC2', 'PECAM1', 'SOX9'], multi=True,
+                 options=df.columns),
+]),
+    html.Div([
+        dcc.Graph(id='scatter-plot_db4-12', 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='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_db4-1", "value"),
+    Output("max-slider_db4-1", "value"),
+    Output("min-slider_db4-2", "value"),
+    Output("max-slider_db4-2", "value"),
+    Output("min-slider_db4-3", "value"),
+    Output("max-slider_db4-3", "value"),
+    Input("min-slider_db4-1", "value"),
+    Input("max-slider_db4-1", "value"),
+    Input("min-slider_db4-2", "value"),
+    Input("max-slider_db4-2", "value"),
+    Input("min-slider_db4-3", "value"),
+    Input("max-slider_db4-3", "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_db4-1', 'value'),
+    Output('range-slider_db4-2', 'value'),
+    Output('range-slider_db4-3', 'value'),
+    Input('min-slider_db4-1', 'value'),
+    Input('max-slider_db4-1', 'value'),
+    Input('min-slider_db4-2', 'value'),
+    Input('max-slider_db4-2', 'value'),
+    Input('min-slider_db4-3', 'value'),
+    Input('max-slider_db4-3', '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_db4', component_property='figure'),
+    Output(component_id='pie-graph_db4', component_property='figure'),
+    Output(component_id='scatter-plot_db4', component_property='figure'),
+    Output(component_id='scatter-plot_db4-2', component_property='figure'),
+    Output(component_id='scatter-plot_db4-3', component_property='figure'),
+    Output(component_id='scatter-plot_db4-4', component_property='figure'),  # Add this new scatter plot
+    Output(component_id='scatter-plot_db4-5', component_property='figure'),
+    Output(component_id='scatter-plot_db4-6', component_property='figure'),
+    Output(component_id='scatter-plot_db4-7', component_property='figure'),
+    Output(component_id='scatter-plot_db4-8', component_property='figure'),
+    Output(component_id='scatter-plot_db4-9', component_property='figure'),
+    Output(component_id='scatter-plot_db4-10', component_property='figure'),
+    Output(component_id='scatter-plot_db4-11', component_property='figure'),
+    Output(component_id='scatter-plot_db4-12', component_property='figure'),
+    Output(component_id='my-graph_db42', 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'),
+    Input(component_id='range-slider_db4-1', component_property='value'),
+    Input(component_id='range-slider_db4-2', component_property='value'),
+    Input(component_id='range-slider_db4-3', 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, 
+    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])
+)
+    
+    #Drop categories that are not in the filtered data
+    dff = dff.with_columns(dff[col_chosen].cast(pl.Categorical))
+
+    dff = dff.sort(col_chosen)
+    
+    # Plot figures
+    fig_violin_db4 = 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"))
+
+    # 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
+
+    # 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
+    # TO DO
+    expression_means = expression_means.join(dff_5, on=[col_chosen,"Gene"], how="inner")
+
+    # Order the dataframe on ascending categories
+    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)
+    
+    fig_pie_db4 = 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()
+
+    # Create the scatter plots
+    fig_scatter_db4 = 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_db4_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_db4_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_db4_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_db4_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='batch', title="S-cycle gene:",template="seaborn")
+
+    fig_scatter_db4_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='batch', title="G2M-cycle gene:",template="seaborn")
+    
+    fig_scatter_db4_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='batch', title="S score:",template="seaborn")
+    
+    fig_scatter_db4_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='batch', title="G2M score:",template="seaborn")
+
+    # Sort values of custom in-between
+    dff = dff.sort(condition1_chosen)
+    
+    fig_scatter_db4_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='batch',template="seaborn")
+    
+    fig_scatter_db4_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='batch',template="seaborn")
+    
+    fig_scatter_db4_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='batch',template="seaborn")
+    
+    fig_scatter_db4_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")
+    
+    fig_violin_db42 = px.violin(data_frame=dff, x=condition1_chosen, y=condition2_chosen, box=True, points="all",
+                            color=condition1_chosen, hover_name=condition1_chosen,template="seaborn")
+
+
+    return fig_violin_db4, fig_pie_db4, fig_scatter_db4, fig_scatter_db4_2, fig_scatter_db4_3, fig_scatter_db4_4, fig_scatter_db4_5, fig_scatter_db4_6, fig_scatter_db4_7, fig_scatter_db4_8, fig_scatter_db4_9, fig_scatter_db4_10, fig_scatter_db4_11, fig_scatter_db4_12, fig_violin_db42
+
+# Set http://localhost:5000/ in web browser
+# Now create your regular FASTAPI application
+
+#if __name__ == '__main__':
+#    app.run_server(debug=False, use_reloader=False, host='0.0.0.0', port=5000) #