File size: 15,621 Bytes
6f1f3b5 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 |
# 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
import plotly.express as px
import dash_callback_chain
import yaml
import polars as pl
pl.enable_string_cache(False)
# Set custom resolution for plots:
config_fig = {
'toImageButtonOptions': {
'format': 'svg',
'filename': 'custom_image',
'height': 600,
'width': 700,
'scale': 1,
}
}
config_path = "./app/azure/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")
conditions = config.get("conditions")
col_features = config.get("col_features")
col_counts = config.get("col_counts")
col_mt = config.get("col_mt")
# Import the data from one .parquet file
df = pl.read_parquet(path_parquet)
#df = df.rename({"__index_level_0__": "Unnamed: 0"})
# Setup the app
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)
# 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
# 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([
dcc.Dropdown(id='dpdn2', value=conditions, multi=True,
options=conditions),
html.Label("N Genes by Counts"),
dcc.RangeSlider(
id='range-slider-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-1', type='number', value=min_value, debounce=True),
dcc.Input(id='max-slider-1', type='number', value=max_value, debounce=True),
html.Label("Total Counts"),
dcc.RangeSlider(
id='range-slider-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-2', type='number', value=min_value_2, debounce=True),
dcc.Input(id='max-slider-2', type='number', value=max_value_2, debounce=True),
html.Label("Percent Mitochondrial Genes"),
dcc.RangeSlider(
id='range-slider-3',
step=0.1,
min=0,
max=1,
value=[min_value_3, max_value_3],
),
dcc.Input(id='min-slider-3', type='number', value=min_value_3, debounce=True),
dcc.Input(id='max-slider-3', type='number', value=max_value_3, debounce=True),
html.Div([
dcc.Graph(id='pie-graph', figure={}, className='four columns',config=config_fig),
dcc.Graph(id='my-graph', figure={}, clickData=None, hoverData=None,
className='four columns',config=config_fig
),
dcc.Graph(id='scatter-plot', figure={}, className='four columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot-2', figure={}, className='four columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot-3', figure={}, className='four columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot-4', figure={}, className='four columns',config=config_fig)
]),
])
# Create the second tab content with scatter-plot-5 and scatter-plot-6
tab2_content = html.Div([
html.Div([
html.Label("S-cycle genes"),
dcc.Dropdown(id='dpdn3', value="Cdc45", multi=False,
options=[
"Cdc45",
"Uhrf1",
"Mcm2",
"Slbp",
"Mcm5",
"Pola1",
"Gmnn",
"Cdc6",
"Rrm2",
"Atad2",
"Dscc1",
"Mcm4",
"Chaf1b",
"Rfc2",
"Msh2",
"Fen1",
"Hells",
"Prim1",
"Tyms",
"Mcm6",
"Wdr76",
"Rad51",
"Pcna",
"Ccne2",
"Casp8ap2",
"Usp1",
"Nasp",
"Rpa2",
"Ung",
"Rad51ap1",
"Blm",
"Pold3",
"Rrm1",
"Cenpu",
"Gins2",
"Tipin",
"Brip1",
"Dtl",
"Exo1",
"Ubr7",
"Clspn",
"E2f8",
"Cdca7"
]),
html.Label("G2M-cycle genes"),
dcc.Dropdown(id='dpdn4', value="Top2a", multi=False,
options=[
"Ube2c",
"Lbr",
"Ctcf",
"Cdc20",
"Cbx5",
"Kif11",
"Anp32e",
"Birc5",
"Cdk1",
"Tmpo",
"Hmmr",
"Pimreg",
"Aurkb",
"Top2a",
"Gtse1",
"Rangap1",
"Cdca3",
"Ndc80",
"Kif20b",
"Cenpf",
"Nek2",
"Nuf2",
"Nusap1",
"Bub1",
"Tpx2",
"Aurka",
"Ect2",
"Cks1b",
"Kif2c",
"Cdca8",
"Cenpa",
"Mki67",
"Ccnb2",
"Kif23",
"Smc4",
"G2e3",
"Tubb4b",
"Anln",
"Tacc3",
"Dlgap5",
"Ckap2",
"Ncapd2",
"Ttk",
"Ckap5",
"Cdc25c",
"Hjurp",
"Cenpe",
"Ckap2l",
"Cdca2",
"Hmgb2",
"Cks2",
"Psrc1",
"Gas2l3"
]),
]),
html.Div([
dcc.Graph(id='scatter-plot-5', figure={}, className='three columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot-6', figure={}, className='three columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot-7', figure={}, className='three columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot-8', figure={}, className='three columns',config=config_fig)
]),
])
# Create the second tab content with scatter-plot-5 and scatter-plot-6
tab3_content = html.Div([
html.Div([
html.Label("UMAP condition 1"),
dcc.Dropdown(id='dpdn5', value="total_counts", 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-9', figure={}, className='four columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot-10', figure={}, className='four columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot-11', figure={}, className='four columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='my-graph2', figure={}, clickData=None, hoverData=None,
className='four columns',config=config_fig
)
]),
])
# Define the tabs layout
app.layout = html.Div([
dcc.Tabs(id='tabs', style= {'width': 400,
'font-size': '100%',
'height': 50}, value='tab1',children=[
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),
]),
])
# Define the circular callback
@app.callback(
Output("min-slider-1", "value"),
Output("max-slider-1", "value"),
Output("min-slider-2", "value"),
Output("max-slider-2", "value"),
Output("min-slider-3", "value"),
Output("max-slider-3", "value"),
Input("min-slider-1", "value"),
Input("max-slider-1", "value"),
Input("min-slider-2", "value"),
Input("max-slider-2", "value"),
Input("min-slider-3", "value"),
Input("max-slider-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
@app.callback(
Output('range-slider-1', 'value'),
Output('range-slider-2', 'value'),
Output('range-slider-3', 'value'),
Input('min-slider-1', 'value'),
Input('max-slider-1', 'value'),
Input('min-slider-2', 'value'),
Input('max-slider-2', 'value'),
Input('min-slider-3', 'value'),
Input('max-slider-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]
@app.callback(
Output(component_id='my-graph', component_property='figure'),
Output(component_id='pie-graph', component_property='figure'),
Output(component_id='scatter-plot', component_property='figure'),
Output(component_id='scatter-plot-2', component_property='figure'),
Output(component_id='scatter-plot-3', component_property='figure'),
Output(component_id='scatter-plot-4', component_property='figure'), # Add this new scatter plot
Output(component_id='scatter-plot-5', component_property='figure'),
Output(component_id='scatter-plot-6', component_property='figure'),
Output(component_id='scatter-plot-7', component_property='figure'),
Output(component_id='scatter-plot-8', component_property='figure'),
Output(component_id='scatter-plot-9', component_property='figure'),
Output(component_id='scatter-plot-10', component_property='figure'),
Output(component_id='scatter-plot-11', component_property='figure'),
Output(component_id='my-graph2', 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='range-slider-1', component_property='value'),
Input(component_id='range-slider-2', component_property='value'),
Input(component_id='range-slider-3', component_property='value')
)
def update_graph_and_pie_chart(batch_chosen, s_chosen, g2m_chosen, condition1_chosen, condition2_chosen, range_value_1, range_value_2, range_value_3):
dff = df.filter(
(pl.col('batch').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['batch'].cast(str))
dff = dff.with_columns(dff['batch'].cast(pl.Categorical))
# Plot figures
fig_violin = px.violin(data_frame=dff, x='batch', y=col_features, box=True, points="all",
color='batch', hover_name='batch',template="seaborn")
# Calculate the percentage of each category (normalized_count) for pie chart
category_counts = dff.group_by("batch").agg(pl.col("batch").count().alias("count"))
total_count = len(dff)
category_counts = category_counts.with_columns((pl.col("count") / total_count * 100).alias("normalized_count"))
# Display the result
labels = category_counts["batch"].to_list()
values = category_counts["normalized_count"].to_list()
total_cells = total_count # Calculate total number of cells
pie_title = f'Percentage of Total Cells: {total_cells}' # Include total cells in the title
fig_pie = px.pie(names=labels, values=values, title=pie_title,template="seaborn")
# Create the scatter plots
fig_scatter = px.scatter(data_frame=dff, x='X_umap-0', y='X_umap-1', color='batch',
labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
hover_name='batch',template="seaborn")
fig_scatter_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_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_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_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_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_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_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")
fig_scatter_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_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_11 = px.scatter(data_frame=dff, x=condition1_chosen, y=condition2_chosen, color='batch',
#labels={'X_umap-0': 'umap1' , 'X_umap-1': 'umap2'},
hover_name='batch',template="seaborn")
fig_violin2 = 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, fig_pie, fig_scatter, fig_scatter_2, fig_scatter_3, fig_scatter_4, fig_scatter_5, fig_scatter_6, fig_scatter_7, fig_scatter_8, fig_scatter_9, fig_scatter_10, fig_scatter_11, fig_violin2
# Set http://localhost:5000/ in web browser
# Now create your regular FASTAPI application
if __name__ == '__main__':
app.run_server(debug=True, use_reloader=False) #host='0.0.0.0', #, port=5000
|