mousesuture / pages /No_suture.py
Arts-of-coding's picture
Update pages/No_suture.py
95f8948 verified
raw
history blame
13.4 kB
# 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 = "datasuture/ctrl/No_suture_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")
#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_db0-5 and scatter-plot_db0-6
tab2_content = html.Div([
html.Div([
html.Label("S-cycle genes"),
dcc.Dropdown(id='dpdn3', value="Mcm5", 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_db0-5', figure={}, className='three columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot_db0-6', figure={}, className='three columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot_db0-7', figure={}, className='three columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot_db0-8', figure={}, className='three columns',config=config_fig)
]),
])
# Create the second tab content with scatter-plot_db0-5 and scatter-plot_db0-6
tab3_content = html.Div([
html.Div([
html.Label("UMAP condition 1"),
dcc.Dropdown(id='dpdn5', value="condition", 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_db0-9', figure={}, className='four columns', hoverData=None ,config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot_db0-10', figure={}, className='four columns', hoverData=None, config=config_fig)
]),
html.Div([
dcc.Graph(id='scatter-plot_db0-11', figure={}, className='four columns',config=config_fig)
]),
html.Div([
dcc.Graph(id='my-graph_db02', figure={}, clickData=None, hoverData=None,
className='four columns',config=config_fig
)
]),
]),
])
tab4_content = html.Div([
html.Label("Column chosen"),
dcc.Dropdown(id='dpdn2', value="cell states", multi=False,
options=df.columns),
html.Div([
html.Label("Multi gene"),
dcc.Dropdown(id='dpdn7', value=["Pax6","Sox9","Cdk8","Il31ra","Gpha2",
"Areg","Krt13","Krt19","Psca","Muc20",
"S100a9","Lama3","Itgb4","Itga6","Thy1","Dcn","Scn7a",
"Cdh19","Mpz","Ptprc","Cd52","Cd69","Cd86","Rgs5","Des","Myh11","Cd93","Pecam1",
"Abcg2","Lyve1","Mki67"], multi=True,
options=df.columns),
]),
html.Div([
dcc.Graph(id='scatter-plot_db0-12', 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_db0-5', component_property='figure'),
Output(component_id='scatter-plot_db0-6', component_property='figure'),
Output(component_id='scatter-plot_db0-7', component_property='figure'),
Output(component_id='scatter-plot_db0-8', component_property='figure'),
Output(component_id='scatter-plot_db0-9', component_property='figure'),
Output(component_id='scatter-plot_db0-10', component_property='figure'),
Output(component_id='scatter-plot_db0-11', component_property='figure'),
Output(component_id='scatter-plot_db0-12', component_property='figure'),
Output(component_id='my-graph_db02', 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_db0_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_db0_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='condition', title="G2M-cycle gene:",template="seaborn")
fig_scatter_db0_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='condition', title="S score:",template="seaborn")
fig_scatter_db0_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='condition', title="G2M score:",template="seaborn")
# Sort values of custom in-between
dff = dff.sort(condition1_chosen)
fig_scatter_db0_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_db0_9.update_traces(hoverinfo='none', hovertemplate=None)
fig_scatter_db0_9.update_layout(hovermode=False)
fig_scatter_db0_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='condition',template="seaborn")
fig_scatter_db0_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='condition',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_db0_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())})
else:
fig_scatter_db0_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_db02 = 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_db0_5, fig_scatter_db0_6, fig_scatter_db0_7, fig_scatter_db0_8, fig_scatter_db0_9, fig_scatter_db0_10, fig_scatter_db0_11, fig_scatter_db0_12, fig_violin_db02