Upload 7 files

Dockerfile

@@ -0,0 +1,55 @@
+# Use an official Python runtime as a base image
+FROM ubuntu:18.04
+FROM python:3.9-slim
+
+# Expose the port to run it
+ENV LISTEN_PORT=5000
+EXPOSE 5000
+
+LABEL Maintainer="arts-of-coding"
+
+WORKDIR /
+
+# fix locales
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends locales \
+    && rm -rf /var/lib/apt/lists/* \
+    && localedef -i en_US -c -f UTF-8 -A /usr/share/locale/locale.alias en_US.UTF-8
+ 
+ENV LANG en_US.utf8
+ 
+# install blobfuse
+RUN apt-get update \
+    && apt-get install -y wget apt-utils \
+    && wget https://packages.microsoft.com/config/ubuntu/18.04/packages-microsoft-prod.deb \
+    && dpkg -i packages-microsoft-prod.deb \
+    && apt-get remove -y wget \
+    && apt-get update \
+    && apt-get install -y --no-install-recommends fuse blobfuse libcurl3-gnutls libgnutls30 \
+    && rm -rf /var/lib/apt/lists/*
+
+COPY mount-blobfuse.sh /
+RUN chmod +x /mount-blobfuse.sh
+#COPY --from=compiler /opt/venv/bin/activate /usr/local/bin/activate_venv
+COPY /mount-blobfuse.sh /app/mount-blobfuse.sh
+
+#ADD /data/ /app/data/
+
+#WORKDIR /app/
+
+# Preset the volume change this to the actual azure folder
+#VOLUME /dash_plotly_QC_scRNA/./data
+
+WORKDIR /
+
+COPY ./requirements.txt ./
+RUN pip install --requirement ./requirements.txt
+
+COPY ./dash_plotly_QC_scRNA.py ./
+
+COPY ./main.py ./
+
+# How the docker app will run
+ENTRYPOINT ["/bin/bash", "-c", "/mount-blobfuse.sh; exec $SHELL"]
+
+CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "5000"]

LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

README.md

@@ -1,11 +1,4 @@
----
-title: Testazurectrl
-emoji: 🌍
-colorFrom: yellow
-colorTo: pink
-sdk: docker
-pinned: false
-license: apache-2.0
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+[<img src="https://img.shields.io/badge/dockerhub-images-blue.svg?logo=Docker">](https://hub.docker.com/repository/docker/artsofcoding/daqcs/general)
+
+# dash_plotly_QC_scRNA (daqcs)
+Dash app to visualize scRNA-seq data quality control metrics from scanpy objects

dash_plotly_QC_scRNA.py

@@ -0,0 +1,422 @@
+# 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

main.py

@@ -0,0 +1,63 @@
+import uvicorn
+from fastapi import FastAPI
+from fastapi.middleware.wsgi import WSGIMiddleware
+from dash_plotly_QC_scRNA import app as dashboard1
+#from app2 import app as dashboard2
+
+#########################################################
+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']
+
+######################################################################
+# Define the FastAPI server
+app = FastAPI()
+# Mount the Dash app as a sub-application in the FastAPI server
+app.mount("/dashboard1", WSGIMiddleware(dashboard1.server))
+#app.mount("/dashboard2", WSGIMiddleware(dashboard2.server))
+
+# Define the main API endpoint
+@app.get("/")
+def index():
+    return "Hello"
+
+# Start the FastAPI server
+if __name__ == "__main__":
+    uvicorn.run(app, host="0.0.0.0")

mount-blobfuse.sh

@@ -0,0 +1,9 @@
+# mount our blobstore
+test ${AZURE_MOUNT_POINT}
+rm -rf ${AZURE_MOUNT_POINT}
+mkdir ${AZURE_MOUNT_POINT}
+ 
+blobfuse ${AZURE_MOUNT_POINT} --use-https=true --tmp-path=/tmp/blobfuse/${AZURE_STORAGE_ACCOUNT} --container-name=${AZURE_STORAGE_ACCOUNT_CONTAINER} -o allow_other
+ 
+# run the command passed to us
+#exec "uvicorn main:app --host 0.0.0.0 --port 5000"

requirements.txt

@@ -0,0 +1,12 @@
+dash==2.13.0
+dash_callback_chain==0.0.2
+numpy==1.24.4
+pandas==2.1.0
+plotly==5.16.1
+pyarrow==13.0.0
+polars==0.19.2
+PyYAML==6.0.1
+scanpy==1.9.4
+umap_learn==0.5.3
+fastapi==0.74.*
+uvicorn[standard]==0.17.*