added pipeline for functional analysis (assembly, correction, binning…

…, annotation, kegg mapping)

added dash app for viewing kegg pathways. for each kegg pathway the user can view all microbes that have the respective enzymes in their genome
improved view (visual enhancements, added pipeline to view)

desktop/build.py

@@ -1,10 +1,11 @@
-from subprocess import call
-from os.path import realpath, dirname, join
 from os import pathsep
+from os.path import realpath, dirname, join
+from subprocess import call
+
+ROOT = dirname(realpath(__file__))
 
 
 def main():
-    root = dirname(realpath(__file__))
     entry_point = join(root, 'src', 'mmonitor', '__main__.py')
     placeholder = join(root, 'src', 'resources', 'images', '.placeholder')
     images_dir_dest = join('resources', 'images')

desktop/requirements.txt

@@ -2,8 +2,13 @@ pandas==1.3.5
 numpy==1.22.1
 scipy==1.7.3
 plotly==5.5.0
-dash==1.20.0
+dash~=2.4.1
 Flask==2.0.2
 future==0.18.2
 mysql-connector-python==8.0.27
-requests==2.27.1
+requests==2.27.1
+setuptools~=57.0.0
+matplotlib~=3.5.2
+tqdm~=4.63.0
+Pillow~=9.0.1
+conda~=4.1.6

desktop/src/mmonitor/dashapp/apps/correlations.py

@@ -1,12 +1,12 @@
 from typing import Tuple, Any, List, Iterable, Dict, Union
 
-import plotly.express as px
 import dash
 import dash_core_components as dcc
 import dash_html_components as html
-from dash_table import DataTable
+import plotly.express as px
 from dash.dependencies import Input, Output, State
 from dash.exceptions import PreventUpdate
+from dash_table import DataTable
 from pandas import DataFrame
 from plotly.graph_objects import Figure
 
@@ -52,6 +52,7 @@ def _init_layout(self) -> None:
 
         # graph dropdown menus in a flex box
         header = html.H1('Correlations of abundances and metadata')
+
         taxonomy_dd = dcc.Dropdown(
             id='taxonomy-dd',
             options=[{'label': t, 'value': t} for t in self._taxonomies],
@@ -143,11 +144,18 @@ def _init_layout(self) -> None:
         correlations_tb = DataTable(id='table-correlations', data=[], columns=[])
         download_tb = dcc.Download(id='download-tb')
 
+        CONTENT_STYLE = {
+
+            "margin-right": "2rem",
+            "padding": "2rem 1rem",
+            'margin-bottom': '200px', 'background-color': 'gainsboro'
+        }
+
         container = html.Div(
             [header, dropdowns, graph_score, graph_test, header_tb, dropdowns_tb,
              selections_tb, correlations_tb, download_tb],
-            style={'margin-bottom': '200px'}
-        )
+            style=CONTENT_STYLE)
+
         self.layout = container
 
     def _init_callbacks(self) -> None:

desktop/src/mmonitor/dashapp/apps/horizon.py

@@ -1,7 +1,7 @@
 import uuid
 
-import dash_html_components as html
 import dash_core_components as dcc
+import dash_html_components as html
 from dash.dependencies import Input, Output, State
 from dash.exceptions import PreventUpdate
 from flask import send_from_directory
@@ -28,7 +28,7 @@ def serve_image(cache_bust):
 class Horizon(BaseApp):
     """
     App to display the taxonomy abundances in a horizon plot.
-    Calls an R script and uploads the generated image.
+    Calls an R script and uploads the pipeline_out image.
     """
 
     def __init__(self, sql: MMonitorDBInterface):

desktop/src/mmonitor/dashapp/apps/kegg.py

@@ -0,0 +1,71 @@
+import base64
+import glob
+
+import dash
+import dash_core_components as dcc
+import dash_html_components as html
+
+from mmonitor.dashapp.app import app
+from mmonitor.dashapp.base_app import BaseApp
+
+
+class Kegg(BaseApp):
+
+    def __init__(self):
+        self._init_layout()
+        self._init_callbacks()
+
+    # @app.server.route('/horizon.png<cache_bust>')
+    # def serve_image(cache_bust):
+    #     """
+    #     Allows dash to display png images from  ../resources/images/
+    #
+    #     The cache_bust is a way to make the url unique.
+    #     This is necessary to force the browser to reload the
+    #     presumably 'static' image file that it had previously cached.
+    #     """
+    #     return send_from_directory(images_path, 'horizon.png')
+
+    def _init_layout(self) -> None:
+        self._static_image_route = "/static/"
+        self._samples = glob.glob("/resources/pipeline_out/*/")
+        print(self._samples)
+        header = html.H1("Functional mapping of annotated genomes to KEGG pathways")
+        print(self._samples)
+        sample_dropdown = dcc.Dropdown(id="sample-dropdown", options=[{'label': t, 'value': t} for t in self._samples],
+                                       value=self._samples[0])
+        pathway_dropdown = dcc.Dropdown(id="pathway-dropdown")
+        dd = html.Div(id='dd-output-container')
+
+        dropdowns = html.Div(
+            [sample_dropdown, pathway_dropdown]
+        )
+
+        image = html.Img(
+            id='kegg-plot',
+            alt='Please select a kegg plot',
+            style={'display': 'block', 'margin-left': 'auto', 'margin-right': 'auto', 'padding': '20px'}
+        )
+
+        container = html.Div([header, dropdowns, dd, image])
+
+        self._layout = container
+
+    def _init_callbacks(self) -> None:
+        @app.callback(
+            dash.dependencies.Output('pathway-dropdown', 'options'),
+            [dash.dependencies.Input('sample-dropdown', 'value')]
+        )
+        def update_pathway_dropdown(sample):
+            return [{'label': i.split("/")[-1].removesuffix(".png"), 'value': i} for i in glob.glob(f"{sample}/*.png")]
+
+        @app.callback(
+            dash.dependencies.Output('kegg-plot', 'src'),
+            dash.dependencies.Input('pathway-dropdown', 'value')
+        )
+        def update_image_src(image_path):
+            print('current image_path = {}'.format(image_path))
+            encoded_image = base64.b64encode(open(image_path, 'rb').read())
+            return 'data:image/png;base64,{}'.format(encoded_image.decode())
+
+            return value

desktop/src/mmonitor/dashapp/apps/kraken.py

@@ -2,11 +2,11 @@
 from io import StringIO
 from typing import List, Tuple, Set
 
-import pandas as pd
-import plotly.express as px
 import dash
 import dash_core_components as dcc
 import dash_html_components as html
+import pandas as pd
+import plotly.express as px
 from dash.dependencies import Input, Output, State
 from dash.exceptions import PreventUpdate
 from plotly.graph_objects import Figure
@@ -52,7 +52,7 @@ def _init_layout(self) -> None:
             multiple=True
         )
 
-        # generated content
+        # pipeline_out content
         graph = dcc.Graph(id='kraken-graph')
 
         # slider to adjust entities per bar
@@ -96,7 +96,7 @@ def _init_callbacks(self) -> None:
         )
         def _update_output(contents, slider_value, tax_rank, filenames, tax_rank_options, content_style):
             """
-            Read the uploaded files and display the generated plot.
+            Read the uploaded files and display the pipeline_out plot.
             The plot is a stacked bar chart with abundances
             projected to 100%. The number of entities per bar
             is adjustable with different elements.

desktop/src/mmonitor/dashapp/index.py

@@ -1,11 +1,11 @@
-import dash_html_components as html
 import dash_core_components as dcc
+import dash_html_components as html
 from dash.dependencies import Input, Output
 from dash.exceptions import PreventUpdate
 from flask import request
 
 from mmonitor.dashapp.app import app
-from mmonitor.dashapp.apps import correlations, taxonomy, kraken, horizon
+from mmonitor.dashapp.apps import correlations, taxonomy, kraken, horizon, kegg
 from mmonitor.dashapp.base_app import BaseApp
 from mmonitor.database.mmonitor_db import MMonitorDBInterface
 
@@ -31,22 +31,28 @@ def _init_apps(self) -> None:
         """
 
         self._apps = {
-            '/apps/correlations': {
-                'name': 'Correlations',
-                'app': correlations.Correlations(self._sql)
-            },
             '/apps/taxonomy': {
                 'name': 'Taxonomy',
                 'app': taxonomy.Taxonomy(self._sql)
             },
-            '/apps/kraken2': {
-                'name': 'Kraken2',
-                'app': kraken.Kraken(self._sql)
-            },
+
             '/apps/horizon': {
                 'name': 'Horizon',
                 'app': horizon.Horizon(self._sql)
             },
+
+            '/apps/correlations': {
+                'name': 'Correlations',
+                'app': correlations.Correlations(self._sql)
+            },
+            '/apps/kraken2': {
+                'name': 'Kraken2',
+                'app': kraken.Kraken(self._sql)
+            },
+            '/apps/kegg': {
+                'name': 'kegg',
+                'app': kegg.Kegg()
+            }
         }
 
     def _init_layout(self) -> None:
@@ -57,7 +63,7 @@ def _init_layout(self) -> None:
 
         location = dcc.Location(id='url', refresh=False)
         navigation = html.Div([
-            dcc.Link(values['name'], href=url, style={'padding': '10px'})
+            dcc.Link(values['name'], href=url, style={'padding': '10px', 'font-size': "30px"})
             for url, values in self._apps.items()
         ], className="row")
         page_content = html.Div(id='page-content', children=[])

desktop/src/mmonitor/database/mmonitor_db.py

@@ -1,8 +1,8 @@
 import sqlite3
+from json import loads, dumps
 from typing import List, Tuple, Any
 
 import pandas as pd
-from json import loads, dumps
 
 
 def _parse_dict(x):
@@ -97,6 +97,7 @@ def create_db(self, db_name):
             abundance INTEGER,
             sample_id INTEGER,
             project_id INTEGER,
+            sample_date TEXT,
             PRIMARY KEY ("read_id")
         )"""