Merge branch 'main' into colored-nodes

.github/ISSUE_TEMPLATE/issue.md

@@ -3,7 +3,7 @@ name: Issue Template
 about: Standard Issue Template
 title: 
 labels: 
-project: PROTzilla 2
+project: "PROTzilla"
 
 ---
 

.github/ISSUE_TEMPLATE/todo_issue.md

@@ -3,7 +3,7 @@ name: TODO
 about: TODO Issue Template
 title: '# TODO <issue_nr>'
 labels: todo
-project: 'PROTzilla2'
+project: 'PROTzilla'
 
 ---
 

.gitignore

@@ -70,7 +70,7 @@ coverage.xml
 # Django stuff:
 *.log
 local_settings.py
-db.sqlite3
+#db.sqlite3 #tracked to remove migrations warning. The database is not actually in use
 db.sqlite3-journal
 
 # Flask stuff:

docs/Makefile

@@ -0,0 +1,20 @@
+# Minimal makefile for Sphinx documentation
+#
+
+# You can set these variables from the command line, and also
+# from the environment for the first two.
+SPHINXOPTS    ?=
+SPHINXBUILD   ?= sphinx-build
+SOURCEDIR     = source
+BUILDDIR      = build
+
+# Put it first so that "make" without argument is like "make help".
+help:
+	@$(SPHINXBUILD) -M help "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)
+
+.PHONY: help Makefile
+
+# Catch-all target: route all unknown targets to Sphinx using the new
+# "make mode" option.  $(O) is meant as a shortcut for $(SPHINXOPTS).
+%: Makefile
+	@$(SPHINXBUILD) -M $@ "$(SOURCEDIR)" "$(BUILDDIR)" $(SPHINXOPTS) $(O)

docs/build_docs.md

@@ -0,0 +1,8 @@
+## Build docs with Sphinx ##
+- Docs are build with sphinx-autoapi
+- after installing the packages in requirements.txt, all necessary dependencies for building the docs should be installed (sphinx==7.2.6, sphinx-autoapi==3.0.0, requests==2.31.0)
+- to build the docs open the docs\ folder in a terminal and run "make html" to create the html documentation
+    - in case the error "Could not import extension sphinx.builders.linkcheck" occurs, try reinstalling python requests (pip install requests==2.31.0)
+    - warnings might occur, they usually do not prevent the successful build of the docs
+- To open the docs open the index.html in the docs\build\html folder
+- when adding docstrings to the code they should follow the correct syntax(https://sphinx-rtd-tutorial.readthedocs.io/en/latest/docstrings.html), in order to be formatted correctly in the generated documentation

docs/make.bat

@@ -0,0 +1,35 @@
+@ECHO OFF
+
+pushd %~dp0
+
+REM Command file for Sphinx documentation
+
+if "%SPHINXBUILD%" == "" (
+	set SPHINXBUILD=sphinx-build
+)
+set SOURCEDIR=source
+set BUILDDIR=build
+
+%SPHINXBUILD% >NUL 2>NUL
+if errorlevel 9009 (
+	echo.
+	echo.The 'sphinx-build' command was not found. Make sure you have Sphinx
+	echo.installed, then set the SPHINXBUILD environment variable to point
+	echo.to the full path of the 'sphinx-build' executable. Alternatively you
+	echo.may add the Sphinx directory to PATH.
+	echo.
+	echo.If you don't have Sphinx installed, grab it from
+	echo.https://www.sphinx-doc.org/
+	exit /b 1
+)
+
+if "%1" == "" goto help
+
+%SPHINXBUILD% -M %1 %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+goto end
+
+:help
+%SPHINXBUILD% -M help %SOURCEDIR% %BUILDDIR% %SPHINXOPTS% %O%
+
+:end
+popd

docs/source/conf.py

@@ -0,0 +1,27 @@
+# Configuration file for the Sphinx documentation builder.
+#
+# For the full list of built-in configuration values, see the documentation:
+# https://www.sphinx-doc.org/en/master/usage/configuration.html
+
+# -- Project information -----------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#project-information
+
+project = "PROTzilla"
+copyright = "2023, BP22/23"
+author = "BP22/23"
+
+# -- General configuration ---------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#general-configuration
+
+extensions = ["sphinx.ext.napoleon", "autoapi.extension"]
+autoapi_dirs = ["../../"]
+
+templates_path = ["_templates"]
+exclude_patterns = []
+
+
+# -- Options for HTML output -------------------------------------------------
+# https://www.sphinx-doc.org/en/master/usage/configuration.html#options-for-html-output
+
+html_theme = "alabaster"
+html_static_path = ["_static"]

docs/source/index.rst

@@ -0,0 +1,20 @@
+.. PROTzilla documentation master file, created by
+   sphinx-quickstart on Wed Sep 27 18:24:09 2023.
+   You can adapt this file completely to your liking, but it should at least
+   contain the root `toctree` directive.
+
+Welcome to PROTzilla's documentation!
+=====================================
+
+.. toctree::
+   :maxdepth: 2
+   :caption: Contents:
+
+
+
+Indices and tables
+==================
+
+* :ref:`genindex`
+* :ref:`modindex`
+* :ref:`search`

protzilla/constants/location_mapping.py

@@ -20,11 +20,9 @@
 )
 from ..importing import metadata_import, ms_data_import, peptide_import
 
-"""
-In this data structure, a method is associated with a location. The location is
-determined by the section, step, and method keys found in the workflow_meta 
-file that correspond to the method.
-"""
+# In this data structure, a method is associated with a location. The location is
+# determined by the section, step, and method keys found in the workflow_meta
+# file that correspond to the method.
 method_map = {
     (
         "importing",
@@ -41,6 +39,11 @@
         "metadata_import",
         "metadata_import_method",
     ): metadata_import.metadata_import_method,
+    (
+        "importing",
+        "metadata_import",
+        "metadata_column_assignment",
+    ): metadata_import.metadata_column_assignment,
     ("importing", "peptide_import", "peptide_import"): peptide_import.peptide_import,
     (
         "data_preprocessing",
@@ -127,6 +130,11 @@
         "imputation",
         "min_value_per_dataset",
     ): imputation.by_min_per_dataset,
+    (
+        "data_preprocessing",
+        "imputation",
+        "normal_distribution_sampling",
+    ): imputation.by_normal_distribution_sampling,
     (
         "data_preprocessing",
         "filter_peptides",
@@ -237,11 +245,10 @@
 # reversed mapping of method callable and location
 location_map = {v: k for k, v in method_map.items()}
 
-"""
-In this data structure, a plot for a given method is associated with a 
-location. The location is determined by the section, step, and method keys 
-found in the workflow_meta file that correspond to the method.
-"""
+
+# In this data structure, a plot for a given method is associated with a
+# location. The location is determined by the section, step, and method keys
+# found in the workflow_meta file that correspond to the method.
 plot_map = {
     (
         "data_preprocessing",
@@ -313,6 +320,11 @@
         "imputation",
         "min_value_per_dataset",
     ): imputation.by_min_per_dataset_plot,
+    (
+        "data_preprocessing",
+        "imputation",
+        "normal_distribution_sampling",
+    ): imputation.by_normal_distribution_sampling_plot,
     (
         "data_preprocessing",
         "outlier_detection",

protzilla/constants/workflow_meta.json

@@ -80,6 +80,32 @@
             "default": "Columns (samples in rows, features in columns)"
           }
         }
+      },
+      "metadata_column_assignment": {
+        "name": "Metadata Column Assignment",
+        "description": "Assign columns to metadata categories, repeatable for each category",
+        "parameters": {
+          "metadata_df": {
+            "type": "empty",
+            "name": "metadata_df",
+            "default": null
+          },
+          "metadata_required_column": {
+            "name": "Missing, but required Metadata Columns",
+            "fill": "metadata_required_columns",
+            "type": "categorical",
+            "categories": [],
+            "default": null
+          },
+          "metadata_unknown_column": {
+            "name": "Existing, but unknown Metadata Columns",
+            "fill": "metadata_unknown_columns",
+            "type": "categorical",
+            "categories": [],
+            "default": null
+          }
+
+        }
       }
     },
     "peptide_import": {
@@ -677,6 +703,69 @@
             }
           }
         ]
+      },
+      "normal_distribution_sampling": {
+        "name": "Normal Distribution Sampling",
+        "description": "Imputation methods include normal distribution sampling per Protein or over Dataset",
+        "parameters": {
+          "strategy": {
+            "name": "Strategy:",
+            "type": "categorical",
+            "categories": [
+              "perProtein",
+              "perDataset"
+            ],
+            "default": "perProtein"
+          },
+          "down_shift": {
+            "name": "Downshift:",
+            "type": "numeric",
+            "min": -10,
+            "max": 10,
+            "default": -1
+          },
+           "scaling_factor": {
+            "name": "Scaling Factor:",
+            "type": "numeric",
+            "min": 0,
+            "max": 1,
+            "default": 1
+          }
+        },
+        "graphs": [
+          {
+            "graph_type": {
+              "name": "Graph type:",
+              "type": "categorical",
+              "categories": [
+                "Boxplot",
+                "Histogram"
+              ],
+              "default": "Boxplot"
+            },
+            "group_by": {
+              "name": "Group by:",
+              "type": "categorical",
+              "categories": [
+                "None",
+                "Sample",
+                "Protein ID"
+              ],
+              "default": "None"
+            }
+          },
+          {
+            "graph_type_quantities": {
+              "name": "Graph type Imputed Values:",
+              "type": "categorical",
+              "categories": [
+                "Bar chart",
+                "Pie chart"
+              ],
+              "default": "Pie chart"
+            }
+          }
+        ]
       }
     },
     "filter_peptides": {
@@ -744,7 +833,7 @@
           "grouping": {
             "name": "Grouping:",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "fill_dynamic": [
               "selected_groups"
             ],
@@ -810,7 +899,7 @@
           "grouping": {
             "name": "Grouping",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "fill_dynamic": [
               "group1",
               "group2"
@@ -876,7 +965,7 @@
           "grouping": {
             "name": "Grouping",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "fill_dynamic": [
               "group1",
               "group2"
@@ -1109,7 +1198,7 @@
           "labels_column": {
             "name": "Choose labels column from metadata",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "fill_dynamic": [
               "positive_label"
             ],
@@ -1245,7 +1334,7 @@
           "labels_column": {
             "name": "Choose labels column from metadata",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "fill_dynamic": [
               "positive_label"
             ],
@@ -1381,7 +1470,7 @@
           "labels_column": {
             "name": "Choose labels column from metadata",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "fill_dynamic": [
               "positive_label"
             ],
@@ -1502,7 +1591,7 @@
           "labels_column": {
             "name": "Choose labels column from metadata",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "fill_dynamic": [
               "positive_label"
             ],
@@ -1708,7 +1797,7 @@
           "labels_column": {
             "name": "Choose labels column from metadata",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "categories": [],
             "default": null
           },
@@ -2457,7 +2546,7 @@
           "grouping": {
             "name": "Grouping from metadata",
             "type": "categorical",
-            "fill": "metadata_columns",
+            "fill": "metadata_non_sample_columns",
             "fill_dynamic": [
               "group1",
               "group2"