Apply best practices

.github/workflows/lint.yml

@@ -0,0 +1,45 @@
+name: Lint
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  lint:
+    name: Lint
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: read
+      packages: read
+      statuses: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v5
+        with:
+          fetch-depth: 0
+          persist-credentials: false
+
+      - name: Lint Code Base
+        uses: super-linter/super-linter@v8.5.0
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
+          VALIDATE_ALL_CODEBASE: true
+          DEFAULT_BRANCH: main
+
+          VALIDATE_SNAKEMAKE_SNAKEFMT: true
+          VALIDATE_PYTHON_BLACK: true
+          VALIDATE_YAML_PRETTIER: true
+
+      - name: Set up R
+        uses: r-lib/actions/setup-r@v2
+
+      - name: Set up R dependencies
+        uses: r-lib/actions/setup-r-dependencies@v2
+        with:
+          packages: styler
+
+      - name: Check R style
+        run: Rscript -e 'changed <- styler::style_dir(".", dry = "on"); if (any(changed$changed)) quit(status = 1)'

.gitignore

@@ -60,4 +60,7 @@ data
 .test/report.html
 
 snakejob_conductor.sh
-settings.json
+settings.json
+
+!.github/
+!.prettierrc.yml

.prettierrc.yml

@@ -0,0 +1,2 @@
+tabWidth: 2
+useTabs: false

CITATION.cff

@@ -10,24 +10,24 @@ type: software
 authors:
   - given-names: Stephan
     family-names: Reichl
-    orcid: 'https://orcid.org/0000-0001-8555-7198'
+    orcid: "https://orcid.org/0000-0001-8555-7198"
     affiliation: CeMM Research Center for Molecular Medicine
   - given-names: Raphael
     family-names: Bednarsky
-    orcid: 'https://orcid.org/0009-0005-0404-3424'
+    orcid: "https://orcid.org/0009-0005-0404-3424"
     affiliation: CeMM Research Center for Molecular Medicine
   - given-names: Christoph
     family-names: Bock
-    orcid: 'https://orcid.org/0000-0001-6091-3088'
+    orcid: "https://orcid.org/0000-0001-6091-3088"
     affiliation: CeMM Research Center for Molecular Medicine
 identifiers:
   - type: doi
     value: 10.5281/zenodo.8405360.
     description: >-
       This DOI represents all versions, and will always
       resolve to the latest one.
-repository-code: 'https://github.com/epigen/unsupervised_analysis'
-url: 'https://epigen.github.io/unsupervised_analysis/'
+repository-code: "https://github.com/epigen/unsupervised_analysis"
+url: "https://epigen.github.io/unsupervised_analysis/"
 abstract: >-
   A general purpose Snakemake workflow to perform
   unsupervised analyses (dimensionality reduction & cluster

_config.yml

@@ -1 +1 @@
-theme: jekyll-theme-cayman
+theme: jekyll-theme-cayman

config/README.md

@@ -4,9 +4,9 @@ You need one configuration file to configure the analyses and one annotation fil
 
 - project configuration (`config/config.yaml`): Different for every project and configures the analyses to be performed.
 - sample annotation (annotation): CSV file consisting of four mandatory columns.
-    -  name: A unique name for the dataset (tip: keep it short but descriptive).
-    -  data: Path to the tabular data as a comma-separated table (CSV).
-    -  metadata: Path to the metadata as a comma-separated table (CSV) with the first column being the index/identifier of each observation/sample and every other column metadata for the respective observation (either numeric or categorical, not mixed). **No NaN or empty values allowed, and no special characters (all except a-z, 0-9, `_`) in the index.**
-    -  samples_by_features: Boolean indicator if the data matrix is observations/samples (rows) x features (columns): 0==no, 1==yes.
+  - name: A unique name for the dataset (tip: keep it short but descriptive).
+  - data: Path to the tabular data as a comma-separated table (CSV).
+  - metadata: Path to the metadata as a comma-separated table (CSV) with the first column being the index/identifier of each observation/sample and every other column metadata for the respective observation (either numeric or categorical, not mixed). **No NaN or empty values allowed, and no special characters (all except a-z, 0-9, `_`) in the index.**
+  - samples_by_features: Boolean indicator if the data matrix is observations/samples (rows) x features (columns): 0==no, 1==yes.
 
 Set workflow-specific `resources` or command line arguments (CLI) in the workflow profile `workflow/profiles/default.config.yaml`, which supersedes global Snakemake profiles.

config/config.yaml

@@ -2,7 +2,7 @@
 
 ##### RESOURCES #####
 # memory in MB
-mem: '32000'
+mem: 32000
 threads: 2
 
 ##### GENERAL #####
@@ -14,8 +14,8 @@ project_name: digits
 # https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html
 # especially relevant for large data
 pca:
-    n_components: 0.9 # variance as float (0-1], number of components as int e.g., 50, or 'mle'
-    svd_solver: 'auto' # options: ‘auto’, ‘full’, ‘covariance_eigh’, ‘arpack’, ‘randomized’
+  n_components: 0.9 # variance as float (0-1], number of components as int e.g., 50, or 'mle'
+  svd_solver: "auto" # options: ‘auto’, ‘full’, ‘covariance_eigh’, ‘arpack’, ‘randomized’
 
 ##### UMAP & densMAP #####
 # https://umap-learn.readthedocs.io/en/latest/parameters.html
@@ -25,52 +25,53 @@ pca:
 # densmap flag: perform densMAP  (0==no, 1==yes) on top of UMAP with all parameter combinations (https://umap-learn.readthedocs.io/en/latest/densmap_demo.html)
 # connectivity visualization flag (0==no, 1==yes), computational expensive (slow), recommendation 0 for exploration and 1 for validation
 umap:
-    metrics: ['euclidean']
-    n_neighbors: [15]
-    min_dist: [0.1]
-    n_components: [2]
-    densmap: 1
-    connectivity: 1
-    diagnostics: 1
+  metrics: ["euclidean"]
+  n_neighbors: [15]
+  min_dist: [0.1]
+  n_components: [2]
+  densmap: 1
+  connectivity: 1
+  diagnostics: 1
 
 ##### HEATMAP #####
 # information on the ComplexHeatmap parameters: https://jokergoo.github.io/ComplexHeatmap-reference/book/index.html
 # distance metrics: for rows and columns. all metrics that are supported by scipy.spatial.distance.pdist (https://docs.scipy.org/doc/scipy-1.14.0/reference/generated/scipy.spatial.distance.pdist.html)
 # clustering methods: methods for hierarchical clustering that are supported by fastcluster's R implementation (https://danifold.net/fastcluster.html)
 # it is the most resource (memory) intensive method, leave empty [] if not required
 heatmap:
-    metrics: ['correlation','cosine']
-    hclust_methods: ['complete']
-    n_observations: 1 # random sampled proportion float (0-1] or absolute number as integer
-    n_features: 0.5 # highly variable features proportion float (0-1] or absolute number as integer
-    
+  metrics: ["correlation", "cosine"]
+  hclust_methods: ["complete"]
+  n_observations: 1 # random sampled proportion float (0-1] or absolute number as integer
+  n_features: 0.5 # highly variable features proportion float (0-1] or absolute number as integer
+
 ##### LEIDEN #####
 # Leiden clustering applied on UMAP KNN graphs specified by the respective parameters (metric, n_neighbors).
 # Leiden algorithm specific parameters (partition_types, resolutions, n_iterations) -> https://leidenalg.readthedocs.io/en/stable/index.html
 # To skip Leiden clustering, leave the "metrics" parameter empty i.e., []
 leiden:
-    metrics: [] # has to be a subset of above's UMAP parameters
-    n_neighbors: [15] # has to be a subset of above's UMAP parameters
-    partition_types: ["RBConfigurationVertexPartition", "ModularityVertexPartition"]
-    resolutions: [0.5,1,1.5,2,4] # only used for relevant partition_types
-    n_iterations: 2 # default: 2; -1 until convergence
+  metrics: [] # has to be a subset of above's UMAP parameters
+  n_neighbors: [15] # has to be a subset of above's UMAP parameters
+  partition_types:
+    ["RBConfigurationVertexPartition", "ModularityVertexPartition"]
+  resolutions: [0.5, 1, 1.5, 2, 4] # only used for relevant partition_types
+  n_iterations: 2 # default: 2; -1 until convergence
 
 ##### clustification #####
 # ML-based clustering approach that iteratively merges clusters based on misclassification.
 # Doesn't support externally provided clusterings.
 clustification:
-    method: "" # starting clustering result method, options: "Leiden"
+  method: "" # starting clustering result method, options: "Leiden"
 
 ##### clustree #####
 # Cluster analysis and visualization using clustree: https://lazappi.github.io/clustree/index.html
 # Clustree specific parameters (count_filter, prop_filter, layout): https://lazappi.github.io/clustree/reference/clustree.html
 # Will be skipped if no clustering results are available
 clustree:
-    count_filter: 0 # default: 0
-    prop_filter: 0.1 # default: 0.1
-    layout: "tree"  # options: "tree" or "sugiyama"
-    categorical_label_option: "majority" # aggregation function for categorical metadata, options: "pure" or "majority"
-    numerical_aggregation_option: "mean" # aggregation function for numerical metadata, options: mean, median, max, min
+  count_filter: 0 # default: 0
+  prop_filter: 0.1 # default: 0.1
+  layout: "tree" # options: "tree" or "sugiyama"
+  categorical_label_option: "majority" # aggregation function for categorical metadata, options: "pure" or "majority"
+  numerical_aggregation_option: "mean" # aggregation function for numerical metadata, options: mean, median, max, min
 
 ##### cluster validation ####
 # Cluster validation using internal cluster indices is computationally very expensive.
@@ -85,21 +86,21 @@ sample_proportion: 1 # float [0-1], >500 samples should be included.
 # - internal cluster validation (categorical metadata interpreted as clusterings)
 # Can be empty [], then the first column of the metadata dataframe will be taken.
 metadata_of_interest: ["target"]
-    
+
 ##### VISUALIZATION #####
-# flag if coordinates should be fixed in 2D plots by +coord_fixed() (0==no, 1==yes) 
+# flag if coordinates should be fixed in 2D plots by +coord_fixed() (0==no, 1==yes)
 # https://ggplot2.tidyverse.org/reference/coord_fixed.html
 coord_fixed: 0
 
 # 2D/3D visualization with ggplot2 and plotly
 # for more than 200 datapoints it is recommended to reduce size to 0.1
 scatterplot2d:
-    size: 1
-    alpha: 1
+  size: 1
+  alpha: 1
 
 # specify features of interest. these features from the data, will be highlighted in the 2D/3D plots
 # motivated by bioinformatics highlighting expression levels of marker genes (eg: ['PTPRC','STAT1','IRF8'])
 # use keyword ['ALL'] to plot all features. WARNING: Only useful for relatively low dimensional data, a plot is generated for each feature and method.
 # if not used leave empty []
-features_to_plot: ['ALL'] #['pixel_0_0','pixel_0_1','pixel_0_2','pixel_0_3']
+features_to_plot: ["ALL"] #['pixel_0_0','pixel_0_1','pixel_0_2','pixel_0_3']