Add some missing descriptions

CHANGELOG.md

@@ -4,6 +4,10 @@
 
 * Removed `split_h5mu_train_test` component (PR #1020).
 
+* `compress_h5mu`: rename `compression` argument to `output_compression` (PR #1017, PR #1018).
+
+* `delimit_fraction`: remove unused `layer` argument (PR #1018).
+
 ## MAJOR CHANGES
 
 * `mapping/cellranger_*`: Upgrade CellRanger to v9.0 (PR #992 and #1006).
@@ -14,6 +18,8 @@
 
 * Move output file compression argument for AnnData and MuData files to a base config file (`src/base/h5_compression_argument.yaml`) (PR #1017).
 
+* Add missing descriptions to components and arguments (PR #1018).
+
 ## BUG FIXES
 
 * Bump viash to 0.9.4. This adds support for nextflow versions starting major version 25.01 and fixes an issue where an integer being passed to a argument with `type: double` resulted in an error (PR #1016).

src/annotate/scanvi/config.vsh.yaml

@@ -21,6 +21,8 @@ argument_groups:
         direction: input
         required: true
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: false

src/annotate/svm_annotation/config.vsh.yaml

@@ -52,6 +52,9 @@ argument_groups:
         type: string
         description:
         required: true
+        description: |
+          Key in .obs attribute of reference modality with cell-type information.
+
       - name:  "--reference_var_gene_names"
         type: string
         required: false

src/cluster/leiden/config.vsh.yaml

@@ -24,6 +24,8 @@ arguments:
     example: input.h5mu
 
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/compression/compress_h5mu/config.vsh.yaml

@@ -18,12 +18,7 @@ arguments:
     description: location of output file.
     required: true
     direction: output
-  - name: "--compression"
-    type: string 
-    description: Compression type.
-    required: false
-    default: "gzip"
-    choices: ["lzf", "gzip"]
+__merge__: [., /src/base/h5_compression_argument.yaml]
 resources:
   - type: python_script
     path: script.py

src/compression/compress_h5mu/run_test.py

@@ -35,7 +35,7 @@ def test_compress_h5mu(run_component, tmp_path, compression_type):
             str(input_file),
             "--output",
             str(output_file),
-            "--compression",
+            "--output_compression",
             compression_type,
         ]
     )

src/compression/compress_h5mu/script.py

@@ -13,4 +13,4 @@
 from compress_h5mu import compress_h5mu
 
 if __name__ == "__main__":
-    compress_h5mu(par["input"], par["output"], compression=par["compression"])
+    compress_h5mu(par["input"], par["output"], compression=par["output_compression"])

src/convert/from_h5ad_to_h5mu/config.vsh.yaml

@@ -15,6 +15,9 @@ arguments:
     required: true
     multiple: true
   - name: "--modality"
+    description: |
+      List of names to use for the modalities. Will be used as the keys in the .mod attribute in the output MuData object
+      The number of items provided for this argument equal the number of input files (--input) and their order should match.
     type: string
     default: "rna"
     required: false

src/convert/from_h5mu_to_h5ad/config.vsh.yaml

@@ -14,6 +14,8 @@ arguments:
     direction: input
     required: true
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/correction/cellbender_remove_background/config.vsh.yaml

@@ -46,6 +46,8 @@ argument_groups:
         type: string
         default: "cellbender_cell_size"
       - name: "--obs_droplet_efficiency"
+        description: |
+          Name of the column in the .obs dataframe to store the droplet efficiencies in.
         type: string
         default: "cellbender_droplet_efficiency"
       - name: "--obs_latent_scale"

src/dataflow/concatenate_h5mu/config.vsh.yaml

@@ -27,6 +27,8 @@ arguments:
       If specified, must be of same length as `--input`.
     required: false
   - name: "--output"
+    description: |
+      Output location for the concatenated MuData object file.
     alternatives: ["-o"]
     type: file
     direction: output

src/dataflow/split_h5mu/config.vsh.yaml

@@ -13,6 +13,8 @@ argument_groups:
     description: Path to a single .h5mu file.
     required: true
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/demux/bcl2fastq/config.vsh.yaml

@@ -32,6 +32,9 @@ arguments:
     description: Reports directory
     example: reports_dir
   - name: "--ignore_missing"
+    description: |
+      Interpret missing *.bcl files as no call (N), interpret missing control files as not-set
+      control bits and fill in with zeros when *.stats files are missing.
     type: boolean_true
 resources:
   - type: bash_script

src/dimred/densmap/config.vsh.yaml

@@ -17,6 +17,8 @@ argument_groups:
         example: input.h5mu
 
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: false

src/dimred/pca/config.vsh.yaml

@@ -16,6 +16,8 @@ arguments:
     example: input.h5mu
 
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/dimred/tsne/config.vsh.yaml

@@ -16,6 +16,8 @@ argument_groups:
         example: input.h5mu
 
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: true

src/dimred/umap/config.vsh.yaml

@@ -16,6 +16,8 @@ argument_groups:
         example: input.h5mu
 
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: false

src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml

@@ -25,6 +25,8 @@ arguments:
     example: input.h5mu
 
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/feature_annotation/score_genes_cell_cycle_scanpy/config.vsh.yaml

@@ -20,6 +20,8 @@ argument_groups:
         required: true
         example: input_file.h5mu
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: false

src/feature_annotation/score_genes_scanpy/config.vsh.yaml

@@ -49,6 +49,8 @@ argument_groups:
       required: false
       example: gene_pool.txt
     - name: "--modality"
+      description: |
+        Which modality from the input MuData file to process.
       type: string
       default: "rna"
       required: false  

src/filter/delimit_fraction/config.vsh.yaml

@@ -17,15 +17,12 @@ argument_groups:
         example: input.h5mu
 
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: false
 
-      - name: "--layer"
-        type: string
-        example: "raw_counts"
-        required: false
-
       - name: "--obs_fraction_column"
         type: string
         required: true

src/filter/do_filter/config.vsh.yaml

@@ -15,6 +15,8 @@ arguments:
     example: input.h5mu
 
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/filter/filter_with_counts/config.vsh.yaml

@@ -21,11 +21,17 @@ argument_groups:
         example: input.h5mu
 
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: false
 
       - name: "--layer"
+        description: |
+        description: |
+          Location of the count matrix. If specified, will be used to select a key from .layers,
+          otherwise .X is used.
         type: string
         example: "raw_counts"
         required: false

src/filter/filter_with_scrublet/config.vsh.yaml

@@ -36,6 +36,8 @@ arguments:
     example: input.h5mu
 
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/filter/intersect_obs/config.vsh.yaml

@@ -19,6 +19,8 @@ arguments:
     example: input.h5mu
 
   - name: "--modalities"
+    description: |
+      Which modalities from the input MuData file to process.
     type: string
     multiple: true
     required: true

src/filter/remove_modality/config.vsh.yaml

@@ -13,6 +13,8 @@ arguments:
     required: true
     example: input.h5mu
   - name: "--modality"
+    description: |
+      Name(s) of the modality to remove
     type: string
     multiple: true
     required: true

src/filter/subset_h5mu/config.vsh.yaml

@@ -13,6 +13,8 @@ arguments:
     required: true
     example: input.h5mu
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/filter/subset_obsp/config.vsh.yaml

@@ -15,6 +15,8 @@ argument_groups:
       required: true
       example: input.h5mu
     - name: "--modality"
+      description: |
+        Which modality from the input MuData file to process.
       type: string
       default: "rna"
       required: false

src/integrate/harmonypy/config.vsh.yaml

@@ -21,6 +21,8 @@ arguments:
     direction: output
     required: true
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/integrate/scanorama/config.vsh.yaml

@@ -15,6 +15,8 @@ arguments:
     direction: input
     required: true
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/integrate/scarches/config.vsh.yaml

@@ -21,6 +21,8 @@ argument_groups:
         description: Layer to be used for scArches, if .X is not to be used.
         required: false
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: false

src/integrate/scvi/config.vsh.yaml

@@ -18,6 +18,8 @@ argument_groups:
         direction: input
         required: true
       - name: "--modality"
+        description: |
+          Which modality from the input MuData file to process.
         type: string
         default: "rna"
         required: false

src/interpret/lianapy/config.vsh.yaml

@@ -20,6 +20,8 @@ arguments:
     direction: output
     required: true
   - name: "--modality"
+    description: |
+      Which modality from the input MuData file to process.
     type: string
     default: "rna"
     required: false

src/mapping/bd_rhapsody/config.vsh.yaml

@@ -620,6 +620,8 @@ argument_groups:
       info:
         config_key: VDJ_VGene_Evalue
     - name: --write_filtered_reads
+      description:
+        Output processed FASTQ reads.
       type: boolean
       multiple: false
       info:

src/mapping/cellranger_count_split/config.vsh.yaml

@@ -15,36 +15,43 @@ arguments:
     example: input_dir
     description: Output directory from a Cell Ranger count run.
   - name: --filtered_h5
+    description: |
+      Output path for the h5 file storing the filtered counts.
     type: file
     direction: output
     required: false
-    # description: Counts in AnnData format.
     example: filtered_feature_bc_matrix.h5
   - name: --metrics_summary
+    description: |
+      Where to store the 'metrics_summary' CSV file.
     type: file
     direction: output
     required: false
-    # description: Counts in AnnData format.
     example: metrics_summary.csv
   - name: --molecule_info
+    description: |
+      Where to store Cell Ranger's 'molecule_info.h5' file.
     type: file
     direction: output
     required: false
-    # description: Counts in AnnData format.
     example: molecule_info.h5
   - name: --bam
+    description: |
+      Location of output BAM files.
     type: file
     direction: output
     required: false
-    # description: Counts in AnnData format.
     example: possorted_genome_bam.bam
   - name: --bai
+    description: |
+      Where to store the BAM index files.
     type: file
     direction: output
     required: false
-    # description: Counts in AnnData format.
     example: possorted_genome_bam.bam.bai
   - name: --raw_h5
+    description: |
+      Output path for the h5 file storing the raw counts.
     type: file
     direction: output
     required: false

src/metadata/add_id/config.vsh.yaml

@@ -23,6 +23,8 @@ arguments:
     description: "Name of the .obs column where to store the id."
     default: "sample_id"
   - name: "--output"
+    description: |
+      Name of output MuData file.
     alternatives: ["-o"]
     type: file
     direction: output