From 6a5ecba20028682520eb94ed4e5b65a09ec80e82 Mon Sep 17 00:00:00 2001 From: Dries Schaumont <5946712+DriesSchaumont@users.noreply.github.com> Date: Fri, 2 May 2025 09:29:30 +0000 Subject: [PATCH 1/8] Put output_compression argument in base --- src/annotate/celltypist/config.vsh.yaml | 6 +----- src/annotate/onclass/config.vsh.yaml | 6 +----- src/annotate/popv/config.vsh.yaml | 7 ++----- src/annotate/random_forest_annotation/config.vsh.yaml | 6 +----- src/annotate/scanvi/config.vsh.yaml | 9 ++------- src/annotate/svm_annotation/config.vsh.yaml | 6 +----- src/base/h5_compression_argument.yaml | 9 +++++++++ src/cluster/leiden/config.vsh.yaml | 8 +------- src/convert/from_10xh5_to_h5mu/config.vsh.yaml | 7 ++----- src/convert/from_10xmtx_to_h5mu/config.vsh.yaml | 7 ++----- src/convert/from_bdrhap_to_h5mu/config.vsh.yaml | 7 ++----- .../from_cellranger_multi_to_h5mu/config.vsh.yaml | 7 ++----- src/convert/from_h5ad_to_h5mu/config.vsh.yaml | 8 +++----- src/convert/from_h5mu_to_h5ad/config.vsh.yaml | 8 +++----- .../cellbender_remove_background/config.vsh.yaml | 7 ++----- .../cellbender_remove_background_v0_2/config.vsh.yaml | 7 ++----- src/dataflow/concatenate_h5mu/config.vsh.yaml | 7 +------ src/dataflow/split_h5mu/config.vsh.yaml | 8 ++------ src/dataflow/split_modalities/config.vsh.yaml | 8 ++------ src/dimred/densmap/config.vsh.yaml | 9 ++------- src/dimred/lsi/config.vsh.yaml | 9 +-------- src/dimred/pca/config.vsh.yaml | 10 +++------- src/dimred/tsne/config.vsh.yaml | 9 ++------- src/dimred/umap/config.vsh.yaml | 8 +------- .../align_query_reference/config.vsh.yaml | 6 +----- .../highly_variable_features_scanpy/config.vsh.yaml | 10 +++------- .../score_genes_cell_cycle_scanpy/config.vsh.yaml | 7 +------ .../score_genes_scanpy/config.vsh.yaml | 8 ++------ src/filter/delimit_fraction/config.vsh.yaml | 8 +------- src/filter/do_filter/config.vsh.yaml | 8 +------- src/filter/filter_with_counts/config.vsh.yaml | 8 +------- src/filter/filter_with_scrublet/config.vsh.yaml | 9 ++------- src/filter/intersect_obs/config.vsh.yaml | 8 ++------ src/filter/remove_modality/config.vsh.yaml | 8 ++------ src/filter/subset_h5mu/config.vsh.yaml | 8 ++------ src/filter/subset_obsp/config.vsh.yaml | 7 +------ src/integrate/harmony/config.vsh.yaml | 7 +------ src/integrate/harmonypy/config.vsh.yaml | 7 +------ src/integrate/scanorama/config.vsh.yaml | 7 +------ src/integrate/scarches/config.vsh.yaml | 7 +------ src/integrate/scvi/config.vsh.yaml | 8 ++------ src/interpret/lianapy/config.vsh.yaml | 6 +----- src/labels_transfer/api/common_arguments.yaml | 9 ++------- src/mapping/htseq_count_to_h5mu/config.vsh.yaml | 8 ++------ src/mapping/multi_star_to_h5mu/config.vsh.yaml | 8 ++------ src/metadata/add_id/config.vsh.yaml | 8 ++------ src/metadata/grep_annotation_column/config.vsh.yaml | 8 ++------ src/metadata/move_obsm_to_obs/config.vsh.yaml | 7 +------ src/neighbors/bbknn/config.vsh.yaml | 9 ++------- src/neighbors/find_neighbors/config.vsh.yaml | 8 +------- src/qc/calculate_atac_qc_metrics/config.vsh.yaml | 8 ++------ src/qc/calculate_qc_metrics/config.vsh.yaml | 8 ++------ src/query/cellxgene_census/config.vsh.yaml | 7 ++----- src/scgpt/binning/config.vsh.yaml | 9 ++------- src/scgpt/cell_type_annotation/config.vsh.yaml | 8 +------- src/scgpt/cross_check_genes/config.vsh.yaml | 6 +----- src/scgpt/embedding/config.vsh.yaml | 9 +-------- src/scgpt/pad_tokenize/config.vsh.yaml | 7 +------ src/transform/bpcells_regress_out/config.vsh.yaml | 8 +------- src/transform/clr/config.vsh.yaml | 8 ++------ src/transform/delete_layer/config.vsh.yaml | 8 ++------ src/transform/log1p/config.vsh.yaml | 10 +++------- src/transform/move_layer/config.vsh.yaml | 9 +++------ src/transform/normalize_total/config.vsh.yaml | 8 +------- src/transform/regress_out/config.vsh.yaml | 8 ++------ src/transform/scale/config.vsh.yaml | 9 +++------ src/transform/tfidf/config.vsh.yaml | 9 ++------- src/velocity/scvelo/config.vsh.yaml | 8 ++------ src/velocity/velocyto_to_h5mu/config.vsh.yaml | 7 +------ 69 files changed, 124 insertions(+), 415 deletions(-) create mode 100644 src/base/h5_compression_argument.yaml diff --git a/src/annotate/celltypist/config.vsh.yaml b/src/annotate/celltypist/config.vsh.yaml index e1e04d7d15c..04578b352bf 100644 --- a/src/annotate/celltypist/config.vsh.yaml +++ b/src/annotate/celltypist/config.vsh.yaml @@ -109,11 +109,6 @@ argument_groups: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_obs_predictions" type: string default: celltypist_pred @@ -126,6 +121,7 @@ argument_groups: required: false description: | In which `.obs` slots to store the probability of the predictions. + __merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/annotate/onclass/config.vsh.yaml b/src/annotate/onclass/config.vsh.yaml index 7019d20ab00..25e369a9304 100644 --- a/src/annotate/onclass/config.vsh.yaml +++ b/src/annotate/onclass/config.vsh.yaml @@ -98,11 +98,6 @@ argument_groups: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_obs_predictions" type: string default: onclass_pred @@ -115,6 +110,7 @@ argument_groups: required: false description: | In which `.obs` slots to store the probability of the predictions. + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Model arguments description: Model arguments diff --git a/src/annotate/popv/config.vsh.yaml b/src/annotate/popv/config.vsh.yaml index 2b07d11d1f3..63f6c16ea1b 100644 --- a/src/annotate/popv/config.vsh.yaml +++ b/src/annotate/popv/config.vsh.yaml @@ -80,11 +80,8 @@ argument_groups: direction: output required: true example: output.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + # - name: "--output_models" # type: file # direction: output diff --git a/src/annotate/random_forest_annotation/config.vsh.yaml b/src/annotate/random_forest_annotation/config.vsh.yaml index a7907ad33c6..60112668509 100644 --- a/src/annotate/random_forest_annotation/config.vsh.yaml +++ b/src/annotate/random_forest_annotation/config.vsh.yaml @@ -71,11 +71,6 @@ argument_groups: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_obs_predictions" type: string default: random_forest_pred @@ -88,6 +83,7 @@ argument_groups: required: false description: | In which `.obs` slots to store the probability of the predictions. + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Model arguments description: Model arguments. diff --git a/src/annotate/scanvi/config.vsh.yaml b/src/annotate/scanvi/config.vsh.yaml index db5f485fac8..27bc8107464 100644 --- a/src/annotate/scanvi/config.vsh.yaml +++ b/src/annotate/scanvi/config.vsh.yaml @@ -68,12 +68,6 @@ argument_groups: description: Folder where the state of the trained model will be saved to. required: false direction: output - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--obsm_output" type: string default: "X_scanvi_integrated" @@ -87,7 +81,8 @@ argument_groups: type: string default: scanvi_proba description: "In which. obs slot to store the probabilities of the predicted labels." - + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: "scANVI training arguments" arguments: - name: "--early_stopping" diff --git a/src/annotate/svm_annotation/config.vsh.yaml b/src/annotate/svm_annotation/config.vsh.yaml index 5a708b7941f..e826e586f72 100644 --- a/src/annotate/svm_annotation/config.vsh.yaml +++ b/src/annotate/svm_annotation/config.vsh.yaml @@ -71,11 +71,6 @@ argument_groups: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_obs_prediction" type: string default: svm_pred @@ -88,6 +83,7 @@ argument_groups: required: false description: | In which `.obs` slots to store the probability of the predictions. + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Model arguments description: Model arguments. diff --git a/src/base/h5_compression_argument.yaml b/src/base/h5_compression_argument.yaml new file mode 100644 index 00000000000..d575860a79e --- /dev/null +++ b/src/base/h5_compression_argument.yaml @@ -0,0 +1,9 @@ +arguments: + - name: "--output_compression" + description: | + Compression format to use for the output AnnData and/or Mudata objects. + By default no compression is applied. + type: string + choices: ["gzip", "lzf"] + required: false + example: "gzip" \ No newline at end of file diff --git a/src/cluster/leiden/config.vsh.yaml b/src/cluster/leiden/config.vsh.yaml index 1b06cdc6076..2661399387b 100644 --- a/src/cluster/leiden/config.vsh.yaml +++ b/src/cluster/leiden/config.vsh.yaml @@ -41,19 +41,13 @@ arguments: direction: output required: true example: output.h5mu - - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--obsm_name" type: string description: | Name of the .obsm key under which to add the cluster labels. The name of the columns in the matrix will correspond to the resolutions. default: "leiden" + __merge__: [., /src/base/h5_compression_argument.yaml] # todo: add uns_params # example: uns["leiden"] = {'params': {'n_iterations': -1, 'random_state': 0, 'resolution': 1.0}} diff --git a/src/convert/from_10xh5_to_h5mu/config.vsh.yaml b/src/convert/from_10xh5_to_h5mu/config.vsh.yaml index 3c0e32f6cc5..908535a1d03 100644 --- a/src/convert/from_10xh5_to_h5mu/config.vsh.yaml +++ b/src/convert/from_10xh5_to_h5mu/config.vsh.yaml @@ -28,15 +28,12 @@ argument_groups: example: output.h5mu direction: output __merge__: api_output.yaml - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--uns_metrics" type: string description: Name of the .uns slot under which to QC metrics (if any). default: "metrics_cellranger" + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: Arguments arguments: - name: "--min_genes" diff --git a/src/convert/from_10xmtx_to_h5mu/config.vsh.yaml b/src/convert/from_10xmtx_to_h5mu/config.vsh.yaml index 4a98b05fd4f..15156317fcb 100644 --- a/src/convert/from_10xmtx_to_h5mu/config.vsh.yaml +++ b/src/convert/from_10xmtx_to_h5mu/config.vsh.yaml @@ -19,11 +19,8 @@ arguments: description: Output h5mu file. example: output.h5mu direction: output - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/convert/from_bdrhap_to_h5mu/config.vsh.yaml b/src/convert/from_bdrhap_to_h5mu/config.vsh.yaml index 3e1787c6516..7098a8fc6e0 100644 --- a/src/convert/from_bdrhap_to_h5mu/config.vsh.yaml +++ b/src/convert/from_bdrhap_to_h5mu/config.vsh.yaml @@ -30,11 +30,8 @@ argument_groups: description: "Output h5mu file." required: true example: output.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml b/src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml index 76558be6c52..8cce946a607 100644 --- a/src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml +++ b/src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml @@ -41,15 +41,12 @@ arguments: description: CSV file describing the sample name per output file direction: output example: "samples.csv" - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--uns_metrics" type: string description: Name of the .uns slot under which to QC metrics (if any). default: "metrics_cellranger" + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/convert/from_h5ad_to_h5mu/config.vsh.yaml b/src/convert/from_h5ad_to_h5mu/config.vsh.yaml index 6bd7cf8a24b..d7c8db648f5 100644 --- a/src/convert/from_h5ad_to_h5mu/config.vsh.yaml +++ b/src/convert/from_h5ad_to_h5mu/config.vsh.yaml @@ -25,11 +25,9 @@ arguments: description: Output MuData file. default: output.h5mu direction: output - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + + resources: - type: python_script path: script.py diff --git a/src/convert/from_h5mu_to_h5ad/config.vsh.yaml b/src/convert/from_h5mu_to_h5ad/config.vsh.yaml index 4591cac30fc..585f9a7e778 100644 --- a/src/convert/from_h5mu_to_h5ad/config.vsh.yaml +++ b/src/convert/from_h5mu_to_h5ad/config.vsh.yaml @@ -23,11 +23,9 @@ arguments: description: Output AnnData file. default: output.h5ad direction: output - - name: "--output_compression" - type: string - description: The compression format to be used on the final h5ad object. - default: "gzip" - choices: ["gzip", "lzf"] + __merge__: [., /src/base/h5_compression_argument.yaml] + + resources: - type: python_script path: script.py diff --git a/src/correction/cellbender_remove_background/config.vsh.yaml b/src/correction/cellbender_remove_background/config.vsh.yaml index 1dfe6a90335..3b06f13452a 100644 --- a/src/correction/cellbender_remove_background/config.vsh.yaml +++ b/src/correction/cellbender_remove_background/config.vsh.yaml @@ -32,11 +32,6 @@ argument_groups: direction: output required: true example: output.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--layer_output" description: Output layer type: string @@ -62,6 +57,8 @@ argument_groups: - name: "--obsm_gene_expression_encoding" type: string default: "cellbender_gene_expression_encoding" + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: Arguments arguments: # custom arg diff --git a/src/correction/cellbender_remove_background_v0_2/config.vsh.yaml b/src/correction/cellbender_remove_background_v0_2/config.vsh.yaml index 8d77841d21e..9210796985b 100644 --- a/src/correction/cellbender_remove_background_v0_2/config.vsh.yaml +++ b/src/correction/cellbender_remove_background_v0_2/config.vsh.yaml @@ -32,11 +32,6 @@ argument_groups: direction: output required: true example: output.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--layer_output" description: Output layer type: string @@ -56,6 +51,8 @@ argument_groups: - name: "--obsm_latent_gene_encoding" type: string default: "cellbender_latent_gene_encoding" + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: Arguments arguments: - name: "--expected_cells" diff --git a/src/dataflow/concatenate_h5mu/config.vsh.yaml b/src/dataflow/concatenate_h5mu/config.vsh.yaml index 3e55c813391..899576a99ea 100644 --- a/src/dataflow/concatenate_h5mu/config.vsh.yaml +++ b/src/dataflow/concatenate_h5mu/config.vsh.yaml @@ -31,12 +31,6 @@ arguments: type: file direction: output example: "output.h5mu" - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--obs_sample_name" type: string description: Name of the .obs key under which to add the sample names. @@ -66,6 +60,7 @@ arguments: type: string choices: ["same", "unique", "first", "only", "make_unique"] default: make_unique +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/dataflow/split_h5mu/config.vsh.yaml b/src/dataflow/split_h5mu/config.vsh.yaml index 1a83d8d3ee0..2497ac6579b 100644 --- a/src/dataflow/split_h5mu/config.vsh.yaml +++ b/src/dataflow/split_h5mu/config.vsh.yaml @@ -36,18 +36,14 @@ argument_groups: direction: output example: "/path/to/output" description: Output directory containing multiple h5mu files. - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_files" type: file required: true direction: output example: sample_files.csv description: A csv containing the base filename and obs feature by which it was split. + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script diff --git a/src/dataflow/split_modalities/config.vsh.yaml b/src/dataflow/split_modalities/config.vsh.yaml index 36279847603..1d5a76cba09 100644 --- a/src/dataflow/split_modalities/config.vsh.yaml +++ b/src/dataflow/split_modalities/config.vsh.yaml @@ -21,18 +21,14 @@ arguments: direction: output example: "/path/to/output" description: Output directory containing multiple h5mu files. - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_types" type: file required: true direction: output example: types.csv description: A csv containing the base filename and modality type per output file. +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/dimred/densmap/config.vsh.yaml b/src/dimred/densmap/config.vsh.yaml index 5e9c7f0685c..db2f6749215 100644 --- a/src/dimred/densmap/config.vsh.yaml +++ b/src/dimred/densmap/config.vsh.yaml @@ -42,17 +42,12 @@ argument_groups: required: true example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--obsm_output" type: string description: The .obsm key to use for storing the densMAP results.. default: "X_densmap" + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: Arguments UMAP arguments: diff --git a/src/dimred/lsi/config.vsh.yaml b/src/dimred/lsi/config.vsh.yaml index 760d5b64b60..5ef07638a3d 100644 --- a/src/dimred/lsi/config.vsh.yaml +++ b/src/dimred/lsi/config.vsh.yaml @@ -58,13 +58,6 @@ argument_groups: required: true example: output.h5mu - - name: "--output_compression" - type: string - default: "gzip" - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - - name: "--obsm_output" type: string default: "X_lsi" @@ -86,7 +79,7 @@ argument_groups: - name: "--overwrite" type: boolean_true description: Allow overwriting .obsm, .varm and .uns slots. - + __merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/dimred/pca/config.vsh.yaml b/src/dimred/pca/config.vsh.yaml index eb7ba4d101a..b99d4fe4de1 100644 --- a/src/dimred/pca/config.vsh.yaml +++ b/src/dimred/pca/config.vsh.yaml @@ -39,13 +39,6 @@ arguments: required: true example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--obsm_output" type: string default: "X_pca" @@ -70,6 +63,9 @@ arguments: - name: "--overwrite" type: boolean_true description: "Allow overwriting .obsm, .varm and .uns slots." + +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/dimred/tsne/config.vsh.yaml b/src/dimred/tsne/config.vsh.yaml index 34a4576dd50..5a8a0549304 100644 --- a/src/dimred/tsne/config.vsh.yaml +++ b/src/dimred/tsne/config.vsh.yaml @@ -36,17 +36,12 @@ argument_groups: required: true example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--obsm_output" type: string description: The .obsm key to use for storing the tSNE results. default: "X_tsne" + + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/dimred/umap/config.vsh.yaml b/src/dimred/umap/config.vsh.yaml index 22f9e2534ac..3598d4a84d4 100644 --- a/src/dimred/umap/config.vsh.yaml +++ b/src/dimred/umap/config.vsh.yaml @@ -35,17 +35,11 @@ argument_groups: required: true example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--obsm_output" type: string description: The pre/postfix under which to store the UMAP results. default: "umap" + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/feature_annotation/align_query_reference/config.vsh.yaml b/src/feature_annotation/align_query_reference/config.vsh.yaml index 34192b236df..da2803f4ba3 100644 --- a/src/feature_annotation/align_query_reference/config.vsh.yaml +++ b/src/feature_annotation/align_query_reference/config.vsh.yaml @@ -114,11 +114,6 @@ argument_groups: description: Aligned reference data. direction: output example: output_reference.h5mu - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_layer" type: string default: "_counts" @@ -151,6 +146,7 @@ argument_groups: type: string default: "_common_vars" description: Name of the .var column in the output query and reference datasets containing the boolean array indicating the common variables. + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments description: Arguments related to the alignment of the input and reference datasets. diff --git a/src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml b/src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml index ec3f580fe91..2408280c141 100644 --- a/src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml +++ b/src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml @@ -44,13 +44,6 @@ arguments: direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--var_name_filter" type: string default: "filter_with_hvg" @@ -112,6 +105,9 @@ arguments: For all flavors, features are first sorted by how many batches they are a HVG. For dispersion-based flavors ties are broken by normalized dispersion. If flavor = 'seurat_v3', ties are broken by the median (across batches) rank based on within-batch normalized variance. + +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/feature_annotation/score_genes_cell_cycle_scanpy/config.vsh.yaml b/src/feature_annotation/score_genes_cell_cycle_scanpy/config.vsh.yaml index 6fe382bcc12..6412e18f9b9 100644 --- a/src/feature_annotation/score_genes_cell_cycle_scanpy/config.vsh.yaml +++ b/src/feature_annotation/score_genes_cell_cycle_scanpy/config.vsh.yaml @@ -95,12 +95,6 @@ argument_groups: Output h5mu file required: true example: output_file.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--obs_phase" type: string description: | @@ -119,6 +113,7 @@ argument_groups: The name of the column in the obs attribute of the adata object that will store the g2m phase score. required: false default: "G2M_score" + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/feature_annotation/score_genes_scanpy/config.vsh.yaml b/src/feature_annotation/score_genes_scanpy/config.vsh.yaml index 11513d831ab..d1b9b846ff4 100644 --- a/src/feature_annotation/score_genes_scanpy/config.vsh.yaml +++ b/src/feature_annotation/score_genes_scanpy/config.vsh.yaml @@ -86,12 +86,8 @@ argument_groups: required: false description: | Name of the score field to be added in .obs. - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: Arguments arguments: diff --git a/src/filter/delimit_fraction/config.vsh.yaml b/src/filter/delimit_fraction/config.vsh.yaml index e179f40a97d..61a661c677e 100644 --- a/src/filter/delimit_fraction/config.vsh.yaml +++ b/src/filter/delimit_fraction/config.vsh.yaml @@ -42,17 +42,11 @@ argument_groups: direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--obs_name_filter" type: string required: true description: In which .obs slot to store a boolean array corresponding to which observations should be removed. + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/filter/do_filter/config.vsh.yaml b/src/filter/do_filter/config.vsh.yaml index 128c34b12ab..c00db5dcbd9 100644 --- a/src/filter/do_filter/config.vsh.yaml +++ b/src/filter/do_filter/config.vsh.yaml @@ -37,13 +37,7 @@ arguments: description: Output h5mu file. direction: output example: output.h5mu - - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/filter/filter_with_counts/config.vsh.yaml b/src/filter/filter_with_counts/config.vsh.yaml index f652c797d6b..2ecb04408ed 100644 --- a/src/filter/filter_with_counts/config.vsh.yaml +++ b/src/filter/filter_with_counts/config.vsh.yaml @@ -36,12 +36,6 @@ argument_groups: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--do_subset" type: boolean_true description: Whether to subset before storing the output. @@ -54,7 +48,7 @@ argument_groups: type: string default: "filter_with_counts" description: In which .var slot to store a boolean array corresponding to which variables should be removed. - + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/filter/filter_with_scrublet/config.vsh.yaml b/src/filter/filter_with_scrublet/config.vsh.yaml index 1be7a74a2fa..f7257800359 100644 --- a/src/filter/filter_with_scrublet/config.vsh.yaml +++ b/src/filter/filter_with_scrublet/config.vsh.yaml @@ -52,13 +52,6 @@ arguments: direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--obs_name_filter" type: string default: "filter_with_scrublet" @@ -132,6 +125,8 @@ arguments: description: | When scrublet fails to automatically determine the double score threshold, allow the component to continue and set the output columns to NA. +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/filter/intersect_obs/config.vsh.yaml b/src/filter/intersect_obs/config.vsh.yaml index 98bde5dbb3a..6e99109bbd5 100644 --- a/src/filter/intersect_obs/config.vsh.yaml +++ b/src/filter/intersect_obs/config.vsh.yaml @@ -31,12 +31,8 @@ arguments: direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script diff --git a/src/filter/remove_modality/config.vsh.yaml b/src/filter/remove_modality/config.vsh.yaml index 93f39bc0b2d..42a5f4e339e 100644 --- a/src/filter/remove_modality/config.vsh.yaml +++ b/src/filter/remove_modality/config.vsh.yaml @@ -21,12 +21,8 @@ arguments: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/filter/subset_h5mu/config.vsh.yaml b/src/filter/subset_h5mu/config.vsh.yaml index e1f7a1c31e8..11f7473d91a 100644 --- a/src/filter/subset_h5mu/config.vsh.yaml +++ b/src/filter/subset_h5mu/config.vsh.yaml @@ -21,16 +21,12 @@ arguments: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--number_of_observations" type: integer description: Number of observations to be selected from the h5mu file. example: 5 +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/filter/subset_obsp/config.vsh.yaml b/src/filter/subset_obsp/config.vsh.yaml index d96300be295..2eb2c272bde 100644 --- a/src/filter/subset_obsp/config.vsh.yaml +++ b/src/filter/subset_obsp/config.vsh.yaml @@ -41,12 +41,7 @@ argument_groups: type: string required: true description: The .obsm key to store the subset in. - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/integrate/harmony/config.vsh.yaml b/src/integrate/harmony/config.vsh.yaml index 85972f7ca78..5a848ab0d17 100644 --- a/src/integrate/harmony/config.vsh.yaml +++ b/src/integrate/harmony/config.vsh.yaml @@ -20,12 +20,6 @@ arguments: description: Output h5mu file. direction: output required: true - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--modality" type: string default: "rna" @@ -50,6 +44,7 @@ arguments: description: "The .obs field(s) that define the covariate(s) to regress out." example: ["batch", "sample"] multiple: true +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: r_script path: script.R diff --git a/src/integrate/harmonypy/config.vsh.yaml b/src/integrate/harmonypy/config.vsh.yaml index 2dbd7479f56..78eee42b131 100644 --- a/src/integrate/harmonypy/config.vsh.yaml +++ b/src/integrate/harmonypy/config.vsh.yaml @@ -20,12 +20,6 @@ arguments: description: Output h5mu file. direction: output required: true - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--modality" type: string default: "rna" @@ -51,6 +45,7 @@ arguments: example: ["batch", "sample"] required: true multiple: true +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script path: script.py diff --git a/src/integrate/scanorama/config.vsh.yaml b/src/integrate/scanorama/config.vsh.yaml index 751d4c24f6c..e8c1d990d83 100644 --- a/src/integrate/scanorama/config.vsh.yaml +++ b/src/integrate/scanorama/config.vsh.yaml @@ -25,12 +25,6 @@ arguments: direction: output required: true default: "output.h5ad" - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--obs_batch" type: string description: Column name discriminating between your batches. @@ -63,6 +57,7 @@ arguments: type: double description: "Alignment score minimum cutoff" default: 0.1 +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script path: script.py diff --git a/src/integrate/scarches/config.vsh.yaml b/src/integrate/scarches/config.vsh.yaml index 3fb02b2c76a..1460ef2847b 100644 --- a/src/integrate/scarches/config.vsh.yaml +++ b/src/integrate/scarches/config.vsh.yaml @@ -60,12 +60,6 @@ argument_groups: description: Output h5mu file. direction: output required: true - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--model_output" type: file default: "model" @@ -86,6 +80,7 @@ argument_groups: default: "scanvi_proba" required: false description: "In which .obs slot to store the probabilities of the label predictions. Only relevant if a scANVI model was provided." + __merge__: [., /src/base/h5_compression_argument.yaml] - name: "Early stopping arguments" arguments: diff --git a/src/integrate/scvi/config.vsh.yaml b/src/integrate/scvi/config.vsh.yaml index 11629a17948..7bd5ffa0ec5 100644 --- a/src/integrate/scvi/config.vsh.yaml +++ b/src/integrate/scvi/config.vsh.yaml @@ -83,17 +83,13 @@ argument_groups: description: Folder where the state of the trained model will be saved to. required: false direction: output - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--obsm_output" type: string default: "X_scvi_integrated" required: false description: "In which .obsm slot to store the resulting integrated embedding." + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: "SCVI options" arguments: - name: --n_hidden_nodes diff --git a/src/interpret/lianapy/config.vsh.yaml b/src/interpret/lianapy/config.vsh.yaml index f6c37ca7dc8..352b02a5c35 100644 --- a/src/interpret/lianapy/config.vsh.yaml +++ b/src/interpret/lianapy/config.vsh.yaml @@ -19,11 +19,6 @@ arguments: description: Output h5mu file. direction: output required: true - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - default: "gzip" - required: false - name: "--modality" type: string default: "rna" @@ -73,6 +68,7 @@ arguments: default: 100 required: false description: "Number of permutations for the permutation test. Note that this is relevant only for permutation-based methods - e.g. 'CellPhoneDB" +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script path: script.py diff --git a/src/labels_transfer/api/common_arguments.yaml b/src/labels_transfer/api/common_arguments.yaml index 5f9514ca099..57b728eb653 100644 --- a/src/labels_transfer/api/common_arguments.yaml +++ b/src/labels_transfer/api/common_arguments.yaml @@ -142,10 +142,5 @@ In which `.obs` slots to store the probability of the predictions. If provided, must have the same length as `--reference_obs_targets`. If empty, will default to the `reference_obs_targets` combined with the `"_probability"` suffix. - - name: "--output_compression" - type: string - description: | - The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + diff --git a/src/mapping/htseq_count_to_h5mu/config.vsh.yaml b/src/mapping/htseq_count_to_h5mu/config.vsh.yaml index cabb1803d85..4a731c7c5a1 100644 --- a/src/mapping/htseq_count_to_h5mu/config.vsh.yaml +++ b/src/mapping/htseq_count_to_h5mu/config.vsh.yaml @@ -36,12 +36,8 @@ argument_groups: description: "Output h5mu file." required: true example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/mapping/multi_star_to_h5mu/config.vsh.yaml b/src/mapping/multi_star_to_h5mu/config.vsh.yaml index 721539e7cdb..1b84d6170a5 100644 --- a/src/mapping/multi_star_to_h5mu/config.vsh.yaml +++ b/src/mapping/multi_star_to_h5mu/config.vsh.yaml @@ -20,12 +20,8 @@ arguments: description: "Output h5mu file." required: true example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/metadata/add_id/config.vsh.yaml b/src/metadata/add_id/config.vsh.yaml index dabfe60abff..6c99bbd929e 100644 --- a/src/metadata/add_id/config.vsh.yaml +++ b/src/metadata/add_id/config.vsh.yaml @@ -27,15 +27,11 @@ arguments: type: file direction: output example: "output.h5mu" - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--make_observation_keys_unique" type: boolean_true description: Join the id to the .obs index (.obs_names). +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/metadata/grep_annotation_column/config.vsh.yaml b/src/metadata/grep_annotation_column/config.vsh.yaml index 2b76d00cc94..38d0c368796 100644 --- a/src/metadata/grep_annotation_column/config.vsh.yaml +++ b/src/metadata/grep_annotation_column/config.vsh.yaml @@ -45,12 +45,6 @@ argument_groups: type: file direction: output example: "output.h5mu" - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_match_column" type: string required: true @@ -61,6 +55,8 @@ argument_groups: description: | For the opposite axis, name of the column to write the fraction of observations that matches to the pattern. + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: Query options description: Options related to the query arguments: diff --git a/src/metadata/move_obsm_to_obs/config.vsh.yaml b/src/metadata/move_obsm_to_obs/config.vsh.yaml index d6096593b97..6ebf61fec02 100644 --- a/src/metadata/move_obsm_to_obs/config.vsh.yaml +++ b/src/metadata/move_obsm_to_obs/config.vsh.yaml @@ -34,12 +34,7 @@ argument_groups: direction: output required: true example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script path: script.py diff --git a/src/neighbors/bbknn/config.vsh.yaml b/src/neighbors/bbknn/config.vsh.yaml index 70bb085dc5f..d2fa1f618db 100644 --- a/src/neighbors/bbknn/config.vsh.yaml +++ b/src/neighbors/bbknn/config.vsh.yaml @@ -37,13 +37,6 @@ arguments: required: true example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--uns_output" type: string default: neighbors @@ -71,6 +64,8 @@ arguments: - name: "--n_trim" type: integer description: Trim the neighbours of each cell to these many top connectivities. May help with population independence and improve the tidiness of clustering. The lower the value the more independent the individual populations, at the cost of more conserved batch effect. If `None` (default), sets the parameter value automatically to 10 times `neighbors_within_batch` times the number of batches. Set to 0 to skip. +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/neighbors/find_neighbors/config.vsh.yaml b/src/neighbors/find_neighbors/config.vsh.yaml index 6272b10f413..004fa4bc746 100644 --- a/src/neighbors/find_neighbors/config.vsh.yaml +++ b/src/neighbors/find_neighbors/config.vsh.yaml @@ -37,13 +37,6 @@ arguments: description: Output h5mu file containing the found neighbors. direction: output example: output.h5mu - - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--uns_output" type: string @@ -76,6 +69,7 @@ arguments: type: integer default: 0 description: A random seed. +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/qc/calculate_atac_qc_metrics/config.vsh.yaml b/src/qc/calculate_atac_qc_metrics/config.vsh.yaml index 07d901923d5..6ed683e0436 100644 --- a/src/qc/calculate_atac_qc_metrics/config.vsh.yaml +++ b/src/qc/calculate_atac_qc_metrics/config.vsh.yaml @@ -78,12 +78,8 @@ argument_groups: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/qc/calculate_qc_metrics/config.vsh.yaml b/src/qc/calculate_qc_metrics/config.vsh.yaml index 95a82e8356b..27659f42a6d 100644 --- a/src/qc/calculate_qc_metrics/config.vsh.yaml +++ b/src/qc/calculate_qc_metrics/config.vsh.yaml @@ -114,12 +114,8 @@ argument_groups: description: Output h5mu file. direction: output example: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/query/cellxgene_census/config.vsh.yaml b/src/query/cellxgene_census/config.vsh.yaml index e49cd9a060f..01e295d2b49 100644 --- a/src/query/cellxgene_census/config.vsh.yaml +++ b/src/query/cellxgene_census/config.vsh.yaml @@ -103,11 +103,6 @@ argument_groups: The format of this file is derived from the [CELLxGENE schema v4.0.0](https://github.com/chanzuckerberg/single-cell-curation/blob/main/schema/4.0.0/schema.md). slots: __merge__: file_output_slots.yaml - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_modality" description: "Which modality to store the output in." type: string @@ -117,6 +112,8 @@ argument_groups: description: "Which layer to store the raw counts in. If not provided, the .X layer will be used." type: string required: false + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/scgpt/binning/config.vsh.yaml b/src/scgpt/binning/config.vsh.yaml index 0c19e935ea1..8f6189f562c 100644 --- a/src/scgpt/binning/config.vsh.yaml +++ b/src/scgpt/binning/config.vsh.yaml @@ -51,13 +51,6 @@ argument_groups: required: true description: | The output h5mu file containing the binned data. - - name: "--output_compression" - type: string - example: "gzip" - required: false - choices: ["gzip", "lzf"] - description: | - The compression algorithm to use for the output h5mu file. - name: "--output_obsm_binned_counts" type: string default: "binned_counts" @@ -67,6 +60,8 @@ argument_groups: type: integer description: | Seed for random number generation. + __merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script diff --git a/src/scgpt/cell_type_annotation/config.vsh.yaml b/src/scgpt/cell_type_annotation/config.vsh.yaml index 715c3056acf..0a23f777fe0 100644 --- a/src/scgpt/cell_type_annotation/config.vsh.yaml +++ b/src/scgpt/cell_type_annotation/config.vsh.yaml @@ -78,13 +78,6 @@ argument_groups: example: output.h5mu description: | The output mudata file. - - name: "--output_compression" - type: string - example: "gzip" - required: false - default: gzip - description: | - The compression algorithm to use for the output h5mu file. - name: "--output_obs_predictions" type: string default: "scgpt_pred" @@ -97,6 +90,7 @@ argument_groups: required: false description: | The name of the adata.obs column to write the probabilities of the predicted cell type labels to. + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/scgpt/cross_check_genes/config.vsh.yaml b/src/scgpt/cross_check_genes/config.vsh.yaml index 7ce8bd55de6..2250e4a3214 100644 --- a/src/scgpt/cross_check_genes/config.vsh.yaml +++ b/src/scgpt/cross_check_genes/config.vsh.yaml @@ -55,15 +55,11 @@ argument_groups: example: output.h5mu description: | The output cross-checked anndata file. - - name: "--output_compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--output_var_filter" type: string default: "id_in_vocab" description: In which .var slot to store a boolean array corresponding to which observations should be filtered out based on HVG and model vocabulary. + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/scgpt/embedding/config.vsh.yaml b/src/scgpt/embedding/config.vsh.yaml index 66a2b0e0ac8..2e2623d5bbb 100644 --- a/src/scgpt/embedding/config.vsh.yaml +++ b/src/scgpt/embedding/config.vsh.yaml @@ -84,19 +84,12 @@ argument_groups: Path to output anndata file containing pre-processed data as well as scGPT embeddings. direction: output example: output.h5mu - - name: "--output_compression" - type: string - example: "gzip" - required: false - choices: ["gzip", "lzf"] - description: | - The compression algorithm to use for the output h5mu file. - name: "--obsm_embeddings" type: string default: "X_scGPT" description: | The name of the adata.obsm array to which scGPT embeddings will be written. - + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: - name: "--pad_token" diff --git a/src/scgpt/pad_tokenize/config.vsh.yaml b/src/scgpt/pad_tokenize/config.vsh.yaml index aa10bb01c13..031cb7d7284 100644 --- a/src/scgpt/pad_tokenize/config.vsh.yaml +++ b/src/scgpt/pad_tokenize/config.vsh.yaml @@ -57,12 +57,6 @@ argument_groups: The output h5mu file containing obsm arrays for gene tokens, tokenized data and padding mask. direction: output example: output.h5mu - - name: "--output_compression" - type: string - example: "gzip" - choices: ["gzip", "lzf"] - description: | - The compression type for the output file. - name: "--obsm_gene_tokens" type: string default: "gene_id_tokens" @@ -79,6 +73,7 @@ argument_groups: default: padding_mask description: | The key of the .obsm array containing the padding mask. + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/transform/bpcells_regress_out/config.vsh.yaml b/src/transform/bpcells_regress_out/config.vsh.yaml index e7f013941b3..65becb43db0 100644 --- a/src/transform/bpcells_regress_out/config.vsh.yaml +++ b/src/transform/bpcells_regress_out/config.vsh.yaml @@ -23,12 +23,6 @@ arguments: direction: output required: true default: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--modality" type: string description: "The modality to run this component on." @@ -51,7 +45,7 @@ arguments: description: | The layer of the adata object containing the regressed count data. If not provided, the X attribute of the adata object will be used. - +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: r_script path: script.R diff --git a/src/transform/clr/config.vsh.yaml b/src/transform/clr/config.vsh.yaml index f36ef8efab5..4f3f1ae6b43 100644 --- a/src/transform/clr/config.vsh.yaml +++ b/src/transform/clr/config.vsh.yaml @@ -24,12 +24,6 @@ arguments: direction: output required: true default: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--input_layer" type: string description: "Input layer to use. By default, .X is used." @@ -45,6 +39,8 @@ arguments: default: 0 required: false choices: [0, 1] +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/transform/delete_layer/config.vsh.yaml b/src/transform/delete_layer/config.vsh.yaml index 16f5bc6ae05..8ed18989f43 100644 --- a/src/transform/delete_layer/config.vsh.yaml +++ b/src/transform/delete_layer/config.vsh.yaml @@ -29,15 +29,11 @@ arguments: direction: output required: true default: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--missing_ok" type: boolean_true description: Do not raise an error if the layer does not exist for all modalities. +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/transform/log1p/config.vsh.yaml b/src/transform/log1p/config.vsh.yaml index c8ec38eec70..431df95a10a 100644 --- a/src/transform/log1p/config.vsh.yaml +++ b/src/transform/log1p/config.vsh.yaml @@ -41,17 +41,13 @@ arguments: required: true default: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - # arguments - name: "--base" type: double example: 2 + +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/transform/move_layer/config.vsh.yaml b/src/transform/move_layer/config.vsh.yaml index 804ed5f7e5d..a5a2ba0802a 100644 --- a/src/transform/move_layer/config.vsh.yaml +++ b/src/transform/move_layer/config.vsh.yaml @@ -26,12 +26,9 @@ arguments: - name: "--output_layer" type: string required: false - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" +__merge__: [., /src/base/h5_compression_argument.yaml] + + resources: - type: python_script path: script.py diff --git a/src/transform/normalize_total/config.vsh.yaml b/src/transform/normalize_total/config.vsh.yaml index e217e773288..14bdef92bb0 100644 --- a/src/transform/normalize_total/config.vsh.yaml +++ b/src/transform/normalize_total/config.vsh.yaml @@ -39,13 +39,6 @@ arguments: required: true default: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--output_layer" type: string description: Output layer to use. By default, use X. @@ -59,6 +52,7 @@ arguments: - name: "--exclude_highly_expressed" type: boolean_true description: Exclude (very) highly expressed genes for the computation of the normalization factor (size factor) for each cell. A gene is considered highly expressed, if it has more than max_fraction of the total counts in at least one cell. The not-excluded genes will sum up to target_sum. +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script path: script.py diff --git a/src/transform/regress_out/config.vsh.yaml b/src/transform/regress_out/config.vsh.yaml index 71a514e646d..f6fa2eff515 100644 --- a/src/transform/regress_out/config.vsh.yaml +++ b/src/transform/regress_out/config.vsh.yaml @@ -22,12 +22,6 @@ arguments: direction: output required: true default: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--modality" type: string description: "Which modality (one or more) to run this component on." @@ -50,6 +44,8 @@ arguments: description: | The layer of the adata object containing the regressed count data. If not provided, the X attribute of the adata object will be used. +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/transform/scale/config.vsh.yaml b/src/transform/scale/config.vsh.yaml index be9f7d8974f..4e80bc666fd 100644 --- a/src/transform/scale/config.vsh.yaml +++ b/src/transform/scale/config.vsh.yaml @@ -41,12 +41,9 @@ arguments: direction: output required: true default: output.h5mu - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" +__merge__: [., /src/base/h5_compression_argument.yaml] + + resources: - type: python_script path: script.py diff --git a/src/transform/tfidf/config.vsh.yaml b/src/transform/tfidf/config.vsh.yaml index af5b2fc1c9a..912b52eb5e3 100644 --- a/src/transform/tfidf/config.vsh.yaml +++ b/src/transform/tfidf/config.vsh.yaml @@ -38,13 +38,6 @@ arguments: direction: output required: true - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - - name: "--output_layer" type: string description: Output layer to use. @@ -73,6 +66,8 @@ arguments: type: boolean default: false +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/velocity/scvelo/config.vsh.yaml b/src/velocity/scvelo/config.vsh.yaml index 0b9c32ebab2..72082117e88 100644 --- a/src/velocity/scvelo/config.vsh.yaml +++ b/src/velocity/scvelo/config.vsh.yaml @@ -43,12 +43,8 @@ argument_groups: type: file direction: output description: "Output mudata file." - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] + - name: "Filtering and normalization" description: Arguments for filtering, normalization an log transform (see scvelo.pp.filter_and_normalize function) arguments: diff --git a/src/velocity/velocyto_to_h5mu/config.vsh.yaml b/src/velocity/velocyto_to_h5mu/config.vsh.yaml index 23dc0a31be0..3ab3247223f 100644 --- a/src/velocity/velocyto_to_h5mu/config.vsh.yaml +++ b/src/velocity/velocyto_to_h5mu/config.vsh.yaml @@ -35,12 +35,6 @@ argument_groups: description: Path to the output MuData file. example: output.h5mu direction: output - - name: "--output_compression" - type: string - description: The compression format to be used on the output h5mu object. - choices: ["gzip", "lzf"] - required: false - example: "gzip" - name: "--layer_spliced" type: string description: Output layer for the spliced reads. @@ -53,6 +47,7 @@ argument_groups: type: string description: Output layer for the ambiguous reads. default: velo_ambiguous + __merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script path: script.py From b62bc9847df33c9f552ba75a8a63061f1021e86e Mon Sep 17 00:00:00 2001 From: Dries Schaumont <5946712+DriesSchaumont@users.noreply.github.com> Date: Fri, 2 May 2025 09:34:45 +0000 Subject: [PATCH 2/8] Fix some indentations --- src/cluster/leiden/config.vsh.yaml | 2 +- src/convert/from_10xh5_to_h5mu/config.vsh.yaml | 2 +- src/convert/from_10xmtx_to_h5mu/config.vsh.yaml | 2 +- src/convert/from_bdrhap_to_h5mu/config.vsh.yaml | 2 +- src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml | 2 +- src/convert/from_h5mu_to_h5ad/config.vsh.yaml | 2 +- 6 files changed, 6 insertions(+), 6 deletions(-) diff --git a/src/cluster/leiden/config.vsh.yaml b/src/cluster/leiden/config.vsh.yaml index 2661399387b..8084a43feff 100644 --- a/src/cluster/leiden/config.vsh.yaml +++ b/src/cluster/leiden/config.vsh.yaml @@ -47,7 +47,7 @@ arguments: Name of the .obsm key under which to add the cluster labels. The name of the columns in the matrix will correspond to the resolutions. default: "leiden" - __merge__: [., /src/base/h5_compression_argument.yaml] +__merge__: [., /src/base/h5_compression_argument.yaml] # todo: add uns_params # example: uns["leiden"] = {'params': {'n_iterations': -1, 'random_state': 0, 'resolution': 1.0}} diff --git a/src/convert/from_10xh5_to_h5mu/config.vsh.yaml b/src/convert/from_10xh5_to_h5mu/config.vsh.yaml index 908535a1d03..e323e90304b 100644 --- a/src/convert/from_10xh5_to_h5mu/config.vsh.yaml +++ b/src/convert/from_10xh5_to_h5mu/config.vsh.yaml @@ -32,7 +32,7 @@ argument_groups: type: string description: Name of the .uns slot under which to QC metrics (if any). default: "metrics_cellranger" - __merge__: [., /src/base/h5_compression_argument.yaml] +__merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/convert/from_10xmtx_to_h5mu/config.vsh.yaml b/src/convert/from_10xmtx_to_h5mu/config.vsh.yaml index 15156317fcb..ff1c7e6092c 100644 --- a/src/convert/from_10xmtx_to_h5mu/config.vsh.yaml +++ b/src/convert/from_10xmtx_to_h5mu/config.vsh.yaml @@ -19,7 +19,7 @@ arguments: description: Output h5mu file. example: output.h5mu direction: output - __merge__: [., /src/base/h5_compression_argument.yaml] +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/convert/from_bdrhap_to_h5mu/config.vsh.yaml b/src/convert/from_bdrhap_to_h5mu/config.vsh.yaml index 7098a8fc6e0..5082822338c 100644 --- a/src/convert/from_bdrhap_to_h5mu/config.vsh.yaml +++ b/src/convert/from_bdrhap_to_h5mu/config.vsh.yaml @@ -30,7 +30,7 @@ argument_groups: description: "Output h5mu file." required: true example: output.h5mu - __merge__: [., /src/base/h5_compression_argument.yaml] +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml b/src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml index 8cce946a607..7d25ceb7920 100644 --- a/src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml +++ b/src/convert/from_cellranger_multi_to_h5mu/config.vsh.yaml @@ -45,7 +45,7 @@ arguments: type: string description: Name of the .uns slot under which to QC metrics (if any). default: "metrics_cellranger" - __merge__: [., /src/base/h5_compression_argument.yaml] +__merge__: [., /src/base/h5_compression_argument.yaml] resources: - type: python_script diff --git a/src/convert/from_h5mu_to_h5ad/config.vsh.yaml b/src/convert/from_h5mu_to_h5ad/config.vsh.yaml index 585f9a7e778..111d9af4d30 100644 --- a/src/convert/from_h5mu_to_h5ad/config.vsh.yaml +++ b/src/convert/from_h5mu_to_h5ad/config.vsh.yaml @@ -23,7 +23,7 @@ arguments: description: Output AnnData file. default: output.h5ad direction: output - __merge__: [., /src/base/h5_compression_argument.yaml] +__merge__: [., /src/base/h5_compression_argument.yaml] resources: From 84f47061df402d362051fb03afe34dfa0c198555 Mon Sep 17 00:00:00 2001 From: Dries Schaumont <5946712+DriesSchaumont@users.noreply.github.com> Date: Fri, 2 May 2025 09:40:48 +0000 Subject: [PATCH 3/8] Fix some more config --- src/cluster/leiden/config.vsh.yaml | 3 ++- src/convert/from_10xh5_to_h5mu/config.vsh.yaml | 2 +- src/convert/from_h5ad_to_h5mu/config.vsh.yaml | 2 +- 3 files changed, 4 insertions(+), 3 deletions(-) diff --git a/src/cluster/leiden/config.vsh.yaml b/src/cluster/leiden/config.vsh.yaml index 8084a43feff..36fa0ec5725 100644 --- a/src/cluster/leiden/config.vsh.yaml +++ b/src/cluster/leiden/config.vsh.yaml @@ -47,7 +47,6 @@ arguments: Name of the .obsm key under which to add the cluster labels. The name of the columns in the matrix will correspond to the resolutions. default: "leiden" -__merge__: [., /src/base/h5_compression_argument.yaml] # todo: add uns_params # example: uns["leiden"] = {'params': {'n_iterations': -1, 'random_state': 0, 'resolution': 1.0}} @@ -61,6 +60,8 @@ __merge__: [., /src/base/h5_compression_argument.yaml] default: [1] required: true multiple: true +__merge__: [., /src/base/h5_compression_argument.yaml] + resources: - type: python_script path: script.py diff --git a/src/convert/from_10xh5_to_h5mu/config.vsh.yaml b/src/convert/from_10xh5_to_h5mu/config.vsh.yaml index e323e90304b..f286133eb73 100644 --- a/src/convert/from_10xh5_to_h5mu/config.vsh.yaml +++ b/src/convert/from_10xh5_to_h5mu/config.vsh.yaml @@ -32,7 +32,7 @@ argument_groups: type: string description: Name of the .uns slot under which to QC metrics (if any). default: "metrics_cellranger" -__merge__: [., /src/base/h5_compression_argument.yaml] + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Arguments arguments: diff --git a/src/convert/from_h5ad_to_h5mu/config.vsh.yaml b/src/convert/from_h5ad_to_h5mu/config.vsh.yaml index d7c8db648f5..1a40dda84c8 100644 --- a/src/convert/from_h5ad_to_h5mu/config.vsh.yaml +++ b/src/convert/from_h5ad_to_h5mu/config.vsh.yaml @@ -25,7 +25,7 @@ arguments: description: Output MuData file. default: output.h5mu direction: output - __merge__: [., /src/base/h5_compression_argument.yaml] +__merge__: [., /src/base/h5_compression_argument.yaml] resources: From 401fce032b32d6848cb24964376f3b24452696b8 Mon Sep 17 00:00:00 2001 From: Dries Schaumont <5946712+DriesSchaumont@users.noreply.github.com> Date: Fri, 2 May 2025 12:57:03 +0000 Subject: [PATCH 4/8] Change split_h5mu_train_test --- src/dataflow/split_h5mu_train_test/config.vsh.yaml | 6 +----- src/dataflow/split_h5mu_train_test/script.py | 8 ++++---- 2 files changed, 5 insertions(+), 9 deletions(-) diff --git a/src/dataflow/split_h5mu_train_test/config.vsh.yaml b/src/dataflow/split_h5mu_train_test/config.vsh.yaml index 17d4c45a2e9..42084c061d9 100644 --- a/src/dataflow/split_h5mu_train_test/config.vsh.yaml +++ b/src/dataflow/split_h5mu_train_test/config.vsh.yaml @@ -41,11 +41,7 @@ argument_groups: direction: output required: false example: output_val.h5mu - - name: "--compression" - type: string - choices: ["gzip", "lzf"] - required: false - example: "gzip" + __merge__: [., /src/base/h5_compression_argument.yaml] - name: Split arguments description: Model arguments. arguments: diff --git a/src/dataflow/split_h5mu_train_test/script.py b/src/dataflow/split_h5mu_train_test/script.py index 551311824b7..24c9d5ae2f3 100644 --- a/src/dataflow/split_h5mu_train_test/script.py +++ b/src/dataflow/split_h5mu_train_test/script.py @@ -12,7 +12,7 @@ "output_train": "train.h5mu", "output_val": "val.h5mu", "output_test": "test.h5mu", - "compression": "gzip", + "output_compression": "gzip", "shuffle": True, } ### VIASH END @@ -60,7 +60,7 @@ def main(): val_mudata = mu.MuData({par["modality"]: val_modality}) test_mudata = mu.MuData({par["modality"]: test_modality}) - val_mudata.write_h5mu(par["output_val"], compression=par["compression"]) + val_mudata.write_h5mu(par["output_val"], compression=par["output_compression"]) else: train_modality = input_modality[train_idx].copy() @@ -69,8 +69,8 @@ def main(): train_mudata = mu.MuData({par["modality"]: train_modality}) test_mudata = mu.MuData({par["modality"]: test_modality}) - train_mudata.write_h5mu(par["output_train"], compression=par["compression"]) - test_mudata.write_h5mu(par["output_test"], compression=par["compression"]) + train_mudata.write_h5mu(par["output_train"], compression=par["output_compression"]) + test_mudata.write_h5mu(par["output_test"], compression=par["output_compression"]) if __name__ == "__main__": From 505f9a6903b0735065558d339e43126f459a1f08 Mon Sep 17 00:00:00 2001 From: Dries Schaumont <5946712+DriesSchaumont@users.noreply.github.com> Date: Fri, 2 May 2025 13:16:28 +0000 Subject: [PATCH 5/8] Add CHANGELOG entry --- CHANGELOG.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/CHANGELOG.md b/CHANGELOG.md index 8b75055cd93..95302192290 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,9 @@ # openpipelines 3.0.0 +## BREAKING CHANGES + +* `split_h5mu_train_test`: rename `compression` argument to `output_compression` (PR #1017) + ## MAJOR CHANGES * `mapping/cellranger_*`: Upgrade CellRanger to v9.0 (PR #992 and #1006). From ab95c48a3944324157c2420f57ee497413d462fa Mon Sep 17 00:00:00 2001 From: Dries Schaumont <5946712+DriesSchaumont@users.noreply.github.com> Date: Fri, 2 May 2025 13:33:57 +0000 Subject: [PATCH 6/8] Add some missing descriptions --- CHANGELOG.md | 2 ++ src/annotate/scanvi/config.vsh.yaml | 2 ++ src/annotate/svm_annotation/config.vsh.yaml | 3 +++ src/cluster/leiden/config.vsh.yaml | 2 ++ src/compression/compress_h5mu/config.vsh.yaml | 7 +------ src/convert/from_h5ad_to_h5mu/config.vsh.yaml | 3 +++ src/convert/from_h5mu_to_h5ad/config.vsh.yaml | 2 ++ .../config.vsh.yaml | 2 ++ src/dataflow/concatenate_h5mu/config.vsh.yaml | 2 ++ src/dataflow/split_h5mu/config.vsh.yaml | 2 ++ src/demux/bcl2fastq/config.vsh.yaml | 3 +++ src/dimred/densmap/config.vsh.yaml | 2 ++ src/dimred/pca/config.vsh.yaml | 2 ++ src/dimred/tsne/config.vsh.yaml | 2 ++ src/dimred/umap/config.vsh.yaml | 2 ++ .../config.vsh.yaml | 2 ++ .../config.vsh.yaml | 2 ++ .../score_genes_scanpy/config.vsh.yaml | 2 ++ src/filter/delimit_fraction/config.vsh.yaml | 7 ++----- src/filter/do_filter/config.vsh.yaml | 2 ++ src/filter/filter_with_counts/config.vsh.yaml | 6 ++++++ src/filter/filter_with_scrublet/config.vsh.yaml | 2 ++ src/filter/intersect_obs/config.vsh.yaml | 2 ++ src/filter/remove_modality/config.vsh.yaml | 2 ++ src/filter/subset_h5mu/config.vsh.yaml | 2 ++ src/filter/subset_obsp/config.vsh.yaml | 2 ++ src/integrate/harmonypy/config.vsh.yaml | 2 ++ src/integrate/scanorama/config.vsh.yaml | 2 ++ src/integrate/scarches/config.vsh.yaml | 2 ++ src/integrate/scvi/config.vsh.yaml | 2 ++ src/interpret/lianapy/config.vsh.yaml | 2 ++ src/mapping/bd_rhapsody/config.vsh.yaml | 2 ++ .../cellranger_count_split/config.vsh.yaml | 17 ++++++++++++----- src/metadata/add_id/config.vsh.yaml | 2 ++ .../grep_annotation_column/config.vsh.yaml | 2 ++ src/metadata/join_csv/config.vsh.yml | 2 ++ src/metadata/join_uns_to_obs/config.vsh.yml | 4 ++++ src/metadata/move_obsm_to_obs/config.vsh.yaml | 2 ++ src/neighbors/bbknn/config.vsh.yaml | 2 ++ src/neighbors/find_neighbors/config.vsh.yaml | 2 ++ .../calculate_atac_qc_metrics/config.vsh.yaml | 2 ++ src/qc/calculate_qc_metrics/config.vsh.yaml | 4 ++++ src/scgpt/binning/config.vsh.yaml | 2 ++ src/scgpt/cell_type_annotation/config.vsh.yaml | 2 ++ src/scgpt/embedding/config.vsh.yaml | 3 +++ src/scgpt/pad_tokenize/config.vsh.yaml | 2 ++ src/transform/clr/config.vsh.yaml | 2 ++ src/transform/delete_layer/config.vsh.yaml | 2 ++ src/transform/log1p/config.vsh.yaml | 4 ++++ src/transform/move_layer/config.vsh.yaml | 8 ++++++++ src/transform/normalize_total/config.vsh.yaml | 2 ++ src/transform/tfidf/config.vsh.yaml | 2 ++ src/velocity/scvelo/config.vsh.yaml | 9 +++++++++ .../annotation/scgpt_annotation/config.vsh.yaml | 2 ++ .../integration/scgpt_leiden/config.vsh.yaml | 2 ++ .../multiomics/split_h5mu/config.vsh.yaml | 2 ++ 56 files changed, 148 insertions(+), 16 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 95302192290..dc30bd95f9e 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,6 +4,8 @@ * `split_h5mu_train_test`: rename `compression` argument to `output_compression` (PR #1017) +* `delimit_fraction`: remove unused `layer` argument (PR #) + ## MAJOR CHANGES * `mapping/cellranger_*`: Upgrade CellRanger to v9.0 (PR #992 and #1006). diff --git a/src/annotate/scanvi/config.vsh.yaml b/src/annotate/scanvi/config.vsh.yaml index 27bc8107464..8daa5693e25 100644 --- a/src/annotate/scanvi/config.vsh.yaml +++ b/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 diff --git a/src/annotate/svm_annotation/config.vsh.yaml b/src/annotate/svm_annotation/config.vsh.yaml index e826e586f72..1996bd628b3 100644 --- a/src/annotate/svm_annotation/config.vsh.yaml +++ b/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 diff --git a/src/cluster/leiden/config.vsh.yaml b/src/cluster/leiden/config.vsh.yaml index 36fa0ec5725..99c868a04af 100644 --- a/src/cluster/leiden/config.vsh.yaml +++ b/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 diff --git a/src/compression/compress_h5mu/config.vsh.yaml b/src/compression/compress_h5mu/config.vsh.yaml index de5553f04c4..eeb72165fba 100644 --- a/src/compression/compress_h5mu/config.vsh.yaml +++ b/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 diff --git a/src/convert/from_h5ad_to_h5mu/config.vsh.yaml b/src/convert/from_h5ad_to_h5mu/config.vsh.yaml index 1a40dda84c8..51645f1a77c 100644 --- a/src/convert/from_h5ad_to_h5mu/config.vsh.yaml +++ b/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 diff --git a/src/convert/from_h5mu_to_h5ad/config.vsh.yaml b/src/convert/from_h5mu_to_h5ad/config.vsh.yaml index 111d9af4d30..962f914d964 100644 --- a/src/convert/from_h5mu_to_h5ad/config.vsh.yaml +++ b/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 diff --git a/src/correction/cellbender_remove_background/config.vsh.yaml b/src/correction/cellbender_remove_background/config.vsh.yaml index 3b06f13452a..c354834d01a 100644 --- a/src/correction/cellbender_remove_background/config.vsh.yaml +++ b/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" diff --git a/src/dataflow/concatenate_h5mu/config.vsh.yaml b/src/dataflow/concatenate_h5mu/config.vsh.yaml index 899576a99ea..75756bcd12c 100644 --- a/src/dataflow/concatenate_h5mu/config.vsh.yaml +++ b/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 diff --git a/src/dataflow/split_h5mu/config.vsh.yaml b/src/dataflow/split_h5mu/config.vsh.yaml index 2497ac6579b..b80d01fbfe9 100644 --- a/src/dataflow/split_h5mu/config.vsh.yaml +++ b/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 diff --git a/src/demux/bcl2fastq/config.vsh.yaml b/src/demux/bcl2fastq/config.vsh.yaml index 85524ff99bb..3bce5bf76e5 100644 --- a/src/demux/bcl2fastq/config.vsh.yaml +++ b/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 diff --git a/src/dimred/densmap/config.vsh.yaml b/src/dimred/densmap/config.vsh.yaml index db2f6749215..9f23a22a3f2 100644 --- a/src/dimred/densmap/config.vsh.yaml +++ b/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 diff --git a/src/dimred/pca/config.vsh.yaml b/src/dimred/pca/config.vsh.yaml index b99d4fe4de1..84c4165ba27 100644 --- a/src/dimred/pca/config.vsh.yaml +++ b/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 diff --git a/src/dimred/tsne/config.vsh.yaml b/src/dimred/tsne/config.vsh.yaml index 5a8a0549304..9f3f200179d 100644 --- a/src/dimred/tsne/config.vsh.yaml +++ b/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 diff --git a/src/dimred/umap/config.vsh.yaml b/src/dimred/umap/config.vsh.yaml index 3598d4a84d4..3fe11628342 100644 --- a/src/dimred/umap/config.vsh.yaml +++ b/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 diff --git a/src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml b/src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml index 2408280c141..27c165187f3 100644 --- a/src/feature_annotation/highly_variable_features_scanpy/config.vsh.yaml +++ b/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 diff --git a/src/feature_annotation/score_genes_cell_cycle_scanpy/config.vsh.yaml b/src/feature_annotation/score_genes_cell_cycle_scanpy/config.vsh.yaml index 6412e18f9b9..d84c25cc78b 100644 --- a/src/feature_annotation/score_genes_cell_cycle_scanpy/config.vsh.yaml +++ b/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 diff --git a/src/feature_annotation/score_genes_scanpy/config.vsh.yaml b/src/feature_annotation/score_genes_scanpy/config.vsh.yaml index d1b9b846ff4..108fbf1dfc5 100644 --- a/src/feature_annotation/score_genes_scanpy/config.vsh.yaml +++ b/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 diff --git a/src/filter/delimit_fraction/config.vsh.yaml b/src/filter/delimit_fraction/config.vsh.yaml index 61a661c677e..37fe7adc974 100644 --- a/src/filter/delimit_fraction/config.vsh.yaml +++ b/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 diff --git a/src/filter/do_filter/config.vsh.yaml b/src/filter/do_filter/config.vsh.yaml index c00db5dcbd9..5be48732885 100644 --- a/src/filter/do_filter/config.vsh.yaml +++ b/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 diff --git a/src/filter/filter_with_counts/config.vsh.yaml b/src/filter/filter_with_counts/config.vsh.yaml index 2ecb04408ed..c717481a775 100644 --- a/src/filter/filter_with_counts/config.vsh.yaml +++ b/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 diff --git a/src/filter/filter_with_scrublet/config.vsh.yaml b/src/filter/filter_with_scrublet/config.vsh.yaml index f7257800359..00b96c590a0 100644 --- a/src/filter/filter_with_scrublet/config.vsh.yaml +++ b/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 diff --git a/src/filter/intersect_obs/config.vsh.yaml b/src/filter/intersect_obs/config.vsh.yaml index 6e99109bbd5..43a885707ff 100644 --- a/src/filter/intersect_obs/config.vsh.yaml +++ b/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 diff --git a/src/filter/remove_modality/config.vsh.yaml b/src/filter/remove_modality/config.vsh.yaml index 42a5f4e339e..c3427766fd4 100644 --- a/src/filter/remove_modality/config.vsh.yaml +++ b/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 diff --git a/src/filter/subset_h5mu/config.vsh.yaml b/src/filter/subset_h5mu/config.vsh.yaml index 11f7473d91a..5b84abe6e96 100644 --- a/src/filter/subset_h5mu/config.vsh.yaml +++ b/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 diff --git a/src/filter/subset_obsp/config.vsh.yaml b/src/filter/subset_obsp/config.vsh.yaml index 2eb2c272bde..c2d3ae13cd3 100644 --- a/src/filter/subset_obsp/config.vsh.yaml +++ b/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 diff --git a/src/integrate/harmonypy/config.vsh.yaml b/src/integrate/harmonypy/config.vsh.yaml index 78eee42b131..23e6ea98ffd 100644 --- a/src/integrate/harmonypy/config.vsh.yaml +++ b/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 diff --git a/src/integrate/scanorama/config.vsh.yaml b/src/integrate/scanorama/config.vsh.yaml index e8c1d990d83..54723344c53 100644 --- a/src/integrate/scanorama/config.vsh.yaml +++ b/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 diff --git a/src/integrate/scarches/config.vsh.yaml b/src/integrate/scarches/config.vsh.yaml index 1460ef2847b..46d0c13f2e0 100644 --- a/src/integrate/scarches/config.vsh.yaml +++ b/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 diff --git a/src/integrate/scvi/config.vsh.yaml b/src/integrate/scvi/config.vsh.yaml index 7bd5ffa0ec5..7c5ac391da3 100644 --- a/src/integrate/scvi/config.vsh.yaml +++ b/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 diff --git a/src/interpret/lianapy/config.vsh.yaml b/src/interpret/lianapy/config.vsh.yaml index 352b02a5c35..48907bfdf99 100644 --- a/src/interpret/lianapy/config.vsh.yaml +++ b/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 diff --git a/src/mapping/bd_rhapsody/config.vsh.yaml b/src/mapping/bd_rhapsody/config.vsh.yaml index 62b50b2c8f8..f786a5f727e 100644 --- a/src/mapping/bd_rhapsody/config.vsh.yaml +++ b/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: diff --git a/src/mapping/cellranger_count_split/config.vsh.yaml b/src/mapping/cellranger_count_split/config.vsh.yaml index d0cd23a31e0..2bec7ef1c28 100644 --- a/src/mapping/cellranger_count_split/config.vsh.yaml +++ b/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 diff --git a/src/metadata/add_id/config.vsh.yaml b/src/metadata/add_id/config.vsh.yaml index 6c99bbd929e..f16c33f35dc 100644 --- a/src/metadata/add_id/config.vsh.yaml +++ b/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 diff --git a/src/metadata/grep_annotation_column/config.vsh.yaml b/src/metadata/grep_annotation_column/config.vsh.yaml index 38d0c368796..f9a9c1e7097 100644 --- a/src/metadata/grep_annotation_column/config.vsh.yaml +++ b/src/metadata/grep_annotation_column/config.vsh.yaml @@ -41,6 +41,8 @@ argument_groups: description: Arguments related to how the output will be written. arguments: - name: "--output" + description: | + Location of the output MuData file. alternatives: ["-o"] type: file direction: output diff --git a/src/metadata/join_csv/config.vsh.yml b/src/metadata/join_csv/config.vsh.yml index ae478be0e55..ddd3ef0830e 100644 --- a/src/metadata/join_csv/config.vsh.yml +++ b/src/metadata/join_csv/config.vsh.yml @@ -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 diff --git a/src/metadata/join_uns_to_obs/config.vsh.yml b/src/metadata/join_uns_to_obs/config.vsh.yml index 5c225838fe7..e0c5a68ed51 100644 --- a/src/metadata/join_uns_to_obs/config.vsh.yml +++ b/src/metadata/join_uns_to_obs/config.vsh.yml @@ -10,10 +10,14 @@ arguments: required: true example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false - name: "--uns_key" + description: | + Lookup key from .uns pointing to the input data. type: string required: true - name: "--output" diff --git a/src/metadata/move_obsm_to_obs/config.vsh.yaml b/src/metadata/move_obsm_to_obs/config.vsh.yaml index 6ebf61fec02..dcbe2318712 100644 --- a/src/metadata/move_obsm_to_obs/config.vsh.yaml +++ b/src/metadata/move_obsm_to_obs/config.vsh.yaml @@ -18,6 +18,8 @@ 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 diff --git a/src/neighbors/bbknn/config.vsh.yaml b/src/neighbors/bbknn/config.vsh.yaml index d2fa1f618db..ada23d8158f 100644 --- a/src/neighbors/bbknn/config.vsh.yaml +++ b/src/neighbors/bbknn/config.vsh.yaml @@ -16,6 +16,8 @@ arguments: direction: input required: true - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/neighbors/find_neighbors/config.vsh.yaml b/src/neighbors/find_neighbors/config.vsh.yaml index 004fa4bc746..3e4dfe9fe78 100644 --- a/src/neighbors/find_neighbors/config.vsh.yaml +++ b/src/neighbors/find_neighbors/config.vsh.yaml @@ -20,6 +20,8 @@ arguments: example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/qc/calculate_atac_qc_metrics/config.vsh.yaml b/src/qc/calculate_atac_qc_metrics/config.vsh.yaml index 6ed683e0436..b3b8d645e74 100644 --- a/src/qc/calculate_atac_qc_metrics/config.vsh.yaml +++ b/src/qc/calculate_atac_qc_metrics/config.vsh.yaml @@ -31,6 +31,8 @@ argument_groups: required: false example: fragments.tsv.gz - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "atac" required: false diff --git a/src/qc/calculate_qc_metrics/config.vsh.yaml b/src/qc/calculate_qc_metrics/config.vsh.yaml index 27659f42a6d..8c0ae77c145 100644 --- a/src/qc/calculate_qc_metrics/config.vsh.yaml +++ b/src/qc/calculate_qc_metrics/config.vsh.yaml @@ -32,10 +32,14 @@ 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 - name: "--layer" + description: | + Layer from modality to use as input data. If not provided the .X attribute is used. type: string example: "raw_counts" required: false diff --git a/src/scgpt/binning/config.vsh.yaml b/src/scgpt/binning/config.vsh.yaml index 8f6189f562c..7b6caced379 100644 --- a/src/scgpt/binning/config.vsh.yaml +++ b/src/scgpt/binning/config.vsh.yaml @@ -21,6 +21,8 @@ argument_groups: description: | Input h5mu file. - name: "--modality" + description: + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/scgpt/cell_type_annotation/config.vsh.yaml b/src/scgpt/cell_type_annotation/config.vsh.yaml index 0a23f777fe0..07806b36abd 100644 --- a/src/scgpt/cell_type_annotation/config.vsh.yaml +++ b/src/scgpt/cell_type_annotation/config.vsh.yaml @@ -50,6 +50,8 @@ argument_groups: description: | The input h5mu file containing of data that have been pre-processed (normalized, binned, genes cross-checked and tokenized). - name: "--modality" + description: + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/scgpt/embedding/config.vsh.yaml b/src/scgpt/embedding/config.vsh.yaml index 2e2623d5bbb..20d214b7983 100644 --- a/src/scgpt/embedding/config.vsh.yaml +++ b/src/scgpt/embedding/config.vsh.yaml @@ -20,6 +20,9 @@ argument_groups: description: | The input h5mu file containing tokenized gene and count data. - name: "--modality" + description: | + Which modality from the input MuData file to process. + type: string default: "rna" required: false diff --git a/src/scgpt/pad_tokenize/config.vsh.yaml b/src/scgpt/pad_tokenize/config.vsh.yaml index 031cb7d7284..6a5498f3980 100644 --- a/src/scgpt/pad_tokenize/config.vsh.yaml +++ b/src/scgpt/pad_tokenize/config.vsh.yaml @@ -21,6 +21,8 @@ argument_groups: description: | The input h5mu file of pre-processed data. - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/transform/clr/config.vsh.yaml b/src/transform/clr/config.vsh.yaml index 4f3f1ae6b43..e2aac00da13 100644 --- a/src/transform/clr/config.vsh.yaml +++ b/src/transform/clr/config.vsh.yaml @@ -14,6 +14,8 @@ arguments: required: true example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "prot" required: false diff --git a/src/transform/delete_layer/config.vsh.yaml b/src/transform/delete_layer/config.vsh.yaml index 8ed18989f43..cb932d81b8c 100644 --- a/src/transform/delete_layer/config.vsh.yaml +++ b/src/transform/delete_layer/config.vsh.yaml @@ -14,6 +14,8 @@ arguments: required: true example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/transform/log1p/config.vsh.yaml b/src/transform/log1p/config.vsh.yaml index 431df95a10a..329fc3b9956 100644 --- a/src/transform/log1p/config.vsh.yaml +++ b/src/transform/log1p/config.vsh.yaml @@ -18,6 +18,8 @@ arguments: example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false @@ -43,6 +45,8 @@ arguments: # arguments - name: "--base" + description: | + Base of the logarithm. Natural logarithm is used by default. type: double example: 2 diff --git a/src/transform/move_layer/config.vsh.yaml b/src/transform/move_layer/config.vsh.yaml index a5a2ba0802a..e39e437c984 100644 --- a/src/transform/move_layer/config.vsh.yaml +++ b/src/transform/move_layer/config.vsh.yaml @@ -10,10 +10,15 @@ arguments: required: true example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false - name: "--input_layer" + description: | + Input layer to move to a new output location. If specified, will be used to select a key from .layers, + otherwise .X is used. type: string required: false - name: "--output" @@ -24,6 +29,9 @@ arguments: required: true example: output.h5mu - name: "--output_layer" + description: | + Destination location for the layer. If not provided, .X will be used, + Otherwise, will be the key for the .layers attribute in the output MuData file. type: string required: false __merge__: [., /src/base/h5_compression_argument.yaml] diff --git a/src/transform/normalize_total/config.vsh.yaml b/src/transform/normalize_total/config.vsh.yaml index 14bdef92bb0..f5e47ec8ce2 100644 --- a/src/transform/normalize_total/config.vsh.yaml +++ b/src/transform/normalize_total/config.vsh.yaml @@ -22,6 +22,8 @@ arguments: example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/transform/tfidf/config.vsh.yaml b/src/transform/tfidf/config.vsh.yaml index 912b52eb5e3..17b29567cc6 100644 --- a/src/transform/tfidf/config.vsh.yaml +++ b/src/transform/tfidf/config.vsh.yaml @@ -21,6 +21,8 @@ arguments: example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "atac" required: false diff --git a/src/velocity/scvelo/config.vsh.yaml b/src/velocity/scvelo/config.vsh.yaml index 72082117e88..5672d325fbc 100644 --- a/src/velocity/scvelo/config.vsh.yaml +++ b/src/velocity/scvelo/config.vsh.yaml @@ -20,14 +20,23 @@ argument_groups: required: true type: string - name: "--layer_spliced" + description: | + Name of the layer to store the spliced abundances in. Will be used as key in the .layer attribute of the + output MuData object. type: string required: false default: "spliced" - name: "--layer_unspliced" + description: | + Name of the layer to store the unspliced abundances in. + Will be used as key in the .layer attribute of the output MuData object. type: string required: false default: "unspliced" - name: "--layer_ambiguous" + description: | + Name of the layer to store the abundances in for which no fate was determined. + Will be used as key in the .layer attribute of the output MuData object. type: string required: false default: "ambiguous" diff --git a/src/workflows/annotation/scgpt_annotation/config.vsh.yaml b/src/workflows/annotation/scgpt_annotation/config.vsh.yaml index 3868cf27d0b..66edf03cb35 100644 --- a/src/workflows/annotation/scgpt_annotation/config.vsh.yaml +++ b/src/workflows/annotation/scgpt_annotation/config.vsh.yaml @@ -37,6 +37,8 @@ argument_groups: description: Path to the input file. example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/workflows/integration/scgpt_leiden/config.vsh.yaml b/src/workflows/integration/scgpt_leiden/config.vsh.yaml index 9fdb5bd6210..b136846bf41 100644 --- a/src/workflows/integration/scgpt_leiden/config.vsh.yaml +++ b/src/workflows/integration/scgpt_leiden/config.vsh.yaml @@ -24,6 +24,8 @@ argument_groups: description: Path to the input file. example: input.h5mu - name: "--modality" + description: | + Which modality from the input MuData file to process. type: string default: "rna" required: false diff --git a/src/workflows/multiomics/split_h5mu/config.vsh.yaml b/src/workflows/multiomics/split_h5mu/config.vsh.yaml index 42038adc699..c79ad081ef2 100644 --- a/src/workflows/multiomics/split_h5mu/config.vsh.yaml +++ b/src/workflows/multiomics/split_h5mu/config.vsh.yaml @@ -16,6 +16,8 @@ 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 From 461898e8b1d78972bf63a41ffe0a9862ce418954 Mon Sep 17 00:00:00 2001 From: Dries Schaumont <5946712+DriesSchaumont@users.noreply.github.com> Date: Fri, 2 May 2025 20:03:45 +0000 Subject: [PATCH 7/8] Add CHANGELOG entry for compress_h5mu; fix tests --- CHANGELOG.md | 4 ++-- src/compression/compress_h5mu/run_test.py | 2 +- src/compression/compress_h5mu/script.py | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index dc30bd95f9e..f6a22174445 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -2,9 +2,9 @@ ## BREAKING CHANGES -* `split_h5mu_train_test`: rename `compression` argument to `output_compression` (PR #1017) +* `split_h5mu_train_test` and `compress_h5mu`: rename `compression` argument to `output_compression` (PR #1017, PR #1018) -* `delimit_fraction`: remove unused `layer` argument (PR #) +* `delimit_fraction`: remove unused `layer` argument (PR #1018) ## MAJOR CHANGES diff --git a/src/compression/compress_h5mu/run_test.py b/src/compression/compress_h5mu/run_test.py index 09f864130c9..b89ce9afdb2 100644 --- a/src/compression/compress_h5mu/run_test.py +++ b/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, ] ) diff --git a/src/compression/compress_h5mu/script.py b/src/compression/compress_h5mu/script.py index 7e6292d9e78..d65408be9e4 100644 --- a/src/compression/compress_h5mu/script.py +++ b/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"]) From 14b5baf3129191e5808154cacedf33172492d627 Mon Sep 17 00:00:00 2001 From: Robrecht Cannoodt Date: Fri, 16 May 2025 09:18:46 +0200 Subject: [PATCH 8/8] add entry to changelog --- CHANGELOG.md | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/CHANGELOG.md b/CHANGELOG.md index 30bc2523cb2..b8908e2f198 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,9 +4,9 @@ * Removed `split_h5mu_train_test` component (PR #1020). -* `compress_h5mu`: rename `compression` argument to `output_compression` (PR #1017, PR #1018) +* `compress_h5mu`: rename `compression` argument to `output_compression` (PR #1017, PR #1018). -* `delimit_fraction`: remove unused `layer` argument (PR #1018) +* `delimit_fraction`: remove unused `layer` argument (PR #1018). ## MAJOR CHANGES @@ -18,6 +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).