diff --git a/CHANGELOG.md b/CHANGELOG.md index ce0719c..45bab6b 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -6,6 +6,10 @@ * MAJOR CHANGE: Raw scRNA-seq datasets must have CELLxGENE-style ontology term ids for the assay, cell type, developmental stage, disease, self-reported ethnicity, sex and tissue. The multimodal loaders use a new `file_multimodal_raw` spec, in which these stay optional. +* BUG FIX: The loaders store `uns['dataset_reference']` and `uns['dataset_organism']` as lists, as declared in `src/api`, since a dataset can have several references and organisms. The OP3 loader takes both as arguments instead of hardcoding them. + +* BUG FIX: `uns['pca_variance']` is declared as an `object` in `file_pca`, since `processors/pca` writes a dict. + * MINOR CHANGE: The OP3 loader adds these ontology term ids, based on its cell type annotation and the donor metadata in GEO. * MINOR CHANGE: Component tests use the `cxg_mouse_pancreas_atlas` test resources instead of the deprecated `pancreas` ones. Its notebook now keeps every processing step. diff --git a/scripts/create_resources/openproblems_v1_multimodal.sh b/scripts/create_resources/openproblems_v1_multimodal.sh index b62ac1f..ff1db40 100755 --- a/scripts/create_resources/openproblems_v1_multimodal.sh +++ b/scripts/create_resources/openproblems_v1_multimodal.sh @@ -33,7 +33,7 @@ param_list: dataset_description: "Single cell RNA-seq and ATAC-seq co-profiling for HEK293T cells, NIH/3T3 cells, A549 cells across three treatment conditions (DEX 0 hour, 1 hour and 3 hour treatment)." dataset_reference: cao2018joint dataset_url: https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE117089 - dataset_organism: "[homo_sapiens, mus_musculus]" + dataset_organism: [homo_sapiens, mus_musculus] obs_cell_type: cell_name layer_counts: counts var_feature_id: index diff --git a/scripts/create_test_resources/scicar_cell_lines.ipynb b/scripts/create_test_resources/scicar_cell_lines.ipynb index 79a1fd9..46efe43 100644 --- a/scripts/create_test_resources/scicar_cell_lines.ipynb +++ b/scripts/create_test_resources/scicar_cell_lines.ipynb @@ -66,7 +66,7 @@ " \"dataset_reference\": \"cao2018joint\",\n", " \"dataset_summary\": \"sciCAR is a combinatorial indexing-based assay that jointly measures cellular transcriptomes and the accessibility of cellular chromatin in the same cells\",\n", " \"dataset_description\": \"sciCAR is a combinatorial indexing-based assay that jointly measures cellular transcriptomes and the accessibility of cellular chromatin in the same cells. Here, we use two sciCAR datasets that were obtained from the same study. The first dataset contains 4,825 cells from three cell lines (HEK293T cells, NIH/3T3 cells, and A549 cells) at multiple timepoints (0, 1 hour, 3 hours) after dexamethasone treatment. The second dataset contains 11,233 cells from wild-type adult mouse kidney.\",\n", - " \"dataset_organism\": \"[homo_sapiens, mus_musculus]\",\n", + " \"dataset_organism\": [\"homo_sapiens\", \"mus_musculus\"],\n", " \"mod1\": \"GEX\",\n", " \"mod2\": \"ATAC\",\n", " \"do_subsample\": True,\n", diff --git a/src/api/file_pca.yaml b/src/api/file_pca.yaml index 28f3c13..a5758d7 100644 --- a/src/api/file_pca.yaml +++ b/src/api/file_pca.yaml @@ -17,7 +17,7 @@ info: description: The PCA loadings matrix. required: true uns: - - type: double + - type: object name: pca_variance description: The PCA variance objects. required: true diff --git a/src/loaders/multimodal/openproblems_neurips2021_bmmc/config.vsh.yaml b/src/loaders/multimodal/openproblems_neurips2021_bmmc/config.vsh.yaml index 95fa0ee..ce0f3ff 100644 --- a/src/loaders/multimodal/openproblems_neurips2021_bmmc/config.vsh.yaml +++ b/src/loaders/multimodal/openproblems_neurips2021_bmmc/config.vsh.yaml @@ -35,6 +35,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -47,6 +48,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Outputs diff --git a/src/loaders/multimodal/openproblems_neurips2021_bmmc/test.py b/src/loaders/multimodal/openproblems_neurips2021_bmmc/test.py index 1908782..6c1ca65 100644 --- a/src/loaders/multimodal/openproblems_neurips2021_bmmc/test.py +++ b/src/loaders/multimodal/openproblems_neurips2021_bmmc/test.py @@ -76,7 +76,7 @@ assert "batch" in output_mod1.obs.columns, "batch column not found in mod 1 output obs" assert output_mod1.uns["dataset_name"] == "BMMC (Multiome)", "Expected: Pancreas as value for dataset_name in mod 1 output uns" assert output_mod1.uns["dataset_url"] == "http://foo.org", "Expected: http://foo.org as value for dataset_url in mod 1 output uns" -assert output_mod1.uns["dataset_reference"] == "foo2000bar", "Expected: foo2000bar as value for dataset_reference in mod 1 output uns" +assert list(output_mod1.uns["dataset_reference"]) == ["foo2000bar"], "Expected: foo2000bar as value for dataset_reference in mod 1 output uns" assert output_mod1.uns["dataset_summary"] == "A short summary.", "Expected: A short summary. as value for dataset_summary in mod 1 output uns" assert output_mod1.uns["dataset_description"] == "A couple of paragraphs worth of text.", "Expected: A couple of paragraphs worth of text. as value for dataset_description in mod 1 output uns" @@ -88,6 +88,6 @@ assert "batch" in output_mod2.obs.columns, "batch column not found in mod 2 output obs" assert output_mod2.uns["dataset_name"] == "BMMC (Multiome)", "Expected: Pancreas as value for dataset_name in mod 2 output uns" assert output_mod2.uns["dataset_url"] == "http://foo.org", "Expected: http://foo.org as value for dataset_url in mod 2 output uns" -assert output_mod2.uns["dataset_reference"] == "foo2000bar", "Expected: foo2000bar as value for dataset_reference in mod 2 output uns" +assert list(output_mod2.uns["dataset_reference"]) == ["foo2000bar"], "Expected: foo2000bar as value for dataset_reference in mod 2 output uns" assert output_mod2.uns["dataset_summary"] == "A short summary.", "Expected: A short summary. as value for dataset_summary in mod 2 output uns" assert output_mod2.uns["dataset_description"] == "A couple of paragraphs worth of text.", "Expected: A couple of paragraphs worth of text. as value for dataset_description in mod 2 output uns" \ No newline at end of file diff --git a/src/loaders/multimodal/openproblems_neurips2022_pbmc/config.vsh.yaml b/src/loaders/multimodal/openproblems_neurips2022_pbmc/config.vsh.yaml index 4efa609..89270d0 100644 --- a/src/loaders/multimodal/openproblems_neurips2022_pbmc/config.vsh.yaml +++ b/src/loaders/multimodal/openproblems_neurips2022_pbmc/config.vsh.yaml @@ -40,6 +40,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -52,6 +53,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Outputs diff --git a/src/loaders/multimodal/openproblems_neurips2022_pbmc/test.py b/src/loaders/multimodal/openproblems_neurips2022_pbmc/test.py index d470c59..b3c2926 100644 --- a/src/loaders/multimodal/openproblems_neurips2022_pbmc/test.py +++ b/src/loaders/multimodal/openproblems_neurips2022_pbmc/test.py @@ -83,7 +83,7 @@ assert "batch" in output_mod1.obs.columns, "batch column not found in mod 1 output obs" assert output_mod1.uns["dataset_name"] == "Kaggle22 PBMC (CITE-seq)", "Expected: Kaggle22 PBMC (CITE-seq) as value for dataset_name in mod 1 output uns" assert output_mod1.uns["dataset_url"] == "https://www.kaggle.com/competitions/open-problems-multimodal/data", "Expected: https://www.kaggle.com/competitions/open-problems-multimodal/data as value for dataset_url in mod 1 output uns" -assert output_mod1.uns["dataset_reference"] == "Neurips22", "Expected: Neurips22 as value for dataset_reference in mod 1 output uns" +assert list(output_mod1.uns["dataset_reference"]) == ["Neurips22"], "Expected: Neurips22 as value for dataset_reference in mod 1 output uns" assert output_mod1.uns["dataset_summary"] == "Neurips22 competition dataset", "Expected: Neurips22 competition dataset as value for dataset_summary in mod 1 output uns" assert output_mod1.uns["dataset_description"] == "The dataset for this competition comprises single-cell multiomics data collected from mobilized peripheral CD34+ hematopoietic stem and progenitor cells (HSPCs) isolated from four healthy human donors.", "Expected: The dataset for this competition comprises single-cell multiomics data collected from mobilized peripheral CD34+ hematopoietic stem and progenitor cells (HSPCs) isolated from four healthy human donors. as value for dataset_description in mod 1 output uns" @@ -95,6 +95,6 @@ assert "batch" in output_mod2.obs.columns, "batch column not found in mod 2 output obs" assert output_mod2.uns["dataset_name"] == "Kaggle22 PBMC (CITE-seq)", "Expected: Kaggle22 PBMC (CITE-seq) as value for dataset_name in mod 2 output uns" assert output_mod2.uns["dataset_url"] == "https://www.kaggle.com/competitions/open-problems-multimodal/data", "Expected: https://www.kaggle.com/competitions/open-problems-multimodal/data as value for dataset_url in mod 2 output uns" -assert output_mod2.uns["dataset_reference"] == "Neurips22", "Expected: Neurips22 as value for dataset_reference in mod 2 output uns" +assert list(output_mod2.uns["dataset_reference"]) == ["Neurips22"], "Expected: Neurips22 as value for dataset_reference in mod 2 output uns" assert output_mod2.uns["dataset_summary"] == "Neurips22 competition dataset", "Expected: Neurips22 competition dataset as value for dataset_summary in mod 2 output uns" assert output_mod2.uns["dataset_description"] == "The dataset for this competition comprises single-cell multiomics data collected from mobilized peripheral CD34+ hematopoietic stem and progenitor cells (HSPCs) isolated from four healthy human donors.", "Expected: The dataset for this competition comprises single-cell multiomics data collected from mobilized peripheral CD34+ hematopoietic stem and progenitor cells (HSPCs) isolated from four healthy human donors. as value for dataset_description in mod 2 output uns" \ No newline at end of file diff --git a/src/loaders/multimodal/openproblems_v1_multimodal/config.vsh.yaml b/src/loaders/multimodal/openproblems_v1_multimodal/config.vsh.yaml index 7baaed0..f647308 100644 --- a/src/loaders/multimodal/openproblems_v1_multimodal/config.vsh.yaml +++ b/src/loaders/multimodal/openproblems_v1_multimodal/config.vsh.yaml @@ -50,6 +50,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -62,6 +63,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Outputs diff --git a/src/loaders/multimodal/openproblems_v1_multimodal/script.py b/src/loaders/multimodal/openproblems_v1_multimodal/script.py index d21b34e..0015f1b 100644 --- a/src/loaders/multimodal/openproblems_v1_multimodal/script.py +++ b/src/loaders/multimodal/openproblems_v1_multimodal/script.py @@ -17,7 +17,7 @@ "dataset_reference": "reference", "dataset_summary": "summary", "dataset_description": "description", - "dataset_organism": "[homo_sapiens, mus_musculus]", + "dataset_organism": ["homo_sapiens", "mus_musculus"], } meta = { "resources_dir": "src/loaders/openproblems_v1/" diff --git a/src/loaders/multimodal/openproblems_v1_multimodal/test.py b/src/loaders/multimodal/openproblems_v1_multimodal/test.py index cfcb966..2570201 100644 --- a/src/loaders/multimodal/openproblems_v1_multimodal/test.py +++ b/src/loaders/multimodal/openproblems_v1_multimodal/test.py @@ -62,7 +62,7 @@ assert output_mod1.uns["dataset_id"] == dataset_id, f"Expected: {dataset_id} as value for dataset_id in mod 1 output uns" assert output_mod1.uns["dataset_name"] == "Pancreas", "Expected: Pancreas as value for dataset_name in mod 1 output uns" assert output_mod1.uns["dataset_url"] == "http://foo.org", "Expected: http://foo.org as value for dataset_url in mod 1 output uns" -assert output_mod1.uns["dataset_reference"] == "foo2000bar", "Expected: foo2000bar as value for dataset_reference in mod 1 output uns" +assert list(output_mod1.uns["dataset_reference"]) == ["foo2000bar"], "Expected: foo2000bar as value for dataset_reference in mod 1 output uns" assert output_mod1.uns["dataset_summary"] == "A short summary.", "Expected: A short summary. as value for dataset_summary in mod 1 output uns" assert output_mod1.uns["dataset_description"] == "A couple of paragraphs worth of text.", "Expected: A couple of paragraphs worth of text. as value for dataset_description in mod 1 output uns" @@ -78,7 +78,7 @@ assert output_mod2.uns["dataset_id"] == dataset_id, f"Expected: {dataset_id} as value for dataset_id in mod 2 output uns" assert output_mod2.uns["dataset_name"] == "Pancreas", "Expected: Pancreas as value for dataset_name in mod 2 output uns" assert output_mod2.uns["dataset_url"] == "http://foo.org", "Expected: http://foo.org as value for dataset_url in mod 2 output uns" -assert output_mod2.uns["dataset_reference"] == "foo2000bar", "Expected: foo2000bar as value for dataset_reference in mod 2 output uns" +assert list(output_mod2.uns["dataset_reference"]) == ["foo2000bar"], "Expected: foo2000bar as value for dataset_reference in mod 2 output uns" assert output_mod2.uns["dataset_summary"] == "A short summary.", "Expected: A short summary. as value for dataset_summary in mod 2 output uns" assert output_mod2.uns["dataset_description"] == "A couple of paragraphs worth of text.", "Expected: A couple of paragraphs worth of text. as value for dataset_description in mod 2 output uns" diff --git a/src/loaders/scrnaseq/cellxgene_census/config.vsh.yaml b/src/loaders/scrnaseq/cellxgene_census/config.vsh.yaml index 719870b..3a49142 100644 --- a/src/loaders/scrnaseq/cellxgene_census/config.vsh.yaml +++ b/src/loaders/scrnaseq/cellxgene_census/config.vsh.yaml @@ -120,6 +120,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -132,6 +133,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: true resources: diff --git a/src/loaders/scrnaseq/cellxgene_census/test.py b/src/loaders/scrnaseq/cellxgene_census/test.py index 385d9e7..10af062 100644 --- a/src/loaders/scrnaseq/cellxgene_census/test.py +++ b/src/loaders/scrnaseq/cellxgene_census/test.py @@ -51,10 +51,10 @@ def test_cellxgene_extract_metadata_expression(run_component, tmp_path): assert adata.uns["dataset_id"] == "test_dataset_id", "Incorrect .uns['dataset_id']" assert adata.uns["dataset_name"] == "test_dataset_name", "Incorrect .uns['dataset_name']" assert adata.uns["dataset_url"] == "https://test_dataset_url.com", "Incorrect .uns['dataset_url']" - assert adata.uns["dataset_reference"] == "test_dataset_reference", "Incorrect .uns['dataset_reference']" + assert list(adata.uns["dataset_reference"]) == ["test_dataset_reference"], "Incorrect .uns['dataset_reference']" assert adata.uns["dataset_summary"] == "test_dataset_summary", "Incorrect .uns['dataset_summary']" assert adata.uns["dataset_description"] == "test_dataset_description", "Incorrect .uns['dataset_description']" - assert adata.uns["dataset_organism"] == "test_homo_sapiens", "Incorrect .uns['dataset_organism']" + assert list(adata.uns["dataset_organism"]) == ["test_homo_sapiens"], "Incorrect .uns['dataset_organism']" if __name__ == '__main__': diff --git a/src/loaders/scrnaseq/cellxgene_census_from_source_h5ad/config.vsh.yaml b/src/loaders/scrnaseq/cellxgene_census_from_source_h5ad/config.vsh.yaml index b723d9f..8d7b13f 100644 --- a/src/loaders/scrnaseq/cellxgene_census_from_source_h5ad/config.vsh.yaml +++ b/src/loaders/scrnaseq/cellxgene_census_from_source_h5ad/config.vsh.yaml @@ -77,6 +77,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -89,6 +90,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: true resources: diff --git a/src/loaders/scrnaseq/cellxgene_census_from_source_h5ad/test.py b/src/loaders/scrnaseq/cellxgene_census_from_source_h5ad/test.py index f79d513..120c7e2 100644 --- a/src/loaders/scrnaseq/cellxgene_census_from_source_h5ad/test.py +++ b/src/loaders/scrnaseq/cellxgene_census_from_source_h5ad/test.py @@ -48,10 +48,10 @@ def test_cellxgene_extract_metadata_expression(run_component, tmp_path): assert adata.uns["dataset_id"] == "test_dataset_id", "Incorrect .uns['dataset_id']" assert adata.uns["dataset_name"] == "test_dataset_name", "Incorrect .uns['dataset_name']" assert adata.uns["dataset_url"] == "https://test_dataset_url.com", "Incorrect .uns['dataset_url']" - assert adata.uns["dataset_reference"] == "test_dataset_reference", "Incorrect .uns['dataset_reference']" + assert list(adata.uns["dataset_reference"]) == ["test_dataset_reference"], "Incorrect .uns['dataset_reference']" assert adata.uns["dataset_summary"] == "test_dataset_summary", "Incorrect .uns['dataset_summary']" assert adata.uns["dataset_description"] == "test_dataset_description", "Incorrect .uns['dataset_description']" - assert adata.uns["dataset_organism"] == "test_homo_sapiens", "Incorrect .uns['dataset_organism']" + assert list(adata.uns["dataset_organism"]) == ["test_homo_sapiens"], "Incorrect .uns['dataset_organism']" if __name__ == '__main__': diff --git a/src/loaders/scrnaseq/openproblems_op3/config.vsh.yaml b/src/loaders/scrnaseq/openproblems_op3/config.vsh.yaml index 9b68d6a..844b2f3 100644 --- a/src/loaders/scrnaseq/openproblems_op3/config.vsh.yaml +++ b/src/loaders/scrnaseq/openproblems_op3/config.vsh.yaml @@ -53,11 +53,18 @@ argument_groups: type: string description: "Detailed description of the dataset" default: "The OP3 dataset is to-date the largest single-cell small molecule perturbation dataset in primary tissue with multiple donor replicates." - - name: "dataset_reference" + - name: "--dataset_reference" type: string + multiple: true description: "Bibtex reference of the paper in which the dataset was published." required: false - default: GSE279945 + default: [GSE279945] + - name: "--dataset_organism" + type: string + multiple: true + description: "The organism of the dataset." + required: false + default: [homo_sapiens] - name: "--dataset_url" type: string description: "Link to the original source of the dataset." diff --git a/src/loaders/scrnaseq/openproblems_op3/script.py b/src/loaders/scrnaseq/openproblems_op3/script.py index 3775e96..eb4c77a 100644 --- a/src/loaders/scrnaseq/openproblems_op3/script.py +++ b/src/loaders/scrnaseq/openproblems_op3/script.py @@ -17,6 +17,8 @@ "dataset_name": "OP3: single-cell multimodal dataset in PBMCs for perturbation prediction benchmarking", "dataset_summary": "The Open Problems Perurbation Prediction (OP3) dataset with small molecule perturbations in PBMCs", "dataset_description": "The OP3 dataset is to-date the largest single-cell small molecule perturbation dataset in primary tissue with multiple donor replicates.", + "dataset_reference": ["GSE279945"], + "dataset_organism": ["homo_sapiens"], "output": "output.zarr", } meta = {} @@ -151,9 +153,9 @@ def add_metadata_to_uns(adata, par): adata.uns['dataset_name'] = par["dataset_name"] adata.uns['dataset_summary'] = par["dataset_summary"] adata.uns['dataset_description'] = par["dataset_description"] - adata.uns['dataset_organism'] = 'Homo sapiens' + adata.uns['dataset_organism'] = par["dataset_organism"] adata.uns['dataset_url'] = par["dataset_url"] - adata.uns['dataset_reference'] = 'GSE279945' + adata.uns['dataset_reference'] = par["dataset_reference"] adata.uns['dataset_version'] = '1.0.0' adata.uns['processing_status'] = 'processed' diff --git a/src/loaders/scrnaseq/openproblems_v1/config.vsh.yaml b/src/loaders/scrnaseq/openproblems_v1/config.vsh.yaml index 00a5514..c321499 100644 --- a/src/loaders/scrnaseq/openproblems_v1/config.vsh.yaml +++ b/src/loaders/scrnaseq/openproblems_v1/config.vsh.yaml @@ -54,6 +54,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -66,6 +67,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false resources: diff --git a/src/loaders/spatial/tenx_visium/config.vsh.yaml b/src/loaders/spatial/tenx_visium/config.vsh.yaml index 5aedee0..2047027 100644 --- a/src/loaders/spatial/tenx_visium/config.vsh.yaml +++ b/src/loaders/spatial/tenx_visium/config.vsh.yaml @@ -37,6 +37,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -49,6 +50,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Gene or spot filtering diff --git a/src/loaders/spatial/tenx_visium/test.py b/src/loaders/spatial/tenx_visium/test.py index 0aba760..3aae130 100644 --- a/src/loaders/spatial/tenx_visium/test.py +++ b/src/loaders/spatial/tenx_visium/test.py @@ -51,7 +51,7 @@ assert adata.uns["dataset_name"] == dataset_name, f"Expected {dataset_name} as value" assert adata.uns["dataset_url"] == dataset_url, f"Expected {dataset_url} as value" assert adata.uns["dataset_summary"] == dataset_summary, f"Expected {dataset_summary} as value" -assert adata.uns["dataset_organism"] == dataset_organism, f"Expected {dataset_organism} as value" +assert list(adata.uns["dataset_organism"]) == [dataset_organism], f"Expected {dataset_organism} as value" assert 'spatial' in adata.obsm, "Spatial spot coordinates not found in .obsm" print(">> All tests passed successfully", flush=True) diff --git a/src/loaders/spatial/zenodo/config.vsh.yaml b/src/loaders/spatial/zenodo/config.vsh.yaml index 9a0faea..941f46f 100644 --- a/src/loaders/spatial/zenodo/config.vsh.yaml +++ b/src/loaders/spatial/zenodo/config.vsh.yaml @@ -33,6 +33,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -45,6 +46,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Gene or spot filtering diff --git a/src/loaders/spatial/zenodo/test.py b/src/loaders/spatial/zenodo/test.py index 71c1cc2..9e5abe4 100644 --- a/src/loaders/spatial/zenodo/test.py +++ b/src/loaders/spatial/zenodo/test.py @@ -49,7 +49,7 @@ assert adata.uns["dataset_name"] == dataset_name, f"Expected {dataset_name} as value" assert adata.uns["dataset_url"] == dataset_url, f"Expected {dataset_url} as value" assert adata.uns["dataset_summary"] == dataset_summary, f"Expected {dataset_summary} as value" -assert adata.uns["dataset_organism"] == dataset_organism, f"Expected {dataset_organism} as value" +assert list(adata.uns["dataset_organism"]) == [dataset_organism], f"Expected {dataset_organism} as value" assert 'spatial' in adata.obsm, "Spatial spot coordinates not found in .obsm" print(">> All tests passed successfully", flush=True) diff --git a/src/loaders/spatial/zenodo_slidetags/config.vsh.yaml b/src/loaders/spatial/zenodo_slidetags/config.vsh.yaml index 22ab1bd..e8e8e00 100644 --- a/src/loaders/spatial/zenodo_slidetags/config.vsh.yaml +++ b/src/loaders/spatial/zenodo_slidetags/config.vsh.yaml @@ -33,6 +33,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -45,6 +46,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Gene or spot filtering diff --git a/src/loaders/spatial/zenodo_slidetags/test.py b/src/loaders/spatial/zenodo_slidetags/test.py index 794239a..a1f250c 100644 --- a/src/loaders/spatial/zenodo_slidetags/test.py +++ b/src/loaders/spatial/zenodo_slidetags/test.py @@ -49,7 +49,7 @@ assert adata.uns["dataset_name"] == dataset_name, f"Expected {dataset_name} as value" assert adata.uns["dataset_url"] == dataset_url, f"Expected {dataset_url} as value" assert adata.uns["dataset_summary"] == dataset_summary, f"Expected {dataset_summary} as value" -assert adata.uns["dataset_organism"] == dataset_organism, f"Expected {dataset_organism} as value" +assert list(adata.uns["dataset_organism"]) == [dataset_organism], f"Expected {dataset_organism} as value" assert 'spatial' in adata.obsm, "Spatial spot coordinates not found in .obsm" print(">> All tests passed successfully", flush=True) diff --git a/src/workflows/multimodal/process_openproblems_neurips2021_bmmc/config.vsh.yaml b/src/workflows/multimodal/process_openproblems_neurips2021_bmmc/config.vsh.yaml index 5b89da3..aeb4814 100644 --- a/src/workflows/multimodal/process_openproblems_neurips2021_bmmc/config.vsh.yaml +++ b/src/workflows/multimodal/process_openproblems_neurips2021_bmmc/config.vsh.yaml @@ -35,6 +35,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -47,6 +48,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Sampling options diff --git a/src/workflows/multimodal/process_openproblems_neurips2022_pbmc/config.vsh.yaml b/src/workflows/multimodal/process_openproblems_neurips2022_pbmc/config.vsh.yaml index deb3000..13a22b2 100644 --- a/src/workflows/multimodal/process_openproblems_neurips2022_pbmc/config.vsh.yaml +++ b/src/workflows/multimodal/process_openproblems_neurips2022_pbmc/config.vsh.yaml @@ -41,6 +41,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -53,6 +54,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Sampling options diff --git a/src/workflows/multimodal/process_openproblems_v1_multimodal/config.vsh.yaml b/src/workflows/multimodal/process_openproblems_v1_multimodal/config.vsh.yaml index 05b8bf5..033607f 100644 --- a/src/workflows/multimodal/process_openproblems_v1_multimodal/config.vsh.yaml +++ b/src/workflows/multimodal/process_openproblems_v1_multimodal/config.vsh.yaml @@ -64,6 +64,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -76,6 +77,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Sampling options diff --git a/src/workflows/scrnaseq/process_cellxgene_census/config.vsh.yaml b/src/workflows/scrnaseq/process_cellxgene_census/config.vsh.yaml index 124c725..07d837a 100644 --- a/src/workflows/scrnaseq/process_cellxgene_census/config.vsh.yaml +++ b/src/workflows/scrnaseq/process_cellxgene_census/config.vsh.yaml @@ -94,6 +94,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -106,6 +107,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: true - name: Sampling options diff --git a/src/workflows/scrnaseq/process_openproblems_op3/config.vsh.yaml b/src/workflows/scrnaseq/process_openproblems_op3/config.vsh.yaml index 8d9610c..680db61 100644 --- a/src/workflows/scrnaseq/process_openproblems_op3/config.vsh.yaml +++ b/src/workflows/scrnaseq/process_openproblems_op3/config.vsh.yaml @@ -50,6 +50,7 @@ argument_groups: default: https://ftp.ncbi.nlm.nih.gov/geo/series/GSE279nnn/GSE279945/suppl/GSE279945_sc_counts_processed.h5ad - name: --dataset_reference type: string + multiple: true description: "Bibtex reference of the paper in which the dataset was published." required: false default: GSE279945 diff --git a/src/workflows/scrnaseq/process_openproblems_v1/config.vsh.yaml b/src/workflows/scrnaseq/process_openproblems_v1/config.vsh.yaml index ae3bcf2..a371652 100644 --- a/src/workflows/scrnaseq/process_openproblems_v1/config.vsh.yaml +++ b/src/workflows/scrnaseq/process_openproblems_v1/config.vsh.yaml @@ -54,6 +54,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -66,6 +67,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Sampling options diff --git a/src/workflows/spatial/process_tenx_visium/config.vsh.yaml b/src/workflows/spatial/process_tenx_visium/config.vsh.yaml index 802ba4f..12d4645 100644 --- a/src/workflows/spatial/process_tenx_visium/config.vsh.yaml +++ b/src/workflows/spatial/process_tenx_visium/config.vsh.yaml @@ -37,6 +37,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -49,6 +50,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Gene or spot filtering diff --git a/src/workflows/spatial/process_zenodo/config.vsh.yaml b/src/workflows/spatial/process_zenodo/config.vsh.yaml index 4ddd194..30e2efa 100644 --- a/src/workflows/spatial/process_zenodo/config.vsh.yaml +++ b/src/workflows/spatial/process_zenodo/config.vsh.yaml @@ -33,6 +33,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -45,6 +46,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Gene or spot filtering diff --git a/src/workflows/spatial/process_zenodo_slidetags/config.vsh.yaml b/src/workflows/spatial/process_zenodo_slidetags/config.vsh.yaml index 341a03b..664e706 100644 --- a/src/workflows/spatial/process_zenodo_slidetags/config.vsh.yaml +++ b/src/workflows/spatial/process_zenodo_slidetags/config.vsh.yaml @@ -33,6 +33,7 @@ argument_groups: required: false - name: --dataset_reference type: string + multiple: true description: Bibtex reference of the paper in which the dataset was published. required: false - name: --dataset_summary @@ -45,6 +46,7 @@ argument_groups: required: true - name: --dataset_organism type: string + multiple: true description: The organism of the dataset. required: false - name: Gene or spot filtering