Merge pull request #887 from openpipelines-bio/add_metrics

add metrics to uns slot after conversion to h5mu

CHANGELOG.md

@@ -171,6 +171,8 @@
 
 * Fix failing tests for `ingestion/cellranger_postprocessing`, `ingestion/conversion` and `multiomics/process_batches` (PR #869).
 
+* `convert/from_10xh5_to_h5mu`: add .uns slot to mdata root when metrics file is provided (PR #887).
+
 ## DOCUMENTATION
 
 * Update authorship of components (PR #835).

src/convert/from_10xh5_to_h5mu/script.py

@@ -44,7 +44,7 @@ def setup_logger():
     .reset_index()\
     .set_index("gene_ids")
 
-# parse metrics summary file and store in .obsm or .obs
+# parse metrics summary file and store in .uns
 if par["input_metrics_summary"] and par["uns_metrics"]:
     logger.info("Reading metrics summary file '%s'", par['input_metrics_summary'])
 
@@ -76,8 +76,9 @@ def read_percentage(val):
 logger.info("Convert to mudata")
 mdata = mudata.MuData(adata)
 
-# override root .obs
+# override root .obs and .uns
 mdata.obs = adata.obs
+mdata.uns = adata.uns
 
 # write output
 logger.info("Writing %s", par["output"])

src/convert/from_10xh5_to_h5mu/test.py

@@ -12,6 +12,7 @@
 ## VIASH END
 
 input = meta["resources_dir"] + "/pbmc_1k_protein_v3/pbmc_1k_protein_v3_filtered_feature_bc_matrix.h5"
+metrics = meta["resources_dir"] + "/pbmc_1k_protein_v3/pbmc_1k_protein_v3_metrics_summary.csv"
 
 def test_run(run_component, random_h5mu_path):
     output = random_h5mu_path()
@@ -40,7 +41,25 @@ def test_run(run_component, random_h5mu_path):
     assert (
         "CD3" in data.mod["prot"].var_names
     ), 'Output should contain antibody column "CD3".'
-
-
+
+def test_run_with_metrics(run_component, random_h5mu_path):
+    output = random_h5mu_path()
+    cmd_pars = [
+        "--input", input,
+        "--output", output,
+        "--input_metrics_summary", metrics,
+        "--output_compression", "gzip",
+    ]
+    run_component(cmd_pars)
+
+    # check if file exists
+    assert path.exists(output), "No output was created."
+
+    # read it with scanpy
+    data = read_h5mu(output)
+
+    # check whether uns slot was found
+    assert "metrics_cellranger" in data.uns, "Output mudata object should contain an .uns slot with cellranger metrics."
+
 if __name__ == "__main__":
     sys.exit(pytest.main([__file__]))