fix issues in scripts

scripts/test_resources/test_pipeline.sh

@@ -44,7 +44,7 @@ viash run src/methods_normalization/normalize_by_volume/config.vsh.yaml -- \
 # run a cell type annotation method
 viash run src/methods_cell_type_annotation/ssam/config.vsh.yaml -- \
   --input_spatial_normalized_counts $OUT_DIR/spatial_normalized_counts.h5ad \
-  --input_transcripts $OUT_DIR/transcript_assignments.zarr \
+  --input_transcript_assignments $OUT_DIR/transcript_assignments.zarr \
   --input_scrnaseq_reference $OUT_DIR/scrnaseq_reference.h5ad \
   --output $OUT_DIR/spatial_with_cell_types.h5ad
 
@@ -53,3 +53,9 @@ viash run src/methods_expression_correction/gene_efficiency_correction/config.vs
   --input_spatial_with_cell_types $OUT_DIR/spatial_with_cell_types.h5ad \
   --input_scrnaseq_reference $OUT_DIR/scrnaseq_reference.h5ad \
   --output $OUT_DIR/spatial_corrected_counts.h5ad
+
+# sync test resources
+aws s3 sync --profile op \
+  "resources_test/task_ist_preprocessing/mouse_brain_combined" \
+  "s3://openproblems-data/resources_test/task_ist_preprocessing/mouse_brain_combined" \
+  --delete --dryrun

src/methods_calculate_cell_volume/alpha_shapes/script.py

@@ -15,7 +15,9 @@
 sdata = sd.read_zarr(par['input'])
 
 print('Determine cell ids', flush=True)
-cell_ids = sdata.tables["table"].obs_names
+cell_ids = sorted(sdata["transcripts"]["cell_id"].unique())
+if cell_ids[0] == 0:
+    cell_ids = cell_ids[1:]
 
 print('Init AnnData object', flush=True)
 adata = ad.AnnData(

src/methods_cell_type_annotation/ssam/config.vsh.yaml

@@ -18,8 +18,11 @@ engines:
     image: openproblems/base_python:1.0.0
     setup:
       - type: python
-        pypi: [planktonspace]
         github: [theislab/txsim@dev]
+      - type: python
+        pypi: [squidpy, rasterio]
+      - type: python
+        pypi: [planktonspace]
   - type: native
 
 runners:

src/methods_cell_type_annotation/ssam/script.py

@@ -4,9 +4,9 @@
 
 ## VIASH START
 par = {
-  'input': 'spatial_norm_counts.h5ad',
-  'input_transcripts': 'spatial_assigned.zarr',
-  'input_sc': 'sc_norm_counts.h5ad',
+  'input_spatial_normalized_counts': 'spatial_norm_counts.h5ad',
+  'input_transcript_assignments': 'spatial_assigned.zarr',
+  'input_scrnaseq_reference': 'sc_norm_counts.h5ad',
   'um_per_pixel': 0.5,
   'output': 'spatial_with_celltypes.h5ad',
   'celltype_key': 'celltype',
@@ -16,14 +16,14 @@
 }
 ## VIASH END
 
-# Optional parameter check: For this specific annotation method the par['input_transcripts'] and par['input_sc'] are required
-assert par['input_transcripts'] is not None, 'Transcripts input is required for this annotation method.'
-assert par['input_sc'] is not None, 'Single cell input is required for this annotation method.'
+# Optional parameter check: For this specific annotation method the par['input_transcript_assignments'] and par['input_sc'] are required
+assert par['input_transcript_assignments'] is not None, 'Transcripts input is required for this annotation method.'
+assert par['input_scrnaseq_reference'] is not None, 'Single cell input is required for this annotation method.'
 
 # Read input
 print('Reading input files', flush=True)
 adata_sp = ad.read_h5ad(par['input_spatial_normalized_counts'])
-transcripts = sd.SpatialData.read(par['input_transcripts'])['transcripts']
+transcripts = sd.SpatialData.read(par['input_transcript_assignments'])['transcripts']
 adata_sc = ad.read_h5ad(par['input_scrnaseq_reference'])
 adata_sp = adata_sp[:,adata_sc.var_names] #TODO: do we want to do this earlier? Maybe not, thinking about transcripts related quality metrics
 

src/methods_normalization/normalize_by_volume/config.vsh.yaml

@@ -12,6 +12,8 @@ engines:
     setup:
       - type: python
         github: [theislab/txsim@dev]
+      - type: python
+        pypi: [squidpy, rasterio]
   - type: native
 
 runners: