add singler python implementation

src/methods_cell_type_annotation/singler/config.vsh.yaml

@@ -0,0 +1,38 @@
+__merge__: /src/api/comp_method_cell_type_annotation.yaml
+
+name: singler
+label: "singler"
+summary: "Cell type annotations using single-cell reference with SingleR"
+description: "Cell type annotations using single-cell reference with SingleR"
+
+links:
+  documentation: "https://github.com/openproblems-bio/task_ist_preprocessing"
+  repository: "https://github.com/openproblems-bio/task_ist_preprocessing"
+references:
+  doi: "10.1038/s41590-018-0276-y"
+
+arguments:
+  - name: --labels_key
+    type: string
+    description: The key of the cell labels in the input data.
+    default: cell_labels
+
+resources:
+  - type: python_script
+    path: script.py
+
+engines:
+  - type: docker
+    image: openproblems/base_python:1
+    setup:
+    - type: python
+      pypi: [singler]
+    __merge__: 
+      - /src/base/setup_spatialdata_partial.yaml
+  - type: native
+
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [ midtime, lowcpu, lowmem ]

src/methods_cell_type_annotation/singler/script.py

@@ -0,0 +1,69 @@
+import anndata as ad
+import os
+import shutil
+
+import singlecellexperiment as sce
+import singler
+
+## VIASH START
+# The following code has been auto-generated by Viash.
+par = {
+  'input_spatial_normalized_counts': r'resources_test/task_ist_preprocessing/mouse_brain_combined/spatial_normalized_counts.h5ad',
+  'input_transcript_assignments': r'resources_test/task_ist_preprocessing/mouse_brain_combined/transcript_assignments.zarr',
+  'input_scrnaseq_reference': r'resources_test/task_ist_preprocessing/mouse_brain_combined/scrnaseq_reference.h5ad',
+  'celltype_key': r'cell_type',
+  'output': r'resources_test/task_ist_preprocessing/mouse_brain_combined/spatial_with_cell_types.h5ad',
+  'labels_key': r'cell_labels'
+}
+meta = {
+  'name': r'singleR',
+  'functionality_name': r'singleR',
+  'resources_dir': r'/private/tmp/viash_inject_singleR6465161111175259990',
+  'executable': r'/private/tmp/viash_inject_singleR6465161111175259990/singleR',
+  'config': r'/private/tmp/viash_inject_singleR6465161111175259990/.config.vsh.yaml',
+  'temp_dir': r'/var/folders/fq/ymt0vml175s4yvqxzbmlmpz80000gn/T/',
+  'cpus': int(r'123'),
+  'memory_b': int(r'123'),
+  'memory_kb': int(r'123'),
+  'memory_mb': int(r'123'),
+  'memory_gb': int(r'123'),
+  'memory_tb': int(r'123'),
+  'memory_pb': int(r'123'),
+  'memory_kib': int(r'123'),
+  'memory_mib': int(r'123'),
+  'memory_gib': int(r'123'),
+  'memory_tib': int(r'123'),
+  'memory_pib': int(r'123')
+}
+dep = {
+
+}
+
+## VIASH END
+sce_h5ad = sce.read_h5ad(par['input_spatial_normalized_counts'])
+adata_sp = ad.read_h5ad(par['input_spatial_normalized_counts'])
+
+sce_ref = sce.read_h5ad(par['input_scrnaseq_reference'])
+
+features = [str(x) for x in sce_h5ad.row_data.row_names]
+
+mat = sce_h5ad.assay("counts") ##example has raw, not sure
+mat = mat.sorted_indices() ## magic line to make sure the matrix is in the right format for SingleR
+
+mat_ref = sce_ref.assay("normalized")
+mat_ref = mat_ref.sorted_indices() ## magic line to make sure the matrix is in the right format for SingleR
+
+## create the reference from our sc data
+built = singler.train_single(ref_data = mat_ref,   
+                             ref_labels = sce_ref.get_column_data().column("cell_type"),    
+                             ref_features = sce_ref.get_row_names(),    
+                             test_features = features,)
+
+## annotate the dataset
+output = singler.classify_single(mat, ref_prebuilt=built)
+
+adata_sp.obs["cell_type"] = output['best']
+
+# Write output
+print('Writing output', flush=True)
+adata_sp.write(par['output'])