Add normalization by total counts (#64)

Author: LouisK92

src/methods_normalization/normalize_by_counts/config.vsh.yaml

@@ -0,0 +1,34 @@
+__merge__: /src/api/comp_method_normalization.yaml
+
+name: normalize_by_counts
+label: "Normalize by Counts"
+summary: "Normalize the spatial transcriptomics data by the total counts"
+description: "Normalize the spatial transcriptomics data by the total counts"
+links:
+  documentation: "https://github.com/openproblems-bio/task_ist_preprocessing"
+  repository: "https://github.com/scverse/scanpy"
+references:
+  doi: "10.1186/s13059-017-1382-0"
+
+arguments:
+  - name: --target_sum
+    type: double
+
+resources:
+  - type: python_script
+    path: script.py
+
+engines:
+  - type: docker
+    image: openproblems/base_python:1
+    setup:
+      - type: python
+        pypi: 
+          - scanpy
+  - type: native
+
+runners:
+  - type: executable
+  - type: nextflow
+    directives:
+      label: [ midtime, lowcpu, lowmem ]

src/methods_normalization/normalize_by_counts/script.py

@@ -0,0 +1,22 @@
+import anndata as ad
+import scanpy as sc
+
+## VIASH START
+par = {
+  'input_spatial_aggregated_counts': 'resources_test/task_ist_preprocessing/mouse_brain_combined/spatial_aggregated_counts.h5ad',
+  'output': 'spatial_norm_counts.h5ad',
+
+  'target_sum': None,
+}
+## VIASH END
+
+print('Reading input files', flush=True)
+adata = ad.read(par['input_spatial_aggregated_counts'])
+
+print('Normalizing by total counts', flush=True)
+adata.layers['normalized'] = adata.layers['counts'].copy()
+sc.pp.normalize_total(adata, layer="normalized", target_sum=par["target_sum"])
+sc.pp.log1p(adata, layer="normalized")
+
+print('Writing output', flush=True)
+adata.write(par['output'])