Various fixes (#114)

* Make sure sc adata var names are unique

* Adjust memory and time

Author: LouisK92

src/data_processors/process_dataset/script.py

@@ -180,6 +180,9 @@ def subsample_adata_group_balanced(adata, group_key, n_samples, seed=0):
 if adata.n_obs > N_MAX_SC:
     adata = adata[subsample_adata_group_balanced(adata, "cell_type", N_MAX_SC, seed=0)]
 
+# Make the single-cell data gene names unique
+adata.var_names_make_unique()
+
 # Subset single-cell and spatial data to shared genes
 sp_genes = sdata['transcripts']['feature_name'].unique().compute().tolist()
 sc_genes = adata.var["feature_name"].unique().tolist()

src/methods_cell_type_annotation/ssam/config.vsh.yaml

@@ -36,4 +36,4 @@ runners:
   - type: executable
   - type: nextflow
     directives:
-      label: [ hightime, midcpu, midmem ]
+      label: [ veryhightime, midcpu, midmem ]

src/methods_expression_correction/gene_efficiency_correction/config.vsh.yaml

@@ -38,4 +38,4 @@ runners:
   - type: executable
   - type: nextflow
     directives:
-      label: [ midtime, lowcpu, lowmem ]
+      label: [ midtime, lowcpu, midmem ]

src/metrics/similarity/config.vsh.yaml

@@ -101,4 +101,4 @@ runners:
   # Allows turning the component into a Nextflow module / pipeline.
   - type: nextflow
     directives:
-      label: [midtime, highmem, midcpu]
+      label: [midtime, veryhighmem, midcpu]