make cluster validation using indices optional #46

config/config.yaml

@@ -70,8 +70,9 @@ clustree:
 
 ##### cluster validation ####
 # Cluster validation using internal cluster indices is computationally very expensive.
-# To reduce complexity and increase performance as proportion of samples can be used for the internal cluster evaluation.
-sample_proportion: 1 # float 0-1, >500 samples should be included.
+# To reduce complexity and increase performance a proportion of samples can be used for the internal cluster evaluation.
+# Internal cluster validation can be skipped with 0.
+sample_proportion: 1 # float (0-1], >500 samples should be included.
 
 ##### categorical metadata column used in the following analyses:
 # - PCA pairs plot (first entry only)

workflow/Snakefile

@@ -151,7 +151,7 @@ rule all:
         # cluster validation with internal and external indices
         cluster_validation = expand(os.path.join(result_path,'{sample}','cluster_validation','plots','{index_type}'),
                                              sample=list(annot.index),
-                                             index_type = ["external", "internal"]
+                                             index_type = ["external", "internal"] if config["sample_proportion"]>0 else ["external"],
                                             ) if len(cluster_methods)>0 else [],
         envs = expand(os.path.join(config["result_path"],'envs',module_name,'{env}.yaml'),env=['clusterCrit','clustree','ComplexHeatmap','ggplot','umap_leiden','plotly','pymcdm','sklearn']),
         configs = os.path.join(config["result_path"],'configs',module_name,'{}_config.yaml'.format(config["project_name"])),