The filepaths folder has been removed from the output. existing_cells…

…np is not saved in the output folder if it has only readme.md
wtsi-hgi · Dec 13, 2024 · 9b499ed · 9b499ed
1 parent ba2a996
commit 9b499ed
Show file tree

Hide file tree

Showing 2 changed files with 25 additions and 13 deletions.
diff --git a/modules/nf-core/modules/cellsnp/main.nf b/modules/nf-core/modules/cellsnp/main.nf
@@ -2,7 +2,8 @@ process capture_cellsnp_files{
 
   publishDir  path: "${params.outdir}/deconvolution/",
         saveAs: {filename ->
-        if (filename == "output_cellsnp.csv" || filename == "existing_cellsnp") {
+        File file = new File(filename)
+        if (filename == "output_cellsnp.csv" || filename == "existing_cellsnp_do_not_save") {
           null
         }else {
           filename
@@ -18,12 +19,23 @@ process capture_cellsnp_files{
   script:
   """
     echo '${params.cellsnp_recapture}'
-    for OUTPUT in \$(ls ${cellsnp_location})
-    do
-    samplename1=\$(echo \$OUTPUT | sed 's/cellsnp_//g') 
-    echo "\$samplename1 \$PWD/${cellsnp_location}/\$OUTPUT" >> output_cellsnp.csv
+    echo "deconvolution_test"
+    for OUTPUT in \$(ls ${cellsnp_location}); do
+        if [ ${cellsnp_location} == "existing_cellsnp" ] && [ -d ${cellsnp_location} ]; then
+            file_count=\$(ls -1 ${cellsnp_location} | wc -l)
+            if [ "\$file_count" -eq 1 ] && [ "\$OUTPUT" == "readme.md" ]; then
+                echo "Skipping folder ${cellsnp_location}"
+                mv ${cellsnp_location} existing_cellsnp_do_not_save
+            else
+              samplename1=\$(echo \$OUTPUT | sed 's/cellsnp_//g') 
+              echo "\$samplename1 \$PWD/${cellsnp_location}/\$OUTPUT" >> output_cellsnp.csv
+            fi
+        else
+          samplename1=\$(echo \$OUTPUT | sed 's/cellsnp_//g') 
+          echo "\$samplename1 \$PWD/${cellsnp_location}/\$OUTPUT" >> output_cellsnp.csv
+        fi
     done
-  """    
+  """
 }
 
 

diff --git a/subworkflows/main_deconvolution.nf b/subworkflows/main_deconvolution.nf
@@ -385,26 +385,26 @@ workflow  main_deconvolution {
 
         // collect file paths to h5ad files in tsv tables:
         header_seed="experiment_id\tdonor\th5ad_filepath"
-        collect_file2(SPLIT_DONOR_H5AD.out.donors_h5ad_tsv.collect(),"donors_h5ad.tsv",params.outdir+'/deconvolution/filepaths',0,header_seed)
+        collect_file2(SPLIT_DONOR_H5AD.out.donors_h5ad_tsv.collect(),"donors_h5ad.tsv",0,0,header_seed)
 
         header_seed="experiment_id\th5ad_filepath"
-        collect_file3(SPLIT_DONOR_H5AD.out.exp__donors_h5ad_tsv.collect(),"exp__donors_h5ad.tsv",params.outdir+'/deconvolution/filepaths',0,header_seed)
+        collect_file3(SPLIT_DONOR_H5AD.out.exp__donors_h5ad_tsv.collect(),"exp__donors_h5ad.tsv",0,0,header_seed)
 
         header_seed="experiment_id\tdonor\th5ad_filepath"
-        collect_file4(SPLIT_DONOR_H5AD.out.donors_h5ad_assigned_tsv.collect(),"donors_h5ad_assigned.tsv",params.outdir+'/deconvolution/filepaths',0,header_seed)
+        collect_file4(SPLIT_DONOR_H5AD.out.donors_h5ad_assigned_tsv.collect(),"donors_h5ad_assigned.tsv",0,0,header_seed)
 
         header_seed="experiment_id\th5ad_filepath"
-        out_h5ad = collect_file5(SPLIT_DONOR_H5AD.out.exp__donors_h5ad_assigned_tsv.collect(),"exp__donors_h5ad_assigned.tsv",params.outdir+'/deconvolution/filepaths',0,header_seed)
+        out_h5ad = collect_file5(SPLIT_DONOR_H5AD.out.exp__donors_h5ad_assigned_tsv.collect(),"exp__donors_h5ad_assigned.tsv",0,0,header_seed)
 
         header_seed="experiment_id\th5ad_filepath"
-        collect_file6(SPLIT_DONOR_H5AD.out.h5ad_tsv.collect(),"cellranger_as_h5ad.tsv",params.outdir+'/deconvolution/filepaths',0,header_seed)
+        collect_file6(SPLIT_DONOR_H5AD.out.h5ad_tsv.collect(),"cellranger_as_h5ad.tsv",0,0,header_seed)
 
         header_seed="experiment_id\tdonor\tn_cells"
-        ch_vireo_donor_n_cells_tsv = collect_file7(REPLACE_GT_DONOR_ID2.out.sample_summary_tsv.collect(),"vireo_donor_n_cells.tsv",params.outdir+'/deconvolution/filepaths',0,header_seed)
+        ch_vireo_donor_n_cells_tsv = collect_file7(REPLACE_GT_DONOR_ID2.out.sample_summary_tsv.collect(),"vireo_donor_n_cells.tsv",0,0,header_seed)
 
         // paste experiment_id and donor ID columns with __ separator
         header_seed="experiment_id\tn_cells"
-        vireo_out_sample__exp_summary_tsv = collect_file8(SPLIT_DONOR_H5AD.out.donor_n_cells.collect(),"vireo_exp__donor_n_cells.tsv",params.outdir+'/deconvolution/filepaths',0,header_seed)
+        vireo_out_sample__exp_summary_tsv = collect_file8(SPLIT_DONOR_H5AD.out.donor_n_cells.collect(),"vireo_exp__donor_n_cells.tsv",0,0,header_seed)
 
         if (params.genotype_input.run_with_genotype_input & params.genotype_input.posterior_assignment) {
             if (params.extra_sample_metadata!='' & params.add_donor_metadata){