2025-02-26

Author: pjhesbest

bin/R/create_pairwise_analaysi_tuple.R bin/R/create_pairwise_analysis_tuple.Rbin/R/create_pairwise_analaysi_tuple.R renamed to bin/R/create_pairwise_analysis_tuple.R

@@ -16,7 +16,7 @@ colnames(run_ids) <- "SampleID"
 
 meta <- readr::read_delim("pairwise_analysis.list.csv", col_names = TRUE, delim = ",") |> 
     distinct() |>
-    filter(!is.na(main_lineage) & !str_detect(main_lineage, ";")) |>
+    filter(!is.na(main_lineage) & !str_detect(main_lineage, ",")) |>
     filter(!str_detect(sample, "CN-"))  # This line filters out any sample that contains 'CN-'
 colnames(meta) <- c("SampleID", "main_lineage", "sub_lineage")
 

modules/local/filtering/compile-sequencing-stats/main.nf

@@ -33,7 +33,7 @@ process COMPILE_SEQUENCING_STATS {
                         --lineages      lineages.fractions.txt
 
     # Generate summary statistics and create the sampleID,lineage df for
-    ## creating into a channel 
+    ## creating into a channel TODO: need to fix this script in generating the output for tuplec creation
         Rscript ${params.r_script_dir}/compile-sequencing-statistics.R \\
                     --minimum_coverage ${params.mtbseq_min_cov} \\
                     --runID ${runID} \\
@@ -50,6 +50,7 @@ process COMPILE_SEQUENCING_STATS {
         awk -F "\t" '{ if ( \$14 > ${params.mtbseq_min_cov} ) print \$4 }' Mapping_and_Variant_Statistics.tab | sort | uniq > min.qual.genomes
         sed 's/\t/,/g' tbdb-tbprofiler.txt | cut -d ',' -f1,2,3 > tmp.pairwise_analysis.list.csv
         grep -f min.qual.genomes tmp.pairwise_analysis.list.csv > pairwise_analysis.list.csv
+        touch pairwise_analysis.list.csv
 
     """
 }    

modules/local/filtering/prepare_pairwise_channels/main.nf

@@ -5,9 +5,9 @@ process PREPARE_PAIRWISE_CHANNELS {
     publishDir "${params.outdir}/results/", mode: 'copy'
 
     input:
-        val runID
-        path pairwise_analysis_list
-        val sampleID_list
+        val(runID)
+        path(pairwise_analysis_list)
+        val(sampleID_list)
 
     output:
         path "final.lineage_samples_tuple.csv", emit: lineage_sample_tuple
@@ -24,7 +24,7 @@ process PREPARE_PAIRWISE_CHANNELS {
             echo '${params.lineage_pairwise_main.join('\n')}' > selected_main-lineage_split.list
 
         # Run the script to generate pairwise analysis tuples
-            Rscript ${params.r_script_dir}/create_pairwise_analaysi_tuple.R \\
+            Rscript ${params.r_script_dir}/create_pairwise_analysis_tuple.R \\
                 1>>.command.out \\
                 2>>.command.err || true # i think this helps
 

modules/local/mtbseq/lineage_joint-amend/main.nf

@@ -8,7 +8,7 @@ process MTBSEQ_LINEAGE_JOINT_AMEND {
     ///        } else { 'quay.io/biocontainers/mtbseq' }
     ///}
 
-    publishDir "${params.outdir}/bbdd/mtbseq/pairwise/${lineage}/", mode: 'copy'
+    publishDir "${params.outdir}/bbdd/mtbseq/pairwise/${lineage}/", mode: 'copy', overwrite: true
 
     input:
         val runID
@@ -46,7 +46,7 @@ process MTBSEQ_LINEAGE_JOINT_AMEND {
 
         """
 
-        rm -rf ${params.outdir}/bbdd/mtbseq/pairwise/${lineage}/*
+        #rm -rf ${params.outdir}/bbdd/mtbseq/pairwise/${lineage}/*
 
         # make the expected directories
             mkdir -p Position_Tables/ Called/ Amend/ Joint/

workflows/pairwise_wf.nf

@@ -45,7 +45,7 @@ workflow PAIRWISE_WF {
                                     )
 
             PREPARE_PAIRWISE_CHANNELS(  runID,
-                                        TBPROFILER_COMPILE_TBDB.out.tbdb_results,
+                                        COMPILE_SEQUENCING_STATS.out.pairwise_analysis_list,
                                         sampleID_list
                                     )