Add mapping file

genepi · Dec 19, 2023 · a98cfae · a98cfae
1 parent edc5bde
commit a98cfae
Show file tree

Hide file tree

Showing 5 changed files with 32 additions and 22 deletions.
diff --git a/modules/local/calculate_statistics.nf b/modules/local/calculate_statistics.nf
@@ -4,17 +4,21 @@ process CALCULATE_STATISTICS {
     path bam_file
 
     output:
-    path "*summary.tab.txt", emit: stats_ch
+    path "*summary.txt", emit: stats_ch
+    path "*mapping.txt", emit: mapping_ch
     path "*.zip", emit: fastqc_ch
 
 
     script:
     def output_name = "${bam_file.baseName}.summary.txt"
-    def output_name_tab = "${bam_file.baseName}.summary.tab.txt"
+    def mapping_name = "${bam_file.baseName}.mapping.txt"
 
     """
+    ## determine mapping
+    echo -e "Sample\tFilename" > $mapping_name
+    samtools samples ${bam_file} >> $mapping_name
+
     ## calculate summary statistics
-    samtools samples  ${bam_file}
     samtools coverage ${bam_file} > samtools_coverage_${bam_file.baseName}.txt
     csvtk grep -t -f3 -p 16569 samtools_coverage_${bam_file.baseName}.txt -T -o mtdna.txt
 
@@ -25,16 +29,14 @@ process CALCULATE_STATISTICS {
     mean_depth=\$(csvtk cut -t -f 7 mtdna.txt)
     mean_base_quality=\$(csvtk cut -t -f 8 mtdna.txt)
     mean_map_quality=\$(csvtk cut -t -f 9 mtdna.txt)
-    echo Sample\tParameter\tValue > $output_name
-    echo ${bam_file.baseName}\tContig\t\${contig} >> $output_name
-    echo ${bam_file.baseName}\tNumberofReads\t\${numreads} >> $output_name
-    echo ${bam_file.baseName}\tCoveredBases\t\${covered_bases} >> $output_name
-    echo ${bam_file.baseName}\tCoveragePercentage\t\${covered_bases_percentage} >> $output_name
-    echo ${bam_file.baseName}\tMeanDepth\t\${mean_depth} >> $output_name
-    echo ${bam_file.baseName}\tMeanBaseQuality\t\${mean_base_quality} >> $output_name
-    echo ${bam_file.baseName}\tMeanMapQuality\t\${mean_map_quality} >> $output_name
-
-    csvtk space2tab $output_name -o $output_name_tab
+    echo -e "Sample\tParameter\tValue" > $output_name
+    echo -e "${bam_file.baseName}\tContig\t\${contig}" >> $output_name
+    echo -e "${bam_file.baseName}\tNumberofReads\t\${numreads}" >> $output_name
+    echo -e "${bam_file.baseName}\tCoveredBases\t\${covered_bases}" >> $output_name
+    echo -e "${bam_file.baseName}\tCoveragePercentage\t\${covered_bases_percentage}" >> $output_name
+    echo -e "${bam_file.baseName}\tMeanDepth\t\${mean_depth}" >> $output_name
+    echo -e "${bam_file.baseName}\tMeanBaseQuality\t\${mean_base_quality}" >> $output_name
+    echo -e "${bam_file.baseName}\tMeanMapQuality\t\${mean_map_quality}" >> $output_name
 
     fastqc $bam_file -o .
 

diff --git a/modules/local/input_validation.nf b/modules/local/input_validation.nf
@@ -4,14 +4,17 @@ process INPUT_VALIDATION {
 
     input:
     path statistics
+    path mapping
 
     output:
     path("sample_statistics.txt"), emit: summarized_ch
+    path("sample_mappings.txt"), emit: mapping_ch
     path("excluded_samples.txt"), emit: excluded_ch
     path("contig.txt"), emit: contig_ch
 
     """
     csvtk concat -t ${statistics} -T -o sample_statistics.txt
+    csvtk concat -t ${mapping} -T -o sample_mappings.txt
     java -jar /opt/mutserve/mutserve.jar stats \
     --input sample_statistics.txt \
     --detection-limit ${params.detection_limit}  \

diff --git a/modules/local/report.nf b/modules/local/report.nf
@@ -1,15 +1,16 @@
 process REPORT {
 
-  publishDir "${params.output_reports}", mode: 'copy'
+    publishDir "${params.output_reports}", mode: 'copy'
 
-  input:
+    input:
     path report
     path variants
     path haplogroups
     path haplocheck
     path statistics
+    path mapping
 
-  output:
+    output:
     file "*.html" 
 
   """
@@ -27,10 +28,11 @@ process REPORT {
   Rscript -e "require('rmarkdown'); render('${report}',
    params = list(
        pipeline_parameters = 'params.txt',
-       variants = '${variants}',
+       variants = '${variants}',vi wo 
        haplogroups = '${haplogroups}',
        haplocheck = '${haplocheck}',
-       statistics = '${statistics}'
+       statistics = '${statistics}',
+       mapping = '${mapping}'
    ),
    knit_root_dir='\$PWD', output_file='\$PWD/report.html')"
   """

diff --git a/reports/report.Rmd b/reports/report.Rmd
@@ -8,6 +8,7 @@ params:
   haplocheck: ../tests/data/report2/haplocheck.txt
   variants:  ../tests/data/report2/variants_ann.txt
   statistics:  ../tests/data/report2/sample_statistics.txt
+  mapping:  ../tests/data/report2/mapping.txt  
   pipeline_parameters:  ../tests/data/report2/pipeline_parameters.txt  
 ---
 
@@ -29,7 +30,7 @@ contamination <- read.delim(params$haplocheck)
 haplogroups <- read.delim(params$haplogroups)
 statistics <- read.delim(params$statistics)
 pipeline_params <- read.delim(params$pipeline_parameters)
-
+mapping <- read.delim(params$mapping)
 
 statTable<-spread(statistics, key = Parameter, value = Value)
 statTable$MeanCoverage<-as.numeric(statTable$MeanDepth)

diff --git a/workflows/mtdna_server_2.nf b/workflows/mtdna_server_2.nf
@@ -15,7 +15,7 @@ if (params.output_reports == null || params.output_auxiliary == null ) {
     params.output_auxiliary = params.output    
 }
 
-   include { INDEX } from '../modules/local/index'
+include { INDEX } from '../modules/local/index'
 include { CALCULATE_STATISTICS } from '../modules/local/calculate_statistics'
 include { INPUT_VALIDATION } from '../modules/local/input_validation'
 include { QUALITY_CONTROL } from '../modules/local/quality_control'
@@ -53,7 +53,8 @@ workflow MTDNA_SERVER_2 {
     )
 
     INPUT_VALIDATION(
-        CALCULATE_STATISTICS.out.stats_ch.collect()
+        CALCULATE_STATISTICS.out.stats_ch.collect(),
+        CALCULATE_STATISTICS.out.mapping_ch.collect()
     )
 
 
@@ -111,7 +112,8 @@ workflow MTDNA_SERVER_2 {
     variants_txt_ch,
     HAPLOGROUP_DETECTION.out.haplogroups_ch,
     CONTAMINATION_DETECTION.out.contamination_txt_ch,
-    INPUT_VALIDATION.out.summarized_ch
+    INPUT_VALIDATION.out.summarized_ch,
+    INPUT_VALIDATION.out.mapping_ch
     )
 
 }