Merge pull request #7 from DKFZ-ODCF/create-warning-upon-too-many-ind…

…els-and-exit0-upon-lt50-germline-variants

Create warning upon too many indels and exit0 upon lt50 germline variants

resources/analysisTools/indelCallingWorkflow/TiN_CanopyBasedClustering.R

@@ -275,6 +275,10 @@ library(vcfR)
 vcf <- read.vcfR(opt$vcf)
 vcf <- as.data.frame(cbind(vcf@fix, vcf@gt))
 vcf$POS <- as.integer(as.character(vcf$POS))
+
+vcf$CHR <- as.character(vcf$CHR)
+dat$CHR <- as.character(dat$CHR)
+
 vcf %>% left_join(dat %>% select(CHR:ALT, TiN_Class) %>% rename("CHROM"="CHR")) %>%
   rename("#CHROM"="CHROM")  %>%
   write_tsv(opt$Ovcf, na=".")

resources/analysisTools/indelCallingWorkflow/checkSampleSwap_TiN.sh

@@ -22,6 +22,8 @@ then
   VCF_NORMAL_HEADER_COL=`basename ${FILENAME_CONTROL_BAM} | sed 's/.bam$//'`
 fi
 
+LOGFILE=$(dirname "$FILENAME_RARE_GERMLINE")/checkSampleSwap_TiN.log
+
 ${PERL_BINARY} ${TOOL_CHECK_SAMPLE_SWAP_SCRIPT} \
     --pid=${PID} \
     --raw_file=${FILENAME_VCF_RAW} \
@@ -48,13 +50,17 @@ ${PERL_BINARY} ${TOOL_CHECK_SAMPLE_SWAP_SCRIPT} \
     --outfile_rareGermline=${FILENAME_RARE_GERMLINE} \
     --outfile_somaticRescue=${FILENAME_SOMATIC_RESCUE} \
     --outfile_allSomatic=${FILENAME_ALL_SOMATIC} \
-    --outfile_swapJson=${FILENAME_SWAP_JSON}
+    --outfile_swapJson=${FILENAME_SWAP_JSON} \
+    2>&1 | tee "$LOGFILE"
 
-### Check the perl run was success or not
-if [[ $? == 0 ]] 
+### Check whether Perl run was success or not
+if [[ $? -eq 0 ]]
 then
-  touch ${FILENAME_CHECKPOINT_SWAP}
-  exit 0
+    touch "$FILENAME_CHECKPOINT_SWAP"
+    exit 0
+elif grep -P 'Less than \d+ rare germline variants' "$LOGFILE"; then
+    touch "$FILENAME_CHECKPOINT_SWAP"
+    exit 0
 else
-  exit 1
+    exit 1
 fi

resources/analysisTools/indelCallingWorkflow/environments/conda.sh

@@ -19,3 +19,4 @@ export TABIX_BINARY=tabix
 export BEDTOOLS_BINARY=bedtools
 export SAMTOOLS_BINARY=samtools
 export PYPY_BINARY=pypy
+export RSCRIPT_BINARY=Rscript

resources/analysisTools/indelCallingWorkflow/environments/tbi-cluster.sh

@@ -38,3 +38,4 @@ export BGZIP_BINARY=bgzip
 export TABIX_BINARY=tabix
 export BEDTOOLS_BINARY=bedtools
 export PYPY_BINARY=pypy-c
+export RSCRIPT_BINARY=Rscript

resources/analysisTools/indelCallingWorkflow/filter_vcf.sh

@@ -76,15 +76,38 @@ functional_var_count=`cat ${somatic_functional_indel_vcf} | wc -l | cut -f1 -d "
 if [[ $functional_var_count -le $MAX_VARIANT_SCREENSHOTS ]]
 then
 
-  [[ "${isControlWorkflow}" == true ]] && ${PYTHON_BINARY} ${TOOL_SCREENSHOT} --vcf=${somatic_functional_indel_vcf} --control=${FILENAME_CONTROL_BAM} --tumor=${FILENAME_TUMOR_BAM} --ref=${REFERENCE_GENOME} --prefix=${VCF_SCREENSHOTS_PREFIX} --window=${WINDOW_SIZE} --annotations=${REPEAT_MASKER} --samtoolsbin=${SAMTOOLS_BINARY} --tabixbin=${TABIX_BINARY}
-  [[ "${isNoControlWorkflow}" == true ]] && ${PYTHON_BINARY} ${TOOL_SCREENSHOT} --vcf=${somatic_functional_indel_vcf} --tumor=${FILENAME_TUMOR_BAM} --ref=${REFERENCE_GENOME} --prefix=${VCF_SCREENSHOTS_PREFIX} --window=${WINDOW_SIZE} --annotations=${REPEAT_MASKER} --samtoolsbin=${SAMTOOLS_BINARY} --tabixbin=${TABIX_BINARY}
+    if [[ "${isControlWorkflow}" == true ]]; then
+        ${PYTHON_BINARY} ${TOOL_SCREENSHOT} \
+            --vcf=${somatic_functional_indel_vcf} \
+            --control=${FILENAME_CONTROL_BAM} \
+            --tumor=${FILENAME_TUMOR_BAM} \
+            --ref=${REFERENCE_GENOME} \
+            --prefix=${VCF_SCREENSHOTS_PREFIX} \
+            --window=${WINDOW_SIZE} \
+            --annotations=${REPEAT_MASKER} \
+            --samtoolsbin=${SAMTOOLS_BINARY} \
+            --tabixbin=${TABIX_BINARY}
+    fi
 
-  pngs=(`ls *.pdf`)
-  sorted=$(printf "%s\n" ${pngs[@]}|sort -k1,1V)
+    if [[ "${isNoControlWorkflow}" == true ]]; then
+        ${PYTHON_BINARY} ${TOOL_SCREENSHOT} \
+            --vcf=${somatic_functional_indel_vcf} \
+            --tumor=${FILENAME_TUMOR_BAM} \
+            --ref=${REFERENCE_GENOME} \
+            --prefix=${VCF_SCREENSHOTS_PREFIX} \
+            --window=${WINDOW_SIZE} \
+            --annotations=${REPEAT_MASKER} \
+            --samtoolsbin=${SAMTOOLS_BINARY} \
+            --tabixbin=${TABIX_BINARY}
+    fi
+    pngs=(`ls *.pdf`)
+    sorted=$(printf "%s\n" ${pngs[@]}|sort -k1,1V)
 
-  ${GHOSTSCRIPT_BINARY} -dBATCH -dNOPAUSE -q -sDEVICE=pdfwrite -sOutputFile=${combined_screen_shots} ${sorted}
+    ${GHOSTSCRIPT_BINARY} -dBATCH -dNOPAUSE -q -sDEVICE=pdfwrite -sOutputFile=${combined_screen_shots} ${sorted}
 else
-  printf "WARNINGS: No screenshots done, more than $MAX_VARIANT_SCREENSHOTS (cvalue - MAX_VARIANT_SCREENSHOTS) functional variants present in ${somatic_functional_indel_vcf} \n"
+    printf "WARNINGS: No screenshots done, more than $MAX_VARIANT_SCREENSHOTS (cvalue - MAX_VARIANT_SCREENSHOTS) functional variants present in ${somatic_functional_indel_vcf}\n"
+    $RSCRIPT_BINARY "$TOOL_TEXT_PDF" "WARNING\nNo screenshots done. More than $MAX_VARIANT_SCREENSHOTS functional variants." \
+        > "$combined_screen_shots"
 fi
 
 #### Indel QC json file

resources/analysisTools/indelCallingWorkflow/textPdf.R

@@ -0,0 +1,15 @@
+#!/usr/bin/env Rscript
+
+args <- commandArgs(trailingOnly=TRUE)
+if (length(args) == 0) {
+    text <- ""
+} else {
+    text <- args[1]
+}
+
+write(text, stdout())
+
+pdf("/dev/stdout", height=3, width=6)
+plot.new()
+mtext(text)
+ignore <- dev.off()

resources/configurationFiles/analysisIndelCalling.xml

@@ -198,6 +198,7 @@
         <tool name="screenshot" value="visualize.py" basepath="indelCallingWorkflow"/>
         <tool name="vcfFilterByCrit" value="vcf_filter_by_crit.py" basepath="indelCallingWorkflow"/>
         <tool name="platypusIndelJson" value="indel_json_v1.0.pl" basepath="indelCallingWorkflow"/>
+        <tool name="textPdf" value="textPdf.R" basepath="indelCallingWorkflow"/>
 
         <!--## SwapChecker -->
         <tool name="checkSampleSwapScript" value="checkSampleSwap_TiN.pl" basepath="indelCallingWorkflow"/>