Fix testcases and format modules

genepi · Feb 26, 2024 · cb57a35 · cb57a35
1 parent ad817d1
commit cb57a35
Show file tree

Hide file tree

Showing 11 changed files with 98 additions and 49 deletions.
diff --git a/modules/local/annotate.nf b/modules/local/annotate.nf
@@ -8,9 +8,13 @@ process ANNOTATE {
     path annotation
 
     output:
-    path ("${variants_ch.baseName}_ann.txt"), emit: variants_ann_ch
+    path ("${variants_ch.baseName}.annotated.txt"), emit: variants_ann_ch
 
     """
-    java -jar /opt/mutserve/mutserve.jar annotate --input ${variants_ch} --output ${variants_ch.baseName}_ann.txt --annotation ${annotation}
+    java -jar /opt/mutserve/mutserve.jar \
+        annotate \
+        --input ${variants_ch} \
+        --output ${variants_ch.baseName}.annotated.txt \
+        --annotation ${annotation}
     """
 }
diff --git a/modules/local/filter_variants.nf b/modules/local/filter_variants.nf
@@ -12,16 +12,26 @@ process FILTER_VARIANTS {
     def vcf_name = "${vcf_file}".replaceAll('.vcf.gz', '')
 
     """
-    echo -e "ID\tFilter\tPos\tRef\tVariant\tVariantLevel\tCoverage\tType" > ${vcf_file.baseName}.${method}.txt
+    echo -e "ID\tFilter\tPos\tRef\tVariant\tVariantLevel\tCoverage\tType" \
+        > ${vcf_file.baseName}.${method}.txt
     
     if [[ ${method} == "mutserve_fusion" ]]
     then
-        bcftools query -f '${vcf_name}.bam\t%FILTER\t%POS\t%REF\t%ALT\t[%AF\t%DP\t%GT]\n' ${vcf_file} >> ${vcf_file.baseName}.${method}.txt
-        awk -F'\t' 'NR == 1 || (length(\$4) == 1 && length(\$5) == 1)' ${vcf_file.baseName}.${method}.txt > ${vcf_file.baseName}.${method}.filtered.txt
+        bcftools query \
+            -f '${vcf_name}.bam\t%FILTER\t%POS\t%REF\t%ALT\t[%AF\t%DP\t%GT]\n' \
+             ${vcf_file} >> ${vcf_file.baseName}.${method}.txt
+        
+        awk -F'\t' 'NR == 1 || (length(\$4) == 1 && length(\$5) == 1)' \
+            ${vcf_file.baseName}.${method}.txt > ${vcf_file.baseName}.${method}.filtered.txt
+
     elif [[ ${method} == "mutect2_fusion" ]]
     then
-        bcftools query -f '${vcf_name}.bam\t%FILTER\t%POS\t%REF\t%ALT\t[%AF\t%DP]\tINDEL\n'  ${vcf_file} >> ${vcf_file.baseName}.${method}.txt
-        awk -F'\t' 'NR == 1 || ((length(\$4) > 1 || length(\$5) > 1) && length(\$4) != length(\$5))' ${vcf_file.baseName}.${method}.txt > ${vcf_file.baseName}.${method}.filtered.txt
+        bcftools query \
+            -f '${vcf_name}.bam\t%FILTER\t%POS\t%REF\t%ALT\t[%AF\t%DP]\tINDEL\n' \
+            ${vcf_file} >> ${vcf_file.baseName}.${method}.txt
+
+        awk -F'\t' 'NR == 1 || ((length(\$4) > 1 || length(\$5) > 1) && length(\$4) != length(\$5))' \
+            ${vcf_file.baseName}.${method}.txt > ${vcf_file.baseName}.${method}.filtered.txt
     fi
     """
 }

diff --git a/modules/local/index.nf b/modules/local/index.nf
@@ -7,6 +7,7 @@ process INDEX {
 
 	"""
     samtools faidx $reference
-    samtools dict $reference -o ${reference.baseName}.dict
+    	samtools dict $reference \
+	    -o ${reference.baseName}.dict
 	"""
 }
diff --git a/modules/local/input_validation.nf b/modules/local/input_validation.nf
@@ -13,17 +13,23 @@ process INPUT_VALIDATION {
     path("contig.txt"), emit: contig_ch
 
     """
-    csvtk concat -t ${statistics} -T -o sample_statistics.txt
-    csvtk concat -t ${mapping} -T -o sample_mappings.txt
+    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}  \
-    --reference ${params.reference}  \
-    --baseQ ${params.baseQ}\
-    --mapQ ${params.mapQ} \
-    --alignQ ${params.alignQ} \
-    --output-excluded-samples excluded_samples.txt \
-    --output-contig contig.txt \
-    --tool ${params.mode}
+        --input sample_statistics.txt \
+        --detection-limit ${params.detection_limit}  \
+        --reference ${params.reference}  \
+        --baseQ ${params.baseQ}\
+        --mapQ ${params.mapQ} \
+        --alignQ ${params.alignQ} \
+        --output-excluded-samples excluded_samples.txt \
+        --output-contig contig.txt \
+        --tool ${params.mode}
     """
 }
diff --git a/modules/local/merging_variants.nf b/modules/local/merging_variants.nf
@@ -5,20 +5,25 @@ process MERGING_VARIANTS {
     val mode
 
     output:
-    path("variants.merged.txt"), emit: txt_summarized_ch
+    path("variants.txt"), emit: txt_summarized_ch
 
     """
-    csvtk concat -t ${variants_txt} -T -o variants.concat.txt
+    csvtk concat \
+        -t ${variants_txt} \
+        -T -o variants.concat.txt
     
-    csvtk sort -t variants.concat.txt -k ID:N -k Pos:n -k Type:r -T -o variants.sorted.txt
+    csvtk sort \
+        -t variants.concat.txt \
+        -k ID:N -k Pos:n -k Type:r \
+        -T -o variants.sorted.txt
 
     if [[ ${mode} == "fusion" ]]
     then
         java -jar /opt/VariantMerger.jar \
             variants.sorted.txt \
-            --output variants.merged.txt
+            --output variants.txt
     else
-        mv variants.sorted.txt variants.merged.txt
+        mv variants.sorted.txt variants.txt
     fi
     """
 }
diff --git a/modules/local/mutect2.nf b/modules/local/mutect2.nf
@@ -17,25 +17,35 @@ process MUTECT2 {
     samtools index ${bam_file}
 
     gatk Mutect2 \
-    -R ${reference} \
-    -L ${detected_contig} \
-    --min-base-quality-score ${params.baseQ} \
-    -callable-depth 6 --max-reads-per-alignment-start 0 \
-    -I ${bam_file} \
-    -O raw.vcf.gz
+        -R ${reference} \
+        -L ${detected_contig} \
+        --min-base-quality-score ${params.baseQ} \
+        -callable-depth 6 --max-reads-per-alignment-start 0 \
+        -I ${bam_file} \
+        -O raw.vcf.gz
     
     gatk FilterMutectCalls \
-    -R ${reference} \
-    --min-reads-per-strand 2 \
-    -V raw.vcf.gz \
-    -O ${bam_file.baseName}.vcf.gz
+        -R ${reference} \
+        --min-reads-per-strand 2 \
+        -V raw.vcf.gz \
+        -O ${bam_file.baseName}.vcf.gz
 
-    rm raw.vcf.gz
-    bcftools norm -m-any -f ${reference} ${bam_file.baseName}.vcf.gz -o ${bam_file.baseName}.norm.vcf.gz -Oz
+    bcftools norm \
+        -m-any \
+        -f ${reference} \
+        -o ${bam_file.baseName}.norm.vcf.gz -Oz \
+        ${bam_file.baseName}.vcf.gz 
+    
     mv ${bam_file.baseName}.norm.vcf.gz ${bam_file.baseName}.vcf.gz
 
     #required for mutect2-only mode!
-    echo -e "ID\tFilter\tPos\tRef\tVariant\tVariantLevel\tCoverage\tType" > ${bam_file.baseName}.txt
-    bcftools query -f '${bam_file}\t%FILTER\t%POS\t%REF\t%ALT\t[%AF\t%DP]\tMUTECT2\n' ${bam_file.baseName}.vcf.gz >> ${bam_file.baseName}.txt
+    echo -e "ID\tFilter\tPos\tRef\tVariant\tVariantLevel\tCoverage\tType" \
+        > ${bam_file.baseName}.txt
+    
+    bcftools query \
+        -f '${bam_file}\t%FILTER\t%POS\t%REF\t%ALT\t[%AF\t%DP]\tMUTECT2\n' \
+        ${bam_file.baseName}.vcf.gz >> ${bam_file.baseName}.txt
+    
+    rm raw.vcf.gz
     """
 }
diff --git a/modules/local/mutserve.nf b/modules/local/mutserve.nf
@@ -6,7 +6,7 @@ process MUTSERVE {
     path excluded_samples
 
     output:
-    path("${bam_file.baseName}.txt"), emit: mutserve_txt_ch
+    path("${bam_file.simpleName}.txt"), emit: mutserve_txt_ch
     tuple path("${bam_file.baseName}.vcf.gz"), val('mutserve_fusion'), emit: mutserve_fusion_vcf_ch
     path("${bam_file.baseName}.vcf.gz"), emit: mutserve_vcf_ch
     path("${bam_file.baseName}.vcf.gz.tbi"), emit: mutserve_vcf_idx_ch
@@ -30,7 +30,12 @@ process MUTSERVE {
         --write-raw \
         ${bam_file} 
 
-    bcftools norm -m-any -f ${reference} ${bam_file.baseName}.vcf.gz -o ${bam_file.baseName}.norm.vcf.gz -Oz
+    bcftools norm \
+        -m-any \
+        -f ${reference} \
+        -o ${bam_file.baseName}.norm.vcf.gz -Oz \
+        ${bam_file.baseName}.vcf.gz 
+    
     mv ${bam_file.baseName}.norm.vcf.gz ${bam_file.baseName}.vcf.gz
     tabix ${bam_file.baseName}.vcf.gz
     """

diff --git a/modules/local/quality_control.nf b/modules/local/quality_control.nf
@@ -1,12 +1,15 @@
 process QUALITY_CONTROL {
+
     publishDir "${params.output_reports}", mode: "copy", pattern: '*.html'
+
     input:
     path excluded_samples
     path zip
+
     output:
 	path "*.html"
 
 	"""
-	 multiqc . 
+	multiqc . 
 	"""
 }
diff --git a/tests/data/bam/HG00096.mapped.ILLUMINA.bwa.GBR.low_coverage.20101123_copy.bam b/tests/data/bam/HG00096.mapped.ILLUMINA.bwa.GBR.low_coverage.20101123_copy.bam
diff --git a/tests/mitocalling.nf.test b/tests/mitocalling.nf.test
@@ -18,7 +18,7 @@ nextflow_pipeline {
 
         then {
             assert workflow.success
-            assert snapshot(path("${launchDir}/out/variants_ann.txt")).match()
+            assert snapshot(path("${launchDir}/out/variants.annotated.txt")).match()
         }
 
     }
@@ -37,7 +37,7 @@ nextflow_pipeline {
         }
 
         then {
-            assert snapshot(path("${launchDir}/out/variants_ann.txt")).match()
+            assert snapshot(path("${launchDir}/out/variants.annotated.txt")).match()
         }
 
     }
@@ -57,8 +57,7 @@ nextflow_pipeline {
 
         then {
             assert workflow.success
-            //TODO: sort variants file by sample after merging to get a deterministic order
-            //assert snapshot(path("${launchDir}/out/variants_ann.txt")).match()
+            assert snapshot(path("${launchDir}/out/variants.annotated.txt")).match()
         }
 
     }

diff --git a/tests/mitocalling.nf.test.snap b/tests/mitocalling.nf.test.snap
@@ -1,14 +1,20 @@
 {
+    "Runs with single BAM file and mutect2": {
+        "content": [
+            "variants.annotated.txt:md5,94fa4b4d0613f61410618a7eba4c5c97"
+        ],
+        "timestamp": "2024-02-26T23:09:58.251860914"
+    },
     "Runs with single BAM file and mutserve": {
         "content": [
-            "variants_ann.txt:md5,1d8423fc3e89a12e226e5e4b89f60150"
+            "variants.annotated.txt:md5,21b561f9b05098cdc137f43b4988570e"
         ],
-        "timestamp": "2024-01-10T14:27:36.082310248"
+        "timestamp": "2024-02-26T23:02:15.242706827"
     },
     "Runs with BAM file including different header contigs": {
         "content": [
-            "variants_ann.txt:md5,c2aa6c45193a921f4a20238fe9bf6cd8"
+            "variants.annotated.txt:md5,d68e6fed173c766228164438a24ecf5a"
         ],
-        "timestamp": "2024-01-10T14:28:13.798945731"
+        "timestamp": "2024-02-26T23:03:07.470112898"
     }
 }