Merge pull request #2 from jfy133/upstream-for-indel

Upstream

modules/bamtools/convert/meta.yml

@@ -42,7 +42,6 @@ output:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  ## TODO nf-core: Delete / customise this example output
   - out:
       type: file
       description: The data in the asked format (bed, fasta, fastq, json, pileup, sam, yaml)

modules/bcftools/concat/main.nf

@@ -8,7 +8,7 @@ process BCFTOOLS_CONCAT {
         'quay.io/biocontainers/bcftools:1.14--h88f3f91_0' }"
 
     input:
-    tuple val(meta), path(vcfs)
+    tuple val(meta), path(vcfs), path(tbi)
 
     output:
     tuple val(meta), path("*.gz"), emit: vcf

modules/bcftools/concat/meta.yml

@@ -25,6 +25,11 @@ input:
       description: |
         List containing 2 or more vcf files
         e.g. [ 'file1.vcf', 'file2.vcf' ]
+  - tbi:
+      type: files
+      description: |
+        List containing 2 or more index files (optional)
+        e.g. [ 'file1.tbi', 'file2.tbi' ]
 output:
   - meta:
       type: map

modules/bcftools/roh/main.nf

@@ -9,7 +9,7 @@ process BCFTOOLS_ROH {
 
     input:
     tuple val(meta), path(vcf), path(tbi)
-    path af_file
+    tuple path(af_file), path(af_file_tbi)
     path genetic_map
     path regions_file
     path samples_file

modules/bcftools/roh/meta.yml

@@ -23,6 +23,9 @@ input:
   - af_file:
       type: file
       description: "Read allele frequencies from a tab-delimited file containing the columns: CHROM\tPOS\tREF,ALT\tAF."
+  - af_file_tbi:
+      type: file
+      description: "tbi index of af_file."
   - genetic_map:
       type: file
       description: "Genetic map in the format required also by IMPUTE2."

modules/cnvkit/batch/main.nf

@@ -10,6 +10,7 @@ process CNVKIT_BATCH {
     input:
     tuple val(meta), path(tumor), path(normal)
     path  fasta
+    path  fasta_fai
     path  targets
     path  reference
 
@@ -28,48 +29,167 @@ process CNVKIT_BATCH {
     script:
     def args = task.ext.args ?: ''
 
+    def tumor_exists = tumor ? true : false
+    def normal_exists = normal ? true : false
+
     // execute samtools only when cram files are input, cnvkit runs natively on bam but is prohibitively slow
-    // input pair is assumed to have same extension if both exist
-    def is_cram = tumor.Extension == "cram" ? true : false
-    def tumor_out = is_cram ? tumor.BaseName + ".bam" : "${tumor}"
+    def tumor_cram = tumor_exists && tumor.Extension == "cram" ? true : false
+    def normal_cram = normal_exists && normal.Extension == "cram" ? true : false
+    def tumor_bam = tumor_exists && tumor.Extension == "bam" ? true : false
+    def normal_bam = normal_exists && normal.Extension == "bam" ? true : false
+
+    def tumor_out = tumor_cram ? tumor.BaseName + ".bam" : "${tumor}"
 
-    // do not run samtools on normal samples in tumor_only mode
-    def normal_exists = normal ? true: false
     // tumor_only mode does not need fasta & target
     // instead it requires a pre-computed reference.cnn which is built from fasta & target
     def (normal_out, normal_args, fasta_args) = ["", "", ""]
+    def fai_reference = fasta_fai ? "--fai-reference ${fasta_fai}" : ""
 
     if (normal_exists){
         def normal_prefix = normal.BaseName
-        normal_out = is_cram ? "${normal_prefix}" + ".bam" : "${normal}"
-        normal_args = normal_prefix ? "--normal $normal_out" : ""
+        normal_out = normal_cram ? "${normal_prefix}" + ".bam" : "${normal}"
         fasta_args = fasta ? "--fasta $fasta" : ""
+
+        // germline mode
+        // normal samples must be input without a flag
+        // requires flag --normal to be empty []
+        if(!tumor_exists){
+            tumor_out = "${normal_prefix}" + ".bam"
+            normal_args = "--normal "
+        }
+        // somatic mode
+        else {
+            normal_args = normal_prefix ? "--normal $normal_out" : ""
+        }
     }
 
     def target_args = targets ? "--targets $targets" : ""
     def reference_args = reference ? "--reference $reference" : ""
 
-    """
-    if $is_cram; then
-        samtools view -T $fasta $tumor -@ $task.cpus -o $tumor_out
-        if $normal_exists; then
-            samtools view -T $fasta $normal -@ $task.cpus -o $normal_out
-        fi
-    fi
-
-    cnvkit.py \\
-        batch \\
-        $tumor_out \\
-        $normal_args \\
-        $fasta_args \\
-        $reference_args \\
-        $target_args \\
-        --processes $task.cpus \\
-        $args
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
-    END_VERSIONS
-    """
+    // somatic_mode cram_input
+    if (tumor_cram && normal_cram){
+        """
+        samtools view -T $fasta $fai_reference $tumor -@ $task.cpus -o $tumor_out
+        samtools view -T $fasta $fai_reference $normal -@ $task.cpus -o $normal_out
+
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // somatic_mode bam_input
+    else if (tumor_bam && normal_bam){
+        """
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // tumor_only_mode cram_input
+    else if(tumor_cram && !normal_exists){
+        """
+        samtools view -T $fasta $fai_reference $tumor -@ $task.cpus -o $tumor_out
+
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // tumor_only bam_input
+    else if(tumor_bam && !normal_exists){
+        """
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // germline mode cram_input
+    // normal_args must be --normal []
+    else if (normal_cram && !tumor_exists){
+        """
+        samtools view -T $fasta $fai_reference $normal -@ $task.cpus -o $tumor_out
+
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+    // germline mode bam_input
+    else if (normal_bam && !tumor_exists){
+        """
+        cnvkit.py \\
+            batch \\
+            $tumor_out \\
+            $normal_args \\
+            $fasta_args \\
+            $reference_args \\
+            $target_args \\
+            --processes $task.cpus \\
+            $args
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            cnvkit: \$(cnvkit.py version | sed -e "s/cnvkit v//g")
+        END_VERSIONS
+        """
+    }
+
 }

modules/cnvkit/batch/meta.yml

@@ -29,6 +29,10 @@ input:
       type: file
       description: |
         Input reference genome fasta file (only needed for cram_input and/or when normal_samples are provided)
+  - fasta_fai:
+      type: file
+      description: |
+        Input reference genome fasta index (optional, but recommended for cram_input)
   - targetfile:
       type: file
       description: |

modules/deeptools/bamcoverage/main.nf

@@ -2,13 +2,15 @@ process DEEPTOOLS_BAMCOVERAGE {
     tag "$meta.id"
     label 'process_low'
 
-    conda (params.enable_conda ? "bioconda::deeptools=3.5.1" : null)
+    conda (params.enable_conda ? "bioconda::deeptools=3.5.1 bioconda::samtools=1.15.1" : null)
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/deeptools:3.5.1--py_0':
-        'quay.io/biocontainers/deeptools:3.5.1--py_0' }"
+        'https://depot.galaxyproject.org/singularity/mulled-v2-eb9e7907c7a753917c1e4d7a64384c047429618a:2c687053c0252667cca265c9f4118f2c205a604c-0':
+        'quay.io/biocontainers/mulled-v2-eb9e7907c7a753917c1e4d7a64384c047429618a:2c687053c0252667cca265c9f4118f2c205a604c-0' }"
 
     input:
     tuple val(meta), path(input), path(input_index)
+    path(fasta)
+    path(fasta_fai)
 
     output:
     tuple val(meta), path("*.bigWig")   , emit: bigwig, optional: true
@@ -22,16 +24,44 @@ process DEEPTOOLS_BAMCOVERAGE {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}.bigWig"
 
-    """
-    bamCoverage \\
-        --bam $input \\
-        $args \\
-        --numberOfProcessors ${task.cpus} \\
-        --outFileName ${prefix}
-
-    cat <<-END_VERSIONS > versions.yml
-    "${task.process}":
-        deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
-    END_VERSIONS
-    """
+    // cram_input is currently not working with deeptools
+    // therefore it's required to convert cram to bam first
+    def is_cram = input.Extension == "cram" ? true : false
+    def input_out = is_cram ? input.BaseName + ".bam" : "${input}"
+    def fai_reference = fasta_fai ? "--fai-reference ${fasta_fai}" : ""
+
+    if (is_cram){
+        """
+        samtools view -T $fasta $input $fai_reference -@ $task.cpus -o $input_out
+        samtools index -b $input_out -@ $task.cpus
+
+        bamCoverage \\
+            --bam $input_out \\
+            $args \\
+            --numberOfProcessors ${task.cpus} \\
+            --outFileName ${prefix}
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+            deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
+        END_VERSIONS
+        """
+
+    }
+    else {
+        """
+        bamCoverage \\
+            --bam $input_out \\
+            $args \\
+            --numberOfProcessors ${task.cpus} \\
+            --outFileName ${prefix}
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            deeptools: \$(bamCoverage --version | sed -e "s/bamCoverage //g")
+        END_VERSIONS
+        """
+    }
+
 }

modules/deeptools/bamcoverage/meta.yml

@@ -25,6 +25,14 @@ input:
       type: file
       description: BAM/CRAM index file
       pattern: "*.{bai,crai}"
+  - fasta:
+      type: file
+      description: Reference file the CRAM file was created with (required with CRAM input)
+      pattern: "*.{fasta,fa}"
+  - fasta_fai:
+      type: file
+      description: Index of the reference file (optional, but recommended)
+      pattern: "*.{fai}"
 
 output:
   - meta:
@@ -47,3 +55,4 @@ output:
 
 authors:
   - "@FriederikeHanssen"
+  - "@SusiJo"

modules/ensemblvep/Dockerfile

@@ -11,8 +11,8 @@ RUN conda env create -f /environment.yml && conda clean -a
 # Setup default ARG variables
 ARG GENOME=GRCh38
 ARG SPECIES=homo_sapiens
-ARG VEP_VERSION=104
-ARG VEP_TAG=104.3
+ARG VEP_VERSION=105
+ARG VEP_TAG=105.0
 
 # Add conda installation dir to PATH (instead of doing 'conda activate')
 ENV PATH /opt/conda/envs/nf-core-vep-${VEP_TAG}/bin:$PATH

modules/ensemblvep/build.sh

@@ -20,9 +20,9 @@ build_push() {
     docker push nfcore/vep:${VEP_TAG}.${GENOME}
 }
 
-build_push "GRCh37"    "homo_sapiens"           "104" "104.3"
-build_push "GRCh38"    "homo_sapiens"           "104" "104.3"
-build_push "GRCm38"    "mus_musculus"           "102" "104.3"
-build_push "GRCm39"    "mus_musculus"           "104" "104.3"
-build_push "CanFam3.1" "canis_lupus_familiaris" "104" "104.3"
-build_push "WBcel235"  "caenorhabditis_elegans" "104" "104.3"
+build_push "GRCh37"    "homo_sapiens"           "105" "105.0"
+build_push "GRCh38"    "homo_sapiens"           "105" "105.0"
+build_push "GRCm38"    "mus_musculus"           "102" "105.0"
+build_push "GRCm39"    "mus_musculus"           "105" "105.0"
+build_push "CanFam3.1" "canis_lupus_familiaris" "104" "105.0"
+build_push "WBcel235"  "caenorhabditis_elegans" "105" "105.0"