Merge pull request #12 from MaxUlysse/dev

Add some modules

tools/bwa/index/main.nf

@@ -0,0 +1,16 @@
+process bwa_index {
+    tag {fasta}
+
+    container 'quay.io/biocontainers/bwa:0.7.17--hed695b0_7'
+
+    input:
+        path(fasta)
+
+    output:
+        path("${fasta}.*")
+
+    script:
+    """
+    bwa index ${fasta}
+    """
+}

tools/bwa/index/meta.yml

@@ -0,0 +1,25 @@
+name: bwa index
+description: create indexes for BWA from a fasta file
+keywords:
+    - index
+tools:
+    - bwa:
+        description: |
+            BWA is a software package for mapping DNA sequences against a large reference genome, such as the human genome.
+        homepage: http://bio-bwa.sourceforge.net/
+        documentation: http://www.htslib.org/doc/samtools.html
+        arxiv: arXiv:1303.3997
+input:
+    -
+        - input:
+            type: file
+            description: Input fasta file
+            pattern: *.{fasta,fa}
+output:
+    -
+        - index:
+            type: file
+            description: bwa indexes file
+            pattern: *.{fasta,fa}.{amb,ann,bwt,pac,sa}
+authors:
+    - @maxulysse

tools/bwa/index/test/main.nf

@@ -0,0 +1,16 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl = 2
+include '../../../nf-core/module_testing/check_process_outputs.nf' params(params)
+include '../main.nf' params(params)
+
+// Define input channels
+input = '../../../test-datasets/tools/bwa/index/input/reference.fasta'
+Channel
+  .from(input)
+  .set { ch_input }
+
+// Run the workflow
+workflow {
+    fastqc(ch_input)
+    // .check_output()
+}

tools/bwa/index/test/nextflow.config

@@ -0,0 +1,2 @@
+docker.enabled = true
+params.outdir = './results'

tools/gatk/dict/main.nf

@@ -0,0 +1,19 @@
+process gatk_dict {
+    tag {fasta}
+
+    container 'quay.io/biocontainers/gatk4-spark:4.1.4.1--1'
+
+    input:
+        path(fasta)
+
+    output:
+        path("${fasta.baseName}.dict")
+
+    script:
+    """
+    gatk --java-options "-Xmx${task.memory.toGiga()}g" \
+        CreateSequenceDictionary \
+        --REFERENCE ${fasta} \
+        --OUTPUT ${fasta.baseName}.dict
+    """
+}

tools/gatk/dict/meta.yml

@@ -0,0 +1,25 @@
+name: gatk dict
+description: create a dictionary file from a fasta file
+keywords:
+    - dictionary
+tools:
+    - gatk:
+        description: |
+            The GATK toolkit offers a wide variety of tools with a primary focus on variant discovery and genotyping, developed in the Data Sciences Platform at the Broad Institute.
+        homepage: https://gatk.broadinstitute.org/hc/en-us
+        documentation: https://gatk.broadinstitute.org/hc/en-us/categories/360002369672s
+        doi: 10.1158/1538-7445.AM2017-3590
+input:
+    -
+        - input:
+            type: file
+            description: Input fasta file
+            pattern: *.{fasta,fa}
+output:
+    -
+        - dict:
+            type: file
+            description: gatk dictionary file
+            pattern: *.{fasta,fa}.{dict}
+authors:
+    - @maxulysse

tools/gatk/dict/test/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl = 2
+include '../../../nf-core/module_testing/check_process_outputs.nf' params(params)
+include '../main.nf' params(params)
+
+// Define input channels
+input = '../../../test-datasets/tools/bwa/index/input/reference.fasta'
+
+// Run the workflow
+workflow {
+    gatk_dict(input)
+    // .check_output()
+}

tools/gatk/dict/test/nextflow.config

@@ -0,0 +1,2 @@
+docker.enabled = true
+params.outdir = './results'

tools/htslib/tabix/main.nf

@@ -0,0 +1,16 @@
+process htslib_tabix {
+    tag {vcf}
+
+    container 'quay.io/biocontainers/tabix:0.2.6--ha92aebf_0'
+
+    input:
+        path(vcf)
+
+    output:
+        path("${vcf}.tbi")
+
+    script:
+    """
+    tabix -p vcf ${vcf}
+    """
+}

tools/htslib/tabix/meta.yml

@@ -0,0 +1,26 @@
+name: htslib tabix
+description: create tabix index from a bgzip vcf file
+keywords:
+    - index
+    - tabix
+tools:
+    - bwa:
+        description: |
+            Generic indexer for TAB-delimited genome position files.
+        homepage: https://www.htslib.org/
+        documentation: https://www.htslib.org/doc/tabix.1.html
+        doi: 10.1093/bioinformatics/btq671
+input:
+    -
+        - input:
+            type: file
+            description: Input vcf.gz file
+            pattern: *.{vcf.gz}
+output:
+    -
+        - index:
+            type: file
+            description: tabix index file
+            pattern: *.{vcf.gz.tbi}
+authors:
+    - @maxulysse

tools/htslib/tabix/test/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl = 2
+include '../../../nf-core/module_testing/check_process_outputs.nf' params(params)
+include '../main.nf' params(params)
+
+// Define input channels
+input = '../../../test-datasets/tools/file.vcf.gz'
+
+// Run the workflow
+workflow {
+    tabix_index(ch_read_files)
+    // .check_output()
+}

tools/htslib/tabix/test/nextflow.config

@@ -0,0 +1,2 @@
+docker.enabled = true
+params.outdir = './results'

tools/samtools/faidx/main.nf

@@ -0,0 +1,16 @@
+process samtools_faidx {
+    tag {fasta}
+
+    container 'quay.io/biocontainers/samtools:1.9--h10a08f8_12'
+
+    input:
+        path(fasta)
+
+    output:
+        path("${fasta}.fai")
+
+    script:
+    """
+    samtools faidx ${fasta}
+    """
+}

tools/samtools/faidx/meta.yml

@@ -0,0 +1,27 @@
+name: samtools faidx
+description: index a fasta file
+keywords:
+    - faidx
+tools:
+    - samtools:
+        description: |
+            SAMtools is a set of utilities for interacting with and post-processing
+            short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+            These files are generated as output by short read aligners like BWA.
+        homepage: http://www.htslib.org/
+        documentation: hhttp://www.htslib.org/doc/samtools.html
+        doi: 10.1093/bioinformatics/btp352
+input:
+    -
+        - input:
+            type: file
+            description: Input fasta file
+            pattern: *.{fasta,fa}
+output:
+    -
+        - faidx:
+            type: file
+            description: samtools index fasta file
+            pattern: *.fasta.fai
+authors:
+    - @maxulysse

tools/samtools/faidx/test/main.nf

@@ -0,0 +1,13 @@
+#!/usr/bin/env nextflow
+nextflow.preview.dsl = 2
+include '../../../nf-core/module_testing/check_process_outputs.nf' params(params)
+include '../main.nf' params(params)
+
+// Define input channels
+input = '../../../test-datasets/tools/bwa/index/input/reference.fasta'
+
+// Run the workflow
+workflow {
+    samtools_faidx(input)
+    // .check_output()
+}

tools/samtools/faidx/test/nextflow.config

@@ -0,0 +1,2 @@
+docker.enabled = true
+params.outdir = './results'

tools/samtools/index/main.nf

@@ -7,15 +7,14 @@ process samtools_index {
     path(bam)
 
     output:
-    path "*.sorted.bam"
+    path "*.bai"
 
     script:
     def suff_mem = ("${(task.memory.toBytes() - 6000000000) / task.cpus}" > 2000000000) ? 'true' : 'false'
     def avail_mem = (task.memory && suff_mem) ? "-m" + "${(task.memory.toBytes() - 6000000000) / task.cpus}" : ''
     """
-    samtools sort $bam \\
-        -@ ${task.cpus} ${avail_mem} \\
-        -o ${bam.baseName}.sorted.bam
+    samtools index $bam \\
+        -@ ${task.cpus} ${avail_mem}
 
     samtools --version &> v_samtools.txt
     """

tools/samtools/index/meta.yml

@@ -1,7 +1,7 @@
-name: samtools sort
-description: Sort a BAM or CRAM file
+name: samtools index
+description: index a BAM or CRAM file
 keywords:
-    - sort
+    - index
 tools:
     - samtools:
         description: |