Merge pull request #17 from ramprasadn/gens

PON for gens

conf/modules/gens_pon.config

@@ -0,0 +1,64 @@
+/*
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Config file for defining DSL2 per module options and publishing paths
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+    Available keys to override module options:
+        ext.args   = Additional arguments appended to command in module.
+        ext.args2  = Second set of arguments appended to command in module (multi-tool modules).
+        ext.args3  = Third set of arguments appended to command in module (multi-tool modules).
+        ext.prefix = File name prefix for output files.
+----------------------------------------------------------------------------------------
+*/
+
+process {
+
+    withName: '.*GENS_PON.*' {
+        publishDir = [
+            enabled: false
+        ]
+    }
+
+    withName: '.*GENS_PON:SAMTOOLS_FAIDX' {
+        ext.when = { params.fai.equals(null) }
+        publishDir = [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/gens_pon/references" },
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: '.*GENS_PON:PICARD_CREATESEQUENCEDICTIONARY' {
+        ext.when = { params.dict.equals(null) }
+        publishDir = [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/gens_pon/references" },
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: '.*GENS_PON:GATK4_PREPROCESSINTERVALS' {
+        ext.args = { ["--imr OVERLAPPING_ONLY",
+                        "--bin-length ${params.gens_bin_length}"].join(" ")
+                    }
+    }
+
+    withName: '.*GENS_PON:GATK4_COLLECTREADCOUNTS' {
+        ext.args = {"--format ${params.gens_readcount_format} --imr OVERLAPPING_ONLY"}
+        publishDir = [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/gens_pon/readcounts" },
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+    withName: '.*GENS_PON:GATK4_CREATEREADCOUNTPANELOFNORMALS' {
+        ext.args   = { ["--minimum-interval-median-percentile 10.0",
+                        "--maximum-chunk-size 29349635"].join(" ")}
+        publishDir = [
+                mode: params.publish_dir_mode,
+                path: { "${params.outdir}/gens_pon/createreadcountpanelofnormals" },
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
+}

conf/modules/germlinecnvcaller_cohort.config

@@ -46,8 +46,8 @@ process {
 
     withName: '.*GERMLINECNVCALLER_COHORT:GATK4_PREPROCESSINTERVALS' {
         ext.args = { ["--imr OVERLAPPING_ONLY",
-                        "--padding ${params.padding}",
-                        "--bin-length ${params.bin_length}"].join(" ")
+                        "--padding ${params.gcnv_padding}",
+                        "--bin-length ${params.gcnv_bin_length}"].join(" ")
                     }
     }
 
@@ -71,7 +71,7 @@ process {
     }
 
     withName: '.*GERMLINECNVCALLER_COHORT:GATK4_INTERVALLISTTOOLS' {
-        ext.args   = {"--SUBDIVISION_MODE INTERVAL_COUNT --SCATTER_CONTENT ${params.scatter_content}"}
+        ext.args   = {"--SUBDIVISION_MODE INTERVAL_COUNT --SCATTER_CONTENT ${params.gcnv_scatter_content}"}
     }
 
     withName: '.*GERMLINECNVCALLER_COHORT:GATK4_DETERMINEGERMLINECONTIGPLOIDY' {

conf/test.config

@@ -26,8 +26,8 @@ params {
     tools = 'cnvkit'
 
     //Germlinecnvcaller options
-    scatter_content = 2
-    ploidy_priors     = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/gatk/contig_ploidy_priors_table.tsv"
+    gcnv_scatter_content = 2
+    gcnv_ploidy_priors   = "https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/illumina/gatk/contig_ploidy_priors_table.tsv"
 
     // Small reference genome
     genome            = null

docs/usage.md

@@ -107,25 +107,6 @@ If you wish to share such profile (such as upload as supplementary material for
 
 ## Workflow specific arguments
 
-### germlinecnvcaller
-
-If you are running the pipeline to generate references for the GATK's germlinecnvcalling workflow, you should ensure that you have provided all the mandatory options specified in the table below.
-
-| Mandatory                 | Optional                          |
-| ------------------------- | --------------------------------- |
-| fasta/genomes             | fai                               |
-| ploidy_priors<sup>1</sup> | dict                              |
-|                           | target_bed/target_interval_list   |
-|                           | exclude_bed/exclude_interval_list |
-|                           | bin_length                        |
-|                           | mappable_regions                  |
-|                           | padding                           |
-|                           | readcount_format                  |
-|                           | scatter_content                   |
-|                           | segmental_duplications            |
-
-<sup>1</sup> To learn more about this file, see [this comment](https://gatk.broadinstitute.org/hc/en-us/community/posts/360074399831/comments/13441240230299) on GATK forum.<br />
-
 ### cnvkit
 
 If you are running the pipeline to generate references for the CNVkit variant calling workflow, you should consider that currently the default method for this pipeline is whole-genome. In order to use the CNVkit default, i.e. hybrid capture, when the user is creating a background for targeted capture sequencing (most commonly, exomes or panels), the user should
@@ -144,6 +125,36 @@ process {
 
 2. provide the `--cnvkit_target` parameter (optional) as a .bed file for the targets
 
+### gens
+
+If you are running the pipeline to generate references for the gens workflow, you should ensure that you have provided all the mandatory options specified in the table below.
+
+| Mandatory     | Optional              |
+| ------------- | --------------------- |
+| fasta/genomes | fai                   |
+|               | dict                  |
+|               | gens_bin_length       |
+|               | gens_readcount_format |
+
+### germlinecnvcaller
+
+If you are running the pipeline to generate references for the GATK's germlinecnvcalling workflow, you should ensure that you have provided all the mandatory options specified in the table below.
+
+| Mandatory                      | Optional                                    |
+| ------------------------------ | ------------------------------------------- |
+| fasta/genomes                  | fai                                         |
+| gcnv_ploidy_priors<sup>1</sup> | dict                                        |
+|                                | gcnv_target_bed/gcnv_target_interval_list   |
+|                                | gcnv_exclude_bed/gcnv_exclude_interval_list |
+|                                | gcnv_bin_length                             |
+|                                | gcnv_mappable_regions                       |
+|                                | gcnv_padding                                |
+|                                | gcnv_readcount_format                       |
+|                                | gcnv_scatter_content                        |
+|                                | gcnv_segmental_duplications                 |
+
+<sup>1</sup> To learn more about this file, see [this comment](https://gatk.broadinstitute.org/hc/en-us/community/posts/360074399831/comments/13441240230299) on GATK forum.<br />
+
 ## Core Nextflow arguments
 
 :::note

main.nf

@@ -30,13 +30,16 @@ include { getGenomeAttribute      } from './subworkflows/local/utils_nfcore_crea
 
 //   This is an example of how to use getGenomeAttribute() to fetch parameters
 //   from igenomes.config using `--genome`
-params.fasta                 = getGenomeAttribute('fasta')
-params.fai                   = getGenomeAttribute('fai')
-params.dict                  = getGenomeAttribute('dict')
-params.target_bed            = getGenomeAttribute('target_bed')
-params.target_interval_list  = getGenomeAttribute('target_interval_list')
-params.exclude_bed           = getGenomeAttribute('exclude_bed')
-params.exclude_interval_list = getGenomeAttribute('exclude_interval_list')
+params.fasta                       = getGenomeAttribute('fasta')
+params.fai                         = getGenomeAttribute('fai')
+params.dict                        = getGenomeAttribute('dict')
+params.gcnv_exclude_bed            = getGenomeAttribute('gcnv_exclude_bed')
+params.gcnv_exclude_interval_list  = getGenomeAttribute('gcnv_exclude_interval_list')
+params.gcnv_mappable_regions       = getGenomeAttribute('gcnv_mappable_regions')
+params.gcnv_target_bed             = getGenomeAttribute('gcnv_target_bed')
+params.gcnv_target_interval_list   = getGenomeAttribute('gcnv_target_interval_list')
+params.gcnv_ploidy_priors          = getGenomeAttribute('gcnv_ploidy_priors')
+params.gcnv_segmental_duplications = getGenomeAttribute('gcnv_segmental_duplications')
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~

modules.json

@@ -25,6 +25,11 @@
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
                         "installed_by": ["modules"]
                     },
+                    "gatk4/createreadcountpanelofnormals": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["modules"]
+                    },
                     "gatk4/determinegermlinecontigploidy": {
                         "branch": "master",
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",

nextflow.config

@@ -23,23 +23,25 @@ params {
     tools                      = null // No default, must be specified
 
     // Germlinecnvcaller options
-    analysis_type              = 'wgs'
-    bin_length                 = 1000
-    mappable_regions           = null
-    padding                    = 0
-    ploidy_priors              = null
-    readcount_format           = 'HDF5'
-    scatter_content            = 5000
-    segmental_duplications     = null
+    gcnv_analysis_type          = 'wgs'
+    gcnv_bin_length             = 1000
+    gcnv_padding                = 0
+    gcnv_readcount_format       = 'HDF5'
+    gcnv_scatter_content        = 5000
+    gcnv_segmental_duplications = null
+
+    // Gens options
+    gens_bin_length             = 100
+    gens_readcount_format       = 'HDF5'
 
     // CNVkit options
-    cnvkit_targets             = null
+    cnvkit_targets              = null
 
     // MultiQC options
-    multiqc_config             = null
-    multiqc_title              = null
-    multiqc_logo               = null
-    max_multiqc_email_size     = '25.MB'
+    multiqc_config              = null
+    multiqc_title               = null
+    multiqc_logo                = null
+    max_multiqc_email_size      = '25.MB'
     multiqc_methods_description = null
 
     // Boilerplate options
@@ -258,6 +260,7 @@ manifest {
 includeConfig 'conf/modules/base.config'
 includeConfig 'conf/modules/cnvkit.config'
 includeConfig 'conf/modules/germlinecnvcaller_cohort.config'
+includeConfig 'conf/modules/gens_pon.config'
 
 // Function to ensure that resource requirements don't go beyond
 // a maximum limit