Merge pull request #453 from genomic-medicine-sweden/add_sex_check

Add sex check
nf-core · Dec 18, 2023 · b366e66 · b366e66
2 parents b68c72e + 556e26f
commit b366e66
Show file tree

Hide file tree

Showing 12 changed files with 178 additions and 13 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -16,6 +16,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - New parameters to skip fastqc and haplocheck (`--skip_fastqc` and `--skip_haplocheck`) [#438](https://github.com/nf-core/raredisease/pull/438)
 - CNVnator for copy number variant calling [#438](https://github.com/nf-core/raredisease/pull/434)
 - A new parameter `svdb_query_bedpedbs` to provide bedpe files as databases for SVDB query [#449](https://github.com/nf-core/raredisease/pull/449)
+- ngsbits samplegender to check sex [#453] (https://github.com/nf-core/raredisease/pull/453)
 
 ### `Changed`
 

diff --git a/CITATIONS.md b/CITATIONS.md
@@ -80,6 +80,8 @@
 
   > Pedersen BS, Quinlan AR. Mosdepth: quick coverage calculation for genomes and exomes. Hancock J, ed. Bioinformatics. 2018;34(5):867-868. doi:10.1093/bioinformatics/btx699
 
+- [ngs-bits-samplegender](https://github.com/imgag/ngs-bits/tree/master)
+
 - [MultiQC](https://pubmed.ncbi.nlm.nih.gov/27312411/)
 
   > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.

diff --git a/conf/modules/qc_bam.config b/conf/modules/qc_bam.config
@@ -53,6 +53,17 @@ process {
         ext.prefix = { "${meta.id}_mosdepth" }
     }
 
+    withName: '.*QC_BAM:NGSBITS_SAMPLEGENDER' {
+        //  NGSBITS_SAMPLEGENDER needs a chrX and chrY in order to run so we skip it for the two test profiles
+        ext.when = { !(workflow.profile.tokenize(',').intersect(['test', 'test_one_sample', 'test_sentieon']).size() >= 1) || workflow.stubRun }
+        ext.prefix = { "${meta.id}_ngsbits_sex" }
+        publishDir = [
+            path: { "${params.outdir}/ngsbits_samplegender" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+        ]
+    }
+
     withName: '.*QC_BAM:PICARD_COLLECTWGSMETRICS' {
         ext.when = { params.analysis_type.equals("wgs") && params.aligner.equals("bwamem2") }
         ext.prefix = { "${meta.id}_wgsmetrics" }

diff --git a/main.nf b/main.nf
@@ -35,6 +35,7 @@ params.known_dbsnp                    = WorkflowMain.getGenomeAttribute(params,
 params.known_dbsnp_tbi                = WorkflowMain.getGenomeAttribute(params, 'known_dbsnp_tbi')
 params.ml_model                       = WorkflowMain.getGenomeAttribute(params, 'ml_model')
 params.mt_fasta                       = WorkflowMain.getGenomeAttribute(params, 'mt_fasta')
+params.ngsbits_samplegender_method    = WorkflowMain.getGenomeAttribute(params, 'ngsbits_samplegender_method')
 params.ploidy_model                   = WorkflowMain.getGenomeAttribute(params, 'ploidy_model')
 params.reduced_penetrance             = WorkflowMain.getGenomeAttribute(params, 'reduced_penetrance')
 params.readcount_intervals            = WorkflowMain.getGenomeAttribute(params, 'readcount_intervals')

diff --git a/modules.json b/modules.json
@@ -277,6 +277,11 @@
                         "git_sha": "a6e11ac655e744f7ebc724be669dd568ffdc0e80",
                         "installed_by": ["modules"]
                     },
+                    "ngsbits/samplegender": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["modules"]
+                    },
                     "peddy": {
                         "branch": "master",
                         "git_sha": "911696ea0b62df80e900ef244d7867d177971f73",

diff --git a/modules/nf-core/ngsbits/samplegender/environment.yml b/modules/nf-core/ngsbits/samplegender/environment.yml
diff --git a/modules/nf-core/ngsbits/samplegender/main.nf b/modules/nf-core/ngsbits/samplegender/main.nf
diff --git a/modules/nf-core/ngsbits/samplegender/meta.yml b/modules/nf-core/ngsbits/samplegender/meta.yml
diff --git a/nextflow.config b/nextflow.config
@@ -10,7 +10,7 @@
 params {
 
     // Required options
-    input                      = null
+    input                       = null
 
     // References
     genome                     = 'GRCh38'
@@ -37,6 +37,9 @@ params {
     cadd_resources             = null
     platform                   = 'illumina'
 
+    // Bam_qc
+    ngsbits_samplegender_method = 'xy'
+
     // File params
     svdb_query_bedpedbs        = null
     svdb_query_dbs             = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -386,6 +386,13 @@
                     "fa_icon": "fas fa-align-center",
                     "enum": ["illumina"]
                 },
+                "ngsbits_samplegender_method": {
+                    "type": "string",
+                    "default": "xy",
+                    "enum": ["xy", "hetx", "sry"],
+                    "description": "Method selection for ngs-bits samplegender",
+                    "fa_icon": "fas fa-align-center"
+                },
                 "save_mapped_as_cram": {
                     "type": "boolean",
                     "description": "Specifies whether to generate and publish alignment files as cram instead of bam",
@@ -473,7 +480,7 @@
                 "cnvnator_binsize": {
                     "type": "number",
                     "description": "Bin size for CNVnator",
-                    "default": "1000",
+                    "default": 1000,
                     "fa_icon": "fas fa-align-center"
                 },
                 "sentieon_dnascope_pcr_indel_model": {

diff --git a/subworkflows/local/qc_bam.nf b/subworkflows/local/qc_bam.nf
@@ -12,20 +12,22 @@ include { PICARD_COLLECTWGSMETRICS as PICARD_COLLECTWGSMETRICS   } from '../../m
 include { PICARD_COLLECTWGSMETRICS as PICARD_COLLECTWGSMETRICS_Y } from '../../modules/nf-core/picard/collectwgsmetrics/main'
 include { SENTIEON_WGSMETRICS                                                        } from '../../modules/nf-core/sentieon/wgsmetrics/main'
 include { SENTIEON_WGSMETRICS as SENTIEON_WGSMETRICS_Y           } from '../../modules/nf-core/sentieon/wgsmetrics/main'
+include { NGSBITS_SAMPLEGENDER                                   } from '../../modules/nf-core/ngsbits/samplegender/main'
 
 workflow QC_BAM {
 
     take:
-        ch_bam              // channel: [mandatory] [ val(meta), path(bam) ]
-        ch_bai              // channel: [mandatory] [ val(meta), path(bai) ]
-        ch_bam_bai          // channel: [mandatory] [ val(meta), path(bam), path(bai) ]
-        ch_genome_fasta     // channel: [mandatory] [ val(meta), path(fasta) ]
-        ch_genome_fai       // channel: [mandatory] [ val(meta), path(fai) ]
-        ch_bait_intervals   // channel: [mandatory] [ path(intervals_list) ]
-        ch_target_intervals // channel: [mandatory] [ path(intervals_list) ]
-        ch_chrom_sizes      // channel: [mandatory] [ path(sizes) ]
-        ch_intervals_wgs    // channel: [mandatory] [ path(intervals) ]
-        ch_intervals_y      // channel: [mandatory] [ path(intervals) ]
+        ch_bam                      // channel: [mandatory] [ val(meta), path(bam) ]
+        ch_bai                      // channel: [mandatory] [ val(meta), path(bai) ]
+        ch_bam_bai                  // channel: [mandatory] [ val(meta), path(bam), path(bai) ]
+        ch_genome_fasta             // channel: [mandatory] [ val(meta), path(fasta) ]
+        ch_genome_fai               // channel: [mandatory] [ val(meta), path(fai) ]
+        ch_bait_intervals           // channel: [mandatory] [ path(intervals_list) ]
+        ch_target_intervals         // channel: [mandatory] [ path(intervals_list) ]
+        ch_chrom_sizes              // channel: [mandatory] [ path(sizes) ]
+        ch_intervals_wgs            // channel: [mandatory] [ path(intervals) ]
+        ch_intervals_y              // channel: [mandatory] [ path(intervals) ]
+        ngsbits_samplegender_method // channel [val(method)]
 
     main:
         ch_versions = Channel.empty()
@@ -59,6 +61,9 @@ workflow QC_BAM {
         SENTIEON_WGSMETRICS ( ch_bam_bai, ch_genome_fasta, ch_genome_fai, ch_intervals_wgs.map{ interval -> [[:], interval]} )
         SENTIEON_WGSMETRICS_Y ( ch_bam_bai, ch_genome_fasta, ch_genome_fai, ch_intervals_y.map{ interval -> [[:], interval]} )
 
+        // Check sex
+        NGSBITS_SAMPLEGENDER(ch_bam_bai, ch_genome_fasta, ch_genome_fai, ngsbits_samplegender_method)
+
         ch_cov   = Channel.empty().mix(PICARD_COLLECTWGSMETRICS.out.metrics, SENTIEON_WGSMETRICS.out.wgs_metrics)
         ch_cov_y = Channel.empty().mix(PICARD_COLLECTWGSMETRICS_Y.out.metrics, SENTIEON_WGSMETRICS_Y.out.wgs_metrics)
 
@@ -67,6 +72,7 @@ workflow QC_BAM {
         ch_versions = ch_versions.mix(TIDDIT_COV.out.versions.first())
         ch_versions = ch_versions.mix(UCSC_WIGTOBIGWIG.out.versions.first())
         ch_versions = ch_versions.mix(MOSDEPTH.out.versions.first())
+        ch_versions = ch_versions.mix(NGSBITS_SAMPLEGENDER.out.versions.first())
         ch_versions = ch_versions.mix(PICARD_COLLECTWGSMETRICS.out.versions.first(), SENTIEON_WGSMETRICS.out.versions.first())
         ch_versions = ch_versions.mix(PICARD_COLLECTWGSMETRICS_Y.out.versions.first(), SENTIEON_WGSMETRICS_Y.out.versions.first())
 
@@ -78,6 +84,7 @@ workflow QC_BAM {
         bigwig           = UCSC_WIGTOBIGWIG.out.bw                   // channel: [ val(meta), path(bw) ]
         d4               = MOSDEPTH.out.per_base_d4                  // channel: [ val(meta), path(d4) ]
         global_dist      = MOSDEPTH.out.global_txt                   // channel: [ val(meta), path(txt) ]
+        sex_check        = NGSBITS_SAMPLEGENDER.out.tsv              // channel: [val(meta), path(tsv) ]
         cov              = ch_cov                                    // channel: [ val(meta), path(metrics) ]
         cov_y            = ch_cov_y                                  // channel: [ val(meta), path(metrics) ]
         versions         = ch_versions                               // channel: [ path(versions.yml) ]

diff --git a/workflows/raredisease.nf b/workflows/raredisease.nf
@@ -339,7 +339,8 @@ workflow RAREDISEASE {
         ch_target_intervals,
         ch_genome_chrsizes,
         ch_intervals_wgs,
-        ch_intervals_y
+        ch_intervals_y,
+        Channel.value(params.ngsbits_samplegender_method)
     )
     ch_versions = ch_versions.mix(QC_BAM.out.versions)