Add NGSCheckMate

CHANGELOG.md

@@ -25,11 +25,29 @@ Special thanks to the following for their contributions to the release:
 
 ### Enhancements & fixes
 
+- [PR #993](https://github.com/nf-core/rnaseq/pull/993) Added NGSCheckMate for checking that samples come from the same individual
 - [PR #1123](https://github.com/nf-core/rnaseq/pull/1123) - Overhaul tximport.r, output length tables
 - [PR #1124](https://github.com/nf-core/rnaseq/pull/1124) - Ensure pseudoaligner is set if pseudoalignment is not skipped
 - [PR #1126](https://github.com/nf-core/rnaseq/pull/1126) - Pipeline fails if transcript_fasta not provided and `skip_gtf_filter = true`.
 - [PR #1127](https://github.com/nf-core/rnaseq/pull/1127) - Enlarge sampling to determine the number of columns in `filter_gtf.py` script.
 
+### Parameters
+
+| Old parameter | New parameter        |
+| ------------- | -------------------- |
+|               | `--ngscheckmate_bed` |
+
+> **NB:** Parameter has been **updated** if both old and new parameter information is present.
+> **NB:** Parameter has been **added** if just the new parameter information is present.
+> **NB:** Parameter has been **removed** if new parameter information isn't present.
+
+### Software dependencies
+
+| Dependency     | Old version | New version |
+| -------------- | ----------- | ----------- |
+| `bcftools`     |             | 1.17        |
+| `ngscheckmate` |             | 1.0.1       |
+
 ## [[3.13.1](https://github.com/nf-core/rnaseq/releases/tag/3.13.1)] - 2023-11-17
 
 ### Enhancements and fixes

conf/igenomes.config

@@ -12,29 +12,31 @@ params {
     // illumina iGenomes reference file paths
     genomes {
         'GRCh37' {
-            fasta       = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa"
-            bwa         = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/"
-            bowtie2     = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/"
-            star        = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/"
-            bismark     = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/"
-            gtf         = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf"
-            bed12       = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed"
-            readme      = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt"
-            mito_name   = "MT"
-            macs_gsize  = "2.7e9"
-            blacklist   = "${projectDir}/assets/blacklists/GRCh37-blacklist.bed"
+            fasta            = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa"
+            bwa              = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/"
+            bowtie2          = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/"
+            star             = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/"
+            bismark          = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/"
+            gtf              = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf"
+            bed12            = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed"
+            ngscheckmate_bed = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh37/Annotation/NGSCheckMate/SNP_GRCh37_hg19_wChr.bed"
+            readme           = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt"
+            mito_name        = "MT"
+            macs_gsize       = "2.7e9"
+            blacklist        = "${projectDir}/assets/blacklists/GRCh37-blacklist.bed"
         }
         'GRCh38' {
-            fasta       = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa"
-            bwa         = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/"
-            bowtie2     = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/"
-            star        = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/"
-            bismark     = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/"
-            gtf         = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf"
-            bed12       = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed"
-            mito_name   = "chrM"
-            macs_gsize  = "2.7e9"
-            blacklist   = "${projectDir}/assets/blacklists/hg38-blacklist.bed"
+            fasta            = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa"
+            bwa              = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/"
+            bowtie2          = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/"
+            star             = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/"
+            bismark          = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/"
+            gtf              = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf"
+            bed12            = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed"
+            ngscheckmate_bed = "${params.igenomes_base}/Homo_sapiens/GATK/GRCh38/Annotation/NGSCheckMate/SNP_GRCh38_hg38_wChr.bed"
+            mito_name        = "chrM"
+            macs_gsize       = "2.7e9"
+            blacklist        = "${projectDir}/assets/blacklists/hg38-blacklist.bed"
         }
         'CHM13' {
             fasta       = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa"

conf/modules.config

@@ -1064,6 +1064,29 @@ if (!params.skip_alignment && !params.skip_qc) {
     }
 }
 
+if (params.ngscheckmate_bed) {
+    process {
+        withName: ".*BAM_NGSCHECKMATE:BCFTOOLS_MPILEUP" {
+            ext.args2 = '--no-version --ploidy 1 -c'
+            ext.args3 = '--no-version'
+            publishDir = [
+                path: { "${params.outdir}/${params.aligner}/ngscheckmate/vcfs" },
+                mode: params.publish_dir_mode,
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            ]
+        }
+
+        withName: ".*BAM_NGSCHECKMATE:NGSCHECKMATE_NCM" {
+            ext.args = '-V'
+            publishDir = [
+                path: { "${params.outdir}/${params.aligner}/ngscheckmate/output" },
+                mode: params.publish_dir_mode,
+                saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
+            ]
+        }
+    }
+}
+
 if (!params.skip_multiqc) {
     process {
         withName: 'MULTIQC' {

conf/test.config

@@ -34,6 +34,8 @@ params {
     hisat2_index       = "https://raw.githubusercontent.com/nf-core/test-datasets/7f1614baeb0ddf66e60be78c3d9fa55440465ac8/reference/hisat2.tar.gz"
     salmon_index       = "https://raw.githubusercontent.com/nf-core/test-datasets/7f1614baeb0ddf66e60be78c3d9fa55440465ac8/reference/salmon.tar.gz"
     rsem_index         = "https://raw.githubusercontent.com/nf-core/test-datasets/7f1614baeb0ddf66e60be78c3d9fa55440465ac8/reference/rsem.tar.gz"
+    rsem_index         = "https://raw.githubusercontent.com/nf-core/test-datasets/7f1614baeb0ddf66e60be78c3d9fa55440465ac8/reference/rsem.tar.gz"
+    ngscheckmate_bed   = "https://raw.githubusercontent.com/nf-core/test-datasets/rnaseq/reference/ngscheckmate.bed"
 
     // Other parameters
     skip_bbsplit        = false

docs/output.md

@@ -669,6 +669,24 @@ The plot on the left hand side shows the standard PC plot - notice the variable
 
 Results generated by MultiQC collate pipeline QC from supported tools i.e. FastQC, Cutadapt, SortMeRNA, STAR, RSEM, HISAT2, Salmon, SAMtools, Picard, RSeQC, Qualimap, Preseq and featureCounts. Additionally, various custom content has been added to the report to assess the output of dupRadar, DESeq2 and featureCounts biotypes, and to highlight samples failing a mimimum mapping threshold or those that failed to match the strand-specificity provided in the input samplesheet. The pipeline has special steps which also allow the software versions to be reported in the MultiQC output for future traceability. For more information about how to use MultiQC reports, see <http://multiqc.info>.
 
+### NGSCheckMate
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `ngscheckmate/vcf`
+  - `*.vcf`: vcf files containing the SNPs called for each sample.
+- `ngscheckmate/output`
+  - `*.pdf`: Plotted dendrogram showing which samples are considered to be matching.
+  - `*_corr_matrix.txt`: A correlation matrix showing the correlations between each sample. Correlations below the threshold are set to 0.
+  - `*_matched.txt`: Text file denoting which samples were considered to be matching. One line per match, stating the correlation and the coverage depth (of the sample in the pair with lowest number of reads).
+  - `*_corr_matrix.txt`: Text file denoting all the individual comparisons. One line per comparison, stating the correlation and the coverage depth (of the sample in the pair with lowest depth).
+
+</details>
+
+[NGSCheckMate](https://github.com/parklab/NGSCheckMate) is a tool to verify that samples come from the same individual, by examining a set of single nucleotide polymorphisms (SNPs). This calculates correlations between the samples, and then applies a depth-dependent model of allele fractions to call samples as being related or not. The principal outputs are a dendrogram, where samples that are considered to match are shown as connected, a matrix showing the correlations between each samples, and a text file detailing each match between files.
+This requires a bed file specifying the SNPs to consider to be provided as input. The NGSCheckMate github provides such sets of bed files for hg19 and hg38 that have been selected as being typically heterogeneous across the population and are present in exonic regions. The tool can also be used to verify samples match between different sequencing modalities, for instance matching RNA-Seq with ATAC-seq, ChIP-seq and WGS.
+
 ## Pseudoalignment and quantification
 
 ### Pseudoalignment

modules.json

@@ -10,6 +10,11 @@
                         "git_sha": "de3e6fc949dcffb8d3508c015f435ace5773ff08",
                         "installed_by": ["modules"]
                     },
+                    "bcftools/mpileup": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["bam_ngscheckmate"]
+                    },
                     "cat/fastq": {
                         "branch": "master",
                         "git_sha": "5c460c5a4736974abde2843294f35307ee2b0e5e",
@@ -75,6 +80,12 @@
                         "git_sha": "bdc2a97ced7adc423acfa390742db83cab98c1ad",
                         "installed_by": ["modules"]
                     },
+                    "ngscheckmate/ncm": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["bam_ngscheckmate"],
+                        "patch": "modules/nf-core/ngscheckmate/ncm/ngscheckmate-ncm.diff"
+                    },
                     "picard/markduplicates": {
                         "branch": "master",
                         "git_sha": "2ee934606f1fdf7fc1cb05d6e8abc13bec8ab448",
@@ -248,6 +259,11 @@
                         "git_sha": "dedc0e31087f3306101c38835d051bf49789445a",
                         "installed_by": ["subworkflows"]
                     },
+                    "bam_ngscheckmate": {
+                        "branch": "master",
+                        "git_sha": "cfd937a668919d948f6fcbf4218e79de50c2f36f",
+                        "installed_by": ["subworkflows"]
+                    },
                     "bam_rseqc": {
                         "branch": "master",
                         "git_sha": "a9784afdd5dcda23b84e64db75dc591065d64653",