Added Minimap2 alignment

.github/workflows/ci.yml

@@ -245,6 +245,8 @@ jobs:
           - tags: "gatk4spark/applybqsr"
           - tags: "gatk4spark/markduplicates"
           - tags: "gawk"
+          - tags: "minimap2/index"
+          - tags: "minimap2/align"
           - tags: "mosdepth"
           - tags: "multiqc"
           - tags: "samblaster"

CITATIONS.md

@@ -94,6 +94,10 @@
 
   > Chen X, Schulz-Trieglaff O, Shaw R, et al.: Manta: rapid detection of structural variants and indels for germline and cancer sequencing applications. Bioinformatics. 2016 Apr 15;32(8):1220-2. doi: 10.1093/bioinformatics/btv710. PubMed PMID: 26647377.
 
+- [Minimap2](https://github.com/lh3/minimap2)
+
+  > Li, H. Minimap2: pairwise alignment for nucleotide sequences. Bioinformatics. 2018 May 10;34:3094-3100. doi:10.1093/bioinformatics/bty191. PubMed PMID: 29750242; PubMed Central PMCID: PMC6137996.
+
 - [Mosdepth](https://academic.oup.com/bioinformatics/article/34/5/867/4583630)
 
   > Brent S Pedersen, Aaron R Quinlan, Mosdepth: quick coverage calculation for genomes and exomes, Bioinformatics, Volume 34, Issue 5, 01 March 2018, Pages 867–868. doi: 10.1093/bioinformatics/btx699. PubMed PMID: 29096012. PubMed Central PMCID: PMC6030888.

conf/base.config

@@ -66,7 +66,7 @@ process {
         cpus   = { check_max( 12 * task.attempt, 'cpus' ) }
         memory = { check_max( 4.GB * task.attempt, 'memory' ) }
     }
-    withName: 'BWAMEM1_MEM|BWAMEM2_MEM' {
+    withName: 'BWAMEM1_MEM|BWAMEM2_MEM|MINIMAP2_ALIGN' {
         cpus   = { check_max( 24 * task.attempt, 'cpus' ) }
         memory = { check_max( 30.GB * task.attempt, 'memory' ) }
     }

conf/modules/aligner.config

@@ -29,11 +29,16 @@ process {
             ext.when   = { params.aligner == 'dragmap' }
         }
 
+        withName: 'MINIMAP2_ALIGN' {
+            ext.args   = { "-ax sr -R ${meta.read_group}" }
+            ext.when   = { params.aligner == 'minimap2' }
+        }
+
         withName: 'SENTIEON_BWAMEM' {
             ext.when   = { params.aligner == 'sentieon-bwamem' }
         }
 
-        withName: 'BWAMEM.*_MEM|DRAGMAP_ALIGN|SENTIEON_BWAMEM' {
+        withName: 'BWAMEM.*_MEM|DRAGMAP_ALIGN|MINIMAP2_ALIGN|SENTIEON_BWAMEM' {
             ext.prefix = { params.split_fastq > 1 ? "${meta.id}".concat('.').concat(reads.get(0).name.tokenize('.')[0]) : "${meta.id}.sorted" }
             publishDir = [
                 mode: params.publish_dir_mode,

conf/modules/prepare_genome.config

@@ -76,6 +76,17 @@ process {
         ]
     }
 
+    withName: 'MINIMAP2_INDEX' {
+        ext.args   = { "-x sr" }
+        ext.when         = { !params.minimap2 && params.step == "mapping" && params.aligner == "minimap2" }
+        publishDir       = [
+            mode: params.publish_dir_mode,
+            path: { "${params.outdir}/reference/minimap2" },
+            pattern: "*mmi",
+            saveAs: { params.save_reference || params.build_only_index ? it : null }
+        ]
+    }
+
     withName: 'MSISENSORPRO_SCAN' {
         ext.when         = { params.tools && params.tools.split(',').contains('msisensorpro') }
         publishDir       = [

docs/output.md

@@ -20,6 +20,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d
     - [BWA](#bwa)
     - [BWA-mem2](#bwa-mem2)
     - [DragMap](#dragmap)
+    - [Minimap2](#minimap2)
     - [Sentieon BWA mem](#sentieon-bwa-mem)
   - [Mark Duplicates](#mark-duplicates)
     - [GATK MarkDuplicates (Spark)](#gatk-markduplicates-spark)
@@ -174,6 +175,10 @@ These files are intermediate and by default not placed in the output-folder kept
 
 These files are intermediate and by default not placed in the output-folder kept in the final files delivered to users. Set `--save_mapped` to enable publishing, furthermore add the flag `save_output_as_bam` for publishing in BAM format.
 
+### Minimap2
+
+[Minimap2](https://github.com/lh3/minimap2) is a versatile pairwise aligner for genomic and spliced nucleotide sequences. The aligned reads are then coordinate-sorted (or name-sorted if [`GATK MarkDuplicatesSpark`](https://gatk.broadinstitute.org/hc/en-us/articles/5358833264411-MarkDuplicatesSpark) is used for duplicate marking) with [samtools](https://www.htslib.org/doc/samtools.html).
+
 #### Sentieon BWA mem
 
 Sentieon [bwa mem](https://support.sentieon.com/manual/usages/general/#bwa-mem-syntax) is a subroutine for mapping low-divergent sequences against a large reference genome. It is part of the proprietary software package [DNAseq](https://www.sentieon.com/detailed-description-of-pipelines/#dnaseq) from [Sentieon](https://www.sentieon.com/).

docs/usage.md

@@ -845,8 +845,9 @@ For GATK.GRCh38 the links for each reference file and the corresponding processe
 | known_indels          | BaseRecalibrator(Spark), FilterVariantTranches                                                                                                                                                                                                                                                                                                                                                                                                       | [GATKBundle](https://console.cloud.google.com/storage/browser/_details/genomics-public-data/resources/broad/hg38/v0/) |                                                                                      |
 | known_indels_tbi      | BaseRecalibrator(Spark), FilterVariantTranches                                                                                                                                                                                                                                                                                                                                                                                                       | [GATKBundle](https://console.cloud.google.com/storage/browser/_details/genomics-public-data/resources/broad/hg38/v0/) |                                                                                      |
 | known_snps            | BaseRecalibrator(Spark), FilterVariantTranches, VariantRecalibrator                                                                                                                                                                                                                                                                                                                                                                                  | [GATKBundle](https://console.cloud.google.com/storage/browser/_details/genomics-public-data/resources/broad/hg38/v0/) |                                                                                      |
-| known_snps_tbi        | BaseRecalibrator(Spark), FilterVariantTranches, VariantRecalibrator                                                                                                                                                                                                                                                                                                                                                                                  | [GATKBundle](https://console.cloud.google.com/storage/browser/_details/genomics-public-data/resources/broad/hg38/v0/) |
+| known_snps_tbi        | BaseRecalibrator(Spark), FilterVariantTranches, VariantRecalibrator                                                                                                                                                                                                                                                                                                                                                                                  | [GATKBundle](https://console.cloud.google.com/storage/browser/_details/genomics-public-data/resources/broad/hg38/v0/) |                                                                                      |
 | mappability           | ControlFREEC                                                                                                                                                                                                                                                                                                                                                                                                                                         | http://xfer.curie.fr/get/vyIi4w8EONl/out100m2_hg38.zip                                                                | http://boevalab.inf.ethz.ch/FREEC/tutorial.html                                      |
+| minimap2              | Minimap2                                                                                                                                                                                                                                                                                                                                                                                                                                             | minimap2 -x sr -d ${fasta.baseName} $fasta                                                                            |                                                                                      |
 | pon                   | Mutect2                                                                                                                                                                                                                                                                                                                                                                                                                                              | [GATKBundle](https://console.cloud.google.com/storage/browser/_details/genomics-public-data/resources/broad/hg38/v0/) | https://gatk.broadinstitute.org/hc/en-us/articles/360035890631-Panel-of-Normals-PON- |
 | pon_tbi               | Mutect2                                                                                                                                                                                                                                                                                                                                                                                                                                              | [GATKBundle](https://console.cloud.google.com/storage/browser/_details/genomics-public-data/resources/broad/hg38/v0/) | https://gatk.broadinstitute.org/hc/en-us/articles/360035890631-Panel-of-Normals-PON- |
 

main.nf

@@ -51,6 +51,7 @@ params.known_snps              = getGenomeAttribute('known_snps')
 params.known_snps_tbi          = getGenomeAttribute('known_snps_tbi')
 params.known_snps_vqsr         = getGenomeAttribute('known_snps_vqsr')
 params.mappability             = getGenomeAttribute('mappability')
+params.minimap2                = getGenomeAttribute('minimap2')
 params.ngscheckmate_bed        = getGenomeAttribute('ngscheckmate_bed')
 params.pon                     = getGenomeAttribute('pon')
 params.pon_tbi                 = getGenomeAttribute('pon_tbi')
@@ -160,11 +161,11 @@ workflow NFCORE_SAREK {
                                     : PREPARE_GENOME.out.bwamem2
     dragmap     = params.dragmap    ? Channel.fromPath(params.dragmap).map{ it -> [ [id:'dragmap'], it ] }.collect()
                                     : PREPARE_GENOME.out.hashtable
+    minimap2   = params.minimap2    ? Channel.fromPath(params.minimap2).collect()
+                                    : PREPARE_GENOME.out.minimap2
 
-    // Gather index for mapping given the chosen aligner
-    index_alignment = (aligner == "bwa-mem" || aligner == "sentieon-bwamem") ? bwa :
-        aligner == "bwa-mem2" ? bwamem2 :
-        dragmap
+    index_alignment = (params.aligner == "bwa-mem" || params.aligner == "sentieon-bwamem") ? bwa :
+        params.aligner == "bwa-mem2" ? bwamem2 : params.aligner == "dragmap" ? dragmap : minimap2
 
     // TODO: add a params for msisensorpro_scan
     msisensorpro_scan      = PREPARE_GENOME.out.msisensorpro_scan

modules.json

@@ -324,6 +324,16 @@
                         "git_sha": "8731a6221dd10fd9039e18518b390b43e14ef9ae",
                         "installed_by": ["modules"]
                     },
+                    "minimap2/align": {
+                        "branch": "master",
+                        "git_sha": "72e277acfd9e61a9f1368eafb4a9e83f5bcaa9f5",
+                        "installed_by": ["modules"]
+                    },
+                    "minimap2/index": {
+                        "branch": "master",
+                        "git_sha": "72e277acfd9e61a9f1368eafb4a9e83f5bcaa9f5",
+                        "installed_by": ["modules"]
+                    },
                     "mosdepth": {
                         "branch": "master",
                         "git_sha": "e0616fba0919adb190bfe070d17fb12d76ba3a26",