DSL2: Starting subworkflow for circularmapper

.github/workflows/ci.yml

@@ -31,7 +31,7 @@ jobs:
           - "-profile test,docker --preprocessing_tool adapterremoval --preprocessing_adapterlist 'https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/adapterremoval/adapterremoval_adapterlist.txt' --sequencing_qc_tool falco --run_genotyping --genotyping_tool 'freebayes' --genotyping_source 'raw'"
           - "-profile test,docker --mapping_tool bwamem --run_mapdamage_rescaling --run_pmd_filtering --run_trim_bam --run_genotyping --genotyping_tool 'ug' --genotyping_source 'trimmed'"
           - "-profile test,docker --mapping_tool bowtie2 --damagecalculation_tool mapdamage --damagecalculation_mapdamage_downsample 100 --run_genotyping --genotyping_tool 'hc' --genotyping_source 'raw'"
-          - "-profile test,docker --skip_preprocessing --convert_inputbam"
+          - "-profile test,docker --mapping_tool circularmapper --skip_preprocessing --convert_inputbam --fasta_circular_target 'NC_007596.2' --mapping_circularmapper_elongation_factor 500"
           - "-profile test_humanbam,docker --run_mtnucratio --run_contamination_estimation_angsd --snpcapture_bed 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz' --run_genotyping --genotyping_tool 'pileupcaller' --genotyping_source 'raw'"
           - "-profile test_humanbam,docker --run_sexdeterrmine --run_genotyping --genotyping_tool 'angsd' --genotyping_source 'raw'"
           - "-profile test_multiref,docker" ## TODO add damage manipulation here instead once it goes multiref

CITATIONS.md

@@ -126,6 +126,10 @@
 
   > Sex.DetERRmine.py Lamnidis, T.C. et al., 2018. Ancient Fennoscandian genomes reveal origin and spread of Siberian ancestry in Europe. Nature communications, 9(1), p.5018. Available at: http://dx.doi.org/10.1038/s41467-018-07483-5. Download: https://github.com/TCLamnidis/Sex.DetERRmine
 
+  - [CircularMapper](https://doi.org/10.1186/s13059-016-0918-z)
+
+  > Peltzer, A., Jäger, G., Herbig, A., Seitz, A., Kniep, C., Krause, J., & Nieselt, K. (2016). EAGER: efficient ancient genome reconstruction. Genome Biology, 17(1), 1–14. doi: [10.1186/s13059-016-0918-z](https://doi.org/10.1186/s13059-016-0918-z)
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

assets/schema_fasta.json

@@ -48,6 +48,20 @@
                 "pattern": "^\\S+$",
                 "errorMessage": "The headers of the chromosome to be extended by circularmapper must not contain any spaces and no leading '>'."
             },
+            "circularmapper_elongated_fasta": {
+                "type": "string",
+                "format": "file-path",
+                "pattern": "^\\S+\\.f(na|asta|a|as)(\\.gz)?$",
+                "exists": true,
+                "errorMessage": "The elongated Fasta files for the mapping reference must be provided with file extensions '.fasta', '.fa', '.fas', '.fna', '.fasta.gz','.fa.gz','.fas.gz', '.fna.gz' and cannot contain any spaces."
+            },
+            "circularmapper_elongated_fai": {
+                "type": "string",
+                "format": "file-path",
+                "pattern": "^\\S+\\.fai$",
+                "exists": true,
+                "errorMessage": "Elongated fasta index files for the mapping reference cannot have any spaces and must have file extension '.fai'."
+            },
             "mitochondrion_header": {
                 "type": "string",
                 "pattern": "^\\S+$",

conf/modules.config

@@ -278,6 +278,35 @@ process {
         ]
     }
 
+    // Reference elongation and indexing for circular mapping
+    withName: GUNZIP_ELONGATED_FASTA {
+        publishDir = [
+            path: { "${params.outdir}/reference/${meta.id}_${params.mapping_circularmapper_elongation_factor}/" },
+            mode: params.publish_dir_mode,
+            pattern: '*[0-9].f*',
+            enabled: params.save_reference
+        ]
+    }
+
+    withName: CIRCULARMAPPER_CIRCULARGENERATOR {
+        tag = { "${meta.id}_${params.mapping_circularmapper_elongation_factor}" }
+        publishDir = [
+            path: { "${params.outdir}/reference/${meta.id}_${params.mapping_circularmapper_elongation_factor}/" },
+            mode: params.publish_dir_mode,
+            pattern: '*[0-9].fasta',
+            enabled: params.save_reference
+        ]
+    }
+
+    withName: BWA_INDEX_CIRCULARISED {
+        publishDir = [
+            path: { "${params.outdir}/reference/${meta.id}_${params.mapping_circularmapper_elongation_factor}/" },
+            mode: params.publish_dir_mode,
+            pattern: 'bwa',
+            enabled: params.save_reference
+        ]
+    }
+
     //
     // BAM INPUT
     //
@@ -529,6 +558,25 @@ process {
         ]
     }
 
+    // Circular mapping
+    // Configuration for BWA_ALN and BWA_SAMSE/SAMPE is the same as for the non-circular mapping
+    withName: CIRCULARMAPPER_REALIGNSAMFILE {
+        tag = { "${meta.reference}|${meta.sample_id}_${meta.library_id}" }
+        ext.prefix = { "${meta.sample_id}_${meta.library_id}_${meta.reference}" }
+        publishDir = [
+            enabled: false
+        ]
+    }
+
+    withName: ".*MAP:FASTQ_ALIGN_BWAALN_ELONGATED:SAMTOOLS_INDEX" {
+        tag = { "${meta.id_index}|${meta.sample_id}_${meta.library_id}_L${meta.lane}" }
+        ext.args = { params.fasta_largeref ? "-c" : "" }
+        ext.prefix = { "${meta.sample_id}_${meta.library_id}_L${meta.lane}_${meta.reference}" }
+        publishDir = [
+            enabled: false
+        ]
+    }
+
     //
     // DEDUPLICATION
     //

docs/output.md

@@ -634,3 +634,14 @@ When using pileupCaller for genotyping, single-stranded and double-stranded libr
 </details>
 
 [ANGSD](http://www.popgen.dk/angsd/index.php/ANGSD) is a software for analyzing next generation sequencing data. It can estimate genotype likelihoods and allele frequencies from next-generation sequencing data. The output provided is a bgzipped genotype likelihood file, containing likelihoods across all samples per reference. Users can specify the model used for genotype likelihood estimation, as well as the output format. For more information on the available options, see the [ANGSD](https://www.popgen.dk/angsd/index.php/Genotype_Likelihoods).
+
+#### CircularMapper
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `mapping/circularmapper`
+
+  - `*realigned.bam`: BAM file realigned to the extended reference
+
+</details>

modules.json

@@ -95,6 +95,16 @@
                         "git_sha": "02fd5bd7275abad27aad32d5c852e0a9b1b98882",
                         "installed_by": ["modules"]
                     },
+                    "circularmapper/circulargenerator": {
+                        "branch": "master",
+                        "git_sha": "0148d00e72e35cd08b3d829d7de3430bc0c92a5a",
+                        "installed_by": ["modules"]
+                    },
+                    "circularmapper/realignsamfile": {
+                        "branch": "master",
+                        "git_sha": "579d2d5f15e126a2190a7b709dfc77696c83688d",
+                        "installed_by": ["modules"]
+                    },
                     "damageprofiler": {
                         "branch": "master",
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",