add yahs to workflow

.github/workflows/linting.yml

@@ -14,12 +14,12 @@ jobs:
   EditorConfig:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/checkout@v3
+      - uses: actions/checkout@v4
 
-      - uses: actions/setup-node@v3
+      - uses: actions/setup-node@v4
 
       - name: Install editorconfig-checker
-        run: npm install -g editorconfig-checker
+        run: npm install -g editorconfig-checker@3.0.2
 
       - name: Run ECLint check
         run: editorconfig-checker -exclude README.md $(find .* -type f | grep -v '.git\|.py\|.md\|json\|yml\|yaml\|html\|css\|work\|.nextflow\|build\|nf_core.egg-info\|log.txt\|Makefile')

README.md

@@ -17,8 +17,8 @@ This is a gitpod set up for BGA23 with a version of TreeVal, although for now gi
 The treeval pipeline has a sister pipeline currently named [curationpretext](https://github.com/sanger-tol/curationpretext) which acts to regenerate the pretext maps and accessory files during genomic curation in order to confirm interventions. This pipeline is sufficiently different to the treeval implementation that it is written as it's own pipeline.
 
 1. Parse input yaml ( YAML_INPUT )
-2. Generate my.genome file ( GENERATE_GENOME )
-3. Generate insilico digests of the input assembly ( INSILICO_DIGEST )
+2. Generate chromosome size file ( GENERATE_GENOME )
+3. Generate Bionano insilico digests of the input assembly ( INSILICO_DIGEST )
 4. Generate gene alignments with high quality data against the input assembly ( GENE_ALIGNMENT )
 5. Generate a repeat density graph ( REPEAT_DENSITY )
 6. Generate a gap track ( GAP_FINDER )

conf/modules.config

@@ -57,6 +57,13 @@ process {
         ]
     }
 
+    withName: YAHS {
+        publishDir      = [
+            path: { "${params.outdir}/hic_files/alignment_bin" },
+            mode: params.publish_dir_mode
+        ]
+    }
+
     //
     // MODULE CONFIGS
     //
@@ -107,6 +114,11 @@ process {
         ext.prefix      = { "${meta.id}.juicer.sorted" }
     }
 
+    withName: ".*:.*:HIC_MAPPING:YAHS" {
+        ext.prefix      = { "${meta.id}.alignment" }
+        ext.args        = "--convert-to-binary"
+    }
+
     //
     // SUBWORKFLOW: SELFCOMP
     //

modules.json

@@ -194,6 +194,11 @@
                         "branch": "master",
                         "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
                         "installed_by": ["modules"]
+                    },
+                    "yahs": {
+                        "branch": "master",
+                        "git_sha": "d3a3d04073af68437f07e0fb9b88aa6172c3f678",
+                        "installed_by": ["modules"]
                     }
                 }
             },

modules/local/find_telomere_regions.nf

@@ -2,7 +2,7 @@ process FIND_TELOMERE_REGIONS {
     tag "${meta.id}"
     label 'process_low'
 
-    container 'docker.io/library/gcc:10.4.0'
+    container 'quay.io/sanger-tol/telomere:0.0.1-c1'
 
     input:
     tuple val( meta ), path( file )

subworkflows/local/generate_genome.nf

@@ -48,6 +48,7 @@ workflow GENERATE_GENOME {
     ch_genomesize       = GENERATE_SORTED_GENOME.out.genomesize
     ch_genome_fai       = GENERATE_SORTED_GENOME.out.ref_index
     ch_versions         = GENERATE_SORTED_GENOME.out.versions
+    ch_ref              = GENERATE_SORTED_GENOME.out.fasta
 
     //
     // SUBWORKFLOW: GENERATE UNSORTED CHROMOSOME SIZES FILE (DEFINED BY USER)
@@ -58,6 +59,7 @@ workflow GENERATE_GENOME {
     ch_versions         = ch_versions.mix( GENERATE_UNSORTED_GENOME.out.versions )
     ch_genomesize       = ch_genomesize.mix( GENERATE_UNSORTED_GENOME.out.genomesize )
     ch_genome_fai       = ch_genome_fai.mix( GENERATE_UNSORTED_GENOME.out.ref_index )
+    ch_ref              = ch_ref.mix( GENERATE_UNSORTED_GENOME.out.fasta )
     ch_versions         = GENERATE_UNSORTED_GENOME.out.versions
 
     //
@@ -73,6 +75,6 @@ workflow GENERATE_GENOME {
     max_scaff_size  = GET_LARGEST_SCAFF.out.scaff_size.toInteger()
     dot_genome      = ch_genomesize
     ref_index       = ch_genome_fai
-    ref             = reference_file
+    ref             = ch_ref
     versions        = ch_versions.ifEmpty(null)
 }

subworkflows/local/generate_sorted_genome.nf

@@ -29,5 +29,6 @@ workflow GENERATE_SORTED_GENOME {
     emit:
     genomesize      = GNU_SORT.out.sorted
     ref_index       = CUSTOM_GETCHROMSIZES.out.fai
+    fasta           = CUSTOM_GETCHROMSIZES.out.fasta
     versions        = ch_versions.ifEmpty(null)
 }

subworkflows/local/generate_unsorted_genome.nf

@@ -23,5 +23,6 @@ workflow GENERATE_UNSORTED_GENOME {
 
     genomesize      = CUSTOM_GETCHROMSIZES.out.sizes
     ref_index       = CUSTOM_GETCHROMSIZES.out.fai
+    fasta           = CUSTOM_GETCHROMSIZES.out.fasta
     versions        = ch_versions.ifEmpty(null)
 }

subworkflows/local/hic_mapping.nf

@@ -16,6 +16,7 @@ include { PRETEXTSNAPSHOT as SNAPSHOT_SRES                } from '../../modules/
 include { GENERATE_CRAM_CSV                               } from '../../modules/local/generate_cram_csv'
 include { JUICER_TOOLS_PRE                                } from '../../modules/local/juicer_tools_pre'
 include { SUBSAMPLE_BAM                                   } from '../../modules/local/subsample_bam.nf'
+include { YAHS                                            } from '../../modules/nf-core/yahs/main'
 include { PRETEXT_INGESTION as PRETEXT_INGEST_SNDRD       } from '../../subworkflows/local/pretext_ingestion'
 include { PRETEXT_INGESTION as PRETEXT_INGEST_HIRES       } from '../../subworkflows/local/pretext_ingestion'
 include { HIC_BAMTOBED as HIC_BAMTOBED_COOLER             } from '../../subworkflows/local/hic_bamtobed'
@@ -28,6 +29,7 @@ workflow HIC_MAPPING {
     reference_tuple     // Channel: tuple [ val(meta), path( file )      ]
     reference_index     // Channel: tuple [ val(meta), path( file )      ]
     dot_genome          // Channel: tuple [ val(meta), path( datafile )  ]
+    ref_yahs            // Channel: path( file )
     hic_reads_path      // Channel: tuple [ val(meta), path( directory ) ]
     assembly_id         // Channel: val( id )
     gap_file            // Channel: tuple [ val(meta), path( file )      ]
@@ -106,6 +108,21 @@ workflow HIC_MAPPING {
     ch_versions         = ch_versions.mix( HIC_BWAMEM2.out.versions )
     mergedbam           = mergedbam.mix(HIC_BWAMEM2.out.mergedbam)
 
+    //
+    // LOGIC: MAKE YAHS INPUT
+    //
+    ref_yahs.map { meta, ref -> ref }.set{ch_ref} 
+    reference_index.map { meta, fai -> fai }.set{ch_fai}
+
+    //
+    // MODULE: RUN YAHS TO GENERATE ALIGNMENT BIN FILE
+    //
+    YAHS ( 
+        mergedbam,
+        ch_ref,
+        ch_fai
+    )
+
     //
     // LOGIC: PREPARING PRETEXT MAP INPUT
     //

workflows/treeval.nf

@@ -234,6 +234,7 @@ workflow TREEVAL {
         YAML_INPUT.out.reference_ch,
         GENERATE_GENOME.out.ref_index,
         GENERATE_GENOME.out.dot_genome,
+        GENERATE_GENOME.out.ref,
         YAML_INPUT.out.hic_reads_ch,
         YAML_INPUT.out.assembly_id,
         GAP_FINDER.out.gap_file,