Merge pull request #347 from sanger-tol/dp24_jbrowse

Dp24 jbrowse
sanger-tol · Jan 10, 2025 · be7155e · be7155e
2 parents f551ab8 + 7f22372
commit be7155e
Show file tree

Hide file tree

Showing 10 changed files with 78 additions and 11 deletions.
diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
@@ -42,7 +42,7 @@ jobs:
         run: |
           curl https://tolit.cog.sanger.ac.uk/test-data/resources/treeval/TreeValTinyData.tar.gz | tar xzf -
 
-      - name: Singularity - Run FULL pipeline with test data
+      - name: Run FULL pipeline with test data
         # Remember that you can parallelise this by using strategy.matrix
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_github,docker --outdir ./Sing-Full
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -118,6 +118,13 @@ This builds on the initial release by adding subworkflows which generate kmer ba
 - Fix a bug in build_alignment_blocks.py to avoid indexing errors happening in large genomes.
 - Change output BEDGRAPH from EXTRACT_TELO module.
 
+#### Hot Fix 1
+
+- Generate CRAM CSV fix to allow for multi-readgroup cram files
+- Removing KMER_READCOV
+- tmp directory was being used
+- Output file adjustment (names and location)
+
 ### Parameters
 
 | Old Parameter | New Parameter |

diff --git a/main.nf b/main.nf
@@ -23,6 +23,7 @@ WorkflowMain.initialise( workflow, params, log )
 */
 
 include { TREEVAL           } from './workflows/treeval'
+include { TREEVAL_JBROWSE   } from './workflows/treeval_jbrowse'
 include { TREEVAL_RAPID     } from './workflows/treeval_rapid'
 include { TREEVAL_RAPID_TOL } from './workflows/treeval_rapid_tol'
 
@@ -33,20 +34,31 @@ workflow SANGERTOL_TREEVAL {
         TREEVAL ()
 }
 
+
+//
+// WORKFLOW: RUN MAIN PIPELINE ONLY THE JBROWSE COMPATIBLE COMPONENTS - E.G. NO MAPS
+//
+workflow SANGERTOL_TREEVAL_JBROWSE {
+        TREEVAL_JBROWSE ()
+}
+
+
 //
 // WORKFLOW: RUN TRUNCATED PIPELINE TO PRODUCE CONTACT MAPS AND PRETEXT ACCESSORIES
 //
 workflow SANGERTOL_TREEVAL_RAPID {
         TREEVAL_RAPID ()
 }
 
+
 //
 // WORKFLOW: RUN TRUNCATED PIPELINE, CONTAINS WORKFLOWS INTERNAL TO SANGERTOL
 //
 workflow SANGERTOL_TREEVAL_RAPID_TOL {
         TREEVAL_RAPID_TOL ()
 }
 
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     RUN ALL WORKFLOWS
@@ -57,17 +69,25 @@ workflow SANGERTOL_TREEVAL_RAPID_TOL {
 // WORKFLOWS: Execute named workflow for the pipeline
 //
 workflow {
-        SANGERTOL_TREEVAL ()
+    SANGERTOL_TREEVAL ()
+}
+
+
+workflow JBROWSE {
+    SANGERTOL_TREEVAL_JBROWSE ()
 }
 
+
 workflow RAPID {
-        SANGERTOL_TREEVAL_RAPID ()
+    SANGERTOL_TREEVAL_RAPID ()
 }
 
+
 workflow RAPID_TOL {
-        SANGERTOL_TREEVAL_RAPID_TOL ()
+    SANGERTOL_TREEVAL_RAPID_TOL ()
 }
 
+
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
     THE END

diff --git a/subworkflows/local/busco_annotation.nf b/subworkflows/local/busco_annotation.nf
@@ -46,7 +46,6 @@ workflow BUSCO_ANNOTATION {
         []
     )
     ch_versions                 = ch_versions.mix(BUSCO_BUSCO.out.versions.first())
-
     ch_grab                     = GrabFiles(BUSCO_BUSCO.out.busco_dir)
 
     //

diff --git a/subworkflows/local/hic_mapping.nf b/subworkflows/local/hic_mapping.nf
@@ -85,6 +85,7 @@ workflow HIC_MAPPING {
         }
         .set{ch_aligner}
 
+
     //
     // SUBWORKFLOW: mapping hic reads using minimap2
     //
@@ -96,6 +97,7 @@ workflow HIC_MAPPING {
     ch_versions         = ch_versions.mix( HIC_MINIMAP2.out.versions )
     mergedbam           = HIC_MINIMAP2.out.mergedbam
 
+
     //
     // SUBWORKFLOW: mapping hic reads using bwamem2
     //
@@ -107,6 +109,7 @@ workflow HIC_MAPPING {
     ch_versions         = ch_versions.mix( HIC_BWAMEM2.out.versions )
     mergedbam           = mergedbam.mix(HIC_BWAMEM2.out.mergedbam)
 
+
     //
     // LOGIC: PREPARING PRETEXT MAP INPUT
     //
@@ -144,6 +147,7 @@ workflow HIC_MAPPING {
             )
     }
 
+
     //
     // MODULE: GENERATE PRETEXT MAP FROM MAPPED BAM FOR LOW RES
     //
@@ -153,6 +157,7 @@ workflow HIC_MAPPING {
     )
     ch_versions         = ch_versions.mix( PRETEXTMAP_STANDRD.out.versions )
 
+
     //
     // MODULE: INGEST ACCESSORY FILES INTO PRETEXT BY DEFAULT
     //
@@ -166,6 +171,7 @@ workflow HIC_MAPPING {
     )
     ch_versions         = ch_versions.mix( PRETEXT_INGEST_SNDRD.out.versions )
 
+
     //
     // MODULE: GENERATE PRETEXT MAP FROM MAPPED BAM FOR HIGH RES
     //
@@ -175,6 +181,7 @@ workflow HIC_MAPPING {
     )
     ch_versions         = ch_versions.mix( PRETEXTMAP_HIGHRES.out.versions )
 
+
     //
     // NOTICE: This could fail on LARGE hires maps due to some memory parameter in the C code
     //         of pretext graph. There is a "fixed" version in sanger /software which may need
@@ -190,6 +197,7 @@ workflow HIC_MAPPING {
     )
     ch_versions         = ch_versions.mix( PRETEXT_INGEST_HIRES.out.versions )
 
+
     //
     // MODULE: GENERATE PNG FROM STANDARD PRETEXT
     //
@@ -198,6 +206,7 @@ workflow HIC_MAPPING {
     )
     ch_versions         = ch_versions.mix ( SNAPSHOT_SRES.out.versions )
 
+
     //
     // LOGIC: BRANCH TO SUBSAMPLE BAM IF LARGER THAN 50G
     //
@@ -216,6 +225,7 @@ workflow HIC_MAPPING {
         }
         .set { ch_merged_bam }
 
+
     // LOGIC: PREPARE BAMTOBED JUICER INPUT.
     if ( workflow_setting != "RAPID_TOL" && params.juicer == false ) {
         //
@@ -236,6 +246,7 @@ workflow HIC_MAPPING {
             }
                 .set { ch_merged_bam }
 
+
         //
         // MODULE: SUBSAMPLE BAM
         //
@@ -244,12 +255,14 @@ workflow HIC_MAPPING {
         )
         ch_versions = ch_versions.mix ( SUBSAMPLE_BAM.out.versions )
 
+
         //
         // LOGIC: COMBINE BRANCHED TO SINGLE OUTPUT
         //
         ch_subsampled_bam = SUBSAMPLE_BAM.out.subsampled_bam
         ch_subsampled_bam.mix(ch_merged_bam.unmodified)
 
+
         //
         // LOGIC: PREPARE BAMTOBED JUICER INPUT
         //
@@ -261,6 +274,7 @@ workflow HIC_MAPPING {
             }
             .set { ch_bamtobed_juicer_input }
 
+
         //
         // SUBWORKFLOW: BAM TO BED FOR JUICER - USES THE SUBSAMPLED MERGED BAM
         //
@@ -270,6 +284,7 @@ workflow HIC_MAPPING {
         )
         ch_versions         = ch_versions.mix( HIC_BAMTOBED_JUICER.out.versions )
 
+
         //
         // LOGIC: PREPARE JUICER TOOLS INPUT
         //
@@ -282,6 +297,7 @@ workflow HIC_MAPPING {
             }
             .set { ch_juicer_input }
 
+
         //
         // MODULE: GENERATE HIC MAP, ONLY IS PIPELINE IS RUNNING ON ENTRY FULL
         //
@@ -293,6 +309,7 @@ workflow HIC_MAPPING {
         ch_versions         = ch_versions.mix( JUICER_TOOLS_PRE.out.versions )
     }
 
+
     //
     // LOGIC: PREPARE BAMTOBED COOLER INPUT
     //
@@ -304,6 +321,7 @@ workflow HIC_MAPPING {
         }
         .set { ch_bamtobed_cooler_input }
 
+
     //
     // SUBWORKFLOW: BAM TO BED FOR COOLER
     //
@@ -313,6 +331,7 @@ workflow HIC_MAPPING {
     )
     ch_versions         = ch_versions.mix( HIC_BAMTOBED_COOLER.out.versions )
 
+
     //
     // LOGIC: BIN CONTACT PAIRS
     //
@@ -321,6 +340,7 @@ workflow HIC_MAPPING {
         .combine( ch_cool_bin )
         .set { ch_binned_pairs }
 
+
     //
     // LOGIC: PREPARE COOLER INPUT
     //
@@ -332,6 +352,7 @@ workflow HIC_MAPPING {
         }
         .set { ch_cooler }
 
+
     //
     // MODULE: GENERATE A MULTI-RESOLUTION COOLER FILE BY COARSENING
     //
@@ -341,6 +362,7 @@ workflow HIC_MAPPING {
     )
     ch_versions         = ch_versions.mix(COOLER_CLOAD.out.versions)
 
+
     //
     // LOGIC: REFACTOR CHANNEL FOR ZOOMIFY
     //
@@ -350,16 +372,17 @@ workflow HIC_MAPPING {
         }
         .set{ch_cool}
 
+
     //
     // MODULE: ZOOM COOL TO MCOOL
     //
     COOLER_ZOOMIFY(ch_cool)
     ch_versions         = ch_versions.mix(COOLER_ZOOMIFY.out.versions)
 
+
     //
     // LOGIC: FOR REPORTING
     //
-
     ch_cram_files = GrabFiles( hic_reads_path )
 
     ch_cram_files

diff --git a/subworkflows/local/synteny.nf b/subworkflows/local/synteny.nf
@@ -7,8 +7,8 @@ include { MINIMAP2_ALIGN        } from '../../modules/nf-core/minimap2/align/mai
 
 workflow SYNTENY {
     take:
-    reference_tuple     // Channel: tuple [ val(meta), path(file) ]
-    synteny_paths        // Channel: val(meta)
+    reference_tuple             // Channel: tuple [ val(meta), path(file) ]
+    synteny_paths               // Channel: val(meta)
 
     main:
     ch_versions                 = Channel.empty()

diff --git a/subworkflows/local/yaml_input.nf b/subworkflows/local/yaml_input.nf
@@ -39,8 +39,6 @@ workflow YAML_INPUT {
         }
         .set{ group }
 
-    group.synteny.view{"INPUT: $it"}
-
     //
     // LOGIC: PARSES THE SECOND LEVEL OF YAML VALUES PER ABOVE OUTPUT CHANNEL
     //

diff --git a/workflows/treeval.nf b/workflows/treeval.nf
@@ -199,14 +199,14 @@ workflow TREEVAL {
     //              and generated a file of syntenic blocks.
     //
     if ( !exclude_workflow_steps.contains("synteny")) {
-        YAML_INPUT.out.synteny_paths.view {"SYNTENY_MAIN: $it"}
         SYNTENY (
             YAML_INPUT.out.reference_ch,
             YAML_INPUT.out.synteny_paths
         )
         ch_versions     = ch_versions.mix( SYNTENY.out.versions )
     }
 
+
     //
     // SUBWORKFLOW: Takes reference, pacbio reads
     //

diff --git a/workflows/treeval_rapid.nf b/workflows/treeval_rapid.nf
@@ -65,6 +65,8 @@ workflow TREEVAL_RAPID {
 
     params.entry    = 'RAPID'
     input_ch        = Channel.fromPath(params.input, checkIfExists: true)
+
+
     //
     // SUBWORKFLOW: reads the yaml and pushing out into a channel per yaml field
     //
@@ -73,6 +75,7 @@ workflow TREEVAL_RAPID {
         params.entry
     )
 
+
     //
     // SUBWORKFLOW: Takes input fasta file and sample ID to generate a my.genome file
     //
@@ -82,6 +85,7 @@ workflow TREEVAL_RAPID {
     )
     ch_versions     = ch_versions.mix( GENERATE_GENOME.out.versions )
 
+
     //
     // SUBWORKFLOW: GENERATES A BIGWIG FOR A REPEAT DENSITY TRACK
     //
@@ -93,6 +97,7 @@ workflow TREEVAL_RAPID {
         ch_versions     = ch_versions.mix( REPEAT_DENSITY.out.versions )
     }
 
+
     //
     // SUBWORKFLOW: GENERATES A GAP.BED FILE TO ID THE LOCATIONS OF GAPS
     //
@@ -103,6 +108,7 @@ workflow TREEVAL_RAPID {
         ch_versions     = ch_versions.mix( GAP_FINDER.out.versions )
     }
 
+
     //
     // SUBWORKFLOW: GENERATE TELOMERE WINDOW FILES WITH PACBIO READS AND REFERENCE
     //
@@ -113,6 +119,7 @@ workflow TREEVAL_RAPID {
         ch_versions     = ch_versions.mix( TELO_FINDER.out.versions )
     }
 
+
     //
     // SUBWORKFLOW: Takes reference, pacbio reads
     //
@@ -152,13 +159,15 @@ workflow TREEVAL_RAPID {
         hic_report = []
     }
 
+
     //
     // SUBWORKFLOW: Collates version data from prior subworflows
     //
     CUSTOM_DUMPSOFTWAREVERSIONS (
         ch_versions.unique().collectFile(name: 'collated_versions.yml')
     )
 
+
     //
     // LOGIC: GENERATE SOME CHANNELS FOR REPORTING
     //
-Original file line number
+Diff line change
@@ Expand Up / @@ -46,7 +46,6 @@ workflow BUSCO_ANNOTATION { @@
             []
         )
         ch_versions                 = ch_versions.mix(BUSCO_BUSCO.out.versions.first())
         ch_grab                     = GrabFiles(BUSCO_BUSCO.out.busco_dir)
         //
@@ Expand Down @@