Final changes for milestone 2.2.0

CHANGELOG.md

@@ -3,14 +3,17 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
-## [v2.2.0dev](https://github.com/nf-core/pairgenomealign/releases/tag/2.2.0)
+## [v2.2.0](https://github.com/nf-core/pairgenomealign/releases/tag/2.2.0) "Chagara ponzu" - [May 29th 2025]
 
 ### `Added`
 
 - Support for export to BAM and CRAM formats ([#31](https://github.com/nf-core/pairgenomealign/issues/31)) ([#43](https://github.com/nf-core/pairgenomealign/issues/43)).
 - SAM/BAM/CRAM alignments files are sorted and their header features all sequences of the _target_ genome.
 - Report ungapped percent identity ([#46](https://github.com/nf-core/pairgenomealign/issues/46)).
 - Update full-size test genomes to feature more T2T assemblies ([#59](https://github.com/nf-core/pairgenomealign/issues/59)).
+- Use a single mulled container for LAST, Samtools and open-fonts, to save ~280 Mb of downloads ([#58](https://github.com/nf-core/pairgenomealign/issues/58)).
+- Allow export to multiple formats (comma-separated list) ([#42](https://github.com/nf-core/pairgenomealign/issues/42)).
+- Allow skipping of the assembly QC with `--skip_assembly_qc` ([#53](https://github.com/nf-core/pairgenomealign/issues/53)).
 
 ### `Dependencies`
 
@@ -20,12 +23,19 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 | `SAMTOOLS_DICT`  |             | 1.21        |
 | `SAMTOOLS_FAIDX` |             | 1.21        |
 
+### `Parameters`
+
+| Old parameter | New parameter        |
+| ------------- | -------------------- |
+|               | `--skip_assembly_qc` |
+
 ### `Fixed`
 
 - Remove noisy tag in the `MULTIQC_ASSEMBLYSCAN_PLOT_DATA` local module ([#64](https://github.com/nf-core/pairgenomealign/issues/64)).
 - Restore BED format support ([#56](https://github.com/nf-core/pairgenomealign/issues/56)).
 - Document the `multiqc_train.txt` and `multiqc_last_o2o.txt` aggregating alignment statistics ([#52](https://github.com/nf-core/pairgenomealign/issues/52)).
 - Point the test configs samplesheets to `nf-core/test-datasets` in order to run the AWS full tests ([#62](https://github.com/nf-core/pairgenomealign/issues/62)).
+- Update metro map, in white background ([#71](https://github.com/nf-core/pairgenomealign/issues/71)).
 
 ## [v2.1.0](https://github.com/nf-core/pairgenomealign/releases/tag/2.1.0) "Goya champuru" - [May 16th 2025]
 

assets/multiqc_config.yml

@@ -1,7 +1,7 @@
 report_comment: >
-  This report has been generated by the <a href="https://github.com/nf-core/pairgenomealign/tree/dev"
+  This report has been generated by the <a href="https://github.com/nf-core/pairgenomealign/releases/tag/2.2.0"
   target="_blank">nf-core/pairgenomealign</a> analysis pipeline. For information about
-  how to interpret these results, please see the <a href="https://nf-co.re/pairgenomealign/dev/docs/output"
+  how to interpret these results, please see the <a href="https://nf-co.re/pairgenomealign/2.2.0/docs/output"
   target="_blank">documentation</a>.
 report_section_order:
   "nf-core-pairgenomealign-methods-description":

conf/modules.config

@@ -147,4 +147,13 @@ process {
         ]
     }
 
+    // Use a single mulled container for all LAST and SAMTOOLS modules
+    // instead of the overlapping last, samtools, last_samtools and last_open-fonts images
+    // to save ~280 Mb of container download.
+    withName:'ALIGNMENT_.*' {
+        container = { "${workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+            'https://community-cr-prod.seqera.io/docker/registry/v2/blobs/sha256/06/06beccfa4d48e5daf30dd8cee4f7e06fd51594963db0d5087ab695365b79903b/data' :
+            'community.wave.seqera.io/library/last_samtools_open-fonts:176a6ab0c8171057'}" }
+    }
+
 }

docs/usage.md

@@ -186,7 +186,7 @@ To change the resource requests, please see the [max resources](https://nf-co.re
 
 In some cases, you may wish to change the container or conda environment used by a pipeline steps for a particular tool. By default, nf-core pipelines use containers and software from the [biocontainers](https://biocontainers.pro/) or [bioconda](https://bioconda.github.io/) projects. However, in some cases the pipeline specified version maybe out of date.
 
-To use a different container from the default container or conda environment specified in a pipeline, please see the [updating tool versions](https://nf-co.re/docs/usage/configuration#updating-tool-versions) section of the nf-core website.
+To use a different container from the default container or conda environment specified in a pipeline, please see the [updating tool versions](https://nf-co.re/docs/usage/configuration#updating-tool-versions) section of the nf-core website. Also please note that this pipeline uses a [Wave container](https://seqera.io/containers/) combining LAST, Samtools, and open fonts, to save the user from downloading multiple overlapping images (LAST alone, Samtools alone, LAST plus Samtools, and LAST plus open fonts). Changing this container is the simplest way to update LAST if you wish so.
 
 ### Custom Tool Arguments
 

nextflow.config

@@ -62,6 +62,8 @@ params {
     seed                       = 'YASS'
     softmask                   = 'tantan'
 
+    // Misc options
+    skip_assembly_qc           = false
     targetName                 = 'target'
     m2m                        = false
 
@@ -274,7 +276,7 @@ manifest {
     mainScript      = 'main.nf'
     defaultBranch   = 'master'
     nextflowVersion = '!>=24.10.1'
-    version         = '2.2.0dev'
+    version         = '2.2.0'
     doi             = ''
 }
 

nextflow_schema.json

@@ -36,6 +36,13 @@
                     "help_text": "By default the _target_ genome is named `target` and this name is concatenated with the sample IDs using `___` as a separator to construct alignment file names. Use this option to provide a more informative name for the target genome.",
                     "description": "Target genome name."
                 },
+                "skip_assembly_qc": {
+                    "type": "boolean",
+                    "default": "false",
+                    "help_text": "If the assembly QC was already done before this pipeline is started, you can skip it with this option.",
+                    "description": "Skip assembly QC.",
+                    "fa_icon": "fas fa-forward"
+                },
                 "outdir": {
                     "type": "string",
                     "format": "directory-path",
@@ -90,25 +97,10 @@
                 "export_aln_to": {
                     "type": "string",
                     "default": "no_export",
-                    "description": "Convert output to a different format than MAF.",
-                    "enum": [
-                        "no_export",
-                        "axt",
-                        "bam",
-                        "bed",
-                        "blast",
-                        "blasttab",
-                        "blasttab+",
-                        "chain",
-                        "cram",
-                        "gff",
-                        "html",
-                        "psl",
-                        "sam",
-                        "tab"
-                    ],
+                    "description": "Convert the final _one-to-one_ alignment to a different format than MAF.",
+                    "pattern": "^((no_export|axt|bam|bed|blast|blasttab|blasttab+|chain|cram|gff|html|psl|sam|tab)?,?)*(?<!,)$",
                     "fa_icon": "fas fa-file-export",
-                    "help_text": "Output extra files for the final _one-to-one_ alignment results in AXT, GFF or SAM format. This is useful for downstream tools that do not parse MAF. The files are always compressed with `gzip`."
+                    "help_text": "Multiple formats separated with commas. Supported formats are `axt`, `bam`, `bed`, `blast`, `blasttab`, `blasttab+`, `chain`, `cram`, `gff`, `html`, `psl`, `sam` and `tab`. This is useful for downstream tools that do not parse MAF. The files in text format are always compressed with `gzip`."
                 },
                 "m2m": {
                     "type": "boolean",

workflows/pairgenomealign.nf

@@ -44,15 +44,16 @@ workflow PAIRGENOMEALIGN {
         ch_samplesheet
     )
 
-    // Extract statistics on contig length and GC content
+    // Allow to skip statistics on contig length and GC content
     //
-    ASSEMBLYSCAN (
-        ch_samplesheet
-    )
-    // Parse assembly-scan's JSON for MultiQC
-    MULTIQC_ASSEMBLYSCAN_PLOT_DATA (
-        ASSEMBLYSCAN.out.json.collect{it[1]}
-    )
+    if (! params.skip_assembly_qc ) {
+        ASSEMBLYSCAN ( ch_samplesheet )
+        ch_versions = ch_versions.mix(ASSEMBLYSCAN.out.versions)
+        MULTIQC_ASSEMBLYSCAN_PLOT_DATA (
+            ASSEMBLYSCAN.out.json.collect{it[1]}
+        )
+        ch_multiqc_files = ch_multiqc_files.mix(MULTIQC_ASSEMBLYSCAN_PLOT_DATA.out.tsv)
+    }
 
     // Prefix query ids with target genome name before producing alignment files
     //
@@ -90,7 +91,8 @@ workflow PAIRGENOMEALIGN {
     ch_targetgenome_gzi = [[],[]]
     ch_targetgenome_dic = [[],[]]
 
-    if (params.export_aln_to.contains('cram') | params.export_aln_to.contains('bam')) {
+    export_formats = params.export_aln_to.tokenize(',')
+    if (export_formats.contains('cram') | export_formats.contains('bam')) {
         FASTA_BGZIP_INDEX_DICT_SAMTOOLS( ch_targetgenome )
         ch_targetgenome_faz = FASTA_BGZIP_INDEX_DICT_SAMTOOLS.out.fasta_gz
         ch_targetgenome_fai = FASTA_BGZIP_INDEX_DICT_SAMTOOLS.out.fai
@@ -101,7 +103,7 @@ workflow PAIRGENOMEALIGN {
 
     if (!(params.export_aln_to == "no_export")) {
         ALIGNMENT_EXP(
-            pairalign_out.o2o. map {it + params.export_aln_to},
+            pairalign_out.o2o.combine(Channel.fromList(export_formats)),
             ch_targetgenome_faz,
             ch_targetgenome_fai,
             ch_targetgenome_gzi,
@@ -114,7 +116,6 @@ workflow PAIRGENOMEALIGN {
 
     ch_versions = ch_versions
         .mix( CUTN_TARGET.out.versions)
-        .mix(ASSEMBLYSCAN.out.versions)
         .mix(   pairalign_out.versions)
 
     softwareVersionsToYAML(ch_versions)
@@ -151,7 +152,6 @@ workflow PAIRGENOMEALIGN {
 
     ch_multiqc_files = ch_multiqc_files
         .mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
-        .mix(MULTIQC_ASSEMBLYSCAN_PLOT_DATA.out.tsv)
         .mix(pairalign_out.multiqc)
         .mix(ch_collated_versions)
         .mix(