Patch release: Fix #449 (wrong contigs from aDNA workflow going to binning)

CHANGELOG.md

@@ -3,6 +3,13 @@
 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).
 
+## v2.3.1 - [2023-06-19]
+
+### `Fixed`
+
+- [#458](https://github.com/nf-core/mag/pull/458) - Correct the major issue in ancient DNA workflow of binning refinement being performed on uncorrected contigs instead of aDNA consensus recalled contigs (issue [#449](https://github.com/nf-core/mag/issues/449))
+- [#451](https://github.com/nf-core/mag/pull/451) - Fix results file overwriting in Ancient DNA workflow (reported by @alexhbnr, fix by @jfy133, and integrated by @maxibor in [#458](https://github.com/nf-core/mag/pull/458) )
+
 ## v2.3.0 - [2023/03/02]
 
 ### `Added`

conf/modules.config

@@ -455,6 +455,7 @@ process {
     }
 
     withName: FREEBAYES {
+        ext.prefix = { "${meta.assembler}-${meta.id}" }
         ext.args   = "-p ${params.freebayes_ploidy} -q ${params.freebayes_min_basequality} -F ${params.freebayes_minallelefreq}"
         publishDir = [
             path: { "${params.outdir}/Ancient_DNA/variant_calling/freebayes" },
@@ -464,8 +465,8 @@ process {
     }
 
     withName: BCFTOOLS_VIEW {
+        ext.prefix = { "${meta.assembler}-${meta.id}.filtered" }
         ext.args   = "-v snps,mnps -i 'QUAL>=${params.bcftools_view_high_variant_quality} || (QUAL>=${params.bcftools_view_medium_variant_quality} && FORMAT/AO>=${params.bcftools_view_minimal_allelesupport})'"
-        ext.prefix = { "${meta.id}.filtered" }
         publishDir = [
             path: { "${params.outdir}/Ancient_DNA/variant_calling/filtered" },
             mode: params.publish_dir_mode,
@@ -474,6 +475,7 @@ process {
     }
 
     withName: BCFTOOLS_CONSENSUS {
+        ext.prefix = { "${meta.assembler}-${meta.id}" }
         publishDir = [
             path: {"${params.outdir}/Ancient_DNA/variant_calling/consensus" },
             mode: params.publish_dir_mode,
@@ -482,6 +484,7 @@ process {
     }
 
     withName: BCFTOOLS_INDEX {
+        ext.prefix = { "${meta.assembler}-${meta.id}" }
         ext.args   = "-t"
         publishDir = [
             path: {"${params.outdir}/Ancient_DNA/variant_calling/index" },
@@ -491,21 +494,24 @@ process {
     }
 
     withName: PYDAMAGE_ANALYZE {
+        ext.prefix = { "${meta.assembler}-${meta.id}" }
         publishDir = [
-            path: {"${params.outdir}/Ancient_DNA/pydamage/analyze/${meta.id}" },
+            path: {"${params.outdir}/Ancient_DNA/pydamage/analyze/" },
             mode: params.publish_dir_mode
         ]
     }
 
     withName: PYDAMAGE_FILTER {
+        ext.prefix = { "${meta.assembler}-${meta.id}" }
         ext.args   = "-t ${params.pydamage_accuracy}"
         publishDir = [
-            path: {"${params.outdir}/Ancient_DNA/pydamage/filter/${meta.id}" },
+            path: {"${params.outdir}/Ancient_DNA/pydamage/filter/" },
             mode: params.publish_dir_mode
         ]
     }
 
     withName: SAMTOOLS_FAIDX {
+        ext.prefix = { "${meta.assembler}-${meta.id}" }
         publishDir = [
             path: {"${params.outdir}/Ancient_DNA/samtools/faidx" },
             mode: params.publish_dir_mode,

docs/output.md

@@ -602,9 +602,9 @@ Optional, only running when parameter `-profile ancient_dna` is specified.
 <summary>Output files</summary>
 
 - `Ancient_DNA/pydamage/analyze`
-  - `[sample/group]/pydamage_results/pydamage_results.csv`: PyDamage raw result tabular file in `.csv` format. Format described here: [pydamage.readthedocs.io/en/0.62/output.html](https://pydamage.readthedocs.io/en/0.62/output.html)
+  - `[assembler]_[sample/group]/pydamage_results/pydamage_results.csv`: PyDamage raw result tabular file in `.csv` format. Format described here: [pydamage.readthedocs.io/en/0.62/output.html](https://pydamage.readthedocs.io/en/0.62/output.html)
 - `Ancient_DNA/pydamage/filter`
-  - `[sample/group]/pydamage_results/pydamage_results.csv`: PyDamage filtered result tabular file in `.csv` format. Format described here: [pydamage.readthedocs.io/en/0.62/output.html](https://pydamage.readthedocs.io/en/0.62/output.html)
+  - `[assembler]_[sample/group]/pydamage_results/pydamage_results.csv`: PyDamage filtered result tabular file in `.csv` format. Format described here: [pydamage.readthedocs.io/en/0.62/output.html](https://pydamage.readthedocs.io/en/0.62/output.html)
 
 </details>
 
@@ -616,11 +616,11 @@ Because of aDNA damage, _de novo_ assemblers sometimes struggle to call a correc
 <summary>Output files</summary>
 
 - `variant_calling/consensus`
-  - `[sample/group].fa`: contigs sequence with re-called consensus from read-to-contig alignment
+  - `[assembler]_[sample/group].fa`: contigs sequence with re-called consensus from read-to-contig alignment
 - `variant_calling/unfiltered`
-  - `[sample/group].vcf.gz`: raw variant calls of the reads aligned back to the contigs.
+  - `[assembler]_[sample/group].vcf.gz`: raw variant calls of the reads aligned back to the contigs.
 - `variant_calling/filtered`
-  - `[sample/group].filtered.vcf.gz`: quality filtered variant calls of the reads aligned back to the contigs.
+  - `[assembler]_[sample/group].filtered.vcf.gz`: quality filtered variant calls of the reads aligned back to the contigs.
 
 </details>
 

nextflow.config

@@ -308,7 +308,7 @@ manifest {
     description     = """Assembly, binning and annotation of metagenomes"""
     mainScript      = 'main.nf'
     nextflowVersion = '!>=22.10.1'
-    version = '2.3.0'
+    version = '2.3.1'
     doi             = '10.1093/nargab/lqac007'
 }
 

subworkflows/local/binning_refinement.nf

@@ -22,22 +22,14 @@ def getColNo(filename) {
 
 workflow BINNING_REFINEMENT {
     take:
-    contigs
+    ch_contigs_for_dastool // channel: [ val(meta), path(contigs) ]
     bins           // channel: [ val(meta), path(bins) ]
     depths
     reads
 
     main:
     ch_versions = Channel.empty()
 
-    // Drop unnecessary files
-    ch_contigs_for_dastool = contigs
-                                .map {
-                                    meta, assembly, bams, bais ->
-                                        def meta_new = meta.clone()
-                                        [ meta_new, assembly ]
-                                }
-
     ch_bins_for_fastatocontig2bin = RENAME_PREDASTOOL(bins).renamed_bins
                                         .branch {
                                             metabat2: it[0]['binner'] == 'MetaBAT2'

workflows/mag.nf

@@ -581,7 +581,14 @@ workflow MAG {
         // If any two of the binners are both skipped at once, do not run because DAS_Tool needs at least one
         if ( params.refine_bins_dastool ) {
 
-            BINNING_REFINEMENT ( BINNING_PREPARATION.out.grouped_mappings, BINNING.out.bins, BINNING.out.metabat2depths, ch_short_reads )
+            if (params.ancient_dna) {
+                ch_contigs_for_binrefinement = ANCIENT_DNA_ASSEMBLY_VALIDATION.out.contigs_recalled
+            } else {
+                ch_contigs_for_binrefinement = BINNING_PREPARATION.out.grouped_mappings
+                    .map{ meta, contigs, bam, bai -> [ meta, contigs ] }
+            }
+
+            BINNING_REFINEMENT ( ch_contigs_for_binrefinement, BINNING.out.bins, BINNING.out.metabat2depths, ch_short_reads )
             ch_versions = ch_versions.mix(BINNING_REFINEMENT.out.versions)
 
             if ( params.postbinning_input == 'raw_bins_only' ) {