Merge pull request #1021 from nf-core/dsl1-2.5.0

Dsl1 2.5.0

Author: TCLamnidis

.github/workflows/ci.yml

@@ -23,7 +23,7 @@ jobs:
     strategy:
       matrix:
         # Nextflow versions: check pipeline minimum and current latest
-        nxf_ver: ['20.07.1', '22.10.6']
+        nxf_ver: ["20.07.1", "22.10.6"]
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@v2
@@ -58,7 +58,7 @@ jobs:
         run: |
           git clone --single-branch --branch eager https://github.com/nf-core/test-datasets.git data
       - name: DELAY to try address some odd behaviour with what appears to be a conflict between parallel htslib jobs leading to CI hangs
-        run: | 
+        run: |
           if [[ $NXF_VER = '' ]]; then sleep 1200; fi
       - name: BASIC Run the basic pipeline with directly supplied single-end FASTQ
         run: |
@@ -74,7 +74,7 @@ jobs:
           nextflow run ${GITHUB_WORKSPACE} -profile test,docker --save_reference
       - name: REFERENCE Basic workflow, with supplied indices
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --bwa_index 'results/reference_genome/bwa_index/BWAIndex/' --fasta_index 'https://github.com/nf-core/test-datasets/blob/eager/reference/Mammoth/Mammoth_MT_Krause.fasta.fai' 
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --bwa_index 'results/reference_genome/bwa_index/BWAIndex/' --fasta_index 'https://github.com/nf-core/test-datasets/blob/eager/reference/Mammoth/Mammoth_MT_Krause.fasta.fai'
       - name: REFERENCE Run the basic pipeline with FastA reference with `fna` extension
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_fna,docker
@@ -107,7 +107,7 @@ jobs:
           nextflow run ${GITHUB_WORKSPACE} -profile test,docker --clip_adapters_list 'https://github.com/nf-core/test-datasets/raw/eager/databases/adapters/adapter-list.txt'
       - name: ADAPTER LIST Run the basic pipeline using an adapter list, skipping adapter removal
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --clip_adapters_list 'https://github.com/nf-core/test-datasets/raw/eager/databases/adapters/adapter-list.txt' --skip_adapterremoval 
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --clip_adapters_list 'https://github.com/nf-core/test-datasets/raw/eager/databases/adapters/adapter-list.txt' --skip_adapterremoval
       - name: POST_AR_FASTQ_TRIMMING Run the basic pipeline post-adapterremoval FASTQ trimming
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test,docker --run_post_ar_trimming
@@ -141,6 +141,9 @@ jobs:
       - name: BEDTOOLS Test bedtools feature annotation
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test,docker --run_bedtools_coverage --anno_file 'https://github.com/nf-core/test-datasets/raw/eager/reference/Mammoth/Mammoth_MT_Krause.gff3'
+      - name: MAPDAMAGE2 damage calculation
+        run: |
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --damage_calculation_tool 'mapdamage'
       - name: GENOTYPING_HC Test running GATK HaplotypeCaller
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_fna,docker --run_genotyping --genotyping_tool 'hc' --gatk_hc_out_mode 'EMIT_ALL_ACTIVE_SITES' --gatk_hc_emitrefconf 'BP_RESOLUTION'
@@ -193,11 +196,11 @@ jobs:
           nextflow run ${GITHUB_WORKSPACE} -profile test,docker --run_bam_filtering  --bam_unmapped_type 'fastq' --run_metagenomic_screening --metagenomic_tool 'malt' --database "/home/runner/work/eager/eager/databases/malt/" --metagenomic_complexity_filter
       - name: MALTEXTRACT Download resource files
         run: |
-            mkdir -p databases/maltextract
-            for i in ncbi.tre ncbi.map; do wget https://github.com/rhuebler/HOPS/raw/0.33/Resources/"$i" -P databases/maltextract/; done
+          mkdir -p databases/maltextract
+          for i in ncbi.tre ncbi.map; do wget https://github.com/rhuebler/HOPS/raw/0.33/Resources/"$i" -P databases/maltextract/; done
       - name: MALTEXTRACT Basic with MALT plus MaltExtract
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --run_bam_filtering  --bam_unmapped_type 'fastq' --run_metagenomic_screening --metagenomic_tool 'malt' --database "/home/runner/work/eager/eager/databases/malt" --run_maltextract --maltextract_ncbifiles "/home/runner/work/eager/eager/databases/maltextract/" --maltextract_taxon_list 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/testdata/Mammoth/maltextract/MaltExtract_list.txt' 
+          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --run_bam_filtering  --bam_unmapped_type 'fastq' --run_metagenomic_screening --metagenomic_tool 'malt' --database "/home/runner/work/eager/eager/databases/malt" --run_maltextract --maltextract_ncbifiles "/home/runner/work/eager/eager/databases/maltextract/" --maltextract_taxon_list 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/testdata/Mammoth/maltextract/MaltExtract_list.txt'
       - name: METAGENOMIC Run the basic pipeline but with unmapped reads going into Kraken
         run: |
           nextflow run ${GITHUB_WORKSPACE} -profile test_tsv_kraken,docker --run_bam_filtering  --bam_unmapped_type 'fastq'

CHANGELOG.md

@@ -3,6 +3,25 @@
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
+## [2.5.0] - 2023-11-01
+
+### `Added`
+
+- [#1020](https://github.com/nf-core/eager/issues/1020) Added mapdamage2 as an alternative for damage calculation.
+
+### `Fixed`
+
+- [#1017](https://github.com/nf-core/eager/issues/1017) Fixed file name collision in niche cases with multiple libraries of multiple UDG treatments.
+- [#1024](https://github.com/nf-core/eager/issues/1024) `multiqc_general_stats.txt` is now generated even if the table is a beeswarm plot in the report.
+- Updated RG tags for all mappers. RG-id now includes Sample as well as Library ID. Added `LB:` tag with the library ID.
+- [#1031](https://github.com/nf-core/eager/issues/1031) Always index fasta regardless of mapper. This ensures that DamageProfiler and genotyping processes get submitted when using bowtie2 and not providing a fasta index.
+
+### `Dependencies`
+
+- `multiqc`: 1.14 -> 1.16
+
+### `Deprecated`
+
 ## [2.4.7] - 2023-05-16
 
 ### `Added`

README.md

@@ -15,6 +15,9 @@
 
 [![Get help on Slack](http://img.shields.io/badge/slack-nf--core%20%23eager-4A154B?logo=slack)](https://nfcore.slack.com/channels/eager)
 
+>[!IMPORTANT]  
+> nf-core/eager versions 2.* are only compatible with Nextflow versions up to 22.10.6!
+
 ## Introduction
 
 <!-- nf-core: Write a 1-2 sentence summary of what data the pipeline is for and what it does -->
@@ -28,7 +31,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
 
 ## Quick Start
 
-1. Install [`nextflow`](https://nf-co.re/usage/installation) (`>=20.07.1`)
+1. Install [`nextflow`](https://nf-co.re/usage/installation) (`>=20.07.1` && `<=22.10.6`)
 
 2. Install any of [`Docker`](https://docs.docker.com/engine/installation/), [`Singularity`](https://www.sylabs.io/guides/3.0/user-guide/), [`Podman`](https://podman.io/), [`Shifter`](https://nersc.gitlab.io/development/shifter/how-to-use/) or [`Charliecloud`](https://hpc.github.io/charliecloud/) for full pipeline reproducibility _(please only use [`Conda`](https://conda.io/miniconda.html) as a last resort; see [docs](https://nf-co.re/usage/configuration#basic-configuration-profiles))_
 
@@ -52,7 +55,7 @@ The pipeline is built using [Nextflow](https://www.nextflow.io), a workflow tool
     nextflow clean -f -k
     ```
 
-See [usage docs](https://nf-co.re/eager/docs/usage.md) for all of the available options when running the pipeline.
+See [usage docs](https://nf-co.re/eager/usage) for all of the available options when running the pipeline.
 
 **N.B.** You can see an overview of the run in the MultiQC report located at `./results/MultiQC/multiqc_report.html`
 
@@ -69,7 +72,7 @@ By default the pipeline currently performs the following:
 * Sequencing adapter removal, paired-end data merging (`AdapterRemoval`)
 * Read mapping to reference using (`bwa aln`, `bwa mem`, `CircularMapper`, or `bowtie2`)
 * Post-mapping processing, statistics and conversion to bam (`samtools`)
-* Ancient DNA C-to-T damage pattern visualisation (`DamageProfiler`)
+* Ancient DNA C-to-T damage pattern visualisation (`DamageProfiler` or `mapDamage`)
 * PCR duplicate removal (`DeDup` or `MarkDuplicates`)
 * Post-mapping statistics and BAM quality control (`Qualimap`)
 * Library Complexity Estimation (`preseq`)
@@ -133,9 +136,9 @@ The nf-core/eager pipeline comes with documentation about the pipeline: [usage](
     * [Pipeline installation](https://nf-co.re/usage/local_installation)
     * [Adding your own system config](https://nf-co.re/usage/adding_own_config)
     * [Reference genomes](https://nf-co.re/usage/reference_genomes)
-3. [Running the pipeline](https://nf-co.re/eager/docs/usage.md)
+3. [Running the pipeline](https://nf-co.re/eager/usage)
    * This includes tutorials, FAQs, and troubleshooting instructions
-4. [Output and how to interpret the results](https://nf-co.re/eager/docs/output.md)
+4. [Output and how to interpret the results](https://nf-co.re/eager/output)
 
 ## Credits
 
@@ -246,7 +249,7 @@ In addition, references of tools and data used in this pipeline are as follows:
 * **Bowtie2**  Langmead, B. and Salzberg, S. L. 2012 Fast gapped-read alignment with Bowtie 2. Nature methods, 9(4), p. 357–359. doi: [10.1038/nmeth.1923](https:/dx.doi.org/10.1038/nmeth.1923).
 * **sequenceTools** Stephan Schiffels (Unpublished). Download: [https://github.com/stschiff/sequenceTools](https://github.com/stschiff/sequenceTools)
 * **EigenstratDatabaseTools** Thiseas C. Lamnidis (Unpublished). Download: [https://github.com/TCLamnidis/EigenStratDatabaseTools.git](https://github.com/TCLamnidis/EigenStratDatabaseTools.git)
-* **mapDamage2** Jónsson, H., et al 2013. mapDamage2.0: fast approximate Bayesian estimates of ancient DNA damage parameters. Bioinformatics , 29(13), 1682–1684. [https://doi.org/10.1093/bioinformatics/btt193](https://doi.org/10.1093/bioinformatics/btt193)
+* **mapDamage** Jónsson, H., et al 2013. mapDamage2.0: fast approximate Bayesian estimates of ancient DNA damage parameters. Bioinformatics , 29(13), 1682–1684. [https://doi.org/10.1093/bioinformatics/btt193](https://doi.org/10.1093/bioinformatics/btt193)
 * **BBduk** Brian Bushnell (Unpublished). Download: [https://sourceforge.net/projects/bbmap/](sourceforge.net/projects/bbmap/)
 
 ## Data References

assets/multiqc_config.yaml

@@ -17,6 +17,7 @@ run_modules:
   - gatk
   - kraken
   - malt
+  - mapdamage
   - mtnucratio
   - multivcfanalyzer
   - picard
@@ -91,6 +92,7 @@ top_modules:
       path_filters:
         - "*.preseq"
   - "damageprofiler"
+  - "mapdamage"
   - "mtnucratio"
   - "qualimap"
   - "sexdeterrmine"
@@ -155,6 +157,11 @@ table_columns_visible:
     3 Prime2: False
     mean_readlength: True
     median: True
+  mapDamage:
+    5 Prime1: True
+    5 Prime2: True
+    3 Prime1: False
+    3 Prime2: False
   mtnucratio:
     mt_nuc_ratio: True
   QualiMap:
@@ -240,10 +247,15 @@ table_columns_placement:
     3 Prime2: 730
     mean_readlength: 740
     median: 750
+  mapDamage:
+    5 Prime1: 760
+    5 Prime2: 765
+    3 Prime1: 770
+    3 Prime2: 775
   mtnucratio:
-    mtreads: 760
-    mt_cov_avg: 770
-    mt_nuc_ratio: 780
+    mtreads: 780
+    mt_cov_avg: 785
+    mt_nuc_ratio: 790
   QualiMap:
     mapped_reads: 800
     mean_coverage: 805