Merge branch 'dev' into nf-core-template-merge-2.14.1

.editorconfig

@@ -8,7 +8,7 @@ trim_trailing_whitespace = true
 indent_size = 4
 indent_style = space
 
-[*.{md,yml,yaml,html,css,scss,js}]
+[*.{md,yml,yaml,html,css,scss,js,cff}]
 indent_size = 2
 
 # These files are edited and tested upstream in nf-core/modules

.github/workflows/ci.yml

@@ -26,6 +26,15 @@ jobs:
         NXF_VER:
           - "23.04.0"
           - "latest-everything"
+        PARAMS:
+          - "-profile test,docker --preprocessing_tool fastp --preprocessing_adapterlist 'https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/fastp/adapters.fasta'"
+          - "-profile test,docker --preprocessing_tool adapterremoval --preprocessing_adapterlist 'https://github.com/nf-core/test-datasets/raw/modules/data/delete_me/adapterremoval/adapterremoval_adapterlist.txt' --sequencing_qc_tool falco --run_genotyping --genotyping_tool 'freebayes' --genotyping_source 'raw'"
+          - "-profile test,docker --mapping_tool bwamem --run_mapdamage_rescaling --run_pmd_filtering --run_trim_bam --run_genotyping --genotyping_tool 'ug' --genotyping_source 'trimmed'"
+          - "-profile test,docker --mapping_tool bowtie2 --damagecalculation_tool mapdamage --damagecalculation_mapdamage_downsample 100 --run_genotyping --genotyping_tool 'hc' --genotyping_source 'raw'"
+          - "-profile test,docker --skip_preprocessing"
+          - "-profile test_humanbam,docker --run_mtnucratio --run_contamination_estimation_angsd --snpcapture_bed 'https://raw.githubusercontent.com/nf-core/test-datasets/eager/reference/Human/1240K.pos.list_hs37d5.0based.bed.gz' --run_genotyping --genotyping_tool 'pileupcaller' --genotyping_source 'raw'"
+          - "-profile test_humanbam,docker --run_sexdeterrmine --run_genotyping --genotyping_tool 'angsd' --genotyping_source 'raw'"
+          - "-profile test_multiref,docker" ## TODO add damage manipulation here instead once it goes multiref
     steps:
       - name: Check out pipeline code
         uses: actions/checkout@0ad4b8fadaa221de15dcec353f45205ec38ea70b # v4
@@ -43,4 +52,4 @@ jobs:
         # For example: adding multiple test runs with different parameters
         # Remember that you can parallelise this by using strategy.matrix
         run: |
-          nextflow run ${GITHUB_WORKSPACE} -profile test,docker --outdir ./results
+          nextflow run ${GITHUB_WORKSPACE} --outdir ./results ${{ matrix.PARAMS }}

.gitignore

@@ -6,3 +6,5 @@ results/
 testing/
 testing*
 *.pyc
+tests/
+test/

.nf-core.yml

@@ -1,2 +1,7 @@
 repository_type: pipeline
 nf_core_version: "2.14.1"
+
+lint:
+  nextflow_config:
+    - config_defaults:
+        - params.contamination_estimation_angsd_hapmap

.prettierignore

@@ -10,3 +10,6 @@ testing/
 testing*
 *.pyc
 bin/
+*.cff
+test/
+dev_docs.md

CITATION.cff

@@ -0,0 +1,52 @@
+cff-version: 1.2.0
+message: "If you use `nf-core/eager` in your work, please cite the following publication"
+authors:
+  - family-names: Fellows Yates
+    given-names: James A.
+  - family-names: Lamnidis
+    given-names: Thiseas C.
+  - family-names: Borry
+    given-names: Maxime
+  - family-names: Andrades Valtueña
+    given-names: Aida
+  - family-names: Fagernãs
+    given-names: Zandra
+  - family-names: Clayton
+    given-names: Stephen
+  - family-names: Garcia
+    given-names: Maxime U.
+  - family-names: Neukamm
+    given-names: Judith
+  - family-names: Peltzer
+    given-names: Alexander
+title: "Reproducible, portable, and efficient ancient genome reconstruction with nf-core/eager"
+version: 3.0.0
+doi: 10.7717/peerj.10947
+date-released: 2022-08-02
+url: https://github.com/nf-core/eager
+prefered-citation:
+    type: article
+    authors:
+        - family-names: Fellows Yates
+          given-names: James A.
+        - family-names: Lamnidis
+          given-names: Thiseas C.
+        - family-names: Borry
+          given-names: Maxime
+        - family-names: Andrades Valtueña
+          given-names: Aida
+        - family-names: Fagernãs
+          given-names: Zandra
+        - family-names: Clayton
+          given-names: Stephen
+        - family-names: Garcia
+          given-names: Maxime U.
+        - family-names: Neukamm
+          given-names: Judith
+        - family-names: Peltzer
+          given-names: Alexander
+    doi: 10.7717/peerj.10947
+    start: e10947
+    title: "Reproducible, portable, and efficient ancient genome reconstruction with nf-core/eager"
+    year: 2021
+    url: https://dx.doi.org/10.1038/10.7717/peerj.10947

CITATIONS.md

@@ -18,6 +18,114 @@
 
   > Ewels P, Magnusson M, Lundin S, Käller M. MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics. 2016 Oct 1;32(19):3047-8. doi: 10.1093/bioinformatics/btw354. Epub 2016 Jun 16. PubMed PMID: 27312411; PubMed Central PMCID: PMC5039924.
 
+- [Falco](https://doi.org/10.12688%2Ff1000research.21142.2)
+
+  > de Sena Brandine, G., Smith, A.D. (2019) Falco: high-speed FastQC emulation for quality control of sequencing data. F1000Res., 8, 1874. doi: [10.12688%2Ff1000research.21142.2](https://doi.org/10.12688%2Ff1000research.21142.2)
+
+- [fastp](https://doi.org/10.1093/bioinformatics/bty560)
+
+  > Chen, S., Zhou, Y., Chen, Y., & Gu, J. (2018). fastp: an ultra-fast all-in-one FASTQ preprocessor. Bioinformatics , 34(17), i884–i890. doi: [10.1093/bioinformatics/bty560](https://doi.org/10.1093/bioinformatics/bty560)
+
+- [AdapterRemoval](https://doi.org/10.1186/s13104-016-1900-2)
+
+  > Schubert, M., Lindgreen, S., & Orlando, L. (2016). AdapterRemoval v2: rapid adapter trimming, identification, and read merging. BMC Research Notes, 9, 88. doi: [10.1186/s13104-016-1900-2](https://doi.org/10.1186/s13104-016-1900-2)
+
+- [Picard Tools](https://broadinstitute.github.io/picard/)
+
+  > Broad Institute (2019). Picard Toolkit. GitHub Repository: https://broadinstitute.github.io/picard/
+
+- [SeqKit](https://bioinf.shenwei.me/seqkit/)
+
+  > Shen, W., Le, S., Li, Y., & Hu, F. (2016). SeqKit: A Cross-Platform and Ultrafast Toolkit for FASTA/Q File Manipulation. PLOS ONE, 11(10), e0163962. doi:[10.1371/journal.pone.0163962](https://doi.org/10.1371/journal.pone.0163962)
+
+- [bwa](https://doi.org/10.1093/bioinformatics/btp324)
+
+  > Li, H., & Durbin, R. (2009). Fast and accurate short read alignment with Burrows-Wheeler transform. Bioinformatics , 25(14), 1754–1760. doi: [10.1093/bioinformatics/btp324](https://doi.org/10.1093/bioinformatics/btp324)
+
+- [BWA-MEM](https://doi.org/10.48550/arXiv.1303.3997)
+
+  > Li, H. (2013). Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM. arXiv , arXiv:1303.3997. doi: [10.48550/arXiv.1303.3997](https://doi.org/10.48550/arXiv.1303.3997)
+
+- [Bowtie 2](https://bowtie-bio.sourceforge.net/bowtie2/manual.shtml)
+
+  > Langmead, B., Salzberg, S. (2012). Fast gapped-read alignment with Bowtie 2. Nat Methods 9, 357–359. doi: [10.1038/nmeth.1923](https://doi.org/10.1038/nmeth.1923)
+
+  > Langmead, B., Wilks, C., Antonescu, V., Charles, R. (2018). Scaling read aligners to hundreds of threads on general-purpose processors. Bioinformatics, 35(3), doi: [10.1093/bioinformatics/bty648](https://doi.org/10.1093/bioinformatics/bty648)
+
+- [SAMtools](https://doi.org/10.1093/bioinformatics/btp324)
+
+  > Li, H., Handsaker, B., Wysoker, A., Fennell, T., Ruan, J., Homer, N., Marth, G., Abecasis, G., Durbin, R., & 1000 Genome Project Data Processing Subgroup. (2009). The Sequence Alignment/Map format and SAMtools. Bioinformatics , 25(16), 2078–2079. doi: [10.1093/bioinformatics/btp352](https://doi.org/10.1093/bioinformatics/btp324)
+
+- [DeDup](https://doi.org/10.1186/s13059-016-0918-z)
+
+  > Peltzer, A., Jäger, G., Herbig, A., Seitz, A., Kniep, C., Krause, J., & Nieselt, K. (2016). EAGER: efficient ancient genome reconstruction. Genome Biology, 17(1), 1–14. doi: [10.1186/s13059-016-0918-z](https://doi.org/10.1186/s13059-016-0918-z)
+
+- [ANGSD](http://www.popgen.dk/angsd/index.php/ANGSD)
+
+  > Korneliussen, T. S., Albrechtsen, A., Nielsen, R. (2014) ANGSD: Analysis of Next Generation Sequencing Data. BMC Bioinformatics, 15, 356. doi: [10.1186/s12859-014-0356-4](https://doi.org/10.1186/s12859-014-0356-4)
+
+  > Rasmussen, M., et. al. (2011) An Aboriginal Australian genome reveals separate human dispersals into Asia. Science, 334(6052), 94-98. doi: [10.1126/science.1211177](https://doi.org/10.1126/science.1211177)
+
+- [prinseqplusplus](https://doi.org/10.7287/peerj.preprints.27553v1)
+
+  > Cantu VA, Sadural J, Edwards R. 2019. PRINSEQ++, a multi-threaded tool for fast and efficient quality control and preprocessing of sequencing datasets. PeerJ Preprints 7:e27553v1. doi: [10.7287/peerj.preprints.27553v1](https://doi.org/10.7287/peerj.preprints.27553v1)
+
+- [bbduk](https://doi.org/10.1371/journal.pone.0185056)
+
+  > Bushnell B, Rood J, Singer E (2017) BBMerge – Accurate paired shotgun read merging via overlap. PLOS ONE 12(10): e0185056. [https://doi.org/10.1371/journal.pone.0185056](https://doi.org/10.1371/journal.pone.0185056)
+
+- [BEDTools](https://doi.org/10.1093/bioinformatics/btq033)
+
+  > Quinlan, A. R., & Hall, I. M. (2010). BEDTools: A flexible suite of utilities for comparing genomic features. Bioinformatics, 26(6), 841–842. [https://doi.org/10.1093/bioinformatics/btq033](https://doi.org/10.1093/bioinformatics/btq033)
+
+- [PreSeq](https://doi.org/10.1038/nmeth.2375)
+
+  > Daley, T., & Smith, A. D. (2013). Predicting the molecular complexity of sequencing libraries. Nature Methods, 10(4), 325–327. doi: [10.1038/nmeth.2375](https://doi.org/10.1038/nmeth.2375)
+
+- [endorS.py](https://doi.org/10.7717/peerj.10947)
+
+  > Fellows Yates JA, Lamnidis TC, Borry M, Valtueña Andrades A, Fagernäs Z, Clayton S, Garcia MU, Neukamm J, Peltzer A. 2021. Reproducible, portable, and efficient ancient genome reconstruction with nf-core/eager. PeerJ 9:e10947. doi: [10.7717/peerj.10947](https://doi.org/10.7717/peerj.10947)
+
+- [mapDamage2](https://doi.org/10.1093/bioinformatics/btt193)
+
+  > Jónsson H, Ginolhac A, Schubert M, Johnson P, Orlando L. mapDamage2.0: fast approximate Bayesian estimates of ancient DNA damage parameters. Bioinformatics 2013. 23rd April 2013. doi: [10.1093/bioinformatics/btt193](https://doi.org/10.1093/bioinformatics/btt193)
+
+- [PMDtools](https://doi.org/10.1073/pnas.1318934111)
+
+  > Skoglund P., Northoff B.H.,Shunkov M.V., Derevianko A., Pääbo S., Krause J., Jakobsson M. (2014) Separating ancient DNA from modern contamination in a Siberian Neandertal, Proceedings of the National Academy of Sciences USA doi: [10.1073/pnas.1318934111](https://doi.org/10.1073/pnas.1318934111)
+
+- [BamUtils](https://doi.org/10.1101/gr.176552.114)
+
+  > Jun, G., Wing, M. K., Abecasis, G. R., & Kang, H. M. (2015). An efficient and scalable analysis framework for variant extraction and refinement from population-scale DNA sequence data. Genome Research, 25(6), 918–925. doi: [10.1101/gr.176552.114](https://doi.org/10.1101/gr.176552.114)
+
+- [QualiMap](https://doi.org/10.1093/bioinformatics/btv566)
+
+  > QualiMap Okonechnikov, K., Conesa, A., & García-Alcalde, F. (2016). Qualimap 2: advanced multi-sample quality control for high-throughput sequencing data. Bioinformatics , 32(2), 292–294. doi: [10.1093/bioinformatics/btv566](https://doi.org/10.1093/bioinformatics/btv566).
+
+- [DamageProfiler](https://doi.org/10.1093/bioinformatics/btab190)
+
+  > DamageProfiler Neukamm, J., Peltzer, A., & Nieselt, K. (2020). DamageProfiler: Fast damage pattern calculation for ancient DNA. In Bioinformatics (btab190). doi: [10.1093/bioinformatics/btab190](https://doi.org/10.1093/bioinformatics/btab190).
+
+- [GATK 3.5](https://console.cloud.google.com/storage/browser/gatk)
+
+  > DePristo M, Banks E, Poplin R, Garimella K, Maguire J, Hartl C, Philippakis A, del Angel G, Rivas MA, Hanna M, McKenna A, Fennell T, Kernytsky A, Sivachenko A, Cibulskis K, Gabriel S, Altshuler D, Daly M. (2011). A framework for variation discovery and genotyping using next-generation DNA sequencing data. Nature Genetics, 43(5), 491–498. doi: [10.1038/ng.806](https://doi.org/10.1038/ng.806).
+
+- [GATK 4.X](https://github.com/broadinstitute/gatk/releases)
+
+  > Poplin R, Ruano-Rubio V, DePristo MA, Fennell TJ, Carneiro MO, Van der Auwera GA, Kling DE, Gauthier LD, Levy-Moonshine A, Roazen D, Shakir K, Thibault J, Chandran S, Whelan C, Lek M, Gabriel S, Daly MJ, Neale B, MacArthur DG, Banks E. (2017). Scaling accurate genetic variant discovery to tens of thousands of samples bioRxiv, 201178. doi: [10.1101/201178](https://doi.org/10.1101/201178).
+
+- [FreeBayes](https://github.com/freebayes/freebayes)
+
+  > Garrison E, Marth G. Haplotype-based variant detection from short-read sequencing. arXiv preprint arXiv:1207.3907 \[q-bio.GN] 2012. doi: [10.48550/arXiv.1207.3907](https://doi.org/10.48550/arXiv.1207.3907).
+
+- [BCFtools](https://github.com/samtools/bcftools)
+
+  > Li H. A statistical framework for SNP calling, mutation discovery, association mapping and population genetical parameter estimation from sequencing data. Bioinformatics (2011) 27(21) 2987-93.doi: [10.1093/bioinformatics/btr509](https://doi.org/10.1093/bioinformatics/btr509).
+
+  - [Sex.DetERRmine.py](http://dx.doi.org/10.1038/s41467-018-07483-5)
+
+  > Sex.DetERRmine.py Lamnidis, T.C. et al., 2018. Ancient Fennoscandian genomes reveal origin and spread of Siberian ancestry in Europe. Nature communications, 9(1), p.5018. Available at: http://dx.doi.org/10.1038/s41467-018-07483-5. Download: https://github.com/TCLamnidis/Sex.DetERRmine
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)