diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md index 333c4f1..ae4285a 100644 --- a/.github/PULL_REQUEST_TEMPLATE.md +++ b/.github/PULL_REQUEST_TEMPLATE.md @@ -15,7 +15,8 @@ Learn more about contributing: [CONTRIBUTING.md](https://github.com/nf-core/taxp - [ ] This comment contains a description of changes (with reason). - [ ] If you've fixed a bug or added code that should be tested, add tests! -- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/taxprofiler/tree/master/.github/CONTRIBUTING.md)- [ ] If necessary, also make a PR on the nf-core/taxprofiler _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository. +- [ ] If you've added a new tool - have you followed the pipeline conventions in the [contribution docs](https://github.com/nf-core/taxprofiler/tree/master/.github/CONTRIBUTING.md) +- [ ] If necessary, also make a PR on the nf-core/taxprofiler _branch_ on the [nf-core/test-datasets](https://github.com/nf-core/test-datasets) repository. - [ ] Make sure your code lints (`nf-core lint`). - [ ] Ensure the test suite passes (`nextflow run . -profile test,docker --outdir `). - [ ] Usage Documentation in `docs/usage.md` is updated. diff --git a/CITATIONS.md b/CITATIONS.md index 2ed0a2b..c9c16ae 100644 --- a/CITATIONS.md +++ b/CITATIONS.md @@ -62,7 +62,7 @@ > Breitwieser, Florian P., Daniel N. Baker, and Steven L. Salzberg. 2018. KrakenUniq: confident and fast metagenomics classification using unique k-mer counts. Genome Biology 19 (1): 198. doi: 10.1186/s13059-018-1568-0 - - [MetaPhlAn3](https://doi.org/10.7554/eLife.65088) +- [MetaPhlAn3](https://doi.org/10.7554/eLife.65088) > Beghini, Francesco, Lauren J McIver, Aitor Blanco-Míguez, Leonard Dubois, Francesco Asnicar, Sagun Maharjan, Ana Mailyan, et al. 2021. “Integrating Taxonomic, Functional, and Strain-Level Profiling of Diverse Microbial Communities with BioBakery 3.” Edited by Peter Turnbaugh, Eduardo Franco, and C Titus Brown. ELife 10 (May): e65088. doi: 10.7554/eLife.65088 @@ -76,7 +76,7 @@ - [DIAMOND](https://doi.org/10.1038/nmeth.3176) -> Buchfink, Benjamin, Chao Xie, and Daniel H. Huson. 2015. “Fast and Sensitive Protein Alignment Using DIAMOND.” Nature Methods 12 (1): 59-60. doi: 10.1038/nmeth.3176. + > Buchfink, Benjamin, Chao Xie, and Daniel H. Huson. 2015. “Fast and Sensitive Protein Alignment Using DIAMOND.” Nature Methods 12 (1): 59-60. doi: 10.1038/nmeth.3176. - [Centrifuge](https://doi.org/10.1101/gr.210641.116) diff --git a/conf/test_krakenuniq.config b/conf/test_krakenuniq.config index c811cd9..586a4d6 100644 --- a/conf/test_krakenuniq.config +++ b/conf/test_krakenuniq.config @@ -45,10 +45,11 @@ params { run_motus = false run_krona = true krona_taxonomy_directory = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/sarscov2/metagenome/krona_taxonomy.tab' - malt_save_reads = true - kraken2_save_reads = true - centrifuge_save_reads = true - diamond_save_reads = true + malt_save_reads = false + kraken2_save_reads = false + centrifuge_save_reads = false + diamond_save_reads = false + run_profile_standardisation = true } process { diff --git a/docs/output.md b/docs/output.md index cbb04f8..2c02879 100644 --- a/docs/output.md +++ b/docs/output.md @@ -16,12 +16,12 @@ The pipeline is built using [Nextflow](https://www.nextflow.io/) and processes d - [AdapterRemoval](#adapterremoval) - Adapter trimming for Illumina data - [Porechop](#porechop) - Adapter removal for Oxford Nanopore data - [BBDuk](#bbduk) - Quality trimming and filtering for Illumina data -- [PRINSEQ++](#prinseq++) - Quality trimming and filtering for Illunina data +- [PRINSEQ++](#prinseq) - Quality trimming and filtering for Illunina data - [Filtlong](#filtlong) - Quality trimming and filtering for Nanopore data - [Bowtie2](#bowtie2) - Host removal for Illumina reads - [minimap2](#minimap2) - Host removal for Nanopore reads -- [SAMtools stats](#samtoolsstats) - Statistics from host removal -- [SAMtools bam2fq](#samtoolsfastq) - Converts unmapped BAM file to fastq format (minimap2 only) +- [SAMtools stats](#samtools-stats) - Statistics from host removal +- [SAMtools bam2fq](#samtools-fastq) - Converts unmapped BAM file to fastq format (minimap2 only) - [Bracken](#bracken) - Taxonomic classifier using k-mers and abundance estimations - [Kraken2](#kraken2) - Taxonomic classifier using exact k-mer matches - [KrakenUniq](#krakenuniq) - Taxonomic classifier that combines the k-mer-based classification and the number of unique k-mers found in each species diff --git a/docs/usage.md b/docs/usage.md index 523d92a..3a45752 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -199,7 +199,7 @@ You can optionally save the FASTQ output of the run merging with the `--save_com > ⚠️ For nanopore data: we do not recommend performing any read preprocessing or complexity filtering if you are using ONTs Guppy toolkit for basecalling and post-processing. -#### Host Removal +#### Host-Read Removal Removal of possible-host reads from FASTQ files prior classification/profiling can be activated with `--perform_shortread_hostremoval` or `--perform_longread_hostremoval`. diff --git a/nextflow.config b/nextflow.config index f6f3340..827b70f 100644 --- a/nextflow.config +++ b/nextflow.config @@ -102,7 +102,7 @@ params { shortread_hostremoval_index = null longread_hostremoval_index = null save_hostremoval_index = false - save_hostremoval_bam = false + save_hostremoval_bam = false save_hostremoval_unmapped = false @@ -302,7 +302,7 @@ manifest { name = 'nf-core/taxprofiler' author = """nf-core community""" homePage = 'https://github.com/nf-core/taxprofiler' - description = """Taxonomic profiling of shotgun metagenomic data""" + description = """Taxonomic classification and profiling of shotgun metagenomic data""" mainScript = 'main.nf' nextflowVersion = '!>=22.10.1' version = '1.0.0' diff --git a/subworkflows/local/profiling.nf b/subworkflows/local/profiling.nf index a55dcaf..28ca7e8 100644 --- a/subworkflows/local/profiling.nf +++ b/subworkflows/local/profiling.nf @@ -329,7 +329,7 @@ workflow PROFILING { reads: [ single_meta + db_meta, reads.flatten() ] db: db } - // Hardcode to _always_ produce the report file (which is our basic otput, and goes into) + // Hardcode to _always_ produce the report file (which is our basic output, and goes into) KRAKENUNIQ_PRELOADEDKRAKENUNIQ ( ch_input_for_krakenuniq.reads, ch_input_for_krakenuniq.db, params.krakenuniq_ram_chunk_size, params.krakenuniq_save_reads, true, params.krakenuniq_save_readclassifications ) ch_multiqc_files = ch_multiqc_files.mix( KRAKENUNIQ_PRELOADEDKRAKENUNIQ.out.report ) ch_versions = ch_versions.mix( KRAKENUNIQ_PRELOADEDKRAKENUNIQ.out.versions.first() )