diff --git a/.nf-core.yml b/.nf-core.yml index a627d94..058edee 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -23,7 +23,7 @@ nf_core_version: 2.14.2.dev0 repository_type: pipeline template: author: Usman Rashid - description: A pipeline to preprocess raw NGS data for downstream reuse across various + description: A pipeline to pre-process raw NGS data for downstream reuse across various pipelines force: true is_nfcore: false diff --git a/README.md b/README.md index 29baaaf..383a627 100644 --- a/README.md +++ b/README.md @@ -12,14 +12,34 @@ **gallvp/prepngs** is a bioinformatics pipeline that pre-processes NGS data for downstream reuse across various pipelines. - - +```mermaid +%%{init: { + 'theme': 'base', + 'themeVariables': { + 'fontSize': '52px", + 'primaryColor': '#9A6421', + 'primaryTextColor': '#ffffff', + 'primaryBorderColor': '#9A6421', + 'lineColor': '#B180A8', + 'secondaryColor': '#455C58', + 'tertiaryColor': '#ffffff' + } +}}%% +flowchart LR + samplesheet(samplesheet.csv) ==> BAM2FASTQ + samplesheet(samplesheet.csv) ==> FASTQC + + BAM2FASTQ ==> FASTQC + FASTQC ==> FASTP + FASTP ==> FASTQC2[FASTQC] + FASTQC2 ==> MULTIQC +``` -1. Raw read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) -2. Adapter trimming ([`FASTP`](https://github.com/OpenGene/fastp)) -3. Trimmed read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) -4. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) +1. BAM to FASTQ ([`PBTK`](https://github.com/PacificBiosciences/pbtk)), `optional` +2. Raw read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) +3. Adapter trimming ([`FASTP`](https://github.com/OpenGene/fastp)) +4. Trimmed read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)) +5. Present QC for raw reads ([`MultiQC`](http://multiqc.info/)) ## Usage @@ -31,16 +51,15 @@ First, prepare a samplesheet with your input data that looks as follows: `samplesheet.csv`: ```csv -sample,fastq_1,fastq_2 -CONTROL_REP1,AEG588A1_S1_L002_R1_001.fastq.gz,AEG588A1_S1_L002_R2_001.fastq.gz +sample,reads_1,reads_2 +test1,SRR4292758_00_R1.fastq.gz,SRR4292758_00_R2.fastq.gz +test2,alz.ccs.bam ``` -Each row represents a fastq file (single-end) or a pair of fastq files (paired end). +Each row represents a fastq/bam file (single-end) or a pair of fastq files (paired end). Now, you can run the pipeline using: - - ```bash nextflow run gallvp/prepngs \ -profile \ @@ -55,9 +74,21 @@ nextflow run gallvp/prepngs \ gallvp/prepngs was originally written by Usman Rashid. -We thank the following people for their extensive assistance in the development of this pipeline: - - +The pipeline uses nf-core modules contributed by following authors: + + + + + + + + + + + + + + ## Contributions and Support diff --git a/docs/contributors.sh b/docs/contributors.sh new file mode 100755 index 0000000..e694e49 --- /dev/null +++ b/docs/contributors.sh @@ -0,0 +1,5 @@ +#!/usr/bin/env bash + +module_authors=$(find ./modules -name meta.yml | xargs -I {} grep -A20 'authors:' {} | grep '\- ' | tr -d '"' | tr '[:upper:]' '[:lower:]' | awk '{print $2}') +workflow_authors=$(find ./subworkflows -name meta.yml | xargs -I {} grep -A20 'authors:' {} | grep '\- ' | tr -d '"' | tr '[:upper:]' '[:lower:]' | awk '{print $2}') +echo -e "${module_authors}\n${workflow_authors}" | sort -V | uniq -c | sort -k1,1 -r | awk '{print $2}' | sed -n 's|@\(.*\)||p' diff --git a/modules.json b/modules.json index f2fe973..e077ea3 100644 --- a/modules.json +++ b/modules.json @@ -2,12 +2,12 @@ "name": "gallvp/prepngs", "homePage": "https://github.com/gallvp/prepngs", "repos": { - "https://github.com/PlantandFoodResearch/nxf-modules.git": { + "https://github.com/GallVp/nxf-components.git": { "modules": { - "pfr": { + "gallvp": { "pbtk/pbindex": { "branch": "main", - "git_sha": "429f064fb5fdf155405dda82a0334b8172f360e8", + "git_sha": "b1b21af9d0298a87a328c3e5664eea7904538cfb", "installed_by": ["modules"] } } diff --git a/modules/pfr/pbtk/pbindex/environment.yml b/modules/gallvp/pbtk/pbindex/environment.yml similarity index 100% rename from modules/pfr/pbtk/pbindex/environment.yml rename to modules/gallvp/pbtk/pbindex/environment.yml diff --git a/modules/pfr/pbtk/pbindex/main.nf b/modules/gallvp/pbtk/pbindex/main.nf similarity index 100% rename from modules/pfr/pbtk/pbindex/main.nf rename to modules/gallvp/pbtk/pbindex/main.nf diff --git a/modules/pfr/pbtk/pbindex/meta.yml b/modules/gallvp/pbtk/pbindex/meta.yml similarity index 100% rename from modules/pfr/pbtk/pbindex/meta.yml rename to modules/gallvp/pbtk/pbindex/meta.yml diff --git a/modules/pfr/pbtk/pbindex/tests/main.nf.test b/modules/gallvp/pbtk/pbindex/tests/main.nf.test similarity index 98% rename from modules/pfr/pbtk/pbindex/tests/main.nf.test rename to modules/gallvp/pbtk/pbindex/tests/main.nf.test index 59993b4..9370620 100644 --- a/modules/pfr/pbtk/pbindex/tests/main.nf.test +++ b/modules/gallvp/pbtk/pbindex/tests/main.nf.test @@ -5,7 +5,7 @@ nextflow_process { process "PBTK_PBINDEX" tag "modules" - tag "modules_pfr" + tag "modules_gallvp" tag "pbtk" tag "pbtk/pbindex" diff --git a/modules/pfr/pbtk/pbindex/tests/main.nf.test.snap b/modules/gallvp/pbtk/pbindex/tests/main.nf.test.snap similarity index 100% rename from modules/pfr/pbtk/pbindex/tests/main.nf.test.snap rename to modules/gallvp/pbtk/pbindex/tests/main.nf.test.snap diff --git a/modules/pfr/pbtk/pbindex/tests/tags.yml b/modules/pfr/pbtk/pbindex/tests/tags.yml deleted file mode 100644 index 21e0ea0..0000000 --- a/modules/pfr/pbtk/pbindex/tests/tags.yml +++ /dev/null @@ -1,2 +0,0 @@ -pbtk/pbindex: - - "modules/pfr/pbtk/pbindex/**" diff --git a/nextflow_schema.json b/nextflow_schema.json index 4287fa4..f50d5fd 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -2,7 +2,7 @@ "$schema": "http://json-schema.org/draft-07/schema", "$id": "https://raw.githubusercontent.com/gallvp/prepngs/master/nextflow_schema.json", "title": "gallvp/prepngs pipeline parameters", - "description": "A pipeline to preprocess raw NGS data for downstream reuse across various pipelines", + "description": "A pipeline to pre-process raw NGS data for downstream reuse across various pipelines", "type": "object", "definitions": { "input_output_options": { diff --git a/workflows/prepngs.nf b/workflows/prepngs.nf index d56f780..a2d2dd6 100644 --- a/workflows/prepngs.nf +++ b/workflows/prepngs.nf @@ -5,7 +5,7 @@ */ include { paramsSummaryMap } from 'plugin/nf-validation' -include { PBTK_PBINDEX } from '../modules/pfr/pbtk/pbindex/main' +include { PBTK_PBINDEX } from '../modules/gallvp/pbtk/pbindex/main' include { PBTK_BAM2FASTQ } from '../modules/nf-core/pbtk/bam2fastq/main' include { MULTIQC } from '../modules/nf-core/multiqc/main'