Merge pull request #148 from genomic-medicine-sweden/add_falco

Add Falco as an alternative to FastQC

.github/workflows/ci.yml

@@ -23,6 +23,7 @@ jobs:
           - "21.10.3"
           - "latest-everything"
         parameters:
+          - "--preprocessing_qc_tool falco"
           - "--perform_longread_qc false"
           - "--perform_shortread_qc false"
           - "--shortread_qc_tool fastp"

CITATIONS.md

@@ -62,6 +62,10 @@
 
 - [FILTLONG](https://github.com/rrwick/Filtlong)
 
+- [falco](https://doi.org/10.12688/f1000research.21142.2)
+
+> de Sena Brandine G and Smith AD. Falco: high-speed FastQC emulation for quality control of sequencing data. F1000Research 2021, 8:1874
+
 ## Software packaging/containerisation tools
 
 - [Anaconda](https://anaconda.com)

README.md

@@ -30,7 +30,7 @@ On release, automated continuous integration tests run the pipeline on a full-si
 
 ![](docs/images/taxprofiler_tube.png)
 
-1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
+1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/) or [`falco`](https://github.com/smithlabcode/falco) as an alternative option)
 2. Performs optional read pre-processing
    - Adapter clipping and merging (short-read: [fastp](https://github.com/OpenGene/fastp), [AdapterRemoval2](https://github.com/MikkelSchubert/adapterremoval); long-read: [porechop](https://github.com/rrwick/Porechop))
    - Low complexity and quality filtering (short-read: [bbduk](https://jgi.doe.gov/data-and-tools/software-tools/bbtools/), [PRINSEQ++](https://github.com/Adrian-Cantu/PRINSEQ-plus-plus); long-read: [Filtlong](https://github.com/rrwick/Filtlong))

conf/modules.config

@@ -40,6 +40,24 @@ process {
         ]
     }
 
+    withName: FALCO {
+        ext.prefix = { "${meta.id}_${meta.run_accession}_raw" }
+        publishDir = [
+            path: { "${params.outdir}/falco/raw" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{html,txt}'
+        ]
+    }
+
+    withName: FALCO_PROCESSED {
+        ext.prefix = { "${meta.id}_${meta.run_accession}_processed" }
+        publishDir = [
+            path: { "${params.outdir}/falco/processed" },
+            mode: params.publish_dir_mode,
+            pattern: '*.{html,txt}'
+        ]
+    }
+
     withName: FASTP_SINGLE {
         ext.args   = [
             // trimming options

docs/usage.md

@@ -166,6 +166,10 @@ work                # Directory containing the nextflow working files
 # Other nextflow hidden files, eg. history of pipeline runs and old logs.
 ```
 
+### Sequencing quality control
+
+nf-core taxprofiler offers [`falco`](https://github.com/smithlabcode/falco] as an alternative option to [`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).
+
 ### Preprocessing Steps
 
 nf-core/taxprofiler offers four main preprocessing steps
@@ -179,7 +183,7 @@ nf-core/taxprofiler offers four main preprocessing steps
 
 Raw sequencing read processing in the form of adapter clipping and paired-end read merging can be activated via the `--perform_shortread_qc` or `--perform_longread_qc` flags.
 
-It is highly recommended to run this on raw reads to remove artefacts from sequencing that can cause false positive identification of taxa (e.g. contaminated reference genomes) and/or skews in taxonomic abundance profiles.
+It is highly recommended to run this on raw reads to remove artifacts from sequencing that can cause false positive identification of taxa (e.g. contaminated reference genomes) and/or skews in taxonomic abundance profiles.
 
 There are currently two options for short-read preprocessing: `fastp` or `adapterremoval`.
 

modules.json

@@ -49,6 +49,10 @@
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"
                     },
+                    "falco": {
+                        "branch": "master",
+                        "git_sha": "fc959214036403ad83efe7a41d43d0606c445cda"
+                    },
                     "fastp": {
                         "branch": "master",
                         "git_sha": "5e34754d42cd2d5d248ca8673c0a53cdf5624905"

modules/nf-core/falco/main.nf

@@ -0,0 +1,57 @@
+process FALCO {
+    tag "$meta.id"
+    label 'process_single'
+
+
+    conda (params.enable_conda ? "bioconda::falco=1.2.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/falco:1.2.1--h867801b_3':
+        'quay.io/biocontainers/falco:1.2.1--h867801b_3' }"
+
+    input:
+    tuple val(meta), path(reads)
+
+    output:
+    tuple val(meta), path("*.html"), emit: html
+    tuple val(meta), path("*.txt") , emit: txt
+    path  "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    if ( reads.toList().size() == 1 ) {
+        """
+        falco $args --threads $task.cpus ${reads} -D ${prefix}_data.txt -S ${prefix}_summary.txt -R ${prefix}_report.html
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            falco:\$( falco --version | sed -e "s/falco//g" )
+        END_VERSIONS
+        """
+    } else {
+        """
+        falco $args --threads $task.cpus ${reads}
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            falco:\$( falco --version | sed -e "s/falco//g" )
+        END_VERSIONS
+        """
+    }
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_data.txt
+    touch ${prefix}_fastqc_data.html
+    touch ${prefix}_summary.txt
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        falco: \$( falco --version | sed -e "s/falco v//g" )
+    END_VERSIONS
+    """
+}

modules/nf-core/falco/meta.yml

@@ -0,0 +1,52 @@
+name: falco
+description: Run falco on sequenced reads
+keywords:
+  - quality control
+  - qc
+  - adapters
+  - fastq
+tools:
+  - fastqc:
+      description: "falco is a drop-in C++ implementation of FastQC to assess the quality of sequence reads."
+
+      homepage: "https://falco.readthedocs.io/"
+      documentation: "https://falco.readthedocs.io/"
+      tool_dev_url: "None"
+      doi: ""
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        respectively.
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - html:
+      type: file
+      description: FastQC like report
+      pattern: "*_{fastqc_report.html}"
+  - txt:
+      type: file
+      description: falco report data
+      pattern: "*_{data.txt}"
+  - txt:
+      type: file
+      description: falco summary file
+      pattern: "*_{summary.txt}"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@lucacozzuto"

nextflow.config

@@ -59,6 +59,8 @@ params {
     // Databases
     databases = null
 
+    preprocessing_qc_tool            = 'fastqc'
+
     // FASTQ preprocessing
     perform_shortread_qc             = false
     shortread_qc_tool                = 'fastp'

nextflow_schema.json

@@ -707,5 +707,14 @@
         {
             "$ref": "#/definitions/reference_genome_options"
         }
-    ]
+    ],
+    "properties": {
+        "preprocessing_qc_tool": {
+            "type": "string",
+            "default": "fastqc",
+            "enum": ["fastqc", "falco"],
+            "help_text": "Falco is designed as a drop-in replacement for FastQC but written in C++ for faster computation. We particularly recommend using falco when using long reads (due to reduced memory constraints), however is also applicable for short reads.",
+            "description": "Specify the tool used for quality control of raw sequencing reads"
+        }
+    }
 }

subworkflows/local/longread_preprocessing.nf

@@ -3,6 +3,8 @@
 //
 
 include { FASTQC as FASTQC_PROCESSED } from '../../modules/nf-core/fastqc/main'
+include { FALCO as FALCO_PROCESSED   } from '../../modules/nf-core/falco/main'
+
 include { PORECHOP                   } from '../../modules/nf-core/porechop/main'
 include { FILTLONG                   } from '../../modules/nf-core/filtlong/main'
 
@@ -52,8 +54,16 @@ workflow LONGREAD_PREPROCESSING {
         ch_multiqc_files = ch_multiqc_files.mix( FILTLONG.out.log )
     }
 
-    FASTQC_PROCESSED ( ch_processed_reads )
-    ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
+    if (params.preprocessing_qc_tool == 'fastqc') {
+        FASTQC_PROCESSED ( ch_processed_reads )
+        ch_versions = ch_versions.mix( FASTQC_PROCESSED.out.versions )
+        ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
+
+    } else if (params.preprocessing_qc_tool == 'falco') {
+        FALCO_PROCESSED ( ch_processed_reads )
+        ch_versions = ch_versions.mix( FALCO_PROCESSED.out.versions )
+        ch_multiqc_files = ch_multiqc_files.mix( FALCO_PROCESSED.out.txt )
+    }
 
     emit:
     reads    = ch_processed_reads   // channel: [ val(meta), [ reads ] ]

subworkflows/local/shortread_preprocessing.nf

@@ -5,7 +5,8 @@
 
 include { SHORTREAD_FASTP             } from './shortread_fastp'
 include { SHORTREAD_ADAPTERREMOVAL    } from './shortread_adapterremoval'
-include { FASTQC as FASTQC_PROCESSED       } from '../../modules/nf-core/fastqc/main'
+include { FASTQC as FASTQC_PROCESSED  } from '../../modules/nf-core/fastqc/main'
+include { FALCO as FALCO_PROCESSED    } from '../../modules/nf-core/falco/main'
 
 workflow SHORTREAD_PREPROCESSING {
     take:
@@ -27,9 +28,15 @@ workflow SHORTREAD_PREPROCESSING {
         ch_processed_reads = reads
     }
 
-    FASTQC_PROCESSED ( ch_processed_reads )
-    ch_versions = ch_versions.mix( FASTQC_PROCESSED.out.versions )
-    ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
+    if (params.preprocessing_qc_tool == 'fastqc') {
+        FASTQC_PROCESSED ( ch_processed_reads )
+        ch_versions = ch_versions.mix( FASTQC_PROCESSED.out.versions )
+        ch_multiqc_files = ch_multiqc_files.mix( FASTQC_PROCESSED.out.zip )
+    } else if  (params.preprocessing_qc_tool == 'falco') {
+        FALCO_PROCESSED ( ch_processed_reads )
+        ch_versions = ch_versions.mix( FALCO_PROCESSED.out.versions )
+        ch_multiqc_files = ch_multiqc_files.mix( FALCO_PROCESSED.out.txt )
+    }
 
     emit:
     reads    = ch_processed_reads   // channel: [ val(meta), [ reads ] ]

workflows/taxprofiler.nf

@@ -84,6 +84,7 @@ include { STANDARDISATION_PROFILES      } from '../subworkflows/local/standardis
 // MODULE: Installed directly from nf-core/modules
 //
 include { FASTQC                      } from '../modules/nf-core/fastqc/main'
+include { FALCO                       } from '../modules/nf-core/falco/main'
 include { MULTIQC                     } from '../modules/nf-core/multiqc/main'
 include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main'
 include { CAT_FASTQ                   } from '../modules/nf-core/cat/fastq/main'
@@ -120,12 +121,13 @@ workflow TAXPROFILER {
     */
     ch_input_for_fastqc = INPUT_CHECK.out.fastq.mix( INPUT_CHECK.out.nanopore )
 
-    FASTQC (
-        ch_input_for_fastqc
-    )
-
-    ch_versions = ch_versions.mix(FASTQC.out.versions.first())
-
+    if ( params.preprocessing_qc_tool == 'falco' ) {
+        FALCO ( ch_input_for_fastqc )
+        ch_versions = ch_versions.mix(FALCO.out.versions.first())
+    } else {
+        FASTQC ( ch_input_for_fastqc )
+        ch_versions = ch_versions.mix(FASTQC.out.versions.first())
+    }
     /*
         SUBWORKFLOW: PERFORM PREPROCESSING
     */
@@ -254,7 +256,13 @@ workflow TAXPROFILER {
     ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml'))
     ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml'))
     ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect())
-    ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
+
+    if ( params.preprocessing_qc_tool == 'falco' ) {
+        ch_multiqc_files = ch_multiqc_files.mix(FALCO.out.txt.collect{it[1]}.ifEmpty([]))
+    } else {
+        ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([]))
+    }
+
 
     if (params.perform_shortread_qc) {
         ch_multiqc_files = ch_multiqc_files.mix( SHORTREAD_PREPROCESSING.out.mqc.collect{it[1]}.ifEmpty([]) )