Merge pull request #77 from genomic-medicine-sweden/add_nanopore_host_reads_removal_with_minimap2

Add nanopore host reads removal with minimap2

conf/modules.config

@@ -164,6 +164,47 @@ process {
         ]
     }
 
+    withName: MINIMAP2_INDEX {
+        ext.args = '-x map-ont'
+        publishDir = [
+            path: { "${params.outdir}/minimap2/index" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_index,
+            pattern: 'minimap2'
+        ]
+    }
+
+    withName: MINIMAP2_ALIGN {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/minimap2/align" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_mapped,
+            pattern: '*.bam'
+        ]
+    }
+
+    withName: SAMTOOLS_VIEW {
+        ext.args = '-f 4'
+        ext.prefix = { "${meta.id}.mapped.sorted" }
+        publishDir = [
+            path: { "${params.outdir}/samtools/view" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_unmapped,
+            pattern: '*.bam'
+        ]
+    }
+
+    withName: SAMTOOLS_BAM2FQ {
+        ext.prefix = { "${meta.id}_${meta.run_accession}" }
+        publishDir = [
+            path: { "${params.outdir}/samtools/bam2fq" },
+            mode: params.publish_dir_mode,
+            enabled: params.save_hostremoval_unmapped,
+            pattern: '*.fq.gz'
+        ]
+    }
+
     withName: BBMAP_BBDUK {
         ext.args =  [
                 "entropy=${params.shortread_complexityfilter_entropy}",

conf/test.config

@@ -28,7 +28,8 @@ params {
     perform_longread_clip                 = false
     perform_shortread_complexityfilter    = true
     perform_shortread_hostremoval         = true
-    shortread_hostremoval_reference       = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
+    perform_longread_hostremoval          = true
+    hostremoval_reference                 = 'https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/genomics/homo_sapiens/genome/genome.fasta'
     run_kaiju                             = true
     run_kraken2                           = true
     run_malt                              = true

docs/usage.md

@@ -191,13 +191,13 @@ You can optionally save the FASTQ output of the run merging with the `--save_com
 
 #### Host Removal
 
-Removal of possible-host reads from FASTQ files prior profiling can be activated with `--perform_shortread_hostremoval`
+Removal of possible-host reads from FASTQ files prior profiling can be activated with `--perform_shortread_hostremoval` or `--perform_longread_hostremoval`.
 
 Similarly to complexity filtering, host-removal can be useful for runtime optimisation and reduction in misclassified reads. It is not always necessary to report classification of reads from a host when you already know the host of the sample, therefore you can gain a run-time and computational advantage by removing these prior typically resource-heavy profiling with more efficient methods. Furthermore, particularly with human samples, you can reduce the number of false positives during profiling that occur due to host-sequence contamination in reference genomes on public databases.
 
 nf-core/taxprofiler currently offers host-removal via alignment against a reference genome with Bowtie2, and the use of the unaligned reads for downstream profiling.
 
-You can supply your reference genome in FASTA format with `--shortread_hostremoval_reference`. You can also optionally supply a directory containing pre-indexed Bowtie2 index files with `--shortread_hostremoval_index`, however nf-core/taxprofiler will generate this for you if necessary. Pre-supplying the directory of index files can greatly speed up the process, and these can be re-used.
+You can supply your reference genome in FASTA format with `--hostremoval_reference`. You can also optionally supply a directory containing pre-indexed Bowtie2 index files with `--shortread_hostremoval_index` or `--longread_hostremoval_index`, however nf-core/taxprofiler will generate this for you if necessary. Pre-supplying the directory of index files can greatly speed up the process, and these can be re-used.
 
 > 💡 If you have multiple taxa or sequences you wish to remove (e.g., the host genome and then also PhiX - common quality-control reagent during sequencing) you can simply concatenate the FASTAs of each taxa or sequences into a single reference file.
 

modules.json

@@ -52,6 +52,12 @@
                 "git_sha": "2d38566eca4cc15142b2ffa7c11837569b39aece"
             },
             "metaphlan3": {
+                "git_sha": "ed4dd1a928ebf4308efb720de878045f7773f8e2"
+            },
+            "minimap2/align": {
+                "git_sha": "1a5a9e7b4009dcf34e6867dd1a5a1d9a718b027b"
+            },
+            "minimap2/index": {
                 "git_sha": "e745e167c1020928ef20ea1397b6b4d230681b4d"
             },
             "multiqc": {
@@ -63,6 +69,12 @@
             "prinseqplusplus": {
                 "git_sha": "f1c5384c31e985591716afdd732cf8c2ae29d05b"
             },
+            "samtools/bam2fq": {
+                "git_sha": "5510ea39fe638594bc26ac34cadf4a84bf27d159"
+            },
+            "samtools/view": {
+                "git_sha": "6b64f9cb6c3dd3577931cc3cd032d6fb730000ce"
+            },
             "untar": {
                 "git_sha": "e080f4c8acf5760039ed12ec1f206170f3f9a918"
             }

modules/nf-core/modules/metaphlan3/main.nf

@@ -23,7 +23,7 @@ process METAPHLAN3 {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def input_type  = ("$input".endsWith(".fastq.gz")) ? "--input_type fastq" :  ("$input".contains(".fasta")) ? "--input_type fasta" : ("$input".endsWith(".bowtie2out.txt")) ? "--input_type bowtie2out" : "--input_type sam"
+    def input_type  = ("$input".endsWith(".fastq.gz") || "$input".endsWith(".fq.gz")) ? "--input_type fastq" :  ("$input".contains(".fasta")) ? "--input_type fasta" : ("$input".endsWith(".bowtie2out.txt")) ? "--input_type bowtie2out" : "--input_type sam"
     def input_data  = ("$input_type".contains("fastq")) && !meta.single_end ? "${input[0]},${input[1]}" : "$input"
     def bowtie2_out = "$input_type" == "--input_type bowtie2out" || "$input_type" == "--input_type sam" ? '' : "--bowtie2out ${prefix}.bowtie2out.txt"
 

modules/nf-core/modules/minimap2/align/main.nf

@@ -0,0 +1,48 @@
+process MINIMAP2_ALIGN {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? 'bioconda::minimap2=2.21 bioconda::samtools=1.12' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' :
+        'quay.io/biocontainers/mulled-v2-66534bcbb7031a148b13e2ad42583020b9cd25c4:1679e915ddb9d6b4abda91880c4b48857d471bd8-0' }"
+
+    input:
+    tuple val(meta), path(reads)
+    path reference
+    val bam_format
+    val cigar_paf_format
+    val cigar_bam
+
+    output:
+    tuple val(meta), path("*.paf"), optional: true, emit: paf
+    tuple val(meta), path("*.bam"), optional: true, emit: bam
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def input_reads = meta.single_end ? "$reads" : "${reads[0]} ${reads[1]}"
+    def bam_output = bam_format ? "-a | samtools sort | samtools view -@ ${task.cpus} -b -h -o ${prefix}.bam" : "-o ${prefix}.paf"
+    def cigar_paf = cigar_paf_format && !bam_format ? "-c" : ''
+    def set_cigar_bam = cigar_bam && bam_format ? "-L" : ''
+    """
+    minimap2 \\
+        $args \\
+        -t $task.cpus \\
+        $reference \\
+        $input_reads \\
+        $cigar_paf \\
+        $set_cigar_bam \\
+        $bam_output
+
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        minimap2: \$(minimap2 --version 2>&1)
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/minimap2/align/meta.yml

@@ -0,0 +1,65 @@
+name: minimap2_align
+description: A versatile pairwise aligner for genomic and spliced nucleotide sequences
+keywords:
+  - align
+  - fasta
+  - fastq
+  - genome
+  - paf
+  - reference
+tools:
+  - minimap2:
+      description: |
+        A versatile pairwise aligner for genomic and spliced nucleotide sequences.
+      homepage: https://github.com/lh3/minimap2
+      documentation: https://github.com/lh3/minimap2#uguide
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - reads:
+      type: file
+      description: |
+        List of input FASTA or FASTQ files of size 1 and 2 for single-end
+        and paired-end data, respectively.
+  - reference:
+      type: file
+      description: |
+        Reference database in FASTA format.
+  - bam_format:
+      type: boolean
+      description: Specify that output should be in BAM format
+  - cigar_paf_format:
+      type: boolean
+      description: Specify that output CIGAR should be in PAF format
+  - cigar_bam:
+      type: boolean
+      description: |
+        Write CIGAR with >65535 ops at the CG tag. This is recommended when
+        doing XYZ (https://github.com/lh3/minimap2#working-with-65535-cigar-operations)
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - paf:
+      type: file
+      description: Alignment in PAF format
+      pattern: "*.paf"
+  - bam:
+      type: file
+      description: Alignment in BAM format
+      pattern: "*.bam"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@heuermh"
+  - "@sofstam"
+  - "@sateeshperi"
+  - "@jfy133"

modules/nf-core/modules/minimap2/index/main.nf

@@ -0,0 +1,33 @@
+process MINIMAP2_INDEX {
+    label 'process_medium'
+
+    conda (params.enable_conda ? 'bioconda::minimap2=2.21' : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/minimap2:2.21--h5bf99c6_0' :
+        'quay.io/biocontainers/minimap2:2.21--h5bf99c6_0' }"
+
+    input:
+    path fasta
+
+    output:
+    path "*.mmi"        , emit: index
+    path "versions.yml" , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    """
+    minimap2 \\
+        -t $task.cpus \\
+        -d ${fasta.baseName}.mmi \\
+        $args \\
+        $fasta
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        minimap2: \$(minimap2 --version 2>&1)
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/minimap2/index/meta.yml

@@ -0,0 +1,30 @@
+name: minimap2_index
+description: Provides fasta index required by minimap2 alignment.
+keywords:
+  - index
+  - fasta
+  - reference
+tools:
+  - minimap2:
+      description: |
+        A versatile pairwise aligner for genomic and spliced nucleotide sequences.
+      homepage: https://github.com/lh3/minimap2
+      documentation: https://github.com/lh3/minimap2#uguide
+      licence: ["MIT"]
+input:
+  - fasta:
+      type: file
+      description: |
+        Reference database in FASTA format.
+output:
+  - mmi:
+      type: file
+      description: Minimap2 fasta index.
+      pattern: "*.mmi"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@yuukiiwa"
+  - "@drpatelh"

modules/nf-core/modules/samtools/bam2fq/main.nf

@@ -0,0 +1,56 @@
+process SAMTOOLS_BAM2FQ {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
+
+    input:
+    tuple val(meta), path(inputbam)
+    val split
+
+    output:
+    tuple val(meta), path("*.fq.gz"), emit: reads
+    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 (split){
+        """
+        samtools \\
+            bam2fq \\
+            $args \\
+            -@ $task.cpus \\
+            -1 ${prefix}_1.fq.gz \\
+            -2 ${prefix}_2.fq.gz \\
+            -0 ${prefix}_other.fq.gz \\
+            -s ${prefix}_singleton.fq.gz \\
+            $inputbam
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        END_VERSIONS
+        """
+    } else {
+        """
+        samtools \\
+            bam2fq \\
+            $args \\
+            -@ $task.cpus \\
+            $inputbam | gzip --no-name > ${prefix}_interleaved.fq.gz
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+        END_VERSIONS
+        """
+    }
+}

modules/nf-core/modules/samtools/bam2fq/meta.yml

@@ -0,0 +1,55 @@
+name: samtools_bam2fq
+description: |
+  The module uses bam2fq method from samtools to
+  convert a SAM, BAM or CRAM file to FASTQ format
+keywords:
+  - bam2fq
+  - samtools
+  - fastq
+tools:
+  - samtools:
+      description: Tools for dealing with SAM, BAM and CRAM files
+      homepage: None
+      documentation: http://www.htslib.org/doc/1.1/samtools.html
+      tool_dev_url: None
+      doi: ""
+      licence: ["MIT"]
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - inputbam:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - split:
+      type: boolean
+      description: |
+        TRUE/FALSE value to indicate if reads should be separated into
+        /1, /2 and if present other, or singleton.
+        Note: choosing TRUE will generate 4 different files.
+        Choosing FALSE will produce a single file, which will be interleaved in case
+        the input contains paired reads.
+
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - reads:
+      type: file
+      description: |
+        FASTQ files, which will be either a group of 4 files (read_1, read_2, other and singleton)
+        or a single interleaved .fq.gz file if the user chooses not to split the reads.
+      pattern: "*.fq.gz"
+
+authors:
+  - "@lescai"

modules/nf-core/modules/samtools/view/main.nf

@@ -0,0 +1,56 @@
+process SAMTOOLS_VIEW {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda (params.enable_conda ? "bioconda::samtools=1.15.1" : null)
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/samtools:1.15.1--h1170115_0' :
+        'quay.io/biocontainers/samtools:1.15.1--h1170115_0' }"
+
+    input:
+    tuple val(meta), path(input), path(index)
+    path fasta
+
+    output:
+    tuple val(meta), path("*.bam") , emit: bam , optional: true
+    tuple val(meta), path("*.cram"), emit: cram, optional: true
+    path  "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args2 = task.ext.args2 ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def reference = fasta ? "--reference ${fasta} -C" : ""
+    def file_type = input.getExtension()
+    if ("$input" == "${prefix}.${file_type}") error "Input and output names are the same, use \"task.ext.prefix\" to disambiguate!"
+    """
+    samtools \\
+        view \\
+        --threads ${task.cpus-1} \\
+        ${reference} \\
+        $args \\
+        $input \\
+        $args2 \\
+        > ${prefix}.${file_type}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}.bam
+    touch ${prefix}.cram
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        samtools: \$(echo \$(samtools --version 2>&1) | sed 's/^.*samtools //; s/Using.*\$//')
+    END_VERSIONS
+    """
+}

modules/nf-core/modules/samtools/view/meta.yml

@@ -0,0 +1,57 @@
+name: samtools_view
+description: filter/convert SAM/BAM/CRAM file
+keywords:
+  - view
+  - bam
+  - sam
+  - cram
+tools:
+  - samtools:
+      description: |
+        SAMtools is a set of utilities for interacting with and post-processing
+        short DNA sequence read alignments in the SAM, BAM and CRAM formats, written by Heng Li.
+        These files are generated as output by short read aligners like BWA.
+      homepage: http://www.htslib.org/
+      documentation: hhttp://www.htslib.org/doc/samtools.html
+      doi: 10.1093/bioinformatics/btp352
+      licence: ["MIT"]
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - input:
+      type: file
+      description: BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+  - index:
+      type: optional file
+      description: BAM.BAI/CRAM.CRAI file
+      pattern: "*.{.bai,.crai}"
+  - fasta:
+      type: optional file
+      description: Reference file the CRAM was created with
+      pattern: "*.{fasta,fa}"
+output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+  - bam:
+      type: file
+      description: filtered/converted BAM/SAM file
+      pattern: "*.{bam,sam}"
+  - cram:
+      type: file
+      description: filtered/converted CRAM file
+      pattern: "*.cram"
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+authors:
+  - "@drpatelh"
+  - "@joseespinosa"
+  - "@FriederikeHanssen"

nextflow.config

@@ -82,12 +82,15 @@ params {
 
     // Host Removal
     perform_shortread_hostremoval          = false
-    shortread_hostremoval_reference   = null
+    perform_longread_hostremoval           = false
+    hostremoval_reference                  = null
     shortread_hostremoval_index            = null
+    longread_hostremoval_index             = null
     save_hostremoval_index                 = false
     save_hostremoval_mapped                = false
     save_hostremoval_unmapped              = false
 
+
     // MALT
     run_malt                   = false
     malt_mode                  = 'BlastN'

nextflow_schema.json

@@ -362,7 +362,10 @@
         "perform_shortread_hostremoval": {
             "type": "boolean"
         },
-        "shortread_hostremoval_reference": {
+        "perform_longread_hostremoval": {
+            "type": "boolean"
+        },
+        "hostremoval_reference": {
             "type": "string",
             "default": "None"
         },
@@ -397,6 +400,10 @@
             "type": "string",
             "default": "tsv",
             "enum": ["blast", "xml", "txt", "daa", "sam", "tsv", "paf"]
+        },
+        "longread_hostremoval_index": {
+            "type": "string",
+            "default": "None"
         }
     }
 }

subworkflows/local/longread_hostremoval.nf

@@ -0,0 +1,47 @@
+//
+// Remove host reads via alignment and export off-target reads
+//
+
+include { MINIMAP2_INDEX             } from '../../modules/nf-core/modules/minimap2/index/main'
+include { MINIMAP2_ALIGN             } from '../../modules/nf-core/modules/minimap2/align/main'
+include { SAMTOOLS_VIEW              } from '../../modules/nf-core/modules/samtools/view/main'
+include { SAMTOOLS_BAM2FQ            } from '../../modules/nf-core/modules/samtools/bam2fq/main'
+
+workflow LONGREAD_HOSTREMOVAL {
+    take:
+    reads     // [ [ meta ], [ reads ] ]
+    reference // /path/to/fasta
+    index     // /path/to/index
+
+    main:
+    ch_versions       = Channel.empty()
+    ch_multiqc_files  = Channel.empty()
+
+    if ( !params.longread_hostremoval_index ) {
+        ch_minimap2_index = MINIMAP2_INDEX ( reference ).index
+        ch_versions       = ch_versions.mix( MINIMAP2_INDEX.out.versions )
+    } else {
+        ch_minimap2_index = index
+    }
+
+    MINIMAP2_ALIGN ( reads, ch_minimap2_index, true, false, false )
+    ch_versions        = ch_versions.mix( MINIMAP2_ALIGN.out.versions.first() )
+    ch_minimap2_mapped = MINIMAP2_ALIGN.out.bam
+        .map {
+            meta, reads ->
+                [ meta, reads, [] ]
+        }
+
+
+    SAMTOOLS_VIEW ( ch_minimap2_mapped , [] )
+    ch_versions      = ch_versions.mix( SAMTOOLS_VIEW.out.versions.first() )
+
+    SAMTOOLS_BAM2FQ ( SAMTOOLS_VIEW.out.bam, false )
+    ch_versions      = ch_versions.mix( SAMTOOLS_BAM2FQ.out.versions.first() )
+
+
+    emit:
+    reads    = SAMTOOLS_BAM2FQ.out.reads   // channel: [ val(meta), [ reads ] ]
+    versions = ch_versions                 // channel: [ versions.yml ]
+}
+

workflows/taxprofiler.nf

@@ -11,7 +11,7 @@ WorkflowTaxprofiler.initialise(params, log)
 
 // TODO nf-core: Add all file path parameters for the pipeline to the list below
 // Check input path parameters to see if they exist
-def checkPathParamList = [ params.input, params.databases, params.shortread_hostremoval_reference,
+def checkPathParamList = [ params.input, params.databases, params.hostremoval_reference,
                             params.shortread_hostremoval_index, params.multiqc_config
                         ]
 for (param in checkPathParamList) { if (param) { file(param, checkIfExists: true) } }
@@ -22,11 +22,12 @@ if (params.databases) { ch_databases = file(params.databases) } else { exit 1, '
 if (params.shortread_clipmerge_mergepairs && params.run_malt ) log.warn "[nf-core/taxprofiler] MALT does not accept uncollapsed paired-reads. Pairs will be profiled as separate files."
 if (params.shortread_clipmerge_excludeunmerged && !params.shortread_clipmerge_mergepairs) exit 1, "ERROR: [nf-core/taxprofiler] cannot include unmerged reads when merging not turned on. Please specify --shortread_clipmerge_mergepairs"
 
-if (params.perform_shortread_hostremoval && !params.shortread_hostremoval_reference) { exit 1, "ERROR: [nf-core/taxprofiler] --shortread_hostremoval requested but no --shortread_hostremoval_reference FASTA supplied. Check input." }
+if (params.perform_shortread_hostremoval && !params.hostremoval_reference) { exit 1, "ERROR: [nf-core/taxprofiler] --shortread_hostremoval requested but no --hostremoval_reference FASTA supplied. Check input." }
-if (!params.shortread_hostremoval_reference && params.shortread_hostremoval_reference_index) { exit 1, "ERROR: [nf-core/taxprofiler] --shortread_hostremoval_index provided but no --shortread_hostremoval_reference FASTA supplied. Check input." }
+if (!params.hostremoval_reference && params.hostremoval_reference_index) { exit 1, "ERROR: [nf-core/taxprofiler] --shortread_hostremoval_index provided but no --hostremoval_reference FASTA supplied. Check input." }
 
-if (params.shortread_hostremoval_reference ) { ch_reference       = file(params.shortread_hostremoval_reference) }
+if (params.hostremoval_reference           ) { ch_reference = file(params.hostremoval_reference) }
-if (params.shortread_hostremoval_index     ) { ch_reference_index = file(params.shortread_hostremoval_index    ) } else { ch_reference_index = [] }
+if (params.shortread_hostremoval_index     ) { ch_shortread_reference_index = file(params.shortread_hostremoval_index    ) } else { ch_shortread_reference_index = [] }
+if (params.longread_hostremoval_index      ) { ch_longread_reference_index  = file(params.longread_hostremoval_index     ) } else { ch_longread_reference_index  = [] }
 
 /*
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -52,6 +53,7 @@ include { DB_CHECK                      } from '../subworkflows/local/db_check'
 include { SHORTREAD_PREPROCESSING       } from '../subworkflows/local/shortread_preprocessing'
 include { LONGREAD_PREPROCESSING        } from '../subworkflows/local/longread_preprocessing'
 include { SHORTREAD_HOSTREMOVAL         } from '../subworkflows/local/shortread_hostremoval'
+include { LONGREAD_HOSTREMOVAL          } from '../subworkflows/local/longread_hostremoval'
 include { SHORTREAD_COMPLEXITYFILTERING } from '../subworkflows/local/shortread_complexityfiltering'
 include { PROFILING                     } from '../subworkflows/local/profiling'
 
@@ -141,16 +143,23 @@ workflow TAXPROFILER {
     */
 
     if ( params.perform_shortread_hostremoval ) {
-        ch_shortreads_hostremoved = SHORTREAD_HOSTREMOVAL ( ch_shortreads_filtered, ch_reference, ch_reference_index ).reads
+        ch_shortreads_hostremoved = SHORTREAD_HOSTREMOVAL ( ch_shortreads_filtered, ch_reference, ch_shortread_reference_index ).reads
         ch_versions = ch_versions.mix(SHORTREAD_HOSTREMOVAL.out.versions)
     } else {
         ch_shortreads_hostremoved = ch_shortreads_filtered
     }
 
+    if ( params.perform_longread_hostremoval ) {
+        ch_longreads_hostremoved = LONGREAD_HOSTREMOVAL ( ch_longreads_preprocessed, ch_reference, ch_longread_reference_index ).reads
+        ch_versions = ch_versions.mix(LONGREAD_HOSTREMOVAL.out.versions)
+    } else {
+        ch_longreads_hostremoved = ch_longreads_preprocessed
+    }
+
     if ( params.perform_runmerging ) {
 
         ch_reads_for_cat_branch = ch_shortreads_hostremoved
-            .mix( ch_longreads_preprocessed )
+            .mix( ch_longreads_hostremoved )
             .map {
                 meta, reads ->
                     def meta_new = meta.clone()
@@ -182,7 +191,7 @@ workflow TAXPROFILER {
 
     } else {
         ch_reads_runmerged = ch_shortreads_hostremoved
-            .mix( ch_longreads_preprocessed, INPUT_CHECK.out.fasta )
+            .mix( ch_longreads_hostremoved, INPUT_CHECK.out.fasta )
     }
 
     /*