From d65991c9069312be9bd565c13c987525bf498cb5 Mon Sep 17 00:00:00 2001
From: TheOafidian <tim.van.rillaer@hotmail.com>
Date: Mon, 5 Jun 2023 21:09:09 +0200
Subject: [PATCH 01/20] Initial script

---
 modules/nf-core/metabuli/classify/main.nf | 65 +++++++++++++++++++++++
 1 file changed, 65 insertions(+)
 create mode 100644 modules/nf-core/metabuli/classify/main.nf

diff --git a/modules/nf-core/metabuli/classify/main.nf b/modules/nf-core/metabuli/classify/main.nf
new file mode 100644
index 00000000000..e6c54a51f3c
--- /dev/null
+++ b/modules/nf-core/metabuli/classify/main.nf
@@ -0,0 +1,65 @@
+// TODO nf-core: If in doubt look at other nf-core/modules to see how we are doing things! :)
+//               https://github.com/nf-core/modules/tree/master/modules/nf-core/
+//               You can also ask for help via your pull request or on the #modules channel on the nf-core Slack workspace:
+//               https://nf-co.re/join
+// TODO nf-core: A module file SHOULD only define input and output files as command-line parameters.
+//               All other parameters MUST be provided using the "task.ext" directive, see here:
+//               https://www.nextflow.io/docs/latest/process.html#ext
+//               where "task.ext" is a string.
+//               Any parameters that need to be evaluated in the context of a particular sample
+//               e.g. single-end/paired-end data MUST also be defined and evaluated appropriately.
+// TODO nf-core: Software that can be piped together SHOULD be added to separate module files
+//               unless there is a run-time, storage advantage in implementing in this way
+//               e.g. it's ok to have a single module for bwa to output BAM instead of SAM:
+//                 bwa mem | samtools view -B -T ref.fasta
+// TODO nf-core: Optional inputs are not currently supported by Nextflow. However, using an empty
+//               list (`[]`) instead of a file can be used to work around this issue.
+
+process METABULI_CLASSIFY {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "bioconda::metabuli=1.0.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/metabuli:1.0.0--pl5321hf1761c0_0':
+        'biocontainers/1.0.0--pl5321hf1761c0_0' }"
+
+    input:
+    // TODO nf-core: Where applicable please provide/convert compressed files as input/output
+    //               e.g. "*.fastq.gz" and NOT "*.fastq", "*.bam" and NOT "*.sam" etc.
+    tuple val(meta), path(fastas)
+    path(db)
+
+    output:
+    tuple val(meta), path("*_classifications.tsv"), emit: classification
+    tuple val(meta), path("*_report.tsv"), emit: report
+    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 = meta.single_end ? "--seq_mode 1 ${fastas}" : "${fastas}"
+    // TODO nf-core: Where possible, a command MUST be provided to obtain the version number of the software e.g. 1.10
+    //               If the software is unable to output a version number on the command-line then it can be manually specified
+    //               e.g. https://github.com/nf-core/modules/blob/master/modules/nf-core/homer/annotatepeaks/main.nf
+    //               Each software used MUST provide the software name and version number in the YAML version file (versions.yml)
+    // TODO nf-core: It MUST be possible to pass additional parameters to the tool as a command-line string via the "task.ext.args" directive
+    """
+    metabuli \\
+        classify \\
+        $args \\
+        --threads $task.cpus \\
+        ${input}
+        ${database}
+        ${prefix} \\
+        ${prefix}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        metabuli: \$(echo \$(metabuli 2>&1) | grep Version | sed 's/^metabuli Version: //;))
+    END_VERSIONS
+    """
+}

From 92cb0546ea4032478fccae16efc0fb617b452695 Mon Sep 17 00:00:00 2001
From: TheOafidian <tim.van.rillaer@hotmail.com>
Date: Mon, 5 Jun 2023 21:24:11 +0200
Subject: [PATCH 02/20] Initial meta

---
 modules/nf-core/metabuli/classify/meta.yml | 55 ++++++++++++++++++++++
 1 file changed, 55 insertions(+)
 create mode 100644 modules/nf-core/metabuli/classify/meta.yml

diff --git a/modules/nf-core/metabuli/classify/meta.yml b/modules/nf-core/metabuli/classify/meta.yml
new file mode 100644
index 00000000000..ffae38def0b
--- /dev/null
+++ b/modules/nf-core/metabuli/classify/meta.yml
@@ -0,0 +1,55 @@
+name: "metabuli_classify"
+## TODO nf-core: Add a description of the module and list keywords
+description: Classify FASTA files against a metabuli database
+keywords:
+  - metabuli
+  - metagenomics
+  - profiling
+  - taxonomy
+  - k-mer
+  - classify
+  - classification
+tools:
+  - "metabuli":
+      description: "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid"
+      homepage: "https://github.com/steineggerlab/Metabuli"
+      documentation: "https://github.com/steineggerlab/Metabuli#readme"
+      tool_dev_url: "https://github.com/steineggerlab/Metabuli"
+      doi: "https://doi.org/10.1101/2023.05.31.543018"
+      licence: "['GPL v3']"
+
+input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
+    - fastas:
+      type: file
+      description: single or paired FASTA files, optionally gzipped
+      pattern: "*.{fa,fa.gz,fasta,fasta.gz,fna,fna.gz}"
+    - db:
+      type: file
+      description: Metabuli databse file from build or custom made.
+
+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"
+  - classification:
+      type: file
+      description: Overview reads and their classification
+      pattern: "*_classifications.tsv"
+  - report:
+      type: file
+      description: Proportions of reads assigned to each taxon
+      pattern: "*_report.tsv"
+
+authors:
+  - "@TheOafidian"

From 96669023a1e3f34bce53d6a921fc23c01a33f8d0 Mon Sep 17 00:00:00 2001
From: TheOafidian <tim.van.rillaer@hotmail.com>
Date: Tue, 6 Jun 2023 01:27:51 +0200
Subject: [PATCH 03/20] Module only accepts fasta

Use seqtk downstream to convert fastqs
---
 modules/nf-core/metabuli/classify/main.nf  | 26 +---------------------
 modules/nf-core/metabuli/classify/meta.yml | 13 +++++------
 2 files changed, 7 insertions(+), 32 deletions(-)

diff --git a/modules/nf-core/metabuli/classify/main.nf b/modules/nf-core/metabuli/classify/main.nf
index e6c54a51f3c..930f5e42287 100644
--- a/modules/nf-core/metabuli/classify/main.nf
+++ b/modules/nf-core/metabuli/classify/main.nf
@@ -1,20 +1,3 @@
-// TODO nf-core: If in doubt look at other nf-core/modules to see how we are doing things! :)
-//               https://github.com/nf-core/modules/tree/master/modules/nf-core/
-//               You can also ask for help via your pull request or on the #modules channel on the nf-core Slack workspace:
-//               https://nf-co.re/join
-// TODO nf-core: A module file SHOULD only define input and output files as command-line parameters.
-//               All other parameters MUST be provided using the "task.ext" directive, see here:
-//               https://www.nextflow.io/docs/latest/process.html#ext
-//               where "task.ext" is a string.
-//               Any parameters that need to be evaluated in the context of a particular sample
-//               e.g. single-end/paired-end data MUST also be defined and evaluated appropriately.
-// TODO nf-core: Software that can be piped together SHOULD be added to separate module files
-//               unless there is a run-time, storage advantage in implementing in this way
-//               e.g. it's ok to have a single module for bwa to output BAM instead of SAM:
-//                 bwa mem | samtools view -B -T ref.fasta
-// TODO nf-core: Optional inputs are not currently supported by Nextflow. However, using an empty
-//               list (`[]`) instead of a file can be used to work around this issue.
-
 process METABULI_CLASSIFY {
     tag "$meta.id"
     label 'process_medium'
@@ -25,8 +8,6 @@ process METABULI_CLASSIFY {
         'biocontainers/1.0.0--pl5321hf1761c0_0' }"
 
     input:
-    // TODO nf-core: Where applicable please provide/convert compressed files as input/output
-    //               e.g. "*.fastq.gz" and NOT "*.fastq", "*.bam" and NOT "*.sam" etc.
     tuple val(meta), path(fastas)
     path(db)
 
@@ -42,18 +23,13 @@ process METABULI_CLASSIFY {
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
     def input = meta.single_end ? "--seq_mode 1 ${fastas}" : "${fastas}"
-    // TODO nf-core: Where possible, a command MUST be provided to obtain the version number of the software e.g. 1.10
-    //               If the software is unable to output a version number on the command-line then it can be manually specified
-    //               e.g. https://github.com/nf-core/modules/blob/master/modules/nf-core/homer/annotatepeaks/main.nf
-    //               Each software used MUST provide the software name and version number in the YAML version file (versions.yml)
-    // TODO nf-core: It MUST be possible to pass additional parameters to the tool as a command-line string via the "task.ext.args" directive
     """
     metabuli \\
         classify \\
         $args \\
         --threads $task.cpus \\
         ${input}
-        ${database}
+        ${db}
         ${prefix} \\
         ${prefix}
 
diff --git a/modules/nf-core/metabuli/classify/meta.yml b/modules/nf-core/metabuli/classify/meta.yml
index ffae38def0b..9e515617a02 100644
--- a/modules/nf-core/metabuli/classify/meta.yml
+++ b/modules/nf-core/metabuli/classify/meta.yml
@@ -1,5 +1,4 @@
 name: "metabuli_classify"
-## TODO nf-core: Add a description of the module and list keywords
 description: Classify FASTA files against a metabuli database
 keywords:
   - metabuli
@@ -15,7 +14,7 @@ tools:
       homepage: "https://github.com/steineggerlab/Metabuli"
       documentation: "https://github.com/steineggerlab/Metabuli#readme"
       tool_dev_url: "https://github.com/steineggerlab/Metabuli"
-      doi: "https://doi.org/10.1101/2023.05.31.543018"
+      doi: "10.1101/2023.05.31.543018"
       licence: "['GPL v3']"
 
 input:
@@ -24,13 +23,13 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-    - fastas:
+  - fastas:
       type: file
-      description: single or paired FASTA files, optionally gzipped
-      pattern: "*.{fa,fa.gz,fasta,fasta.gz,fna,fna.gz}"
-    - db:
+      description: single or paired FASTA files
+      pattern: "*.{fa,fasta,fna}"
+  - db:
       type: file
-      description: Metabuli databse file from build or custom made.
+      description: Metabuli database file, prebuild or custom made.
 
 output:
   - meta:

From 7a0d144c5e4eff6dd85313da980b45fbd6e852c9 Mon Sep 17 00:00:00 2001
From: TheOafidian <tim.van.rillaer@hotmail.com>
Date: Tue, 6 Jun 2023 04:19:51 +0200
Subject: [PATCH 04/20] Start testing

---
 modules/nf-core/metabuli/classify/main.nf     | 17 ++++---
 tests/config/pytest_modules.yml               |  4 ++
 .../modules/nf-core/metabuli/classify/main.nf | 50 +++++++++++++++++++
 .../nf-core/metabuli/classify/nextflow.config |  9 ++++
 .../nf-core/metabuli/classify/test.yml        | 13 +++++
 5 files changed, 85 insertions(+), 8 deletions(-)
 create mode 100644 tests/modules/nf-core/metabuli/classify/main.nf
 create mode 100644 tests/modules/nf-core/metabuli/classify/nextflow.config
 create mode 100644 tests/modules/nf-core/metabuli/classify/test.yml

diff --git a/modules/nf-core/metabuli/classify/main.nf b/modules/nf-core/metabuli/classify/main.nf
index 930f5e42287..4ed582e7614 100644
--- a/modules/nf-core/metabuli/classify/main.nf
+++ b/modules/nf-core/metabuli/classify/main.nf
@@ -5,15 +5,15 @@ process METABULI_CLASSIFY {
     conda "bioconda::metabuli=1.0.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/metabuli:1.0.0--pl5321hf1761c0_0':
-        'biocontainers/1.0.0--pl5321hf1761c0_0' }"
+        'biocontainers/metabuli:1.0.0--pl5321hf1761c0_0' }"
 
     input:
     tuple val(meta), path(fastas)
     path(db)
 
     output:
-    tuple val(meta), path("*_classifications.tsv"), emit: classification
-    tuple val(meta), path("*_report.tsv"), emit: report
+    tuple val(meta), path("*/*_classifications.tsv"), emit: classification
+    tuple val(meta), path("*/*_report.tsv"), emit: report
     path "versions.yml"           , emit: versions
 
     when:
@@ -22,20 +22,21 @@ process METABULI_CLASSIFY {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def input = meta.single_end ? "--seq_mode 1 ${fastas}" : "${fastas}"
+    def input = meta.single_end ? "--seq-mode 1 ${fastas.baseName}" : "${fastas.each{file -> file.baseName}}"
     """
+    gunzip *.gz
     metabuli \\
         classify \\
         $args \\
         --threads $task.cpus \\
-        ${input}
-        ${db}
-        ${prefix} \\
+        ${input} \\
+        ${db} \\
+        ${prefix}_out \\
         ${prefix}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        metabuli: \$(echo \$(metabuli 2>&1) | grep Version | sed 's/^metabuli Version: //;))
+        metabuli: \$(echo \$(metabuli 2>&1) | grep Version | sed 's/^metabuli Version: //';))
     END_VERSIONS
     """
 }
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index a090ee6fec6..595fbdb4c78 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -2266,6 +2266,10 @@ metabat2/metabat2:
   - modules/nf-core/metabat2/metabat2/**
   - tests/modules/nf-core/metabat2/metabat2/**
 
+metabuli/classify:
+  - modules/nf-core/metabuli/classify/**
+  - tests/modules/nf-core/metabuli/classify/**
+
 metaphlan/makedb:
   - modules/nf-core/metaphlan/makedb/**
   - tests/modules/nf-core/metaphlan/makedb/**
diff --git a/tests/modules/nf-core/metabuli/classify/main.nf b/tests/modules/nf-core/metabuli/classify/main.nf
new file mode 100644
index 00000000000..ba6ce18c668
--- /dev/null
+++ b/tests/modules/nf-core/metabuli/classify/main.nf
@@ -0,0 +1,50 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { SEQTK_SEQ } from '../../../../../modules/nf-core/seqtk/seq/main.nf'
+include { UNTAR } from '../../../../../modules/nf-core/untar/main.nf'
+include { METABULI_CLASSIFY } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
+
+// test with single end data
+workflow test_metabuli_classify_se {
+    
+    input = [
+        [ id:'test_se', single_end:true ], // meta map
+        [
+          file("${params.test_data_base}/data/genomics/sarscov2/nanopore/fastq/test_2.fastq.gz", checkIfExists: true),
+        ]
+    ]
+
+    db_archive = [
+        [ id:'test_se'], // meta map
+        file("refseq_virus.tar.gz",checkIfExists: true)
+        //file("${params.test_data_base}/data/delete_me/metabuli/classify",checkIfExists: true)
+    ]
+
+    UNTAR(db_archive)
+    SEQTK_SEQ(input)
+    METABULI_CLASSIFY ( SEQTK_SEQ.out.fastx , UNTAR.out.untar.map{it[1]})
+}
+
+// test with paired end data
+workflow test_metabuli_classify_pe {
+    
+    input = [
+        [ id:'test_pe', single_end:false ], // meta map
+        [
+          file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_1.fastq.gz", checkIfExists: true),
+          file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_2.fastq.gz", checkIfExists: true),
+        ]
+    ]
+
+    db_archive = [
+        [ id:'test_pe', single_end:false ], // meta map
+        file("refseq_virus.tar.gz",checkIfExists: true)
+        //file("${params.test_data_base}/data/delete_me/metabuli/classify",checkIfExists: true)
+    ]
+
+    UNTAR(db_archive)
+    // TODO: transform both reads to fasta prior to classification
+    //METABULI_CLASSIFY ( (fastas) , UNTAR.out.untar.map{it[1]})
+}
diff --git a/tests/modules/nf-core/metabuli/classify/nextflow.config b/tests/modules/nf-core/metabuli/classify/nextflow.config
new file mode 100644
index 00000000000..d3c9e4d170c
--- /dev/null
+++ b/tests/modules/nf-core/metabuli/classify/nextflow.config
@@ -0,0 +1,9 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+    withName: SEQTK_SEQ {
+        ext.args = "-a"
+    }
+}
+
diff --git a/tests/modules/nf-core/metabuli/classify/test.yml b/tests/modules/nf-core/metabuli/classify/test.yml
new file mode 100644
index 00000000000..b6777c8fcbe
--- /dev/null
+++ b/tests/modules/nf-core/metabuli/classify/test.yml
@@ -0,0 +1,13 @@
+## TODO nf-core: Please run the following command to build this file:
+#                nf-core modules create-test-yml metabuli/classify
+- name: "metabuli classify"
+  command: nextflow run ./tests/modules/nf-core/metabuli/classify -entry test_metabuli_classify -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/classify/nextflow.config
+  tags:
+    - "metabuli"
+    - "metabuli/classify"
+  files:
+    - path: "output/metabuli/test.bam"
+      md5sum: e667c7caad0bc4b7ac383fd023c654fc
+    - path: "output/metabuli/versions.yml"
+      md5sum: a01fe51bc4c6a3a6226fbf77b2c7cf3b
+    

From 85a872031f31a050522e553e304b072f3dbcda3c Mon Sep 17 00:00:00 2001
From: Tim <tim.van.rillaer@hotmail.com>
Date: Tue, 6 Jun 2023 19:28:00 +0200
Subject: [PATCH 05/20] Local test succeeded

---
 modules/nf-core/metabuli/classify/main.nf     |  4 +-
 .../modules/nf-core/metabuli/classify/main.nf | 60 ++++++++++++-------
 .../nf-core/metabuli/classify/nextflow.config |  8 ++-
 .../nf-core/metabuli/classify/test.yml        | 37 ++++++++----
 4 files changed, 75 insertions(+), 34 deletions(-)

diff --git a/modules/nf-core/metabuli/classify/main.nf b/modules/nf-core/metabuli/classify/main.nf
index 4ed582e7614..b2a824889ff 100644
--- a/modules/nf-core/metabuli/classify/main.nf
+++ b/modules/nf-core/metabuli/classify/main.nf
@@ -22,7 +22,7 @@ process METABULI_CLASSIFY {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def input = meta.single_end ? "--seq-mode 1 ${fastas.baseName}" : "${fastas.each{file -> file.baseName}}"
+    def input = meta.single_end ? "--seq-mode 1 ${fastas.baseName}" : "${fastas[0].baseName} ${fastas[1].baseName}"
     """
     gunzip *.gz
     metabuli \\
@@ -36,7 +36,7 @@ process METABULI_CLASSIFY {
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        metabuli: \$(echo \$(metabuli 2>&1) | grep Version | sed 's/^metabuli Version: //';))
+        metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))
     END_VERSIONS
     """
 }
diff --git a/tests/modules/nf-core/metabuli/classify/main.nf b/tests/modules/nf-core/metabuli/classify/main.nf
index ba6ce18c668..ea47316a6a3 100644
--- a/tests/modules/nf-core/metabuli/classify/main.nf
+++ b/tests/modules/nf-core/metabuli/classify/main.nf
@@ -2,9 +2,13 @@
 
 nextflow.enable.dsl = 2
 
-include { SEQTK_SEQ } from '../../../../../modules/nf-core/seqtk/seq/main.nf'
+include { SEQTK_SEQ as SEQTK_SEQ_PE } from '../../../../../modules/nf-core/seqtk/seq/main.nf'
+include { SEQTK_SEQ as SEQTK_SEQ_PE_RV } from '../../../../../modules/nf-core/seqtk/seq/main.nf'
+include { SEQTK_SEQ as SEQTK_SEQ_SE } from '../../../../../modules/nf-core/seqtk/seq/main.nf'
 include { UNTAR } from '../../../../../modules/nf-core/untar/main.nf'
-include { METABULI_CLASSIFY } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
+include { METABULI_CLASSIFY as METABULI_CLASSIFY_PE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
+include { METABULI_CLASSIFY as METABULI_CLASSIFY_SE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
+
 
 // test with single end data
 workflow test_metabuli_classify_se {
@@ -16,35 +20,51 @@ workflow test_metabuli_classify_se {
         ]
     ]
 
-    db_archive = [
-        [ id:'test_se'], // meta map
-        file("refseq_virus.tar.gz",checkIfExists: true)
+    db_archive = file("${params.localDir}/modules/refseq_virus.tar.gz",checkIfExists: true)
         //file("${params.test_data_base}/data/delete_me/metabuli/classify",checkIfExists: true)
-    ]
 
-    UNTAR(db_archive)
-    SEQTK_SEQ(input)
-    METABULI_CLASSIFY ( SEQTK_SEQ.out.fastx , UNTAR.out.untar.map{it[1]})
+    UNTAR( [[:], db_archive])
+    SEQTK_SEQ_SE(input)
+    METABULI_CLASSIFY_SE ( SEQTK_SEQ_SE.out.fastx , UNTAR.out.untar.map{it[1]})
 }
 
 // test with paired end data
 workflow test_metabuli_classify_pe {
     
-    input = [
-        [ id:'test_pe', single_end:false ], // meta map
+    input = Channel.from(
+        [[ id:'test_pe', single_end:false ], // meta map
         [
           file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_1.fastq.gz", checkIfExists: true),
           file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_2.fastq.gz", checkIfExists: true),
-        ]
-    ]
+        ]],
+        [[ id:'test_pe2', single_end:false ], // meta map
+        [
+          file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_1.fastq.gz", checkIfExists: true),
+          file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_2.fastq.gz", checkIfExists: true),
+        ]]
+    )
+    
 
-    db_archive = [
-        [ id:'test_pe', single_end:false ], // meta map
-        file("refseq_virus.tar.gz",checkIfExists: true)
+    db_archive = file("${params.localDir}/modules/refseq_virus.tar.gz",checkIfExists: true)
+        //TODO Replace with remote database (and make a smaller one)
         //file("${params.test_data_base}/data/delete_me/metabuli/classify",checkIfExists: true)
-    ]
 
-    UNTAR(db_archive)
-    // TODO: transform both reads to fasta prior to classification
-    //METABULI_CLASSIFY ( (fastas) , UNTAR.out.untar.map{it[1]})
+    UNTAR([[:], db_archive])
+    //transform pe reads to fasta prior to classification
+    
+    input.map{meta, reads -> [meta, reads[0]]}
+      .set{fw_reads}
+
+    input.map{meta, reads -> [meta, reads[1]]}
+      .set{rv_reads}
+
+    SEQTK_SEQ_PE(fw_reads)
+
+    SEQTK_SEQ_PE_RV(rv_reads)
+    
+    fastas = SEQTK_SEQ_PE.out.fastx
+      .combine(SEQTK_SEQ_PE_RV.out.fastx, by: 0)
+      .map{meta, read1, read2 -> [meta, [read1, read2]]}
+
+    METABULI_CLASSIFY_PE ( fastas , UNTAR.out.untar.map{it[1]})
 }
diff --git a/tests/modules/nf-core/metabuli/classify/nextflow.config b/tests/modules/nf-core/metabuli/classify/nextflow.config
index d3c9e4d170c..86ef29a269e 100644
--- a/tests/modules/nf-core/metabuli/classify/nextflow.config
+++ b/tests/modules/nf-core/metabuli/classify/nextflow.config
@@ -1,9 +1,15 @@
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-    
+    localDir = "/mnt/d/tim/Projects"
+
     withName: SEQTK_SEQ {
         ext.args = "-a"
     }
+
+    withName: SEQTK_SEQ_PE_RV {
+        ext.args = "-a"
+        ext.prefix = "reverse"
+    }
 }
 
diff --git a/tests/modules/nf-core/metabuli/classify/test.yml b/tests/modules/nf-core/metabuli/classify/test.yml
index b6777c8fcbe..83d2927a9e9 100644
--- a/tests/modules/nf-core/metabuli/classify/test.yml
+++ b/tests/modules/nf-core/metabuli/classify/test.yml
@@ -1,13 +1,28 @@
-## TODO nf-core: Please run the following command to build this file:
-#                nf-core modules create-test-yml metabuli/classify
-- name: "metabuli classify"
-  command: nextflow run ./tests/modules/nf-core/metabuli/classify -entry test_metabuli_classify -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/classify/nextflow.config
+- name: metabuli classify test_metabuli_classify_se
+  command: nextflow run ./tests/modules/nf-core/metabuli/classify -entry test_metabuli_classify_se -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/classify/nextflow.config
   tags:
-    - "metabuli"
-    - "metabuli/classify"
+    - metabuli/classify
+    - metabuli
   files:
-    - path: "output/metabuli/test.bam"
-      md5sum: e667c7caad0bc4b7ac383fd023c654fc
-    - path: "output/metabuli/versions.yml"
-      md5sum: a01fe51bc4c6a3a6226fbf77b2c7cf3b
-    
+    - path: output/metabuli/test_se_out/test_se_classifications.tsv
+      contains:
+        - "2697049"
+    - path: output/metabuli/test_se_out/test_se_report.tsv
+      md5sum: 21efd0f1c3c9b988e43e9f6c7add67ef
+    - path: output/metabuli/versions.yml
+
+- name: metabuli classify test_metabuli_classify_pe
+  command: nextflow run ./tests/modules/nf-core/metabuli/classify -entry test_metabuli_classify_pe -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/classify/nextflow.config
+  tags:
+    - metabuli/classify
+    - metabuli
+  files:
+    - path: output/metabuli/test_pe2_out/test_pe2_classifications.tsv
+      md5sum: 5c47d641e35afc8b57955b5110da72f9
+    - path: output/metabuli/test_pe2_out/test_pe2_report.tsv
+      md5sum: 3bfc704ed233bd85b8a7cca89c0b121e
+    - path: output/metabuli/test_pe_out/test_pe_classifications.tsv
+      md5sum: 5c47d641e35afc8b57955b5110da72f9
+    - path: output/metabuli/test_pe_out/test_pe_report.tsv
+      md5sum: 3bfc704ed233bd85b8a7cca89c0b121e
+    - path: output/metabuli/versions.yml

From 648b58ef74358903dc456d02dd94a6884b220d82 Mon Sep 17 00:00:00 2001
From: Tim <tim.van.rillaer@hotmail.com>
Date: Wed, 7 Jun 2023 11:14:28 +0200
Subject: [PATCH 06/20] Conditional gz

---
 modules/nf-core/metabuli/classify/main.nf | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/modules/nf-core/metabuli/classify/main.nf b/modules/nf-core/metabuli/classify/main.nf
index b2a824889ff..ec4715810e0 100644
--- a/modules/nf-core/metabuli/classify/main.nf
+++ b/modules/nf-core/metabuli/classify/main.nf
@@ -22,9 +22,19 @@ process METABULI_CLASSIFY {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def input = meta.single_end ? "--seq-mode 1 ${fastas.baseName}" : "${fastas[0].baseName} ${fastas[1].baseName}"
+    def is_compressed = meta.single_end ? fastas.getName().endsWith(".gz") : fastas[0].getName().endsWith(".gz")
+    def input = meta.single_end ? "--seq-mode 1 ${fastas}" : "${fastas[0]} ${fastas[1]}"
+    if (is_compressed && meta.single_end) {
+      input = "--seq-mode 1 ${fastas.baseName}"
+    } else if (is_compressed) {
+      input =  "${fastas[0].baseName} ${fastas[1].baseName}"
+    }
+    
     """
-    gunzip *.gz
+    if [ "$is_compressed" == "true" ]; then
+    gzip -d *.gz
+    fi
+
     metabuli \\
         classify \\
         $args \\

From d2212c1b42ab82bab864a19a1af3e551577cfed8 Mon Sep 17 00:00:00 2001
From: Tim <tim.van.rillaer@hotmail.com>
Date: Wed, 7 Jun 2023 11:46:01 +0200
Subject: [PATCH 07/20] Replaced with minimal db

---
 tests/modules/nf-core/metabuli/classify/test.yml | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/tests/modules/nf-core/metabuli/classify/test.yml b/tests/modules/nf-core/metabuli/classify/test.yml
index 83d2927a9e9..a7bd8f85d64 100644
--- a/tests/modules/nf-core/metabuli/classify/test.yml
+++ b/tests/modules/nf-core/metabuli/classify/test.yml
@@ -5,10 +5,9 @@
     - metabuli
   files:
     - path: output/metabuli/test_se_out/test_se_classifications.tsv
-      contains:
-        - "2697049"
+      md5sum: 3870c45887908e8e4b3c60c23ae3e008
     - path: output/metabuli/test_se_out/test_se_report.tsv
-      md5sum: 21efd0f1c3c9b988e43e9f6c7add67ef
+      md5sum: 686930217102cd8d249906387de3e6b5
     - path: output/metabuli/versions.yml
 
 - name: metabuli classify test_metabuli_classify_pe
@@ -18,11 +17,11 @@
     - metabuli
   files:
     - path: output/metabuli/test_pe2_out/test_pe2_classifications.tsv
-      md5sum: 5c47d641e35afc8b57955b5110da72f9
+      md5sum: d3b961b3a1e3f1181d182583ee246523
     - path: output/metabuli/test_pe2_out/test_pe2_report.tsv
-      md5sum: 3bfc704ed233bd85b8a7cca89c0b121e
+      md5sum: 0cc7f995f15304368574b4217cdd13b9
     - path: output/metabuli/test_pe_out/test_pe_classifications.tsv
-      md5sum: 5c47d641e35afc8b57955b5110da72f9
+      md5sum: d3b961b3a1e3f1181d182583ee246523
     - path: output/metabuli/test_pe_out/test_pe_report.tsv
-      md5sum: 3bfc704ed233bd85b8a7cca89c0b121e
+      md5sum: 0cc7f995f15304368574b4217cdd13b9
     - path: output/metabuli/versions.yml

From e4ea479d5a4c3285ba1f3764b8deba518fcb67f1 Mon Sep 17 00:00:00 2001
From: Tim <tim.van.rillaer@hotmail.com>
Date: Sun, 11 Jun 2023 04:06:01 +0200
Subject: [PATCH 08/20] Add metabuli build

---
 modules/nf-core/metabuli/build/main.nf        | 53 +++++++++++++++++++
 modules/nf-core/metabuli/build/meta.yml       | 48 +++++++++++++++++
 tests/config/pytest_modules.yml               |  4 ++
 tests/modules/nf-core/metabuli/build/main.nf  | 47 ++++++++++++++++
 .../nf-core/metabuli/build/nextflow.config    |  5 ++
 5 files changed, 157 insertions(+)
 create mode 100644 modules/nf-core/metabuli/build/main.nf
 create mode 100644 modules/nf-core/metabuli/build/meta.yml
 create mode 100644 tests/modules/nf-core/metabuli/build/main.nf
 create mode 100644 tests/modules/nf-core/metabuli/build/nextflow.config

diff --git a/modules/nf-core/metabuli/build/main.nf b/modules/nf-core/metabuli/build/main.nf
new file mode 100644
index 00000000000..e938e442641
--- /dev/null
+++ b/modules/nf-core/metabuli/build/main.nf
@@ -0,0 +1,53 @@
+
+process METABULI_BUILD {
+    tag 'build'
+    label 'process_single'
+
+    conda "bioconda::metabuli=1.0.0"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/metabuli:1.0.0--pl5321hf1761c0_0':
+        'biocontainers/metabuli:1.0.0--pl5321hf1761c0_0' }"
+
+    input:
+    path(genomes)
+    path(acc2taxid)
+    path(db)
+
+    output:
+    path "metabuli_db.tar.gz", emit: db
+    path "versions.yml"           , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def args_lib = task.ext.args_lib ?: ''
+    """
+    ls $genomes > fastas.txt
+    metabuli \\
+        add-to-library \\
+        fastas.txt \\
+        $acc2taxid \\
+        $db
+        $args_lib
+
+    ls $db/library > lib.txt
+    metabuli \\
+        build \\
+        --threads $task.cpus \\
+        $db \\
+        lib.txt \\
+        $acc2taxid \\
+        $args
+    
+    mkdir metabuli_db
+    mv $db/!(*y) metabuli_db
+    tar -czf "${db}.tar.gz" metabuli_db
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/metabuli/build/meta.yml b/modules/nf-core/metabuli/build/meta.yml
new file mode 100644
index 00000000000..b4e0b5d04e5
--- /dev/null
+++ b/modules/nf-core/metabuli/build/meta.yml
@@ -0,0 +1,48 @@
+name: "metabuli_build"
+description: Build a database needed to use the metabuli classification tool
+keywords:
+  - metabuli
+  - metagenomics
+  - profiling
+  - taxonomy
+  - database
+tools:
+  - "metabuli":
+      description: "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid"
+      homepage: "https://github.com/steineggerlab/Metabuli"
+      documentation: "https://github.com/steineggerlab/Metabuli#readme"
+      tool_dev_url: "https://github.com/steineggerlab/Metabuli"
+      doi: "10.1101/2023.05.31.543018"
+      licence: "['GPL v3']"
+
+input:
+  - genomes:
+      type: file
+      description: Genome files that serve as entries in the database
+      pattern: "*.{fa,fasta,fna}"
+  - acc2taxid:
+      type: file
+      description: |
+        Accession number to taxid file. 
+        A four column tsv with the following header: 
+        accession, accession.revision, taxid, gi.
+  - db:
+      type: directory
+      description: |
+        Output folder name for the database. 
+        If the taxonomy-path optional parameter is not set to a directory 
+        containing names.dmp and nodes.dmp, this directory needs 
+        to contain a folder named taxonomy containing those two files.
+
+output:
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  - db:
+      type: file
+      description: Compressed metabuli database
+      pattern: "*.tar.gz"
+
+authors:
+  - "@TheOafidian"
diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 595fbdb4c78..2ab1ac941d0 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -2266,6 +2266,10 @@ metabat2/metabat2:
   - modules/nf-core/metabat2/metabat2/**
   - tests/modules/nf-core/metabat2/metabat2/**
 
+metabuli/build:
+  - modules/nf-core/metabuli/build/**
+  - tests/modules/nf-core/metabuli/build/**
+
 metabuli/classify:
   - modules/nf-core/metabuli/classify/**
   - tests/modules/nf-core/metabuli/classify/**
diff --git a/tests/modules/nf-core/metabuli/build/main.nf b/tests/modules/nf-core/metabuli/build/main.nf
new file mode 100644
index 00000000000..7e7e7cfdf69
--- /dev/null
+++ b/tests/modules/nf-core/metabuli/build/main.nf
@@ -0,0 +1,47 @@
+#!/usr/bin/env nextflow
+
+nextflow.enable.dsl = 2
+
+include { METABULI_BUILD } from '../../../../../modules/nf-core/metabuli/build/main.nf'
+
+process BUILD_ACC2TAXID {
+    input:
+      path(genomes)
+    output:
+      path(acc2taxid)
+
+    script:
+    """
+    echo -e "accession\taccession.version\ttaxid\tgi" > acc2taxid
+    accessionv=\$(cat ${genomes} | head -n1 | 
+                  cut -d " " -f1 | sed 's/>//')
+    echo -e "\${accessionv%.*}\t\$accessionv\t2697049\t111" >> acc2taxid
+    """
+}
+
+process CREATE_TAXONOMY_FOLDER{
+    input:
+    path(dmpfiles)
+
+    output:
+    path(db)
+
+    script:
+    """
+    mkdir -p db/taxonomy
+    mv *.dmp db/taxonomy
+    """
+
+}
+
+workflow test_metabuli_build {
+    
+    genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
+    dmp_files = [
+        file("${params.test_data_base}/data/genomics/sarscov2/metagenome/names.dmp"),
+        file("${params.test_data_base}/data/genomics/sarscov2/metagenome/nodes.dmp")
+    ]
+    acc2taxid = BUILD_ACC2TAXID(genome)
+    tax = CREATE_TAXONOMY_FOLDER(dmp_files) 
+    METABULI_BUILD ( genome, acc2taxid, tax )
+}
diff --git a/tests/modules/nf-core/metabuli/build/nextflow.config b/tests/modules/nf-core/metabuli/build/nextflow.config
new file mode 100644
index 00000000000..50f50a7a357
--- /dev/null
+++ b/tests/modules/nf-core/metabuli/build/nextflow.config
@@ -0,0 +1,5 @@
+process {
+
+    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+    
+}
\ No newline at end of file

From 3947e0d53cba176234537ee8f3cd1d561b9a08dd Mon Sep 17 00:00:00 2001
From: Tim <tim.van.rillaer@hotmail.com>
Date: Sun, 11 Jun 2023 21:11:47 +0200
Subject: [PATCH 09/20] Add build module and tests

---
 modules/nf-core/metabuli/build/main.nf              | 13 +++++++------
 tests/modules/nf-core/metabuli/build/main.nf        |  5 +++--
 .../modules/nf-core/metabuli/build/nextflow.config  |  9 ++++++++-
 tests/modules/nf-core/metabuli/build/test.yml       |  8 ++++++++
 4 files changed, 26 insertions(+), 9 deletions(-)
 create mode 100644 tests/modules/nf-core/metabuli/build/test.yml

diff --git a/modules/nf-core/metabuli/build/main.nf b/modules/nf-core/metabuli/build/main.nf
index e938e442641..50f257b3de2 100644
--- a/modules/nf-core/metabuli/build/main.nf
+++ b/modules/nf-core/metabuli/build/main.nf
@@ -1,7 +1,7 @@
 
 process METABULI_BUILD {
     tag 'build'
-    label 'process_single'
+    label 'process_medium'
 
     conda "bioconda::metabuli=1.0.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
@@ -23,6 +23,7 @@ process METABULI_BUILD {
     script:
     def args = task.ext.args ?: ''
     def args_lib = task.ext.args_lib ?: ''
+    def skip_lib = params.skip_lib ?: false 
     """
     ls $genomes > fastas.txt
     metabuli \\
@@ -32,7 +33,7 @@ process METABULI_BUILD {
         $db
         $args_lib
 
-    ls $db/library > lib.txt
+    ls $db/library/* > lib.txt
     metabuli \\
         build \\
         --threads $task.cpus \\
@@ -40,10 +41,10 @@ process METABULI_BUILD {
         lib.txt \\
         $acc2taxid \\
         $args
-    
-    mkdir metabuli_db
-    mv $db/!(*y) metabuli_db
-    tar -czf "${db}.tar.gz" metabuli_db
+        
+    rm -r $db/library
+    tar -czf metabuli_db.tar.gz $db
+    rm -r $db
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
diff --git a/tests/modules/nf-core/metabuli/build/main.nf b/tests/modules/nf-core/metabuli/build/main.nf
index 7e7e7cfdf69..89075ead7d9 100644
--- a/tests/modules/nf-core/metabuli/build/main.nf
+++ b/tests/modules/nf-core/metabuli/build/main.nf
@@ -30,6 +30,7 @@ process CREATE_TAXONOMY_FOLDER{
     """
     mkdir -p db/taxonomy
     mv *.dmp db/taxonomy
+    touch db/taxonomy/merged.dmp
     """
 
 }
@@ -38,8 +39,8 @@ workflow test_metabuli_build {
     
     genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
     dmp_files = [
-        file("${params.test_data_base}/data/genomics/sarscov2/metagenome/names.dmp"),
-        file("${params.test_data_base}/data/genomics/sarscov2/metagenome/nodes.dmp")
+        file("${params.test_data_metabuli}/data/genomics/sarscov2/metagenome/names.dmp"),
+        file("${params.test_data_metabuli}/data/genomics/sarscov2/metagenome/nodes.dmp")
     ]
     acc2taxid = BUILD_ACC2TAXID(genome)
     tax = CREATE_TAXONOMY_FOLDER(dmp_files) 
diff --git a/tests/modules/nf-core/metabuli/build/nextflow.config b/tests/modules/nf-core/metabuli/build/nextflow.config
index 50f50a7a357..7c8e76ebcbf 100644
--- a/tests/modules/nf-core/metabuli/build/nextflow.config
+++ b/tests/modules/nf-core/metabuli/build/nextflow.config
@@ -1,5 +1,12 @@
+params {
+    test_data_metabuli = 'https://raw.githubusercontent.com/nf-core/test-datasets/metabuli'
+}    
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-    
+    withLabel:process_medium {
+        cpus   = 6
+        memory = 36.GB
+        time   = 8.h
+    }
 }
\ No newline at end of file
diff --git a/tests/modules/nf-core/metabuli/build/test.yml b/tests/modules/nf-core/metabuli/build/test.yml
new file mode 100644
index 00000000000..d2143c98872
--- /dev/null
+++ b/tests/modules/nf-core/metabuli/build/test.yml
@@ -0,0 +1,8 @@
+- name: metabuli build test_metabuli_build
+  command: nextflow run ./tests/modules/nf-core/metabuli/build -entry test_metabuli_build -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/build/nextflow.config
+  tags:
+    - metabuli
+    - metabuli/build
+  files:
+    - path: output/metabuli/metabuli_db.tar.gz
+    - path: output/metabuli/versions.yml

From 15cadac7853f9addbb17f974623dc4c3075743d0 Mon Sep 17 00:00:00 2001
From: Tim <tim.van.rillaer@hotmail.com>
Date: Thu, 15 Jun 2023 11:43:19 +0200
Subject: [PATCH 10/20] Use modules branch of testdata

---
 tests/modules/nf-core/metabuli/build/main.nf         | 4 ++--
 tests/modules/nf-core/metabuli/build/nextflow.config | 9 ++-------
 2 files changed, 4 insertions(+), 9 deletions(-)

diff --git a/tests/modules/nf-core/metabuli/build/main.nf b/tests/modules/nf-core/metabuli/build/main.nf
index 89075ead7d9..c6250b23d11 100644
--- a/tests/modules/nf-core/metabuli/build/main.nf
+++ b/tests/modules/nf-core/metabuli/build/main.nf
@@ -39,8 +39,8 @@ workflow test_metabuli_build {
     
     genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
     dmp_files = [
-        file("${params.test_data_metabuli}/data/genomics/sarscov2/metagenome/names.dmp"),
-        file("${params.test_data_metabuli}/data/genomics/sarscov2/metagenome/nodes.dmp")
+        file("${params.test_data_base}/delete_me/metabuli/names.dmp"),
+        file("${params.test_data_base}/delete_me/metabuli/nodes.dmp")
     ]
     acc2taxid = BUILD_ACC2TAXID(genome)
     tax = CREATE_TAXONOMY_FOLDER(dmp_files) 
diff --git a/tests/modules/nf-core/metabuli/build/nextflow.config b/tests/modules/nf-core/metabuli/build/nextflow.config
index 7c8e76ebcbf..c070c5fe3cf 100644
--- a/tests/modules/nf-core/metabuli/build/nextflow.config
+++ b/tests/modules/nf-core/metabuli/build/nextflow.config
@@ -1,12 +1,7 @@
-params {
-    test_data_metabuli = 'https://raw.githubusercontent.com/nf-core/test-datasets/metabuli'
-}    
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
     withLabel:process_medium {
-        cpus   = 6
-        memory = 36.GB
-        time   = 8.h
+        memory = 6.5GB
     }
-}
\ No newline at end of file
+}

From d36fb27513622af9c679315c8547e08a9391b6e4 Mon Sep 17 00:00:00 2001
From: Tim <tim.van.rillaer@hotmail.com>
Date: Fri, 16 Jun 2023 00:23:40 +0200
Subject: [PATCH 11/20] Build database from scratch

---
 .../modules/nf-core/metabuli/classify/main.nf | 27 ++++++++++++++-----
 .../nf-core/metabuli/classify/nextflow.config |  4 ++-
 2 files changed, 23 insertions(+), 8 deletions(-)

diff --git a/tests/modules/nf-core/metabuli/classify/main.nf b/tests/modules/nf-core/metabuli/classify/main.nf
index ea47316a6a3..d18f80abaca 100644
--- a/tests/modules/nf-core/metabuli/classify/main.nf
+++ b/tests/modules/nf-core/metabuli/classify/main.nf
@@ -8,6 +8,23 @@ include { SEQTK_SEQ as SEQTK_SEQ_SE } from '../../../../../modules/nf-core/seqtk
 include { UNTAR } from '../../../../../modules/nf-core/untar/main.nf'
 include { METABULI_CLASSIFY as METABULI_CLASSIFY_PE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
 include { METABULI_CLASSIFY as METABULI_CLASSIFY_SE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
+include { BUILD_ACC2TAXID, CREATE_TAXONOMY_FOLDER } from '../build'
+include { METABULI_BUILD } from '../../../../../modules/nf-core/metabuli/build/main.nf'
+
+workflow create_db {
+  genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
+  dmp_files = [
+      file("${params.test_data_base}/delete_me/metabuli/names.dmp"),
+      file("${params.test_data_base}/delete_me/metabuli/nodes.dmp")
+  ]
+  acc2taxid = BUILD_ACC2TAXID(genome)
+  tax = CREATE_TAXONOMY_FOLDER(dmp_files) 
+  METABULI_BUILD ( genome, acc2taxid, tax )
+
+  emit:
+    METABULI_BUILD.out
+}
+
 
 
 // test with single end data
@@ -19,10 +36,8 @@ workflow test_metabuli_classify_se {
           file("${params.test_data_base}/data/genomics/sarscov2/nanopore/fastq/test_2.fastq.gz", checkIfExists: true),
         ]
     ]
-
-    db_archive = file("${params.localDir}/modules/refseq_virus.tar.gz",checkIfExists: true)
-        //file("${params.test_data_base}/data/delete_me/metabuli/classify",checkIfExists: true)
-
+    
+    db_archive =  create_db().out.db
     UNTAR( [[:], db_archive])
     SEQTK_SEQ_SE(input)
     METABULI_CLASSIFY_SE ( SEQTK_SEQ_SE.out.fastx , UNTAR.out.untar.map{it[1]})
@@ -45,9 +60,7 @@ workflow test_metabuli_classify_pe {
     )
     
 
-    db_archive = file("${params.localDir}/modules/refseq_virus.tar.gz",checkIfExists: true)
-        //TODO Replace with remote database (and make a smaller one)
-        //file("${params.test_data_base}/data/delete_me/metabuli/classify",checkIfExists: true)
+    db_archive =  create_db().out.db
 
     UNTAR([[:], db_archive])
     //transform pe reads to fasta prior to classification
diff --git a/tests/modules/nf-core/metabuli/classify/nextflow.config b/tests/modules/nf-core/metabuli/classify/nextflow.config
index 86ef29a269e..d83f1b3fd12 100644
--- a/tests/modules/nf-core/metabuli/classify/nextflow.config
+++ b/tests/modules/nf-core/metabuli/classify/nextflow.config
@@ -1,8 +1,10 @@
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-    localDir = "/mnt/d/tim/Projects"
 
+    withLabel:process_medium {
+        memory = 6.5GB
+    }
     withName: SEQTK_SEQ {
         ext.args = "-a"
     }

From e839656c51088a8a7d89d658651a424330ccd89d Mon Sep 17 00:00:00 2001
From: TheOaphidian <tim.van.rillaer@hotmail.com>
Date: Wed, 21 Jun 2023 12:53:19 +0200
Subject: [PATCH 12/20] Adapt location test dumpfiles

---
 modules/nf-core/metabuli/classify/meta.yml    |  2 +-
 tests/modules/nf-core/metabuli/build/main.nf  |  4 +--
 .../nf-core/metabuli/build/nextflow.config    |  5 ++--
 .../modules/nf-core/metabuli/classify/main.nf | 27 +++++++------------
 .../nf-core/metabuli/classify/nextflow.config |  2 +-
 5 files changed, 17 insertions(+), 23 deletions(-)

diff --git a/modules/nf-core/metabuli/classify/meta.yml b/modules/nf-core/metabuli/classify/meta.yml
index 9e515617a02..0d8b2004023 100644
--- a/modules/nf-core/metabuli/classify/meta.yml
+++ b/modules/nf-core/metabuli/classify/meta.yml
@@ -26,7 +26,7 @@ input:
   - fastas:
       type: file
       description: single or paired FASTA files
-      pattern: "*.{fa,fasta,fna}"
+      pattern: "*.{fa,fasta,fna,fq,fastq}"
   - db:
       type: file
       description: Metabuli database file, prebuild or custom made.
diff --git a/tests/modules/nf-core/metabuli/build/main.nf b/tests/modules/nf-core/metabuli/build/main.nf
index c6250b23d11..b9f2617e29b 100644
--- a/tests/modules/nf-core/metabuli/build/main.nf
+++ b/tests/modules/nf-core/metabuli/build/main.nf
@@ -39,8 +39,8 @@ workflow test_metabuli_build {
     
     genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
     dmp_files = [
-        file("${params.test_data_base}/delete_me/metabuli/names.dmp"),
-        file("${params.test_data_base}/delete_me/metabuli/nodes.dmp")
+        file("${params.test_data_base}/data/delete_me/metabuli/names.dmp"),
+        file("${params.test_data_base}/data/delete_me/metabuli/nodes.dmp")
     ]
     acc2taxid = BUILD_ACC2TAXID(genome)
     tax = CREATE_TAXONOMY_FOLDER(dmp_files) 
diff --git a/tests/modules/nf-core/metabuli/build/nextflow.config b/tests/modules/nf-core/metabuli/build/nextflow.config
index c070c5fe3cf..90fe74d6bbd 100644
--- a/tests/modules/nf-core/metabuli/build/nextflow.config
+++ b/tests/modules/nf-core/metabuli/build/nextflow.config
@@ -1,7 +1,8 @@
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
+
     withLabel:process_medium {
-        memory = 6.5GB
+        memory = 6.5.GB
     }
-}
+}   
diff --git a/tests/modules/nf-core/metabuli/classify/main.nf b/tests/modules/nf-core/metabuli/classify/main.nf
index d18f80abaca..b8fbfa70b87 100644
--- a/tests/modules/nf-core/metabuli/classify/main.nf
+++ b/tests/modules/nf-core/metabuli/classify/main.nf
@@ -8,9 +8,10 @@ include { SEQTK_SEQ as SEQTK_SEQ_SE } from '../../../../../modules/nf-core/seqtk
 include { UNTAR } from '../../../../../modules/nf-core/untar/main.nf'
 include { METABULI_CLASSIFY as METABULI_CLASSIFY_PE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
 include { METABULI_CLASSIFY as METABULI_CLASSIFY_SE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
-include { BUILD_ACC2TAXID, CREATE_TAXONOMY_FOLDER } from '../build'
+include { BUILD_ACC2TAXID; CREATE_TAXONOMY_FOLDER } from '../build/main.nf'
 include { METABULI_BUILD } from '../../../../../modules/nf-core/metabuli/build/main.nf'
 
+
 workflow create_db {
   genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
   dmp_files = [
@@ -22,11 +23,10 @@ workflow create_db {
   METABULI_BUILD ( genome, acc2taxid, tax )
 
   emit:
-    METABULI_BUILD.out
+    METABULI_BUILD.out.db
 }
 
 
-
 // test with single end data
 workflow test_metabuli_classify_se {
     
@@ -37,10 +37,11 @@ workflow test_metabuli_classify_se {
         ]
     ]
     
-    db_archive =  create_db().out.db
+    create_db()
+    db_archive =  create_db.out
+    db_archive = METABULI_BUILD.out.db
     UNTAR( [[:], db_archive])
-    SEQTK_SEQ_SE(input)
-    METABULI_CLASSIFY_SE ( SEQTK_SEQ_SE.out.fastx , UNTAR.out.untar.map{it[1]})
+    METABULI_CLASSIFY_SE ( input , UNTAR.out.untar.map{it[1]})
 }
 
 // test with paired end data
@@ -59,8 +60,8 @@ workflow test_metabuli_classify_pe {
         ]]
     )
     
-
-    db_archive =  create_db().out.db
+    create_db()
+    db_archive =  create_db.out
 
     UNTAR([[:], db_archive])
     //transform pe reads to fasta prior to classification
@@ -71,13 +72,5 @@ workflow test_metabuli_classify_pe {
     input.map{meta, reads -> [meta, reads[1]]}
       .set{rv_reads}
 
-    SEQTK_SEQ_PE(fw_reads)
-
-    SEQTK_SEQ_PE_RV(rv_reads)
-    
-    fastas = SEQTK_SEQ_PE.out.fastx
-      .combine(SEQTK_SEQ_PE_RV.out.fastx, by: 0)
-      .map{meta, read1, read2 -> [meta, [read1, read2]]}
-
-    METABULI_CLASSIFY_PE ( fastas , UNTAR.out.untar.map{it[1]})
+    METABULI_CLASSIFY_PE ( input , UNTAR.out.untar.map{it[1]})
 }
diff --git a/tests/modules/nf-core/metabuli/classify/nextflow.config b/tests/modules/nf-core/metabuli/classify/nextflow.config
index d83f1b3fd12..5b77ae739ad 100644
--- a/tests/modules/nf-core/metabuli/classify/nextflow.config
+++ b/tests/modules/nf-core/metabuli/classify/nextflow.config
@@ -3,7 +3,7 @@ process {
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
     withLabel:process_medium {
-        memory = 6.5GB
+        memory = 6.5.GB
     }
     withName: SEQTK_SEQ {
         ext.args = "-a"

From c409189852105df63704e586e9716ef34aef5329 Mon Sep 17 00:00:00 2001
From: TheOaphidian <tim.van.rillaer@hotmail.com>
Date: Wed, 21 Jun 2023 13:45:22 +0200
Subject: [PATCH 13/20] Run stub for test

metabuli build requires too much RAM (aprox ~12GB) to feasibly run on GH CI containers
---
 modules/nf-core/metabuli/build/main.nf              |  9 +++++++++
 .../modules/nf-core/metabuli/build/nextflow.config  |  3 ---
 tests/modules/nf-core/metabuli/build/test.yml       | 13 +++++++++++--
 3 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/modules/nf-core/metabuli/build/main.nf b/modules/nf-core/metabuli/build/main.nf
index 50f257b3de2..b7870d1b14f 100644
--- a/modules/nf-core/metabuli/build/main.nf
+++ b/modules/nf-core/metabuli/build/main.nf
@@ -51,4 +51,13 @@ process METABULI_BUILD {
         metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))
     END_VERSIONS
     """
+
+    stub:
+    """
+    touch metabuli_db.tar.gz
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))
+    END_VERSIONS
+    """
 }
diff --git a/tests/modules/nf-core/metabuli/build/nextflow.config b/tests/modules/nf-core/metabuli/build/nextflow.config
index 90fe74d6bbd..487e5dd5d41 100644
--- a/tests/modules/nf-core/metabuli/build/nextflow.config
+++ b/tests/modules/nf-core/metabuli/build/nextflow.config
@@ -2,7 +2,4 @@ process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
 
-    withLabel:process_medium {
-        memory = 6.5.GB
-    }
 }   
diff --git a/tests/modules/nf-core/metabuli/build/test.yml b/tests/modules/nf-core/metabuli/build/test.yml
index d2143c98872..aadaa1b9279 100644
--- a/tests/modules/nf-core/metabuli/build/test.yml
+++ b/tests/modules/nf-core/metabuli/build/test.yml
@@ -1,8 +1,17 @@
 - name: metabuli build test_metabuli_build
-  command: nextflow run ./tests/modules/nf-core/metabuli/build -entry test_metabuli_build -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/build/nextflow.config
+  command: nextflow run ./tests/modules/nf-core/metabuli/build -entry test_metabuli_build -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/build/nextflow.config -stub-run
   tags:
-    - metabuli
     - metabuli/build
+    - metabuli
   files:
+    - path: output/build/acc2taxid
+      md5sum: 4ae5ac3b865cb7bf301c3cc72153a7a8
+    - path: output/create/db/taxonomy/merged.dmp
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
+    - path: output/create/db/taxonomy/names.dmp
+      md5sum: 1cacf8dba5defe61c7b31dc4342801a0
+    - path: output/create/db/taxonomy/nodes.dmp
+      md5sum: a41041a713e9fb2be5eac4723a421385
     - path: output/metabuli/metabuli_db.tar.gz
+      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/metabuli/versions.yml

From e67e9f2dd196dda2219b2cb5519cb788615ffe13 Mon Sep 17 00:00:00 2001
From: TheOaphidian <tim.van.rillaer@hotmail.com>
Date: Wed, 21 Jun 2023 13:52:23 +0200
Subject: [PATCH 14/20] Rewrite to use existing database

---
 .../modules/nf-core/metabuli/classify/main.nf | 39 ++-----------------
 1 file changed, 3 insertions(+), 36 deletions(-)

diff --git a/tests/modules/nf-core/metabuli/classify/main.nf b/tests/modules/nf-core/metabuli/classify/main.nf
index b8fbfa70b87..a2366ad0c42 100644
--- a/tests/modules/nf-core/metabuli/classify/main.nf
+++ b/tests/modules/nf-core/metabuli/classify/main.nf
@@ -2,30 +2,9 @@
 
 nextflow.enable.dsl = 2
 
-include { SEQTK_SEQ as SEQTK_SEQ_PE } from '../../../../../modules/nf-core/seqtk/seq/main.nf'
-include { SEQTK_SEQ as SEQTK_SEQ_PE_RV } from '../../../../../modules/nf-core/seqtk/seq/main.nf'
-include { SEQTK_SEQ as SEQTK_SEQ_SE } from '../../../../../modules/nf-core/seqtk/seq/main.nf'
 include { UNTAR } from '../../../../../modules/nf-core/untar/main.nf'
 include { METABULI_CLASSIFY as METABULI_CLASSIFY_PE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
 include { METABULI_CLASSIFY as METABULI_CLASSIFY_SE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
-include { BUILD_ACC2TAXID; CREATE_TAXONOMY_FOLDER } from '../build/main.nf'
-include { METABULI_BUILD } from '../../../../../modules/nf-core/metabuli/build/main.nf'
-
-
-workflow create_db {
-  genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
-  dmp_files = [
-      file("${params.test_data_base}/delete_me/metabuli/names.dmp"),
-      file("${params.test_data_base}/delete_me/metabuli/nodes.dmp")
-  ]
-  acc2taxid = BUILD_ACC2TAXID(genome)
-  tax = CREATE_TAXONOMY_FOLDER(dmp_files) 
-  METABULI_BUILD ( genome, acc2taxid, tax )
-
-  emit:
-    METABULI_BUILD.out.db
-}
-
 
 // test with single end data
 workflow test_metabuli_classify_se {
@@ -36,10 +15,8 @@ workflow test_metabuli_classify_se {
           file("${params.test_data_base}/data/genomics/sarscov2/nanopore/fastq/test_2.fastq.gz", checkIfExists: true),
         ]
     ]
-    
-    create_db()
-    db_archive =  create_db.out
-    db_archive = METABULI_BUILD.out.db
+        
+    db_archive =  file("${params.test_data_base}/data/delete_me/metabuli/metabuli_db.tar.gz", checkIfExists: true)
     UNTAR( [[:], db_archive])
     METABULI_CLASSIFY_SE ( input , UNTAR.out.untar.map{it[1]})
 }
@@ -59,18 +36,8 @@ workflow test_metabuli_classify_pe {
           file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_2.fastq.gz", checkIfExists: true),
         ]]
     )
-    
-    create_db()
-    db_archive =  create_db.out
 
+    db_archive =  file("${params.test_data_base}/data/delete_me/metabuli/metabuli_db.tar.gz", checkIfExists: true)
     UNTAR([[:], db_archive])
-    //transform pe reads to fasta prior to classification
-    
-    input.map{meta, reads -> [meta, reads[0]]}
-      .set{fw_reads}
-
-    input.map{meta, reads -> [meta, reads[1]]}
-      .set{rv_reads}
-
     METABULI_CLASSIFY_PE ( input , UNTAR.out.untar.map{it[1]})
 }

From 09815c8157b48bf92bdba23c4162830fb1e1bffe Mon Sep 17 00:00:00 2001
From: Tim <tim.van.rillaer@hotmail.com>
Date: Wed, 19 Jul 2023 10:15:32 +0200
Subject: [PATCH 15/20] Update paths and min memory needed

---
 tests/modules/nf-core/metabuli/build/main.nf  | 23 ++++---------------
 .../nf-core/metabuli/build/nextflow.config    |  3 ++-
 2 files changed, 7 insertions(+), 19 deletions(-)

diff --git a/tests/modules/nf-core/metabuli/build/main.nf b/tests/modules/nf-core/metabuli/build/main.nf
index b9f2617e29b..b665bafd1fc 100644
--- a/tests/modules/nf-core/metabuli/build/main.nf
+++ b/tests/modules/nf-core/metabuli/build/main.nf
@@ -4,21 +4,6 @@ nextflow.enable.dsl = 2
 
 include { METABULI_BUILD } from '../../../../../modules/nf-core/metabuli/build/main.nf'
 
-process BUILD_ACC2TAXID {
-    input:
-      path(genomes)
-    output:
-      path(acc2taxid)
-
-    script:
-    """
-    echo -e "accession\taccession.version\ttaxid\tgi" > acc2taxid
-    accessionv=\$(cat ${genomes} | head -n1 | 
-                  cut -d " " -f1 | sed 's/>//')
-    echo -e "\${accessionv%.*}\t\$accessionv\t2697049\t111" >> acc2taxid
-    """
-}
-
 process CREATE_TAXONOMY_FOLDER{
     input:
     path(dmpfiles)
@@ -38,11 +23,13 @@ process CREATE_TAXONOMY_FOLDER{
 workflow test_metabuli_build {
     
     genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
+    
     dmp_files = [
-        file("${params.test_data_base}/data/delete_me/metabuli/names.dmp"),
-        file("${params.test_data_base}/data/delete_me/metabuli/nodes.dmp")
+        file("${params.test_data_base}/data/delete_me/metabuli/taxonomy/names.dmp"),
+        file("${params.test_data_base}/data/delete_me/metabuli/taxonomy/nodes.dmp")
     ]
-    acc2taxid = BUILD_ACC2TAXID(genome)
+    acc2taxid = file("${params.test_data_base}/data/delete_me/metabuli/acc2taxid")
+
     tax = CREATE_TAXONOMY_FOLDER(dmp_files) 
     METABULI_BUILD ( genome, acc2taxid, tax )
 }
diff --git a/tests/modules/nf-core/metabuli/build/nextflow.config b/tests/modules/nf-core/metabuli/build/nextflow.config
index 487e5dd5d41..5c70d71b82f 100644
--- a/tests/modules/nf-core/metabuli/build/nextflow.config
+++ b/tests/modules/nf-core/metabuli/build/nextflow.config
@@ -1,5 +1,6 @@
 process {
 
     publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-
+    memory = "16GB"
+    
 }   

From 8f30f74f916f08c53a716789140bd574f946e774 Mon Sep 17 00:00:00 2001
From: Joon-Klaps <joon.klaps@kuleuven.be>
Date: Fri, 21 Jun 2024 08:14:31 +0000
Subject: [PATCH 16/20] init nf-test & add add module

---
 modules/nf-core/metabuli/add/environment.yml  |   9 +
 modules/nf-core/metabuli/add/main.nf          |  57 ++
 modules/nf-core/metabuli/add/meta.yml         |  57 ++
 .../nf-core/metabuli/add/tests/main.nf.test   |  74 +++
 modules/nf-core/metabuli/add/tests/tags.yml   |   2 +
 .../nf-core/metabuli/build/environment.yml    |   6 +
 modules/nf-core/metabuli/build/main.nf        |  12 +-
 modules/nf-core/metabuli/build/meta.yml       |  11 +-
 .../nf-core/metabuli/build/tests/main.nf.test | 597 ++++++++++++++++++
 .../metabuli/build/tests/main.nf.test.snap    | 184 ++++++
 modules/nf-core/metabuli/build/tests/tags.yml |   2 +
 .../nf-core/metabuli/classify/environment.yml |   6 +
 modules/nf-core/metabuli/classify/main.nf     |  10 +-
 modules/nf-core/metabuli/classify/meta.yml    |   3 +-
 14 files changed, 1013 insertions(+), 17 deletions(-)
 create mode 100644 modules/nf-core/metabuli/add/environment.yml
 create mode 100644 modules/nf-core/metabuli/add/main.nf
 create mode 100644 modules/nf-core/metabuli/add/meta.yml
 create mode 100644 modules/nf-core/metabuli/add/tests/main.nf.test
 create mode 100644 modules/nf-core/metabuli/add/tests/tags.yml
 create mode 100644 modules/nf-core/metabuli/build/environment.yml
 create mode 100644 modules/nf-core/metabuli/build/tests/main.nf.test
 create mode 100644 modules/nf-core/metabuli/build/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/metabuli/build/tests/tags.yml
 create mode 100644 modules/nf-core/metabuli/classify/environment.yml

diff --git a/modules/nf-core/metabuli/add/environment.yml b/modules/nf-core/metabuli/add/environment.yml
new file mode 100644
index 00000000000..44ccbb344ec
--- /dev/null
+++ b/modules/nf-core/metabuli/add/environment.yml
@@ -0,0 +1,9 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
+name: "metabuli_add"
+channels:
+  - conda-forge
+  - bioconda
+  - defaults
+dependencies:
+  - "bioconda::metabuli=1.0.5"
diff --git a/modules/nf-core/metabuli/add/main.nf b/modules/nf-core/metabuli/add/main.nf
new file mode 100644
index 00000000000..41c657fe373
--- /dev/null
+++ b/modules/nf-core/metabuli/add/main.nf
@@ -0,0 +1,57 @@
+process METABULI_ADD {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/metabuli:1.0.5--pl5321h6a68c12_1':
+        'biocontainers/metabuli:1.0.5--pl5321h6a68c12_1' }"
+
+    input:
+    tuple val(meta), path(fasta)
+    path taxonomy_names, stageAs: 'taxonomy/names.dmp'
+    path taxonomy_nodes, stageAs: 'taxonomy/nodes.dmp'
+    path accession2taxid, stageAs: 'taxonomy/*'
+
+    output:
+    tuple val(meta), path("${prefix}"), emit: db
+    path "versions.yml"               , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+
+    """
+    samtools \\
+        sort \\
+        $args \\
+        -@ $task.cpus \\
+        -o ${prefix}.bam \\
+        -T $prefix \\
+        $bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        metabuli: \$(samtools --version |& sed '1!d ; s/samtools //')
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    // TODO nf-core: A stub section should mimic the execution of the original module as best as possible
+    //               Have a look at the following examples:
+    //               Simple example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bcftools/annotate/main.nf#L47-L63
+    //               Complex example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bedtools/split/main.nf#L38-L54
+    """
+    touch ${prefix}.bam
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        metabuli: \$(samtools --version |& sed '1!d ; s/samtools //')
+    END_VERSIONS
+    """
+}
diff --git a/modules/nf-core/metabuli/add/meta.yml b/modules/nf-core/metabuli/add/meta.yml
new file mode 100644
index 00000000000..0537f1e027d
--- /dev/null
+++ b/modules/nf-core/metabuli/add/meta.yml
@@ -0,0 +1,57 @@
+---
+# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
+name: "metabuli_add"
+## TODO nf-core: Add a description of the module and list keywords
+description: write your description here
+keywords:
+  - sort
+  - example
+  - genomics
+tools:
+  - "metabuli":
+      ## TODO nf-core: Add a description and other details for the software below
+      description: "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid"
+      homepage: "None"
+      documentation: "None"
+      tool_dev_url: "None"
+      doi: ""
+      licence: ['GPL v3']
+
+## TODO nf-core: Add a description of all of the variables used as input
+input:
+  # Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  
+  ## TODO nf-core: Delete / customise this example input
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+## TODO nf-core: Add a description of all of the variables used as output
+output:
+  #Only when we have meta
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. `[ id:'sample1', single_end:false ]`
+  
+  - versions:
+      type: file
+      description: File containing software versions
+      pattern: "versions.yml"
+  ## TODO nf-core: Delete / customise this example output
+  - bam:
+      type: file
+      description: Sorted BAM/CRAM/SAM file
+      pattern: "*.{bam,cram,sam}"
+
+authors:
+  - "@Joon-Klaps"
+maintainers:
+  - "@Joon-Klaps"
diff --git a/modules/nf-core/metabuli/add/tests/main.nf.test b/modules/nf-core/metabuli/add/tests/main.nf.test
new file mode 100644
index 00000000000..e2af01e861a
--- /dev/null
+++ b/modules/nf-core/metabuli/add/tests/main.nf.test
@@ -0,0 +1,74 @@
+// TODO nf-core: Once you have added the required tests, please run the following command to build this file:
+// nf-core modules test metabuli/add
+nextflow_process {
+
+    name "Test Process METABULI_ADD"
+    script "../main.nf"
+    process "METABULI_ADD"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "metabuli"
+    tag "metabuli/add"
+
+    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used
+    test("sarscov2 - bam") {
+
+        // TODO nf-core: If you are created a test for a chained module
+        // (the module requires running more than one process to generate the required output)
+        // add the 'setup' method here.
+        // You can find more information about how to use a 'setup' method in the docs (https://nf-co.re/docs/contributing/modules#steps-for-creating-nf-test-for-chained-modules).
+
+        when {
+            process {
+                """
+                // TODO nf-core: define inputs of the process here. Example:
+                
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+                //TODO nf-core: Add all required assertions to verify the test output.
+                // See https://nf-co.re/docs/contributing/tutorials/nf-test_assertions for more information and examples.
+            )
+        }
+
+    }
+
+    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used but keep the " - stub" suffix.
+    test("sarscov2 - bam - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                // TODO nf-core: define inputs of the process here. Example:
+                
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+                //TODO nf-core: Add all required assertions to verify the test output.
+            )
+        }
+
+    }
+
+}
diff --git a/modules/nf-core/metabuli/add/tests/tags.yml b/modules/nf-core/metabuli/add/tests/tags.yml
new file mode 100644
index 00000000000..5fb30a9102f
--- /dev/null
+++ b/modules/nf-core/metabuli/add/tests/tags.yml
@@ -0,0 +1,2 @@
+metabuli/add:
+  - "modules/nf-core/metabuli/add/**"
diff --git a/modules/nf-core/metabuli/build/environment.yml b/modules/nf-core/metabuli/build/environment.yml
new file mode 100644
index 00000000000..b7c37e88c07
--- /dev/null
+++ b/modules/nf-core/metabuli/build/environment.yml
@@ -0,0 +1,6 @@
+name: metabuli_build
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::metabuli=1.0.5
diff --git a/modules/nf-core/metabuli/build/main.nf b/modules/nf-core/metabuli/build/main.nf
index b7870d1b14f..d85e0f4180a 100644
--- a/modules/nf-core/metabuli/build/main.nf
+++ b/modules/nf-core/metabuli/build/main.nf
@@ -5,17 +5,17 @@ process METABULI_BUILD {
 
     conda "bioconda::metabuli=1.0.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/metabuli:1.0.0--pl5321hf1761c0_0':
-        'biocontainers/metabuli:1.0.0--pl5321hf1761c0_0' }"
+        'https://depot.galaxyproject.org/singularity/metabuli:1.0.5--pl5321h6a68c12_1':
+        'biocontainers/metabuli:1.0.5--pl5321h6a68c12_1' }"
 
     input:
-    path(genomes)
+    tuple val(meta),path(genomes)
     path(acc2taxid)
     path(db)
 
     output:
     path "metabuli_db.tar.gz", emit: db
-    path "versions.yml"           , emit: versions
+    path "versions.yml"      , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -23,7 +23,7 @@ process METABULI_BUILD {
     script:
     def args = task.ext.args ?: ''
     def args_lib = task.ext.args_lib ?: ''
-    def skip_lib = params.skip_lib ?: false 
+    // def skip_lib = params.skip_lib ?: false
     """
     ls $genomes > fastas.txt
     metabuli \\
@@ -41,7 +41,7 @@ process METABULI_BUILD {
         lib.txt \\
         $acc2taxid \\
         $args
-        
+
     rm -r $db/library
     tar -czf metabuli_db.tar.gz $db
     rm -r $db
diff --git a/modules/nf-core/metabuli/build/meta.yml b/modules/nf-core/metabuli/build/meta.yml
index b4e0b5d04e5..14879d950f7 100644
--- a/modules/nf-core/metabuli/build/meta.yml
+++ b/modules/nf-core/metabuli/build/meta.yml
@@ -23,15 +23,15 @@ input:
   - acc2taxid:
       type: file
       description: |
-        Accession number to taxid file. 
-        A four column tsv with the following header: 
+        Accession number to taxid file.
+        A four column tsv with the following header:
         accession, accession.revision, taxid, gi.
   - db:
       type: directory
       description: |
-        Output folder name for the database. 
-        If the taxonomy-path optional parameter is not set to a directory 
-        containing names.dmp and nodes.dmp, this directory needs 
+        Output folder name for the database.
+        If the taxonomy-path optional parameter is not set to a directory
+        containing names.dmp and nodes.dmp, this directory needs
         to contain a folder named taxonomy containing those two files.
 
 output:
@@ -46,3 +46,4 @@ output:
 
 authors:
   - "@TheOafidian"
+  - "@Joon-Klaps"
diff --git a/modules/nf-core/metabuli/build/tests/main.nf.test b/modules/nf-core/metabuli/build/tests/main.nf.test
new file mode 100644
index 00000000000..e72cdba89b4
--- /dev/null
+++ b/modules/nf-core/metabuli/build/tests/main.nf.test
@@ -0,0 +1,597 @@
+// nf-core modules test metabuli/build
+nextflow_process {
+
+    name "Test Process METABULI_BUILD"
+    script "../main.nf"
+    process "METABULI_BUILD"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "metabuli"
+    tag "metabuli/build"
+
+
+    test("sarscov2 - paired-end illumina reads") {
+
+        setup {
+
+            run("SEQTK_MERGEPE") {
+                script "../../../seqtk/mergepe/main.nf"
+                config "./modules.config"
+                tag    "seqtk/mergepe"
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test', single_end:false ], // meta map
+                        [
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                        ]
+                    ]
+                    """
+                }
+            }
+
+            run("MERYL_COUNT") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = SEQTK_MERGEPE.out.reads
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+
+        }
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                input[1] = MERYL_COUNT.out.meryl_db
+                input[2] = []
+                input[3] = []
+                input[4] = 10
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.get(0), process.out.get(2)).match() },
+                // The following asserts that the instable output stdout_log generated by the module is complete
+                { assert path(process.out.get(1).get(0)).readLines().last().contains("Bye!") }
+            )
+        }
+
+    }
+
+    test("sarscov2 - paired-end illumina reads - stub") {
+
+        options "-stub"
+
+        setup {
+
+            run("SEQTK_MERGEPE") {
+                script "../../../seqtk/mergepe/main.nf"
+                config "./modules.config"
+                tag    "seqtk/mergepe"
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test', single_end:false ], // meta map
+                        [
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                        ]
+                    ]
+                    """
+                }
+            }
+
+            run("MERYL_COUNT") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = SEQTK_MERGEPE.out.reads
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+
+        }
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                input[1] = MERYL_COUNT.out.meryl_db
+                input[2] = []
+                input[3] = []
+                input[4] = 10
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+
+    }
+
+
+    test("sarscov2 - paired-end illumina reads plus optional inputs lookup_table and seqmers") {
+
+        setup {
+
+            run("SEQTK_MERGEPE") {
+                script "../../../seqtk/mergepe/main.nf"
+                config "./modules.config"
+                tag    "seqtk/mergepe"
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test', single_end:false ], // meta map
+                        [
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                        ]
+                    ]
+                    """
+                }
+            }
+
+            run("MERYL_COUNT", alias: "MERYL_COUNT_READS") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = SEQTK_MERGEPE.out.reads
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("MERYL_COUNT", alias: "MERYL_COUNT_ASM") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test', single_end:false ], // meta map
+                        file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                    ]
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("MERYL_HISTOGRAM") {
+                script "../../../meryl/histogram/main.nf"
+                config "./modules.config"
+                tag    "meryl/histogram"
+                process {
+                    """
+                    input[0] = MERYL_COUNT_READS.out.meryl_db
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("GENOMESCOPE2") {
+                script "../../../genomescope2/main.nf"
+                config "./modules.config"
+                tag    "genomescope2"
+                process {
+                    """
+                    input[0] = MERYL_HISTOGRAM.out.hist
+                    """
+                }
+            }
+
+
+
+
+        }
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                input[1] = MERYL_COUNT_READS.out.meryl_db
+                input[2] = GENOMESCOPE2.out.lookup_table.map{ meta, lkp -> lkp}
+                input[3] = MERYL_COUNT_ASM.out.meryl_db.map{ meta, meryl_db -> meryl_db }
+                input[4] = 10
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.get(0), process.out.get(2)).match() },
+                // The following asserts that the instable output stdout_log generated by the module is complete
+                { assert path(process.out.get(1).get(0)).readLines().last().contains("Bye!") }
+            )
+        }
+
+    }
+
+    test("sarscov2 - paired-end illumina reads plus inputs lookup_table and seqmers - stub") {
+
+        options "-stub"
+
+        setup {
+
+            run("SEQTK_MERGEPE") {
+                script "../../../seqtk/mergepe/main.nf"
+                config "./modules.config"
+                tag    "seqtk/mergepe"
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test', single_end:false ], // meta map
+                        [
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                        ]
+                    ]
+                    """
+                }
+            }
+
+            run("MERYL_COUNT", alias: "MERYL_COUNT_READS") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = SEQTK_MERGEPE.out.reads
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("MERYL_COUNT", alias: "MERYL_COUNT_ASM") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test', single_end:false ], // meta map
+                        file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                    ]
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("MERYL_HISTOGRAM") {
+                script "../../../meryl/histogram/main.nf"
+                config "./modules.config"
+                tag    "meryl/histogram"
+                process {
+                    """
+                    input[0] = MERYL_COUNT_READS.out.meryl_db
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("GENOMESCOPE2") {
+                script "../../../genomescope2/main.nf"
+                config "./modules.config"
+                tag    "genomescope2"
+                process {
+                    """
+                    input[0] = MERYL_HISTOGRAM.out.hist
+                    """
+                }
+            }
+
+
+
+
+        }
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                input[1] = MERYL_COUNT_READS.out.meryl_db
+                input[2] = GENOMESCOPE2.out.lookup_table.map{ meta, lkp -> lkp }
+                input[3] = MERYL_COUNT_ASM.out.meryl_db.map{ meta, meryl_db -> meryl_db }
+                input[4] = 10
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() },
+            )
+        }
+
+    }
+
+    test("Multiple samples - sarscov2 + bacteroides_fragilis - paired-end illumina reads") {
+
+        setup {
+
+            run("SEQTK_MERGEPE") {
+                script "../../../seqtk/mergepe/main.nf"
+                config "./modules.config"
+                tag    "seqtk/mergepe"
+                process {
+                    """
+                    input[0] = Channel.from([
+                        [ id:'test_sars', single_end:false ], // meta map
+                        [
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                        ]
+                    ], [
+                        [ id:'test_fragilis', single_end:false ], // meta map
+                        [
+                            file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/illumina/fastq/test1_1.fastq.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/illumina/fastq/test1_2.fastq.gz', checkIfExists: true)
+                        ]
+                    ])
+                    """
+                }
+            }
+
+            run("MERYL_COUNT", alias: "MERYL_COUNT_READS") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = SEQTK_MERGEPE.out.reads
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("MERYL_COUNT", alias: "MERYL_COUNT_ASM") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = Channel.from([
+                        [ id:'test_sars', single_end:false ], // meta map
+                        file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                    ],[
+                        [ id:'test_fragilis', single_end:false ], // meta map
+                        file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
+                    ])
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("MERYL_HISTOGRAM") {
+                script "../../../meryl/histogram/main.nf"
+                config "./modules.config"
+                tag    "meryl/histogram"
+                process {
+                    """
+                    input[0] = MERYL_COUNT_READS.out.meryl_db
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("GENOMESCOPE2") {
+                script "../../../genomescope2/main.nf"
+                config "./modules.config"
+                tag    "genomescope2"
+                process {
+                    """
+                    input[0] = MERYL_HISTOGRAM.out.hist
+                    """
+                }
+            }
+
+
+
+
+        }
+
+        when {
+            process {
+                """
+                Channel.from([
+                    [ id:'test_sars', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ],[
+                    [ id:'test_fragilis', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
+                ])
+                .set{ input_zero_ch }
+
+                input_zero_ch.join( MERYL_COUNT_READS.out.meryl_db )
+                             .join( MERYL_COUNT_ASM.out.meryl_db )
+                             .join( GENOMESCOPE2.out.lookup_table )
+                             .multiMap{ meta, asm, meryl_db, asm_meryl_db, lookup_table ->
+                    asm_ch: [meta, asm]
+                    meryl_ch: [meta, meryl_db]
+                    asm_meryl_ch: [asm_meryl_db]
+                    lk_ch: [lookup_table]
+                }.set{ multimap_inputs_ch }
+
+                input[0] = multimap_inputs_ch.asm_ch
+                input[1] = multimap_inputs_ch.meryl_ch
+                input[2] = multimap_inputs_ch.lk_ch
+                input[3] = multimap_inputs_ch.asm_meryl_ch
+                input[4] = 10
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.get(0), process.out.get(2)).match() },
+                // The following asserts that the output stdout_log generated by the module is complete
+                { assert path(process.out.get(1).get(0)).readLines().last().contains("Bye!") }
+            )
+        }
+
+    }
+
+    test("Multiple samples - sarscov2 + bacteroides_fragilis - paired-end illumina reads - stub") {
+
+        options "-stub"
+
+        setup {
+
+            run("SEQTK_MERGEPE") {
+                script "../../../seqtk/mergepe/main.nf"
+                config "./modules.config"
+                tag    "seqtk/mergepe"
+                process {
+                    """
+                    input[0] = Channel.from([
+                        [ id:'test_sars', single_end:false ], // meta map
+                        [
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                        ]
+                    ], [
+                        [ id:'test_fragilis', single_end:false ], // meta map
+                        [
+                            file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/illumina/fastq/test1_1.fastq.gz', checkIfExists: true),
+                            file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/illumina/fastq/test1_2.fastq.gz', checkIfExists: true)
+                        ]
+                    ])
+                    """
+                }
+            }
+
+            run("MERYL_COUNT", alias: "MERYL_COUNT_READS") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = SEQTK_MERGEPE.out.reads
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("MERYL_COUNT", alias: "MERYL_COUNT_ASM") {
+                script "../../../meryl/count/main.nf"
+                config "./modules.config"
+                tag    "meryl/count"
+                process {
+                    """
+                    input[0] = Channel.from([
+                        [ id:'test_sars', single_end:false ], // meta map
+                        file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                    ],[
+                        [ id:'test_fragilis', single_end:false ], // meta map
+                        file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
+                    ])
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("MERYL_HISTOGRAM") {
+                script "../../../meryl/histogram/main.nf"
+                config "./modules.config"
+                tag    "meryl/histogram"
+                process {
+                    """
+                    input[0] = MERYL_COUNT_READS.out.meryl_db
+                    input[1] = Channel.value(6)
+                    """
+                }
+            }
+
+            run("GENOMESCOPE2") {
+                script "../../../genomescope2/main.nf"
+                config "./modules.config"
+                tag    "genomescope2"
+                process {
+                    """
+                    input[0] = MERYL_HISTOGRAM.out.hist
+                    """
+                }
+            }
+
+
+
+
+        }
+
+        when {
+            process {
+                """
+                Channel.from([
+                    [ id:'test_sars', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ],[
+                    [ id:'test_fragilis', single_end:false ], // meta map
+                    file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
+                ])
+                .set{ input_zero_ch }
+
+
+                input_zero_ch.join( MERYL_COUNT_READS.out.meryl_db )
+                             .join( MERYL_COUNT_ASM.out.meryl_db )
+                             .join( GENOMESCOPE2.out.lookup_table )
+                             .multiMap{ meta, asm, meryl_db, asm_meryl_db, lookup_table ->
+                    asm_ch: [meta, asm]
+                    meryl_ch: [meta, meryl_db]
+                    asm_meryl_ch: [asm_meryl_db]
+                    lk_ch: [lookup_table]
+                }.set{ multimap_inputs_ch }
+
+                input[0] = multimap_inputs_ch.asm_ch
+                input[1] = multimap_inputs_ch.meryl_ch
+                input[2] = multimap_inputs_ch.lk_ch
+                input[3] = MERYL_COUNT_ASM.out.meryl_db.map{ meta, meryl_db -> meryl_db }
+                input[4] = 10
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out.get(0), process.out.get(2)).match() }
+            )
+        }
+
+    }
+}
diff --git a/modules/nf-core/metabuli/build/tests/main.nf.test.snap b/modules/nf-core/metabuli/build/tests/main.nf.test.snap
new file mode 100644
index 00000000000..2d1f4e9da8f
--- /dev/null
+++ b/modules/nf-core/metabuli/build/tests/main.nf.test.snap
@@ -0,0 +1,184 @@
+{
+    "Multiple samples - sarscov2 + bacteroides_fragilis - paired-end illumina reads": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test_fragilis",
+                        "single_end": false
+                    },
+                    "test_fragilis.hist:md5,3380e6f8b82739edc44b45ac6b50525e"
+                ],
+                [
+                    {
+                        "id": "test_sars",
+                        "single_end": false
+                    },
+                    "test_sars.hist:md5,564c5dc22b9a10041b248405bb2b15d0"
+                ]
+            ],
+            [
+                "versions.yml:md5,078b89694148fc55475e89987173ac4e",
+                "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-02T11:05:51.416187"
+    },
+    "sarscov2 - paired-end illumina reads - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "test.hist.stderr.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ],
+                "2": [
+                    "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+                ],
+                "hist": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "log_stderr": [
+                    "test.hist.stderr.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ],
+                "versions": [
+                    "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-02T11:04:28.744584"
+    },
+    "sarscov2 - paired-end illumina reads plus inputs lookup_table and seqmers - stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "1": [
+                    "test.hist.stderr.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ],
+                "2": [
+                    "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+                ],
+                "hist": [
+                    [
+                        {
+                            "id": "test",
+                            "single_end": false
+                        },
+                        "test.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                    ]
+                ],
+                "log_stderr": [
+                    "test.hist.stderr.log:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ],
+                "versions": [
+                    "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-02T11:04:51.831185"
+    },
+    "sarscov2 - paired-end illumina reads plus optional inputs lookup_table and seqmers": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": false
+                    },
+                    "test.hist:md5,564c5dc22b9a10041b248405bb2b15d0"
+                ]
+            ],
+            [
+                "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-02T11:04:41.739829"
+    },
+    "Multiple samples - sarscov2 + bacteroides_fragilis - paired-end illumina reads - stub": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test_fragilis",
+                        "single_end": false
+                    },
+                    "test_fragilis.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ],
+                [
+                    {
+                        "id": "test_sars",
+                        "single_end": false
+                    },
+                    "test_sars.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                ]
+            ],
+            [
+                "versions.yml:md5,078b89694148fc55475e89987173ac4e",
+                "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-02T11:06:03.566853"
+    },
+    "sarscov2 - paired-end illumina reads": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": false
+                    },
+                    "test.hist:md5,e722be64a7fffeec654a10bea92ec619"
+                ]
+            ],
+            [
+                "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-02T11:04:20.733553"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/metabuli/build/tests/tags.yml b/modules/nf-core/metabuli/build/tests/tags.yml
new file mode 100644
index 00000000000..b931e457ad4
--- /dev/null
+++ b/modules/nf-core/metabuli/build/tests/tags.yml
@@ -0,0 +1,2 @@
+metabuli/build:
+  - "modules/nf-core/metabuli/build/**"
diff --git a/modules/nf-core/metabuli/classify/environment.yml b/modules/nf-core/metabuli/classify/environment.yml
new file mode 100644
index 00000000000..78c213cdfea
--- /dev/null
+++ b/modules/nf-core/metabuli/classify/environment.yml
@@ -0,0 +1,6 @@
+name: metabuli_classify
+channels:
+  - conda-forge
+  - bioconda
+dependencies:
+  - bioconda::metabuli=1.0.5
diff --git a/modules/nf-core/metabuli/classify/main.nf b/modules/nf-core/metabuli/classify/main.nf
index ec4715810e0..02096f785c9 100644
--- a/modules/nf-core/metabuli/classify/main.nf
+++ b/modules/nf-core/metabuli/classify/main.nf
@@ -4,8 +4,8 @@ process METABULI_CLASSIFY {
 
     conda "bioconda::metabuli=1.0.0"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/metabuli:1.0.0--pl5321hf1761c0_0':
-        'biocontainers/metabuli:1.0.0--pl5321hf1761c0_0' }"
+        'https://depot.galaxyproject.org/singularity/metabuli:1.0.5--pl5321h6a68c12_1':
+        'biocontainers/metabuli:1.0.5--pl5321h6a68c12_1' }"
 
     input:
     tuple val(meta), path(fastas)
@@ -13,8 +13,8 @@ process METABULI_CLASSIFY {
 
     output:
     tuple val(meta), path("*/*_classifications.tsv"), emit: classification
-    tuple val(meta), path("*/*_report.tsv"), emit: report
-    path "versions.yml"           , emit: versions
+    tuple val(meta), path("*/*_report.tsv")         , emit: report
+    path "versions.yml"                             , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -29,7 +29,7 @@ process METABULI_CLASSIFY {
     } else if (is_compressed) {
       input =  "${fastas[0].baseName} ${fastas[1].baseName}"
     }
-    
+
     """
     if [ "$is_compressed" == "true" ]; then
     gzip -d *.gz
diff --git a/modules/nf-core/metabuli/classify/meta.yml b/modules/nf-core/metabuli/classify/meta.yml
index 0d8b2004023..fd910db5c21 100644
--- a/modules/nf-core/metabuli/classify/meta.yml
+++ b/modules/nf-core/metabuli/classify/meta.yml
@@ -36,7 +36,7 @@ output:
       type: map
       description: |
         Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]  
+        e.g. [ id:'test', single_end:false ]
   - versions:
       type: file
       description: File containing software versions
@@ -52,3 +52,4 @@ output:
 
 authors:
   - "@TheOafidian"
+  - "@Joon-Klaps"

From f2f8ea93e0d4c24c35e216349151e2619fff6849 Mon Sep 17 00:00:00 2001
From: Joon-Klaps <joon.klaps@kuleuven.be>
Date: Fri, 21 Jun 2024 09:00:59 +0000
Subject: [PATCH 17/20] furthere splitting up add  & build

---
 modules/nf-core/metabuli/add/main.nf   | 31 ++++++------
 modules/nf-core/metabuli/add/meta.yml  | 69 ++++++++++++--------------
 modules/nf-core/metabuli/build/main.nf | 15 ------
 3 files changed, 47 insertions(+), 68 deletions(-)

diff --git a/modules/nf-core/metabuli/add/main.nf b/modules/nf-core/metabuli/add/main.nf
index 41c657fe373..4e463b7a62c 100644
--- a/modules/nf-core/metabuli/add/main.nf
+++ b/modules/nf-core/metabuli/add/main.nf
@@ -9,9 +9,8 @@ process METABULI_ADD {
 
     input:
     tuple val(meta), path(fasta)
-    path taxonomy_names, stageAs: 'taxonomy/names.dmp'
-    path taxonomy_nodes, stageAs: 'taxonomy/nodes.dmp'
-    path accession2taxid, stageAs: 'taxonomy/*'
+    path accession2taxid
+    path db
 
     output:
     tuple val(meta), path("${prefix}"), emit: db
@@ -25,33 +24,31 @@ process METABULI_ADD {
     def prefix = task.ext.prefix ?: "${meta.id}"
 
     """
-    samtools \\
-        sort \\
-        $args \\
-        -@ $task.cpus \\
-        -o ${prefix}.bam \\
-        -T $prefix \\
-        $bam
+    mkdir -p $prefix
+    mv $db/* $prefix
+
+    ls $fasta > fasta.txt
+    metabuli add-to-library \\
+        fasta.txt \\
+        $accession2taxid \\
+        $prefix \\
+        $args
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        metabuli: \$(samtools --version |& sed '1!d ; s/samtools //')
+        metabuli: \$(metabuli version)
     END_VERSIONS
     """
 
     stub:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    // TODO nf-core: A stub section should mimic the execution of the original module as best as possible
-    //               Have a look at the following examples:
-    //               Simple example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bcftools/annotate/main.nf#L47-L63
-    //               Complex example: https://github.com/nf-core/modules/blob/818474a292b4860ae8ff88e149fbcda68814114d/modules/nf-core/bedtools/split/main.nf#L38-L54
     """
-    touch ${prefix}.bam
+    mkdir -p $prefix
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        metabuli: \$(samtools --version |& sed '1!d ; s/samtools //')
+        metabuli: \$(metabuli version)
     END_VERSIONS
     """
 }
diff --git a/modules/nf-core/metabuli/add/meta.yml b/modules/nf-core/metabuli/add/meta.yml
index 0537f1e027d..cfcc06b4836 100644
--- a/modules/nf-core/metabuli/add/meta.yml
+++ b/modules/nf-core/metabuli/add/meta.yml
@@ -1,57 +1,54 @@
----
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json
 name: "metabuli_add"
-## TODO nf-core: Add a description of the module and list keywords
-description: write your description here
+description: Add fasta sequences to a database needed to use the metabuli classification tool
 keywords:
-  - sort
-  - example
-  - genomics
+  - metabuli
+  - metagenomics
+  - profiling
+  - taxonomy
+  - database
 tools:
   - "metabuli":
-      ## TODO nf-core: Add a description and other details for the software below
       description: "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid"
-      homepage: "None"
-      documentation: "None"
-      tool_dev_url: "None"
-      doi: ""
-      licence: ['GPL v3']
+      homepage: "https://github.com/steineggerlab/Metabuli"
+      documentation: "https://github.com/steineggerlab/Metabuli#readme"
+      tool_dev_url: "https://github.com/steineggerlab/Metabuli"
+      doi: "10.1101/2023.05.31.543018"
+      licence: "['GPL v3']"
 
-## TODO nf-core: Add a description of all of the variables used as input
 input:
-  # Only when we have meta
   - meta:
       type: map
       description: |
         Groovy Map containing sample information
-        e.g. `[ id:'sample1', single_end:false ]`
-  
-  ## TODO nf-core: Delete / customise this example input
-  - bam:
+        e.g. [ id:'test', single_end:false ]
+  - fasta:
       type: file
-      description: Sorted BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
+      description: Genome files that serve as entries in the database
+      pattern: "*.{fa,fasta,fna}"
+  - accession2taxid:
+      type: file
+      description: |
+        Accession number to taxid file.
+        A four column tsv with the following header:
+        accession, accession.revision, taxid, gi.
+  - db:
+      type: directory
+      description: |
+        Output folder name for the database.
+        If the taxonomy-path optional parameter is not set to a directory
+        containing names.dmp and nodes.dmp, this directory needs
+        to contain a folder named taxonomy containing those two files.
 
-## TODO nf-core: Add a description of all of the variables used as output
 output:
-  #Only when we have meta
-  - meta:
-      type: map
-      description: |
-        Groovy Map containing sample information
-        e.g. `[ id:'sample1', single_end:false ]`
-  
   - versions:
       type: file
       description: File containing software versions
       pattern: "versions.yml"
-  ## TODO nf-core: Delete / customise this example output
-  - bam:
-      type: file
-      description: Sorted BAM/CRAM/SAM file
-      pattern: "*.{bam,cram,sam}"
+  - db:
+      type: directory
+      description: Compressed metabuli database
+      pattern: "${prefix}/"
 
 authors:
-  - "@Joon-Klaps"
-maintainers:
+  - "@TheOafidian"
   - "@Joon-Klaps"
diff --git a/modules/nf-core/metabuli/build/main.nf b/modules/nf-core/metabuli/build/main.nf
index d85e0f4180a..4645babe3fe 100644
--- a/modules/nf-core/metabuli/build/main.nf
+++ b/modules/nf-core/metabuli/build/main.nf
@@ -9,8 +9,6 @@ process METABULI_BUILD {
         'biocontainers/metabuli:1.0.5--pl5321h6a68c12_1' }"
 
     input:
-    tuple val(meta),path(genomes)
-    path(acc2taxid)
     path(db)
 
     output:
@@ -22,16 +20,7 @@ process METABULI_BUILD {
 
     script:
     def args = task.ext.args ?: ''
-    def args_lib = task.ext.args_lib ?: ''
-    // def skip_lib = params.skip_lib ?: false
     """
-    ls $genomes > fastas.txt
-    metabuli \\
-        add-to-library \\
-        fastas.txt \\
-        $acc2taxid \\
-        $db
-        $args_lib
 
     ls $db/library/* > lib.txt
     metabuli \\
@@ -42,10 +31,6 @@ process METABULI_BUILD {
         $acc2taxid \\
         $args
 
-    rm -r $db/library
-    tar -czf metabuli_db.tar.gz $db
-    rm -r $db
-
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))

From 1b9d0eab74873192ed519fd0bbea168fa39905e7 Mon Sep 17 00:00:00 2001
From: Joon-Klaps <joon.klaps@kuleuven.be>
Date: Fri, 21 Jun 2024 13:33:35 +0000
Subject: [PATCH 18/20] removing old pytest files

---
 tests/config/pytest_modules.yml               |  6 ---
 tests/modules/nf-core/metabuli/build/main.nf  | 35 ---------------
 .../nf-core/metabuli/build/nextflow.config    |  6 ---
 tests/modules/nf-core/metabuli/build/test.yml | 17 --------
 .../modules/nf-core/metabuli/classify/main.nf | 43 -------------------
 .../nf-core/metabuli/classify/nextflow.config | 17 --------
 .../nf-core/metabuli/classify/test.yml        | 27 ------------
 7 files changed, 151 deletions(-)
 delete mode 100644 tests/modules/nf-core/metabuli/build/main.nf
 delete mode 100644 tests/modules/nf-core/metabuli/build/nextflow.config
 delete mode 100644 tests/modules/nf-core/metabuli/build/test.yml
 delete mode 100644 tests/modules/nf-core/metabuli/classify/main.nf
 delete mode 100644 tests/modules/nf-core/metabuli/classify/nextflow.config
 delete mode 100644 tests/modules/nf-core/metabuli/classify/test.yml

diff --git a/tests/config/pytest_modules.yml b/tests/config/pytest_modules.yml
index 08255a01594..e94f139e46a 100644
--- a/tests/config/pytest_modules.yml
+++ b/tests/config/pytest_modules.yml
@@ -990,12 +990,6 @@ metabat2/metabat2:
 metaeuk/easypredict:
   - modules/nf-core/metaeuk/easypredict/**
   - tests/modules/nf-core/metaeuk/easypredict/**
-metabuli/build:
-  - modules/nf-core/metabuli/build/**
-  - tests/modules/nf-core/metabuli/build/**
-metabuli/classify:
-  - modules/nf-core/metabuli/classify/**
-  - tests/modules/nf-core/metabuli/classify/**
 metaphlan/makedb:
   - modules/nf-core/metaphlan/makedb/**
   - tests/modules/nf-core/metaphlan/makedb/**
diff --git a/tests/modules/nf-core/metabuli/build/main.nf b/tests/modules/nf-core/metabuli/build/main.nf
deleted file mode 100644
index b665bafd1fc..00000000000
--- a/tests/modules/nf-core/metabuli/build/main.nf
+++ /dev/null
@@ -1,35 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl = 2
-
-include { METABULI_BUILD } from '../../../../../modules/nf-core/metabuli/build/main.nf'
-
-process CREATE_TAXONOMY_FOLDER{
-    input:
-    path(dmpfiles)
-
-    output:
-    path(db)
-
-    script:
-    """
-    mkdir -p db/taxonomy
-    mv *.dmp db/taxonomy
-    touch db/taxonomy/merged.dmp
-    """
-
-}
-
-workflow test_metabuli_build {
-    
-    genome = file("${params.test_data_base}/data/genomics/sarscov2/genome/genome.fasta", checkIfExists: true)
-    
-    dmp_files = [
-        file("${params.test_data_base}/data/delete_me/metabuli/taxonomy/names.dmp"),
-        file("${params.test_data_base}/data/delete_me/metabuli/taxonomy/nodes.dmp")
-    ]
-    acc2taxid = file("${params.test_data_base}/data/delete_me/metabuli/acc2taxid")
-
-    tax = CREATE_TAXONOMY_FOLDER(dmp_files) 
-    METABULI_BUILD ( genome, acc2taxid, tax )
-}
diff --git a/tests/modules/nf-core/metabuli/build/nextflow.config b/tests/modules/nf-core/metabuli/build/nextflow.config
deleted file mode 100644
index 5c70d71b82f..00000000000
--- a/tests/modules/nf-core/metabuli/build/nextflow.config
+++ /dev/null
@@ -1,6 +0,0 @@
-process {
-
-    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-    memory = "16GB"
-    
-}   
diff --git a/tests/modules/nf-core/metabuli/build/test.yml b/tests/modules/nf-core/metabuli/build/test.yml
deleted file mode 100644
index aadaa1b9279..00000000000
--- a/tests/modules/nf-core/metabuli/build/test.yml
+++ /dev/null
@@ -1,17 +0,0 @@
-- name: metabuli build test_metabuli_build
-  command: nextflow run ./tests/modules/nf-core/metabuli/build -entry test_metabuli_build -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/build/nextflow.config -stub-run
-  tags:
-    - metabuli/build
-    - metabuli
-  files:
-    - path: output/build/acc2taxid
-      md5sum: 4ae5ac3b865cb7bf301c3cc72153a7a8
-    - path: output/create/db/taxonomy/merged.dmp
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
-    - path: output/create/db/taxonomy/names.dmp
-      md5sum: 1cacf8dba5defe61c7b31dc4342801a0
-    - path: output/create/db/taxonomy/nodes.dmp
-      md5sum: a41041a713e9fb2be5eac4723a421385
-    - path: output/metabuli/metabuli_db.tar.gz
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
-    - path: output/metabuli/versions.yml
diff --git a/tests/modules/nf-core/metabuli/classify/main.nf b/tests/modules/nf-core/metabuli/classify/main.nf
deleted file mode 100644
index a2366ad0c42..00000000000
--- a/tests/modules/nf-core/metabuli/classify/main.nf
+++ /dev/null
@@ -1,43 +0,0 @@
-#!/usr/bin/env nextflow
-
-nextflow.enable.dsl = 2
-
-include { UNTAR } from '../../../../../modules/nf-core/untar/main.nf'
-include { METABULI_CLASSIFY as METABULI_CLASSIFY_PE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
-include { METABULI_CLASSIFY as METABULI_CLASSIFY_SE } from '../../../../../modules/nf-core/metabuli/classify/main.nf'
-
-// test with single end data
-workflow test_metabuli_classify_se {
-    
-    input = [
-        [ id:'test_se', single_end:true ], // meta map
-        [
-          file("${params.test_data_base}/data/genomics/sarscov2/nanopore/fastq/test_2.fastq.gz", checkIfExists: true),
-        ]
-    ]
-        
-    db_archive =  file("${params.test_data_base}/data/delete_me/metabuli/metabuli_db.tar.gz", checkIfExists: true)
-    UNTAR( [[:], db_archive])
-    METABULI_CLASSIFY_SE ( input , UNTAR.out.untar.map{it[1]})
-}
-
-// test with paired end data
-workflow test_metabuli_classify_pe {
-    
-    input = Channel.from(
-        [[ id:'test_pe', single_end:false ], // meta map
-        [
-          file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_1.fastq.gz", checkIfExists: true),
-          file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_2.fastq.gz", checkIfExists: true),
-        ]],
-        [[ id:'test_pe2', single_end:false ], // meta map
-        [
-          file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_1.fastq.gz", checkIfExists: true),
-          file("${params.test_data_base}/data/genomics/sarscov2/illumina/fastq/test2_2.fastq.gz", checkIfExists: true),
-        ]]
-    )
-
-    db_archive =  file("${params.test_data_base}/data/delete_me/metabuli/metabuli_db.tar.gz", checkIfExists: true)
-    UNTAR([[:], db_archive])
-    METABULI_CLASSIFY_PE ( input , UNTAR.out.untar.map{it[1]})
-}
diff --git a/tests/modules/nf-core/metabuli/classify/nextflow.config b/tests/modules/nf-core/metabuli/classify/nextflow.config
deleted file mode 100644
index 5b77ae739ad..00000000000
--- a/tests/modules/nf-core/metabuli/classify/nextflow.config
+++ /dev/null
@@ -1,17 +0,0 @@
-process {
-
-    publishDir = { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }
-
-    withLabel:process_medium {
-        memory = 6.5.GB
-    }
-    withName: SEQTK_SEQ {
-        ext.args = "-a"
-    }
-
-    withName: SEQTK_SEQ_PE_RV {
-        ext.args = "-a"
-        ext.prefix = "reverse"
-    }
-}
-
diff --git a/tests/modules/nf-core/metabuli/classify/test.yml b/tests/modules/nf-core/metabuli/classify/test.yml
deleted file mode 100644
index a7bd8f85d64..00000000000
--- a/tests/modules/nf-core/metabuli/classify/test.yml
+++ /dev/null
@@ -1,27 +0,0 @@
-- name: metabuli classify test_metabuli_classify_se
-  command: nextflow run ./tests/modules/nf-core/metabuli/classify -entry test_metabuli_classify_se -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/classify/nextflow.config
-  tags:
-    - metabuli/classify
-    - metabuli
-  files:
-    - path: output/metabuli/test_se_out/test_se_classifications.tsv
-      md5sum: 3870c45887908e8e4b3c60c23ae3e008
-    - path: output/metabuli/test_se_out/test_se_report.tsv
-      md5sum: 686930217102cd8d249906387de3e6b5
-    - path: output/metabuli/versions.yml
-
-- name: metabuli classify test_metabuli_classify_pe
-  command: nextflow run ./tests/modules/nf-core/metabuli/classify -entry test_metabuli_classify_pe -c ./tests/config/nextflow.config -c ./tests/modules/nf-core/metabuli/classify/nextflow.config
-  tags:
-    - metabuli/classify
-    - metabuli
-  files:
-    - path: output/metabuli/test_pe2_out/test_pe2_classifications.tsv
-      md5sum: d3b961b3a1e3f1181d182583ee246523
-    - path: output/metabuli/test_pe2_out/test_pe2_report.tsv
-      md5sum: 0cc7f995f15304368574b4217cdd13b9
-    - path: output/metabuli/test_pe_out/test_pe_classifications.tsv
-      md5sum: d3b961b3a1e3f1181d182583ee246523
-    - path: output/metabuli/test_pe_out/test_pe_report.tsv
-      md5sum: 0cc7f995f15304368574b4217cdd13b9
-    - path: output/metabuli/versions.yml

From 92aaf7f827d1e039d3ebe0b0a8dc3a3f7b9173b2 Mon Sep 17 00:00:00 2001
From: Joon-Klaps <joon.klaps@kuleuven.be>
Date: Fri, 21 Jun 2024 13:34:16 +0000
Subject: [PATCH 19/20] testing setups metabuli - needs fixing

---
 modules/nf-core/metabuli/add/environment.yml  |   3 -
 modules/nf-core/metabuli/add/main.nf          |  22 +-
 modules/nf-core/metabuli/add/meta.yml         |  33 +-
 .../nf-core/metabuli/add/tests/main.nf.test   |  77 ++-
 .../metabuli/add/tests/main.nf.test.snap      |  94 +++
 .../nf-core/metabuli/build/environment.yml    |   4 +-
 modules/nf-core/metabuli/build/main.nf        |  38 +-
 modules/nf-core/metabuli/build/meta.yml       |  39 +-
 .../nf-core/metabuli/build/tests/main.nf.test | 556 +-----------------
 .../metabuli/build/tests/main.nf.test.snap    | 249 ++++----
 .../metabuli/build/tests/nextflow.config      |   6 +
 .../nf-core/metabuli/classify/environment.yml |   2 +-
 modules/nf-core/metabuli/classify/main.nf     |  42 +-
 .../metabuli/classify/tests/main.nf.test      |  81 +++
 .../metabuli/classify/tests/main.nf.test.snap |  82 +++
 .../classify/tests/nextflow-se.config         |   5 +
 .../nf-core/metabuli/classify/tests/tags.yml  |   3 +
 17 files changed, 551 insertions(+), 785 deletions(-)
 create mode 100644 modules/nf-core/metabuli/add/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/metabuli/build/tests/nextflow.config
 create mode 100644 modules/nf-core/metabuli/classify/tests/main.nf.test
 create mode 100644 modules/nf-core/metabuli/classify/tests/main.nf.test.snap
 create mode 100644 modules/nf-core/metabuli/classify/tests/nextflow-se.config
 create mode 100644 modules/nf-core/metabuli/classify/tests/tags.yml

diff --git a/modules/nf-core/metabuli/add/environment.yml b/modules/nf-core/metabuli/add/environment.yml
index 44ccbb344ec..0e5eef64f23 100644
--- a/modules/nf-core/metabuli/add/environment.yml
+++ b/modules/nf-core/metabuli/add/environment.yml
@@ -1,9 +1,6 @@
----
-# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json
 name: "metabuli_add"
 channels:
   - conda-forge
   - bioconda
-  - defaults
 dependencies:
   - "bioconda::metabuli=1.0.5"
diff --git a/modules/nf-core/metabuli/add/main.nf b/modules/nf-core/metabuli/add/main.nf
index 4e463b7a62c..022f201308a 100644
--- a/modules/nf-core/metabuli/add/main.nf
+++ b/modules/nf-core/metabuli/add/main.nf
@@ -9,28 +9,32 @@ process METABULI_ADD {
 
     input:
     tuple val(meta), path(fasta)
-    path accession2taxid
-    path db
+    path taxonomy_names, stageAs: 'taxonomy/names.dmp'
+    path taxonomy_nodes, stageAs: 'taxonomy/nodes.dmp'
+    path taxonomy_merged, stageAs: 'taxonomy/merged.dmp'
+    path accession2taxid, stageAs: 'taxonomy/*'
 
     output:
-    tuple val(meta), path("${prefix}"), emit: db
-    path "versions.yml"               , emit: versions
+    tuple val(meta), path("$prefix"), emit: db
+    path "versions.yml"             , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
+    prefix = task.ext.prefix ?: "${meta.id}"
+    make_merged = taxonomy_merged ? "" : "touch ${prefix}/taxonomy/merged.dmp"
 
     """
     mkdir -p $prefix
-    mv $db/* $prefix
+    mv "taxonomy" $prefix
+    $make_merged
 
-    ls $fasta > fasta.txt
+    realpath $fasta > fasta.txt
     metabuli add-to-library \\
         fasta.txt \\
-        $accession2taxid \\
+        $prefix/$accession2taxid \\
         $prefix \\
         $args
 
@@ -42,7 +46,7 @@ process METABULI_ADD {
 
     stub:
     def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
+    prefix = task.ext.prefix ?: "${meta.id}"
     """
     mkdir -p $prefix
 
diff --git a/modules/nf-core/metabuli/add/meta.yml b/modules/nf-core/metabuli/add/meta.yml
index cfcc06b4836..c8a4e70f0a1 100644
--- a/modules/nf-core/metabuli/add/meta.yml
+++ b/modules/nf-core/metabuli/add/meta.yml
@@ -20,24 +20,27 @@ input:
       type: map
       description: |
         Groovy Map containing sample information
-        e.g. [ id:'test', single_end:false ]
+        e.g. `[ id:'sample1', single_end:false ]`
   - fasta:
       type: file
-      description: Genome files that serve as entries in the database
-      pattern: "*.{fa,fasta,fna}"
+      description: fasta file that will be added to the database
+      pattern: "*.{fa,fasta,fna,ffn}"
+  - taxonomy_names:
+      type: file
+      description: used for associating sequences with taxonomy IDs
+      pattern: "*.dmp"
+  - taxonomy_nodes:
+      type: file
+      description: tree nodes using NCBI taxonomy nomenclature
+      pattern: "*.dmp"
+  - taxonomy_merged:
+      type: file
+      description: merged.dmp maps secondary taxids onto primary taxids for taxa that have been synonymized in the database
+      pattern: "*.dmp"
   - accession2taxid:
       type: file
-      description: |
-        Accession number to taxid file.
-        A four column tsv with the following header:
-        accession, accession.revision, taxid, gi.
-  - db:
-      type: directory
-      description: |
-        Output folder name for the database.
-        If the taxonomy-path optional parameter is not set to a directory
-        containing names.dmp and nodes.dmp, this directory needs
-        to contain a folder named taxonomy containing those two files.
+      description: associates sequence accession IDs to taxonomy IDs
+      pattern: "*.accession2taxid"
 
 output:
   - versions:
@@ -46,7 +49,7 @@ output:
       pattern: "versions.yml"
   - db:
       type: directory
-      description: Compressed metabuli database
+      description: Metabuli database
       pattern: "${prefix}/"
 
 authors:
diff --git a/modules/nf-core/metabuli/add/tests/main.nf.test b/modules/nf-core/metabuli/add/tests/main.nf.test
index e2af01e861a..8909691f6dd 100644
--- a/modules/nf-core/metabuli/add/tests/main.nf.test
+++ b/modules/nf-core/metabuli/add/tests/main.nf.test
@@ -1,5 +1,3 @@
-// TODO nf-core: Once you have added the required tests, please run the following command to build this file:
-// nf-core modules test metabuli/add
 nextflow_process {
 
     name "Test Process METABULI_ADD"
@@ -11,23 +9,22 @@ nextflow_process {
     tag "metabuli"
     tag "metabuli/add"
 
-    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used
-    test("sarscov2 - bam") {
-
-        // TODO nf-core: If you are created a test for a chained module
-        // (the module requires running more than one process to generate the required output)
-        // add the 'setup' method here.
-        // You can find more information about how to use a 'setup' method in the docs (https://nf-co.re/docs/contributing/modules#steps-for-creating-nf-test-for-chained-modules).
+    test("sarscov2 protein_db") {
 
         when {
             process {
                 """
-                // TODO nf-core: define inputs of the process here. Example:
-                
                 input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
-                ]
+                    [ id:'test' ],
+                        [
+                        file(params.modules_testdata_base_path +'genomics/sarscov2/genome/genome.fasta', checkIfExists: true),
+                        file(params.modules_testdata_base_path +'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true),
+                        ]
+                    ]
+                input[1] = file(params.modules_testdata_base_path +'genomics/sarscov2/metagenome/prot_names.dmp', checkIfExists: true)
+                input[2] = file(params.modules_testdata_base_path +'genomics/sarscov2/metagenome/prot_nodes.dmp', checkIfExists: true)
+                input[3] = [] // needs a merged.dmp
+                input[4] = file(params.modules_testdata_base_path + 'delete_me/metabuli/acc2taxid', checkIfExists: true)
                 """
             }
         }
@@ -35,40 +32,38 @@ nextflow_process {
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out).match() }
-                //TODO nf-core: Add all required assertions to verify the test output.
-                // See https://nf-co.re/docs/contributing/tutorials/nf-test_assertions for more information and examples.
+                { assert snapshot (process.out).match()},
             )
         }
-
     }
 
-    // TODO nf-core: Change the test name preferably indicating the test-data and file-format used but keep the " - stub" suffix.
-    test("sarscov2 - bam - stub") {
+    test("sarscov2 protein_db stub") {
 
-        options "-stub"
+            options "-stub"
 
-        when {
-            process {
-                """
-                // TODO nf-core: define inputs of the process here. Example:
-                
-                input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/bam/test.paired_end.bam', checkIfExists: true)
-                    ]
-                """
+            when {
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test' ],
+                            [
+                            file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true),
+                            file(params.test_data['sarscov2']['genome']['proteome_fasta'], checkIfExists: true)
+                            ]
+                        ]
+                    input[1] = file(params.test_data['sarscov2']['metagenome']['prot_names_dmp'], checkIfExists: true)
+                    input[2] = file(params.test_data['sarscov2']['metagenome']['prot_nodes_dmp'], checkIfExists: true)
+                    input[3] = [] // needs a merged.dmp
+                    input[4] = file(params.modules_testdata_base_path + 'delete_me/metabuli/acc2taxid', checkIfExists: true)
+                    """
+                }
             }
-        }
 
-        then {
-            assertAll(
-                { assert process.success },
-                { assert snapshot(process.out).match() }
-                //TODO nf-core: Add all required assertions to verify the test output.
-            )
+            then {
+                assertAll(
+                    { assert process.success },
+                    { assert snapshot (process.out).match()},
+                )
+            }
         }
-
-    }
-
 }
diff --git a/modules/nf-core/metabuli/add/tests/main.nf.test.snap b/modules/nf-core/metabuli/add/tests/main.nf.test.snap
new file mode 100644
index 00000000000..6d002ee38ea
--- /dev/null
+++ b/modules/nf-core/metabuli/add/tests/main.nf.test.snap
@@ -0,0 +1,94 @@
+{
+    "sarscov2 protein_db": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            [
+                                "694009.fna:md5,e73599798195a519ba2565c3f0275b93"
+                            ],
+                            [
+                                "acc2taxid:md5,4ae5ac3b865cb7bf301c3cc72153a7a8",
+                                "merged.dmp:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "names.dmp:md5,130f9132095562e09c732679c562f5e9",
+                                "nodes.dmp:md5,c471c27a4ce85ae74d2c63633c9ce1e3"
+                            ],
+                            "unmapped.txt:md5,b8c64bc37b7dc465fdaf61b3cd90c29a"
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,2a8623d8302b84cba425ddf9381464d4"
+                ],
+                "db": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            [
+                                "694009.fna:md5,e73599798195a519ba2565c3f0275b93"
+                            ],
+                            [
+                                "acc2taxid:md5,4ae5ac3b865cb7bf301c3cc72153a7a8",
+                                "merged.dmp:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "names.dmp:md5,130f9132095562e09c732679c562f5e9",
+                                "nodes.dmp:md5,c471c27a4ce85ae74d2c63633c9ce1e3"
+                            ],
+                            "unmapped.txt:md5,b8c64bc37b7dc465fdaf61b3cd90c29a"
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,2a8623d8302b84cba425ddf9381464d4"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2024-06-21T12:01:48.840753727"
+    },
+    "sarscov2 protein_db stub": {
+        "content": [
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+
+                        ]
+                    ]
+                ],
+                "1": [
+                    "versions.yml:md5,2a8623d8302b84cba425ddf9381464d4"
+                ],
+                "db": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,2a8623d8302b84cba425ddf9381464d4"
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2024-06-21T11:40:58.903080427"
+    }
+}
diff --git a/modules/nf-core/metabuli/build/environment.yml b/modules/nf-core/metabuli/build/environment.yml
index b7c37e88c07..96f5393db66 100644
--- a/modules/nf-core/metabuli/build/environment.yml
+++ b/modules/nf-core/metabuli/build/environment.yml
@@ -1,6 +1,6 @@
-name: metabuli_build
+name: "metabuli_build"
 channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::metabuli=1.0.5
+  - "bioconda::metabuli=1.0.5"
diff --git a/modules/nf-core/metabuli/build/main.nf b/modules/nf-core/metabuli/build/main.nf
index 4645babe3fe..8310467f935 100644
--- a/modules/nf-core/metabuli/build/main.nf
+++ b/modules/nf-core/metabuli/build/main.nf
@@ -1,48 +1,60 @@
 
 process METABULI_BUILD {
-    tag 'build'
+    tag "$meta.id"
     label 'process_medium'
 
-    conda "bioconda::metabuli=1.0.0"
+    conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/metabuli:1.0.5--pl5321h6a68c12_1':
         'biocontainers/metabuli:1.0.5--pl5321h6a68c12_1' }"
 
     input:
-    path(db)
+    tuple val(meta), path(db)
+    path accession2taxid, stageAs: 'taxonomy/acc2taxid'
 
     output:
-    path "metabuli_db.tar.gz", emit: db
-    path "versions.yml"      , emit: versions
+    tuple val(meta), path("$prefix"), emit: db
+    path "versions.yml"             , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
     def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
+    acc2taxid = accession2taxid ? "${accession2taxid}" : "${db}/taxonomy/acc2taxid"
     """
+    find ${db}/library -type f -name '*.fna' > library-files.txt
 
-    ls $db/library/* > lib.txt
     metabuli \\
         build \\
-        --threads $task.cpus \\
-        $db \\
-        lib.txt \\
-        $acc2taxid \\
+        ${db} \\
+        library-files.txt \\
+        ${acc2taxid} \\
+        --db-name ${prefix} \\
+        --threads ${task.cpus} \\
         $args
 
+    if [[ \$(basename ${db}) != "${prefix}" ]]; then
+        mkdir -p ${prefix}
+        mv ${db}/* ${prefix}
+    fi
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))
+        metabuli: \$(metabuli version)
     END_VERSIONS
     """
 
     stub:
+    def args = task.ext.args ?: ''
+    prefix = task.ext.prefix ?: "${meta.id}"
     """
-    touch metabuli_db.tar.gz
+    mkdir -p "$prefix"
+
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))
+        metabuli: \$(metabuli version)
     END_VERSIONS
     """
 }
diff --git a/modules/nf-core/metabuli/build/meta.yml b/modules/nf-core/metabuli/build/meta.yml
index 14879d950f7..fe320627286 100644
--- a/modules/nf-core/metabuli/build/meta.yml
+++ b/modules/nf-core/metabuli/build/meta.yml
@@ -8,31 +8,24 @@ keywords:
   - database
 tools:
   - "metabuli":
-      description: "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid"
-      homepage: "https://github.com/steineggerlab/Metabuli"
-      documentation: "https://github.com/steineggerlab/Metabuli#readme"
-      tool_dev_url: "https://github.com/steineggerlab/Metabuli"
-      doi: "10.1101/2023.05.31.543018"
-      licence: "['GPL v3']"
+    description: "Metabuli: specific and sensitive metagenomic classification via joint analysis of DNA and amino acid"
+    homepage: "https://github.com/steineggerlab/Metabuli"
+    documentation: "https://github.com/steineggerlab/Metabuli#readme"
+    tool_dev_url: "https://github.com/steineggerlab/Metabuli"
+    doi: "10.1101/2023.05.31.543018"
+    licence: "['GPL v3']"
 
 input:
-  - genomes:
-      type: file
-      description: Genome files that serve as entries in the database
-      pattern: "*.{fa,fasta,fna}"
-  - acc2taxid:
-      type: file
-      description: |
-        Accession number to taxid file.
-        A four column tsv with the following header:
-        accession, accession.revision, taxid, gi.
+  - meta:
+    type: map
+    description: |
+      Groovy Map containing sample information
+      e.g. `[ id:'sample1', single_end:false ]`
   - db:
-      type: directory
-      description: |
-        Output folder name for the database.
-        If the taxonomy-path optional parameter is not set to a directory
-        containing names.dmp and nodes.dmp, this directory needs
-        to contain a folder named taxonomy containing those two files.
+    type: directory
+    description: |
+      contains required files to build the database
+      [ taxonomy/names.dmp, taxonomy/nodes.dmp, taxonomy/merged.dmp, acc2taxid, library/*.fna ]
 
 output:
   - versions:
@@ -42,7 +35,7 @@ output:
   - db:
       type: file
       description: Compressed metabuli database
-      pattern: "*.tar.gz"
+      pattern: "${prefix}/"
 
 authors:
   - "@TheOafidian"
diff --git a/modules/nf-core/metabuli/build/tests/main.nf.test b/modules/nf-core/metabuli/build/tests/main.nf.test
index e72cdba89b4..b4fb6dc4a79 100644
--- a/modules/nf-core/metabuli/build/tests/main.nf.test
+++ b/modules/nf-core/metabuli/build/tests/main.nf.test
@@ -1,228 +1,44 @@
-// nf-core modules test metabuli/build
 nextflow_process {
 
     name "Test Process METABULI_BUILD"
     script "../main.nf"
     process "METABULI_BUILD"
-
-    tag "modules"
-    tag "modules_nfcore"
+    config "./nextflow.config"
     tag "metabuli"
     tag "metabuli/build"
+    tag "metabuli/add"
+    tag "modules"
+    tag "modules_nfcore"
 
-
-    test("sarscov2 - paired-end illumina reads") {
-
-        setup {
-
-            run("SEQTK_MERGEPE") {
-                script "../../../seqtk/mergepe/main.nf"
-                config "./modules.config"
-                tag    "seqtk/mergepe"
-                process {
-                    """
-                    input[0] = [
-                        [ id:'test', single_end:false ], // meta map
-                        [
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
-                        ]
-                    ]
-                    """
-                }
-            }
-
-            run("MERYL_COUNT") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = SEQTK_MERGEPE.out.reads
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-
-        }
-
-        when {
+    setup {
+        run("METABULI_ADD") {
+            script "modules/nf-core/metabuli/add/main.nf"
             process {
                 """
                 input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                ]
-                input[1] = MERYL_COUNT.out.meryl_db
-                input[2] = []
-                input[3] = []
-                input[4] = 10
-                """
-            }
-        }
-
-        then {
-            assertAll(
-                { assert process.success },
-                { assert snapshot(process.out.get(0), process.out.get(2)).match() },
-                // The following asserts that the instable output stdout_log generated by the module is complete
-                { assert path(process.out.get(1).get(0)).readLines().last().contains("Bye!") }
-            )
-        }
-
-    }
-
-    test("sarscov2 - paired-end illumina reads - stub") {
-
-        options "-stub"
-
-        setup {
-
-            run("SEQTK_MERGEPE") {
-                script "../../../seqtk/mergepe/main.nf"
-                config "./modules.config"
-                tag    "seqtk/mergepe"
-                process {
-                    """
-                    input[0] = [
-                        [ id:'test', single_end:false ], // meta map
+                    [ id:'test' ],
                         [
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
+                        file(params.modules_testdata_base_path +'genomics/sarscov2/genome/genome.fasta', checkIfExists: true),
+                        file(params.modules_testdata_base_path +'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true),
                         ]
                     ]
-                    """
-                }
-            }
-
-            run("MERYL_COUNT") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = SEQTK_MERGEPE.out.reads
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-
-        }
-
-        when {
-            process {
-                """
-                input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                ]
-                input[1] = MERYL_COUNT.out.meryl_db
-                input[2] = []
-                input[3] = []
-                input[4] = 10
+                input[1] = file(params.modules_testdata_base_path +'genomics/sarscov2/metagenome/prot_names.dmp', checkIfExists: true)
+                input[2] = file(params.modules_testdata_base_path +'genomics/sarscov2/metagenome/prot_nodes.dmp', checkIfExists: true)
+                input[3] = [] // needs a merged.dmp
+                input[4] = file(params.modules_testdata_base_path + 'delete_me/metabuli/acc2taxid', checkIfExists: true)
                 """
             }
         }
 
-        then {
-            assertAll(
-                { assert process.success },
-                { assert snapshot(process.out).match() }
-            )
-        }
-
     }
 
-
-    test("sarscov2 - paired-end illumina reads plus optional inputs lookup_table and seqmers") {
-
-        setup {
-
-            run("SEQTK_MERGEPE") {
-                script "../../../seqtk/mergepe/main.nf"
-                config "./modules.config"
-                tag    "seqtk/mergepe"
-                process {
-                    """
-                    input[0] = [
-                        [ id:'test', single_end:false ], // meta map
-                        [
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
-                        ]
-                    ]
-                    """
-                }
-            }
-
-            run("MERYL_COUNT", alias: "MERYL_COUNT_READS") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = SEQTK_MERGEPE.out.reads
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("MERYL_COUNT", alias: "MERYL_COUNT_ASM") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = [
-                        [ id:'test', single_end:false ], // meta map
-                        file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                    ]
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("MERYL_HISTOGRAM") {
-                script "../../../meryl/histogram/main.nf"
-                config "./modules.config"
-                tag    "meryl/histogram"
-                process {
-                    """
-                    input[0] = MERYL_COUNT_READS.out.meryl_db
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("GENOMESCOPE2") {
-                script "../../../genomescope2/main.nf"
-                config "./modules.config"
-                tag    "genomescope2"
-                process {
-                    """
-                    input[0] = MERYL_HISTOGRAM.out.hist
-                    """
-                }
-            }
-
-
-
-
-        }
+    test("sarscov2 protein_db") {
 
         when {
             process {
                 """
-                input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                ]
-                input[1] = MERYL_COUNT_READS.out.meryl_db
-                input[2] = GENOMESCOPE2.out.lookup_table.map{ meta, lkp -> lkp}
-                input[3] = MERYL_COUNT_ASM.out.meryl_db.map{ meta, meryl_db -> meryl_db }
-                input[4] = 10
+                input[0] = METABULI_ADD.out.db
+                input[1] = []
                 """
             }
         }
@@ -230,228 +46,18 @@ nextflow_process {
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out.get(0), process.out.get(2)).match() },
-                // The following asserts that the instable output stdout_log generated by the module is complete
-                { assert path(process.out.get(1).get(0)).readLines().last().contains("Bye!") }
+                { assert snapshot (process.out).match()},
             )
         }
-
     }
 
-    test("sarscov2 - paired-end illumina reads plus inputs lookup_table and seqmers - stub") {
-
-        options "-stub"
-
-        setup {
-
-            run("SEQTK_MERGEPE") {
-                script "../../../seqtk/mergepe/main.nf"
-                config "./modules.config"
-                tag    "seqtk/mergepe"
-                process {
-                    """
-                    input[0] = [
-                        [ id:'test', single_end:false ], // meta map
-                        [
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
-                        ]
-                    ]
-                    """
-                }
-            }
-
-            run("MERYL_COUNT", alias: "MERYL_COUNT_READS") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = SEQTK_MERGEPE.out.reads
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("MERYL_COUNT", alias: "MERYL_COUNT_ASM") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = [
-                        [ id:'test', single_end:false ], // meta map
-                        file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                    ]
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("MERYL_HISTOGRAM") {
-                script "../../../meryl/histogram/main.nf"
-                config "./modules.config"
-                tag    "meryl/histogram"
-                process {
-                    """
-                    input[0] = MERYL_COUNT_READS.out.meryl_db
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("GENOMESCOPE2") {
-                script "../../../genomescope2/main.nf"
-                config "./modules.config"
-                tag    "genomescope2"
-                process {
-                    """
-                    input[0] = MERYL_HISTOGRAM.out.hist
-                    """
-                }
-            }
-
-
-
-
-        }
-
-        when {
-            process {
-                """
-                input[0] = [
-                    [ id:'test', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                ]
-                input[1] = MERYL_COUNT_READS.out.meryl_db
-                input[2] = GENOMESCOPE2.out.lookup_table.map{ meta, lkp -> lkp }
-                input[3] = MERYL_COUNT_ASM.out.meryl_db.map{ meta, meryl_db -> meryl_db }
-                input[4] = 10
-                """
-            }
-        }
-
-        then {
-            assertAll(
-                { assert process.success },
-                { assert snapshot(process.out).match() },
-            )
-        }
-
-    }
-
-    test("Multiple samples - sarscov2 + bacteroides_fragilis - paired-end illumina reads") {
-
-        setup {
-
-            run("SEQTK_MERGEPE") {
-                script "../../../seqtk/mergepe/main.nf"
-                config "./modules.config"
-                tag    "seqtk/mergepe"
-                process {
-                    """
-                    input[0] = Channel.from([
-                        [ id:'test_sars', single_end:false ], // meta map
-                        [
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
-                        ]
-                    ], [
-                        [ id:'test_fragilis', single_end:false ], // meta map
-                        [
-                            file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/illumina/fastq/test1_1.fastq.gz', checkIfExists: true),
-                            file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/illumina/fastq/test1_2.fastq.gz', checkIfExists: true)
-                        ]
-                    ])
-                    """
-                }
-            }
-
-            run("MERYL_COUNT", alias: "MERYL_COUNT_READS") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = SEQTK_MERGEPE.out.reads
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("MERYL_COUNT", alias: "MERYL_COUNT_ASM") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = Channel.from([
-                        [ id:'test_sars', single_end:false ], // meta map
-                        file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                    ],[
-                        [ id:'test_fragilis', single_end:false ], // meta map
-                        file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
-                    ])
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("MERYL_HISTOGRAM") {
-                script "../../../meryl/histogram/main.nf"
-                config "./modules.config"
-                tag    "meryl/histogram"
-                process {
-                    """
-                    input[0] = MERYL_COUNT_READS.out.meryl_db
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("GENOMESCOPE2") {
-                script "../../../genomescope2/main.nf"
-                config "./modules.config"
-                tag    "genomescope2"
-                process {
-                    """
-                    input[0] = MERYL_HISTOGRAM.out.hist
-                    """
-                }
-            }
-
-
-
-
-        }
+    test("sarscov2 - protein_db - acc2taxid") {
 
         when {
             process {
                 """
-                Channel.from([
-                    [ id:'test_sars', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                ],[
-                    [ id:'test_fragilis', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
-                ])
-                .set{ input_zero_ch }
-
-                input_zero_ch.join( MERYL_COUNT_READS.out.meryl_db )
-                             .join( MERYL_COUNT_ASM.out.meryl_db )
-                             .join( GENOMESCOPE2.out.lookup_table )
-                             .multiMap{ meta, asm, meryl_db, asm_meryl_db, lookup_table ->
-                    asm_ch: [meta, asm]
-                    meryl_ch: [meta, meryl_db]
-                    asm_meryl_ch: [asm_meryl_db]
-                    lk_ch: [lookup_table]
-                }.set{ multimap_inputs_ch }
-
-                input[0] = multimap_inputs_ch.asm_ch
-                input[1] = multimap_inputs_ch.meryl_ch
-                input[2] = multimap_inputs_ch.lk_ch
-                input[3] = multimap_inputs_ch.asm_meryl_ch
-                input[4] = 10
+                input[0] = METABULI_ADD.out.db
+                input[1] = file(params.modules_testdata_base_path + 'delete_me/metabuli/acc2taxid', checkIfExists: true)
                 """
             }
         }
@@ -459,129 +65,20 @@ nextflow_process {
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out.get(0), process.out.get(2)).match() },
-                // The following asserts that the output stdout_log generated by the module is complete
-                { assert path(process.out.get(1).get(0)).readLines().last().contains("Bye!") }
+                { assert snapshot (process.out).match()},
             )
         }
-
     }
 
-    test("Multiple samples - sarscov2 + bacteroides_fragilis - paired-end illumina reads - stub") {
+    test("sarscov2 protein_db stub") {
 
         options "-stub"
 
-        setup {
-
-            run("SEQTK_MERGEPE") {
-                script "../../../seqtk/mergepe/main.nf"
-                config "./modules.config"
-                tag    "seqtk/mergepe"
-                process {
-                    """
-                    input[0] = Channel.from([
-                        [ id:'test_sars', single_end:false ], // meta map
-                        [
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true),
-                            file(params.modules_testdata_base_path + '/genomics/sarscov2/illumina/fastq/test_2.fastq.gz', checkIfExists: true)
-                        ]
-                    ], [
-                        [ id:'test_fragilis', single_end:false ], // meta map
-                        [
-                            file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/illumina/fastq/test1_1.fastq.gz', checkIfExists: true),
-                            file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/illumina/fastq/test1_2.fastq.gz', checkIfExists: true)
-                        ]
-                    ])
-                    """
-                }
-            }
-
-            run("MERYL_COUNT", alias: "MERYL_COUNT_READS") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = SEQTK_MERGEPE.out.reads
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("MERYL_COUNT", alias: "MERYL_COUNT_ASM") {
-                script "../../../meryl/count/main.nf"
-                config "./modules.config"
-                tag    "meryl/count"
-                process {
-                    """
-                    input[0] = Channel.from([
-                        [ id:'test_sars', single_end:false ], // meta map
-                        file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                    ],[
-                        [ id:'test_fragilis', single_end:false ], // meta map
-                        file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
-                    ])
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("MERYL_HISTOGRAM") {
-                script "../../../meryl/histogram/main.nf"
-                config "./modules.config"
-                tag    "meryl/histogram"
-                process {
-                    """
-                    input[0] = MERYL_COUNT_READS.out.meryl_db
-                    input[1] = Channel.value(6)
-                    """
-                }
-            }
-
-            run("GENOMESCOPE2") {
-                script "../../../genomescope2/main.nf"
-                config "./modules.config"
-                tag    "genomescope2"
-                process {
-                    """
-                    input[0] = MERYL_HISTOGRAM.out.hist
-                    """
-                }
-            }
-
-
-
-
-        }
-
         when {
             process {
                 """
-                Channel.from([
-                    [ id:'test_sars', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + '/genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
-                ],[
-                    [ id:'test_fragilis', single_end:false ], // meta map
-                    file(params.modules_testdata_base_path + '/genomics/prokaryotes/bacteroides_fragilis/genome/genome.fna.gz', checkIfExists: true)
-                ])
-                .set{ input_zero_ch }
-
-
-                input_zero_ch.join( MERYL_COUNT_READS.out.meryl_db )
-                             .join( MERYL_COUNT_ASM.out.meryl_db )
-                             .join( GENOMESCOPE2.out.lookup_table )
-                             .multiMap{ meta, asm, meryl_db, asm_meryl_db, lookup_table ->
-                    asm_ch: [meta, asm]
-                    meryl_ch: [meta, meryl_db]
-                    asm_meryl_ch: [asm_meryl_db]
-                    lk_ch: [lookup_table]
-                }.set{ multimap_inputs_ch }
-
-                input[0] = multimap_inputs_ch.asm_ch
-                input[1] = multimap_inputs_ch.meryl_ch
-                input[2] = multimap_inputs_ch.lk_ch
-                input[3] = MERYL_COUNT_ASM.out.meryl_db.map{ meta, meryl_db -> meryl_db }
-                input[4] = 10
+                input[0] = METABULI_ADD.out.db
+                input[1] = []
                 """
             }
         }
@@ -589,9 +86,8 @@ nextflow_process {
         then {
             assertAll(
                 { assert process.success },
-                { assert snapshot(process.out.get(0), process.out.get(2)).match() }
+                { assert snapshot (process.out).match()}
             )
         }
-
     }
 }
diff --git a/modules/nf-core/metabuli/build/tests/main.nf.test.snap b/modules/nf-core/metabuli/build/tests/main.nf.test.snap
index 2d1f4e9da8f..74f66077987 100644
--- a/modules/nf-core/metabuli/build/tests/main.nf.test.snap
+++ b/modules/nf-core/metabuli/build/tests/main.nf.test.snap
@@ -1,184 +1,177 @@
 {
-    "Multiple samples - sarscov2 + bacteroides_fragilis - paired-end illumina reads": {
-        "content": [
-            [
-                [
-                    {
-                        "id": "test_fragilis",
-                        "single_end": false
-                    },
-                    "test_fragilis.hist:md5,3380e6f8b82739edc44b45ac6b50525e"
-                ],
-                [
-                    {
-                        "id": "test_sars",
-                        "single_end": false
-                    },
-                    "test_sars.hist:md5,564c5dc22b9a10041b248405bb2b15d0"
-                ]
-            ],
-            [
-                "versions.yml:md5,078b89694148fc55475e89987173ac4e",
-                "versions.yml:md5,078b89694148fc55475e89987173ac4e"
-            ]
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-04-02T11:05:51.416187"
-    },
-    "sarscov2 - paired-end illumina reads - stub": {
+    "sarscov2 protein_db": {
         "content": [
             {
                 "0": [
                     [
                         {
-                            "id": "test",
-                            "single_end": false
+                            "id": "test"
                         },
-                        "test.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        [
+                            "acc2taxid.map:md5,4eb8b3bde8a5cc1414afeeeab385e208",
+                            "db.parameters:md5,481509eb7cddc0ec93fbcd61b7820616",
+                            "diffIdx:md5,8ac88d03fabf6917698a02841e410b33",
+                            "info:md5,ba18c68b0d90630fad4dfe02b5101b72",
+                            [
+                                "694009.fna:md5,e73599798195a519ba2565c3f0275b93"
+                            ],
+                            "split:md5,6306fc471e89174e65c71fd0cc69f780",
+                            "taxID_list:md5,40064b0651b7d558820d6fc1014de0fd",
+                            [
+                                "acc2taxid:md5,4ae5ac3b865cb7bf301c3cc72153a7a8",
+                                "merged.dmp:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "names.dmp:md5,130f9132095562e09c732679c562f5e9",
+                                "nodes.dmp:md5,c471c27a4ce85ae74d2c63633c9ce1e3"
+                            ],
+                            "taxonomyDB:md5,029a03295afff91c5d2a011c7e8b8db5",
+                            "unmapped.txt:md5,b8c64bc37b7dc465fdaf61b3cd90c29a"
+                        ]
                     ]
                 ],
                 "1": [
-                    "test.hist.stderr.log:md5,d41d8cd98f00b204e9800998ecf8427e"
-                ],
-                "2": [
-                    "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+                    "versions.yml:md5,acaa33b47a40006743150a1f9db99393"
                 ],
-                "hist": [
+                "db": [
                     [
                         {
-                            "id": "test",
-                            "single_end": false
+                            "id": "test"
                         },
-                        "test.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        [
+                            "acc2taxid.map:md5,4eb8b3bde8a5cc1414afeeeab385e208",
+                            "db.parameters:md5,481509eb7cddc0ec93fbcd61b7820616",
+                            "diffIdx:md5,8ac88d03fabf6917698a02841e410b33",
+                            "info:md5,ba18c68b0d90630fad4dfe02b5101b72",
+                            [
+                                "694009.fna:md5,e73599798195a519ba2565c3f0275b93"
+                            ],
+                            "split:md5,6306fc471e89174e65c71fd0cc69f780",
+                            "taxID_list:md5,40064b0651b7d558820d6fc1014de0fd",
+                            [
+                                "acc2taxid:md5,4ae5ac3b865cb7bf301c3cc72153a7a8",
+                                "merged.dmp:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "names.dmp:md5,130f9132095562e09c732679c562f5e9",
+                                "nodes.dmp:md5,c471c27a4ce85ae74d2c63633c9ce1e3"
+                            ],
+                            "taxonomyDB:md5,029a03295afff91c5d2a011c7e8b8db5",
+                            "unmapped.txt:md5,b8c64bc37b7dc465fdaf61b3cd90c29a"
+                        ]
                     ]
                 ],
-                "log_stderr": [
-                    "test.hist.stderr.log:md5,d41d8cd98f00b204e9800998ecf8427e"
-                ],
                 "versions": [
-                    "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+                    "versions.yml:md5,acaa33b47a40006743150a1f9db99393"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-04-02T11:04:28.744584"
+        "timestamp": "2024-06-21T13:06:57.889836817"
     },
-    "sarscov2 - paired-end illumina reads plus inputs lookup_table and seqmers - stub": {
+    "sarscov2 - protein_db - acc2taxid": {
         "content": [
             {
                 "0": [
                     [
                         {
-                            "id": "test",
-                            "single_end": false
+                            "id": "test"
                         },
-                        "test.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        [
+                            "acc2taxid.map:md5,4eb8b3bde8a5cc1414afeeeab385e208",
+                            "db.parameters:md5,481509eb7cddc0ec93fbcd61b7820616",
+                            "diffIdx:md5,8ac88d03fabf6917698a02841e410b33",
+                            "info:md5,ba18c68b0d90630fad4dfe02b5101b72",
+                            [
+                                "694009.fna:md5,e73599798195a519ba2565c3f0275b93"
+                            ],
+                            "split:md5,6306fc471e89174e65c71fd0cc69f780",
+                            "taxID_list:md5,40064b0651b7d558820d6fc1014de0fd",
+                            [
+                                "acc2taxid:md5,4ae5ac3b865cb7bf301c3cc72153a7a8",
+                                "merged.dmp:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "names.dmp:md5,130f9132095562e09c732679c562f5e9",
+                                "nodes.dmp:md5,c471c27a4ce85ae74d2c63633c9ce1e3"
+                            ],
+                            "taxonomyDB:md5,8efd02b34af565a1a808e43bc239c75a",
+                            "unmapped.txt:md5,b8c64bc37b7dc465fdaf61b3cd90c29a"
+                        ]
                     ]
                 ],
                 "1": [
-                    "test.hist.stderr.log:md5,d41d8cd98f00b204e9800998ecf8427e"
-                ],
-                "2": [
-                    "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+                    "versions.yml:md5,acaa33b47a40006743150a1f9db99393"
                 ],
-                "hist": [
+                "db": [
                     [
                         {
-                            "id": "test",
-                            "single_end": false
+                            "id": "test"
                         },
-                        "test.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+                        [
+                            "acc2taxid.map:md5,4eb8b3bde8a5cc1414afeeeab385e208",
+                            "db.parameters:md5,481509eb7cddc0ec93fbcd61b7820616",
+                            "diffIdx:md5,8ac88d03fabf6917698a02841e410b33",
+                            "info:md5,ba18c68b0d90630fad4dfe02b5101b72",
+                            [
+                                "694009.fna:md5,e73599798195a519ba2565c3f0275b93"
+                            ],
+                            "split:md5,6306fc471e89174e65c71fd0cc69f780",
+                            "taxID_list:md5,40064b0651b7d558820d6fc1014de0fd",
+                            [
+                                "acc2taxid:md5,4ae5ac3b865cb7bf301c3cc72153a7a8",
+                                "merged.dmp:md5,d41d8cd98f00b204e9800998ecf8427e",
+                                "names.dmp:md5,130f9132095562e09c732679c562f5e9",
+                                "nodes.dmp:md5,c471c27a4ce85ae74d2c63633c9ce1e3"
+                            ],
+                            "taxonomyDB:md5,8efd02b34af565a1a808e43bc239c75a",
+                            "unmapped.txt:md5,b8c64bc37b7dc465fdaf61b3cd90c29a"
+                        ]
                     ]
                 ],
-                "log_stderr": [
-                    "test.hist.stderr.log:md5,d41d8cd98f00b204e9800998ecf8427e"
-                ],
                 "versions": [
-                    "versions.yml:md5,078b89694148fc55475e89987173ac4e"
+                    "versions.yml:md5,acaa33b47a40006743150a1f9db99393"
                 ]
             }
         ],
         "meta": {
             "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-04-02T11:04:51.831185"
-    },
-    "sarscov2 - paired-end illumina reads plus optional inputs lookup_table and seqmers": {
-        "content": [
-            [
-                [
-                    {
-                        "id": "test",
-                        "single_end": false
-                    },
-                    "test.hist:md5,564c5dc22b9a10041b248405bb2b15d0"
-                ]
-            ],
-            [
-                "versions.yml:md5,078b89694148fc55475e89987173ac4e"
-            ]
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-04-02T11:04:41.739829"
+        "timestamp": "2024-06-21T13:08:00.235429024"
     },
-    "Multiple samples - sarscov2 + bacteroides_fragilis - paired-end illumina reads - stub": {
+    "sarscov2 protein_db stub": {
         "content": [
-            [
-                [
-                    {
-                        "id": "test_fragilis",
-                        "single_end": false
-                    },
-                    "test_fragilis.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
+            {
+                "0": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            
+                        ]
+                    ]
                 ],
-                [
-                    {
-                        "id": "test_sars",
-                        "single_end": false
-                    },
-                    "test_sars.hist:md5,d41d8cd98f00b204e9800998ecf8427e"
-                ]
-            ],
-            [
-                "versions.yml:md5,078b89694148fc55475e89987173ac4e",
-                "versions.yml:md5,078b89694148fc55475e89987173ac4e"
-            ]
-        ],
-        "meta": {
-            "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
-        },
-        "timestamp": "2024-04-02T11:06:03.566853"
-    },
-    "sarscov2 - paired-end illumina reads": {
-        "content": [
-            [
-                [
-                    {
-                        "id": "test",
-                        "single_end": false
-                    },
-                    "test.hist:md5,e722be64a7fffeec654a10bea92ec619"
+                "1": [
+                    "versions.yml:md5,acaa33b47a40006743150a1f9db99393"
+                ],
+                "db": [
+                    [
+                        {
+                            "id": "test"
+                        },
+                        [
+                            
+                        ]
+                    ]
+                ],
+                "versions": [
+                    "versions.yml:md5,acaa33b47a40006743150a1f9db99393"
                 ]
-            ],
-            [
-                "versions.yml:md5,078b89694148fc55475e89987173ac4e"
-            ]
+            }
         ],
         "meta": {
             "nf-test": "0.8.4",
-            "nextflow": "23.10.1"
+            "nextflow": "24.04.2"
         },
-        "timestamp": "2024-04-02T11:04:20.733553"
+        "timestamp": "2024-06-21T13:08:14.59465885"
     }
 }
\ No newline at end of file
diff --git a/modules/nf-core/metabuli/build/tests/nextflow.config b/modules/nf-core/metabuli/build/tests/nextflow.config
new file mode 100644
index 00000000000..32a9775a4b1
--- /dev/null
+++ b/modules/nf-core/metabuli/build/tests/nextflow.config
@@ -0,0 +1,6 @@
+process {
+    withName: METABULI_BUILD {
+        memory = 12.GB
+        ext.args = '--db-date 2024-6-21'
+    }
+}
diff --git a/modules/nf-core/metabuli/classify/environment.yml b/modules/nf-core/metabuli/classify/environment.yml
index 78c213cdfea..ce1ebe71f5b 100644
--- a/modules/nf-core/metabuli/classify/environment.yml
+++ b/modules/nf-core/metabuli/classify/environment.yml
@@ -3,4 +3,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::metabuli=1.0.5
+  - "bioconda::metabuli=1.0.5"
diff --git a/modules/nf-core/metabuli/classify/main.nf b/modules/nf-core/metabuli/classify/main.nf
index 02096f785c9..e0994ea975b 100644
--- a/modules/nf-core/metabuli/classify/main.nf
+++ b/modules/nf-core/metabuli/classify/main.nf
@@ -2,19 +2,19 @@ process METABULI_CLASSIFY {
     tag "$meta.id"
     label 'process_medium'
 
-    conda "bioconda::metabuli=1.0.0"
+    conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
         'https://depot.galaxyproject.org/singularity/metabuli:1.0.5--pl5321h6a68c12_1':
         'biocontainers/metabuli:1.0.5--pl5321h6a68c12_1' }"
 
     input:
     tuple val(meta), path(fastas)
-    path(db)
+    tuple val(meta2), path(db)
 
     output:
-    tuple val(meta), path("*/*_classifications.tsv"), emit: classification
-    tuple val(meta), path("*/*_report.tsv")         , emit: report
-    path "versions.yml"                             , emit: versions
+    tuple val(meta), path("*classifications.tsv"), emit: classification
+    tuple val(meta), path("*report.tsv")         , emit: report
+    path "versions.yml"                          , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
@@ -22,31 +22,33 @@ process METABULI_CLASSIFY {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
-    def is_compressed = meta.single_end ? fastas.getName().endsWith(".gz") : fastas[0].getName().endsWith(".gz")
-    def input = meta.single_end ? "--seq-mode 1 ${fastas}" : "${fastas[0]} ${fastas[1]}"
-    if (is_compressed && meta.single_end) {
-      input = "--seq-mode 1 ${fastas.baseName}"
-    } else if (is_compressed) {
-      input =  "${fastas[0].baseName} ${fastas[1].baseName}"
-    }
-
     """
-    if [ "$is_compressed" == "true" ]; then
-    gzip -d *.gz
-    fi
-
     metabuli \\
         classify \\
         $args \\
+        ${fastas} \\
         --threads $task.cpus \\
-        ${input} \\
+        --max-ram ${task.memory.toGiga()} \\
         ${db} \\
-        ${prefix}_out \\
+        . \\
         ${prefix}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
-        metabuli: \$(metabuli | grep Version | sed 's/^metabuli Version: //';))
+        metabuli: \$(metabuli version)
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch "${prefix}_classifications.tsv"
+    touch "${prefix}_report.tsv"
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        metabuli: \$(metabuli version)
     END_VERSIONS
     """
 }
diff --git a/modules/nf-core/metabuli/classify/tests/main.nf.test b/modules/nf-core/metabuli/classify/tests/main.nf.test
new file mode 100644
index 00000000000..35a3f7e9ce5
--- /dev/null
+++ b/modules/nf-core/metabuli/classify/tests/main.nf.test
@@ -0,0 +1,81 @@
+nextflow_process {
+    name "Test Process METABULI_CLASSIFY"
+    script "../main.nf"
+    process "METABULI_CLASSIFY"
+    tag "modules"
+    tag "modules_nfcore"
+    tag "untar"
+    tag "metabuli"
+    tag "metabuli/classify"
+
+    setup {
+        run("UNTAR") {
+            script "modules/nf-core/untar/main.nf"
+            process {
+                """
+                input[0] = Channel.of([
+                    [],
+                    file(params.modules_testdata_base_path  + "delete_me/metabuli/metabuli_db.tar.gz", checkIfExists: true)
+                ])
+                """
+            }
+        }
+    }
+
+    test("sarscov2 illumina single end [fastq]") {
+        config "./nextflow-se.config"
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:true ], // meta map
+                    [ file(
+                        params.test_data['sarscov2']['illumina']['test_1_fastq_gz'],
+                        checkIfExists: true
+                    )]
+                ]
+                input[1] = UNTAR.out.untar
+                """
+            }
+        }
+
+        then {
+            assertAll(
+            { assert process.success },
+            { assert snapshot(process.out).match()},
+            )
+        }
+    }
+
+    test("sarscov2 illumina paired end [fastq]") {
+        when {
+
+            process {
+                """
+                input[0] = [
+                    [ id:'test', single_end:false ], // meta map
+                    [
+                        file(
+                            params.test_data['sarscov2']['illumina']['test_1_fastq_gz'],
+                            checkIfExists: true
+                        ),
+                        file(
+                            params.test_data['sarscov2']['illumina']['test_2_fastq_gz'],
+                            checkIfExists: true
+                        )
+
+                    ]
+                ]
+                input[1] = UNTAR.out.untar
+                """
+            }
+        }
+
+        then {
+            assertAll(
+            { assert process.success },
+            { assert snapshot(process.out).match()},
+            )
+        }
+    }
+}
diff --git a/modules/nf-core/metabuli/classify/tests/main.nf.test.snap b/modules/nf-core/metabuli/classify/tests/main.nf.test.snap
new file mode 100644
index 00000000000..a81aa198e67
--- /dev/null
+++ b/modules/nf-core/metabuli/classify/tests/main.nf.test.snap
@@ -0,0 +1,82 @@
+{
+    "sarscov2 illumina single end [fastq]": {
+        "content": [
+            {
+                "0": [
+                    
+                ],
+                "1": [
+                    
+                ],
+                "2": [
+                    
+                ],
+                "classification": [
+                    
+                ],
+                "report": [
+                    
+                ],
+                "versions": [
+                    
+                ]
+            }
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "24.04.2"
+        },
+        "timestamp": "2024-06-21T13:33:51.151143139"
+    },
+    "sarscov2 illumina paired end [fastq]": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": false
+                    },
+                    "test.kraken2.report.txt:md5,4227755fe40478b8d7dc8634b489761e"
+                ]
+            ],
+            [
+                "versions.yml:md5,79adf2ca1cfc625cb77e391b27142c43"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-04T18:47:13.75649"
+    },
+    "sarscov2 illumina single end [fastq] + save_reads_assignment": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": true
+                    },
+                    "test.kraken2.report.txt:md5,4227755fe40478b8d7dc8634b489761e"
+                ]
+            ],
+            [
+                [
+                    {
+                        "id": "test",
+                        "single_end": true
+                    },
+                    "test.kraken2.classifiedreads.txt:md5,e7a90531f0d8d777316515c36fe4cae0"
+                ]
+            ],
+            [
+                "versions.yml:md5,79adf2ca1cfc625cb77e391b27142c43"
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.8.4",
+            "nextflow": "23.10.1"
+        },
+        "timestamp": "2024-04-04T18:47:22.459465"
+    }
+}
\ No newline at end of file
diff --git a/modules/nf-core/metabuli/classify/tests/nextflow-se.config b/modules/nf-core/metabuli/classify/tests/nextflow-se.config
new file mode 100644
index 00000000000..f8aca203f12
--- /dev/null
+++ b/modules/nf-core/metabuli/classify/tests/nextflow-se.config
@@ -0,0 +1,5 @@
+process {
+    withName: METABULI_CLASSIFY {
+        ext.args = '--seq-mode 1'
+    }
+}
diff --git a/modules/nf-core/metabuli/classify/tests/tags.yml b/modules/nf-core/metabuli/classify/tests/tags.yml
new file mode 100644
index 00000000000..9ebfd7ab6ee
--- /dev/null
+++ b/modules/nf-core/metabuli/classify/tests/tags.yml
@@ -0,0 +1,3 @@
+kraken2/kraken2:
+  - modules/nf-core/kraken2/kraken2/**
+  - modules/nf-core/untar/**

From d159b8c903104f3be72e61ff898674b1422e2325 Mon Sep 17 00:00:00 2001
From: Joon-Klaps <joon.klaps@kuleuven.be>
Date: Wed, 3 Jul 2024 13:05:53 +0000
Subject: [PATCH 20/20] fix linting & resource requirements

---
 modules/nf-core/metabuli/add/environment.yml  |  1 +
 modules/nf-core/metabuli/add/meta.yml         |  2 +-
 .../nf-core/metabuli/build/environment.yml    |  1 +
 modules/nf-core/metabuli/build/meta.yml       |  2 +-
 .../metabuli/build/tests/nextflow.config      |  2 +-
 .../nf-core/metabuli/classify/environment.yml |  1 +
 modules/nf-core/metabuli/classify/meta.yml    |  2 +-
 .../metabuli/classify/tests/main.nf.test      | 35 ++++++++++++++-----
 8 files changed, 33 insertions(+), 13 deletions(-)

diff --git a/modules/nf-core/metabuli/add/environment.yml b/modules/nf-core/metabuli/add/environment.yml
index 0e5eef64f23..492ffab0470 100644
--- a/modules/nf-core/metabuli/add/environment.yml
+++ b/modules/nf-core/metabuli/add/environment.yml
@@ -2,5 +2,6 @@ name: "metabuli_add"
 channels:
   - conda-forge
   - bioconda
+  - defaults
 dependencies:
   - "bioconda::metabuli=1.0.5"
diff --git a/modules/nf-core/metabuli/add/meta.yml b/modules/nf-core/metabuli/add/meta.yml
index c8a4e70f0a1..f7a9f78f66c 100644
--- a/modules/nf-core/metabuli/add/meta.yml
+++ b/modules/nf-core/metabuli/add/meta.yml
@@ -13,7 +13,7 @@ tools:
       documentation: "https://github.com/steineggerlab/Metabuli#readme"
       tool_dev_url: "https://github.com/steineggerlab/Metabuli"
       doi: "10.1101/2023.05.31.543018"
-      licence: "['GPL v3']"
+      licence: ['GPL v3']
 
 input:
   - meta:
diff --git a/modules/nf-core/metabuli/build/environment.yml b/modules/nf-core/metabuli/build/environment.yml
index 96f5393db66..b165712d709 100644
--- a/modules/nf-core/metabuli/build/environment.yml
+++ b/modules/nf-core/metabuli/build/environment.yml
@@ -2,5 +2,6 @@ name: "metabuli_build"
 channels:
   - conda-forge
   - bioconda
+  - defaults
 dependencies:
   - "bioconda::metabuli=1.0.5"
diff --git a/modules/nf-core/metabuli/build/meta.yml b/modules/nf-core/metabuli/build/meta.yml
index fe320627286..cc77e4fa5a9 100644
--- a/modules/nf-core/metabuli/build/meta.yml
+++ b/modules/nf-core/metabuli/build/meta.yml
@@ -13,7 +13,7 @@ tools:
     documentation: "https://github.com/steineggerlab/Metabuli#readme"
     tool_dev_url: "https://github.com/steineggerlab/Metabuli"
     doi: "10.1101/2023.05.31.543018"
-    licence: "['GPL v3']"
+    licence: ['GPL v3']
 
 input:
   - meta:
diff --git a/modules/nf-core/metabuli/build/tests/nextflow.config b/modules/nf-core/metabuli/build/tests/nextflow.config
index 32a9775a4b1..d1468cac635 100644
--- a/modules/nf-core/metabuli/build/tests/nextflow.config
+++ b/modules/nf-core/metabuli/build/tests/nextflow.config
@@ -1,6 +1,6 @@
 process {
     withName: METABULI_BUILD {
-        memory = 12.GB
+        memory = 7.GB
         ext.args = '--db-date 2024-6-21'
     }
 }
diff --git a/modules/nf-core/metabuli/classify/environment.yml b/modules/nf-core/metabuli/classify/environment.yml
index ce1ebe71f5b..abb788f31a2 100644
--- a/modules/nf-core/metabuli/classify/environment.yml
+++ b/modules/nf-core/metabuli/classify/environment.yml
@@ -2,5 +2,6 @@ name: metabuli_classify
 channels:
   - conda-forge
   - bioconda
+  - defaults
 dependencies:
   - "bioconda::metabuli=1.0.5"
diff --git a/modules/nf-core/metabuli/classify/meta.yml b/modules/nf-core/metabuli/classify/meta.yml
index fd910db5c21..3dcd9e99219 100644
--- a/modules/nf-core/metabuli/classify/meta.yml
+++ b/modules/nf-core/metabuli/classify/meta.yml
@@ -15,7 +15,7 @@ tools:
       documentation: "https://github.com/steineggerlab/Metabuli#readme"
       tool_dev_url: "https://github.com/steineggerlab/Metabuli"
       doi: "10.1101/2023.05.31.543018"
-      licence: "['GPL v3']"
+      licence: ['GPL v3']
 
 input:
   - meta:
diff --git a/modules/nf-core/metabuli/classify/tests/main.nf.test b/modules/nf-core/metabuli/classify/tests/main.nf.test
index 35a3f7e9ce5..38b79ff54ca 100644
--- a/modules/nf-core/metabuli/classify/tests/main.nf.test
+++ b/modules/nf-core/metabuli/classify/tests/main.nf.test
@@ -7,16 +7,34 @@ nextflow_process {
     tag "untar"
     tag "metabuli"
     tag "metabuli/classify"
+    tag "metabuli/add"
+    tag "metabuli/build"
 
     setup {
-        run("UNTAR") {
-            script "modules/nf-core/untar/main.nf"
+        run("METABULI_ADD") {
+            script "modules/nf-core/metabuli/add/main.nf"
             process {
                 """
-                input[0] = Channel.of([
-                    [],
-                    file(params.modules_testdata_base_path  + "delete_me/metabuli/metabuli_db.tar.gz", checkIfExists: true)
-                ])
+                input[0] = [
+                    [ id:'test' ],
+                        [
+                        file(params.modules_testdata_base_path +'genomics/sarscov2/genome/genome.fasta', checkIfExists: true),
+                        file(params.modules_testdata_base_path +'genomics/sarscov2/genome/proteome.fasta', checkIfExists: true),
+                        ]
+                    ]
+                input[1] = file(params.modules_testdata_base_path +'genomics/sarscov2/metagenome/prot_names.dmp', checkIfExists: true)
+                input[2] = file(params.modules_testdata_base_path +'genomics/sarscov2/metagenome/prot_nodes.dmp', checkIfExists: true)
+                input[3] = [] // needs a merged.dmp
+                input[4] = file(params.modules_testdata_base_path + 'delete_me/metabuli/acc2taxid', checkIfExists: true)
+                """
+            }
+        }
+        run("METABULI_BUILD") {
+            script "modules/nf-core/metabuli/build/main.nf"
+            process {
+                """
+                input[0] = METABULI_ADD.out.db
+                input[1] = []
                 """
             }
         }
@@ -34,7 +52,7 @@ nextflow_process {
                         checkIfExists: true
                     )]
                 ]
-                input[1] = UNTAR.out.untar
+                input[1] = METABULI_BUILD.out.db
                 """
             }
         }
@@ -49,7 +67,6 @@ nextflow_process {
 
     test("sarscov2 illumina paired end [fastq]") {
         when {
-
             process {
                 """
                 input[0] = [
@@ -66,7 +83,7 @@ nextflow_process {
 
                     ]
                 ]
-                input[1] = UNTAR.out.untar
+                input[1] = METABULI_BUILD.out.db
                 """
             }
         }