Fix fastANI module

modules/nf-core/fastani/environment.yml

@@ -4,4 +4,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::fastani=1.32
+  - bioconda::fastani=1.34

modules/nf-core/fastani/main.nf

@@ -4,47 +4,43 @@ process FASTANI {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/fastani:1.32--he1c1bb9_0' :
-        'biocontainers/fastani:1.32--he1c1bb9_0' }"
+        'https://depot.galaxyproject.org/singularity/fastani:1.34--hb66fcc3_7' :
+        'biocontainers/fastani:1.34--hb66fcc3_7' }"
 
     input:
-    tuple val(meta), path(query)
-    path reference
+    tuple val(meta),  path(query)
+    tuple val(meta2), path(reference)
+    path(ql)
+    path(rl)
 
     output:
-    tuple val(meta), path("*.ani.txt"), emit: ani
-    path "versions.yml"               , emit: versions
+    tuple val(meta), path("*.txt")   , emit: ani
+    tuple val(meta), path("*.visual"), optional:true, emit: visual
+    tuple val(meta), path("*.matrix"), optional:true, emit: matrix
+    tuple val("${task.process}"), val("fastani"), eval('fastANI --version'), topic: versions, emit: versions_fastani
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: ''
-    def prefix = task.ext.prefix ?: "${meta.id}"
-
-    if (meta.batch_input) {
-        """
-        fastANI \\
-            -ql $query \\
-            -rl $reference \\
-            -o ${prefix}.ani.txt
-
-        cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            fastani: \$(fastANI --version 2>&1 | sed 's/version//;')
-        END_VERSIONS
-        """
-    } else {
-        """
-        fastANI \\
-            -q $query \\
-            -r $reference \\
-            -o ${prefix}.ani.txt
-
-        cat <<-END_VERSIONS > versions.yml
-        "${task.process}":
-            fastani: \$(fastANI --version 2>&1 | sed 's/version//;')
-        END_VERSIONS
-        """
-    }
+    def args            = task.ext.args ?: ''
+    def prefix          = task.ext.prefix ?: ( meta.id ?: 'all' )
+    def prefix2         = task.ext.prefix2 ?: ( meta2.id ?: 'all' )
+    def input_query     = query ? "-q ${query}": "--ql ${ql}"
+    def input_reference = reference ? "-r ${reference}": "--rl ${rl}"
+    """
+    fastANI \\
+        $input_query \\
+        $input_reference \\
+        --threads $task.cpus \\
+        -o ${prefix}.txt
+    """
+
+    stub:
+    def prefix          = task.ext.prefix  ?: ( meta.id  ?: 'all')
+    """
+    touch ${prefix}.visual
+    touch ${prefix}.txt
+    touch ${prefix}.matrix
+    """
 }

modules/nf-core/fastani/meta.yml

@@ -1,13 +1,12 @@
 name: fastani
-description: Alignment-free computation of average nucleotide Identity (ANI)
+description: Alignment-free computation of Average Nucleotide Identity (ANI)
 keywords:
   - genome
   - fasta
   - ANI
 tools:
   - fastani:
-      description: FastANI is developed for fast alignment-free computation of whole-genome
-        Average Nucleotide Identity (ANI).
+      description: FastANI is developed for fast alignment-free computation of whole-genome Average Nucleotide Identity (ANI).
       homepage: https://github.com/ParBLiSS/FastANI
       documentation: https://github.com/ParBLiSS/FastANI
       tool_dev_url: https://github.com/ParBLiSS/FastANI
@@ -19,37 +18,85 @@ input:
         type: map
         description: |
           Groovy Map containing sample information
-          e.g. [ id:'test', single_end:false ]
+          e.g. [ id:'test' ]
     - query:
         type: file
-        description: Fasta file(s) to be queried
-        pattern: "*.fasta"
-        ontologies: []
-  - reference:
+        description: Fasta file to be used as the query. If provided, ql will be ignored.
+        pattern: "*.{fasta,fna,fa}"
+        ontologies:
+          - edam: http://edamontology.org/format_1929 # FASTA
+  - - meta2:
+        type: map
+        description: Groovy Map containing sample information for the reference
+    - reference:
+        type: file
+        description: Fasta file to be used as the reference. If provided, rl will be ignored.
+        pattern: "*.{fasta,fna,fa}"
+        ontologies:
+          - edam: http://edamontology.org/format_1929 # FASTA
+  - ql:
+      type: file
+      description: File containing a list of query fasta paths. query input takes precedence over this list if both are provided.
+      pattern: "*.txt"
+      ontologies:
+        - edam: "http://edamontology.org/format_2330" # TXT
+  - rl:
       type: file
-      description: Fasta file(s) to be used as reference for the query
-      pattern: "*.fasta"
-      ontologies: []
+      description: File containing a list of reference fasta paths. reference input takes precedence over this list if both are provided.
+      pattern: "*.txt"
+      ontologies:
+        - edam: "http://edamontology.org/format_2330" # TXT
 output:
   ani:
     - - meta:
           type: map
           description: |
             Groovy Map containing sample information
-            e.g. [ id:'test', single_end:false ]
-      - "*.ani.txt":
+            e.g. [ id:'test' ]
+      - "*.txt":
           type: file
-          description: Results of the query
-          pattern: "*.ani.txt"
-          ontologies: []
-  versions:
-    - versions.yml:
-        type: file
-        description: File containing software versions
-        pattern: "versions.yml"
-        ontologies:
-          - edam: http://edamontology.org/format_3750 # YAML
+          description: ANI results file
+          pattern: "*.txt"
+          ontologies:
+            - edam: "http://edamontology.org/format_2330" # TXT
+  visual:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*.visual":
+          type: file
+          optional: true
+          description: FastANI visualization output
+          pattern: "*.visual"
+          ontologies:
+            - edam: "http://edamontology.org/format_3475" # TSV
+  matrix:
+    - - meta:
+          type: map
+          description: |
+            Groovy Map containing sample information
+            e.g. [ id:'test' ]
+      - "*.matrix":
+          type: file
+          optional: true
+          description: ANI matrix output
+          ontologies:
+            - edam: "http://edamontology.org/format_3033" # MATRIX
+  versions_fastani:
+    - - ${task.process}:
+          type: string
+          description: The name of the process
+      - fastani:
+          type: string
+          description: The name of the tool
+      - fastANI --version:
+          type: eval
+          description: The expression to obtain the version of the tool
 authors:
   - "@abhi18av"
+  - "@Ethan-Hetrick"
 maintainers:
   - "@abhi18av"
+  - "@Ethan-Hetrick"

modules/nf-core/fastani/tests/main.nf.test

@@ -6,8 +6,8 @@ nextflow_process {
     tag "fastani"
     script "../main.nf"
     process "FASTANI"
-
-    test("FastANI") {
+    config "./nextflow.config"
+    test("sarscov2 - referece vs contigs - fastANI - 1 v 1 mode") {
 
         when {
             process {
@@ -16,14 +16,90 @@ nextflow_process {
                     [ id:'test' ],
                     file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
                 ]
-                input[1] = file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/contigs.fasta', checkIfExists: true)
+                input[1] = [
+                    [ id:'test2' ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/contigs.fasta', checkIfExists: true)
+                ]
+                input[2] = []
+                input[3] = []
+                """
+            }
+        }
+
+        then {
+            assertAll (
+                { assert snapshot(
+                    process.out.ani,
+                    process.out.findAll { key, val -> key.startsWith("versions")}
+                ).match() }
+            )
+        }
+    }
+
+    test("sarscov2 - referece vs contigs - fastANI - all vs all mode") {
+
+        when {
+            process {
+                """
+                def q_src = file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                def r_src = file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/contigs.fasta', checkIfExists: true)
+
+                // stage into the nf-test execution directory
+                def q_stage = new File(workDir.toString(), 'query.fasta')
+                def r_stage = new File(workDir.toString(), 'ref.fasta')
+
+                // Ensures files are staged locally
+                q_stage.bytes = q_src.bytes
+                r_stage.bytes = r_src.bytes
+
+                // create ql/rl list files
+                def ql_file = new File(workDir.toString(), 'query.list')
+                def rl_file = new File(workDir.toString(), 'reference.list')
+
+                ql_file.text = q_stage.getAbsolutePath() + System.lineSeparator()
+                rl_file.text = r_stage.getAbsolutePath() + System.lineSeparator()
+
+                input[0] = [ [], [] ]
+                input[1] = [ [], [] ]
+                input[2] = file( ql_file.getAbsolutePath(), checkIfExists: true )
+                input[3] = file( rl_file.getAbsolutePath(), checkIfExists: true )
                 """
             }
         }
 
         then {
             assertAll(
-                { assert process.success },
+                { assert snapshot(
+                    process.out.ani,
+                    process.out.findAll { key, val -> key.startsWith("versions") }
+                ).match() }
+            )
+        }
+    }
+
+    test("stub") {
+
+        options '-stub'
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/genome/genome.fasta', checkIfExists: true)
+                ]
+                input[1] = [
+                    [ id:'test2' ],
+                    file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fasta/contigs.fasta', checkIfExists: true)
+                ]
+                input[2] = []
+                input[3] = []
+                """
+            }
+        }
+
+        then {
+            assertAll (
                 { assert snapshot(process.out).match() }
             )
         }