Untar unzip meta (#1408)

* fix: remove left-over unnecessary code

* Adds support for meta lists for unzip and untar

* Fix test inputs

* Update all modules to support extraction of decompressed file from untar/unzip new meta + file tuple

* Update all modules to support extraction of decompressed file from untar/unzip new meta + file tuple

* Fix MALTEXTRACT/AMPS

* Fix further modules

* Fix cellranger

* Apply suggestions from code review

Co-authored-by: Harshil Patel <drpatelh@users.noreply.github.com>

modules/untar/main.nf

@@ -8,19 +8,19 @@ process UNTAR {
         'biocontainers/biocontainers:v1.2.0_cv1' }"
 
     input:
-    path archive
+    tuple val(meta), path(archive)
 
     output:
-    path "$untar"      , emit: untar
+    tuple val(meta), path("$untar"), emit: untar
-    path "versions.yml", emit: versions
+    path "versions.yml"            , emit: versions
 
     when:
     task.ext.when == null || task.ext.when
 
     script:
-    def args = task.ext.args ?: ''
+    def args  = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
-    untar        = archive.toString() - '.tar.gz'
+    untar     = archive.toString() - '.tar.gz'
     """
     tar \\
         -xzvf \\

modules/untar/meta.yml

@@ -10,11 +10,21 @@ tools:
       documentation: https://www.gnu.org/software/tar/manual/
       licence: ["GPL-3.0-or-later"]
 input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
   - archive:
       type: file
       description: File to be untar
       pattern: "*.{tar}.{gz}"
 output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
   - untar:
       type: file
       description:

modules/unzip/main.nf

@@ -8,11 +8,11 @@ process UNZIP {
         'quay.io/biocontainers/p7zip:15.09--h2d50403_4' }"
 
     input:
-    path archive
+    tuple val(meta), path(archive)
 
     output:
-    path "${archive.baseName}/", emit: unzipped_archive
+    tuple val(meta), path("${archive.baseName}/"), emit: unzipped_archive
-    path "versions.yml"        , emit: versions
+    path "versions.yml"                          , emit: versions
 
     when:
     task.ext.when == null || task.ext.when

modules/unzip/meta.yml

@@ -12,12 +12,22 @@ tools:
       licence: ["LGPL-2.1-or-later"]
 
 input:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
   - archive:
       type: file
       description: ZIP file
       pattern: "*.zip"
 
 output:
+  - meta:
+      type: map
+      description: |
+        Groovy Map containing sample information
+        e.g. [ id:'test', single_end:false ]
   - unzipped_archive:
       type: directory
       description: Directory contents of the unzipped archive

tests/modules/amps/main.nf

@@ -15,18 +15,21 @@ workflow test_amps {
     fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     gff = []
     seq_type = "DNA"
-    map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true)
+    map_db = [ [], file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true) ]
-    input = file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    ]
     mode = "BlastN"
     taxon_list = file(params.test_data['sarscov2']['genome']['taxon_list_txt'], checkIfExists: true)
-    ncbi_dir = file(params.test_data['sarscov2']['genome']['ncbi_taxmap_zip'], checkIfExists: true)
+    ncbi_dir = [ [], file(params.test_data['sarscov2']['genome']['ncbi_taxmap_zip'], checkIfExists: true) ]
-    filter = "def_anc"
 
     UNZIP_MALT ( map_db )
     UNZIP_MALTEXTRACT ( ncbi_dir )
-    MALT_BUILD ( fastas, seq_type, gff, UNZIP_MALT.out.unzipped_archive )
+    MALT_BUILD ( fastas, seq_type, gff, UNZIP_MALT.out.unzipped_archive.map{ it[1] } )
     MALT_RUN ( input, mode, MALT_BUILD.out.index )
-    MALTEXTRACT ( MALT_RUN.out.rma6, taxon_list, UNZIP_MALTEXTRACT.out.unzipped_archive)
+    ch_input_to_maltextract = MALT_RUN.out.rma6.map{ it[1] }
+    MALTEXTRACT ( ch_input_to_maltextract, taxon_list, UNZIP_MALTEXTRACT.out.unzipped_archive.map{ it[1] })
 
     AMPS ( MALTEXTRACT.out.results, taxon_list, filter )
 }

tests/modules/artic/minion/main.nf

@@ -11,12 +11,12 @@ workflow test_artic_minion {
         [ id:'test', single_end:false ], // meta map
         file(params.test_data['sarscov2']['nanopore']['test_fastq_gz'], checkIfExists: true)
     ]
-    fast5_tar          = file(params.test_data['sarscov2']['nanopore']['fast5_tar_gz'], checkIfExists: true)
+    fast5_tar          = [ [], file(params.test_data['sarscov2']['nanopore']['fast5_tar_gz'], checkIfExists: true) ]
     sequencing_summary = file(params.test_data['sarscov2']['nanopore']['test_sequencing_summary'], checkIfExists: true)
     fasta              = file('https://github.com/artic-network/primer-schemes/raw/master/nCoV-2019/V3/nCoV-2019.reference.fasta', checkIfExists: true)
     bed                = file('https://github.com/artic-network/primer-schemes/raw/master/nCoV-2019/V3/nCoV-2019.primer.bed', checkIfExists: true)
 
-    fast5_dir = UNTAR ( fast5_tar ).untar
+    fast5_dir = UNTAR ( fast5_tar ).untar.map{ it[1] }
 
     ARTIC_MINION ( input, fast5_dir, sequencing_summary, fasta, bed, [], '', 'nCoV-2019', '3')
 }

tests/modules/cellranger/mkfastq/main.nf

@@ -8,19 +8,19 @@ include { CELLRANGER_MKFASTQ } from '../../../../modules/cellranger/mkfastq/main
 workflow test_cellranger_mkfastq_simple {
 
     simple_csv = file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-simple-1.2.0.csv", checkIfExists: true)
-    tiny_bcl = file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-1.2.0.tar.gz", checkIfExists: true)
+    tiny_bcl = [ [], file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-1.2.0.tar.gz", checkIfExists: true) ]
 
     UNTAR ( tiny_bcl )
 
-    CELLRANGER_MKFASTQ ( UNTAR.out.untar, simple_csv)
+    CELLRANGER_MKFASTQ ( UNTAR.out.untar.map{ it[1] }, simple_csv)
 }
 
 workflow test_cellranger_mkfastq_illumina {
 
     samplesheet_csv = file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-samplesheet-1.2.0.csv", checkIfExists: true)
-    tiny_bcl = file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-1.2.0.tar.gz", checkIfExists: true)
+    tiny_bcl = [ [], file("https://cf.10xgenomics.com/supp/cell-exp/cellranger-tiny-bcl-1.2.0.tar.gz", checkIfExists: true) ]
 
     UNTAR ( tiny_bcl )
 
-    CELLRANGER_MKFASTQ ( UNTAR.out.untar, samplesheet_csv)
+    CELLRANGER_MKFASTQ ( UNTAR.out.untar.map{ it[1] }, samplesheet_csv)
 }

tests/modules/controlfreec/main.nf

@@ -19,7 +19,7 @@ workflow test_controlfreec {
     dbsnp = file(params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz'], checkIfExists: true)
     dbsnp_tbi = file(params.test_data['homo_sapiens']['genome']['dbsnp_138_hg38_21_vcf_gz_tbi'], checkIfExists: true)
 
-    chrfiles = file(params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir'], checkIfExists: true)
+    chrfiles = [ [], file(params.test_data['homo_sapiens']['genome']['genome_21_chromosomes_dir'], checkIfExists: true) ]
     target_bed = file(params.test_data['homo_sapiens']['genome']['genome_21_multi_interval_bed'], checkIfExists: true)
 
     UNTAR(chrfiles)
@@ -29,7 +29,7 @@ workflow test_controlfreec {
                             [],
                             dbsnp,
                             dbsnp_tbi,
-                            UNTAR.out.untar,
+                            UNTAR.out.untar.map{ it[1] },
                             [],
                             target_bed,
                             []

tests/modules/gatk4/createsomaticpanelofnormals/main.nf

@@ -6,12 +6,12 @@ include { UNTAR           } from '../../../../modules/untar/main.nf'
 include { GATK4_CREATESOMATICPANELOFNORMALS } from '../../../../modules/gatk4/createsomaticpanelofnormals/main.nf'
 
 workflow test_gatk4_createsomaticpanelofnormals {
-    db    = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+    db    = [[], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( db )
 
     input = Channel.of([ id:'test'])
-              .combine(UNTAR.out.untar)
+              .combine(UNTAR.out.untar.map{ it[1] })
 
     fasta = file(params.test_data['homo_sapiens']['genome']['genome_fasta'], checkIfExists: true)
     fastaidx = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)

tests/modules/gatk4/genomicsdbimport/main.nf

@@ -22,7 +22,7 @@ workflow test_gatk4_genomicsdbimport_create_genomicsdb {
 }
 
 workflow test_gatk4_genomicsdbimport_get_intervalslist {
-    db    = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+    db    = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( db )
 
@@ -31,7 +31,7 @@ workflow test_gatk4_genomicsdbimport_get_intervalslist {
               [] ,
               [] ,
               [] ])
-              .combine(UNTAR.out.untar)
+              .combine(UNTAR.out.untar.map{ it[1] })
 
     run_intlist = true
     run_updatewspace = false
@@ -41,7 +41,7 @@ workflow test_gatk4_genomicsdbimport_get_intervalslist {
 }
 
 workflow test_gatk4_genomicsdbimport_update_genomicsdb {
-    db    = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+    db    = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( db )
 
@@ -50,7 +50,7 @@ workflow test_gatk4_genomicsdbimport_update_genomicsdb {
               file( params.test_data['homo_sapiens']['illumina']['test2_genome_vcf_gz_tbi'] , checkIfExists: true) ,
               [] ,
               [] ])
-              .combine(UNTAR.out.untar)
+              .combine(UNTAR.out.untar.map{ it[1] })
 
     run_intlist = false
     run_updatewspace = true

tests/modules/gatk4/genotypegvcfs/main.nf

@@ -97,10 +97,10 @@ workflow test_gatk4_genotypegvcfs_gendb_input {
     fastaIndex      = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
     fastaDict       = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
-    test_genomicsdb = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+    test_genomicsdb = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( test_genomicsdb )
-    gendb = UNTAR.out.untar.collect()
+    gendb = UNTAR.out.untar.map{ it[1] }.collect()
     gendb.add([])
     gendb.add([])
 
@@ -119,10 +119,10 @@ workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp {
     dbsnp        = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz'], checkIfExists: true)
     dbsnpIndex   = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
 
-    test_genomicsdb = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+    test_genomicsdb = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( test_genomicsdb )
-    gendb = UNTAR.out.untar.collect()
+    gendb = UNTAR.out.untar.map{ it[1] }.collect()
     gendb.add([])
     gendb.add([])
     input = Channel.of([ id:'test' ]).combine(gendb)
@@ -137,10 +137,10 @@ workflow test_gatk4_genotypegvcfs_gendb_input_intervals {
     fastaIndex   = file(params.test_data['homo_sapiens']['genome']['genome_fasta_fai'], checkIfExists: true)
     fastaDict    = file(params.test_data['homo_sapiens']['genome']['genome_dict'], checkIfExists: true)
 
-    test_genomicsdb = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+    test_genomicsdb = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( test_genomicsdb )
-    gendb = UNTAR.out.untar.collect()
+    gendb = UNTAR.out.untar.map{ it[1] }.collect()
     gendb.add([])
     gendb.add([file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)])
     input = Channel.of([ id:'test' ]).combine(gendb)
@@ -158,10 +158,10 @@ workflow test_gatk4_genotypegvcfs_gendb_input_dbsnp_intervals {
     dbsnp        = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz'], checkIfExists: true)
     dbsnpIndex   = file(params.test_data['homo_sapiens']['genome']['dbsnp_146_hg38_vcf_gz_tbi'], checkIfExists: true)
 
-    test_genomicsdb = file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true)
+    test_genomicsdb = [ [], file(params.test_data['homo_sapiens']['illumina']['test_genomicsdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( test_genomicsdb )
-    gendb = UNTAR.out.untar.collect()
+    gendb = UNTAR.out.untar.map{ it[1] }.collect()
     gendb.add([])
     gendb.add([file(params.test_data['homo_sapiens']['genome']['genome_bed'], checkIfExists: true)])
     input = Channel.of([ id:'test' ]).combine(gendb)

tests/modules/kraken2/kraken2/main.nf

@@ -9,10 +9,10 @@ workflow test_kraken2_kraken2_single_end {
     input = [ [ id:'test', single_end:true ], // meta map
               [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
             ]
-    db    = file(params.test_data['sarscov2']['genome']['kraken2_tar_gz'], checkIfExists: true)
+    db    = [ [], file(params.test_data['sarscov2']['genome']['kraken2_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( db )
-    KRAKEN2_KRAKEN2 ( input, UNTAR.out.untar )
+    KRAKEN2_KRAKEN2 ( input, UNTAR.out.untar.map{ it[1] } )
 }
 
 workflow test_kraken2_kraken2_paired_end {
@@ -20,8 +20,8 @@ workflow test_kraken2_kraken2_paired_end {
               [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true),
                 file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
             ]
-    db    = file(params.test_data['sarscov2']['genome']['kraken2_tar_gz'], checkIfExists: true)
+    db    = [ [], file(params.test_data['sarscov2']['genome']['kraken2_tar_gz'], checkIfExists: true) ]
-    
+
     UNTAR ( db )
-    KRAKEN2_KRAKEN2 ( input, UNTAR.out.untar )   
+    KRAKEN2_KRAKEN2 ( input, UNTAR.out.untar.map{ it[1] } )
 }

tests/modules/last/lastal/main.nf

@@ -10,10 +10,10 @@ workflow test_last_lastal_with_dummy_param_file {
     input = [ [ id:'contigs', single_end:false ], // meta map
               file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true),
               [] ]
-    db    = [ file(params.test_data['sarscov2']['genome']['lastdb_tar_gz'], checkIfExists: true) ]
+    db    = [ [], file(params.test_data['sarscov2']['genome']['lastdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( db )
-    LAST_LASTAL ( input, UNTAR.out.untar)
+    LAST_LASTAL ( input, UNTAR.out.untar.map{ it[1] })
 }
 
 workflow test_last_lastal_with_real_param_file {
@@ -21,8 +21,8 @@ workflow test_last_lastal_with_real_param_file {
     input      = [ [ id:'contigs', single_end:false ], // meta map
                    file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true),
                    file(params.test_data['sarscov2']['genome']['contigs_genome_par'], checkIfExists: true) ]
-    db         = [ file(params.test_data['sarscov2']['genome']['lastdb_tar_gz'], checkIfExists: true) ]
+    db         = [ [], file(params.test_data['sarscov2']['genome']['lastdb_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( db )
-    LAST_LASTAL ( input, UNTAR.out.untar)
+    LAST_LASTAL ( input, UNTAR.out.untar.map{ it[1] })
 }

tests/modules/last/train/main.nf

@@ -7,9 +7,9 @@ include { LAST_TRAIN } from '../../../../modules/last/train/main.nf'
 
 workflow test_last_train {
 
-    db =         [ file(params.test_data['sarscov2']['genome']['lastdb_tar_gz'], checkIfExists: true) ]
+    db =         [ [], file(params.test_data['sarscov2']['genome']['lastdb_tar_gz'], checkIfExists: true) ]
     input =      [ [ id:'contigs' ], // meta map
                    file(params.test_data['sarscov2']['illumina']['contigs_fasta'], checkIfExists: true) ]
     UNTAR ( db )
-    LAST_TRAIN ( input, UNTAR.out.untar )
+    LAST_TRAIN ( input, UNTAR.out.untar.map{ it[1] } )
 }

tests/modules/malt/build_test/main.nf

@@ -9,18 +9,18 @@ workflow test_malt_build {
     fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     seq_type = "DNA"
     gff = []
-    map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true)
+    map_db = [ [], file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true) ]
 
     UNZIP ( map_db )
-    MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive )
+    MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive.map{ it[1] } )
 }
 
 workflow test_malt_build_gff {
     fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     seq_type = "DNA"
     gff = file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true)
-    map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true)
+    map_db = [ [], file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true) ]
 
     UNZIP ( map_db )
-    MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive )
+    MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive.map{ it[1] } )
 }

tests/modules/malt/run/main.nf

@@ -2,16 +2,16 @@
 
 nextflow.enable.dsl = 2
 
-include { UNZIP } from '../../../../modules/unzip/main.nf'
+include { UNZIP      } from '../../../../modules/unzip/main.nf'
 include { MALT_BUILD } from  '../../../../modules/malt/build/main.nf'
-include { MALT_RUN } from '../../../../modules/malt/run/main.nf'
+include { MALT_RUN   } from '../../../../modules/malt/run/main.nf'
 
 workflow test_malt_run {
 
     fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     gff = file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true)
     seq_type = "DNA"
-    map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true)
+    map_db = [ [], file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true) ]
     input = [
         [ id:'test', single_end:false ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
@@ -19,7 +19,7 @@ workflow test_malt_run {
     mode = "BlastN"
 
     UNZIP ( map_db )
-    MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive )
+    MALT_BUILD ( fastas, seq_type, gff, UNZIP.out.unzipped_archive.map { it[1] } )
     MALT_RUN ( input, mode, MALT_BUILD.out.index )
 }
 

tests/modules/maltextract/main.nf

@@ -4,24 +4,28 @@ nextflow.enable.dsl = 2
 
 include { UNZIP as UNZIP_MALT        } from '../../../modules/unzip/main.nf'
 include { UNZIP as UNZIP_MALTEXTRACT }  from '../../../modules/unzip/main.nf'
-include { MALT_BUILD  } from  '../../../modules/malt/build/main.nf'
+include { MALT_BUILD                 } from  '../../../modules/malt/build/main.nf'
-include { MALT_RUN    } from '../../../modules/malt/run/main.nf'
+include { MALT_RUN                   } from '../../../modules/malt/run/main.nf'
-include { MALTEXTRACT } from '../../../modules/maltextract/main.nf'
+include { MALTEXTRACT                } from '../../../modules/maltextract/main.nf'
 
 workflow test_maltextract {
 
     fastas = file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true)
     gff = []
     seq_type = "DNA"
-    map_db = file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true)
+    map_db = [ [], file("https://software-ab.informatik.uni-tuebingen.de/download/megan6/megan-nucl-Jan2021.db.zip", checkIfExists: true) ]
-    input = file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    input = [
+        [ id:'test', single_end:false ], // meta map
+        file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true)
+    ]
     mode = "BlastN"
     taxon_list = file(params.test_data['sarscov2']['genome']['taxon_list_txt'], checkIfExists: true)
-    ncbi_dir = file(params.test_data['sarscov2']['genome']['ncbi_taxmap_zip'], checkIfExists: true)
+    ncbi_dir = [ [], file(params.test_data['sarscov2']['genome']['ncbi_taxmap_zip'], checkIfExists: true) ]
 
     UNZIP_MALT ( map_db )
     UNZIP_MALTEXTRACT ( ncbi_dir )
-    MALT_BUILD ( fastas, seq_type, gff, UNZIP_MALT.out.unzipped_archive )
+    MALT_BUILD ( fastas, seq_type, gff, UNZIP_MALT.out.unzipped_archive.map{ it[1] } )
     MALT_RUN ( input, mode, MALT_BUILD.out.index )
-    MALTEXTRACT ( MALT_RUN.out.rma6, taxon_list, UNZIP_MALTEXTRACT.out.unzipped_archive)
+    ch_input_to_maltextract = MALT_RUN.out.rma6.map{ it[1] }
+    MALTEXTRACT ( ch_input_to_maltextract, taxon_list, UNZIP_MALTEXTRACT.out.unzipped_archive.map{ it[1] })
 }

tests/modules/maltextract/test.yml

@@ -3,8 +3,6 @@
   tags:
     - maltextract
   files:
-    - path: output/maltextract/results/error.txt
-      md5sum: d41d8cd98f00b204e9800998ecf8427e
     - path: output/maltextract/results/error.txt
     - path: output/maltextract/results/log.txt
       contains:

tests/modules/metaphlan3/main.nf

@@ -12,10 +12,10 @@ workflow test_metaphlan3_single_end {
               [ file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) ]
             ]
 
-    db    = channel.fromPath('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan_database.tar.gz', type: 'dir', checkIfExists: true)
+    db    = [ [], file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan_database.tar.gz', checkIfExists: true) ]
 
     UNTAR ( db )
-    METAPHLAN3 ( input, UNTAR.out.untar )
+    METAPHLAN3 ( input, UNTAR.out.untar.map{ it[1] } )
 }
 
 workflow test_metaphlan3_paired_end {
@@ -25,11 +25,10 @@ workflow test_metaphlan3_paired_end {
                 file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
             ]
 
-    db    = channel.fromPath('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan_database.tar.gz', type: 'dir', checkIfExists: true)
+    db    = [ [], file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan_database.tar.gz', checkIfExists: true) ]
-
 
     UNTAR ( db )
-    METAPHLAN3 ( input, UNTAR.out.untar )
+    METAPHLAN3 ( input, UNTAR.out.untar.map{ it[1] } )
 }
 
 workflow test_metaphlan3_sam {
@@ -38,12 +37,11 @@ workflow test_metaphlan3_sam {
               [ file(params.test_data['sarscov2']['illumina']['test_single_end_bam'], checkIfExists: true) ]
             ]
 
-    db    = channel.fromPath('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan_database.tar.gz', type: 'dir', checkIfExists: true)
+    db    = [ [], file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan_database.tar.gz', checkIfExists: true) ]
-
 
     UNTAR ( db )
     SAMTOOLS_VIEW ( input, [] )
-    METAPHLAN3 ( SAMTOOLS_VIEW.out.bam, UNTAR.out.untar )
+    METAPHLAN3 ( SAMTOOLS_VIEW.out.bam, UNTAR.out.untar.map{ it[1] } )
 }
 
 workflow test_metaphlan3_fasta {
@@ -52,8 +50,8 @@ workflow test_metaphlan3_fasta {
               [ file(params.test_data['sarscov2']['genome']['transcriptome_fasta'], checkIfExists: true) ]
             ]
 
-    db    = channel.fromPath('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan_database.tar.gz', type: 'dir', checkIfExists: true)
+    db    = [ [], file('https://raw.githubusercontent.com/nf-core/test-datasets/modules/data/delete_me/metaphlan_database.tar.gz', checkIfExists: true) ]
 
     UNTAR ( db )
-    METAPHLAN3 ( input, UNTAR.out.untar )
+    METAPHLAN3 ( input, UNTAR.out.untar.map{ it[1] } )
 }

tests/modules/sratools/fasterqdump/main.nf

@@ -7,22 +7,22 @@ include { SRATOOLS_FASTERQDUMP } from '../../../../modules/sratools/fasterqdump/
 
 workflow test_sratools_fasterqdump_single_end {
 
-    archive = file(params.test_data['sarscov2']['illumina']['SRR13255544_tar_gz'], checkIfExists: true)
+    archive = [ [], file(params.test_data['sarscov2']['illumina']['SRR13255544_tar_gz'], checkIfExists: true) ]
     UNTAR ( archive )
 
     def input = Channel.of([ id:'test_single_end', single_end:true ])
-        .combine(UNTAR.out.untar)
+        .combine(UNTAR.out.untar.map{ it[1] })
 
     SRATOOLS_FASTERQDUMP ( input )
 }
 
 workflow test_sratools_fasterqdump_paired_end {
 
-    archive = file(params.test_data['sarscov2']['illumina']['SRR11140744_tar_gz'], checkIfExists: true)
+    archive = [ [], file(params.test_data['sarscov2']['illumina']['SRR11140744_tar_gz'], checkIfExists: true) ]
     UNTAR ( archive )
 
     def input = Channel.of([ id:'test_paired_end', single_end:false ])
-        .combine(UNTAR.out.untar)
+        .combine(UNTAR.out.untar.map{ it[1] })
 
     SRATOOLS_FASTERQDUMP ( input )
 }

tests/modules/untar/main.nf

@@ -5,7 +5,10 @@ nextflow.enable.dsl = 2
 include { UNTAR } from '../../../modules/untar/main.nf'
 
 workflow test_untar {
-    input = file(params.test_data['sarscov2']['genome']['kraken2_tar_gz'], checkIfExists: true)
+    input = [
+        [],
+        file(params.test_data['sarscov2']['genome']['kraken2_tar_gz'], checkIfExists: true)
+    ]
 
     UNTAR ( input )
 }

tests/modules/unzip/main.nf

@@ -6,7 +6,10 @@ include { UNZIP } from '../../../modules/unzip/main.nf'
 
 workflow test_unzip {
 
-    archive = file(params.test_data['sarscov2']['genome']['ncbi_taxmap_zip'], checkIfExists: true)
+    archive = [
+        [],
+        file(params.test_data['sarscov2']['genome']['ncbi_taxmap_zip'], checkIfExists: true)
+    ]
 
     UNZIP ( archive )
 }

tests/modules/vcfanno/main.nf

@@ -6,36 +6,36 @@ include { UNTAR } from '../../../modules/untar/main.nf'
 include { VCFANNO } from '../../../modules/vcfanno/main.nf'
 
 workflow test_vcfanno {
-    
+
-    input = [ 
+    input = [
         [ id:'test_compressed', single_end:false ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf_gz'], checkIfExists: true),
         file(params.test_data['sarscov2']['illumina']['test_vcf_gz_tbi'], checkIfExists: true)
     ]
-    
+
-    input_2 = [ [ id:'test_compressed', single_end:false ], // meta map 
+    input_2 = [ [ id:'test_compressed', single_end:false ], // meta map
                 [] ]
 
     toml = file(params.test_data['homo_sapiens']['genome']['vcfanno_toml'], checkIfExists: true)
-    resource_dir = file(params.test_data['homo_sapiens']['genome']['vcfanno_tar_gz'], checkIfExists: true)
+    resource_dir = [[], file(params.test_data['homo_sapiens']['genome']['vcfanno_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( resource_dir )
-    VCFANNO ( input, input_2, toml, UNTAR.out.untar )
+    VCFANNO ( input, input_2, toml, UNTAR.out.untar.map{ it[1] } )
 }
 
 workflow test_vcfanno_uncompressed {
 
     input = [ [ id:'test_uncompressed', single_end:false ], // meta map
                 [] ,[] ]
-    
+
-    input_2 = [ 
+    input_2 = [
         [ id:'test_uncompressed', single_end:false ], // meta map
         file(params.test_data['sarscov2']['illumina']['test_vcf'], checkIfExists: true)
     ]
 
     toml = file(params.test_data['homo_sapiens']['genome']['vcfanno_toml'], checkIfExists: true)
-    resource_dir = file(params.test_data['homo_sapiens']['genome']['vcfanno_tar_gz'], checkIfExists: true)
+    resource_dir = [[], file(params.test_data['homo_sapiens']['genome']['vcfanno_tar_gz'], checkIfExists: true) ]
 
     UNTAR ( resource_dir )
-    VCFANNO ( input, input_2, toml, UNTAR.out.untar )
+    VCFANNO ( input, input_2, toml, UNTAR.out.untar.map{ it[1] } )
-}
+}