Change Spades input (#1039)

* Change spades module

* correct meta map description

* adjust memory handling

* remove trailing whitespace

* fix hmm input

* Update modules/spades/main.nf

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

modules/spades/main.nf

@@ -19,46 +19,57 @@ process SPADES {
     }
 
     input:
-    tuple val(meta), path(reads)
+    tuple val(meta), path(illumina), path(pacbio), path(nanopore)
     path  hmm
 
     output:
-    tuple val(meta), path('*.scaffolds.fa')    , optional:true, emit: scaffolds
+    tuple val(meta), path('*.scaffolds.fa.gz')    , optional:true, emit: scaffolds
-    tuple val(meta), path('*.contigs.fa')      , optional:true, emit: contigs
+    tuple val(meta), path('*.contigs.fa.gz')      , optional:true, emit: contigs
-    tuple val(meta), path('*.transcripts.fa')  , optional:true, emit: transcripts
+    tuple val(meta), path('*.transcripts.fa.gz')  , optional:true, emit: transcripts
-    tuple val(meta), path('*.gene_clusters.fa'), optional:true, emit: gene_clusters
+    tuple val(meta), path('*.gene_clusters.fa.gz'), optional:true, emit: gene_clusters
-    tuple val(meta), path('*.assembly.gfa')    , optional:true, emit: gfa
+    tuple val(meta), path('*.assembly.gfa.gz')    , optional:true, emit: gfa
     tuple val(meta), path('*.log')                , emit: log
     path  "versions.yml"                          , emit: versions
 
     script:
     def prefix = options.suffix ? "${meta.id}${options.suffix}" : "${meta.id}"
-    def input_reads = meta.single_end ? "-s $reads" : "-1 ${reads[0]} -2 ${reads[1]}"
+    def maxmem = task.memory.toGiga()
-    def custom_hmms = params.spades_hmm ? "--custom-hmms $hmm" : ""
+    def illumina_reads = illumina ? ( meta.single_end ? "-s $illumina" : "-1 ${illumina[0]} -2 ${illumina[1]}" ) : ""
+    def pacbio_reads = pacbio ? "--pacbio $pacbio" : ""
+    def nanopore_reads = nanopore ? "--nanopore $nanopore" : ""
+    def custom_hmms = hmm ? "--custom-hmms $hmm" : ""
     """
     spades.py \\
         $options.args \\
         --threads $task.cpus \\
+        --memory $maxmem \\
         $custom_hmms \\
-        $input_reads \\
+        $illumina_reads \\
+        $pacbio_reads \\
+        $nanopore_reads \\
         -o ./
     mv spades.log ${prefix}.spades.log
 
     if [ -f scaffolds.fasta ]; then
         mv scaffolds.fasta ${prefix}.scaffolds.fa
+        gzip -n ${prefix}.scaffolds.fa
     fi
     if [ -f contigs.fasta ]; then
         mv contigs.fasta ${prefix}.contigs.fa
+        gzip -n ${prefix}.contigs.fa
     fi
     if [ -f transcripts.fasta ]; then
         mv transcripts.fasta ${prefix}.transcripts.fa
+        gzip -n ${prefix}.transcripts.fa
     fi
     if [ -f assembly_graph_with_scaffolds.gfa ]; then
         mv assembly_graph_with_scaffolds.gfa ${prefix}.assembly.gfa
+        gzip -n ${prefix}.assembly.gfa
     fi
 
     if [ -f gene_clusters.fasta ]; then
         mv gene_clusters.fasta ${prefix}.gene_clusters.fa
+        gzip -n ${prefix}.gene_clusters.fa
     fi
 
     cat <<-END_VERSIONS > versions.yml

modules/spades/meta.yml

@@ -20,11 +20,20 @@ input:
       description: |
         Groovy Map containing sample information
         e.g. [ id:'test', single_end:false ]
-  - reads:
+  - illumina:
       type: file
       description: |
-        List of input FastQ files of size 1 and 2 for single-end and paired-end data,
+        List of input FastQ (Illumina or PacBio CCS reads) files
-        respectively.
+        of size 1 and 2 for single-end and paired-end data,
+        respectively. This input data type is required.
+  - pacbio:
+      type: file
+      description: |
+        List of input PacBio CLR FastQ files of size 1.
+  - nanopore:
+      type: file
+      description: |
+        List of input FastQ files of size 1, originating from Oxford Nanopore technology.
   - hmm:
       type: file
       description:
@@ -39,26 +48,32 @@ output:
       type: file
       description: |
         Fasta file containing scaffolds
+      pattern: "*.fa.gz"
   - contigs:
       type: file
       description: |
         Fasta file containing contigs
+      pattern: "*.fa.gz"
   - transcripts:
       type: file
       description: |
         Fasta file containing transcripts
+      pattern: "*.fa.gz"
   - gene_clusters:
       type: file
       description: |
         Fasta file containing gene_clusters
+      pattern: "*.fa.gz"
   - gfa:
       type: file
       description: |
         gfa file containing assembly
+      pattern: "*.gfa.gz"
   - log:
       type: file
       description: |
         Spades log file
+      pattern: "*.log"
   - versions:
       type: file
       description: File containing software versions
@@ -67,3 +82,4 @@ output:
 authors:
   - "@JoseEspinosa"
   - "@drpatelh"
+  - "@d4straub"

tests/modules/spades/main.nf

@@ -2,11 +2,13 @@
 
 nextflow.enable.dsl = 2
 
-include { SPADES } from '../../../modules/spades/main.nf' addParams( spades_hmm: false ,options: ['args': '--rnaviral'] )
+include { SPADES } from '../../../modules/spades/main.nf' addParams( options: ['args': '--rnaviral'] )
 
 workflow test_spades_single_end {
     input = [ [ id:'test', single_end:true ], // meta map
-              [ file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ]
+              [ file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ],
+              [],
+              []
             ]
     SPADES ( input, [] )
 }
@@ -14,7 +16,32 @@ workflow test_spades_single_end {
 workflow test_spades_paired_end {
     input = [ [ 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) ]
+                file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) ],
+              [],
+              []
+            ]
+
+    SPADES ( input, [] )
+}
+
+workflow test_spades_illumina_nanopore {
+    input = [ [ 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) ],
+              [],
+              [ file(params.test_data['sarscov2']['nanopore']['test_fastq_gz'], checkIfExists: true) ]
+            ]
+
+    SPADES ( input, [] )
+}
+
+// that isnt perfect, because CCS reads should rather be used with -s instead of --pacbio
+workflow test_spades_illumina_pacbio {
+    input = [ [ id:'test', single_end:false ], // meta map
+              [ file(params.test_data['homo_sapiens']['illumina']['test_1_fastq_gz'], checkIfExists: true),
+                file(params.test_data['homo_sapiens']['illumina']['test_2_fastq_gz'], checkIfExists: true) ],
+              [ file(params.test_data['homo_sapiens']['pacbio']['ccs_fq_gz'], checkIfExists: true) ],
+              []
             ]
 
     SPADES ( input, [] )

tests/modules/spades/test.yml

@@ -1,23 +1,52 @@
-- name: spades single end
+- name: spades test_spades_single_end
-  command: nextflow run ./tests/modules/spades -entry test_spades_single_end -c tests/config/nextflow.config
+  command: nextflow run tests/modules/spades -entry test_spades_single_end -c tests/config/nextflow.config
   tags:
     - spades
   files:
-    - path: output/spades/test.assembly.gfa
+    - path: output/spades/test.assembly.gfa.gz
-      md5sum: a995d1d413031534180d2b3b715fa921
+      md5sum: e5eab229363a906954a07df00e2495a6
-    - path: output/spades/test.contigs.fa
+    - path: output/spades/test.contigs.fa.gz
-      md5sum: 65ba6a517c152dbe219bf4b5b92bdad7
+      md5sum: 64f6b339872b934138c6efd6baa445f4
-    - path: output/spades/test.scaffolds.fa
+    - path: output/spades/test.scaffolds.fa.gz
-      md5sum: 65ba6a517c152dbe219bf4b5b92bdad7
+      md5sum: 64f6b339872b934138c6efd6baa445f4
     - path: output/spades/test.spades.log
 
-- name: spades paired end
+- name: spades test_spades_paired_end
-  command: nextflow run ./tests/modules/spades -entry test_spades_paired_end -c tests/config/nextflow.config
+  command: nextflow run tests/modules/spades -entry test_spades_paired_end -c tests/config/nextflow.config
   tags:
     - spades
   files:
-    - path: output/spades/test.assembly.gfa
+    - path: output/spades/test.assembly.gfa.gz
-      md5sum: bb053ef4e9250829c980ca17fbdbe3e9
+      md5sum: c8614fb69907ae832a1359a054af240f
-    - path: output/spades/test.contigs.fa
+    - path: output/spades/test.contigs.fa.gz
-      md5sum: 4476d409da70d9f7fc2aa8f25bbaf7fd
+      md5sum: eab5165b3cda96c235aaa1388010cb27
     - path: output/spades/test.spades.log
+    - path: output/spades/warnings.log
+
+- name: spades test_spades_illumina_nanopore
+  command: nextflow run tests/modules/spades -entry test_spades_illumina_nanopore -c tests/config/nextflow.config
+  tags:
+    - spades
+  files:
+    - path: output/spades/test.assembly.gfa.gz
+      md5sum: e438534f14e107f005efdd659adeba6a
+    - path: output/spades/test.contigs.fa.gz
+      md5sum: 027b0e54bfd8f4bc359e751e094133ef
+    - path: output/spades/test.scaffolds.fa.gz
+      md5sum: 027b0e54bfd8f4bc359e751e094133ef
+    - path: output/spades/test.spades.log
+    - path: output/spades/warnings.log
+
+- name: spades test_spades_illumina_pacbio
+  command: nextflow run tests/modules/spades -entry test_spades_illumina_pacbio -c tests/config/nextflow.config
+  tags:
+    - spades
+  files:
+    - path: output/spades/test.assembly.gfa.gz
+      md5sum: e12aaf83d8dbfc313339b7636ba43447
+    - path: output/spades/test.contigs.fa.gz
+      md5sum: 78523f66d34ac4d5a4890f353c1a6ec6
+    - path: output/spades/test.scaffolds.fa.gz
+      md5sum: 78523f66d34ac4d5a4890f353c1a6ec6
+    - path: output/spades/test.spades.log
+    - path: output/spades/warnings.log