Merge branch 'master' into pl_gatk_vcf2table

modules/nf-core/mirtrace/qc/main.nf

@@ -8,7 +8,7 @@ process MIRTRACE_QC {
         'biocontainers/mirtrace:1.0.1--0' }"
 
     input:
-    tuple val(meta), path(reads)
+    tuple val(meta), path(reads), path(mirtrace_config)
     val(mirtrace_species)
 
     output:
@@ -25,14 +25,15 @@ process MIRTRACE_QC {
     script:
     def args = task.ext.args ?: ''
     def prefix = task.ext.prefix ?: "${meta.id}"
+    def mirtrace_mode = mirtrace_config ? "--config ${mirtrace_config}": "${reads}"
 
     """
     mirtrace qc  \\
         --species ${mirtrace_species} \\
         --write-fasta \\
         --output-dir . \\
         --force \\
-        ${reads}
+        ${mirtrace_mode}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/nf-core/mirtrace/qc/meta.yml

@@ -25,6 +25,9 @@ input:
       type: file
       description: microRNA sequencing data
       pattern: "*.{fastq,fastq.gz}"
+  - mirtrace_config:
+      type: file
+      description: (Optional) CSV with list of FASTQ files to process with one entry per row. No headers. Each row consists of the following columns "FASTQ file path, id, adapter, PHRED-ASCII-offset".
   - mirtrace_species:
       type: string
       description: Target species in microRNA sequencing data (miRbase encoding, e.g. “hsa” for Homo sapiens)

modules/nf-core/mirtrace/qc/tests/main.nf.test

@@ -18,7 +18,8 @@ nextflow_process {
                     [ id:'test', single_end:false ], // meta map
                     [
                         file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz', checkIfExists: true)
-                    ]
+                    ],
+                    []
                 ]
                 input[1] = "hsa"
                 """
@@ -61,7 +62,8 @@ nextflow_process {
                     [ id:'test', single_end:false ], // meta map
                     [
                         file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz', checkIfExists: true),
-                    ]
+                    ],
+                    []
                 ]
                 input[1] = "hsa"
                 """
@@ -77,4 +79,51 @@ nextflow_process {
 
     }
 
+    test("human - fastq - optional config") {
+
+        when {
+            process {
+                """
+                ch_reads = Channel.of([
+                    [ id:'test' ], // meta map
+                    [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/illumina/fastq/test_rnaseq_1.fastq.gz', checkIfExists: true)
+                    ]
+                ])
+
+                ch_mirtrace_config = Channel.of(
+                        "./test_rnaseq_1.fastq.gz,test_rnaseq_1,TGGAATTCTCGGGTGCCAAGG,33")
+                        .collectFile(name: "mirtrace_config.txt", newLine: true)
+
+                input[0] = ch_reads
+                        .combine(ch_mirtrace_config)
+
+                input[1] = "hsa"
+
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+
+                // Check HTML
+                { assert path(process.out.html.get(0).get(1)).text.contains("This file is part of miRTrace.")} ,
+
+                // Check JSON
+                { assert path(process.out.json.get(0).get(1)).json.results[0].stats.uniqueQCPassedSeqsCount == 912 },
+
+                // Check TSV
+                { assert snapshot(process.out.tsv).match("tsv_config") },
+
+                // Check FASTA files
+                { assert snapshot(process.out.rnatype_unknown_fa).match("rnatype_unknown_fa_config") },
+                { assert snapshot(process.out.all_fa).match("all_fa_config") },
+
+            )
+        }
+
+    }
+
 }

modules/nf-core/mirtrace/qc/tests/main.nf.test.snap

@@ -1,4 +1,21 @@
 {
+    "all_fa_config": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test_rnaseq_1.fasta:md5,125963c9ee39a49b3a680903e28e7c9d"
+                ]
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-10T18:35:10.022991825"
+    },
     "all_fa": {
         "content": [
             [
@@ -15,7 +32,7 @@
             "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-09-05T18:05:42.043272808"
+        "timestamp": "2024-09-10T18:33:02.971744888"
     },
     "versions": {
         "content": [
@@ -29,6 +46,31 @@
         },
         "timestamp": "2024-09-02T14:00:50.712738593"
     },
+    "tsv_config": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    [
+                        "mirtrace-stats-contamination_basic.tsv:md5,ac69ca6d2a709854f1048b635d06e927",
+                        "mirtrace-stats-contamination_detailed.tsv:md5,ef80997ac12662c64cbcf5fe9851e786",
+                        "mirtrace-stats-length.tsv:md5,630b3a845953321ae4cf2fc4a4943ab5",
+                        "mirtrace-stats-mirna-complexity.tsv:md5,ab2a7600a2daa5c1797eea13d0abc2f0",
+                        "mirtrace-stats-phred.tsv:md5,44eaeae26ec629e71fb31e56bfb5a548",
+                        "mirtrace-stats-qcstatus.tsv:md5,623cf3a0c5e363488966844feb0dd978",
+                        "mirtrace-stats-rnatype.tsv:md5,ed8d3a76247a1432a365def87c3f4c67"
+                    ]
+                ]
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-10T18:35:09.99291948"
+    },
     "tsv": {
         "content": [
             [
@@ -53,7 +95,24 @@
             "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-09-05T18:05:41.888457948"
+        "timestamp": "2024-09-10T18:33:02.856967195"
+    },
+    "rnatype_unknown_fa_config": {
+        "content": [
+            [
+                [
+                    {
+                        "id": "test"
+                    },
+                    "test_rnaseq_1.fasta:md5,125963c9ee39a49b3a680903e28e7c9d"
+                ]
+            ]
+        ],
+        "meta": {
+            "nf-test": "0.9.0",
+            "nextflow": "24.04.4"
+        },
+        "timestamp": "2024-09-10T18:35:10.010723637"
     },
     "human - fastq - stub": {
         "content": [
@@ -178,6 +237,6 @@
             "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-09-05T18:05:41.978281344"
+        "timestamp": "2024-09-10T18:33:02.917439516"
     }
 }

modules/nf-core/nextclade/datasetget/environment.yml

@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::nextclade=2.12.0
+  - bioconda::nextclade=3.8.2

modules/nf-core/nextclade/datasetget/main.nf

@@ -4,12 +4,11 @@ process NEXTCLADE_DATASETGET {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/nextclade:2.12.0--h9ee0642_0' :
-        'biocontainers/nextclade:2.12.0--h9ee0642_0' }"
+        'https://depot.galaxyproject.org/singularity/nextclade:3.8.2--h9ee0642_0' :
+        'biocontainers/nextclade:3.8.2--h9ee0642_0' }"
 
     input:
     val dataset
-    val reference
     val tag
 
     output:
@@ -22,15 +21,13 @@ process NEXTCLADE_DATASETGET {
     script:
     def args = task.ext.args ?: ''
     prefix = task.ext.prefix ?: "${dataset}"
-    def fasta = reference ? "--reference ${reference}" : ''
     def version = tag ? "--tag ${tag}" : ''
     """
     nextclade \\
         dataset \\
         get \\
         $args \\
         --name $dataset \\
-        $fasta \\
         $version \\
         --output-dir $prefix
 
@@ -39,4 +36,23 @@ process NEXTCLADE_DATASETGET {
         nextclade: \$(echo \$(nextclade --version 2>&1) | sed 's/^.*nextclade //; s/ .*\$//')
     END_VERSIONS
     """
+
+    stub:
+    prefix = task.ext.prefix ?: "${dataset}"
+    """
+    mkdir -p ${prefix}
+    touch ${prefix}/CHANGELOG.md
+    touch ${prefix}/README.md
+    touch ${prefix}/genome_annotation.gff3
+    touch ${prefix}/pathogen.json
+    touch ${prefix}/reference.fasta
+    touch ${prefix}/sequences.fasta
+    touch ${prefix}/tree.json
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        nextclade: \$(echo \$(nextclade --version 2>&1) | sed 's/^.*nextclade //; s/ .*\$//')
+    END_VERSIONS
+    """
+
 }

modules/nf-core/nextclade/datasetget/meta.yml

@@ -16,10 +16,6 @@ input:
       type: string
       description: Name of dataset to retrieve. A list of available datasets can be obtained using the nextclade dataset list command.
       pattern: ".+"
-  - reference:
-      type: string
-      description: Accession id to download dataset based on a particular reference sequence. A list of available datasets can be obtained using the nextclade dataset list command.
-      pattern: ".+"
   - tag:
       type: string
       description: Version tag of the dataset to download. A list of available datasets can be obtained using the nextclade dataset list command.
@@ -39,3 +35,5 @@ authors:
 maintainers:
   - "@antunderwood"
   - "@drpatelh"
+updated on 2024.08.27:
+  - "@nmshahir"

modules/nf-core/nextclade/datasetget/tests/main.nf.test

@@ -10,21 +10,40 @@ nextflow_process {
     tag "nextclade"
     tag "nextclade/datasetget"
 
-    test("species-id-time") {
-
+    test("species-tag") {
+
+        when {
+            process {
+                """
+                input[0] = 'nextstrain/sars-cov-2/wuhan-hu-1/orfs'
+				input[1] = '2024-01-16--20-31-02Z'
+
+                """
+            }
+        }
+
+        then {
+            assert process.success
+            assert snapshot(process.out).match()
+        }
+
+    }
+
+    test("species-tag-stub") {
+        options '-stub'
+
         when {
             process {
                 """
-                input[0] = 'sars-cov-2'
-				input[1] = 'MN908947'
-				input[2] = '2022-01-18T12:00:00Z'
+                input[0] = 'nextstrain/sars-cov-2/wuhan-hu-1/orfs'
+				input[1] = '2024-01-16--20-31-02Z'
 
                 """
             }
         }
 
         then {
-            assertAll(
+            assertAll (
                 { assert process.success },
                 { assert snapshot(process.out).match() }
             )

modules/nf-core/nextclade/datasetget/tests/main.nf.test.snap

@@ -1,43 +1,41 @@
 {
-    "test-nextclade-datasetget": {
+    "species-tag": {
         "content": [
             {
                 "0": [
                     [
-                        "genemap.gff:md5,21ebebfd0f416eeb959e55ebffd808e8",
-                        "primers.csv:md5,5990c3483bf66ce607aeb90a44e7ef2e",
-                        "qc.json:md5,c512f51fda0212b21ffff05779180963",
+                        "CHANGELOG.md:md5,ebbe8be5a3c378ed903c1afb4d8c441d",
+                        "README.md:md5,c69387d632361334f0d7c9b66065f947",
+                        "genome_annotation.gff3:md5,4dff84d2d6ada820e0e3a8bc6798d402",
+                        "pathogen.json:md5,db5bbec52359c1e168ffc5e6dc0ea32a",
                         "reference.fasta:md5,c7ce05f28e4ec0322c96f24e064ef55c",
-                        "sequences.fasta:md5,41129d255b99e0e92bdf20e866b99a1b",
-                        "tag.json:md5,402ac2b87e2a6a64a3fbf5ad16497af3",
-                        "tree.json:md5,b8f32f547ff9e2131d6fc66b68fc54b1",
-                        "virus_properties.json:md5,5f2de3949e07cb633f3d9e4a7654dc81"
+                        "sequences.fasta:md5,c2a4d6cbb837dce22d81f9c36dd0629e",
+                        "tree.json:md5,e180607cd34a6cb6bab101d295f6cedf"
                     ]
                 ],
                 "1": [
-                    "versions.yml:md5,12e8751f1d841b9aee87d31206c102a7"
+                    "versions.yml:md5,8c64a653330d1c5cb58ee1b8363b22d3"
                 ],
                 "dataset": [
                     [
-                        "genemap.gff:md5,21ebebfd0f416eeb959e55ebffd808e8",
-                        "primers.csv:md5,5990c3483bf66ce607aeb90a44e7ef2e",
-                        "qc.json:md5,c512f51fda0212b21ffff05779180963",
+                        "CHANGELOG.md:md5,ebbe8be5a3c378ed903c1afb4d8c441d",
+                        "README.md:md5,c69387d632361334f0d7c9b66065f947",
+                        "genome_annotation.gff3:md5,4dff84d2d6ada820e0e3a8bc6798d402",
+                        "pathogen.json:md5,db5bbec52359c1e168ffc5e6dc0ea32a",
                         "reference.fasta:md5,c7ce05f28e4ec0322c96f24e064ef55c",
-                        "sequences.fasta:md5,41129d255b99e0e92bdf20e866b99a1b",
-                        "tag.json:md5,402ac2b87e2a6a64a3fbf5ad16497af3",
-                        "tree.json:md5,b8f32f547ff9e2131d6fc66b68fc54b1",
-                        "virus_properties.json:md5,5f2de3949e07cb633f3d9e4a7654dc81"
+                        "sequences.fasta:md5,c2a4d6cbb837dce22d81f9c36dd0629e",
+                        "tree.json:md5,e180607cd34a6cb6bab101d295f6cedf"
                     ]
                 ],
                 "versions": [
-                    "versions.yml:md5,12e8751f1d841b9aee87d31206c102a7"
+                    "versions.yml:md5,8c64a653330d1c5cb58ee1b8363b22d3"
                 ]
             }
         ],
         "meta": {
-            "nf-test": "0.8.4",
+            "nf-test": "0.9.0",
             "nextflow": "24.04.4"
         },
-        "timestamp": "2024-08-23T11:33:31.41372"
+        "timestamp": "2024-08-27T19:55:42.211731791"
     }
 }

modules/nf-core/nextclade/run/environment.yml

@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::nextclade=2.12.0
+  - bioconda::nextclade=3.8.2