Merge branch 'master' into gridss_envs

.github/workflows/lint.yml

@@ -83,7 +83,7 @@ jobs:
                 .replace('modules/nf-core/', '')
                 .split('/')
                 .slice(0, 2)
-                .filter(x => !x.startsWith('main.nf') && x !== 'tests' && x !== 'meta.yml' && x !== 'environment.yml')
+                .filter(x => !x.startsWith('main.nf') && x !== 'tests' && x !== 'templates' && x !== 'meta.yml' && x !== 'environment.yml' && !x.endsWith('.md'))
                 .join('/'))
               )
             ];

.github/workflows/pytest-workflow.yml

@@ -308,7 +308,7 @@ jobs:
 
       - name: Upload logs on failure
         if: failure()
-        uses: actions/upload-artifact@6f51ac03b9356f520e9adb1b1b7802705f340c2b # v4
+        uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4
         with:
           name: logs-${{ matrix.profile }}-${{ steps.parsed.outputs.result }}
           path: |

modules/nf-core/custom/filterdifferentialtable/main.nf

@@ -9,10 +9,8 @@ process CUSTOM_FILTERDIFFERENTIALTABLE {
 
     input:
     tuple val(meta), path(input_file)
-    val(logFC_column)
-    val(FC_threshold)
-    val(padj_column)
-    val(padj_threshold)
+    tuple val(logfc_column), val(fc_threshold), val(fc_cardinality)
+    tuple val(stat_column), val(stat_threshold), val(stat_cardinality)
 
     output:
     tuple val(meta), path("*_filtered.tsv"), emit: filtered
@@ -41,14 +39,27 @@ process CUSTOM_FILTERDIFFERENTIALTABLE {
     table = pd.read_csv("${input_file}", sep=sep)
 
     # Calculate log2 fold change threshold
-    logFC_threshold = log2(float("${FC_threshold}"))
+    logfc_threshold = log2(float("${fc_threshold}"))
+
+    # define evaluation
+    def evaluate_condition(x, threshold, cardinality):
+        if cardinality == ">=":
+            return x >= threshold
+        elif cardinality == "<=":
+            return x <= threshold
+        elif cardinality == ">":
+            return x > threshold
+        elif cardinality == "<":
+            return x < threshold
+        else:
+            raise ValueError(f"Invalid cardinality: {cardinality}")
 
     # Apply filters
     mask = (
-        table["${logFC_column}"].notna() &
-        table["${padj_column}"].notna() &
-        (table["${logFC_column}"].abs() >= logFC_threshold) &
-        (table["${padj_column}"] <= float("${padj_threshold}"))
+        table["${logfc_column}"].notna() &
+        table["${stat_column}"].notna() &
+        table["${logfc_column}"].abs().apply(lambda x: evaluate_condition(x, logfc_threshold, "${fc_cardinality}")) &
+        table["${stat_column}"].apply(lambda x: evaluate_condition(x, float("${stat_threshold}"), "${stat_cardinality}"))
     )
     filtered_table = table[mask]
 

modules/nf-core/custom/filterdifferentialtable/meta.yml

@@ -4,6 +4,7 @@ keywords:
   - filter
   - differential expression
   - logFC
+  - significance statistic
   - p-value
 tools:
   - "pandas":
@@ -26,18 +27,30 @@ input:
         type: file
         description: Input differential expression table (CSV, TSV, or TXT format)
         pattern: "*.{csv,tsv,txt}"
-  - - logFC_column:
+  - - logfc_column:
         type: string
         description: Name of the column containing log fold change values
-  - - FC_threshold:
+    - fc_threshold:
         type: float
         description: Fold change threshold for filtering
-  - - padj_column:
+    - fc_cardinality:
         type: string
-        description: Name of the column containing adjusted p-values
-  - - padj_threshold:
+        description: |
+          Operator to compare the fold change values with the threshold.
+          Valid values are: ">=", "<=", ">", "<".
+  - - stat_column:
+        type: string
+        description: |
+          Name of the column containing the significance statistic values
+          (eg. adjusted p-values).
+    - stat_threshold:
         type: float
-        description: Adjusted p-value threshold for filtering
+        description: Statistic threshold for filtering
+    - stat_cardinality:
+        type: string
+        description: |
+          Operator to compare the column values with the threshold.
+          Valid values are: ">=", "<=", ">", "<".
 output:
   - filtered:
       - meta:

modules/nf-core/custom/filterdifferentialtable/tests/main.nf.test

@@ -15,10 +15,8 @@ nextflow_process {
             process {
                 """
                 input[0] = [ [ id:'test' ], file(params.modules_testdata_base_path + "genomics/mus_musculus/rnaseq_expression/SRP254919.salmon.merged.deseq2.results.tsv", checkIfExists: true) ]
-                input[1] = 'log2FoldChange'
-                input[2] = 2
-                input[3] = 'padj'
-                input[4] = 0.05
+                input[1] = Channel.of(['log2FoldChange', 2, '>='])
+                input[2] = Channel.of(['padj', 0.05, '<='])
                 """
             }
         }

modules/nf-core/galah/environment.yml

@@ -2,4 +2,4 @@ channels:
   - conda-forge
   - bioconda
 dependencies:
-  - bioconda::galah=0.3.1
+  - bioconda::galah=0.4.2

modules/nf-core/galah/main.nf

@@ -4,38 +4,39 @@ process GALAH {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/galah%3A0.3.1--h031d066_3':
-        'biocontainers/galah:0.3.1--h031d066_3' }"
+        'https://depot.galaxyproject.org/singularity/galah:0.4.2--h7b50bb2_1':
+        'biocontainers/galah:0.4.2--h7b50bb2_1' }"
 
     input:
     tuple val(meta), path(bins), path(qc_table), val(qc_format)
 
     output:
-    tuple val(meta), path("*.tsv")                    , emit: tsv
-    tuple val(meta), path("${prefix}-dereplicated/*") , emit: dereplicated_bins
-    path "versions.yml"                               , emit: versions
+    tuple val(meta), path("*.tsv")      , emit: tsv
+    tuple val(meta), path("${prefix}/*"), emit: dereplicated_bins
+    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}"
-    def qc_args = (qc_format == "checkm") ? "--checkm-tab-table ${qc_table}" : "--genome-info ${qc_table}"
-    def qc_input = qc_table ? qc_args : ""
-    def valid_qc_format = qc_format in ["checkm", "genome_info"]
-    if( qc_table && !valid_qc_format ) {
-        error "Invalid qc_format supplied! qc_format should be either 'checkm' or 'genome_info'."
+    def qc_input = ""
+    if(qc_format == "checkm2") {
+        qc_input = "--checkm2-quality-report ${qc_table}"
+    } else if(qc_format == "checkm") {
+        qc_input = "--checkm-tab-table ${qc_table}"
+    } else if(qc_format == "genome-info") {
+        qc_input = "--genome-info ${qc_table}"
     }
     """
-    mkdir ${prefix}-dereplicated
-
     galah cluster \\
         --threads ${task.cpus} \\
         --genome-fasta-files ${bins} \\
         ${qc_input} \\
-        --output-cluster-definition ${prefix}-dereplicated_bins.tsv \\
-        --output-representative-fasta-directory ${prefix}-dereplicated
+        --output-cluster-definition ${prefix}.tsv \\
+        --output-representative-fasta-directory ${prefix} \\
+        ${args}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
@@ -44,12 +45,11 @@ process GALAH {
     """
 
     stub:
-    def args = task.ext.args ?: ''
     prefix = task.ext.prefix ?: "${meta.id}"
     """
-    mkdir ${prefix}-dereplicated/
-    touch ${prefix}-dereplicated/test.fa
-    touch ${prefix}-dereplicated_bins.tsv
+    mkdir ${prefix}/
+    touch ${prefix}/test.fa
+    touch ${prefix}.tsv
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

modules/nf-core/galah/meta.yml

@@ -29,17 +29,18 @@ input:
     - qc_table:
         type: file
         description: |
-          (optional) Either a (CheckM)[https://nf-co.re/modules/checkm_lineagewf] summary TSV containing
-          information on the completeness and contamination of the input genomes (13 columns),
-          or a 3-column csv with the header `genome,completeness,contamination`.
-          In both cases the first column should contain the names of the input genome files,
-          minus the last file extension
-          (i.e. if the genome is gzipped, the genome name should retain the .fasta extension).
+          (optional) A summary TSV from either CheckM [https://nf-co.re/modules/checkm_lineagewf],
+          CheckM2 [https://nf-co.re/modules/checkm2_predict/], or a CSV 
+          in drep-style format [https://github.com/MrOlm/drep] with three columnns,
+          `genome,completeness,contamination`. In both cases the first column should contain the 
+          names of the input genome files, minus the last file extension 
+          (i.e. if the genome is gzipped, the genome name should 
+          retain the .fasta extension).
         pattern: "*.{csv,tsv}"
     - qc_format:
         type: string
         description: Defines the type if input table in `qc_table`, if specified.
-        pattern: "checkm|genome_info"
+        pattern: "checkm|checkm2|genome_info"
 output:
   - tsv:
       - meta:
@@ -57,7 +58,7 @@ output:
           description: |
             Groovy Map containing sample information
             e.g. `[ id:'test', single_end:false ]`
-      - ${prefix}-dereplicated/*:
+      - ${prefix}/*:
           type: file
           description: The representative genomes following dereplication by galah.
           pattern: "*"

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

@@ -0,0 +1,133 @@
+nextflow_process {
+
+    name "Test Process GALAH"
+    script "../main.nf"
+    config "./nextflow.config"
+    process "GALAH"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "galah"
+    tag "checkm2/databasedownload"
+    tag "checkm2/predict"
+    tag "gawk"
+
+    test("genomes - no qc_table") {
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+                    [file("https://github.com/nf-core/test-datasets/raw/refs/heads/magmap/testdata/GCA_002688505.1_ASM268850v1_genomic.fna.gz", checkIfExists: true),
+                    file("https://github.com/nf-core/test-datasets/raw/refs/heads/magmap/testdata/GCF_004296495.1_ASM429649v1_genomic.fna.gz", checkIfExists: true)],
+                    [],
+                    []
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match()
+                }
+            )
+        }
+
+    }
+
+    test("genomes - checkm2 qc_table") {
+
+        setup {
+            run("CHECKM2_DATABASEDOWNLOAD") {
+                script "../../checkm2/databasedownload/main.nf"
+                process {
+                    """
+                    input[0] = "5571251"
+                    """
+                }
+            }
+
+            run("CHECKM2_PREDICT") {
+                script "../../checkm2/predict/main.nf"
+                process {
+                    """
+                    input[0] = [
+                        [ id:'test_checkm2' ], // meta map
+                        [file("https://github.com/nf-core/test-datasets/raw/refs/heads/magmap/testdata/GCA_002688505.1_ASM268850v1_genomic.fna.gz", checkIfExists: true),
+                        file("https://github.com/nf-core/test-datasets/raw/refs/heads/magmap/testdata/GCF_004296495.1_ASM429649v1_genomic.fna.gz", checkIfExists: true)]
+                    ]
+                    input[1] = CHECKM2_DATABASEDOWNLOAD.out.database
+                    """
+                }
+            }
+
+            run("GAWK") {
+                script "../../gawk/main.nf"
+                process {
+                    """
+                    input[0] = CHECKM2_PREDICT.out.checkm2_tsv
+                    input[1] = []
+                    """
+                }
+            }
+        }
+
+        when {
+            process {
+                """
+                ch_checkm_tsv = GAWK.out.output
+                    | map { meta, tsv -> [ [id: "test"], tsv ] }
+
+                input[0] = Channel.of([
+                    [ id:'test' ], // meta map
+                    [file("https://github.com/nf-core/test-datasets/raw/refs/heads/magmap/testdata/GCA_002688505.1_ASM268850v1_genomic.fna.gz", checkIfExists: true),
+                    file("https://github.com/nf-core/test-datasets/raw/refs/heads/magmap/testdata/GCF_004296495.1_ASM429649v1_genomic.fna.gz", checkIfExists: true)]
+                ])
+                .combine(ch_checkm_tsv, by: 0)
+                .map { meta, bins, tsv -> [ meta, bins, tsv, "checkm2" ] }
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match()
+                }
+            )
+        }
+
+    }
+
+    test("genomes - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = [
+                    [ id:'test' ], // meta map
+                    [file("https://github.com/nf-core/test-datasets/raw/refs/heads/magmap/testdata/GCA_002688505.1_ASM268850v1_genomic.fna.gz", checkIfExists: true),
+                    file("https://github.com/nf-core/test-datasets/raw/refs/heads/magmap/testdata/GCF_004296495.1_ASM429649v1_genomic.fna.gz", checkIfExists: true)],
+                    [],
+                    "checkm2"
+                    ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match()
+                }
+            )
+        }
+
+    }
+
+}