Remove reference to max_* params and fix input schema

jfy133 · jfy133 · commit 43b00a68402b · 2024-10-17T15:46:20.000+02:00
diff --git a/assets/schema_input.json b/assets/schema_input.json
@@ -21,7 +21,7 @@
                 "errorMessage": "Column 'run' contains an empty field. Either remove column 'run' or fill each field with a value."
             },
             "group": {
-                "type": "string",
+                "type": ["string", "integer"],
                 "pattern": "^\\S+$",
                 "meta": ["group"],
                 "errorMessage": "Column 'group' contains an empty field. Either remove column 'group' or fill each field with a value."
@@ -38,18 +38,21 @@
                 "format": "file-path",
                 "exists": true,
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "dependentRequired": ["short_reads_1"],
                 "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             },
             "long_reads": {
                 "type": "string",
                 "format": "file-path",
                 "exists": true,
                 "pattern": "^\\S+\\.f(ast)?q\\.gz$",
-                "dependentRequired": ["short_reads_1", "short_reads_2"],
                 "errorMessage": "FastQ file for long reads cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'"
             }
         },
         "required": ["sample", "short_reads_1"]
+    },
+    "uniqueEntries": ["sample", "run"],
+    "dependentRequired": {
+        "short_reads_2": ["short_reads_1"],
+        "long_reads": ["short_reads_1", "short_reads_2"]
     }
 }
diff --git a/conf/test_adapterremoval.config b/conf/test_adapterremoval.config
@@ -10,14 +10,18 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    config_profile_name        = 'Test profile for running with AdapterRemoval and domain classification'
-    config_profile_description = 'Minimal test dataset to check pipeline function with AdapterRemoval data and domain classification.'
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
+params {
+    config_profile_name         = 'Test profile for running with AdapterRemoval and domain classification'
+    config_profile_description  = 'Minimal test dataset to check pipeline function with AdapterRemoval data and domain classification.'
 
     // Input data
     input                       = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.euk.csv'
diff --git a/conf/test_ancient_dna.config b/conf/test_ancient_dna.config
@@ -10,14 +10,19 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    config_profile_name        = 'Ancient DNA test profile '
-    config_profile_description = 'Minimal test dataset to check pipeline function for ancient DNA step'
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
+
+params {
+    config_profile_name                  = 'Ancient DNA test profile '
+    config_profile_description           = 'Minimal test dataset to check pipeline function for ancient DNA step'
 
     // Input data
     input                                = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
diff --git a/conf/test_bbnorm.config b/conf/test_bbnorm.config
@@ -10,32 +10,36 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test dataset to check pipeline function'
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
+params {
+    config_profile_name         = 'Test profile'
+    config_profile_description  = 'Minimal test dataset to check pipeline function'
 
     // Input data
-    input                         = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
-    keep_phix                     = true
-    skip_clipping                 = true
-    skip_prokka                   = true
-    skip_prodigal                 = true
-    skip_quast                    = true
-    skip_binning                  = true
-    centrifuge_db                 = params.pipelines_testdata_base_path + 'mag/test_data/minigut_cf.tar.gz'
-    kraken2_db                    = params.pipelines_testdata_base_path + 'mag/test_data/minigut_kraken.tgz'
-    skip_krona                    = true
-    min_length_unbinned_contigs   = 1
-    max_unbinned_contigs          = 2
-    busco_db                      = "https://busco-data.ezlab.org/v5/data/lineages/bacteria_odb10.2024-01-08.tar.gz"
-    busco_clean                   = true
-    skip_gtdbtk                   = true
-    gtdbtk_min_completeness       = 0
-    bbnorm                        = true
-    coassemble_group              = true
+    input                       = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
+    keep_phix                   = true
+    skip_clipping               = true
+    skip_prokka                 = true
+    skip_prodigal               = true
+    skip_quast                  = true
+    skip_binning                = true
+    centrifuge_db               = params.pipelines_testdata_base_path + 'mag/test_data/minigut_cf.tar.gz'
+    kraken2_db                  = params.pipelines_testdata_base_path + 'mag/test_data/minigut_kraken.tgz'
+    skip_krona                  = true
+    min_length_unbinned_contigs = 1
+    max_unbinned_contigs        = 2
+    busco_db                    = "https://busco-data.ezlab.org/v5/data/lineages/bacteria_odb10.2024-01-08.tar.gz"
+    busco_clean                 = true
+    skip_gtdbtk                 = true
+    gtdbtk_min_completeness     = 0
+    bbnorm                      = true
+    coassemble_group            = true
 }
diff --git a/conf/test_binrefinement.config b/conf/test_binrefinement.config
@@ -10,14 +10,18 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test dataset to check pipeline function'
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
+params {
+    config_profile_name           = 'Test profile'
+    config_profile_description    = 'Minimal test dataset to check pipeline function'
 
     // Input data
     input                         = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
diff --git a/conf/test_busco_auto.config b/conf/test_busco_auto.config
@@ -10,14 +10,18 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test dataset to check pipeline function'
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
+params {
+    config_profile_name         = 'Test profile'
+    config_profile_description  = 'Minimal test dataset to check pipeline function'
 
     // Input data
     input                       = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
diff --git a/conf/test_concoct.config b/conf/test_concoct.config
@@ -11,33 +11,37 @@
 ----------------------------------------------------------------------------------------
 */
 
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
 params {
     config_profile_name        = 'Test CONCOCT profile'
     config_profile_description = 'Minimal test dataset to check pipeline function'
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
-
     // Input data
-    input                         = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
-    centrifuge_db                 = null
-    kraken2_db                    = null
-    skip_krona                    = true
-    skip_clipping                 = true
-    skip_adapter_trimming         = false
-    skip_spades                   = true
-    skip_spadeshybrid             = true
-    skip_megahit                  = false
-    skip_quast                    = true
-    skip_prodigal                 = true
-    skip_binning                  = false
-    skip_metabat2                 = false
-    skip_maxbin2                  = true
-    skip_concoct                  = false
-    skip_prokka                   = true
-    skip_binqc                    = true
-    skip_gtdbtk                   = true
-    gtdbtk_min_completeness       = 0
+    input                      = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.csv'
+    centrifuge_db              = null
+    kraken2_db                 = null
+    skip_krona                 = true
+    skip_clipping              = true
+    skip_adapter_trimming      = false
+    skip_spades                = true
+    skip_spadeshybrid          = true
+    skip_megahit               = false
+    skip_quast                 = true
+    skip_prodigal              = true
+    skip_binning               = false
+    skip_metabat2              = false
+    skip_maxbin2               = true
+    skip_concoct               = false
+    skip_prokka                = true
+    skip_binqc                 = true
+    skip_gtdbtk                = true
+    gtdbtk_min_completeness    = 0
 }
diff --git a/conf/test_host_rm.config b/conf/test_host_rm.config
@@ -10,14 +10,18 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test dataset to check pipeline function'
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
+params {
+    config_profile_name         = 'Test profile'
+    config_profile_description  = 'Minimal test dataset to check pipeline function'
 
     // Input data
     host_fasta                  = params.pipelines_testdata_base_path + 'mag/host_reference/genome.hg38.chr21_10000bp_region.fa'
diff --git a/conf/test_hybrid.config b/conf/test_hybrid.config
@@ -10,14 +10,18 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test dataset to check pipeline function'
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
+params {
+    config_profile_name         = 'Test profile'
+    config_profile_description  = 'Minimal test dataset to check pipeline function'
 
     // Input data
     input                       = params.pipelines_testdata_base_path + 'mag/samplesheets/samplesheet.hybrid.csv'
diff --git a/conf/test_hybrid_host_rm.config b/conf/test_hybrid_host_rm.config
@@ -10,14 +10,18 @@
 ----------------------------------------------------------------------------------------
 */
 
-params {
-    config_profile_name        = 'Test profile'
-    config_profile_description = 'Minimal test dataset to check pipeline function'
+// Limit resources so that this can run on GitHub Actions
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
 
-    // Limit resources so that this can run on GitHub Actions
-    max_cpus   = 2
-    max_memory = '6.GB'
-    max_time   = '6.h'
+params {
+    config_profile_name         = 'Test profile'
+    config_profile_description  = 'Minimal test dataset to check pipeline function'
 
     // Input data
     host_fasta                  = params.pipelines_testdata_base_path + 'mag/host_reference/genome.hg38.chr21_10000bp_region.fa'
diff --git a/conf/test_nothing.config b/conf/test_nothing.config
diff --git a/conf/test_single_end.config b/conf/test_single_end.config
diff --git a/conf/test_virus_identification.config b/conf/test_virus_identification.config
diff --git a/subworkflows/local/utils_nfcore_mag_pipeline/main.nf b/subworkflows/local/utils_nfcore_mag_pipeline/main.nf
