POC using module classes

.nf-core.yml

@@ -2,4 +2,5 @@ repository_type: pipeline
 nf_core_version: "2.14.1"
 lint:
   multiqc_config: False
-  files_exist: conf/igenomes.config
+  files_exist:
+    - conf/igenomes.config

README.md

@@ -54,24 +54,6 @@ Each row represents a set of sequences (in this case the seatoxin and toxin prot
 > [!NOTE]
 > The only required input is the id column and either fasta or structures.
 
-#### 2. TOOLSHEET
-
-Each line of the toolsheet defines a combination of guide tree and multiple sequence aligner to run with the respective arguments to be used.
-
-It should look at follows:
-
-`toolsheet.csv`:
-
-```csv
-tree,args_tree,aligner,args_aligner,
-FAMSA, -gt upgma -medoidtree, FAMSA,
-, ,TCOFFEE,
-FAMSA,,REGRESSIVE,
-```
-
-> [!NOTE]
-> The only required input is aligner.
-
 #### 3. RUN THE PIPELINE
 
 Now, you can run the pipeline using:
@@ -80,7 +62,6 @@ Now, you can run the pipeline using:
 nextflow run nf-core/multiplesequencealign \
    -profile test \
    --input samplesheet.csv \
-   --tools toolsheet.csv \
    --outdir outdir
 ```
 

assets/schema_evaluate.json

@@ -0,0 +1,67 @@
+{
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "$id": "https://raw.githubusercontent.com/nf-core/multiplesequencealign/master/assets/schema_evaluate.json",
+    "title": "nf-core/multiplesequencealign pipeline - schema for the evaluation workflow",
+    "description": "Schema for the evaluation workflow",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "id": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "Sample name must be provided and cannot contain spaces",
+                "meta": ["id"]
+            },
+            "alignment": {
+                "type": "string",
+                "description": "the alignment tool from params.alignment",
+                "meta": ["alignment"]
+            },
+            "alignment_args": {
+                "type": "string",
+                "description": "the alignment arguments from params.alignment_args",
+                "meta": ["alignment_args"]
+            },
+            "guidetree": {
+                "type": "string",
+                "description": "the guidetree tool from params.guidetree",
+                "meta": ["guidetree"]
+            },
+            "guidetree_args": {
+                "type": "string",
+                "description": "the guidetree arguments from params.guidetree_args",
+                "meta": ["guidetree_args"]
+            },
+            "treealign": {
+                "type": "string",
+                "description": "the treealign tool from params.treealign",
+                "meta": ["treealign"]
+            },
+            "treealign_args": {
+                "type": "string",
+                "description": "the treealign arguments from params.treealign_args",
+                "meta": ["treealign_args"]
+            },
+            "msa": {
+                "type": "string",
+                "format": "file-path",
+                "pattern": "^\\S+\\.aln(\\.gz)?$",
+                "description": "aln file containing the MSA",
+                "errorMessage": "Must end with .aln or .aln.gz",
+                "meta": ["msa"]
+            },
+            "reference": {
+                "type": "string",
+                "format": "file-path",
+                "meta": ["reference"]
+            },
+            "structures": {
+                "type": "string",
+                "format": "file-path",
+                "meta": ["structures"]
+            }
+        },
+        "anyOf": [{ "required": ["id", "msa"] }, { "required": ["id", "structures"] }]
+    }
+}

assets/schema_input.json

@@ -1,5 +1,5 @@
 {
-    "$schema": "http://json-schema.org/draft-07/schema",
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
     "$id": "https://raw.githubusercontent.com/nf-core/multiplesequencealign/master/assets/schema_input.json",
     "title": "nf-core/multiplesequencealign pipeline - params.input schema",
     "description": "Schema for the file provided with params.input",
@@ -15,20 +15,24 @@
             },
             "fasta": {
                 "type": "string",
+                "format": "file-path",
                 "pattern": "^\\S+\\.f(ast)?a$",
                 "errorMessage": "fasta file. Must end with .fa or .fasta"
             },
             "reference": {
-                "type": "string"
+                "type": "string",
+                "format": "file-path"
             },
-            "structures": {
-                "type": "string"
+            "dependencies": {
+                "type": "string",
+                "format": "file-path"
             },
             "template": {
-                "type": "string"
+                "type": "string",
+                "format": "file-path"
             }
         },
         "required": ["id"],
-        "anyOf": [{ "required": ["fasta"] }, { "required": ["structures"] }]
+        "anyOf": [{ "required": ["fasta"] }, { "required": ["dependencies"] }]
     }
 }

assets/schema_stats.json

@@ -0,0 +1,27 @@
+{
+    "$schema": "https://json-schema.org/draft/2020-12/schema",
+    "$id": "https://raw.githubusercontent.com/nf-core/multiplesequencealign/master/assets/schema_stats.json",
+    "title": "nf-core/multiplesequencealign pipeline - schema",
+    "description": "Schema for the stats file",
+    "type": "array",
+    "items": {
+        "type": "object",
+        "properties": {
+            "id": {
+                "type": "string",
+                "pattern": "^\\S+$",
+                "errorMessage": "Sample name must be provided and cannot contain spaces",
+                "meta": ["id"]
+            },
+            "stats": {
+                "type": "string",
+                "format": "file-path",
+                "pattern": "^\\S+\\.csv$",
+                "description": "dsv file containing the stats of the input sequences.",
+                "errorMessage": "Must end with .csv",
+                "meta": ["stats"]
+            }
+        },
+        "required": ["id", "stats"]
+    }
+}

conf/base.config

@@ -10,9 +10,9 @@
 
 process {
 
-    cpus   = { check_max( 1    * task.attempt, 'cpus'   ) }
-    memory = { check_max( 6.GB * task.attempt, 'memory' ) }
-    time   = { check_max( 4.h  * task.attempt, 'time'   ) }
+    cpus   = { 1    }
+    memory = { 6.GB }
+    time   = { 4.h  }
 
     errorStrategy = { task.exitStatus in ((130..145) + 104) ? 'retry' : 'finish' }
     maxRetries    = 1
@@ -25,30 +25,30 @@ process {
     //        adding in your local modules too.
     // See https://www.nextflow.io/docs/latest/config.html#config-process-selectors
     withLabel:process_single {
-        cpus   = { check_max( 1                  , 'cpus'    ) }
-        memory = { check_max( 6.GB * task.attempt, 'memory'  ) }
-        time   = { check_max( 4.h  * task.attempt, 'time'    ) }
+        cpus   = { 1    }
+        memory = { 6.GB }
+        time   = { 4.h  }
     }
     withLabel:process_low {
-        cpus   = { check_max( 2     * task.attempt, 'cpus'    ) }
-        memory = { check_max( 12.GB * task.attempt, 'memory'  ) }
-        time   = { check_max( 4.h   * task.attempt, 'time'    ) }
+        cpus   = { 2     }
+        memory = { 12.GB }
+        time   = { 4.h   }
     }
     withLabel:process_medium {
-        cpus   = { check_max( 6     * task.attempt, 'cpus'    ) }
-        memory = { check_max( 36.GB * task.attempt, 'memory'  ) }
-        time   = { check_max( 8.h   * task.attempt, 'time'    ) }
+        cpus   = { 6     }
+        memory = { 36.GB }
+        time   = { 8.h   }
     }
     withLabel:process_high {
-        cpus   = { check_max( 12    * task.attempt, 'cpus'    ) }
-        memory = { check_max( 72.GB * task.attempt, 'memory'  ) }
-        time   = { check_max( 16.h  * task.attempt, 'time'    ) }
+        cpus   = { 12    }
+        memory = { 72.GB }
+        time   = { 16.h  }
     }
     withLabel:process_long {
-        time   = { check_max( 20.h  * task.attempt, 'time'    ) }
+        time   = { 20.h }
     }
     withLabel:process_high_memory {
-        memory = { check_max( 200.GB * task.attempt, 'memory' ) }
+        memory = { 200.GB }
     }
     withLabel:error_ignore {
         errorStrategy = 'ignore'