Params linting

nf_core/lint.py

@@ -4,7 +4,7 @@
 Tests Nextflow-based pipelines to check that they adhere to
 the nf-core community guidelines.
 """
-
+import json
 import logging
 import io
 import os
@@ -171,7 +171,8 @@ def lint_pipeline(self, release_mode=False):
             'check_readme',
             'check_conda_env_yaml',
             'check_conda_dockerfile',
-            'check_pipeline_todos'
+            'check_pipeline_todos',
+            'check_params_json'
         ]
         if release_mode:
             self.release_mode = True
@@ -221,6 +222,7 @@ def check_files_exist(self):
             ['LICENSE', 'LICENSE.md', 'LICENCE', 'LICENCE.md'], # NB: British / American spelling
             'README.md',
             'CHANGELOG.md',
+            'parameters.settings.json',
             'docs/README.md',
             'docs/output.md',
             'docs/usage.md',
@@ -263,6 +265,7 @@ def pf(file_path):
             with open(os.path.join(self.path, 'environment.yml'), 'r') as fh:
                 self.conda_config = yaml.load(fh)
 
+
     def check_docker(self):
         """Checks that Dockerfile contains the string ``FROM``."""
         fn = os.path.join(self.path, "Dockerfile")
@@ -502,6 +505,7 @@ def check_ci_config(self):
                 elif minNextflowVersion != self.minNextflowVersion:
                     self.failed.append((5, "Minimum NF version differed from CI and what was set in the pipelines manifest: {}".format(fn)))
 
+
     def check_readme(self):
         """Checks the repository README file for errors.
 
@@ -785,6 +789,18 @@ def check_pipeline_todos(self):
                                 l = '{}..'.format(l[:50-len(fname)])
                             self.warned.append((10, "TODO string found in '{}': {}".format(fname,l)))
 
+
+    def check_params_json(self):
+        fn = os.path.join(self.path, 'parameters.settings.json')
+        with open(fn, 'r') as paramsfile:
+            try:
+                json.loads(paramsfile.read())
+            except(ValueError):
+                self.failed.append((11, "{} file not a valid JSON file.".format(fn)))
+
+
+        return
+
     def print_results(self):
         # Print results
         rl = "\n  Using --release mode linting tests" if self.release_mode else ''

nf_core/pipeline-template/{{cookiecutter.name_noslash}}/main.nf

@@ -10,48 +10,81 @@
 */
 
 
-def helpMessage() {
-    // TODO nf-core: Add to this help message with new command line parameters
+def readParamsFromJsonSettings() {
+    List paramsWithUsage
+    try {
+        paramsWithUsage = tryReadParamsFromJsonSettings()
+    } catch (Exception e) {
+        println "Could not read parameters settings from Json. $e"
+        paramsWithUsage = Collections.emptyMap()
+    }
+    return paramsWithUsage
+}
+
+def tryReadParamsFromJsonSettings() throws Exception {
+    def paramsContent = new File(config.params_description.path).text
+    def paramsWithUsage = new groovy.json.JsonSlurper().parseText(paramsContent)
+    return paramsWithUsage.get('parameters')
+}
+
+def formatParameterHelpData(param) {
+    result = [name: param.name, value: '', usage: param.usage]
+    // value descibes the expected input for the param
+    result.value = (param.type == boolean.toString()) ? '' : param.choices ?: param.type ?: ''
+    return result
+}
+
+String prettyFormatParamGroupWithPaddingAndIndent(List paramGroup, String groupName, Integer padding = 2, Integer indent = 4) {
+    def maxParamNameLength = paramGroup.collect { it.name.size() }.max()
+    def paramChoices = paramGroup.findAll { it.choices }.collect { it.choices }
+    def maxChoiceStringLength = paramChoices.collect { it.toString().size() }.max()
+    def maxTypeLength = paramGroup.collect { (it.type as String).size() }.max()
+
+    def paramsFormattedList = paramGroup.sort { it.name }.collect {
+        Map param ->
+            paramHelpData = formatParameterHelpData(param)
+            sprintf("%${indent}s%-${maxParamNameLength + padding}s%-${maxChoiceStringLength + padding}s %s\n", "", "--${paramHelpData.name}", "${paramHelpData.value}", "${paramHelpData.usage}")
+    }
+    return String.format("%s:\n%s", groupName.toUpperCase(), paramsFormattedList.join()).stripIndent()
+}
+
+String prettyFormatParamsWithPaddingAndIndent(List paramsWithUsage, Integer padding = 2, Integer indent = 4) {
+
+    def groupedParamsWithUsage = paramsWithUsage.groupBy { it.group }
+    def formattedParamsGroups = groupedParamsWithUsage.collect {
+        prettyFormatParamGroupWithPaddingAndIndent(it.value, it.key, padding, indent)
+    }
+    return formattedParamsGroups.join('\n')
+}
+
+
+def helpMessage(paramsWithUsage) {
+    // TODO nf-core: Add typical command for running your pipeline
     log.info nfcoreHeader()
-    log.info"""
+    def usageHelp = String.format("""\
 
     Usage:
 
     The typical command for running the pipeline is as follows:
 
     nextflow run {{ cookiecutter.name }} --reads '*_R{1,2}.fastq.gz' -profile docker
 
-    Mandatory arguments:
-      --reads                       Path to input data (must be surrounded with quotes)
-      -profile                      Configuration profile to use. Can use multiple (comma separated)
-                                    Available: conda, docker, singularity, awsbatch, test and more.
-
     Options:
-      --genome                      Name of iGenomes reference
-      --singleEnd                   Specifies that the input is single end reads
-
-    References                      If not specified in the configuration file or you wish to overwrite any of the references.
-      --fasta                       Path to Fasta reference
-
-    Other options:
-      --outdir                      The output directory where the results will be saved
-      --email                       Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits
-      --maxMultiqcEmailFileSize     Theshold size for MultiQC report to be attached in notification email. If file generated by pipeline exceeds the threshold, it will not be attached (Default: 25MB)
-      -name                         Name for the pipeline run. If not specified, Nextflow will automatically generate a random mnemonic.
 
-    AWSBatch options:
-      --awsqueue                    The AWSBatch JobQueue that needs to be set when running on AWSBatch
-      --awsregion                   The AWS Region for your AWS Batch job to run on
-    """.stripIndent()
+    %s
+    """.stripIndent(), prettyFormatParamsWithPaddingAndIndent(paramsWithUsage, 2, 4))
+    log.info usageHelp
 }
 
 /*
  * SET UP CONFIGURATION VARIABLES
  */
 
+def paramsWithUsage = readParamsFromJsonSettings()
+
 // Show help emssage
 if (params.help){
-    helpMessage()
+    helpMessage(paramsWithUsage)
     exit 0
 }
 

nf_core/pipeline-template/{{cookiecutter.name_noslash}}/nextflow.config

@@ -39,6 +39,11 @@ params {
 // Developmental code should specify :dev
 process.container = '{{ cookiecutter.name_docker }}:dev'
 
+// Specify params.settings.json settings
+params_description {
+       path = "$baseDir/parameters.settings.json"
+}
+
 // Load base.config by default for all pipelines
 includeConfig 'conf/base.config'
 

nf_core/pipeline-template/{{cookiecutter.name_noslash}}/parameters.settings.json

@@ -0,0 +1,117 @@
+{
+    "parameters": [
+        {
+            "name": "reads",
+            "label": "Input files",
+            "usage": "Specify the location of your input FastQ files.",
+            "group": "Main options",
+            "default_value": "'data/*{1,2}.fastq.gz'",
+            "render": "textfield",
+            "pattern": ".*\\*.*",
+            "type": "string"
+        },
+        {
+            "name": "genome",
+            "label": "Alignment reference iGenomes key",
+            "usage": "Ref. genome key for iGenomes",
+            "group": "Alignment",
+            "render": "drop-down",
+            "type": "string",
+            "choices": [
+                    "",
+                    "GRCh37",
+                    "GRCm38",
+                    "TAIR10",
+                    "EB2",
+                    "UMD3.1",
+                    "WBcel235",
+                    "CanFam3.1",
+                    "GRCz10",
+                    "BDGP6",
+                    "EquCab2",
+                    "EB1",
+                    "Galgal4",
+                    "Gm01",
+                    "Mmul_1",
+                    "IRGSP-1.0",
+                    "CHIMP2.1.4",
+                    "Rnor_6.0",
+                    "R64-1-1",
+                    "EF2",
+                    "Sbi1",
+                    "Sscrofa10.2",
+                    "AGPv3"
+            ],
+            "default_value": ""
+        },
+        {
+            "name": "singleEnd",
+            "label": "Single-end sequencing input",
+            "usage": "Use single-end sequencing inputs instead of paired-end.",
+            "group": "Main options",
+            "render": "check-box",
+            "default_value": false,
+            "type": "boolean"
+        },
+        {
+            "name": "fasta",
+            "label": "FASTA",
+            "usage": "Path to Fasta reference",
+            "group": "Alignment",
+            "render": "file",
+            "type": "string",
+            "pattern": ".*",
+            "default_value": ""
+        },
+        {
+            "name": "outdir",
+            "label": "Output directory",
+            "usage": "Set where to save the results from the pipeline",
+            "group": "Main options",
+            "default_value": "./results",
+            "render": "textfield",
+            "pattern": ".*",
+            "type": "string"
+        },
+        {
+            "name": "email",
+            "label": "Your email address",
+            "usage": "Your email address, required to receive completion notification.",
+            "group": "Pipeline defaults",
+            "render": "textfield",
+            "pattern": "^$|(^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\\.[a-zA-Z0-9-.]+$)",
+            "type": "string",
+            "default_value": ""
+        },
+        {
+            "name": "maxMultiqcEmailFileSize",
+            "label": "Maximum MultiQC email file size",
+            "usage": "Theshold size for MultiQC report to be attached in notification email. If file generated by pipeline exceeds the threshold, it will not be attached.",
+            "group": "Pipeline defaults",
+            "default_value": "25.MB",
+            "render": "textfield",
+            "pattern": "\\d+\\.[KMGT]?B",
+            "type": "string"
+        },
+        {
+            "name": "awsregion",
+            "label": "AWS Region",
+            "usage": "The AWS region to run your job in.",
+            "group": "AWS cloud usage",
+            "default_value": "eu-west-1",
+            "render": "textfield",
+            "pattern": ".*",
+            "type": "string"
+        },
+        {
+            "name": "awsqueue",
+            "label": "AWS job queue",
+            "usage": "The JobQueue that you intend to use on AWS Batch.",
+            "group": "AWS cloud usage",
+            "render": "textfield",
+            "pattern": ".*",
+            "type": "string",
+            "default_value": ""
+        }
+    ]
+}