Adds fq/lint for early validation of FASTQs

CHANGELOG.md

@@ -15,6 +15,7 @@ Initial release of nf-core/seqinspector, created with the [nf-core](https://nf-c
 - [#50](https://github.com/nf-core/seqinspector/pull/50) Add an optional subsampling step.
 - [#51](https://github.com/nf-core/seqinspector/pull/51) Add nf-test to CI.
 - [#63](https://github.com/nf-core/seqinspector/pull/63) Contribution guidelines added about displaying results for new tools
+- [#67](https://github.com/nf-core/seqinspector/pull/67) Add FASTQ linting for early validation
 
 ### `Fixed`
 

CITATIONS.md

@@ -10,6 +10,8 @@
 
 ## Pipeline tools
 
+- [FQ](https://github.com/stjude-rust-labs/fq)
+
 - [FastQC](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/)
 
 > Andrews, S. (2010). FastQC: A Quality Control Tool for High Throughput Sequence Data [Online].

README.md

@@ -31,9 +31,10 @@
      workflows use the "tube map" design for that. See https://nf-co.re/docs/contributing/design_guidelines#examples for examples.   -->
 <!-- TODO nf-core: Fill in short bullet-pointed list of the default steps in the pipeline -->
 
+1. Lint FASTQs with ([`fq`](https://github.com/stjude-rust-labs/fq))
 1. Subsample reads ([`Seqtk`](https://github.com/lh3/seqtk))
-2. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
-3. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
+1. Read QC ([`FastQC`](https://www.bioinformatics.babraham.ac.uk/projects/fastqc/))
+1. Present QC for raw reads ([`MultiQC`](http://multiqc.info/))
 
 ## Usage
 

conf/modules.config

@@ -18,6 +18,15 @@ process {
         saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
     ]
 
+    withName: 'FQ_LINT' {
+        ext.args      = { params.fq_lint_args }
+        errorStrategy = {
+                            task.exitStatus in ((130..145) + 104) ? 'retry'  :
+                            params.continue_with_lint_fail        ? 'ignore' :
+                            'finish'
+                        }
+    }
+
     withName: SEQTK_SAMPLE {
         ext.args = '-s100'
     }

modules.json

@@ -10,6 +10,11 @@
                         "git_sha": "666652151335353eef2fcd58880bcef5bc2928e1",
                         "installed_by": ["modules"]
                     },
+                    "fq/lint": {
+                        "branch": "master",
+                        "git_sha": "a1abf90966a2a4016d3c3e41e228bfcbd4811ccc",
+                        "installed_by": ["modules"]
+                    },
                     "multiqc": {
                         "branch": "master",
                         "git_sha": "cf17ca47590cc578dfb47db1c2a44ef86f89976d",

nextflow.config

@@ -13,6 +13,13 @@ params {
     // Input options
     input                      = null
     sample_size                = 0
+
+    // Options
+    skip_linting               = false
+    fq_lint_args               = ""
+    continue_with_lint_fail    = false
+
+
     // References
     genome                     = null
     fasta                      = null

nextflow_schema.json

@@ -31,7 +31,6 @@
                 },
                 "outdir": {
                     "type": "string",
-                    "default": null,
                     "format": "directory-path",
                     "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
                     "fa_icon": "fas fa-folder-open"
@@ -50,6 +49,30 @@
                 }
             }
         },
+        "validation_options": {
+            "title": "Validation options",
+            "type": "object",
+            "description": "Options for validating and screening FASTQ files.",
+            "default": "",
+            "properties": {
+                "skip_linting": {
+                    "type": "boolean",
+                    "default": false,
+                    "description": "Whether to lint the FASTQs before performing QC on the sequences",
+                    "help_text": "FASTQ files will be linted with FQ early in the pipeline. If they fail validation, the pipeline will terminate preventing expensive quality control steps being performed on the other samples. If ignoring FQ is enabled, quality control will be performed on the remaining samples."
+                },
+                "fq_lint_args": {
+                    "type": "string",
+                    "description": "Arguments to pass to FQ lint",
+                    "help_text": "Arguments to pass to FQ lint. This can be used to disable overly strict linting. See https://github.com/stjude-rust-labs/fq?tab=readme-ov-file#lint for more information."
+                },
+                "continue_with_lint_fail": {
+                    "type": "boolean",
+                    "description": "Whether to continue with the pipeline if linting fails for a single sample.",
+                    "help_text": "If set to true, the pipeline will continue with the remaining samples if linting fails for a single sample. If set to false, the pipeline will terminate if linting fails for a single sample."
+                }
+            }
+        },
         "reference_genome_options": {
             "title": "Reference genome options",
             "type": "object",
@@ -233,6 +256,9 @@
         {
             "$ref": "#/$defs/input_output_options"
         },
+        {
+            "$ref": "#/$defs/validation_options"
+        },
         {
             "$ref": "#/$defs/reference_genome_options"
         },

tests/rnaseq.main.nf.test

@@ -0,0 +1,87 @@
+nextflow_pipeline {
+
+    name "Test Workflow main.nf on NovaSeq6000 data"
+    script "../main.nf"
+    tag "seqinspector"
+    tag "PIPELINE"
+
+    test("rnaseq data test fail linting") {
+
+        when {
+            config "./rnaseq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+            }
+        }
+
+        then {
+            assertAll(
+                // Linting should fail!
+                { assert workflow.failed }
+            )
+        }
+    }
+
+    test("rnaseq data test skip linting") {
+
+        when {
+            config "./rnaseq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                skip_linting = true
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success }
+            )
+        }
+    }
+
+    test("rnaseq data test ignore linting") {
+
+        when {
+            config "./rnaseq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                continue_with_lint_fail = true
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt")
+                    )
+                },
+            )
+        }
+    }
+
+    test("rnaseq data test add args to fq/lint") {
+
+        when {
+            config "./rnaseq.main.nf.test.config"
+            params {
+                outdir = "$outputDir"
+                fq_lint_args = "--disable-validator P001"
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert snapshot(
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_citations.txt"),
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_fastqc.txt"),
+                        path("$outputDir/multiqc/global_report/multiqc_data/multiqc_general_stats.txt")
+                    )
+                },
+            )
+        }
+    }
+}

tests/rnaseq.main.nf.test.config

@@ -0,0 +1,8 @@
+// Load the basic test config
+includeConfig 'nextflow.config'
+
+// Load the correct samplesheet for that test
+params {
+    input  = params.pipelines_testdata_base_path + '626c8fab639062eade4b10747e919341cbf9b41a/samplesheet/v3.10/samplesheet_test.csv'
+
+}