test: Add testing CI and mention paper (#40)

* docs: Add new citation

* chore: Remove unnecessary todo

* test: Add local test cases for subwfs

* ci: Add unit test workflow

* ci: Remove tap

* ci: Fix regex

.github/workflows/test.yml

@@ -0,0 +1,42 @@
+name: nf-test CI
+# This workflow runs the nf-test test suite
+on:
+  pull_request:
+  release:
+    types: [published]
+
+env:
+  NXF_ANSI_LOG: false
+
+jobs:
+  test:
+    name: Run ${{ matrix.profile }} pipeline test
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        NXF_VER:
+          - "latest-stable"
+        profile: ["docker"] # TODO , "singularity", "conda"]
+    steps:
+      - name: Check out pipeline code
+        uses: actions/checkout@v2
+
+      - uses: actions/cache@v2
+        with:
+          path: /usr/local/bin/nextflow
+          key: ${{ runner.os }}
+          restore-keys: |
+            ${{ runner.os }}-nextflow-
+
+      - name: Install Nextflow
+        uses: nf-core/setup-nextflow@v1
+        with:
+          version: "${{ matrix.NXF_VER }}"
+
+      - name: Install nf-test
+        run: |
+          wget -qO- https://code.askimed.com/install/nf-test | bash
+          sudo mv nf-test /usr/local/bin/
+
+      - name: Run nf-test
+        run: nf-test test --profile=${{ matrix.profile }} tests/*nf.test

.gitignore

@@ -8,3 +8,8 @@ testing/
 testing*
 *.pyc
 test_data/kraken_viral_db/
+.nf-test
+nf-test
+.nf-test.log
+test.nf
+site

CITATIONS.md

@@ -1,5 +1,9 @@
 # dalmolingroup/euryale: Citations
 
+## [EURYALE](https://ieeexplore.ieee.org/document/10702116)
+
+> J. V. F. Cavalcante, I. Dantas de Souza, D. A. A. Morais and R. J. S. Dalmolin, "EURYALE: A versatile Nextflow pipeline for taxonomic classification and functional annotation of metagenomics data," 2024 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Natal, Brazil, 2024, pp. 1-7, doi: 10.1109/CIBCB58642.2024.10702116.
+
 ## [nf-core](https://pubmed.ncbi.nlm.nih.gov/32055031/)
 
 > Ewels PA, Peltzer A, Fillinger S, Patel H, Alneberg J, Wilm A, Garcia MU, Di Tommaso P, Nahnsen S. The nf-core framework for community-curated bioinformatics pipelines. Nat Biotechnol. 2020 Mar;38(3):276-278. doi: 10.1038/s41587-020-0439-x. PubMed PMID: 32055031.

README.md

@@ -149,10 +149,9 @@ We thank the following people for their extensive assistance in the development
 
 ## Citations
 
-> Morais DAA, Cavalcante JVF, Monteiro SS, Pasquali MAB and Dalmolin RJS (2022)
-> MEDUSA: A Pipeline for Sensitive Taxonomic Classification and Flexible Functional Annotation
-> of Metagenomic Shotgun Sequences.
-> Front. Genet. 13:814437. doi: 10.3389/fgene.2022.814437
+> J. V. F. Cavalcante, I. Dantas de Souza, D. A. A. Morais and R. J. S. Dalmolin, "EURYALE: A versatile Nextflow pipeline for taxonomic classification and functional annotation of metagenomics data,"
+> 2024 IEEE Conference on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), Natal, Brazil, 2024, pp. 1-7,
+> doi: 10.1109/CIBCB58642.2024.10702116.
 
 This pipeline uses code and infrastructure developed and maintained by the [nf-core](https://nf-co.re) community, reused here under the [MIT license](https://github.com/nf-core/tools/blob/master/LICENSE).
 

lib/WorkflowMain.groovy

@@ -9,9 +9,8 @@ class WorkflowMain {
     //
     public static String citation(workflow) {
         return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" +
-            // TODO nf-core: Add Zenodo DOI for pipeline after first release
-            //"* The pipeline\n" +
-            //"  https://doi.org/10.5281/zenodo.XXXXXXX\n\n" +
+            "* The pipeline\n" +
+            "  https://doi.org/10.1109/CIBCB58642.2024.10702116\n\n" +
             "* The nf-core framework\n" +
             "  https://doi.org/10.1038/s41587-020-0439-x\n\n" +
             "* Software dependencies\n" +

nextflow.config

@@ -9,7 +9,6 @@
 // Global default params, used in configs
 params {
 
-    // TODO nf-core: Specify your pipeline's command line flags
     // Input options
     input                      = null
 

nf-test.config

@@ -0,0 +1,5 @@
+config {
+    testsDir "tests"
+    workDir ".nf-test"
+    profile "test,docker"
+}

tests/alignment.nf.test

@@ -0,0 +1,57 @@
+nextflow_workflow {
+
+    name "Test ALIGNMENT workflow"
+    script "subworkflows/local/alignment.nf"
+    workflow "ALIGNMENT"
+    tag "ALIGNMENT"
+    tag "subworkflows"
+
+    test("Should run alignment with DIAMOND_MAKEDB and DIAMOND_BLASTX") {
+
+        when {
+            workflow {
+                """
+                input[0] = [[id:'MEGAHIT-test_minigut'], "$baseDir/test_data/MEGAHIT-test_minigut.contigs.fa.gz"]
+                input[1] = Channel.fromPath("$baseDir/test_data/protein.faa.gz")
+                input[2] = []
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert workflow.trace.succeeded().size() == 2 },
+                { assert workflow.out.alignments },
+                { assert workflow.out.multiqc_files },
+                { assert workflow.out.versions },
+                { assert path(workflow.out.alignments[0][1]).exists() },
+            )
+
+        }
+    }
+
+    test("Should run alignment with pre-built DIAMOND database") {
+
+        when {
+            workflow {
+                """
+                input[0] = [[id:'minigut'], '$baseDir/test_data/MEGAHIT-test_minigut.contigs.fa.gz']
+                input[1] = Channel.fromPath("$baseDir/test_data/protein.faa.gz")
+                input[2] = Channel.fromPath("$baseDir/test_data/protein.faa.gz.dmnd")
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert workflow.trace.succeeded().size() == 1 },
+                { assert workflow.out.alignments },
+                { assert workflow.out.multiqc_files },
+                { assert workflow.out.versions },
+                { assert path(workflow.out.alignments[0][1]).exists() },
+            )
+        }
+    }
+}

tests/functional.nf.test

@@ -0,0 +1,54 @@
+nextflow_workflow {
+
+    name "Test FUNCTIONAL workflow"
+    script "subworkflows/local/functional.nf"
+    workflow "FUNCTIONAL"
+    tag "FUNCTIONAL"
+    tag "subworkflows"
+
+    test("Should run functional annotation workflow") {
+
+        when {
+            workflow {
+                """
+                input[0] = [
+                    [ id:'test_sample' ],
+                    file("$baseDir/test_data/test_minigut_sample2.txt.gz")
+                ]
+                input[1] = file("$baseDir/test_data/idmapping_selected.tab.example.gz")
+                """
+            }
+            params {
+                minimum_bitscore = 50
+                minimum_pident = 90
+                minimum_alen = 100
+                maximum_evalue = 1e-5
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert workflow.out.annotated },
+            )
+
+            // Check GUNZIP output
+            with(workflow.out.annotated) {
+                assert size() == 1
+                with(get(0)) {
+                    assert get(0).id == "test_sample"
+                }
+            }
+
+            // Check ANNOTATE output
+            with(workflow.out.annotated) {
+                assert size() == 1
+                with(get(0)) {
+                    assert get(0).id == "test_sample"
+                    assert get(1).readLines().size() > 0
+                    // You might want to add more specific checks on the content of the annotated file
+                }
+            }
+        }
+    }
+}

tests/nextflow.config

@@ -0,0 +1,38 @@
+/*
+========================================================================================
+    Nextflow config file for running tests
+========================================================================================
+*/
+
+params {
+    // Limit resources so that this can run on GitHub Actions
+    cpus   = 2
+    memory = 4.GB
+    time   = 4.h
+}
+
+process {
+    withLabel:process_single {
+        cpus   =  1
+        memory = 6.GB
+        time   = 4.h
+    }
+    withLabel:process_low {
+        cpus   =  2
+        memory = 4.GB
+        time   = 4.h
+    }
+    withLabel:process_medium {
+        cpus   =  2
+        memory = 4.GB
+        time   = 4.h
+    }
+    withLabel:process_high {
+        cpus   =  2
+        memory = 4.GB
+        time   = 4.h
+    }
+    withLabel:process_high_memory {
+        memory = 4.GB
+    }
+}

tests/preprocess.nf.test

@@ -0,0 +1,60 @@
+nextflow_workflow {
+
+    name "Test PREPROCESS workflow"
+    script "subworkflows/local/preprocess.nf"
+    workflow "PREPROCESS"
+    tag "PREPROCESS"
+    tag "subworkflows"
+
+    test("Should run preprocessing with paired-end reads") {
+
+        when {
+            workflow {
+                """
+                input[0] = [
+                    [ id:'test_sample', single_end:false ], // meta map
+                    [
+                        "https://raw.githubusercontent.com/nf-core/test-datasets/mag/test_data/test_minigut_R1.fastq.gz",
+                        "https://raw.githubusercontent.com/nf-core/test-datasets/mag/test_data/test_minigut_R2.fastq.gz"
+                    ]
+                ]
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert workflow.out.reads },
+                { assert workflow.out.merged_reads },
+                { assert workflow.out.multiqc_files },
+                { assert workflow.out.versions }
+            )
+
+            // Check FASTP output
+            with(workflow.out.reads) {
+                assert size() == 1
+                with(get(0)) {
+                    assert get(0).id == "test_sample"
+                    assert get(0).single_end == false
+                    assert get(1).size() == 2  // Two fastq files for paired-end
+                }
+            }
+
+            // Check merged reads
+            with(workflow.out.merged_reads) {
+                assert size() == 1
+                with(get(0)) {
+                    assert get(0).id == "test_sample"
+                    assert get(0).single_end == true
+                }
+            }
+
+            // Check versions
+            with(workflow.out.versions) {
+                assert size() == 3
+                assert path(get(0)).text.contains("FASTP")
+            }
+        }
+    }
+}

tests/taxonomy.nf.test

@@ -0,0 +1,47 @@
+nextflow_workflow {
+
+    name "Test TAXONOMY workflow"
+    script "subworkflows/local/taxonomy.nf"
+    workflow "TAXONOMY"
+    tag "TAXONOMY"
+    tag "subworkflows"
+
+    test("Should run taxonomy workflow with Kraken2") {
+
+        when {
+            workflow {
+                """
+                input[0] = [
+                    [ id:'test_sample', single_end:false ], // meta map
+                    [
+                        "https://raw.githubusercontent.com/nf-core/test-datasets/mag/test_data/test_minigut_R1.fastq.gz",
+                        "https://raw.githubusercontent.com/nf-core/test-datasets/mag/test_data/test_minigut_R2.fastq.gz"
+                    ]
+
+                ]
+                input[1] = []
+                input[2] = file("$baseDir/test_data/testdb-kraken2")
+                """
+            }
+            params {
+                run_kaiju = false
+                run_kraken2 = true
+                skip_microview = true
+            }
+        }
+
+        then {
+            assertAll(
+                { assert workflow.success },
+                { assert workflow.out.tax_report },
+                { assert workflow.out.krona_report },
+                { assert workflow.out.versions }
+            )
+
+            // Check Krona output
+            with(workflow.out.krona_report) {
+                assert size() == 1
+            }
+        }
+    }
+}