Bump kallistobustools to 0.28.2 (nf-core#4981)

* bump version, add new options from 0.28.2 * waiting on conda * style * Update environment.yml * workflow mode is reqd * editing tests: the quantification logic has changed * fixing licenses * workflow should be specified explicitly * container fixed at bioconda * incorrectly recorded md5s * Added nf-tests for kallistobustools modules * Delete modules/nf-core/kallistobustools/ref/tests/nextflow.config * Added kallistobustools/ref tag to kallistobustools/count test * Don't include path lines in count test * Apply suggestions from code review Co-authored-by: Jasmin Frangenberg <73216762+jasmezz@users.noreply.github.com> --------- Co-authored-by: Carson J Miller <carsonjmiller@outlook.com> Co-authored-by: Carson J Miller <68351153+CarsonJM@users.noreply.github.com> Co-authored-by: Jasmin Frangenberg <73216762+jasmezz@users.noreply.github.com>
RSC-RP · Mar 20, 2024 · d695534 · d695534
1 parent 96b1e50
commit d695534
Show file tree

Hide file tree

Showing 20 changed files with 531 additions and 178 deletions.
diff --git a/modules/nf-core/kallistobustools/count/environment.yml b/modules/nf-core/kallistobustools/count/environment.yml
@@ -4,4 +4,4 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::kb-python=0.27.2
+  - bioconda::kb-python=0.28.2
diff --git a/modules/nf-core/kallistobustools/count/main.nf b/modules/nf-core/kallistobustools/count/main.nf
@@ -4,8 +4,8 @@ process KALLISTOBUSTOOLS_COUNT {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/kb-python:0.27.2--pyhdfd78af_0' :
-        'biocontainers/kb-python:0.27.2--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/kb-python:0.28.2--pyhdfd78af_2' :
+        'biocontainers/kb-python:0.28.2--pyhdfd78af_2' }"
 
     input:
     tuple val(meta), path(reads)
@@ -14,11 +14,12 @@ process KALLISTOBUSTOOLS_COUNT {
     path  t1c
     path  t2c
     val   technology
+    val   workflow_mode
 
     output:
-    tuple val(meta), path ("*.count"), emit: count
-    path "versions.yml"              , emit: versions
-    path "*.count/*/*.mtx"           , emit: matrix //Ensure that kallisto finished and produced outputs
+    tuple val(meta), path ("*.count")   , emit: count
+    path "versions.yml"                 , emit: versions
+    path "*.count/*/*.mtx"              , emit: matrix //Ensure that kallisto finished and produced outputs
 
     when:
     task.ext.when == null || task.ext.when
@@ -27,7 +28,7 @@ process KALLISTOBUSTOOLS_COUNT {
     def args    = task.ext.args ?: ''
     def prefix  = task.ext.prefix ?: "${meta.id}"
     def cdna    = t1c ? "-c1 $t1c" : ''
-    def introns = t2c ? "-c2 $t2c" : ''
+    def intron  = t2c ? "-c2 $t2c" : ''
     def memory  = task.memory.toGiga() - 1
     """
     kb \\
@@ -36,12 +37,25 @@ process KALLISTOBUSTOOLS_COUNT {
         -i $index \\
         -g $t2g \\
         $cdna \\
-        $introns \\
+        $intron \\
         -x $technology \\
+        --workflow $workflow_mode \\
         $args \\
         -o ${prefix}.count \\
-        ${reads.join( " " )} \\
-        -m ${memory}G
+        -m ${memory}G \\
+        ${reads.join( " " )}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        kallistobustools: \$(echo \$(kb --version 2>&1) | sed 's/^.*kb_python //;s/positional arguments.*\$//')
+    END_VERSIONS
+    """
+
+    stub:
+    def prefix  = task.ext.prefix ?: "${meta.id}"
+    """
+    mkdir -p ${prefix}.count/counts_unfiltered/
+    touch ${prefix}.count/counts_unfiltered/cells_x_genes.mtx
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":

diff --git a/modules/nf-core/kallistobustools/count/meta.yml b/modules/nf-core/kallistobustools/count/meta.yml
@@ -12,7 +12,7 @@ tools:
       homepage: https://www.kallistobus.tools/
       documentation: https://kb-python.readthedocs.io/en/latest/index.html
       tool_dev_url: https://github.com/pachterlab/kb_python
-      licence: MIT License
+      licence: ["MIT"]
 input:
   - meta:
       type: map
@@ -34,16 +34,16 @@ input:
       pattern: "*t2g.txt"
   - t1c:
       type: file
-      description: kb ref's c1 spliced_t2c file
+      description: kb ref's c1 cdna_t2c file
       pattern: "*.{cdna_t2c.txt}"
   - t2c:
       type: file
-      description: kb ref's c2 unspliced_t2c file
-      pattern: "*.{introns_t2c.txt}"
+      description: kb ref's c2 intron_t2c file
+      pattern: "*.{intron_t2c.txt}"
   - workflow_mode:
       type: string
-      description: String value defining workflow to use, can be one of "standard", "lamanno", "nucleus"
-      pattern: "{standard,lamanno,nucleus,kite}"
+      description: String value defining workflow to use, can be one of "standard", "nac", "lamanno" (obsolete)
+      pattern: "{standard,lamanno,nac}"
   - technology:
       type: string
       description: String value defining the sequencing technology used.

diff --git a/modules/nf-core/kallistobustools/count/tests/main.nf.test b/modules/nf-core/kallistobustools/count/tests/main.nf.test
@@ -0,0 +1,98 @@
+nextflow_process {
+
+    name "Test Process KALLISTOBUSTOOLS_COUNT"
+    script "../main.nf"
+    process "KALLISTOBUSTOOLS_COUNT"
+
+    tag "modules"
+    tag "modules_nfcore"
+    tag "kallistobustools"
+    tag "kallistobustools/count"
+    tag "kallistobustools/ref"
+
+    setup {
+        run("KALLISTOBUSTOOLS_REF") {
+            script "../../ref/main.nf"
+            process {
+                """
+                input[0] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.fasta', checkIfExists: true)
+                input[1] = file(params.modules_testdata_base_path + 'genomics/homo_sapiens/genome/genome.gtf', checkIfExists: true)
+                input[2] = "standard"
+                """
+            }
+        }
+    }
+
+    test("genome.fasta + genome.gtf + '10X3' + 'standard'") {
+
+        when {
+            process {
+                """
+                input[0] = Channel.of(
+                    [
+                        [id:'test'], // meta map
+                        [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc_cmo/fastqs/gex_1/subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R1_001.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc_cmo/fastqs/gex_1/subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R2_001.fastq.gz', checkIfExists: true)
+                        ]
+                    ]
+                )
+                input[1] = KALLISTOBUSTOOLS_REF.out.index
+                input[2] = KALLISTOBUSTOOLS_REF.out.t2g
+                input[3] = KALLISTOBUSTOOLS_REF.out.cdna_t2c.ifEmpty{ [] }   // when empty the module doesn't run unless something is passed.
+                input[4] = KALLISTOBUSTOOLS_REF.out.intron_t2c.ifEmpty{ [] } // when empty the module doesn't run unless something is passed.
+                input[5] = "10XV3"
+                input[6] = "standard"
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(
+                    process.out.versions,
+                    process.out.matrix,
+                    path(process.out.count.get(0).get(1)).list().findAll { file(it.toString()).name != "run_info.json" && file(it.toString()).name != "kb_info.json" },
+                    file(path(process.out.count.get(0).get(1)).list().find { file(it.toString()).name == "kb_info.json" }.toString()).readLines()[15..22],
+                    file(path(process.out.count.get(0).get(1)).list().find { file(it.toString()).name == "run_info.json" }.toString()).readLines()[0..9]
+                    ).match()
+                }
+            )
+        }
+    }
+
+    test("genome.fasta + genome.gtf + '10X3' + 'standard' - stub") {
+
+        options "-stub"
+
+        when {
+            process {
+                """
+                input[0] = Channel.of(
+                    [
+                        [id:'test'], // meta map
+                        [
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc_cmo/fastqs/gex_1/subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R1_001.fastq.gz', checkIfExists: true),
+                        file(params.modules_testdata_base_path + 'genomics/homo_sapiens/10xgenomics/cellranger/10k_pbmc_cmo/fastqs/gex_1/subsampled_SC3_v3_NextGem_DI_CellPlex_Human_PBMC_10K_1_gex_S2_L001_R2_001.fastq.gz', checkIfExists: true)
+                        ]
+                    ]
+                )
+                input[1] = KALLISTOBUSTOOLS_REF.out.index
+                input[2] = KALLISTOBUSTOOLS_REF.out.t2g
+                input[3] = KALLISTOBUSTOOLS_REF.out.cdna_t2c.ifEmpty{ [] }   // when empty the module doesn't run unless something is passed.
+                input[4] = KALLISTOBUSTOOLS_REF.out.intron_t2c.ifEmpty{ [] } // when empty the module doesn't run unless something is passed.
+                input[5] = "10XV3"
+                input[6] = "standard"
+                """
+            }
+        }
+
+        then {
+            assertAll(
+                { assert process.success },
+                { assert snapshot(process.out).match() }
+            )
+        }
+    }
+}
diff --git a/modules/nf-core/kallistobustools/count/tests/main.nf.test.snap b/modules/nf-core/kallistobustools/count/tests/main.nf.test.snap
diff --git a/modules/nf-core/kallistobustools/count/tests/nextflow.config b/modules/nf-core/kallistobustools/count/tests/nextflow.config
@@ -0,0 +1,5 @@
+process {
+    withName: KALLISTOBUSTOOLS_COUNT {
+        ext.args = '--cellranger -m 1'
+    }
+}
diff --git a/modules/nf-core/kallistobustools/count/tests/tags.yml b/modules/nf-core/kallistobustools/count/tests/tags.yml
@@ -0,0 +1,2 @@
+kallistobustools/count:
+  - "modules/nf-core/kallistobustools/count/**"
diff --git a/modules/nf-core/kallistobustools/ref/environment.yml b/modules/nf-core/kallistobustools/ref/environment.yml
@@ -4,5 +4,5 @@ channels:
   - bioconda
   - defaults
 dependencies:
-  - bioconda::kb-python=0.27.2
+  - bioconda::kb-python=0.28.2
   - conda-forge::requests>=2.23.0
diff --git a/modules/nf-core/kallistobustools/ref/main.nf b/modules/nf-core/kallistobustools/ref/main.nf
@@ -4,8 +4,8 @@ process KALLISTOBUSTOOLS_REF {
 
     conda "${moduleDir}/environment.yml"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/kb-python:0.27.2--pyhdfd78af_0' :
-        'biocontainers/kb-python:0.27.2--pyhdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/kb-python:0.28.2--pyhdfd78af_2' :
+        'biocontainers/kb-python:0.28.2--pyhdfd78af_2' }"
 
     input:
     path fasta
@@ -62,4 +62,32 @@ process KALLISTOBUSTOOLS_REF {
         END_VERSIONS
         """
     }
+
+    stub:
+    if (workflow_mode == "standard") {
+        """
+        touch kb_ref_out.idx \\
+        touch t2g.txt \\
+        touch cdna.fa
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            kallistobustools: \$(echo \$(kb --version 2>&1) | sed 's/^.*kb_python //;s/positional arguments.*\$//')
+        END_VERSIONS
+        """
+    } else {
+        """
+        touch kb_ref_out.idx \\
+        touch t2g.txt \\
+        touch cdna.fa
+        touch intron.fa \\
+        touch cdna_t2c.txt \\
+        touch intron_t2c.txt
+
+        cat <<-END_VERSIONS > versions.yml
+        "${task.process}":
+            kallistobustools: \$(echo \$(kb --version 2>&1) | sed 's/^.*kb_python //;s/positional arguments.*\$//')
+        END_VERSIONS
+        """
+    }
 }