Merge branch 'dev' of https://github.com/nf-core/scrnaseq into 420-do…

…cument-cellbender-properly
nf-core · Jan 20, 2025 · 0316a79 · 0316a79
2 parents 8a263f5 + dd6c49d
commit 0316a79
Show file tree

Hide file tree

Showing 6 changed files with 35 additions and 16 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Update cellbender module to latest nf-core version ([#419](https://github.com/nf-core/scrnaseq/pull/419/))
 - Add profile for gpu processes ([#419](https://github.com/nf-core/scrnaseq/pull/419/))
 - Update example usage command in README with valid reference genome parameter ([#339](https://github.com/nf-core/scrnaseq/issues/339))
+- Removed `--kb_filter` parameter. Kallisto filtering is triggered by default and can be turned off with `ext.args` ([#421](https://github.com/nf-core/scrnaseq/issues/421))
 - Document better that `cellbender` is used for empty drops calling and not the `emptydrops` method (([#420](https://github.com/nf-core/scrnaseq/issues/420)))
 
 ## v3.0.0 - 2024-12-09

diff --git a/conf/modules.config b/conf/modules.config
@@ -203,13 +203,12 @@ if (params.aligner == 'kallisto') {
             ]
         }
         withName: KALLISTOBUSTOOLS_COUNT {
-            def kb_filter = (params.kb_filter) ? '--filter' : ''
             publishDir = [
                 path: { "${params.outdir}/${params.aligner}" },
                 mode: params.publish_dir_mode,
                 saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
             ]
-            ext.args = "--workflow ${params.kb_workflow} ${kb_filter}"
+            ext.args = "--workflow ${params.kb_workflow} --filter"
         }
     }
 }

diff --git a/nextflow.config b/nextflow.config
@@ -33,7 +33,6 @@ params {
     kb_workflow       = "standard"
     kb_t1c            = null
     kb_t2c            = null
-    kb_filter         = false
 
     // STARsolo parameters
     star_index          = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -251,11 +251,6 @@
                     "description": "Type of workflow. Use `nac` for an index type that can quantify nascent and mature RNA. Use `lamanno` for RNA velocity based on La Manno et al. 2018 logic. (default: standard)",
                     "fa_icon": "fas fa-rainbow",
                     "enum": ["standard", "lamanno", "nac"]
-                },
-                "kb_filter": {
-                    "type": "boolean",
-                    "fa_icon": "fas fa-fish",
-                    "description": "Activate Kallisto/BUStools filtering algorithm"
                 }
             }
         },

diff --git a/tests/main_pipeline_kallisto.nf.test b/tests/main_pipeline_kallisto.nf.test
@@ -25,22 +25,24 @@ nextflow_pipeline {
                 {assert workflow.success},
 
                 // How many tasks were executed?
-                {assert workflow.trace.tasks().size() == 13},
+                {assert workflow.trace.tasks().size() == 19},
 
                 // How many results were produced?
                 {assert path("${outputDir}/results_kallisto").list().size() == 4},
                 {assert path("${outputDir}/results_kallisto/kallisto").list().size() == 3},
-                {assert path("${outputDir}/results_kallisto/kallisto/mtx_conversions").list().size() == 5},
-                {assert path("${outputDir}/results_kallisto/kallisto/Sample_X.count").list().size() == 9},
-                {assert path("${outputDir}/results_kallisto/kallisto/Sample_Y.count").list().size() == 9},
+                {assert path("${outputDir}/results_kallisto/kallisto/mtx_conversions").list().size() == 8},
+                {assert path("${outputDir}/results_kallisto/kallisto/Sample_X.count").list().size() == 12},
+                {assert path("${outputDir}/results_kallisto/kallisto/Sample_Y.count").list().size() == 12},
                 {assert path("${outputDir}/results_kallisto/fastqc").list().size() == 12},
                 {assert path("${outputDir}/results_kallisto/multiqc").list().size() == 3},
 
                 //
                 // Check if files were produced
                 //
                 {assert new File( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_X/Sample_X_raw_matrix.h5ad" ).exists()},
+                {assert new File( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_X/Sample_X_filtered_matrix.h5ad" ).exists()},
                 {assert new File( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_Y/Sample_Y_raw_matrix.h5ad" ).exists()},
+                {assert new File( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_Y/Sample_Y_filtered_matrix.h5ad" ).exists()},
 
                 //
                 // Check if files are the same
@@ -49,13 +51,26 @@ nextflow_pipeline {
                     path( "${outputDir}/results_kallisto/kallisto/Sample_X.count/counts_unfiltered/cells_x_genes.barcodes.txt" ),
                     path( "${outputDir}/results_kallisto/kallisto/Sample_X.count/counts_unfiltered/cells_x_genes.genes.txt"    ),
                     path( "${outputDir}/results_kallisto/kallisto/Sample_X.count/counts_unfiltered/cells_x_genes.mtx"          ),
+                    path( "${outputDir}/results_kallisto/kallisto/Sample_X.count/counts_filtered/cells_x_genes.barcodes.txt" ),
+                    path( "${outputDir}/results_kallisto/kallisto/Sample_X.count/counts_filtered/cells_x_genes.genes.txt"    ),
+                    path( "${outputDir}/results_kallisto/kallisto/Sample_X.count/counts_filtered/cells_x_genes.mtx"          ),
+
                     path( "${outputDir}/results_kallisto/kallisto/Sample_Y.count/counts_unfiltered/cells_x_genes.barcodes.txt" ),
                     path( "${outputDir}/results_kallisto/kallisto/Sample_Y.count/counts_unfiltered/cells_x_genes.genes.txt"    ),
                     path( "${outputDir}/results_kallisto/kallisto/Sample_Y.count/counts_unfiltered/cells_x_genes.mtx"          ),
+                    path( "${outputDir}/results_kallisto/kallisto/Sample_Y.count/counts_filtered/cells_x_genes.barcodes.txt" ),
+                    path( "${outputDir}/results_kallisto/kallisto/Sample_Y.count/counts_filtered/cells_x_genes.genes.txt"    ),
+                    path( "${outputDir}/results_kallisto/kallisto/Sample_Y.count/counts_filtered/cells_x_genes.mtx"          ),
+
                     path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_X/Sample_X_raw_matrix.seurat.rds"     ),
                     path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_X/Sample_X_raw_matrix.sce.rds"        ),
+                    path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_X/Sample_X_filtered_matrix.seurat.rds"     ),
+                    path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_X/Sample_X_filtered_matrix.sce.rds"        ),
+
                     path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_Y/Sample_Y_raw_matrix.seurat.rds"     ),
-                    path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_Y/Sample_Y_raw_matrix.sce.rds"        )
+                    path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_Y/Sample_Y_raw_matrix.sce.rds"        ),
+                    path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_Y/Sample_Y_filtered_matrix.seurat.rds"     ),
+                    path( "${outputDir}/results_kallisto/kallisto/mtx_conversions/Sample_Y/Sample_Y_filtered_matrix.sce.rds"        )
                 ).match()}
 
             ) // end of assertAll()

diff --git a/tests/main_pipeline_kallisto.nf.test.snap b/tests/main_pipeline_kallisto.nf.test.snap
@@ -4,18 +4,28 @@
             "cells_x_genes.barcodes.txt:md5,72d78bb1c1ee7cb174520b30f695aa48",
             "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6",
             "cells_x_genes.mtx:md5,894d60da192e3788de11fa8fc1fa711d",
+            "cells_x_genes.barcodes.txt:md5,9e456448a0d4da992d4ca89987c1feba",
+            "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6",
+            "cells_x_genes.mtx:md5,6cf18c72ed8d4f96e4f01d2bf637f962",
             "cells_x_genes.barcodes.txt:md5,a8cf7ea4b2d075296a94bf066a64b7a4",
             "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6",
             "cells_x_genes.mtx:md5,abd83de117204d0a77df3c92d00cc025",
+            "cells_x_genes.barcodes.txt:md5,32464c83608493daf0a22dc39ede6bc8",
+            "cells_x_genes.genes.txt:md5,acd9d00120f52031974b2add3e7521b6",
+            "cells_x_genes.mtx:md5,fb032cbac4888032c81ed79a740fa181",
             "Sample_X_raw_matrix.seurat.rds:md5,6dba7ab652441df6a2b0712c7529053b",
             "Sample_X_raw_matrix.sce.rds:md5,3fef29fea599561551a06caa82811e2b",
+            "Sample_X_filtered_matrix.seurat.rds:md5,a25a8c6d0b26facffaae352c2f2742fc",
+            "Sample_X_filtered_matrix.sce.rds:md5,554e1376664bbff371cb09c39a969d06",
             "Sample_Y_raw_matrix.seurat.rds:md5,a9e9ac3d1bf83f4e791d6f0c3f6540de",
-            "Sample_Y_raw_matrix.sce.rds:md5,6818392c6b8b65d762521406aa963b2a"
+            "Sample_Y_raw_matrix.sce.rds:md5,6818392c6b8b65d762521406aa963b2a",
+            "Sample_Y_filtered_matrix.seurat.rds:md5,f872ac3625f2b2f1fca77a5b736cc18f",
+            "Sample_Y_filtered_matrix.sce.rds:md5,e93e974427f87e8774636c64d33d628e"
         ],
         "meta": {
             "nf-test": "0.9.0",
-            "nextflow": "24.10.2"
+            "nextflow": "24.10.1"
         },
-        "timestamp": "2024-11-29T09:54:53.033167911"
+        "timestamp": "2025-01-17T10:13:54.332011219"
     }
 }