addess commenets

nf-core · Feb 11, 2025 · ef240e2 · ef240e2
1 parent a8fb237
commit ef240e2
Show file tree

Hide file tree

Showing 4 changed files with 47 additions and 37 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -15,6 +15,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Update documents related to `simpleaf`, `alevin`, `salmon`, and `alevin-fry` for consistency.
 - Rename the default aligner from `alevin` to `simpleaf` for consistency.
 - Update the `mtx_to_h5ad` template for `simpleaf` to start from the h5ad file generated by simpleaf.
+- Upgrade alevinqc from 1.12.1 to 1.18.0 to match the latest output file structure of simpleaf.
 
 ## v3.0.0 - 2024-12-09
 

diff --git a/conf/modules.config b/conf/modules.config
@@ -127,7 +127,7 @@ if(params.aligner == "cellrangerarc") {
     }
 }
 
-if (params.aligner == "simpleaf" || params.aligner == "alevin") {
+if ( params.aligner == "simpleaf" ) {
     process {
         withName: 'SIMPLEAF_INDEX' {
             publishDir = [

diff --git a/subworkflows/local/simpleaf.nf b/subworkflows/local/simpleaf.nf
@@ -3,7 +3,7 @@ include { ALEVINQC              } from '../../modules/local/alevinqc'
 include { SIMPLEAF_INDEX        } from '../../modules/nf-core/simpleaf/index'
 include { SIMPLEAF_QUANT        } from '../../modules/nf-core/simpleaf/quant'
 
-workflow SCRNASEQ_SIMPLEAF {
+workflow SIMPLEAF {
 
     take:
     ch_genome_fasta // channel
@@ -21,38 +21,48 @@ workflow SCRNASEQ_SIMPLEAF {
     ch_versions = Channel.empty()
 
     /*
-    * Build simpleaf index
+    * Build simpleaf index if needed
+    * If simpleaf_index is provided, we skip this step
+    * If map_dir is provided, we skip this step
+    * Otherwise, we build the index
     */
-    if ( !simpleaf_index || !map_dir ) {
-        // define input channels for index building
-        // we can either use a genome fasta and gtf file pair or a transcript fasta file
-        if ( transcript_fasta ) {
-            ch_genome_fasta_gtf = [ [:],[],[] ] // meta, genome fasta, genome gtf
-            ch_transcript_fasta = [ [id: "${transcript_fasta.getName()}"], transcript_fasta ] // meta, transcript fasta
-        } else {
-            ch_genome_fasta_gtf = ch_genome_fasta.combine( ch_genome_gtf ).map{ fasta, gtf -> [[id: "${fasta.getName()}"], fasta, gtf] }
-            ch_transcript_fasta = [ [:], [] ] // meta, transcript fasta
-        }
+    if ( !simpleaf_index ) {
+        if ( !map_dir ) {
+            // We do not have a simpleaf index or a map dir, so we need to build the index
+
+            // define input channels for index building
+            // we can either use a genome fasta and gtf file pair or a transcript fasta file
+            if ( transcript_fasta ) {
+                ch_genome_fasta_gtf = [ [:],[],[] ] // meta, genome fasta, genome gtf
+                ch_transcript_fasta = [ [id: "${transcript_fasta.getName()}"], transcript_fasta ] // meta, transcript fasta
+            } else {
+                ch_genome_fasta_gtf = ch_genome_fasta.combine( ch_genome_gtf ).map{ fasta, gtf -> [[id: "${fasta.getName()}"], fasta, gtf] }
+                ch_transcript_fasta = [ [:], [] ] // meta, transcript fasta
+            }
 
-        SIMPLEAF_INDEX(
-            ch_genome_fasta_gtf,
-            ch_transcript_fasta,
-            [[:], []], // meta, probe CSV
-            [[:], []] // meta, feature CSV
-        )
-        // Channel of tuple(meta, index dir)
-        simpleaf_index = SIMPLEAF_INDEX.out.index.collect()
-        // Channel of t2g path or empty
-        t2g = SIMPLEAF_INDEX.out.t2g.collect().map { _meta, it -> it }
-        ch_versions = ch_versions.mix( SIMPLEAF_INDEX.out.versions )
+            SIMPLEAF_INDEX(
+                ch_genome_fasta_gtf,
+                ch_transcript_fasta,
+                [[:], []], // meta, probe CSV
+                [[:], []] // meta, feature CSV
+            )
+            // Channel of tuple(meta, index dir)
+            simpleaf_index = SIMPLEAF_INDEX.out.index.collect()
+            // Channel of version
+            ch_versions = ch_versions.mix( SIMPLEAF_INDEX.out.versions )
 
-        // ensure txp2gene is a Channel
-        if (!txp2gene) {
-            txp2gene = t2g
+            // ensure txp2gene is a Channel
+            if (!txp2gene) {
+                txp2gene = SIMPLEAF_INDEX.out.t2g.collect().map { _meta, it -> it }
+            } else {
+                txp2gene = Channel.of( txp2gene )
+            }
         } else {
-            txp2gene = Channel.of( txp2gene )
+            // we have a map dir, so we do not need to build the index
+            simpleaf_index = Channel.of( [ [:], [] ] )
         }
     } else {
+        // we have a simpleaf index, we use it directly
         // ensure simpleaf index and txp2gene are Channels
         simpleaf_index = Channel.of( [ [ id: simpleaf_index.getName() ], simpleaf_index ] )
     }

diff --git a/workflows/scrnaseq.nf b/workflows/scrnaseq.nf
@@ -11,7 +11,7 @@ include { methodsDescriptionText                            } from '../subworkfl
 include { getGenomeAttribute                                } from '../subworkflows/local/utils_nfcore_scrnaseq_pipeline'
 include { FASTQC_CHECK                                      } from '../subworkflows/local/fastqc'
 include { KALLISTO_BUSTOOLS                                 } from '../subworkflows/local/kallisto_bustools'
-include { SCRNASEQ_SIMPLEAF                                 } from '../subworkflows/local/simpleaf'
+include { SIMPLEAF                                          } from '../subworkflows/local/simpleaf'
 include { STARSOLO                                          } from '../subworkflows/local/starsolo'
 include { CELLRANGER_ALIGN                                  } from "../subworkflows/local/align_cellranger"
 include { CELLRANGER_MULTI_ALIGN                            } from "../subworkflows/local/align_cellrangermulti"
@@ -134,9 +134,9 @@ workflow SCRNASEQ {
     }
 
     // Run simpleaf pipeline
-    if (params.aligner == "simpleaf" || params.aligner == "alevin") {
+    if ( params.aligner == "simpleaf" ) {
 
-        SCRNASEQ_SIMPLEAF(
+        SIMPLEAF(
             ch_genome_fasta,
             ch_filter_gtf,
             ch_transcript_fasta,
@@ -148,10 +148,10 @@ workflow SCRNASEQ {
             ch_fastq,
             [] // for existing map dir; not applicable
         )
-        ch_versions = ch_versions.mix(SCRNASEQ_SIMPLEAF.out.ch_versions)
-        ch_multiqc_files = ch_multiqc_files.mix(SCRNASEQ_SIMPLEAF.out.quant.map{ meta, it -> it })
+        ch_versions = ch_versions.mix(SIMPLEAF.out.ch_versions)
+        ch_multiqc_files = ch_multiqc_files.mix(SIMPLEAF.out.quant.map{ meta, it -> it })
         ch_mtx_matrices = ch_mtx_matrices.mix(
-            SCRNASEQ_SIMPLEAF.out.quant.map{
+            SIMPLEAF.out.quant.map{
                 meta, files -> [
                     meta +
                     [input_type: meta["filtered"] ? "filtered" : "raw" ],
@@ -160,7 +160,7 @@ workflow SCRNASEQ {
             }
         )
 
-        ch_txp2gene = SCRNASEQ_SIMPLEAF.out.txp2gene
+        ch_txp2gene = SIMPLEAF.out.txp2gene
     }
 
     // Run STARSolo pipeline
@@ -299,11 +299,10 @@ workflow SCRNASEQ {
         H5AD_REMOVEBACKGROUND_BARCODES_CELLBENDER_ANNDATA (
             ch_h5ads
                 .filter { meta, mtx_files -> meta.input_type == 'raw' }
-                .map { meta, mtx_files -> [ meta + [input_type: 'filtered'], mtx_files ]} // to avoid name collision
+                .map { meta, mtx_files -> [ meta + [input_type: 'cellbender_filter'], mtx_files ]} // to avoid name collision
         )
         ch_h5ads = ch_h5ads.mix(
             H5AD_REMOVEBACKGROUND_BARCODES_CELLBENDER_ANNDATA.out.h5ad
-                .map{ meta, file -> [ meta + [input_type: 'cellbender_filter'], file ]}
         )
     }