Merge pull request #93 from PixelgenTechnologies/improve-read-renaming

Improve read renaming

CHANGELOG.md

@@ -13,6 +13,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - [[PR #90](https://github.com/nf-core/pixelator/pull/90)] - The `graph` and `annotate` steps are now using `process_high` as their resource tags
 - [[PR #91](https://github.com/nf-core/pixelator/pull/91)] - Set `process_high` to use 64GB of RAM and `process_high_memory` to use 128GB of RAM
 - [[PR #92](https://github.com/nf-core/pixelator/pull/92)] - Minor touch-ups to the documentation
+- [[PR #93](https://github.com/nf-core/pixelator/pull/93)] - Merge RENAME_READS functionality into PIXELATOR_AMPLICON
 
 ### Software dependencies
 

conf/modules.config

@@ -46,13 +46,6 @@ process {
         publishDir = [ enabled: false ]
     }
 
-    withName: RENAME_READS {
-        publishDir = [
-            enabled: false,
-            path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" },
-        ]
-    }
-
 
     // use explicit (params.my_option instanceof Integer) checks to avoid issues with 0 evaluating false
     // since most pixelator flags do accept zero as a value

modules/local/pixelator/single-cell/amplicon/main.nf

@@ -26,7 +26,19 @@ process PIXELATOR_AMPLICON {
     def prefix = task.ext.prefix ?: "${meta.id}"
     def args = task.ext.args ?: ''
 
+    // Make list of old name and new name pairs to use for renaming in the bash while loop
+    def old_new_pairs = (reads instanceof Path || reads.size() == 1)
+        ? [[ reads, "${prefix}${getFileSuffix(reads)}" ]]
+        : reads.withIndex().collect { entry, index -> [ entry, "${prefix}_${index + 1}${getFileSuffix(entry)}" ] }
+
+    def rename_to = old_new_pairs*.join(' ').join(' ')
+    def renamed_reads = old_new_pairs.collect { old_name, new_name -> new_name }.join(' ')
+
     """
+    printf "%s %s\\n" $rename_to | while read old_name new_name; do
+        [ -f "\${new_name}" ] || ln -s \$old_name \$new_name
+    done
+
     pixelator \\
         --cores $task.cpus \\
         --log-file ${prefix}.pixelator-amplicon.log \\
@@ -35,11 +47,19 @@ process PIXELATOR_AMPLICON {
         amplicon \\
         --output . \\
         $args \\
-        ${reads}
+        ${renamed_reads}
 
     cat <<-END_VERSIONS > versions.yml
     "${task.process}":
         pixelator: \$(echo \$(pixelator --version 2>/dev/null) | sed 's/pixelator, version //g' )
     END_VERSIONS
     """
 }
+
+
+// for .gz files also include the second to last extension if it is present. E.g., .fasta.gz
+// Source: nf-core/modules/cat/cat
+def getFileSuffix(filename) {
+    def match = filename =~ /^.*?((\.\w{1,5})?(\.\w{1,5}\.gz$))/
+    return match ? match[0][1] : filename.substring(filename.lastIndexOf('.'))
+}

workflows/pixelator.nf

@@ -50,7 +50,6 @@ include { CAT_FASTQ }                   from '../modules/nf-core/cat/fastq/main'
 //
 // MODULE: Defined locally
 //
-include { RENAME_READS                  } from '../modules/local/rename_reads'
 include { PIXELATOR_COLLECT_METADATA    } from '../modules/local/pixelator/collect_metadata'
 include { PIXELATOR_AMPLICON            } from '../modules/local/pixelator/single-cell/amplicon/main'
 include { PIXELATOR_QC                  } from '../modules/local/pixelator/single-cell/qc/main'
@@ -126,18 +125,10 @@ workflow PIXELATOR {
 
     ch_versions = ch_versions.mix(CAT_FASTQ.out.versions.first())
 
-
-    //
-    // MODULE: Rename input reads to match the sample ids from the samplesheet
-    //
-    RENAME_READS ( ch_cat_fastq )
-    ch_renamed_reads = RENAME_READS.out.reads
-    ch_versions = ch_versions.mix(RENAME_READS.out.versions.first())
-
     //
     // MODULE: Run pixelator single-cell amplicon
     //
-    PIXELATOR_AMPLICON ( ch_renamed_reads )
+    PIXELATOR_AMPLICON ( ch_cat_fastq )
     ch_merged = PIXELATOR_AMPLICON.out.merged
     ch_versions = ch_versions.mix(PIXELATOR_AMPLICON.out.versions.first())