fix: Illumina PE read headers for IRMA

CHANGELOG.md

@@ -3,6 +3,10 @@
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [[3.5.3](https://github.com/CFIA-NCFAD/nf-flu/releases/tag/3.5.3)] - 2024-11-01
+
+This patch release fixes an issue ([#22](https://github.com/peterk87/nf-flu/issues/22)) with Illumina paired-end read analysis by IRMA producing empty consensus sequences when the forward and reverse reads do not contain "1:N:0:." or "2:N:0:." in the FASTQ header lines.
+
 ## [[3.5.2](https://github.com/CFIA-NCFAD/nf-flu/releases/tag/3.5.2)] - 2024-10-18
 
 This patch release fixes a few issues when running the pipeline.

modules/local/cat_illumina_fastq.nf

@@ -59,34 +59,47 @@ process CAT_ILLUMINA_FASTQ {
       // append 1:N:0:. or 2:N:0:. to forward and reverse reads if "[12]:N:.*"
       // not present in the FASTQ header for compatability with IRMA assembly
 """
+function modify_fastq_header() {
+  local replacement="\$1"
+  awk -v repl="\$replacement" '
+    NR % 4 == 1 {
+        # Only process the first line of each 4-line block
+        if (\$0 ~ /^@/ && \$0 !~ /[12]:N:.*/) {
+            sub(/\\s*\$/, " " repl ":N:0:."); # Append " <replacement>:N:0:."
+        }
+    }
+    { print }
+  '
+}
+
 touch ${prefix}_1.merged.fastq.gz
 
 touch ${prefix}_2.merged.fastq.gz
 
 if [[ ${read1.size} > 0 ]]; then
   cat ${read1.join(' ')} \\
-  | perl -ne 'if (\$_ =~ /^@.* .*/ && !(\$_ =~ /^@.* [12]:N:.*/)){  chomp \$_; print "\$_ 1:N:0:.\n"; } else { print "\$_"; }' \\
+  | modify_fastq_header 1 \\
   | gzip -ck \\
   >> ${prefix}_1.merged.fastq.gz
 fi
 
 if [[ ${read1gz.size} > 0 ]]; then
   zcat ${read1gz.join(' ')} \\
-  | perl -ne 'if (\$_ =~ /^@.* .*/ && !(\$_ =~ /^@.* [12]:N:.*/)){  chomp \$_; print "\$_ 1:N:0:.\n"; } else { print "\$_"; }' \\
+  | modify_fastq_header 1 \\
   | gzip -ck \\
   >> ${prefix}_1.merged.fastq.gz
 fi
 
 if [[ ${read2.size} > 0 ]]; then
   cat ${read2.join(' ')} \\
-  | perl -ne 'if (\$_ =~ /^@.* .*/ && !(\$_ =~ /^@.* [12]:N:.*/)){  chomp \$_; print "\$_ 2:N:0:.\n"; } else { print "\$_"; }' \\
+  | modify_fastq_header 2 \\
   | gzip -ck \\
   >> ${prefix}_2.merged.fastq.gz
 fi
 
 if [[ ${read2gz.size} > 0 ]]; then
   zcat ${read2gz.join(' ')} \\
-  | perl -ne 'if (\$_ =~ /^@.* .*/ && !(\$_ =~ /^@.* [12]:N:.*/)){  chomp \$_; print "\$_ 2:N:0:.\n"; } else { print "\$_"; }' \\
+  | modify_fastq_header 2 \\
   | gzip -ck \\
   >> ${prefix}_2.merged.fastq.gz
 fi

nextflow.config

@@ -155,7 +155,7 @@ manifest {
   description     = 'Influenza A virus genome assembly pipeline'
   homePage        = 'https://github.com/CFIA-NCFAD/nf-flu'
   author          = 'Peter Kruczkiewicz, Hai Nguyen'
-  version         = '3.5.2'
+  version         = '3.5.3'
   nextflowVersion = '!>=22.10.1'
   mainScript      = 'main.nf'
   doi             = '10.5281/zenodo.13892044'