feat: add FluMut

CHANGELOG.md

@@ -3,6 +3,14 @@
 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).
 
+## [[3.6.0](https://github.com/CFIA-NCFAD/nf-flu/releases/tag/3.6.0)] - 2024-12-02
+
+This minor release adds [FluMut](https://github.com/izsvenezie-virology/FluMut) to "to search for molecular markers with potential impact on the biological characteristics of Influenza A viruses of the A(H5N1) subtype."
+
+### Changes
+
+* **feat**: Added FluMut (v0.6.3)
+
 ## [[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.

conf/modules.config

@@ -44,6 +44,16 @@ process {
   withName: 'BLAST_BLASTN.*' {
     ext.args = '-outfmt "6 qaccver saccver pident length mismatch gapopen qstart qend sstart send evalue bitscore qlen slen qcovs stitle" -num_alignments 1000000 -evalue 1e-6'
   }
+  withName: '.*FLUMUT.*' {
+    ext.args = ''
+    publishDir = [
+      [
+        path: { "${params.outdir}/flumut" },
+        saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        mode: params.publish_dir_mode
+      ]
+    ]
+  }
   withName: 'IRMA' {
     publishDir = [
       [

docs/output.md

@@ -15,6 +15,7 @@ The directories listed below will be created in the results directory after the
 - [Variant Calling](#variant-calling)
 - [H/N Subtyping](#hn-subtyping)
 - [Annotation](#annotation)
+- [FluMut](#flumut)
 
 ### IRMA
 
@@ -263,6 +264,19 @@ Consensus sequences are annotated using [VADR][]. The output files are available
 
 </details>
 
+### FluMut
+
+Consensus sequences are analyzed using [FluMut] to identify mutations of interest, specifically for H5N1. The output files are available in multiple formats including Excel and TSV.
+
+<details markdown="1">
+<summary>Output files</summary>
+
+- `flumut/`
+  - `flumut.xlsm`: Excel file containing all the results from the FluMut analysis.
+  - `flumut-markers.tsv`: Tab-separated file containing the list of detected markers by FluMut analysis.
+  - `flumut-mutations.tsv`: Tab-separated file containing the list of amino acids present in the positions of mutations of interest for each sample by FluMut analysis.
+  - `seqs-for-flumut.fasta`: FASTA file containing the sequences of the samples that were analyzed by FluMut.
+
 ### Pipeline information
 
 <details markdown="1">
@@ -278,7 +292,8 @@ Consensus sequences are annotated using [VADR][]. The output files are available
 
 [Nextflow](https://www.nextflow.io/docs/latest/tracing.html) provides excellent functionality for generating various reports relevant to the running and execution of the pipeline. This will allow you to troubleshoot errors with the running of the pipeline, and also provide you with other information such as launch commands, run times and resource usage.
 
-[NCBI Influenza DB]: https://www.ncbi.nlm.nih.gov/genomes/FLU/Database/nph-select.cgi?go=database
-[IRMA]: https://wonder.cdc.gov/amd/flu/irma/
 [BLAST]: https://blast.ncbi.nlm.nih.gov/Blast.cgi
+[FluMut]: https://github.com/izsvenezie-virology/FluMut
+[IRMA]: https://wonder.cdc.gov/amd/flu/irma/
+[NCBI Influenza DB]: https://www.ncbi.nlm.nih.gov/genomes/FLU/Database/nph-select.cgi?go=database
 [VADR]: https://github.com/ncbi/vadr

modules/local/flumut.nf

@@ -0,0 +1,57 @@
+process PREP_FLUMUT_FASTA {
+  conda 'bioconda::bcftools=1.20 conda-forge::gsl=2.7'
+  if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+    container 'https://depot.galaxyproject.org/singularity/bcftools:1.20--h8b25389_0'
+  } else {
+    container 'quay.io/biocontainers/bcftools:1.20--h8b25389_0'
+  }
+
+  input:
+  path(fastas)
+
+  output:
+  path('seqs-for-flumut.fasta'), emit: fasta
+
+  script:
+  """
+  awk 'BEGIN {FS=OFS=""}
+     /^>/ {
+         gsub(/_segment7_M/, "_MP", \$0);  # Replace "_segment7_M" with "_MP"
+         gsub(/segment[0-9]+_/, "", \$0);  # Remove "segment1-9_"
+     }
+     {print}' $fastas > seqs-for-flumut.fasta
+  """
+}
+
+process FLUMUT {
+  label 'process_low'
+
+  conda 'bioconda::flumut=0.6.3'
+  if (workflow.containerEngine == 'singularity' && !params.singularity_pull_docker_container) {
+    container 'https://depot.galaxyproject.org/singularity/flumut:0.6.3--pyhdfd78af_0'
+  } else {
+    container 'quay.io/biocontainers/flumut:0.6.3--pyhdfd78af_0'
+  }
+
+  input:
+  path(fasta)
+
+  output:
+  path('flumut.xlsm'), emit: xlsm
+  path('flumut-markers.tsv'), emit: markers
+  path('flumut-mutations.tsv'), emit: mutations
+  path "versions.yml" , emit: versions
+
+  script:
+  """
+  flumut \\
+    -x flumut.xlsm \\
+    -m flumut-markers.tsv \\
+    -M flumut-mutations.tsv \\
+    $fasta
+
+  cat <<-END_VERSIONS > versions.yml
+  "${task.process}":
+      flumut: \$(flumut --version 2>&1 | sed 's/^.*flumut, version //;s/, .*//')
+  """
+}

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         = '3.5.3'
+  version         = '3.6.0'
   nextflowVersion = '!>=22.10.1'
   mainScript      = 'main.nf'
   doi             = '10.5281/zenodo.13892044'

tests/run-nanopore-test.sh

@@ -64,7 +64,7 @@ done
 
 shift $((OPTIND-1))
 
-if [[ "$1" == "--" ]]; then
+if [[ "${1:-}" == "--" ]]; then
     shift
 fi
 

workflows/illumina.nf

@@ -52,6 +52,7 @@ include { PRE_TABLE2ASN as PRE_TABLE2ASN_BCFTOOLS
 include { TABLE2ASN as TABLE2ASN_BCFTOOLS                                                  } from '../modules/local/table2asn'
 include { POST_TABLE2ASN as POST_TABLE2ASN_BCFTOOLS                                        } from '../modules/local/table2asn'
 include { MQC_VERSIONS_TABLE                                                               } from '../modules/local/mqc_versions_table'
+include { FLUMUT; PREP_FLUMUT_FASTA                                                        } from '../modules/local/flumut'
 
 //=============================================================================
 // Workflow Params Setup
@@ -265,6 +266,10 @@ workflow ILLUMINA {
   )
   ch_versions = ch_versions.mix(SUBTYPING_REPORT_BCF_CONSENSUS.out.versions)
 
+  PREP_FLUMUT_FASTA(CAT_CONSENSUS.out.consensus_fasta.collect({ it[1] }))
+  FLUMUT(PREP_FLUMUT_FASTA.out.fasta)
+  ch_versions = ch_versions.mix(FLUMUT.out.versions)
+
   workflow_summary    = Schema.params_summary_multiqc(workflow, summary_params)
   ch_workflow_summary = Channel.value(workflow_summary)
   ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yaml")

workflows/nanopore.nf

@@ -33,6 +33,7 @@ include { BLAST_BLASTN as BLAST_BLASTN_CONSENSUS              } from '../modules
 include { BLAST_BLASTN as BLAST_BLASTN_CONSENSUS_REF_DB       } from '../modules/local/blastn'
 include { SETUP_FLU_VADR_MODEL; VADR; VADR_SUMMARIZE_ISSUES   } from '../modules/local/vadr'
 include { PRE_TABLE2ASN; TABLE2ASN; POST_TABLE2ASN            } from '../modules/local/table2asn'
+include { FLUMUT; PREP_FLUMUT_FASTA                           } from '../modules/local/flumut'
 include { MULTIQC                                             } from '../modules/local/multiqc'
 include { MQC_VERSIONS_TABLE } from '../modules/local/mqc_versions_table'
 
@@ -284,6 +285,10 @@ workflow NANOPORE {
     ch_versions = ch_versions.mix(BLASTN_REPORT.out.versions)
   }
 
+  PREP_FLUMUT_FASTA(CAT_CONSENSUS.out.consensus_fasta.collect({ it[1] }))
+  FLUMUT(PREP_FLUMUT_FASTA.out.fasta)
+  ch_versions = ch_versions.mix(FLUMUT.out.versions)
+
   workflow_summary    = Schema.params_summary_multiqc(workflow, summary_params)
   ch_workflow_summary = Channel.value(workflow_summary)
   ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yaml")