Merge branch 'dev' into simonleandergrimm-patch-1

CHANGELOG.md

@@ -1,3 +1,9 @@
+# v2.6.1.0
+- Replace Trimmomatic with Atria
+
+# v2.6.0.0
+- Updated verison to reflect the new versioning scheme, which is described in `docs/version_schema.md`.
+
 # v2.5.3
 - Added new LOAD_SAMPLESHEET subworkflow to centralize samplesheet processing
 - Updated tags to prevent inappropriate S3 auto-cleanup

configs/containers.config

@@ -73,4 +73,7 @@ process {
     withLabel: fastp {
         container = "staphb/fastp:0.23.4"
     }
+    withLabel: atria {
+        container = "harmonb/atria:latest"
+    }
 }

docker/atria.Dockerfile

@@ -0,0 +1,50 @@
+# Use Ubuntu as the base image
+FROM ubuntu:22.04
+
+# Prevent interactive prompts during package installation
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install essential dependencies, R, and system libraries needed for R packages
+RUN apt-get update && apt-get install -y \
+    wget \
+    pigz \
+    pbzip2 \
+    r-base \
+    r-base-dev \
+    libcurl4-openssl-dev \
+    libssl-dev \
+    libxml2-dev \
+    libfontconfig1-dev \
+    libharfbuzz-dev \
+    libfribidi-dev \
+    libfreetype6-dev \
+    libpng-dev \
+    libtiff5-dev \
+    libjpeg-dev \
+    libcairo2-dev \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install pacman first, then use it to install other packages
+RUN R -e "install.packages('pacman', repos='https://cran.rstudio.com/')" && \
+    R -e "pacman::p_load(argparse, plotly, ggsci, tidyverse)"
+
+# Set working directory
+WORKDIR /opt
+
+# Install Atria
+RUN wget https://github.com/cihga39871/Atria/releases/download/v4.1.0/atria-4.1.0-linux-ubuntu22.tar.gz && \
+    tar -zxf atria-4.1.0-linux-ubuntu22.tar.gz && \
+    rm atria-4.1.0-linux-ubuntu22.tar.gz
+
+# Create symbolic link
+RUN chmod +x /opt/atria-4.1.0/bin/atria && \
+    ln -s /opt/atria-4.1.0/bin/atria /usr/local/bin/atria
+
+# Set environment variables
+ENV PATH="/usr/local/bin:/opt/atria-4.1.0/bin:$PATH"
+
+# Verify installations
+RUN which atria && \
+    atria --version && \
+    Rscript --version && \
+    R -e "pacman::p_loaded()"

modules/local/atria/main.nf

@@ -0,0 +1,16 @@
+process ATRIA {
+    label "atria"
+    label "large"
+    input:
+        // reads is a list of two files: forward/reverse reads
+        tuple val(sample), path(reads)
+        val(adapters_ch)
+    output:
+        tuple val(sample), path("*{1,2}.atria.fastq.gz"), emit: reads
+    shell:
+        '''
+        par="--adapter1 !{adapters_ch.join(' ')} --adapter2 !{adapters_ch.join(' ')} --kmer-tolerance 2 --kmer-n-match 9 --trim-score-pe 10.0 --quality-kmer 4 --quality-score 15 --length-range 20:999999 --no-consensus"
+        in="--read1 !{reads[0]} --read2 !{reads[1]}"
+        atria ${par} ${in}
+        '''
+}

subworkflows/local/extractViralReads/main.nf

@@ -4,7 +4,7 @@
 
 include { BBDUK_HITS } from "../../../modules/local/bbduk"
 include { CUTADAPT } from "../../../modules/local/cutadapt"
-include { TRIMMOMATIC } from "../../../modules/local/trimmomatic"
+include { ATRIA } from "../../../modules/local/atria"
 include { BOWTIE2 as BOWTIE2_VIRUS } from "../../../modules/local/bowtie2"
 include { BOWTIE2 as BOWTIE2_HUMAN } from "../../../modules/local/bowtie2"
 include { BOWTIE2 as BOWTIE2_OTHER } from "../../../modules/local/bowtie2"
@@ -63,11 +63,21 @@ workflow EXTRACT_VIRAL_READS {
         bbm_human_index_path = "${ref_dir}/results/bbm-human-index"
         bbm_other_index_path = "${ref_dir}/results/bbm-other-index"
         virus_db_path = "${ref_dir}/results/total-virus-db-annotated.tsv.gz"
-        // Run initial screen against viral genomes with BBDuk
+
+        // Read adapter file and create a channel containing just the adapter sequences
+        adapters_ch = Channel
+            .fromPath(adapter_path)
+            .splitFasta(record: [seqString: true])
+            .map { it.seqString }
+            .collect()
+
+       // Run initial screen against viral genomes with BBDuk
         bbduk_ch = BBDUK_HITS(reads_ch, viral_genome_path, min_kmer_hits, k, bbduk_suffix)
         // Carry out stringent adapter removal with Cutadapt and Trimmomatic
         adapt_ch = CUTADAPT(bbduk_ch.fail, adapter_path)
-        trim_ch = TRIMMOMATIC(adapt_ch.reads, adapter_path, encoding)
+        // trim_ch = TRIMMOMATIC(adapt_ch.reads, adapter_path, encoding)
+        atria_ch = ATRIA(adapt_ch.reads, adapters_ch)
+        trim_ch = atria_ch
         // Grouping for deduplication
         if (grouping) {
             // Join samplesheet with trimmed_reads and update fastq files

tests/main.nf.test.snap

@@ -7,16 +7,16 @@
             "qc_basic_stats.tsv.gz:md5,fd1a20ad7bb06eecaaa9cc51b81efa8d",
             "qc_quality_base_stats.tsv.gz:md5,1e75fe721479280f83d7e2f8c9fa975b",
             "qc_quality_sequence_stats.tsv.gz:md5,0d835c1d9417df961b4aadd7ac42137d",
-            "virus_clade_counts.tsv.gz:md5,3fcf57def952c95bf43cad8cfb268926",
-            "virus_hits_db.tsv.gz:md5,2232a0cfa4a2812621bb852c276ef9a1",
-            "blast_hits_paired.tsv.gz:md5,f2d110487d36ca58b1232f6d02aa69af",
-            "virus_hits_1.fasta.gz:md5,6024105b15a879de8616e54cb2dc3bb0",
-            "virus_hits_2.fasta.gz:md5,a08a14e81a6277d56ec16d04f3be7b8e"
+            "virus_clade_counts.tsv.gz:md5,89f68c2cc7912f37b22745168b2fc7e4",
+            "virus_hits_db.tsv.gz:md5,72e692fb3d168dc5199ab97ac4c58426",
+            "blast_hits_paired.tsv.gz:md5,6dce9cbf1aa6397a9145c9752aa4c723",
+            "virus_hits_1.fasta.gz:md5,941487995f144f88df4c2994f2fc551c",
+            "virus_hits_2.fasta.gz:md5,e285ccfb350fed7f0e73e29aaa1f10c1"
         ],
         "meta": {
             "nf-test": "0.9.2",
             "nextflow": "24.10.1"
         },
-        "timestamp": "2024-12-20T21:16:59.561007756"
+        "timestamp": "2025-01-10T16:29:00.730413741"
     }
 }