Implement BAM and CSV input and fix conflict in reditools2 container dependencies

config/softwares.config

@@ -2,6 +2,9 @@ process {
     withLabel: 'agat' {
         container = 'quay.io/biocontainers/agat:1.4.2--pl5321hdfd78af_0'
     }
+    withLabel: 'bash' {
+        container = 'ubuntu:24.04'
+    }
     withLabel: 'bamutil' {
         container = 'quay.io/biocontainers/bamutil:1.0.15--h43eeafb_4'
     }

docker/reditools2/Dockerfile

@@ -1,15 +1,11 @@
 FROM condaforge/miniforge3:24.7.1-2
 
-# Auto-activating Conda setup for Python 2.7
-RUN conda config --add channels bioconda \
-    && conda config --add channels conda-forge \
-    && conda create -n myenv \
-    && echo "conda activate myenv" >> ~/.bashrc
-
 # Tool-specific dependencies
 COPY env_reditools2.yml .
-RUN conda env update -n myenv --file env_reditools2.yml \
-    && conda clean --all -f -y
+RUN conda env create -n myenv --file env_reditools2.yml \
+    && conda clean --all -f -y \
+    && echo "conda activate myenv" >> ~/.bashrc # Auto-activating Conda setup for Python 2.7
+
 
 # Get and install tools
 RUN git clone --depth=1 https://github.com/BioinfoUNIBA/REDItools2.git reditools2

docker/reditools2/env_reditools2.yml

@@ -1,3 +1,5 @@
+name: myenv
+
 channels:
   - bioconda
   - conda-forge
@@ -6,8 +8,8 @@ dependencies:
   - _openmp_mutex=4.5=2_gnu
   - attr=2.5.1=h166bdaf_1
   - bzip2=1.0.8=h4bc722e_7
-  - c-ares=1.34.4=hb9d3cd8_0
-  - ca-certificates=2025.1.31=hbcca054_0
+  - c-ares=1.34.5=hb9d3cd8_0
+  - ca-certificates=2025.4.26=hbd8a1cb_0
   - certifi=2019.11.28=py27h8c360ce_1
   - htslib=1.17=h6bc39ce_1
   - icu=73.2=h59595ed_0
@@ -16,55 +18,53 @@ dependencies:
   - ld_impl_linux-64=2.43=h712a8e2_4
   - libcap=2.71=h39aace5_0
   - libcurl=7.87.0=h6312ad2_0
-  - libdeflate=1.23=h4ddbbb0_0
-  - libedit=3.1.20250104=pl5321h7949ede_0
+  - libdeflate=1.24=h86f0d12_0
+  - libedit=3.1.20191231=he28a2e2_2
   - libev=4.33=hd590300_2
-  - libfabric=2.0.0=ha770c72_1
-  - libfabric1=2.0.0=h14e6f36_1
+  - libfabric=2.1.0=ha770c72_0
+  - libfabric1=2.1.0=h14e6f36_0
   - libffi=3.2.1=he1b5a44_1007
-  - libgcc=14.2.0=h767d61c_2
-  - libgcc-ng=14.2.0=h69a702a_2
-  - libgcrypt-lib=1.11.0=hb9d3cd8_2
-  - libgfortran=14.2.0=h69a702a_2
-  - libgfortran5=14.2.0=hf1ad2bd_2
-  - libgomp=14.2.0=h767d61c_2
-  - libgpg-error=1.51=hbd13f7d_1
+  - libgcc=15.1.0=h767d61c_2
+  - libgcc-ng=15.1.0=h69a702a_2
+  - libgcrypt-lib=1.11.1=hb9d3cd8_0
+  - libgfortran=15.1.0=h69a702a_2
+  - libgfortran5=15.1.0=hcea5267_2
+  - libgomp=15.1.0=h767d61c_2
+  - libgpg-error=1.55=h3f2d84a_0
   - libhwloc=2.11.2=default_he43201b_1000
   - libiconv=1.18=h4ce23a2_1
-  - liblzma=5.6.4=hb9d3cd8_0
   - libnghttp2=1.51.0=hdcd2b5c_0
   - libnl=3.11.0=hb9d3cd8_0
-  - libsqlite=3.46.0=hde9e2c9_0
   - libssh2=1.10.0=haa6b8db_3
-  - libstdcxx=14.2.0=h8f9b012_2
-  - libstdcxx-ng=14.2.0=h4852527_2
-  - libsystemd0=257.3=h3dc2cb9_0
-  - libudev1=257.3=h9a4d06a_0
+  - libstdcxx=15.1.0=h8f9b012_2
+  - libstdcxx-ng=15.1.0=h4852527_2
+  - libsystemd0=256.9=h2774228_0
+  - libudev1=257.4=h9a4d06a_0
   - libxml2=2.12.7=hc051c1a_1
   - libzlib=1.2.13=h4ab18f5_6
-  - lz4-c=1.10.0=h5888daf_1
+  - lz4-c=1.9.4=hcb278e6_0
   - mpi=1.0.1=mpich
   - mpi4py=3.0.3=py27hf423c55_1
   - mpich=4.3.0=h1a8bee6_100
-  - ncurses=6.5=h2d0b736_3
-  - netifaces=0.10.9=py27hdf8410d_1002
+  - ncurses=6.2=h58526e2_4
+  - netifaces=0.10.4=py27_1
   - openssl=1.1.1w=hd590300_0
   - pip=20.1.1=pyh9f0ad1d_0
   - psutil=5.7.0=py27hdf8410d_1
   - pysam=0.20.0=py27h7835474_0
   - python=2.7.15=h5a48372_1011_cpython
   - python_abi=2.7=1_cp27mu
-  - rdma-core=56.0=h5888daf_0
-  - readline=8.2=h8c095d6_2
-  - samtools=1.18=hd87286a_0
+  - rdma-core=55.0=h5888daf_0
+  - readline=8.1=h46c0cb4_0
+  - samtools=1.12=h9aed4be_1
   - setuptools=44.0.0=py27_0
   - sortedcontainers=2.4.0=pyhd8ed1ab_0
-  - sqlite=3.46.0=h6d4b2fc_0
+  - sqlite=3.37.0=h9cd32fc_0
   - tabix=1.11=hdfd78af_0
   - tk=8.6.13=noxft_h4845f30_101
-  - ucx=1.18.0=hfd9a62f_1
+  - ucx=1.18.0=hfd9a62f_3
   - wheel=0.37.1=pyhd8ed1ab_0
   - xz=5.2.6=h166bdaf_0
   - zlib=1.2.13=h4ab18f5_6
   - zstd=1.5.6=ha6fb4c9_0
-
+  

lib/Rain_utilities.groovy

@@ -0,0 +1,24 @@
+// dedicated to the utility functions
+class Rain_utilities {
+
+    // Function to chek if we
+    public static Boolean is_url(file) {
+
+        // check if the file is a URL
+        if (file =~ /^(http|https|ftp|s3|az|gs):\/\/.*/) {
+            return true
+        } else {
+            return false
+        }
+    }
+    // Function to chek if we
+    public static Boolean is_fastq(file) {
+
+        // check if the file is a URL
+        if (file =~ /.*(fq|fastq|fq.gz|fastq.gz)$/) {
+            return true
+        } else {
+            return false
+        }
+    }
+}

modules/aline.nf

@@ -30,7 +30,7 @@ process AliNe {
                 profile,
                 config,
                 reads,
-                "--genome ${genome}",
+                "--reference ${genome}",
                 read_type,
                 aligner,
                 library_type,

modules/bamutil.nf

@@ -1,18 +1,19 @@
 process bamutil_clipoverlap {
     label 'bamutil'
-    tag "$sample_id"
+    tag "${meta.id}"
     publishDir "${params.outdir}/bamutil_clipoverlap", mode: 'copy'
 
     input:
-    tuple val(sample_id), path(bam)
+    tuple val(meta), path(bam)
 
     output:
-    tuple val(sample_id), path ("*clipoverlap.bam"), emit: tuple_sample_clipoverbam
+    tuple val(meta), path ("*clipoverlap.bam"), emit: tuple_sample_clipoverbam
     path ("*_bamutil_clipoverlap.log"), emit: log
 
     script:
-    """
-    bam clipOverlap --storeOrig CG --poolSize 50000000 --in ${bam} --out ${bam}_clipoverlap.bam --stats > ${sample_id}_bamutil_clipoverlap.log
-    """
+
+        """
+        bam clipOverlap --storeOrig CG --poolSize 50000000 --in ${bam} --out ${bam}_clipoverlap.bam --stats > ${meta.id}_bamutil_clipoverlap.log
+        """
 
 }

modules/bash.nf

@@ -0,0 +1,21 @@
+/*
+Here are described all processes related to bash
+*/
+
+// A process to compute the mean read length of a FASTQ
+process extract_libtype {
+    label 'bash'
+    tag "$id"
+
+    input:
+        tuple val(id), path(samlmon_json)
+
+    output:
+        tuple val(id), env(LIBTYPE), emit: tuple_id_libtype
+
+    script:
+        """
+            LIBTYPE=\$(grep expected_format ${samlmon_json} | awk '{print \$2}' | tr -d '",\n')
+        """
+
+}

modules/fastp.nf

@@ -1,49 +1,57 @@
 process fastp {
     label 'fastp'
-    publishDir "${params.output}/${id}/qc", mode: 'copy'
+    tag "${meta.id}"
+    publishDir "${params.output}/${meta.id}/qc", mode: 'copy'
+
     input:
-        tuple val(id), path(illumina)
+        tuple val(meta), path(illumina)
         val(phred_type)
+
     output:
-        tuple val(id), path("*_R?_clean.fastq")
-        path("${id}_fastp_report.html")
+        tuple val(meta), path("*_R?_clean.fastq")
+        path("${meta.id}_fastp_report.html")
+
     script:
         """
         if [ "${phred_type}" == "64" ]
         then
           fastp -i ${illumina[0]} -I ${illumina[1]} \
-              -o ${id}_R1_clean.fastq -O ${id}_R2_clean.fastq \
+              -o ${meta.id}_R1_clean.fastq -O ${meta.id}_R2_clean.fastq \
               --phred64 \
-              --detect_adapter_for_pe --html ${id}_fastp_report.html
+              --detect_adapter_for_pe --html ${meta.id}_fastp_report.html
         else
           fastp -i ${illumina[0]} -I ${illumina[1]} \
-              -o ${id}_R1_clean.fastq -O ${id}_R2_clean.fastq \
-              --detect_adapter_for_pe --html ${id}_fastp_report.html
+              -o ${meta.id}_R1_clean.fastq -O ${meta.id}_R2_clean.fastq \
+              --detect_adapter_for_pe --html ${meta.id}_fastp_report.html
         fi
         """
 }
 
 process fastp_hybrid {
     label 'fastp'
+    tag "${meta.id}"
     publishDir "${params.output}/${id}/qc", mode: 'copy'
+
     input:
-        tuple val(id), path(illuminaR1), path(illuminaR2), path(ont)
+        tuple val(meta), path(illuminaR1), path(illuminaR2), path(ont)
         val(phred_type)
+
     output:
-        tuple val(id), path("${id}_R1_clean.fastq"),path("${id}_R2_clean.fastq"), path(ont), emit: trimmed_hybrid
-        path("${id}_fastp_report.html")
+        tuple val(meta), path("${meta.id}_R1_clean.fastq"),path("${meta.id}_R2_clean.fastq"), path(ont), emit: trimmed_hybrid
+        path("${meta.id}_fastp_report.html")
+
     script:
         """
         if [ "${phred_type}" == "64" ]
         then
           fastp -i ${illuminaR1} -I ${illuminaR2} \
-              -o ${id}_R1_clean.fastq -O ${id}_R2_clean.fastq \
+              -o ${meta.id}_R1_clean.fastq -O ${meta.id}_R2_clean.fastq \
               --phred64 \
-              --detect_adapter_for_pe --html ${id}_fastp_report.html
+              --detect_adapter_for_pe --html ${meta.id}_fastp_report.html
         else
           fastp -i ${illuminaR1} -I ${illuminaR2} \
-              -o ${id}_R1_clean.fastq -O ${id}_R2_clean.fastq \
-              --detect_adapter_for_pe --html ${id}_fastp_report.html
+              -o ${meta.id}_R1_clean.fastq -O ${meta.id}_R2_clean.fastq \
+              --detect_adapter_for_pe --html ${meta.id}_fastp_report.html
         fi
         """
 }

modules/fastqc.nf

@@ -1,19 +1,19 @@
 process fastqc {
     label 'fastqc'
-    tag "$sample_id"
+    tag "${meta.id}"
     publishDir "${params.outdir}/FastQC", mode: 'copy'
 
     input:
-    tuple val(sample_id), path(reads)
-    val (suffix)
+        tuple val(meta), path(reads)
+        val (suffix)
 
     output:
-    path ("fastqc_${sample_id}_logs_${suffix}")
+        path ("fastqc_${meta.id}_logs_${suffix}")
 
     script:
-    """
-    mkdir fastqc_${sample_id}_logs_${suffix}
-    fastqc -t ${task.cpus} -o fastqc_${sample_id}_logs_${suffix} -q ${reads}
-    """
+        """
+        mkdir fastqc_${meta.id}_logs_${suffix}
+        fastqc -t ${task.cpus} -o fastqc_${meta.id}_logs_${suffix} -q ${reads}
+        """
 
 }

modules/gatk.nf

@@ -1,22 +1,22 @@
 process gatk_markduplicates {
     label 'gatk'
-    tag "$sample_id"
+    tag "${meta.id}"
     publishDir "${params.outdir}/gatk_markduplicates", mode: 'copy'
 
     input:
-    tuple val(sample_id), path(bam)
+      tuple val(meta), path(bam)
 
     output:
-    tuple val(sample_id), path ("*_marked_duplicates.bam"), emit: tuple_sample_dedupbam
-    path ("*_marked_dup_metrics.txt") , emit: log
+      tuple val(meta), path ("*_marked_duplicates.bam"), emit: tuple_sample_dedupbam
+      path ("*_marked_dup_metrics.txt") , emit: log
 
     script:
-    """
-    gatk MarkDuplicates \
-      -I ${bam} \
-      -O ${bam.baseName}_marked_duplicates.bam \
-      -M ${bam.baseName}_marked_dup_metrics.txt \
-      --REMOVE_DUPLICATES
-    """
 
+      """
+      gatk MarkDuplicates \
+        -I ${bam} \
+        -O ${bam.baseName}_marked_duplicates.bam \
+        -M ${bam.baseName}_marked_dup_metrics.txt \
+        --REMOVE_DUPLICATES
+      """
 }

modules/jacusa2.nf

@@ -1,18 +1,19 @@
 process jacusa2 {
     label "jacusa2"
+    tag "${meta.id}"
     publishDir("${params.outdir}/jacusa2", mode: "copy")
 
     input:
-    tuple(val(sample), path(bam), path(bamindex))
-    tuple(path(genome), path(fastaindex))
+        tuple(val(meta), path(bam), path(bamindex))
+        tuple(path(genome), path(fastaindex))
 
     output:
-    path("*.txt")
-    path("*.filtered")
-    // tuple(sample, path("filtered_output.txt", emit: tuple_sample_jacusa2_table))
+        path("*.txt")
+        path("*.filtered")
+        // tuple(sample, path("filtered_output.txt", emit: tuple_sample_jacusa2_table))
 
     script:
-    """
-    java -Xmx${task.memory.toMega()}M -jar /usr/local/bin/JACUSA_v2.0.4.jar call-1 -a D -f V -p ${task.cpus} -r jacusa_out.txt -c 1 -s -R ${genome} ${bam}
-    """
+        """
+        java -Xmx${task.memory.toMega()}M -jar /usr/local/bin/JACUSA_v2.0.4.jar call-1 -a D -f V -p ${task.cpus} -r jacusa_out.txt -c 1 -s -R ${genome} ${bam}
+        """
 }

modules/multiqc.nf

@@ -3,15 +3,15 @@ process multiqc {
     publishDir "${params.outdir}/MultiQC", mode: 'copy'
 
     input:
-    path log_files
-    path multiqc_config
+        path log_files
+        path multiqc_config
 
     output:
-    path "*multiqc_report.html"
-    path "*_data"
+        path "*multiqc_report.html"
+        path "*_data"
 
     script:
-    """
-    multiqc -p . -c ${multiqc_config}
-    """
+        """
+        multiqc -p . -c ${multiqc_config}
+        """
 }