unselected RNA-seq based workflow

.github/workflows/ci.yml

@@ -62,6 +62,8 @@ jobs:
             "test_10x_sc",
             "test_clontech_umi",
             "test_nebnext_umi",
+            "test_rnaseq_bulk",
+            "test_rnaseq_sc",
           ]
       fail-fast: false
     steps:

conf/test_rnaseq_bulk.config

@@ -0,0 +1,27 @@
+/*
+ * -------------------------------------------------
+ *  Nextflow config file for running tests
+ * -------------------------------------------------
+ * Defines bundled input files and everything required
+ * to run a fast and simple test. Use as follows:
+ *   nextflow run nf-core/airrflow -profile test_rnaseq_bulk,<docker/singularity>
+ */
+
+params {
+    config_profile_name = 'Test bulk RNA-seq based workflow using TRUST4'
+    config_profile_description = 'Minimal test dataset to check pipeline function with raw bulk RNA-seq data'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus = 2
+    max_memory = 6.GB
+    max_time = 48.h
+
+    // params
+    mode = 'fastq'
+    library_generation_method = 'trust4'
+    clonal_threshold = 0
+
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-rnaseq/rnaseq_metadata.tsv'
+    coord_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-rnaseq/IMGT+C.fa'
+}

conf/test_rnaseq_sc.config

@@ -0,0 +1,31 @@
+/*
+ * -------------------------------------------------
+ *  Nextflow config file for running tests
+ * -------------------------------------------------
+ * Defines bundled input files and everything required
+ * to run a fast and simple test. Use as follows:
+ *   nextflow run nf-core/airrflow -profile test_rnaseq_sc,<docker/singularity>
+ */
+
+params {
+    config_profile_name = 'Test single-cell RNA-seq based workflow using TRUST4'
+    config_profile_description = 'Minimal test dataset to check pipeline function with raw single-cell RNA-seq data'
+
+    // Limit resources so that this can run on GitHub Actions
+    max_cpus = 2
+    max_memory = 6.GB
+    max_time = 48.h
+
+    // params
+    mode = 'fastq'
+    library_generation_method = 'trust4'
+    clonal_threshold = 0
+    barcode_read = R1
+    umi_position = R1
+    read_format = "bc:0:15,um:16:27"
+    skip_lineage = True
+
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-rnaseq/sc_rnaseq_metadata.tsv'
+    coord_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-rnaseq/IMGT+C.fa'
+}

docs/usage.md

@@ -42,13 +42,13 @@ nextflow run nf-core/airrflow \
 A typical command to run the pipeline from **single cell raw fastq files** is:
 
 ```bash
-nextflow run nf-core/airrflow -r dev \
+nextflow run nf-core/airrflow \
 -profile <docker/singularity/podman/shifter/charliecloud/conda/institute> \
 --mode fastq \
 --input input_samplesheet.tsv \
 --library_generation_method sc_10x_genomics \
 --reference_10x reference/refdata-cellranger-vdj-GRCh38-alts-ensembl-5.0.0.tar.gz \
---outdir ./results
+--outdir results
 ```
 
 A typical command for running the pipeline departing from **single-cell AIRR rearrangement tables or assembled bulk sequencing fasta** data is:
@@ -123,7 +123,7 @@ If you wish to share such profile (such as upload as supplementary material for
 
 ## Input samplesheet
 
-### Fastq input samplesheet (bulk sequencing)
+### Fastq input samplesheet (bulk AIRR and bulk/sc RNA sequencing)
 
 The required input file for processing raw BCR or TCR bulk targeted sequencing data is a sample sheet in TSV format (tab separated). The columns `sample_id`, `filename_R1`, `filename_R2`, `subject_id`, `species`, `tissue`, `pcr_target_locus`, `single_cell`, `sex`, `age` and `biomaterial_provider` are required. An example samplesheet is:
 
@@ -511,6 +511,49 @@ nextflow run nf-core/airrflow -r dev \
 - The 10xGenomics reference can be downloaded from the [download page](https://www.10xgenomics.com/support/software/cell-ranger/downloads)
 - To generate a V(D)J segment fasta file as reference from IMGT one can follow the [cellranger docs](https://support.10xgenomics.com/single-cell-vdj/software/pipelines/latest/advanced/references#imgt).
 
+## Supported unselected RNA-seq based methods
+
+nf-core/airrflow supports unselected bulk or single-cell RNA-seq fastq files as input. [TRUST4](https://github.com/liulab-dfci/TRUST4) is used to extract TCR/BCR sequences from these files. The resulting AIRR tables are then fed into airrflow's Immcantation based workflow. <br>
+To use unselected RNA-seq based input, specify `--library_generation_method trust4`.
+
+### Bulk RNA-seq
+
+A typical command to run the pipeline from **bulk RNA-seq fastq files** is:
+
+```bash
+nextflow run nf-core/airrfow \
+-profile <docker/singularity/podman/shifter/charliecloud/conda/institute> \
+--mode fastq \
+--input input_samplesheet.tsv \
+--library_generation_method trust4 \
+--coord_fasta reference/IMGT+C.fa \
+--outdir results
+```
+
+### Single-cell RNA-seq
+
+A typical command to run the pipeline from **single-cell RNA-seq fastq files** is:
+
+```bash
+nextflow run nf-core/airrfow \
+-profile <docker/singularity/podman/shifter/charliecloud/conda/institute> \
+--mode fastq \
+--input input_samplesheet.tsv \
+--library_generation_method trust4 \
+--umi_position R1 \
+--read_format bc:0:15,um:16:27
+--coord_fasta reference/IMGT+C.fa \
+--outdir results
+```
+
+- If UMI's are present, the read containing them must be specified using the `--umi_position` parameter.
+- The `--read_format` parameter can be used to specify the Barcode and UMI position within the reads (see TRUST4 [docs](https://github.com/liulab-dfci/TRUST4?tab=readme-ov-file#10x-genomics-data-and-barcode-based-single-cell-data))
+
+#### Reference file
+
+TRUST4 requires a reference. This can provided using the `--coord_fasta` parameter.
+The reference fasta can be downloaded from IMGT and created using [TRUST4](https://github.com/liulab-dfci/TRUST4?tab=readme-ov-file#build-custom-vjc-gene-database-files-for--f-and---ref)
+
 ## Core Nextflow arguments
 
 :::note

modules.json

@@ -46,7 +46,7 @@
                     },
                     "utils_nfcore_pipeline": {
                         "branch": "master",
-                        "git_sha": "5caf7640a9ef1d18d765d55339be751bb0969dfa",
+                        "git_sha": "92de218a329bfc9a9033116eb5f65fd270e72ba3",
                         "installed_by": ["subworkflows"]
                     },
                     "utils_nfvalidation_plugin": {

modules/local/rename_fastq_trust4.nf

@@ -0,0 +1,23 @@
+// Import generic module functions
+process RENAME_FASTQ_TRUST4 {
+    tag "$meta.id"
+    label 'process_low'
+
+    conda "conda-forge::python=3.8.0 conda-forge::biopython=1.74"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/mulled-v2-adc9bb9edc31eb38b3c24786a83b7dfa530e2bea:47d6d7765d7537847ced7dac873190d164146022-0' :
+        'biocontainers/mulled-v2-adc9bb9edc31eb38b3c24786a83b7dfa530e2bea:47d6d7765d7537847ced7dac873190d164146022-0' }"
+
+    input:
+    tuple val(meta), path(R1), path(R2)
+    tuple val(meta_2), path(orig_r1), path(orig_r2)
+
+    output:
+    tuple val(meta), path(orig_r1), path(orig_r2) , emit: reads
+
+    script:
+    """
+    mv ${R1} ${orig_r1}
+    mv ${R2} ${orig_r2}
+    """
+}

modules/local/trust4.nf

@@ -0,0 +1,102 @@
+process TRUST4 {
+    tag "$meta.id"
+    label 'process_medium'
+
+    conda "bioconda::trust4=1.0.13"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/trust4:1.0.13--h43eeafb_0':
+        'biocontainers/trust4:1.0.13--h43eeafb_0' }"
+
+    input:
+    tuple val(meta), path(bam), path(reads)
+    tuple val(meta2), path(fasta)
+    tuple val(meta3), path(vdj_reference)
+
+    output:
+    tuple val(meta), path("*.tsv")                          , emit: tsv
+    tuple val(meta), path("*_airr.tsv")                     , emit: airr_files
+    tuple val(meta), path("${meta.id}_airr.tsv")            , emit: airr_tsv
+    tuple val(meta), path("*_report.tsv")                   , emit: report_tsv
+    tuple val(meta), path("*.fa")                           , emit: fasta
+    tuple val(meta), path("*.out")                          , emit: out
+    tuple val(meta), path("*.fq")                           , emit: fq
+    tuple val(meta), path("**")                             , emit: outs
+    path "versions.yml"                                     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    def bam_mode = bam ? "-b ${bam}" : ''
+    def single_end_mode = reads && meta.single_end ? "-u ${reads}" : ''
+    // reference is optional for fastq input
+    def reference = vdj_reference ? "--ref ${vdj_reference}" : ""
+    // separate forward from reverse pairs
+    def (forward, reverse) = reads.collate(2).transpose()
+    def paired_end_mode = reads && (meta.single_end == false) ? "-1 ${forward[0]} -2 ${reverse[0]}" : ''
+    def readFormat = params.read_format ? "--readFormat ${params.read_format}" : ''
+    def barcode = ''
+    if (meta.barcode_read) {
+        if (meta.barcode_read == "R1") {
+            barcode = "--barcode ${forward[0]}"
+        } else if (meta.barcode_read == "R2") {
+            barcode = "--barcode ${reverse[0]}"
+        }
+    }
+    else {
+        barcode = ''
+    }
+    def umi_position = ''
+    if (meta.umi_position) {
+        if (meta.umi_position == "R1") {
+            umi_position = "--UMI ${forward[0]}"
+        } else if (meta.umi_position == "R2") {
+            umi_position = "--UMI ${reverse[0]}"
+        }
+    }
+    else {
+        umi_position = ''
+    }
+
+    """
+    run-trust4 \\
+        ${bam_mode} \\
+        ${single_end_mode} \\
+        ${paired_end_mode} \\
+        ${barcode} \\
+        ${readFormat} \\
+        ${umi_position} \\
+        -t $task.cpus \\
+        -f ${fasta} \\
+        -o ${prefix} \\
+        ${reference} \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        trust4: \$(run-trust4 2>&1 | grep -o 'v[0-9.]*-r[0-9]*' | sed 's/^/TRUST4 using /' )
+    END_VERSIONS
+    """
+
+    stub:
+    def args = task.ext.args ?: ''
+    def prefix = task.ext.prefix ?: "${meta.id}"
+    """
+    touch ${prefix}_airr.tsv
+    touch ${prefix}_airr_align.tsv
+    touch ${prefix}_report.tsv
+    touch ${prefix}_assembled_reads.fa
+    touch ${prefix}_annot.fa
+    touch ${prefix}_cdr3.out
+    touch ${prefix}_raw.out
+    touch ${prefix}_final.out
+    touch ${prefix}_toassemble.fq
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        trust4: \$(run-trust4 2>&1 | grep -o 'v[0-9.]*-r[0-9]*' | sed 's/^/TRUST4 using /' )
+    END_VERSIONS
+    """
+}

nextflow.config

@@ -31,7 +31,7 @@ params {
     primer_revpr = false
 
     // UMI and primer handling
-    umi_position = 'R1'
+    umi_position = null
     umi_length = -1
     umi_start = 0
 
@@ -123,6 +123,13 @@ params {
     // -----------------------
     reference_10x = null
 
+    // -----------------------
+    // raw RNA seq input options
+    // -----------------------
+    barcode_read = null
+    read_format = null
+    coord_fasta = null
+
 
     // -----------------------
     // generic nf-core options
@@ -299,6 +306,8 @@ profiles {
     test_10x_sc { includeConfig 'conf/test_10x_sc.config' }
     test_clontech_umi { includeConfig 'conf/test_clontech_umi.config' }
     test_nebnext_umi { includeConfig 'conf/test_nebnext_umi.config' }
+    test_rnaseq_bulk { includeConfig 'conf/test_rnaseq_bulk.config' }
+    test_rnaseq_sc { includeConfig 'conf/test_rnaseq_sc.config' }
     nebnext_umi_tcr { includeConfig 'conf/nebnext_umi_tcr.config' }
     nebnext_umi_bcr { includeConfig 'conf/nebnext_umi_bcr.config' }
     clontech_umi_bcr { includeConfig 'conf/clontech_umi_bcr.config' }