Cellranger vdj

.github/workflows/ci.yml

@@ -56,6 +56,7 @@ jobs:
             "test_fetchimgt",
             "test_assembled_hs",
             "test_assembled_mm",
+            "test_10x_sc",
             "test_clontech_umi",
             "test_nebnext_umi",
           ]

.gitignore

@@ -11,3 +11,4 @@ package-lock.json
 .idea/
 nf-params.json
 .vscode/
+tests/

CHANGELOG.md

@@ -9,6 +9,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 - [#294](https://github.com/nf-core/airrflow/pull/294) Merge template updates nf-core/tools v2.11.1
 - [#299](https://github.com/nf-core/airrflow/pull/299) Add profile for common NEB and TAKARA protocols
+- Add possibility to merge multi-lane samples when starting from fastq files
 
 ### `Fixed`
 

bin/check_samplesheet.py

@@ -124,11 +124,6 @@ def check_samplesheet(file_in, assembled):
                         )
                     )
         else:
-            if any(tab["single_cell"].tolist()):
-                print_error(
-                    "Some single cell column values are TRUE. The raw mode only accepts bulk samples. If processing single cell samples, please set the `--mode assembled` flag, and provide an AIRR rearrangement as input."
-                )
-
             for col in required_columns_raw:
                 if col not in header:
                     print("ERROR: Please check samplesheet header: {} ".format(",".join(header)))
@@ -165,9 +160,12 @@ def check_samplesheet(file_in, assembled):
 
         ## Check that sample ids are unique
         if len(tab["sample_id"]) != len(set(tab["sample_id"])):
-            print_error(
-                "Sample IDs are not unique! The sample IDs in the input samplesheet should be unique for each sample."
-            )
+            if assembled:
+                print_error(
+                    "Sample IDs are not unique! The sample IDs in the input samplesheet should be unique for each sample."
+                )
+            else:
+                print("WARNING: Sample IDs are not unique! FastQs with the same sample ID will be merged.")
 
         ## Check that pcr_target_locus is IG or TR
         for val in tab["pcr_target_locus"]:

bin/reveal_add_metadata.R

@@ -61,8 +61,12 @@ if (!("INPUTID" %in% names(opt))) {
 # Read metadata file
 metadata <- read.csv(opt$METADATA, sep = "\t", header = TRUE, stringsAsFactors = F)
 
+# Merging samples over multiple lanes introduces multi-rows per sample
+# We expect only one row per sample
 metadata <- metadata %>%
-    filter(sample_id == opt$INPUTID)
+    dplyr::filter(sample_id == opt$INPUTID) %>%
+    dplyr::select(!starts_with("filename_")) %>%
+    dplyr::distinct()
 
 if (nrow(metadata) != 1) {
     stop("Expecting nrow(metadata) == 1; nrow(metadata) == ", nrow(metadata), " found")
@@ -81,10 +85,7 @@ internal_fields <-
         "id",
         "filetype",
         "valid_single_cell",
-        "valid_pcr_target_locus",
-        "filename_R1",
-        "filename_R2",
-        "filename_I1"
+        "valid_pcr_target_locus"
     )
 metadata <- metadata[, !colnames(metadata) %in% internal_fields]
 

conf/test_10x_sc.config

@@ -0,0 +1,28 @@
+/*
+ * -------------------------------------------------
+ *  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_10x_sc,<docker/singularity>
+ */
+
+params {
+    config_profile_name = 'Test 10xGenomics single cell data'
+    config_profile_description = 'Minimal test dataset to check pipeline function with raw single cell data from 10xGenomics'
+
+    // 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 = 'sc_10x_genomics'
+    clonal_threshold = 0
+
+
+    // Input data
+    input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-sc/10x_sc_raw.tsv'
+    reference_10x = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-sc/refdata-cellranger-vdj-GRCh38-alts-ensembl-5.0.0.tar.gz'
+}

modules.json

@@ -5,6 +5,21 @@
         "https://github.com/nf-core/modules.git": {
             "modules": {
                 "nf-core": {
+                    "cat/fastq": {
+                        "branch": "master",
+                        "git_sha": "02fd5bd7275abad27aad32d5c852e0a9b1b98882",
+                        "installed_by": ["modules"]
+                    },
+                    "cellranger/mkvdjref": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["modules"]
+                    },
+                    "cellranger/vdj": {
+                        "branch": "master",
+                        "git_sha": "3f5420aa22e00bd030a2556dfdffc9e164ec0ec5",
+                        "installed_by": ["modules"]
+                    },
                     "custom/dumpsoftwareversions": {
                         "branch": "master",
                         "git_sha": "8ec825f465b9c17f9d83000022995b4f7de6fe93",

modules/local/cellranger/mkvdjref.nf

@@ -0,0 +1,37 @@
+process CELLRANGER_MKVDJREF {
+    tag "${meta.id}"
+    label 'process_high'
+
+    container "nf-core/cellranger:7.1.0"
+
+    input:
+    path fasta
+    // path gtf // maybe this can be used to decide whether --seqs or --genes should be used. If its possible to set gtf as an optional parameter.
+    val reference_name
+
+    output:
+    path "${reference_name}", emit: reference
+    path "versions.yml"     , emit: versions
+
+    when:
+    task.ext.when == null || task.ext.when
+
+    script:
+    // Exit if running this module with -profile conda / -profile mamba
+    if (workflow.profile.tokenize(',').intersect(['conda', 'mamba']).size() >= 1) {
+        error "CELLRANGER_MKVDJREF module does not support Conda. Please use Docker / Singularity / Podman instead."
+    }
+    def args = task.ext.args ?: ''
+    """
+    cellranger \\
+        mkvdjref \\
+        --genome=$reference_name \\
+        --seqs=$fasta \\
+        $args
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        cellranger: \$(echo \$( cellranger --version 2>&1) | sed 's/^.*[^0-9]\\([0-9]*\\.[0-9]*\\.[0-9]*\\).*\$/\\1/' )
+    END_VERSIONS
+    """
+}

modules/local/unzip_cellrangerdb.nf

@@ -0,0 +1,29 @@
+process UNZIP_CELLRANGERDB {
+    tag "unzip_cellrangerdb"
+    label 'process_single'
+
+    conda "${moduleDir}/environment.yml"
+    container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
+        'https://depot.galaxyproject.org/singularity/ubuntu:20.04' :
+        'nf-core/ubuntu:20.04' }"
+
+    input:
+    path(archive)
+
+    output:
+    path("$unzipped")   , emit: unzipped
+    path "versions.yml", emit: versions
+
+    script:
+    unzipped = archive.toString() - '.tar.gz'
+    """
+    echo "${unzipped}"
+
+    tar -xzvf ${archive}
+
+    cat <<-END_VERSIONS > versions.yml
+    "${task.process}":
+        unzip_cellrangerdb: \$(echo \$(tar --version 2>&1 | sed 's/^.*(GNU tar) //; s/ Copyright.*\$//')
+    END_VERSIONS
+    """
+}