nf-core · ggabernet · Apr 23, 2024 · Apr 22, 2024 · Apr 23, 2024 · Apr 23, 2024
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -25,6 +25,8 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 
 - `--skip_lineage_trees` is now deprecated in favor of `--lineage_trees`. Lineage trees are skipped by default.
 - `--igphyml` parameter is deprecated in favor of `--lineage_tree_exec`. All lineage tree building software part of Dowser are now supported.
+- `--igblast_base` is deprecated in favor of `--reference_igblast`.
+- `--imgtdb_base` is depracated in favor of `--reference_fasta`.
 
 ## [3.3.0] - 2024-03-31 Confringo
 

diff --git a/README.md b/README.md
@@ -59,7 +59,7 @@ nf-core/airrflow allows the end-to-end processing of BCR and TCR bulk and single
 
 2. V(D)J annotation and filtering (bulk and single-cell)
 
-- Assign gene segments with `IgBlast` using the IMGT database (`Change-O AssignGenes`).
+- Assign gene segments with `IgBlast` using a germline reference (`Change-O AssignGenes`).
 - Annotate alignments in AIRR format (`Change-O MakeDB`)
 - Filter by alignment quality (locus matching v_call chain, min 200 informative positions, max 10% N nucleotides)
 - Filter productive sequences (`Change-O ParseDB split`)

diff --git a/conf/test.config b/conf/test.config
@@ -23,8 +23,8 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/C_primers.fasta'
     vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/V_primers.fasta'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     mode = 'fastq'
 

diff --git a/conf/test_assembled_hs.config b/conf/test_assembled_hs.config
@@ -19,8 +19,8 @@ params {
     // Input data
     mode = 'assembled'
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-reveal/test_assembled_metadata_hs.tsv'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     reassign = true
     productive_only = true

diff --git a/conf/test_assembled_immcantation_devel_hs.config b/conf/test_assembled_immcantation_devel_hs.config
@@ -19,8 +19,8 @@ params {
     // Input data
     mode = 'assembled'
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-reveal/test_assembled_metadata_hs.tsv'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     reassign = true
     productive_only = true

diff --git a/conf/test_assembled_immcantation_devel_mm.config b/conf/test_assembled_immcantation_devel_mm.config
@@ -19,8 +19,8 @@ params {
     // Input data
     mode = 'assembled'
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-reveal/test_assembled_metadata_mm.tsv'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     reassign = true
     productive_only = true

diff --git a/conf/test_assembled_mm.config b/conf/test_assembled_mm.config
@@ -19,8 +19,8 @@ params {
     // Input data
     mode = 'assembled'
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-reveal/test_assembled_metadata_mm.tsv'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     reassign = true
     productive_only = true

diff --git a/conf/test_clontech_umi.config b/conf/test_clontech_umi.config
@@ -23,8 +23,8 @@ params {
     // Input data
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-clontech/samplesheet.tsv'
 
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     clonal_threshold = 0.1
 

diff --git a/conf/test_full.config b/conf/test_full.config
@@ -18,8 +18,8 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/metadata_pcr_umi_airr_300.tsv'
     cprimers = 's3://ngi-igenomes/test-data/airrflow/pcr_umi/cprimers.fasta'
     vprimers = 's3://ngi-igenomes/test-data/airrflow/pcr_umi/vprimers.fasta'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     lineage_trees = true
 
@@ -29,7 +29,6 @@ params {
     umi_length = 15
     umi_start = 0
     umi_position = 'R1'
-
     isotype_column = 'c_primer'
 }
 
@@ -43,7 +42,7 @@ process {
     withName:DEFINE_CLONES_COMPUTE{
         ext.args = ['outname':'', 'model':'hierarchical',
                     'method':'nt', 'linkage':'single',
-                    'min_n':30, 'isotype_column':'c_primer']
+                    'min_n':30]
 
     }
     withName:DEFINE_CLONES_REPORT{

diff --git a/conf/test_nebnext_umi.config b/conf/test_nebnext_umi.config
@@ -24,8 +24,8 @@ params {
     // Input data
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-neb/samplesheet.tsv'
 
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     clonal_threshold = 0.1
 

diff --git a/conf/test_no_umi.config b/conf/test_no_umi.config
@@ -30,8 +30,8 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-no-umi/Metadata_test-no-umi_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-no-umi/Greiff2014_CPrimers.fasta'
     vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-no-umi/Greiff2014_VPrimers.fasta'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
 
 }

diff --git a/conf/test_nocluster.config b/conf/test_nocluster.config
@@ -23,8 +23,8 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/Metadata_test_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/C_primers.fasta'
     vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/V_primers.fasta'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     mode = 'fastq'
 

diff --git a/conf/test_raw_immcantation_devel.config b/conf/test_raw_immcantation_devel.config
@@ -24,8 +24,8 @@ params {
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/C_primers.fasta'
     vprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-bcr/V_primers.fasta'
 
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
     mode = 'fastq'
 

diff --git a/conf/test_tcr.config b/conf/test_tcr.config
@@ -31,8 +31,8 @@ params {
     input = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-tcr/TCR_metadata_airr.tsv'
     cprimers = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-tcr/cprimers.fasta'
     race_linker = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/testdata-tcr/linker.fasta'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
 
 }
 

diff --git a/docs/output.md b/docs/output.md
@@ -245,7 +245,7 @@ generate a `.fasta` file from the rearrangement table.
 
 </details>
 
-Assign genes with Igblast, using the IMGT database is performed by the [AssignGenes](https://changeo.readthedocs.io/en/stable/examples/igblast.html#running-igblast) command of the Change-O tool from the Immcantation Framework.
+Assign genes with Igblast, using the a germline reference is performed by the [AssignGenes](https://changeo.readthedocs.io/en/stable/examples/igblast.html#running-igblast) command of the Change-O tool from the Immcantation Framework.
 
 ### Make database from assigned genes
 
@@ -482,7 +482,7 @@ Parsing the logs from the previous processes. Summary of the number of sequences
 
 Copy of the downloaded IMGT database by the process `fetch_databases`, used for the gene assignment step.
 
-If databases are provided with `--imgtdb_base` and `--igblast_base` this folder will not be present.
+If databases are provided with `--reference_fasta` and `--reference_igblast` this folder will not be present.
 
 ## MultiQC
 

diff --git a/modules/local/changeo/changeo_creategermlines.nf b/modules/local/changeo/changeo_creategermlines.nf
@@ -11,7 +11,7 @@ process CHANGEO_CREATEGERMLINES {
 
     input:
     tuple val(meta), path(tab) // sequence tsv table in AIRR format
-    path(imgt_base) // imgt db
+    path(reference_fasta) // reference fasta
 
     output:
     tuple val(meta), path("*germ-pass.tsv"), emit: tab
@@ -22,7 +22,7 @@ process CHANGEO_CREATEGERMLINES {
     def args = task.ext.args ?: ''
     """
     CreateGermlines.py -d ${tab} \\
-    -r ${imgt_base}/${meta.species}/vdj/ \\
+    -r ${reference_fasta}/${meta.species}/vdj/ \\
     -g dmask --format airr \\
     --log ${meta.id}.log --outname ${meta.id} $args > ${meta.id}_create-germlines_command_log.txt
     ParseLog.py -l ${meta.id}.log -f ID V_CALL D_CALL J_CALL

diff --git a/modules/local/changeo/changeo_makedb.nf b/modules/local/changeo/changeo_makedb.nf
@@ -6,14 +6,13 @@ process CHANGEO_MAKEDB {
 
     conda "bioconda::changeo=1.3.0 bioconda::igblast=1.22.0 conda-forge::wget=1.20.1"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-    //TODO: update mulled containers when available
         'https://depot.galaxyproject.org/singularity/mulled-v2-7d8e418eb73acc6a80daea8e111c94cf19a4ecfd:a9ee25632c9b10bbb012da76e6eb539acca8f9cd-1' :
         'biocontainers/mulled-v2-7d8e418eb73acc6a80daea8e111c94cf19a4ecfd:a9ee25632c9b10bbb012da76e6eb539acca8f9cd-1' }"
 
     input:
     tuple val(meta), path(reads) // reads in fasta format
     path(igblast) // igblast fasta from ch_igblast_db_for_process_igblast.mix(ch_igblast_db_for_process_igblast_mix).collect()
-    path(imgt_base)
+    path(reference_fasta)
 
     output:
     tuple val(meta), path("*db-pass.tsv"), emit: tab //sequence table in AIRR format
@@ -24,7 +23,7 @@ process CHANGEO_MAKEDB {
     def args = task.ext.args ?: ''
     """
     MakeDb.py igblast -i $igblast -s $reads -r \\
-    ${imgt_base}/${meta.species.toLowerCase()}/vdj/ \\
+    ${reference_fasta}/${meta.species.toLowerCase()}/vdj/ \\
     $args \\
     --outname ${meta.id} > ${meta.id}_makedb_command_log.txt
 

diff --git a/modules/local/enchantr/define_clones.nf b/modules/local/enchantr/define_clones.nf
@@ -31,7 +31,7 @@ process DEFINE_CLONES {
     input:
     tuple val(meta), path(tabs) // meta, sequence tsv in AIRR format
     val threshold
-    path imgt_base
+    path reference_fasta
     path repertoires_samplesheet
 
     output:
@@ -53,7 +53,7 @@ process DEFINE_CLONES {
     """
     Rscript -e "enchantr::enchantr_report('define_clones', \\
                                         report_params=list('input'='${input}', \\
-                                        'imgt_db'='${imgt_base}', \\
+                                        'imgt_db'='${reference_fasta}', \\
                                         'species'='auto', \\
                                         'cloneby'='${params.cloneby}', \\
                                         'outputby'='${params.cloneby}', \\

diff --git a/modules/local/enchantr/remove_chimeric.nf b/modules/local/enchantr/remove_chimeric.nf
@@ -15,7 +15,7 @@ process REMOVE_CHIMERIC {
 
     input:
     tuple val(meta), path(tab) // sequence tsv in AIRR format
-    path(imgt_base)
+    path(reference_fasta)
 
     output:
     tuple val(meta), path("*chimera-pass.tsv"), emit: tab // sequence tsv in AIRR format

diff --git a/modules/local/fetch_databases.nf b/modules/local/fetch_databases.nf
@@ -10,7 +10,7 @@ process FETCH_DATABASES {
 
     output:
     path("igblast_base"), emit: igblast
-    path("imgtdb_base"), emit: imgt
+    path("imgtdb_base"), emit: reference_fasta
     path "versions.yml" , emit: versions
     path("igblast_base/database/imgt_human_ig_v.ndb"), emit: igblast_human_ig_v
     path("igblast_base/database/imgt_human_ig_d.ndb"), emit: igblast_human_ig_d

diff --git a/nextflow.config b/nextflow.config
@@ -81,8 +81,8 @@ params {
     // -----------------------
     productive_only = true
     reassign = true
-    igblast_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
-    imgtdb_base = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
+    reference_igblast = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/igblast_base.zip'
+    reference_fasta = 'https://raw.githubusercontent.com/nf-core/test-datasets/airrflow/database-cache/imgtdb_base.zip'
     fetch_imgt = false
     save_databases = true
     isotype_column = 'c_call'

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -338,16 +338,16 @@
                     "description": "Save databases so you can use the cache in future runs.",
                     "fa_icon": "fas fa-file-download"
                 },
-                "imgtdb_base": {
+                "reference_fasta": {
                     "type": "string",
-                    "description": "Path to the cached IMGT database.",
-                    "help_text": "By default, we provide a pre-downloaded version of the IMGT database. It is also possible to provide a custom IMGT reference database. To fetch a fresh version of IMGT, set the `--fetch_imgt` parameter instead.",
+                    "description": "Path to the germline reference fasta.",
+                    "help_text": "By default, we provide a pre-downloaded version of the IMGT database. It is also possible to provide a custom reference fasta database. To fetch a fresh version of IMGT, set the `--fetch_imgt` parameter instead.",
                     "fa_icon": "fas fa-database"
                 },
-                "igblast_base": {
+                "reference_igblast": {
                     "type": "string",
                     "description": "Path to the cached igblast database.",
-                    "help_text": "By default, we provide a pre-downloaded version of the IMGT database. It is also possible to provide a custom IMGT reference database. To fetch a fresh version of IMGT, set the `--fetch_imgt` parameter instead.",
+                    "help_text": "By default, we provide a pre-downloaded version of the IMGT database. It is also possible to provide a custom reference fasta database. To fetch a fresh version of IMGT, set the `--fetch_imgt` parameter instead.",
                     "fa_icon": "fas fa-database"
                 },
                 "fetch_imgt": {

diff --git a/subworkflows/local/bulk_qc_and_filter.nf b/subworkflows/local/bulk_qc_and_filter.nf
@@ -7,7 +7,7 @@ workflow BULK_QC_AND_FILTER {
 
     take:
     ch_repertoire // tuple [meta, repertoire_tab]
-    ch_imgt
+    ch_reference_fasta
 
     main:
 
@@ -20,15 +20,15 @@ workflow BULK_QC_AND_FILTER {
         // Create germlines (not --cloned)
         CHANGEO_CREATEGERMLINES(
             ch_repertoire,
-            ch_imgt.collect()
+            ch_reference_fasta.collect()
         )
         ch_logs = ch_logs.mix(CHANGEO_CREATEGERMLINES.out.logs)
         ch_versions = ch_versions.mix(CHANGEO_CREATEGERMLINES.out.versions)
 
         // Remove chimera
         REMOVE_CHIMERIC(
             CHANGEO_CREATEGERMLINES.out.tab,
-            ch_imgt.collect()
+            ch_reference_fasta.collect()
         )
         ch_logs = ch_logs.mix(REMOVE_CHIMERIC.out.logs)
         ch_versions = ch_versions.mix(REMOVE_CHIMERIC.out.versions)

diff --git a/subworkflows/local/clonal_analysis.nf b/subworkflows/local/clonal_analysis.nf
@@ -7,7 +7,7 @@ include { DOWSER_LINEAGES } from '../../modules/local/enchantr/dowser_lineages'
 workflow CLONAL_ANALYSIS {
     take:
     ch_repertoire
-    ch_imgt
+    ch_reference_fasta
     ch_logo
 
     main:
@@ -76,7 +76,7 @@ workflow CLONAL_ANALYSIS {
     DEFINE_CLONES_COMPUTE(
         ch_define_clones,
         clone_threshold.collect(),
-        ch_imgt.collect(),
+        ch_reference_fasta.collect(),
         []
     )
 
@@ -102,7 +102,7 @@ workflow CLONAL_ANALYSIS {
         DEFINE_CLONES_REPORT(
             ch_all_repertoires_cloned,
             clone_threshold.collect(),
-            ch_imgt.collect(),
+            ch_reference_fasta.collect(),
             ch_all_repertoires_cloned_samplesheet
         )
         ch_versions = DEFINE_CLONES_REPORT.out.versions