Merge branch 'dev' of https://github.com/nf-core/airrflow into dev

CHANGELOG.md

@@ -3,7 +3,27 @@
 The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/)
 and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.html).
 
-## [3.1] - 2023-06-05 "Protego"
+## [3.2.0dev] -
+
+### `Added`
+
+- [#268](https://github.com/nf-core/airrflow/pull/268) Added parameters for FindThreshold in `modules.config`.
+- [#268](https://github.com/nf-core/airrflow/pull/268) Validate samplesheet also for `assembled` samplesheet.
+- [#259](https://github.com/nf-core/airrflow/pull/259) Update to `EnchantR v0.1.3`.
+
+### `Fixed`
+
+- [#268](https://github.com/nf-core/airrflow/pull/268) Allows for uppercase and lowercase locus in samplesheet `pcr_target_locus`.
+- [#259](https://github.com/nf-core/airrflow/pull/259) Samplesheet only allows data from one species.
+- [#259](https://github.com/nf-core/airrflow/pull/259) Introduced fix for a too long command with hundreds of datasets.
+
+### `Dependencies`
+
+| Dependency | Old version | New version |
+| ---------- | ----------- | ----------- |
+| r-enchantr | 0.1.2       | 0.1.3       |
+
+## [3.1.0] - 2023-06-05 "Protego"
 
 ### `Added`
 

assets/repertoire_comparison.Rmd

@@ -149,7 +149,8 @@ col_select <- c(
 )
 df_all <- dplyr::bind_rows(lapply(all_files, read_rearrangement, col_select=col_select))
 
-# Remove underscores in these columns (only needed if including clonal abundance and diversity)
+
+# Remove underscores in these columns
 df_all$subject_id <- stringr::str_replace_all(df_all$subject_id, "_", "")
 df_all$sample_id <- stringr::str_replace_all(df_all$sample_id , "_", "")
 

bin/check_samplesheet.py

@@ -46,7 +46,7 @@ def check_samplesheet(file_in, assembled):
     - contains the compulsory fields: sample_id, filename_R1, filename_R2, subject_id, pcr_target_locus, species, single_cell
     - sample ids are unique
     - samples from the same subject come from the same species
-    - pcr_target_locus is "IG" or "TR"
+    - pcr_target_locus is "IG"/"ig" or "TR"/"tr"
     - species is "human" or "mouse"
     """
 

bin/fetch_imgt.sh

@@ -68,15 +68,14 @@ do
     echo "|---- Ig"
     for CHAIN in IGHV IGHD IGHJ IGKV IGKJ IGLV IGLJ
     do
-        URL="http://www.imgt.org/IMGT_GENE-DB/GENElect?query=7.14+${CHAIN}&species=${VALUE}"
+        URL="https://www.imgt.org/genedb/GENElect?query=7.14+${CHAIN}&species=${VALUE}"
         FILE_NAME="${FILE_PATH}/${REPERTOIRE}_${KEY}_${CHAIN}.fasta"
         TMP_FILE="${FILE_NAME}.tmp"
         #echo $URL
         wget $URL -O $TMP_FILE -q
         awk '/<pre>/{i++}/<\/pre>/{j++}{if(j==2){exit}}{if(i==2 && j==1 && $0!~"^<pre>"){print}}' $TMP_FILE > $FILE_NAME
 
         # Checking once that file exists and is not empty (checks IMGT server is online)
-        read file
         if [ -s "$FILE_NAME" ]
         then
             echo "IMGT Fasta file exists and is not empty"
@@ -93,7 +92,7 @@ do
     # V amino acid for Ig
     for CHAIN in IGHV IGKV IGLV
     do
-        URL="http://www.imgt.org/IMGT_GENE-DB/GENElect?query=7.3+${CHAIN}&species=${VALUE}"
+        URL="https://www.imgt.org/genedb/GENElect?query=7.3+${CHAIN}&species=${VALUE}"
         FILE_NAME="${FILE_PATH_AA}/${REPERTOIRE}_aa_${KEY}_${CHAIN}.fasta"
         TMP_FILE="${FILE_NAME}.tmp"
         #echo $URL
@@ -108,7 +107,7 @@ do
     echo "|---- TCR"
     for CHAIN in TRAV TRAJ TRBV TRBD TRBJ TRDV TRDD TRDJ TRGV TRGJ
     do
-        URL="http://www.imgt.org/IMGT_GENE-DB/GENElect?query=7.14+${CHAIN}&species=${VALUE}"
+        URL="https://www.imgt.org/genedb/GENElect?query=7.14+${CHAIN}&species=${VALUE}"
         FILE_NAME="${FILE_PATH}/${REPERTOIRE}_${KEY}_${CHAIN}.fasta"
         TMP_FILE="${FILE_NAME}.tmp"
         #echo $URL
@@ -121,7 +120,7 @@ do
     # V amino acid for TCR
     for CHAIN in TRAV TRBV TRDV TRGV
     do
-        URL="http://www.imgt.org/IMGT_GENE-DB/GENElect?query=7.3+${CHAIN}&species=${VALUE}"
+        URL="https://www.imgt.org/genedb/GENElect?query=7.3+${CHAIN}&species=${VALUE}"
         FILE_NAME="${FILE_PATH_AA}/${REPERTOIRE}_aa_${KEY}_${CHAIN}.fasta"
         TMP_FILE="${FILE_NAME}.tmp"
         #echo $URL
@@ -140,7 +139,7 @@ do
     echo "|---- Ig"
     for CHAIN in IGH IGK IGL
     do
-        URL="http://www.imgt.org/IMGT_GENE-DB/GENElect?query=8.1+${CHAIN}V&species=${VALUE}&IMGTlabel=L-PART1+L-PART2"
+        URL="https://www.imgt.org/genedb/GENElect?query=8.1+${CHAIN}V&species=${VALUE}&IMGTlabel=L-PART1+L-PART2"
         FILE_NAME="${FILE_PATH}/${REPERTOIRE}_${KEY}_${CHAIN}L.fasta"
         TMP_FILE="${FILE_NAME}.tmp"
         #echo $URL
@@ -154,7 +153,7 @@ do
     echo "|---- TCR"
     for CHAIN in TRA TRB TRG TRD
     do
-        URL="http://www.imgt.org/IMGT_GENE-DB/GENElect?query=8.1+${CHAIN}V&species=${VALUE}&IMGTlabel=L-PART1+L-PART2"
+        URL="https://www.imgt.org/genedb/GENElect?query=8.1+${CHAIN}V&species=${VALUE}&IMGTlabel=L-PART1+L-PART2"
         FILE_NAME="${FILE_PATH}/${REPERTOIRE}_${KEY}_${CHAIN}L.fasta"
         TMP_FILE="${FILE_NAME}.tmp"
         #echo $URL
@@ -179,7 +178,7 @@ do
             QUERY=7.5
         fi
 
-        URL="http://www.imgt.org/IMGT_GENE-DB/GENElect?query=${QUERY}+${CHAIN}&species=${VALUE}"
+        URL="https://www.imgt.org/genedb/GENElect?query=${QUERY}+${CHAIN}&species=${VALUE}"
         FILE_NAME="${FILE_PATH}/${REPERTOIRE}_${KEY}_${CHAIN}.fasta"
         TMP_FILE="${FILE_NAME}.tmp"
         #echo $URL
@@ -193,7 +192,7 @@ do
     echo "|---- TCR"
     for CHAIN in TRAC TRBC TRGC TRDC
     do
-        URL="http://www.imgt.org/IMGT_GENE-DB/GENElect?query=14.1+${CHAIN}&species=${VALUE}"
+        URL="https://www.imgt.org/genedb/GENElect?query=14.1+${CHAIN}&species=${VALUE}"
         FILE_NAME="${FILE_PATH}/${REPERTOIRE}_${KEY}_${CHAIN}.fasta"
         TMP_FILE="${FILE_NAME}.tmp"
         #echo $URL
@@ -209,7 +208,7 @@ done
 
 # Write download info
 INFO_FILE=${OUTDIR}/IMGT.yaml
-echo -e "source:  http://www.imgt.org/IMGT_GENE-DB" > $INFO_FILE
+echo -e "source:  https://www.imgt.org/genedb" > $INFO_FILE
 echo -e "date:    ${DATE}" >> $INFO_FILE
 echo -e "species:" >> $INFO_FILE
 for Q in ${SPECIES_QUERY[@]}

conf/modules.config

@@ -420,6 +420,11 @@ process {
             mode: params.publish_dir_mode,
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename }
         ]
+        ext.args = ['findthreshold_method':'gmm',
+            'findthreshold_model':'gamma-norm',
+            'findthreshold_edge':0.9,
+            'findthreshold_cutoff':'user',
+            'findthreshold_spc':0.995]
     }
 
     withName: REPORT_THRESHOLD {
@@ -450,7 +455,7 @@ process {
         ]
         ext.args = ['outname':'', 'model':'hierarchical',
                     'method':'nt', 'linkage':'single',
-                    'skip_convergence':true,
+                    'skip_convergence':false,
                     'outputby':'sample_id', 'min_n':30]
     }
 

docs/usage.md

@@ -116,14 +116,14 @@ The required input file for processing raw BCR or TCR bulk targeted sequencing d
 - `filename` for bulk assembled data: path to `sequences.fasta` file, containing the assembled and error-corrected reads.
 
 
-Assembled bulk and single-cell sequencing data can be processed in the same run and can be provided in the same samplesheet as shown below.
+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`, `subject_id`, `species`, `tissue`, `single_cell`, `pcr_target_locus`, `sex`, `age` and `biomaterial_provider` are required.
 
 An example samplesheet is:
 
-| filename                                                 | species | subject_id | sample_id                         | tissue     | sex  | age | biomaterial_provider | pcr_target_locus | single_cell |
-| -------------------------------------------------------- | ------- | ---------- | --------------------------------- | ---------- | ---- | --- | -------------------- | ---------------- | ----------- |
-| sc5p_v2_hs_PBMC_1k_b_airr_rearrangement.tsv              | human   | subject_x  | sc5p_v2_hs_PBMC_1k_5fb            | PBMC       | NA   | NA  | 10x Genomics         | IG               | TRUE        |
-| bulk-Laserson-2014.fasta                                 | human   | PGP1       | PGP1                              | PBMC       | male | NA  | Laserson-2014        | IG               | FALSE       |
+| filename                                    | species | subject_id | sample_id              | tissue | sex  | age | biomaterial_provider | pcr_target_locus | single_cell |
+| ------------------------------------------- | ------- | ---------- | ---------------------- | ------ | ---- | --- | -------------------- | ---------------- | ----------- |
+| sc5p_v2_hs_PBMC_1k_b_airr_rearrangement.tsv | human   | subject_x  | sc5p_v2_hs_PBMC_1k_5fb | PBMC   | NA   | NA  | 10x Genomics         | IG               | TRUE        |
+| bulk-Laserson-2014.fasta                    | human   | PGP1       | PGP1                   | PBMC   | male | NA  | Laserson-2014        | IG               | FALSE       |
 
 ### Supported AIRR metadata fields
 

modules/local/airrflow_report/airrflow_report.nf

@@ -2,10 +2,10 @@ process AIRRFLOW_REPORT {
     tag "${meta.id}"
     label 'process_high'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     tuple val(meta), path(tab) // sequence tsv table in AIRR format

modules/local/changeo/changeo_parsedb_select.nf

@@ -20,7 +20,7 @@ process CHANGEO_PARSEDB_SELECT {
     script:
     def args = task.ext.args ?: ''
     def args2 = task.ext.args2 ?: ''
-    if (meta.locus == 'IG'){
+    if (meta.locus.toUpperCase() == 'IG'){
         """
         ParseDb.py select -d $tab $args --outname ${meta.id} > ${meta.id}_select_command_log.txt
 
@@ -30,7 +30,7 @@ process CHANGEO_PARSEDB_SELECT {
             changeo: \$( ParseDb.py --version | awk -F' '  '{print \$2}' )
         END_VERSIONS
         """
-    } else if (meta.locus == 'TR'){
+    } else if (meta.locus.toUpperCase() == 'TR'){
         """
         ParseDb.py select -d $tab $args2 --outname ${meta.id} > "${meta.id}_command_log.txt"
 

modules/local/enchantr/collapse_duplicates.nf

@@ -4,10 +4,10 @@ process COLLAPSE_DUPLICATES {
     label 'process_long_parallelized'
     label 'immcantation'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     tuple val(meta), path(tabs) // tuple [val(meta), sequence tsv in AIRR format ]

modules/local/enchantr/define_clones.nf

@@ -21,10 +21,10 @@ process DEFINE_CLONES {
     label 'process_long_parallelized'
     label 'immcantation'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     tuple val(meta), path(tabs) // meta, sequence tsv in AIRR format

modules/local/enchantr/detect_contamination.nf

@@ -5,10 +5,10 @@ process DETECT_CONTAMINATION {
     label 'immcantation'
 
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     path(tabs)

modules/local/enchantr/dowser_lineages.nf

@@ -21,10 +21,10 @@ process DOWSER_LINEAGES {
     label 'process_long_parallelized'
     label 'immcantation'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     tuple val(meta), path(tabs)

modules/local/enchantr/find_threshold.nf

@@ -21,10 +21,10 @@ process FIND_THRESHOLD {
     label 'process_long_parallelized'
     label 'immcantation'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
 
     input:

modules/local/enchantr/remove_chimeric.nf

@@ -5,10 +5,10 @@ process REMOVE_CHIMERIC {
     label 'immcantation'
 
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
 
     input:

modules/local/enchantr/report_file_size.nf

@@ -6,10 +6,10 @@ process REPORT_FILE_SIZE {
     label 'immcantation'
     label 'process_single'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     path logs

modules/local/enchantr/single_cell_qc.nf

@@ -20,10 +20,10 @@ process SINGLE_CELL_QC {
     label 'immcantation'
     label 'process_medium'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     path(tabs)

modules/local/enchantr/validate_input.nf

@@ -6,10 +6,10 @@ process VALIDATE_INPUT {
     label 'immcantation'
     label 'process_single'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     file samplesheet

modules/local/reveal/add_meta_to_tab.nf

@@ -3,10 +3,10 @@ process ADD_META_TO_TAB {
     label 'immcantation'
     label 'process_single'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     cache 'deep' // Without 'deep' this process would run when using -resume
 

modules/local/reveal/filter_junction_mod3.nf

@@ -3,10 +3,10 @@ process FILTER_JUNCTION_MOD3 {
     label 'immcantation'
     label 'process_single'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     tuple val(meta), path(tab) // sequence tsv in AIRR format

modules/local/reveal/filter_quality.nf

@@ -3,10 +3,10 @@ process FILTER_QUALITY {
     label 'immcantation'
     label 'process_single'
 
-    conda "bioconda::r-enchantr=0.1.2"
+    conda "bioconda::r-enchantr=0.1.3"
     container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ?
-        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.2--r42hdfd78af_0':
-        'biocontainers/r-enchantr:0.1.2--r42hdfd78af_0' }"
+        'https://depot.galaxyproject.org/singularity/r-enchantr:0.1.3--r42hdfd78af_0':
+        'biocontainers/r-enchantr:0.1.3--r42hdfd78af_0' }"
 
     input:
     tuple val(meta), path(tab) // sequence tsv in AIRR format