Fix reassign option

.github/workflows/ci.yml

@@ -112,6 +112,7 @@ jobs:
             "test_10x_sc",
             "test_takara_smartseq_umi_bcr",
             "test_nebnext_umi",
+            "test_reassign_false",
             "test_rnaseq_bulk",
             "test_rnaseq_sc",
             "test_maskprimers_extract",

CHANGELOG.md

@@ -25,6 +25,7 @@ and this project adheres to [Semantic Versioning](http://semver.org/spec/v2.0.0.
 - [#416](https://github.com/nf-core/airrflow/pull/416) Fixed bug in number of sequences report.
 - [#416](https://github.com/nf-core/airrflow/pull/416) Fixed bug in report file size.
 - [#422](https://github.com/nf-core/airrflow/pull/422) Fixed annoying automatic clonal threshold message on any failure.
+- Fixed reassign false option and added tests.
 
 ### `Dependencies`
 

bin/reveal_filter_quality.R

@@ -55,9 +55,6 @@ if (packageVersion("alakazam") < "1.0.3") {
     }
 }
 
-# Concordant locus
-same_locus <- getLocus(db[["v_call"]]) == db[["locus"]]
-
 # Max 10% N
 n_count <- stri_count(db$sequence_alignment, regex = "Nn")
 positions_count <- stri_count(db$sequence_alignment, regex = "[^-.]")
@@ -71,18 +68,36 @@ low_n <- n_count <= 0.10
 # Min length 200 nt
 long_seq <- stri_count(db$sequence_alignment, regex = "[^-.Nn]") >= 200
 
-log <- data.frame(
-    "same_locus" = same_locus,
-    "low_n" = low_n,
-    "long_seq" = long_seq, stringsAsFactors = F
-)
+if ("locus" %in% colnames(db)) {
+    # Concordant locus
+    same_locus <- getLocus(db[["v_call"]]) == db[["locus"]]
+
+    # Generate logs and summary
+    log <- data.frame(
+        "same_locus" = same_locus,
+        "low_n" = low_n,
+        "long_seq" = long_seq, stringsAsFactors = F
+    )
+    summary <- log %>%
+        group_by(same_locus, low_n, long_seq) %>%
+        summarize(n = n(), .groups = "drop_last")
+    filter_pass <- same_locus & low_n & long_seq
+} else {
+    db$locus <- getLocus(db[["v_call"]])
 
-summary <- log %>%
-    group_by(same_locus, low_n, long_seq) %>%
-    summarize(n = n(), .groups = "drop_last")
+    # Generate logs and summary
+    log <- data.frame(
+        "low_n" = low_n,
+        "long_seq" = long_seq, stringsAsFactors = F
+    )
+
+    summary <- log %>%
+        group_by(low_n, long_seq) %>%
+        summarize(n = n(), .groups = "drop_last")
+
+    filter_pass <- low_n & long_seq
+}
 
-# Filter and save
-filter_pass <- same_locus & low_n & long_seq
 
 if (!is.null(opt$OUTPUT)) {
     output_fn <- paste0(opt$OUTPUT, "_quality-pass.tsv")

conf/test_reassign_false.config

@@ -0,0 +1,32 @@
+/*
+ * -------------------------------------------------
+ *  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_reassign_false,<docker/singularity>
+ */
+
+process {
+    resourceLimits = [
+        cpus: 4,
+        memory: '15.GB',
+        time: '1.h'
+    ]
+}
+
+params {
+    config_profile_name        = 'Test assembled mode'
+    config_profile_description = 'Minimal test dataset to test assembled mode'
+
+    // Input data
+    mode = 'assembled'
+    input = pipelines_testdata_base_path + 'testdata-reveal/test_assembled_metadata_assigned.tsv'
+    reference_fasta = pipelines_testdata_base_path + 'database-cache/imgtdb_base.zip'
+    reference_igblast = pipelines_testdata_base_path + 'database-cache/igblast_base.zip'
+
+    reassign = false
+    productive_only = true
+    collapseby = 'filename'
+    cloneby = 'subject_id'
+}

nextflow.config

@@ -321,6 +321,7 @@ profiles {
     test_maskprimers_extract { includeConfig 'conf/test_maskprimers_extract.config' }
     test_maskprimers_align {includeConfig 'conf/test_maskprimers_align.config' }
     test_nebnext_umi { includeConfig 'conf/test_nebnext_umi.config' }
+    test_reassign_false { includeConfig 'conf/test_reassign_false.config' }
     test_rnaseq_bulk { includeConfig 'conf/test_rnaseq_bulk.config' }
     test_rnaseq_sc { includeConfig 'conf/test_rnaseq_sc.config' }
     test_embeddings_H { includeConfig 'conf/test_embeddings_H.config' }

subworkflows/local/vdj_annotation.nf

@@ -11,6 +11,7 @@ workflow VDJ_ANNOTATION {
 
     take:
     ch_fasta // [meta, fasta]
+    ch_tsv // [meta, tsv]
     ch_validated_samplesheet
     ch_igblast
     ch_reference_fasta
@@ -35,7 +36,8 @@ workflow VDJ_ANNOTATION {
     ch_logs = ch_logs.mix(CHANGEO_MAKEDB.out.logs)
     ch_versions = ch_versions.mix(CHANGEO_MAKEDB.out.versions)
 
-    ch_assigned_tab = CHANGEO_MAKEDB.out.tab
+    ch_assigned_tab = ch_tsv.mix(CHANGEO_MAKEDB.out.tab)
+
     ch_assignment_logs = CHANGEO_MAKEDB.out.logs
 
     if (!params.skip_alignment_filter){

workflows/airrflow.nf

@@ -97,51 +97,52 @@ workflow AIRRFLOW {
 
                 ch_validated_samplesheet                = SC_RAW_INPUT.out.samplesheet.collect()
 
-            ch_presto_filterseq_logs                = Channel.empty()
-            ch_presto_maskprimers_logs              = Channel.empty()
-            ch_presto_pairseq_logs                  = Channel.empty()
-            ch_presto_clustersets_logs              = Channel.empty()
-            ch_presto_buildconsensus_logs           = Channel.empty()
-            ch_presto_postconsensus_pairseq_logs    = Channel.empty()
-            ch_presto_assemblepairs_logs            = Channel.empty()
-            ch_presto_collapseseq_logs              = Channel.empty()
-            ch_presto_splitseq_logs                 = Channel.empty()
-            ch_fastp_html                           = Channel.empty()
-            ch_fastp_json                           = Channel.empty()
-            ch_fastqc_postassembly_mqc              = Channel.empty()
-
-        }  else if (params.library_generation_method == "trust4") {
-            // Extract VDJ sequences from "general" RNA seq data using TRUST4
-
-            RNASEQ_INPUT (
-                ch_input,
-                DATABASES.out.igblast.collect()
-            )
+                ch_presto_filterseq_logs                = Channel.empty()
+                ch_presto_maskprimers_logs              = Channel.empty()
+                ch_presto_pairseq_logs                  = Channel.empty()
+                ch_presto_clustersets_logs              = Channel.empty()
+                ch_presto_buildconsensus_logs           = Channel.empty()
+                ch_presto_postconsensus_pairseq_logs    = Channel.empty()
+                ch_presto_assemblepairs_logs            = Channel.empty()
+                ch_presto_collapseseq_logs              = Channel.empty()
+                ch_presto_splitseq_logs                 = Channel.empty()
+                ch_fastp_html                           = Channel.empty()
+                ch_fastp_json                           = Channel.empty()
+                ch_fastqc_postassembly_mqc              = Channel.empty()
+                ch_tsv_files                            = Channel.empty()
+
+            }  else if (params.library_generation_method == "trust4") {
+                // Extract VDJ sequences from "general" RNA seq data using TRUST4
+
+                RNASEQ_INPUT (
+                    ch_input,
+                    DATABASES.out.igblast.collect()
+                )
 
-            ch_fasta                                = RNASEQ_INPUT.out.fasta
-            ch_versions                             = ch_versions.mix(RNASEQ_INPUT.out.versions)
-
-            ch_validated_samplesheet                = RNASEQ_INPUT.out.samplesheet.collect()
-
-            ch_presto_filterseq_logs                = Channel.empty()
-            ch_presto_maskprimers_logs              = Channel.empty()
-            ch_presto_pairseq_logs                  = Channel.empty()
-            ch_presto_clustersets_logs              = Channel.empty()
-            ch_presto_buildconsensus_logs           = Channel.empty()
-            ch_presto_postconsensus_pairseq_logs    = Channel.empty()
-            ch_presto_assemblepairs_logs            = Channel.empty()
-            ch_presto_collapseseq_logs              = Channel.empty()
-            ch_presto_splitseq_logs                 = Channel.empty()
-            ch_fastp_html                           = RNASEQ_INPUT.out.fastp_reads_html
-            ch_fastp_json                           = RNASEQ_INPUT.out.fastp_reads_json
-            ch_fastqc_postassembly_mqc              = Channel.empty()
-        }
-        else {
-            // Perform sequence assembly if input type is fastq from bulk sequencing data
-            SEQUENCE_ASSEMBLY(
-                ch_input,
-                DATABASES.out.igblast.collect()
-            )
+                ch_fasta                                = RNASEQ_INPUT.out.fasta
+                ch_versions                             = ch_versions.mix(RNASEQ_INPUT.out.versions)
+
+                ch_validated_samplesheet                = RNASEQ_INPUT.out.samplesheet.collect()
+
+                ch_presto_filterseq_logs                = Channel.empty()
+                ch_presto_maskprimers_logs              = Channel.empty()
+                ch_presto_pairseq_logs                  = Channel.empty()
+                ch_presto_clustersets_logs              = Channel.empty()
+                ch_presto_buildconsensus_logs           = Channel.empty()
+                ch_presto_postconsensus_pairseq_logs    = Channel.empty()
+                ch_presto_assemblepairs_logs            = Channel.empty()
+                ch_presto_collapseseq_logs              = Channel.empty()
+                ch_presto_splitseq_logs                 = Channel.empty()
+                ch_fastp_html                           = RNASEQ_INPUT.out.fastp_reads_html
+                ch_fastp_json                           = RNASEQ_INPUT.out.fastp_reads_json
+                ch_fastqc_postassembly_mqc              = Channel.empty()
+                ch_tsv_files                            = Channel.empty()
+            } else {
+                // Perform sequence assembly if input type is fastq from bulk sequencing data
+                SEQUENCE_ASSEMBLY(
+                    ch_input,
+                    DATABASES.out.igblast.collect()
+                )
 
                 ch_fasta                                = SEQUENCE_ASSEMBLY.out.fasta
                 ch_versions                             = ch_versions.mix(SEQUENCE_ASSEMBLY.out.versions)
@@ -158,6 +159,7 @@ workflow AIRRFLOW {
                 ch_presto_assemblepairs_logs            = SEQUENCE_ASSEMBLY.out.presto_assemblepairs_logs.ifEmpty([])
                 ch_presto_collapseseq_logs              = SEQUENCE_ASSEMBLY.out.presto_collapseseq_logs.ifEmpty([])
                 ch_presto_splitseq_logs                 = SEQUENCE_ASSEMBLY.out.presto_splitseq_logs.ifEmpty([])
+                ch_tsv_files                            = Channel.empty()
             }
 
         } else if ( params.mode == "assembled" ) {
@@ -178,8 +180,10 @@ workflow AIRRFLOW {
                 ch_fasta_from_tsv = CHANGEO_CONVERTDB_FASTA_FROM_AIRR.out.fasta
                 ch_versions = ch_versions.mix(CHANGEO_CONVERTDB_FASTA_FROM_AIRR.out.versions)
                 ch_reassign_logs = ch_reassign_logs.mix(CHANGEO_CONVERTDB_FASTA_FROM_AIRR.out.logs)
+                ch_tsv_files = Channel.empty()
             } else {
                 ch_fasta_from_tsv = Channel.empty()
+                ch_tsv_files = ASSEMBLED_INPUT_CHECK.out.ch_tsv
             }
 
             ch_fasta = ASSEMBLED_INPUT_CHECK.out.ch_fasta.mix(ch_fasta_from_tsv)
@@ -201,9 +205,11 @@ workflow AIRRFLOW {
         } else {
             error "Mode parameter value not valid."
         }
+
         // Perform V(D)J annotation and filtering
         VDJ_ANNOTATION(
             ch_fasta,
+            ch_tsv_files,
             ch_validated_samplesheet.collect(),
             DATABASES.out.igblast.collect(),
             DATABASES.out.reference_fasta.collect()