feat allow user to provide sample annotation

genomic-medicine-sweden · Aug 6, 2023 · f6111c3 · f6111c3
1 parent 780fd70
commit f6111c3
Show file tree

Hide file tree

Showing 5 changed files with 30 additions and 6 deletions.
diff --git a/conf/modules.config b/conf/modules.config
@@ -314,6 +314,15 @@ process {
             saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
         ]
     }
+
+    withName: '.*ANALYSE_TRANSCRIPTS:DROP_ANNOTATION' {
+        ext.when = {!params.drop_annot_file}
+        publishDir = [
+            path: { "${params.outdir}/analyse_transcripts" },
+            mode: params.publish_dir_mode,
+            saveAs: { filename -> filename.equals('versions.yml') ? null : filename },
+        ]
+    }
 
     withName: '.*ANALYSE_TRANSCRIPTS:DROP_CONFIG_RUN_AE' {
         publishDir = [

diff --git a/nextflow.config b/nextflow.config
@@ -36,6 +36,7 @@ params {
     variant_caller             = 'bcftools'
     bcftools_caller_mode       = 'multiallelic'
     run_drop_ae                = true
+    drop_annot_file            = null
 
     // MultiQC options
     multiqc_config             = null

diff --git a/nextflow_schema.json b/nextflow_schema.json
@@ -262,6 +262,14 @@
                     "description": "Should DROP Aberrant Expression module be run?",
                     "fa_icon": "fas fa-toggle-off"
                 },
+                "drop_annot_file": {
+                    "type": "string",
+                    "default": "None",
+                    "description": "Path to a tsv file containing sample annotation for DROP. If it is not provided, it will be generated.",
+                    "fa_icon": "fas fa-file",
+                    "format": "file-path",
+                    "mimetype": "tsv"
+                },
                 "reference_count_file": {
                     "type": "string",
                     "default": "None",

diff --git a/subworkflows/local/analyse_transcripts.nf b/subworkflows/local/analyse_transcripts.nf
@@ -15,6 +15,7 @@ workflow ANALYSE_TRANSCRIPTS {
         ch_fasta_fai_meta    // channel (mandatory): [ val(meta), [ path(fasta), path(fai) ]
         gene_counts          // channel [val(meta), path(tsv)] 
         reference_count_file // channel [ path(tsv) ]
+        drop_annot_file      // channel [ path(tsv) ]
 
     main:
         ch_versions = Channel.empty()
@@ -25,14 +26,15 @@ workflow ANALYSE_TRANSCRIPTS {
         star_samp  = gene_counts.map{ meta, cnt_file -> meta }.collect()
         DROP_COUNTS(star_count, star_samp, ch_gtf, reference_count_file)
 
-        // Annotation file
+        // Generates sample annotation file is it hasn't been provided by user
         DROP_ANNOTATION(DROP_COUNTS.out.processed_gene_counts, ch_gtf)
-
-        // Config file
+        ch_samp_annot = drop_annot_file.mix(DROP_ANNOTATION.out.sample_annotation_drop)
+
+        // Generates  config file and runs Aberrant expression module
         DROP_CONFIG_RUN_AE(
             ch_fasta_fai_meta, 
             ch_gtf, 
-            DROP_ANNOTATION.out.sample_annotation_drop,
+            ch_samp_annot,
             DROP_COUNTS.out.processed_gene_counts
         )
 
@@ -62,7 +64,7 @@ workflow ANALYSE_TRANSCRIPTS {
         annotated_gtf         = GFFCOMPARE.out.annotated_gtf               // channel: [ val(meta), [ path(annotated_gtf) ] ]
         stats_gtf             = GFFCOMPARE.out.stats                       // channel: [ val(meta), [ path(stats) ] ]
         processed_gene_counts = DROP_COUNTS.out.processed_gene_counts      // channel: [ path(tsv) ]
-        annotation_drop       = DROP_ANNOTATION.out.sample_annotation_drop // channel: [ path(tsv) ]
+        annotation_drop       = ch_samp_annot                              // channel: [ path(tsv) ]
         config_drop           = DROP_CONFIG_RUN_AE.out.config_drop         // channel: [ path(confg_file.yml) ]
         drop_ae_out           = DROP_CONFIG_RUN_AE.out.drop_ae_out
         versions              = ch_versions                                // channel: [ path(versions.yml) ]

diff --git a/workflows/tomte.nf b/workflows/tomte.nf
@@ -27,6 +27,7 @@ def checkPathParamList = [
     params.salmon_index,
     params.transcript_fasta,
     params.gtf,
+    params.drop_annot_file,
     params.reference_count_file,
     params.subsample_bed,
     params.vep_filters,
@@ -117,6 +118,8 @@ workflow TOMTE {
                                                                 : Channel.empty()
     ch_reference_count_file  = params.reference_count_file      ? Channel.fromPath(params.reference_count_file).collect()
                                                                 : Channel.empty()
+    ch_drop_annot_filee      = params.drop_annot_file           ? Channel.fromPath(params.drop_annot_file).collect()
+                                                                : Channel.empty()
 
     PREPARE_REFERENCES(
         fasta,
@@ -179,7 +182,8 @@ workflow TOMTE {
         ch_references.gtf,
         ch_references.fasta_fai_meta,
         ch_alignment.gene_counts,
-        ch_reference_count_file
+        ch_reference_count_file,
+        ch_drop_annot_filee
     )
     ch_versions = ch_versions.mix(ANALYSE_TRANSCRIPTS.out.versions)