Merge branch 'CW-2680' into 'dev'

deal with transcriptome fasta headers that contains |

Closes CW-2680

See merge request epi2melabs/workflows/wf-transcriptomes!124

.gitlab-ci.yml

@@ -45,7 +45,8 @@ docker-run:
             - MATRIX_NAME: [
                 "fusions", "differential_expression", "isoforms",
                 "only_differential_expression", "differential_expression_gff3",
-                "ncbi_gzip", "denovo", "ncbi_no_gene_id", "ensembl_with_versions"
+                "ncbi_gzip", "denovo", "ncbi_no_gene_id", "ensembl_with_versions",
+                "differential_expression_mouse"
             ]
     rules:
         # NOTE As we're overriding the rules block for the included docker-run
@@ -58,18 +59,18 @@ docker-run:
               NF_BEFORE_SCRIPT: wget -O test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf  test_data.tar.gz
               NF_WORKFLOW_OPTS: "--fastq  ERR6053095_chr20.fastq --transcriptome-source reference-guided \
                   --ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf"
-              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref
+              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
         - if: $MATRIX_NAME == "denovo"
           variables:
               NF_WORKFLOW_OPTS: "--fastq test_data/fastq/SIRV_E0_PCS109_50.fq.gz --transcriptome_source denovo"
-              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,build_minimap_index
+              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,build_minimap_index,decompress_transcriptome,preprocess_ref_transcriptome
         - if: $MATRIX_NAME == "fusions"
           variables:
               NF_BEFORE_SCRIPT: wget -O test_data.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/wf-isoforms_test_data.tar.gz && tar -xzvf  test_data.tar.gz
               NF_WORKFLOW_OPTS: "--fastq  ERR6053095_chr20.fastq --transcriptome-source reference-guided \
                   --ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf \
                   --jaffal_refBase chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22"
-              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref
+              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
         - if: $MATRIX_NAME == "differential_expression"
           variables:
               NF_BEFORE_SCRIPT: wget -O differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf differential_expression.tar.gz
@@ -78,7 +79,7 @@ docker-run:
                   --ref_genome differential_expression/hg38_chr20.fa --transcriptome-source reference-guided \
                 --ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
                 --direct_rna --minimap2_index_opts '-k 15'  --sample_sheet test_data/sample_sheet.csv"
-              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref
+              NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
         - if: $MATRIX_NAME == "only_differential_expression"
           variables:
               NF_BEFORE_SCRIPT: wget -O differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf differential_expression.tar.gz
@@ -92,7 +93,7 @@ docker-run:
                 --sample_sheet test_data/sample_sheet.csv"
               NF_IGNORE_PROCESSES: >
                 preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,decompress_ref,
-                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam
+                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome
         - if: $MATRIX_NAME == "differential_expression_gff3"
           variables:
               NF_BEFORE_SCRIPT: wget -O differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf differential_expression.tar.gz
@@ -106,7 +107,7 @@ docker-run:
                 --sample_sheet test_data/sample_sheet.csv"
               NF_IGNORE_PROCESSES: >
                 preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,decompress_ref,
-                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam
+                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome
         - if: $MATRIX_NAME == "ncbi_gzip"
           variables:
               NF_BEFORE_SCRIPT: wget -O differential_expression_ncbi.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression_ncbi.tar.gz && tar -xzvf differential_expression_ncbi.tar.gz
@@ -120,7 +121,7 @@ docker-run:
                --sample_sheet test_data/sample_sheet.csv"
               NF_IGNORE_PROCESSES: >
                 preprocess_reads,merge_transcriptomes,assemble_transcripts,
-                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam           
+                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome           
         - if: $MATRIX_NAME == "ncbi_no_gene_id"
           variables:
               NF_BEFORE_SCRIPT: wget -O differential_expression_ncbi.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression_ncbi.tar.gz && tar -xzvf differential_expression_ncbi.tar.gz
@@ -133,7 +134,7 @@ docker-run:
                 --transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv"
               NF_IGNORE_PROCESSES: >
                 preprocess_reads,merge_transcriptomes,assemble_transcripts,
-                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam           
+                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome      
         - if: $MATRIX_NAME == "ensembl_with_versions"
           variables:
               NF_BEFORE_SCRIPT: wget -O differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf differential_expression.tar.gz
@@ -146,4 +147,17 @@ docker-run:
                 --transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv"
               NF_IGNORE_PROCESSES: >
                 preprocess_reads,merge_transcriptomes,assemble_transcripts,
-                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam           
+                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam,decompress_transcriptome,preprocess_ref_transcriptome
+        - if: $MATRIX_NAME == "differential_expression_mouse"
+          variables:
+              NF_BEFORE_SCRIPT: wget -O differential_expression_mouse.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression_mouse.tar.gz && tar -xzvf differential_expression_mouse.tar.gz
+              NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
+                --fastq differential_expression_mouse/differential_expression_fastq \
+                --transcriptome-source precomputed --de_analysis \
+                --ref_genome differential_expression_mouse/GRCm39.genome.fa.gz \
+                --ref_annotation differential_expression_mouse/gencode.vM33.annotation.gtf \
+                --direct_rna --ref_transcriptome differential_expression_mouse/gencode.vM33.transcripts.fa.gz \
+                --transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv"
+              NF_IGNORE_PROCESSES: >
+                preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,
+                build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam    

CHANGELOG.md

@@ -4,6 +4,10 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [v0.3.1]
+### Added
+- Handling for input reference transcriptome headers that contain `|`
+
 ## [v0.3.0]
 ### Changed
 - Improve differential expression outputs.

README.md

@@ -245,12 +245,13 @@ nextflow run epi2me-labs/wf-transcriptomes \
   --ref_transcriptome differential_expression/ref_transcriptome.fasta \
   --sample_sheet test_data/sample_sheet.csv
 ```
-You can also run the differential expression section of the workflow on its own by providing a reference transcriptome and setting the transcriptome assembly parameter to false.
+You can also run the differential expression section of the workflow on its own by providing a reference transcriptome and setting the `--transcriptome_source` to precomputed.
 eg.
 ```
 nextflow run epi2me-labs/wf-transcriptomes \
   --fastq  differential_expression/differential_expression_fastq \
   --de_analysis \
+  --transcriptome_source precomputed \
   --ref_genome differential_expression/hg38_chr20.fa \
   --ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
   --direct_rna --minimap2_index_opts '-k 15' \

docs/quickstart.md

@@ -155,12 +155,13 @@ nextflow run epi2me-labs/wf-transcriptomes \
   --ref_transcriptome differential_expression/ref_transcriptome.fasta \
   --sample_sheet test_data/sample_sheet.csv
 ```
-You can also run the differential expression section of the workflow on its own by providing a reference transcriptome and setting the transcriptome assembly parameter to false.
+You can also run the differential expression section of the workflow on its own by providing a reference transcriptome and setting the `--transcriptome_source` to precomputed.
 eg.
 ```
 nextflow run epi2me-labs/wf-transcriptomes \
   --fastq  differential_expression/differential_expression_fastq \
   --de_analysis \
+  --transcriptome_source precomputed \
   --ref_genome differential_expression/hg38_chr20.fa \
   --ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
   --direct_rna --minimap2_index_opts '-k 15' \

main.nf

@@ -58,6 +58,7 @@ process getParams {
 }
 
 
+
 process decompress_ref {
     label "isoforms"
     cpus 1
@@ -83,6 +84,21 @@ process decompress_annotation {
     """
 }
 
+
+
+process decompress_transcriptome {
+    label "isoforms"
+    cpus 1
+    input:
+        path "compressed_ref.gz"
+    output:
+        path "compressed_ref", emit: decompressed_ref
+    """
+    gzip -df "compressed_ref.gz"
+    """
+}
+
+
 // Remove empty transcript ID fields
 process preprocess_ref_annotation {
     label "isoforms"
@@ -97,6 +113,21 @@ process preprocess_ref_annotation {
     """
 }
 
+// Just keep transcript ID for each transcriptome fasta
+process preprocess_ref_transcriptome {
+    label "isoforms"
+    cpus 1
+    input:
+        path "ref_transcriptome"
+    output:
+        path "ammended.${ref_transcriptome}"
+    """
+    sed -i -e 's/|.*//' ${ref_transcriptome}
+    mv ${ref_transcriptome} "ammended.${ref_transcriptome}"
+    """
+}
+
+
 
 process preprocess_reads {
     /*
@@ -581,6 +612,10 @@ workflow pipeline {
             }
             else {
                 transcriptome =  Channel.fromPath(ref_transcriptome)
+                if (file(params.ref_transcriptome).extension == "gz") {
+                    transcriptome = decompress_transcriptome(ref_transcriptome)
+                }
+                transcriptome = preprocess_ref_transcriptome(transcriptome)
                 gtf = ref_annotation
             }
             de = differential_expression(transcriptome, input_reads, sample_sheet, gtf)