kfukuta/wf-transcriptomes-v202
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Resource updates

Browse Source
This commit is contained in:
Sarah Griffiths 2024-02-12 10:20:02 +00:00
parent 9cf89d4360
commit 4bb02049ec
7 changed files with 47 additions and 35 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
.gitlab-ci.yml
View File

@ -4,13 +4,14 @@ include:
file: "wf-containers.yaml"
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
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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "--fastq differential_expression/differential_expression_fastq \
--de_analysis --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 differential_expression/sample_sheet.csv \
--jaffal_refBase differential_expression/chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22"
--jaffal_refBase differential_expression/chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22 \
-c demo.nextflow.config"
CI_FLAVOUR: "new"
macos-run:
@ -62,35 +63,39 @@ docker-run:
when: never
- if: $MATRIX_NAME == "isoforms"
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_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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
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 --pychopper_backend phmm"
--ref_genome chr20/hg38_chr20.fa --ref_annotation chr20/gencode.v22.annotation.chr20.gtf --pychopper_backend phmm \
-c demo.nextflow.config"
NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
- if: $MATRIX_NAME == "no_ref_annotation"
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_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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "--fastq ERR6053095_chr20.fastq --transcriptome-source reference-guided \
--ref_genome chr20/hg38_chr20.fa"
--ref_genome chr20/hg38_chr20.fa \
-c demo.nextflow.config"
NF_IGNORE_PROCESSES: run_gffcompare,preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,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_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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
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"
--jaffal_refBase chr20/ --jaffal_genome hg38_chr20 --jaffal_annotation genCode22 \
-c demo.nextflow.config"
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
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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "--fastq differential_expression/differential_expression_fastq \
--de_analysis \
--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 differential_expression/sample_sheet.csv"
--direct_rna --minimap2_index_opts '-k 15' --sample_sheet differential_expression/sample_sheet.csv \
-c demo.nextflow.config"
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
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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "--fastq differential_expression/differential_expression_fastq \
--transcriptome-source precomputed \
--de_analysis \
@ -98,13 +103,14 @@ docker-run:
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gff \
--direct_rna --minimap2_index_opts '-k 15' \
--ref_transcriptome differential_expression/ref_transcriptome.fasta \
--sample_sheet test_data/sample_sheet.csv"
--sample_sheet test_data/sample_sheet.csv \
-c demo.nextflow.config"
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,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
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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "--fastq differential_expression/differential_expression_fastq \
--transcriptome-source precomputed \
--de_analysis \
@ -112,13 +118,14 @@ docker-run:
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gff3 \
--direct_rna --minimap2_index_opts '-k 15' \
--ref_transcriptome differential_expression/ref_transcriptome.fasta \
--sample_sheet test_data/sample_sheet.csv"
--sample_sheet test_data/sample_sheet.csv \
-c demo.nextflow.config"
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,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
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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
--fastq differential_expression_ncbi/differential_expression_fastq \
--transcriptome-source precomputed \
@ -126,46 +133,50 @@ docker-run:
--ref_genome differential_expression_ncbi/GRCh38.p14.NCBI_test.fna.gz \
--ref_annotation differential_expression_ncbi/GRCh38.p14_NCBI_test.gtf.gz \
--direct_rna --minimap2_index_opts '-w 25' \
--sample_sheet test_data/sample_sheet.csv"
--sample_sheet test_data/sample_sheet.csv \
-c demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,
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
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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
--fastq differential_expression_ncbi/differential_expression_fastq \
--transcriptome-source precomputed --de_analysis \
--ref_genome differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_genomic.fna.gz \
--ref_annotation differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_genomic.gff.gz \
--direct_rna --ref_transcriptome differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_rna.fna.gz \
--transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv"
--transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv \
-c demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,
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
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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
--fastq differential_expression/differential_expression_fastq \
--transcriptome-source precomputed --de_analysis \
--ref_genome differential_expression/Homo_sapiens.GRCh38.dna.primary_assembly.fa.gz \
--ref_annotation differential_expression/Homo_sapiens.GRCh38.109.gtf.gz \
--direct_rna --ref_transcriptome differential_expression/Homo_sapiens.GRCh38.cdna.all.fa.gz \
--transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv"
--transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv \
-c demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,
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_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 && wget https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
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"
--transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv \
-c demo.nextflow.config"
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

1
CHANGELOG.md
View File

@ -10,6 +10,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Renamed files:
- `de_analysis/all_counts_filtered.tsv` to `de_analysis/filtered_transcript_counts_with_genes.tsv`
- `de_analysis/de_tpm_transcript_counts.tsv` to `de_analysis/unfiltered_tpm_transcript_counts.tsv`
- Minimum memory requirements to `32 GB`.
### Added
- Published isoforms table to output directory.
- Output additional `de_analysis/cpm_gene_counts.tsv` with counts per million gene counts.

2
README.md
View File

@ -27,7 +27,7 @@ Recommended requirements:
Minimum requirements:
+ CPUs = 8
+ Memory = 16GB
+ Memory = 32GB
Approximate run time: 15 minutes per sample, with 1 million reads and recommended resources.

2
docs/03_compute_requirements.md
View File

@ -6,7 +6,7 @@ Recommended requirements:
Minimum requirements:
+ CPUs = 8
+ Memory = 16GB
+ Memory = 32GB
Approximate run time: 15 minutes per sample, with 1 million reads and recommended resources.

18
main.nf
View File

@ -19,7 +19,7 @@ OPTIONAL_FILE = file("$projectDir/data/OPTIONAL_FILE")
process getVersions {
label "isoforms"
cpus 1
memory "500MB"
memory "2 GB"
output:
path "versions.txt"
script:
@ -44,7 +44,7 @@ process getVersions {
process getParams {
label "isoforms"
cpus 1
memory "500MB"
memory "2 GB"
output:
path "params.json"
script:
@ -60,7 +60,7 @@ process getParams {
process decompress_ref {
label "isoforms"
cpus 1
memory "500MB"
memory "2 GB"
input:
path compressed_ref
output:
@ -74,7 +74,7 @@ process decompress_ref {
process decompress_annotation {
label "isoforms"
cpus 1
memory "500MB"
memory "2 GB"
input:
path compressed_annotation
output:
@ -89,7 +89,7 @@ process decompress_annotation {
process decompress_transcriptome {
label "isoforms"
cpus 1
memory "500MB"
memory "2 GB"
input:
path "compressed_ref.gz"
output:
@ -104,7 +104,7 @@ process decompress_transcriptome {
process preprocess_ref_annotation {
label "isoforms"
cpus 1
memory "500MB"
memory "2 GB"
input:
path ref_annotation
output:
@ -119,7 +119,7 @@ process preprocess_ref_annotation {
process preprocess_ref_transcriptome {
label "isoforms"
cpus 1
memory "500MB"
memory "2 GB"
input:
path "ref_transcriptome"
output:
@ -177,7 +177,7 @@ process build_minimap_index{
*/
label "isoforms"
cpus params.threads
memory "16 GB"
memory "31 GB"
input:
path reference
@ -367,7 +367,7 @@ process merge_transcriptomes {
// Merge the transcriptomes from all samples
label 'isoforms'
cpus 2
memory "4 GB"
memory "2 GB"
input:
path "query_annotations/*"
path ref_annotation

2
nextflow_schema.json
View File

@ -388,7 +388,7 @@
},
"minimum": {
"cpus": 8,
"memory": "16GB"
"memory": "32GB"
},
"run_time": "15 minutes per sample, with 1 million reads and recommended resources.",
"arm_support": false

2
subworkflows/reference_assembly.nf
View File

@ -6,7 +6,7 @@ process map_reads{
*/
label "isoforms"
cpus params.threads
memory "16 GB"
memory "31 GB"
input:
tuple val(sample_id), path (fastq_reads), path(index), path(reference)