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

Merge branch 'CW-4613' into 'dev'

Browse Source 
CW-4613 IGV config

Closes CW-4613

See merge request epi2melabs/workflows/wf-transcriptomes!181
This commit is contained in:
Sarah Griffiths 2024-09-06 09:27:56 +00:00
commit f8e08baed1
12 changed files with 251 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

55
.gitlab-ci.yml
View File

@ -53,7 +53,7 @@ docker-run:
"only_differential_expression", "differential_expression_gff3",
"ncbi_gzip", "ncbi_no_gene_id", "ensembl_with_versions",
"differential_expression_mouse", "no_ref_annotation",
"unstranded_annotation_error"
"unstranded_annotation_error", "igv", "igv_fai_gz"
]
rules:
# NOTE As we're overriding the rules block for the included docker-run
@ -67,21 +67,21 @@ docker-run:
NF_WORKFLOW_OPTS: "--fastq ${CI_PROJECT_NAME}/data/ERR6053095_chr20.fastq --transcriptome-source reference-guided \
--ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf --pychopper_backend phmm \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: preprocess_reads,check_annotation_strand,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
NF_IGNORE_PROCESSES: preprocess_reads,faidx,gz_faidx,check_annotation_strand,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
- if: $MATRIX_NAME == "isoforms_bam"
variables:
NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/wf-isoforms_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 ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz -C ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "--bam ${CI_PROJECT_NAME}/data/ERR6053095_chr20.bam --transcriptome-source reference-guided \
--ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa --ref_annotation ${CI_PROJECT_NAME}/data/chr20/gencode.v22.annotation.chr20.gtf --pychopper_backend phmm \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: preprocess_reads,check_annotation_strand,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
NF_IGNORE_PROCESSES: preprocess_reads,faidx,gz_faidx,check_annotation_strand,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
- if: $MATRIX_NAME == "no_ref_annotation"
variables:
NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/wf-isoforms_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 ${CI_PROJECT_NAME}/data/wf-isoforms_test_data.tar.gz -C ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "--fastq ${CI_PROJECT_NAME}/data/ERR6053095_chr20.fastq --transcriptome-source reference-guided \
--ref_genome ${CI_PROJECT_NAME}/data/chr20/hg38_chr20.fa \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: run_gffcompare,check_annotation_strand,preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
NF_IGNORE_PROCESSES: run_gffcompare,check_annotation_strand,preprocess_reads,faidx,gz_faidx,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
- if: $MATRIX_NAME == "differential_expression"
variables:
NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
@ -91,7 +91,7 @@ docker-run:
--ref_annotation ${CI_PROJECT_NAME}/data/differential_expression/gencode.v22.annotation.chr20.gtf \
--direct_rna --minimap2_index_opts '-k 15' --sample_sheet ${CI_PROJECT_NAME}/data/differential_expression/sample_sheet.csv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
NF_IGNORE_PROCESSES: preprocess_reads,faidx,gz_faidx,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
- if: $MATRIX_NAME == "only_differential_expression"
variables:
NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
@ -105,7 +105,7 @@ docker-run:
--sample_sheet test_data/sample_sheet.csv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,decompress_ref,
preprocess_reads,faidx,gz_faidx,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:
@ -120,7 +120,7 @@ docker-run:
--sample_sheet test_data/sample_sheet.csv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,decompress_ref,
preprocess_reads,faidx,gz_faidx,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:
@ -135,7 +135,7 @@ docker-run:
--sample_sheet test_data/sample_sheet.csv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,
preprocess_reads,faidx,gz_faidx,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:
@ -149,7 +149,7 @@ docker-run:
--transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,
preprocess_reads,faidx,gz_faidx,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:
@ -163,7 +163,7 @@ docker-run:
--transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,
preprocess_reads,faidx,gz_faidx,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:
@ -177,7 +177,7 @@ docker-run:
--transcriptome_assembly false --sample_sheet ${CI_PROJECT_NAME}/data/differential_expression_mouse/sample_sheet.csv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,decompress_annotation,
preprocess_reads,faidx,gz_faidx,merge_transcriptomes,assemble_transcripts,decompress_annotation,
build_minimap_index,get_transcriptome,merge_gff_bundles,run_gffcompare,build_minimap_index,split_bam
- if: $MATRIX_NAME == "unstranded_annotation_error"
variables:
@ -188,6 +188,37 @@ docker-run:
--ref_annotation ${CI_PROJECT_NAME}/data/differential_expression/unstranded_annotation.gtf \
--direct_rna --minimap2_index_opts '-k 15' --sample_sheet ${CI_PROJECT_NAME}/data/differential_expression/sample_sheet.csv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: preprocess_reads,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
NF_IGNORE_PROCESSES: preprocess_reads,faidx,gz_faidx,merge_transcriptomes,decompress_annotation,decompress_ref,decompress_transcriptome,preprocess_ref_transcriptome
ASSERT_NEXTFLOW_FAILURE: "test_fail" # set to any non-zero length str to allow the nextflow CMD to fail
ASSERT_NEXTFLOW_FAILURE_REXP: "In ref_annotation, transcript features must have a strand of either '+' or '-'"
- if: $MATRIX_NAME == "igv"
variables:
NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/differential_expression.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression.tar.gz -C ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "--fastq ${CI_PROJECT_NAME}/data/differential_expression/differential_expression_fastq \
--de_analysis \
--ref_genome ${CI_PROJECT_NAME}/data/differential_expression/hg38_chr20.fa \
--ref_annotation ${CI_PROJECT_NAME}/data/differential_expression/gencode.v22.annotation.chr20.gff \
--direct_rna --minimap2_index_opts '-k 15' \
--ref_transcriptome ${CI_PROJECT_NAME}/data/differential_expression/ref_transcriptome.fasta \
--sample_sheet test_data/sample_sheet.csv \
--igv \
-c ${CI_PROJECT_NAME}/data/demo.nextflow.config"
NF_IGNORE_PROCESSES: >
preprocess_reads,gz_faidx,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 == "igv_fai_gz"
variables:
NF_BEFORE_SCRIPT: mkdir -p ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/differential_expression_ncbi.tar.gz https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-transcriptomes/differential_expression_ncbi.tar.gz && tar -xzvf ${CI_PROJECT_NAME}/data/differential_expression_ncbi.tar.gz -C ${CI_PROJECT_NAME}/data/ && wget -O ${CI_PROJECT_NAME}/data/demo.nextflow.config https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-isoforms/demo.nextflow.config
NF_WORKFLOW_OPTS: "-executor.\\$$local.memory 16GB \
--fastq ${CI_PROJECT_NAME}/data/differential_expression_ncbi/differential_expression_fastq \
--transcriptome-source precomputed --de_analysis \
--ref_genome ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_genomic.fna.gz \
--ref_annotation ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_genomic.gff.gz \
--direct_rna --ref_transcriptome ${CI_PROJECT_NAME}/data/differential_expression_ncbi/GCF_000001405.40_GRCh38.p14_rna.fna.gz \
--transcriptome_assembly false --sample_sheet test_data/sample_sheet.csv \
--igv \
-c ${CI_PROJECT_NAME}/data/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

7
CHANGELOG.md
View File

@ -4,6 +4,13 @@ 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).
## [unreleased]
## Added
- `--igv` parameter (default: false) for outputting IGV config allowing visualisation of read alignments in the EPI2ME App.
- If required for IGV, reference indexes are output in to a `igv_reference` directory
### Changed
- BAMS are output in to a BAMS directory.
## [v1.3.0]
### Removed
- Fusion detection subworkflow, as the functionality is not robust enough for general use at this time.

11
README.md
View File

@ -153,6 +153,7 @@ input_reads.fastq ─── input_directory ─── input_directory
| Nextflow parameter name | Type | Description | Help | Default |
|--------------------------|------|-------------|------|---------|
| out_dir | string | Directory for output of all user-facing files. | | output |
| igv | boolean | Visualize outputs in the EPI2ME IGV visualizer. | Enabling this option will visualize the output alignment files in the EPI2ME Desktop App IGV visualizer. | False |
### Sample Options
@ -232,6 +233,11 @@ Output files may be aggregated including information for all samples or provided
| Transcript counts filtered | de_analysis/filtered_transcript_counts_with_genes.tsv | Filtered transcript counts, used for differential transcript usage analysis. Includes a reference to the associated gene ID. | aggregated |
| Transcript info table | {{ alias }}_transcripts_table.tsv | This file details each isoform that was reconstructed from the input reads. It contains a subset of columns from the .tmap output from [gffcompare](https://ccb.jhu.edu/software/stringtie/gffcompare.shtml) | per-sample |
| Final non redundant transcriptome | de_analysis/final_non_redundant_transcriptome.fasta | Transcripts that were used for differential expression analysis including novel transcripts with the identifiers used for DE analysis. | aggregated |
| Index of reference FASTA file | igv_reference/{{ ref_genome file }}.fai | Reference genome index of the FASTA file required for IGV config. | aggregated |
| GZI index of the reference FASTA file | igv_reference/{{ ref_genome file }}.gzi | GZI Index of the reference FASTA file. | aggregated |
| JSON configuration file for IGV browser | igv.json | JSON configuration file to be loaded in IGV for visualising alignments against the reference. | aggregated |
| BAM file (minimap2) | BAMS/{{ alias }}.reads_aln_sorted.bam | BAM file generated from mapping input reads to the reference. | per-sample |
| BAM index file (minimap2) | BAMS/{{ alias }}.reads_aln_sort.bam.bai | Index file generated from mapping input reads to the reference. | per-sample |
@ -250,6 +256,8 @@ If the `transcriptome_source` parameter is "reference-guided" a transcriptome wi
#### 3.1 Align reads with reference genome.
The reference genome will be indexed and aligned using [Minimap2](https://github.com/lh3/minimap2). The output is sorted and converted to a BAM file using [Samtools](https://www.htslib.org/). Alignment stats are created from these using [Seqkit BAM](https://bioinf.shenwei.me/seqkit/usage/#bam).
Additionally, the workflow will generate an IGV configuration file if `--igv` is selected. This file allows the user to view the aligned BAM in the EPI2ME Desktop Application in the Viewer tab.
#### 3.2 Chunk BAM
The aligned BAMs are split into chunks using the bundle_min_reads parameter (default: 50000).
@ -316,6 +324,7 @@ The final component of this isoform analysis is a stage-wise statistical test us
+ If the workflow fails please run it with the demo data set to ensure the workflow itself is working. This will help us determine if the issue is related to the environment, input parameters or a bug.
+ See how to interpret some common nextflow exit codes [here](https://labs.epi2me.io/trouble-shooting/).
+ Renaming, moving or deleting the input BAM, reference genome or the output directory from the location provided at runtime will stop IGV in the EPI2ME Desktop app from loading.
@ -323,6 +332,8 @@ The final component of this isoform analysis is a stage-wise statistical test us
*Does the workflow support de novo assembly?* - Currently the workflow does not have a *de novo* mode.
*Why is the IGV panel not showing?* - The workflow expects either an uncompressed or [`bgzip`](https://www.htslib.org/doc/bgzip.html)-compressed reference. If the user provides a reference compressed not with `bgzip`, the workflow will run to completion, but won't be able to generate the necessary indexes to visualize the outputs in IGV.
If your question is not answered here, please report any issues or suggestions on the [github issues](https://github.com/epi2me-labs/wf-transcriptomes/issues) page or start a discussion on the [community](https://community.nanoporetech.com/).

1
docs/06_input_parameters.md
View File

@ -17,6 +17,7 @@
| Nextflow parameter name | Type | Description | Help | Default |
|--------------------------|------|-------------|------|---------|
| out_dir | string | Directory for output of all user-facing files. | | output |
| igv | boolean | Visualize outputs in the EPI2ME IGV visualizer. | Enabling this option will visualize the output alignment files in the EPI2ME Desktop App IGV visualizer. | False |
### Sample Options

5
docs/07_outputs.md
View File

@ -26,3 +26,8 @@ Output files may be aggregated including information for all samples or provided
| Transcript counts filtered | de_analysis/filtered_transcript_counts_with_genes.tsv | Filtered transcript counts, used for differential transcript usage analysis. Includes a reference to the associated gene ID. | aggregated |
| Transcript info table | {{ alias }}_transcripts_table.tsv | This file details each isoform that was reconstructed from the input reads. It contains a subset of columns from the .tmap output from [gffcompare](https://ccb.jhu.edu/software/stringtie/gffcompare.shtml) | per-sample |
| Final non redundant transcriptome | de_analysis/final_non_redundant_transcriptome.fasta | Transcripts that were used for differential expression analysis including novel transcripts with the identifiers used for DE analysis. | aggregated |
| Index of reference FASTA file | igv_reference/{{ ref_genome file }}.fai | Reference genome index of the FASTA file required for IGV config. | aggregated |
| GZI index of the reference FASTA file | igv_reference/{{ ref_genome file }}.gzi | GZI Index of the reference FASTA file. | aggregated |
| JSON configuration file for IGV browser | igv.json | JSON configuration file to be loaded in IGV for visualising alignments against the reference. | aggregated |
| BAM file (minimap2) | BAMS/{{ alias }}.reads_aln_sorted.bam | BAM file generated from mapping input reads to the reference. | per-sample |
| BAM index file (minimap2) | BAMS/{{ alias }}.reads_aln_sort.bam.bai | Index file generated from mapping input reads to the reference. | per-sample |

2
docs/08_pipeline_overview.md
View File

@ -10,6 +10,8 @@ If the `transcriptome_source` parameter is "reference-guided" a transcriptome wi
#### 3.1 Align reads with reference genome.
The reference genome will be indexed and aligned using [Minimap2](https://github.com/lh3/minimap2). The output is sorted and converted to a BAM file using [Samtools](https://www.htslib.org/). Alignment stats are created from these using [Seqkit BAM](https://bioinf.shenwei.me/seqkit/usage/#bam).
Additionally, the workflow will generate an IGV configuration file if `--igv` is selected. This file allows the user to view the aligned BAM in the EPI2ME Desktop Application in the Viewer tab.
#### 3.2 Chunk BAM
The aligned BAMs are split into chunks using the bundle_min_reads parameter (default: 50000).

3
docs/09_troubleshooting.md
View File

@ -1,2 +1,3 @@
+ If the workflow fails please run it with the demo data set to ensure the workflow itself is working. This will help us determine if the issue is related to the environment, input parameters or a bug.
+ See how to interpret some common nextflow exit codes [here](https://labs.epi2me.io/trouble-shooting/).
+ See how to interpret some common nextflow exit codes [here](https://labs.epi2me.io/trouble-shooting/).
+ Renaming, moving or deleting the input BAM, reference genome or the output directory from the location provided at runtime will stop IGV in the EPI2ME Desktop app from loading.

2
docs/10_FAQ.md
View File

@ -1,3 +1,5 @@
*Does the workflow support de novo assembly?* - Currently the workflow does not have a *de novo* mode.
*Why is the IGV panel not showing?* - The workflow expects either an uncompressed or [`bgzip`](https://www.htslib.org/doc/bgzip.html)-compressed reference. If the user provides a reference compressed not with `bgzip`, the workflow will run to completion, but won't be able to generate the necessary indexes to visualize the outputs in IGV.
If your question is not answered here, please report any issues or suggestions on the [github issues](https://github.com/epi2me-labs/wf-transcriptomes/issues) page or start a discussion on the [community](https://community.nanoporetech.com/).

130
main.nf
View File

@ -10,6 +10,7 @@ import java.util.ArrayList;
nextflow.enable.dsl = 2
include { fastq_ingress; xam_ingress } from './lib/ingress'
include { configure_igv } from './lib/common'
include { reference_assembly } from './subworkflows/reference_assembly'
include { differential_expression } from './subworkflows/differential_expression'
@ -526,6 +527,50 @@ process check_annotation_strand {
}
// Process to create the faidx index
process faidx {
// If the input file is gzipped, we need to emit the indexes for the input gzip file
// only. Therefore, this become redundant to be emitted as it won't be used by the
// IGV configuration, but only by internal processes together with the decompressed
// FASTA file. To avoid unnecessary emissions, we enable only if the input file is
// decompressed.
publishDir "${params.out_dir}/igv_reference", mode: 'copy', pattern: "*", enabled: !params.ref_genome.toLowerCase().endsWith("gz")
label "wf_common"
cpus 1
memory 4.GB
input:
path(ref)
output:
path("${ref}.fai")
script:
"""
samtools faidx ${ref}
"""
}
// Process to create the faidx indexes for a gzipped reference
process gz_faidx {
publishDir "${params.out_dir}/igv_reference", mode: 'copy', pattern: "*"
label "wf_common"
cpus 1
memory 4.GB
// If a user provides a non-bgzipped file, the process won't
// generate the indexes. We should tolerate that, still avoid emitting
// the reference and simply have a broken IGV file.
// The gzi is not required to operate the workflow, so we actually tolerate any failure.
errorStrategy 'ignore'
input:
path(ref)
output:
tuple path("${ref}.fai"), path("${ref}.gzi")
script:
"""
samtools faidx ${ref}
"""
}
// workflow module
workflow pipeline {
@ -580,6 +625,8 @@ workflow pipeline {
results = Channel.empty()
// Define BAM output Directory
String publish_bams = "BAMS"
software_versions = getVersions()
workflow_params = getParams()
input_reads = reads.map{ meta, samples, stats -> [meta, samples]}
@ -634,7 +681,9 @@ workflow pipeline {
merge_gff = merge_gff_bundles.out.gff.map{ it -> it[1]}.collect()
results = results.concat(assembly.bam.map {sample_id, bam, bai -> [bam, bai]}.flatten())
// Output BAMS in a dedicated directory
bam_results = assembly.bam.map{
sample_id, bam, bai -> [bam, bai]}.flatten().map{ [it, publish_bams] }
}
else{
gff_compare = OPTIONAL_FILE
@ -723,6 +772,85 @@ workflow pipeline {
}
results.concat(workflow_params.map{ [it, null]})
// IGV config
if (params.transcriptome_source == "precomputed" && params.igv){
log.warn("IGV configuration does not work if transcriptome sources is set to `precomputed`.")
}
if (params.transcriptome_source != "precomputed" && params.igv){
is_compressed = file("${params.ref_genome}").extension == "gz"
String publish_ref = "igv_reference"
String current_dir = "${file('.').toUriString()}"
reference_genome = Channel.fromPath("${params.ref_genome}")
igv_ref = reference_genome | flatten | map { it -> "${it.toUriString()}" }
if (is_compressed){
// Define indexes names.
String input_fai_index = "${params.ref_genome}.fai"
String input_gzi_index = "${params.ref_genome}.gzi"
// Check whether the input gzref is indexed. If so, pass these as indexes.
// Otherwise, generate the gzip + fai indexes for the compressed reference.
if (file(input_fai_index).exists() && file(input_gzi_index).exists()){
gzindexes = Channel.fromPath(input_fai_index)
| mix(
Channel.fromPath(input_gzi_index)
)
gz_igv = gzindexes | flatten | map { it -> "${it.toUriString()}" }
} else {
gz_igv = gz_faidx(Channel.fromPath("${params.ref_genome}"))
| flatten
| map { it -> "$current_dir/$params.out_dir/$publish_ref/${it.Name}" }
gz_igv | ifEmpty{
if (params.containsKey("igv") && params.igv){
log.warn """\
The input reference is compressed but not with bgzip, which is required to create an index.
The workflow will proceed but it will not be possible to load the reference in the IGV Viewer.
To use the IGV Viewer, provide an uncompressed, or bgzip compressed version of the input reference next time you run the workflow.
""".stripIndent()
}
}
}
} else {
gzindexes = Channel.empty()
gz_igv = Channel.empty()
}
// Generate fai index if the file is either compressed, or if fai doesn't exists
if (!is_compressed && file("${params.ref_genome}.fai").exists()){
ref_idx = Channel.fromPath("${params.ref_genome}.fai")
igv_index = ref_idx | flatten | map { it -> "${it.toUriString()}" }
} else {
ref_idx = faidx(reference_genome)
igv_index = ref_idx | map { it -> "$current_dir/$params.out_dir/$publish_ref/${it.Name}" }
}
// get list of file names
// Absolute paths required for directories
igv_files = reads
| map { meta, sample, stats -> meta.alias }
| toSortedList
| map { list -> list.collect{
[
"$current_dir/$params.out_dir/$publish_bams/${it}_reads_aln_sorted.bam",
"$current_dir/$params.out_dir/$publish_bams/${it}_reads_aln_sorted.bam.bai"
]
} }
| concat ( igv_index)
| flatten
| concat (igv_ref)
| concat (gz_igv)
| flatten
| collectFile(name: "file-names.txt", newLine: true, sort: false)
// configure IGV
igv_conf = configure_igv(
igv_files,
Channel.of(null), // igv locus
[displayMode: "SQUISHED", colorBy: "strand"], // bam extra opts
Channel.of(null), // vcf extra opts
)
results = results.concat(igv_conf.map{ [it, null]})
results = results.concat(bam_results)
}
emit:

3
nextflow.config
View File

@ -31,6 +31,7 @@ params {
version = false
monochrome_logs = false
igv = false
validate_params = true
show_hidden_params = false
schema_ignore_params = 'show_hidden_params,validate_params,monochrome_logs,aws_queue,aws_image_prefix,wf'
@ -95,7 +96,7 @@ params {
]
agent = null
container_sha = "shafb1e2372e1535f0b42891ed2c68ffdac2ca1d658"
common_sha = "shab540ba556d0d8c38bea8fec520f0bdedd9e59520"
common_sha = "shad399cf22079b5b153920ac39ee40095a677933f1"
}
}

7
nextflow_schema.json
View File

@ -110,6 +110,13 @@
"format": "directory-path",
"default": "output",
"description": "Directory for output of all user-facing files."
},
"igv": {
"title": "Show in IGV",
"type": "boolean",
"default": false,
"description": "Visualize outputs in the EPI2ME IGV visualizer.",
"help_text": "Enabling this option will visualize the output alignment files in the EPI2ME Desktop App IGV visualizer."
}
}
},

40
output_definition.json
View File

@ -191,6 +191,46 @@
"mime-type": "text/x-fasta",
"optional": true,
"type": "aggregated"
},
"reference-index": {
"filepath": "igv_reference/{{ ref_genome file }}.fai",
"title": "Index of reference FASTA file",
"description": "Reference genome index of the FASTA file required for IGV config.",
"mime-type": "text/tab-separated-values",
"optional": true,
"type": "aggregated"
},
"reference-gzi-index": {
"filepath": "igv_reference/{{ ref_genome file }}.gzi",
"title": "GZI index of the reference FASTA file",
"description": "GZI Index of the reference FASTA file.",
"mime-type": "application/octet-stream",
"optional": true,
"type": "aggregated"
},
"igv-config": {
"filepath": "igv.json",
"title": "JSON configuration file for IGV browser",
"description": "JSON configuration file to be loaded in IGV for visualising alignments against the reference.",
"mime-type": "text/json",
"optional": true,
"type": "aggregated"
},
"minimap2-bam": {
"filepath": "BAMS/{{ alias }}.reads_aln_sorted.bam",
"title": "BAM file (minimap2)",
"description": "BAM file generated from mapping input reads to the reference.",
"mime-type": "application/gzip",
"optional": true,
"type": "per-sample"
},
"minimap2-index": {
"filepath": "BAMS/{{ alias }}.reads_aln_sort.bam.bai",
"title": "BAM index file (minimap2)",
"description": "Index file generated from mapping input reads to the reference.",
"mime-type": "application/octet-stream",
"optional": true,
"type": "per-sample"
}
}
}