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

Merge branch 'schema-5.1.1' into 'dev'

Browse Source 
add titles

See merge request epi2melabs/workflows/wf-transcriptomes!119
This commit is contained in:
Sarah Griffiths 2023-08-08 11:18:15 +00:00
commit 3a5de57317
8 changed files with 49 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
.gitlab-ci.yml
View File

@ -77,7 +77,7 @@ docker-run:
--de_analysis \
--ref_genome differential_expression/hg38_chr20.fa --transcriptome-source reference-guided \
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
--direct_rna --minimap_index_opts '-k 15' --sample_sheet test_data/sample_sheet.csv"
--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
- if: $MATRIX_NAME == "only_differential_expression"
variables:
@ -87,7 +87,7 @@ docker-run:
--de_analysis \
--ref_genome differential_expression/hg38_chr20.fa \
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gff \
--direct_rna --minimap_index_opts '-k 15' \
--direct_rna --minimap2_index_opts '-k 15' \
--ref_transcriptome differential_expression/ref_transcriptome.fasta \
--sample_sheet test_data/sample_sheet.csv"
NF_IGNORE_PROCESSES: >
@ -101,7 +101,7 @@ docker-run:
--de_analysis \
--ref_genome differential_expression/hg38_chr20.fa \
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gff3 \
--direct_rna --minimap_index_opts '-k 15' \
--direct_rna --minimap2_index_opts '-k 15' \
--ref_transcriptome differential_expression/ref_transcriptome.fasta \
--sample_sheet test_data/sample_sheet.csv"
NF_IGNORE_PROCESSES: >
@ -116,7 +116,7 @@ docker-run:
--de_analysis \
--ref_genome differential_expression_ncbi/GRCh38.p14.NCBI_test.fna.gz \
--ref_annotation differential_expression_ncbi/GRCh38.p14_NCBI_test.gtf.gz \
--direct_rna --minimap_index_opts '-w 25' \
--direct_rna --minimap2_index_opts '-w 25' \
--sample_sheet test_data/sample_sheet.csv"
NF_IGNORE_PROCESSES: >
preprocess_reads,merge_transcriptomes,assemble_transcripts,

1
CHANGELOG.md
View File

@ -7,6 +7,7 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
## [updated]
### Changed
- Nextflow minimum required version to 23.04.2
- `--minimap_index_opts` parameter has been changed to `minimap2_index_opts` for consistency.
## [v0.2.1]
### Changed

4
README.md
View File

@ -241,7 +241,7 @@ nextflow run epi2me-labs/wf-transcriptomes \
--de_analysis \
--ref_genome differential_expression/hg38_chr20.fa \
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
--direct_rna --minimap_index_opts \
--direct_rna --minimap2_index_opts \
-k15
```
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.
@ -252,7 +252,7 @@ nextflow run epi2me-labs/wf-transcriptomes \
--de_analysis \
--ref_genome differential_expression/hg38_chr20.fa \
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
--direct_rna --minimap_index_opts \
--direct_rna --minimap2_index_opts \
-k15 \
--ref_transcriptome differential_expression/ref_transcriptome.fasta
```

4
docs/quickstart.md
View File

@ -151,7 +151,7 @@ nextflow run epi2me-labs/wf-transcriptomes \
--de_analysis \
--ref_genome differential_expression/hg38_chr20.fa \
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
--direct_rna --minimap_index_opts \
--direct_rna --minimap2_index_opts \
-k15
```
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.
@ -162,7 +162,7 @@ nextflow run epi2me-labs/wf-transcriptomes \
--de_analysis \
--ref_genome differential_expression/hg38_chr20.fa \
--ref_annotation differential_expression/gencode.v22.annotation.chr20.gtf \
--direct_rna --minimap_index_opts \
--direct_rna --minimap2_index_opts \
-k15 \
--ref_transcriptome differential_expression/ref_transcriptome.fasta
```

6
main.nf
View File

@ -137,7 +137,7 @@ process build_minimap_index{
path "genome_index.mmi", emit: index
script:
"""
minimap2 -t ${params.threads} ${params.minimap_index_opts} -I 1000G -d "genome_index.mmi" ${reference}
minimap2 -t ${params.threads} ${params.minimap2_index_opts} -I 1000G -d "genome_index.mmi" ${reference}
"""
}
@ -668,6 +668,10 @@ workflow {
error = null
if (params.containsKey("minimap_index_opts")) {
error = "`--minimap_index_opts` parameter is deprecated. Use parameter `--minimap2_index_opts` instead."
}
if (!fastq.exists()) {
error = "--fastq: File doesn't exist, check path."
}

4
nextflow.config
View File

@ -40,7 +40,7 @@ params {
pychopper_opts = "-m edlib"
// Extra option passed to minimap2 when generating index
minimap_index_opts = "-k14"
minimap2_index_opts = "-k14"
// Extra options passed to minimap2
// For SIRV data
@ -98,7 +98,7 @@ params {
"--condition_sheet 'wf-transcriptomes-demo/condition_sheet.tsv'",
"--direct_rna",
"--fastq 'wf-transcriptomes-demo/differential_expression_fastq'",
"--minimap_index_opts '-k15'",
"--minimap2_index_opts '-k15'",
"--ref_annotation 'wf-transcriptomes-demo/gencode.v22.annotation.chr20.gtf'",
"--ref_genome 'wf-transcriptomes-demo/hg38_chr20.fa'",
]

35
nextflow_schema.json
View File

@ -17,6 +17,7 @@
"fastq": {
"type": "string",
"format": "path",
"title": "FASTQ",
"demo_data": "${projectDir}/test_data/fastq",
"description": "FASTQ files to use in the analysis.",
"help_text": "This accepts one of three cases: (i) the path to a single FASTQ file; (ii) the path to a top-level directory containing FASTQ files; (iii) the path to a directory containing one level of sub-directories which in turn contain FASTQ files. In the first and second case, a sample name can be supplied with `--sample`. In the last case, the data is assumed to be multiplexed with the names of the sub-directories as barcodes. In this case, a sample sheet can be provided with `--sample_sheet`."
@ -33,6 +34,7 @@
},
"ref_genome": {
"type": "string",
"title": "Reference genome",
"format": "file-path",
"demo_data": "${projectDir}/test_data/SIRV_150601a.fasta",
"description": "Path to reference genome sequence [.fa/.fq/.fa.gz/fq.gz]. Required for reference-based workflow.",
@ -40,12 +42,14 @@
},
"ref_transcriptome": {
"type": "string",
"title": "Reference transcriptome",
"format": "file-path",
"description": "Transcriptome reference file. Required for precomputed transcriptome calculation and for differential expression analysis.",
"help_text": "A reference transcriptome related to the sample under study. Must be supplied when the 'Transcriptome source' parameter has been set to 'precomputed' or to perform differential expression."
},
"ref_annotation": {
"type": "string",
"title": "Reference annotation",
"format": "file-path",
"demo_data": "${projectDir}/test_data/SIRV_isoforms.gtf",
"description": "A reference annotation in GFF2 or GFF3 format (extensions .gtf(.gz), .gff(.gz), .gff3(.gz))",
@ -53,11 +57,13 @@
},
"direct_rna": {
"type": "boolean",
"title": "direct RNA",
"description": "Set to true for direct RNA sequencing.",
"help_text": " Omits the pychopper step."
},
"analyse_unclassified": {
"type": "boolean",
"title": "Analyse unclassified",
"description": "Analyse unclassified reads from input directory. By default the workflow will not process reads in the unclassified directory.",
"help_text": "If selected and if the input is a multiplex directory the workflow will also process the unclassified directory."
}
@ -89,6 +95,7 @@
"properties": {
"sample_sheet": {
"type": "string",
"title": "Sample sheet",
"format": "file-path",
"description": "A CSV file used to map barcodes to sample aliases. The sample sheet can be provided when the input data is a directory containing sub-directories with FASTQ files. If you are running the differential expression workflow, there should be an additional column `condition` with any two distinct labels eg. `treated`,`untreated`. There should be at least 3 repeats for each condition.",
"help_text": "The sample sheet is a CSV file with, minimally, columns named `barcode` and `alias`. Extra columns are allowed. A `type` column is required for certain workflows and should have the following values; `test_sample`, `positive_control`, `negative_control`, `no_template_control`."
@ -106,23 +113,27 @@
"properties": {
"plot_gffcmp_stats": {
"type": "boolean",
"title": "Plot gffcompare statistics",
"description": "Create a PDF of plots from showing gffcompare results",
"help_text": "If set to true, a PDF file containing detailed gffcompare reults will be output"
},
"gffcompare_opts": {
"type": "string",
"title": "Plot gffcompare options",
"description": "Extra command-line options to give to gffcompare -r",
"default": " -R ",
"help_text": "For a list of possible options see [gffcompare](https://ccb.jhu.edu/software/stringtie/gffcompare.shtml)."
},
"minimap_index_opts": {
"minimap2_index_opts": {
"type": "string",
"title": "Minimap2 index options",
"description": "Extra command-line options for minimap2 indexing.",
"default": "-k14",
"help_text": "See [minimap2 index options](https://lh3.github.io/minimap2/minimap2.html#4) for more information. These will only be relevant in the reference based transcriptome assembly."
},
"minimap2_opts": {
"type": "string",
"title": "Minimap2 options",
"description": "Additional command-line options for minimap2 alignment.",
"default": "-uf",
"help_text": "See [minimap2 options](https://lh3.github.io/minimap2/minimap2.html#5) for further information. These will only be relevant in the reference based transcriptome assembly."
@ -142,6 +153,7 @@
},
"max_poly_run": {
"type": "integer",
"title": "Maximum poly run",
"description": "Max poly(A) region allowed with poly_context-sized end regions.",
"help_text": "See `poly_context` parameter. This parameter defines the maximum allowed polyA tract within a `poly_context` defined genomic region.",
"hidden": true,
@ -149,6 +161,7 @@
},
"stringtie_opts": {
"type": "string",
"title": "Stringtie options",
"description": "Extra command-line options for stringtie transcript assembly.",
"default": " --conservative ",
"help_text": "For additional String tie options see [here](https://github.com/gpertea/stringtie#stringtie-options)."
@ -163,7 +176,7 @@
"isOnClust2_batch_size": {
"type": "integer",
"description": "Number of batches to to process the data in.",
"help_text": "If set to -1 number of batches witll be the same as the number of threads avaiable.",
"help_text": "If set to -1 number of batches will be the same as the number of threads avaiable.",
"default": -1
},
"isOnClust2_sort_options": {
@ -181,18 +194,21 @@
"properties": {
"jaffal_refBase": {
"type": "string",
"title": "JAFFAL reference genome directory",
"format": "directory-path",
"description": "JAFFAl reference genome directory.",
"help_text": "JAFFAL human hg38 reference data directory can be downloaded from here: https://figshare.com/ndownloader/files/25410494 or see the README for alternative instructions. If custom gemome files are required, see the instructions here: https://github.com/Oshlack/JAFFA/wiki/FAQandTroubleshooting#how-can-i-generate-the-reference-files-for-a-non-supported-genome."
},
"jaffal_genome": {
"type": "string",
"title": "JAFFAL genome reference prefix",
"description": "Genome reference prefix. e.g. hg38.",
"help_text": "JAFFAL reference files are prefixed with the genome reference file name and need to be supplied . If using the human reference data provided by JAFFAL, this can be left at `hg38`.",
"default": "hg38"
},
"jaffal_annotation": {
"type": "string",
"title": "JAFFAL annotation suffix",
"description": "Annotation suffix.",
"help_text": "JAFFAL reference files are suffixed with the annotation filename and this needs to be supplied. For the human hg38 reference data supplied by JAFFAL, this is `genCode22`.",
"default": "genCode22"
@ -214,33 +230,43 @@
"properties": {
"de_analysis": {
"type": "boolean",
"title": "Differential expression analysis",
"description": "Run DE anaylsis",
"help_text": "Running this requires you to provide at least two replicates for a control and treated sample as well as a condition sheet param."
"help_text": "Running this requires you to provide at least two replicates for a control and treated sample as well as a sample sheet param."
},
"min_gene_expr": {
"type": "integer",
"title": "Minimum gene expression",
"default": 10,
"description": "Minimum gene counts",
"help_text": "The minimum number of total mapped sequence reads for a gene to be considered expressed."
},
"min_feature_expr": {
"type": "integer",
"title": "Minimum feature expression",
"default": 3,
"description": "Minimum transcript counts",
"help_text": "The minimum number of total mapped sequence reads for a transcript to be considered."
},
"min_samps_gene_expr": {
"type": "integer",
"title": "Minimum samples with gene expression",
"description": "Genes expressed in a minimum of this many samples will be included in the differential expression analysis.",
"default": 3,
"help_text": "A gene must be mapped to at least this minimum number of samples for the gene be included in the analysis."
},
"min_samps_feature_expr": {
"type": "integer",
"title": "Minimum samples with feature expression",
"default": 1,
"description": "Transcripts expressed in minimum this many samples",
"help_text": "A transcript must be mapped in at least this this minimum number of samples to be included in the analysis."
}
},
"dependencies": {
"de_analysis": [
"sample_sheet"
]
}
},
"advanced_options": {
@ -256,16 +282,19 @@
},
"pychopper_opts": {
"type": "string",
"title": "Pychopper options",
"description": "Extra pychopper opts",
"default": "-m edlib",
"help_text": "See available options (here)[https://github.com/epi2me-labs/pychopper#usage]"
},
"bundle_min_reads": {
"type": "integer",
"title": "Bundle minimum reads",
"description": "Minimum size of bam bundle for parallel processing."
},
"isoform_table_nrows": {
"type": "integer",
"title": "Isoform table number of rows",
"description": "Maximum rows to dispay in the isoform report table",
"default": 5000
}

2
subworkflows/differential_expression.nf
View File

@ -126,7 +126,7 @@ process build_minimap_index_transcriptome{
tuple path("genome_index.mmi"), path(reference), emit: index
script:
"""
minimap2 -t "${task.cpus}" ${params.minimap_index_opts} -I 1000G -d "genome_index.mmi" "${reference}"
minimap2 -t "${task.cpus}" ${params.minimap2_index_opts} -I 1000G -d "genome_index.mmi" "${reference}"
"""
}