diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 8abd0a7..8134142 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -8,7 +8,7 @@ repos: always_run: true pass_filenames: false additional_dependencies: - - epi2melabs>=0.0.49 + - epi2melabs>=0.0.50 - id: build_models name: build_models entry: datamodel-codegen --strict-nullable --base-class workflow_glue.results_schema_helpers.BaseModel --use-schema-description --disable-timestamp --input results_schema.yml --input-file-type openapi --output bin/workflow_glue/results_schema.py diff --git a/CHANGELOG.md b/CHANGELOG.md index 8a9fb0e..cfe2197 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -4,10 +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] +## [v1.0.0] ### Added - Published minimap2 and pychopper results to output directory. - Two extra pychopper parameters `--cdna_kit` and `--pychopper_backend`. `--pychopper_options` is still available to define any other options. +- Memory requirements for each process. +### Changed +- Documentation. ## [v0.4.2] ### Changed diff --git a/README.md b/README.md index ec8928e..c527339 100644 --- a/README.md +++ b/README.md @@ -163,13 +163,13 @@ Find related protocols in the [Nanopore community](https://community.nanoporetec ## Outputs -Outputs files may be aggregated including information for all samples or provided per sample. Per sample files will be prefixed with respective aliases and represented below as {{ alias }}. +Outputs files may be aggregated including information for all samples or provided per sample. Per-sample files will be prefixed with respective aliases and represented below as {{ alias }}. | Title | File path | Description | Per sample or aggregated | |-------|-----------|-------------|--------------------------| | workflow report | wf-transcriptomes-report.html | a HTML report document detailing the primary findings of the workflow | aggregated | | Per file read stats | fastq_ingress_results/reads/fastcat_stats/per-file-stats.tsv | A TSV with per file read stats, including all samples. | aggregated | -| Per file read stats | fastq_ingress_results/reads/fastcat_stats/per-read-stats.tsv | A TSV with per read stats, including all samples. | aggregated | +| Read stats | fastq_ingress_results/reads/fastcat_stats/per-read-stats.tsv | A TSV with per read stats, including all samples. | aggregated | | Run ID's | fastq_ingress_results/reads/fastcat_stats/run_ids | List of run IDs present in reads. | aggregated | | Meta map json | fastq_ingress_results/reads/metamap.json | Metadata used in workflow presented in a JSON. | aggregated | | Concatenated sequence data | fastq_ingress_results/reads/{{ alias }}.fastq.gz | Per sample reads concatenated in to one FASTQ file. | per-sample | @@ -180,7 +180,7 @@ Outputs files may be aggregated including information for all sample | Differential gene expression results | /de_analysis/results_dge.tsv | This is a gene-level result file that describes genes and the probability that they show differential expression between experimental conditions . | aggregated | | Differential gene expression report | /de_analysis/results_dge.pdf | Summary report of differential gene expression analysis as a PDF. | aggregated | | Differential transcript usage gene TSV | /de_analysis/results_dtu_gene.tsv | This is a gene-level result file from DEXSeq that lists annotated genes and their probabilities of differential expression. | aggregated | -| Differential gene expression report | /de_analysis/results_dtu.pdf | Summary report of differential transcript usage results as a PDF. | aggregated | +| Differential transcript usage report | /de_analysis/results_dtu.pdf | Summary report of differential transcript usage results as a PDF. | aggregated | | Differential transcript usage TSV | /de_analysis/results_dtu_transcript.tsv | This is a transcript-level result file from DEXSeq that lists annotated genes and their probabilities of differential expression. | aggregated | | Differential transcript usage stageR TSV | /de_analysis/results_dtu_stageR.tsv | This is the output from StageR and it shows both gene and transcript probabilities of differential expression | aggregated | | Differential transcript usage DEXSeq TSV | /de_analysis/results_dexseq.tsv | The complete output from the DEXSeq-analysis, shows both gene and transcript probabilities of differential expression. | aggregated | diff --git a/docs/07_outputs.md b/docs/07_outputs.md index e7854fd..1368f96 100644 --- a/docs/07_outputs.md +++ b/docs/07_outputs.md @@ -1,10 +1,10 @@ -Outputs files may be aggregated including information for all samples or provided per sample. Per sample files will be prefixed with respective aliases and represented below as {{ alias }}. +Outputs files may be aggregated including information for all samples or provided per sample. Per-sample files will be prefixed with respective aliases and represented below as {{ alias }}. | Title | File path | Description | Per sample or aggregated | |-------|-----------|-------------|--------------------------| | workflow report | wf-transcriptomes-report.html | a HTML report document detailing the primary findings of the workflow | aggregated | | Per file read stats | fastq_ingress_results/reads/fastcat_stats/per-file-stats.tsv | A TSV with per file read stats, including all samples. | aggregated | -| Per file read stats | fastq_ingress_results/reads/fastcat_stats/per-read-stats.tsv | A TSV with per read stats, including all samples. | aggregated | +| Read stats | fastq_ingress_results/reads/fastcat_stats/per-read-stats.tsv | A TSV with per read stats, including all samples. | aggregated | | Run ID's | fastq_ingress_results/reads/fastcat_stats/run_ids | List of run IDs present in reads. | aggregated | | Meta map json | fastq_ingress_results/reads/metamap.json | Metadata used in workflow presented in a JSON. | aggregated | | Concatenated sequence data | fastq_ingress_results/reads/{{ alias }}.fastq.gz | Per sample reads concatenated in to one FASTQ file. | per-sample | @@ -15,7 +15,7 @@ Outputs files may be aggregated including information for all sample | Differential gene expression results | /de_analysis/results_dge.tsv | This is a gene-level result file that describes genes and the probability that they show differential expression between experimental conditions . | aggregated | | Differential gene expression report | /de_analysis/results_dge.pdf | Summary report of differential gene expression analysis as a PDF. | aggregated | | Differential transcript usage gene TSV | /de_analysis/results_dtu_gene.tsv | This is a gene-level result file from DEXSeq that lists annotated genes and their probabilities of differential expression. | aggregated | -| Differential gene expression report | /de_analysis/results_dtu.pdf | Summary report of differential transcript usage results as a PDF. | aggregated | +| Differential transcript usage report | /de_analysis/results_dtu.pdf | Summary report of differential transcript usage results as a PDF. | aggregated | | Differential transcript usage TSV | /de_analysis/results_dtu_transcript.tsv | This is a transcript-level result file from DEXSeq that lists annotated genes and their probabilities of differential expression. | aggregated | | Differential transcript usage stageR TSV | /de_analysis/results_dtu_stageR.tsv | This is the output from StageR and it shows both gene and transcript probabilities of differential expression | aggregated | | Differential transcript usage DEXSeq TSV | /de_analysis/results_dexseq.tsv | The complete output from the DEXSeq-analysis, shows both gene and transcript probabilities of differential expression. | aggregated | diff --git a/lib/NfcoreSchema.groovy b/lib/NfcoreSchema.groovy index 3b29be1..81fdc2e 100644 --- a/lib/NfcoreSchema.groovy +++ b/lib/NfcoreSchema.groovy @@ -141,7 +141,7 @@ class NfcoreSchema { for (specifiedParam in params.keySet()) { // nextflow params if (nf_params.contains(specifiedParam)) { - log.error "ERROR: You used a core Nextflow option with two hyphens: '--${specifiedParam}'. Please resubmit with '-${specifiedParam}'" + log.error "You used a core Nextflow option with two hyphens: '--${specifiedParam}'. Please resubmit with '-${specifiedParam}'" has_error = true } // unexpected params @@ -180,7 +180,7 @@ class NfcoreSchema { schema.validate(params_json) } catch (ValidationException e) { println '' - log.error 'ERROR: Validation of pipeline parameters failed!' + log.error 'Validation of pipeline parameters failed!' JSONObject exceptionJSON = e.toJSON() HashSet observed_exceptions = [] printExceptions(exceptionJSON, params_json, log, enums, raw_schema, observed_exceptions) diff --git a/lib/ingress.nf b/lib/ingress.nf index 5839730..b5d8dfa 100644 --- a/lib/ingress.nf +++ b/lib/ingress.nf @@ -240,6 +240,7 @@ process checkBamHeaders { label "ingress" label "wf_common" cpus 1 + memory "2 GB" input: tuple val(meta), path("input_dir/reads*.bam") output: // set the two env variables by `eval`-ing the output of the python script @@ -257,6 +258,7 @@ process mergeBams { label "ingress" label "wf_common" cpus 3 + memory "4 GB" input: tuple val(meta), path("input_bams/reads*.bam") output: tuple val(meta), path("reads.bam") shell: @@ -271,6 +273,7 @@ process catSortBams { label "ingress" label "wf_common" cpus 4 + memory "4 GB" input: tuple val(meta), path("input_bams/reads*.bam") output: tuple val(meta), path("reads.bam") script: @@ -285,6 +288,7 @@ process sortBam { label "ingress" label "wf_common" cpus 3 + memory "4 GB" input: tuple val(meta), path("reads.bam") output: tuple val(meta), path("reads.sorted.bam") script: @@ -298,6 +302,7 @@ process bamstats { label "ingress" label "wf_common" cpus 3 + memory "4 GB" input: tuple val(meta), path("reads.bam") output: @@ -414,6 +419,7 @@ process move_or_compress_fq_file { label "ingress" label "wf_common" cpus 1 + memory "2 GB" input: // don't stage `input` with a literal because we check the file extension tuple val(meta), path(input) @@ -439,6 +445,7 @@ process fastcat { label "ingress" label "wf_common" cpus 3 + memory "2 GB" input: tuple val(meta), path("input") val extra_args @@ -737,6 +744,7 @@ process validate_sample_sheet { cpus 1 label "ingress" label "wf_common" + memory "2 GB" input: path "sample_sheet.csv" val required_sample_types diff --git a/nextflow.config b/nextflow.config index 9911804..cd9c5dc 100644 --- a/nextflow.config +++ b/nextflow.config @@ -92,12 +92,12 @@ params { wf { example_cmd = [ - "--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'" + "--condition_sheet 'wf-transcriptomes-demo/condition_sheet.tsv'", + "--direct_rna", + "--fastq 'wf-transcriptomes-demo/differential_expression_fastq'", + "--minimap2_index_opts '-k15'", + "--ref_annotation 'wf-transcriptomes-demo/gencode.v22.annotation.chr20.gtf'", + "--ref_genome 'wf-transcriptomes-demo/hg38_chr20.fa'", ] agent = null container_sha = "shae7c9f184996a384e99be68e790f0612f0c732867" @@ -112,7 +112,7 @@ manifest { description = 'Transcriptome analysis including gene fusions, differential expression as well as assembly and annotation of cDNA and direct RNA sequencing data.' mainScript = 'main.nf' nextflowVersion = '>=23.04.2' - version = 'v0.4.2' + version = 'v1.0.0' } epi2melabs { diff --git a/output_definition.json b/output_definition.json index 4d4955a..98b0d77 100644 --- a/output_definition.json +++ b/output_definition.json @@ -18,7 +18,7 @@ }, "read-stats-per-read": { "filepath": "fastq_ingress_results/reads/fastcat_stats/per-read-stats.tsv", - "title": "Per file read stats", + "title": "Read stats", "description": "A TSV with per read stats, including all samples.", "mime-type": "text/tab-separated-values", "optional": false, @@ -106,7 +106,7 @@ }, "dtu-report-pdf": { "filepath": "/de_analysis/results_dtu.pdf", - "title": "Differential gene expression report", + "title": "Differential transcript usage report", "description": "Summary report of differential transcript usage results as a PDF.", "mime-type": "application/pdf", "optional": true, @@ -194,4 +194,4 @@ } } -} \ No newline at end of file +}