From d36c50aff6a16691d86de22fdbebba519a7065d0 Mon Sep 17 00:00:00 2001 From: Usman Rashid Date: Tue, 23 Apr 2024 18:11:41 +1200 Subject: [PATCH] Updated linting checks --- .github/workflows/linting.yml | 19 +++++- .nf-core.yml | 4 +- assets/multiqc_config.yml | 16 ----- docs/parameters.md | 119 +++++++++++++++++----------------- 4 files changed, 77 insertions(+), 81 deletions(-) delete mode 100644 assets/multiqc_config.yml diff --git a/.github/workflows/linting.yml b/.github/workflows/linting.yml index d2b8cea..b4aba65 100644 --- a/.github/workflows/linting.yml +++ b/.github/workflows/linting.yml @@ -53,9 +53,22 @@ jobs: GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} GITHUB_PR_COMMIT: ${{ github.event.pull_request.head.sha }} run: | - eval `ssh-agent -s` - ssh-add - <<< '${{ secrets.PFR_NXF_MODULES_SSH_KEY }}' - nf-core -l lint_log.txt lint --dir ${GITHUB_WORKSPACE} --markdown lint_results.md + nf-core -l lint_log.txt lint \ + --dir ${GITHUB_WORKSPACE} \ + --markdown lint_results.md \ + --key actions_ci \ + --key actions_schema_validation \ + --key files_exist \ + --key files_unchanged \ + --key merge_markers \ + --key nextflow_config \ + --key pipeline_name_conventions \ + --key pipeline_todos \ + --key readme \ + --key schema_description \ + --key schema_lint \ + --key schema_params \ + --key system_exit - name: Save PR number if: ${{ always() }} diff --git a/.nf-core.yml b/.nf-core.yml index a2b9401..42acee5 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -15,12 +15,10 @@ lint: - .github/ISSUE_TEMPLATE/bug_report.yml - docs/README.md - .github/CONTRIBUTING.md - multiqc_config: - - report_comment + - .github/workflows/linting.yml nextflow_config: - manifest.name - manifest.homePage - template_strings: False repository_type: pipeline template: prefix: plant-food-research-open diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml deleted file mode 100644 index 0b99513..0000000 --- a/assets/multiqc_config.yml +++ /dev/null @@ -1,16 +0,0 @@ -report_comment: > - - This report has been generated by the plant-food-research-open/assemblyqc - analysis pipeline. - -report_section_order: - "plant-food-research-open-assemblyqc-methods-description": - order: -1000 - software_versions: - order: -1001 - "plant-food-research-open-assemblyqc-summary": - order: -1002 - -export_plots: true - -disable_version_detection: true diff --git a/docs/parameters.md b/docs/parameters.md index 5be3940..f02e854 100644 --- a/docs/parameters.md +++ b/docs/parameters.md @@ -4,36 +4,36 @@ A NextFlow pipeline which evaluates assembly quality with multiple QC tools and ## Input/output options -| Parameter | Description | Type | Default | Required | Hidden | -| --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | -------- | ------ | -| `input` | Input assembly sheet in CSV format
HelpFASTA and other associated files for input assemblies provided as a formatted CSV file
| -| `outdir` | The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure. | `string` | ./results | True | | -| `email` | Email address for completion summary.
HelpSet this parameter to your e-mail address to get a summary e-mail with details of the run sent to you | +| Parameter | Description | Type | Default | Required | Hidden | +| --------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | --------- | -------- | ------ | +| `input` | Input assembly sheet in CSV format
HelpFASTA and other associated files for input assemblies provided as a formatted CSV file
| `string` | | True | | +| `outdir` | The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure. | `string` | ./results | True | | +| `email` | Email address for completion summary.
HelpSet this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.
| `string` | | | | ## General stats options -| Parameter | Description | Type | Default | Required | Hidden | -| ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ------- | -------- | ------ | -| `assemblathon_stats_n_limit` | The number of 'N's for the unknown gap size
HelpThis number is used to split the scaffolds into contigs to compute contig-r | +| Parameter | Description | Type | Default | Required | Hidden | +| ---------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ | +| `assemblathon_stats_n_limit` | The number of 'N's for the unknown gap size
HelpThis number is used to split the scaffolds into contigs to compute contig-related stats such as the number of contigs, N50, etc. NCBI recommendation is 100.
| `integer` | 100 | | | ## NCBI FCS options -| Parameter | Description | Type | Default | Required | Hidden | -| ------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ | -| `ncbi_fcs_adaptor_skip` | Skip NCBI FCS Adaptor checking | `boolean` | True | | | -| `ncbi_fcs_adaptor_empire` | Empire for NCBI FCS Adaptor checking
Help'euk' for eukaryotes, or 'prok' for prokaryotes
| `string` | | | -| `ncbi_fcs_gx_skip` | Skip NCBI FCS external organism contamination checking | `boolean` | True | | | -| `ncbi_fcs_gx_tax_id` | Tax ID for NCBI FCS GX
HelpGet correct tax ID from https://www.ncbi.nlm.nih.gov/taxonomy
| `number` | | | | -| `ncbi_fcs_gx_db_path` | Path to NCBI FCS GX database
HelpNCBI FCS GX DB path

Due to enormity of the DB size, the pipeline does NOT download the dat | +| Parameter | Description | Type | Default | Required | Hidden | +| ------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ | +| `ncbi_fcs_adaptor_skip` | Skip NCBI FCS Adaptor checking | `boolean` | True | | | +| `ncbi_fcs_adaptor_empire` | Empire for NCBI FCS Adaptor checking
Help'euk' for eukaryotes, or 'prok' for prokaryotes
| `string` | | | | +| `ncbi_fcs_gx_skip` | Skip NCBI FCS external organism contamination checking | `boolean` | True | | | +| `ncbi_fcs_gx_tax_id` | Tax ID for NCBI FCS GX
HelpGet correct tax ID from https://www.ncbi.nlm.nih.gov/taxonomy
| `number` | | | | +| `ncbi_fcs_gx_db_path` | Path to NCBI FCS GX database
HelpNCBI FCS GX DB path

Due to enormity of the DB size, the pipeline does NOT download the data. It must be setup by the user manually before running the pipeline. See instructions for DB setup: https://github.com/ncbi/fcs/wiki/FCS-GX
| `string` | | | | ## BUSCO options -| Parameter | Description | Type | Default | Required | Hidden | -| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------- | ------- | -------- | ------ | -| `busco_skip` | Skip BUSCO | `boolean` | True | | | -| `busco_mode` | BUSCO mode
Help'geno' or 'genome' for genome assemblies (DNA), 'tran' or 'transcriptome' for transcriptome assemblies (DNA), 'prot' or 'pro | -| `busco_lineage_datasets` | BUSCO lineages
HelpEach input assembly is assessed against each lineage. It should be provided as a space-separated list of lin | -| `busco_download_path` | Download path for BUSCO
HelpBUSCO DB download path

The pipeline automatically downloads the required DB if neededHelp'geno' or 'genome' for genome assemblies (DNA), 'tran' or 'transcriptome' for transcriptome assemblies (DNA), 'prot' or 'proteins' for annotated gene sets (protein)
| `string` | | | | +| `busco_lineage_datasets` | BUSCO lineages
HelpEach input assembly is assessed against each lineage. It should be provided as a space-separated list of lineages: 'fungi_odb10 microsporidia_odb10'
| `string` | | | | +| `busco_download_path` | Download path for BUSCO
HelpBUSCO DB download path

The pipeline automatically downloads the required DB if needed
| `string` | | | | ## TIDK options @@ -60,62 +60,63 @@ A NextFlow pipeline which evaluates assembly quality with multiple QC tools and ## HiC options | Parameter | Description | Type | Default | Required | Hidden | -| -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------- | ------------------------------------------------- | -------- | ------ | -| `hic` | HiC reads
HelpPath to reads provided as a SRA ID or as a path to paired reads with pattern '\*{1,2}.(fastq | fq).gz'
| `string` | | +| -------------------- | --------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------- | ------------------------------------------------- | -------- | ------ | --- | +| `hic` | HiC reads
HelpPath to reads provided as a SRA ID or as a path to paired reads with pattern '\*{1,2}.(fastq | fq).gz'
| `string` | | | | | `hic_skip_fastp` | Skip HiC read trimming | `boolean` | | | | | `hic_skip_fastqc` | Skip HiC read QC | `boolean` | | | | | `hic_fastp_ext_args` | Additional parameters for fastp trimming | `string` | --qualified_quality_phred 20 --length_required 50 | | | ## Synteny options -| Parameter | Description | Type | Default | Required | Hidden | -| ---------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ | -| `synteny_skip` | Skip synteny analysis | `boolean` | True | | | -| `synteny_between_input_assemblies` | Create syntenic plots between each pair of input assemblies | `boolean` | True | | | -| `synteny_many_to_many_align` | Include alignment blocks with many-to-many mappings (dnadiff .mcoords file) | `boolean` | | | | -| `synteny_max_gap` | Alignments within this distance are bundled together | `integer` | 1000000 | | | -| `synteny_min_bundle_size` | After bundling, any bundle smaller than this size is filtered out | `integer` | 1000 | | | -| `synteny_plot_1_vs_all` | Create a separate synteny plot for each contig of the target assembly versus all contigs of the reference assembly | `boolean` | True | | | -| `synteny_color_by_contig` | Synteny plot is colored by contig | `boolean` | True | | | -| `synteny_xref_assemblies` | Reference assemblies for synteny analysis
HelpFASTA and synteny label tsv files should be provided in a formatted CSV file HelpFASTA and synteny label tsv files should be provided in a formatted CSV file
| `string` | | | | ## Max job request options Set the top limit for requested resources for any single job. -| Parameter | Description | Type | Default | Required | Hidden | -| ------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---- | ------- | -------- | ------ | -| `max_cpus` | Maximum number of CPUs that can be requested for any single job.
HelpUse to set an upper-limit for the CPU requirement for each process. Shou | -| `max_memory` | Maximum amount of memory that can be requested for any single job.
HelpUse to set an upper-limit for the memory requirement for each proces | -| `max_time` | Maximum amount of time that can be requested for any single job.
HelpUse to set an upper-limit for the time requirement for each process. Sho | +| Parameter | Description | Type | Default | Required | Hidden | +| ------------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ | +| `max_cpus` | Maximum number of CPUs that can be requested for any single job.
HelpUse to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`
| `integer` | 16 | | True | +| `max_memory` | Maximum amount of memory that can be requested for any single job.
HelpUse to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`
| `string` | 512.GB | | True | +| `max_time` | Maximum amount of time that can be requested for any single job.
HelpUse to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`
| `string` | 7.day | | True | ## Institutional config options Parameters used to describe centralised config profiles. These should not be edited. -| Parameter | Description | Type | Default | Required | Hidden | -| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | ------- | -------- | ------ | -| `custom_config_version` | Git commit id for Institutional configs. | `string` | master | | True | -| `custom_config_base` | Base directory for Institutional configs.
HelpIf you're running offline, Nextflow will not be able to fetch the institutional confi | -| `config_profile_name` | Institutional config name. | `string` | | | True | -| `config_profile_description` | Institutional config description. | `string` | | | True | -| `config_profile_contact` | Institutional config contact information. | `string` | | | True | -| `config_profile_url` | Institutional config URL link. | `string` | | | True | +| Parameter | Description | Type | Default | Required | Hidden | +| ---------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------- | -------------------------------------------------------- | -------- | ------ | +| `custom_config_version` | Git commit id for Institutional configs. | `string` | master | | True | +| `custom_config_base` | Base directory for Institutional configs.
HelpIf you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.
| `string` | https://raw.githubusercontent.com/nf-core/configs/master | | True | +| `config_profile_name` | Institutional config name. | `string` | | | True | +| `config_profile_description` | Institutional config description. | `string` | | | True | +| `config_profile_contact` | Institutional config contact information. | `string` | | | True | +| `config_profile_url` | Institutional config URL link. | `string` | | | True | ## Generic options Less common options for the pipeline, typically set in a config file. -| Parameter | Description | Type | Default | Required | Hidden | -| ---------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | --------- | ------- | -------- | ------ | -| `help` | Display help text. | `boolean` | | | True | -| `version` | Display version and exit. | `boolean` | | | True | -| `publish_dir_mode` | Method used to save pipeline results to output directory.
HelpThe Nextflow `publishDir` option specifies which intermediate files sho | -| `email_on_fail` | Email address for completion summary, only when pipeline fails.
HelpAn email address to send a summary email to when the pipeline is com | -| `plaintext_email` | Send plain-text email instead of HTML. | `boolean` | | | True | -| `monochrome_logs` | Do not use coloured log outputs. | `boolean` | | | True | -| `hook_url` | Incoming hook URL for messaging service
HelpIncoming hook URL for messaging service. Currently, MS Teams and Slack are supported.HelpBy default, parameters set as _hidden_ in the schema are not shown on the command l | -| `validationFailUnrecognisedParams` | Validation of parameters fails when an unrecognised parameter is found.
HelpBy default, when an unrecognised paramete | -| `validationLenientMode` | Validation of parameters in lenient more.
HelpAllows string values that are parseable as numbers or booleans. For further inform | +| Parameter | Description | Type | Default | Required | Hidden | +| ---------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | --------- | ------- | -------- | ------ | +| `help` | Display help text. | `boolean` | | | True | +| `version` | Display version and exit. | `boolean` | | | True | +| `publish_dir_mode` | Method used to save pipeline results to output directory.
HelpThe Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.
| `string` | copy | | True | +| `email_on_fail` | Email address for completion summary, only when pipeline fails.
HelpAn email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.
| `string` | | | True | +| `plaintext_email` | Send plain-text email instead of HTML. | `boolean` | | | True | +| `monochrome_logs` | Do not use coloured log outputs. | `boolean` | | | True | +| `monochromeLogs` | Do not use coloured log outputs. | `boolean` | | | True | +| `hook_url` | Incoming hook URL for messaging service
HelpIncoming hook URL for messaging service. Currently, MS Teams and Slack are supported.
| `string` | | | True | +| `validate_params` | Boolean whether to validate parameters against the schema at runtime | `boolean` | True | | True | +| `validationShowHiddenParams` | Show all params when using `--help`
HelpBy default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters.
| `boolean` | | | True | +| `validationFailUnrecognisedParams` | Validation of parameters fails when an unrecognised parameter is found.
HelpBy default, when an unrecognised parameter is found, it returns a warinig.
| `boolean` | | | True | +| `validationLenientMode` | Validation of parameters in lenient more.
HelpAllows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode).
| `boolean` | | | True |