diff --git a/.github/CONTRIBUTING.md b/.github/CONTRIBUTING.md index 06fa6805..1fcaa542 100644 --- a/.github/CONTRIBUTING.md +++ b/.github/CONTRIBUTING.md @@ -116,4 +116,3 @@ To get started: Devcontainer specs: - [DevContainer config](.devcontainer/devcontainer.json) -- [Dockerfile](.devcontainer/Dockerfile) diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index 7fe6cd6d..34300c5d 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -42,7 +42,7 @@ body: attributes: label: System information description: | - * Nextflow version _(eg. 22.10.1)_ + * Nextflow version _(eg. 23.04.0)_ * Hardware _(eg. HPC, Desktop, Cloud)_ * Executor _(eg. slurm, local, awsbatch)_ * Container engine: _(e.g. Docker, Singularity, Conda, Podman, Shifter, Charliecloud, or Apptainer)_ diff --git a/.github/workflows/awsfulltest.yml b/.github/workflows/awsfulltest.yml index 06728e6d..b4ab0269 100644 --- a/.github/workflows/awsfulltest.yml +++ b/.github/workflows/awsfulltest.yml @@ -14,18 +14,23 @@ jobs: runs-on: ubuntu-latest steps: - name: Launch workflow via tower - uses: seqeralabs/action-tower-launch@v1 + uses: seqeralabs/action-tower-launch@v2 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} compute_env: ${{ secrets.TOWER_COMPUTE_ENV }} + revision: ${{ github.sha }} workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/funcscan/work-${{ github.sha }} parameters: | { + "hook_url": "${{ secrets.MEGATESTS_ALERTS_SLACK_HOOK_URL }}", "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/funcscan/results-${{ github.sha }}" } - profiles: test_full,aws_tower + profiles: test_full + - uses: actions/upload-artifact@v3 with: name: Tower debug log file - path: tower_action_*.log + path: | + tower_action_*.log + tower_action_*.json diff --git a/.github/workflows/awstest.yml b/.github/workflows/awstest.yml index b50ef8e8..cb05b166 100644 --- a/.github/workflows/awstest.yml +++ b/.github/workflows/awstest.yml @@ -12,18 +12,22 @@ jobs: steps: # Launch workflow using Tower CLI tool action - name: Launch workflow via tower - uses: seqeralabs/action-tower-launch@v1 + uses: seqeralabs/action-tower-launch@v2 with: workspace_id: ${{ secrets.TOWER_WORKSPACE_ID }} access_token: ${{ secrets.TOWER_ACCESS_TOKEN }} compute_env: ${{ secrets.TOWER_COMPUTE_ENV }} + revision: ${{ github.sha }} workdir: s3://${{ secrets.AWS_S3_BUCKET }}/work/funcscan/work-${{ github.sha }} parameters: | { "outdir": "s3://${{ secrets.AWS_S3_BUCKET }}/funcscan/results-test-${{ github.sha }}" } - profiles: test,aws_tower + profiles: test + - uses: actions/upload-artifact@v3 with: name: Tower debug log file - path: tower_action_*.log + path: | + tower_action_*.log + tower_action_*.json diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index ff568ad9..1d02035e 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -24,7 +24,7 @@ jobs: strategy: matrix: NXF_VER: - - "22.10.1" + - "23.04.0" - "latest-everything" parameters: - "--annotation_tool prodigal" @@ -52,7 +52,7 @@ jobs: strategy: matrix: NXF_VER: - - "22.10.1" + - "23.04.0" - "latest-everything" parameters: - "--annotation_tool prodigal" @@ -80,7 +80,7 @@ jobs: strategy: matrix: NXF_VER: - - "22.10.1" + - "23.04.0" - "latest-everything" parameters: - "--annotation_tool bakta --annotation_bakta_db_downloadtype light" diff --git a/.gitpod.yml b/.gitpod.yml index 85d95ecc..25488dcc 100644 --- a/.gitpod.yml +++ b/.gitpod.yml @@ -1,4 +1,9 @@ image: nfcore/gitpod:latest +tasks: + - name: Update Nextflow and setup pre-commit + command: | + pre-commit install --install-hooks + nextflow self-update vscode: extensions: # based on nf-core.nf-core-extensionpack diff --git a/CITATIONS.md b/CITATIONS.md index 73e74b41..97fe5961 100644 --- a/CITATIONS.md +++ b/CITATIONS.md @@ -20,7 +20,7 @@ - [AMPlify](https://doi.org/10.1186/s12864-022-08310-4) - > CLi, C., Sutherland, D., Hammond, S. A., Yang, C., Taho, F., Bergman, L., Houston, S., Warren, R. L., Wong, T., Hoang, L., Cameron, C. E., Helbing, C. C., & Birol, I. (2022). AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens. BMC genomics, 23(1), 77. [DOI: 10.1186/s12864-022-08310-4](https://doi.org/10.1186/s12864-022-08310-4) + > Li, C., Sutherland, D., Hammond, S. A., Yang, C., Taho, F., Bergman, L., Houston, S., Warren, R. L., Wong, T., Hoang, L., Cameron, C. E., Helbing, C. C., & Birol, I. (2022). AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens. BMC genomics, 23(1), 77. [DOI: 10.1186/s12864-022-08310-4](https://doi.org/10.1186/s12864-022-08310-4) - [AMRFinderPlus](https://doi.org/10.1038/s41598-021-91456-0) @@ -34,6 +34,14 @@ > Schwengers, O., Jelonek, L., Dieckmann, M. A., Beyvers, S., Blom, J., & Goesmann, A. (2021). Bakta: rapid and standardized annotation of bacterial genomes via alignment-free sequence identification. Microbial Genomics, 7(11). [DOI: 10.1099/mgen.0.000685](https://doi.org/10.1099/mgen.0.000685) +- [bioawk](https://github.com/lh3/bioawk) + + > Li, H. (2023). bioawk: BWK awk modified for biological data. Github. Retrieved July 12, 2023, from https://github.com/lh3/bioawk + +- [comBGC](https://github.com/nf-core/funcscan) + + > Frangenberg, J., Fellows Yates, J. A., Ibrahim, A., Perelo, L., & Beber, M. E. (2023). nf-core/funcscan: 1.0.0 - German Rollmops - 2023-02-15. https://doi.org/10.5281/zenodo.7643100 + - [DeepARG](https://doi.org/10.1186/s40168-018-0401-z) > Arango-Argoty, G., Garner, E., Pruden, A., Heath, L. S., Vikesland, P., & Zhang, L. (2018). DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data. Microbiome, 6(1), 23. [DOI: 10.1186/s40168-018-0401-z](https://doi.org/10.1186/s40168-018-0401-z) @@ -58,6 +66,10 @@ > Ibrahim, A. & Perelo, L. (2023). Darcy220606/AMPcombi. [DOI: 10.5281/zenodo.7639121](https://doi.org/10.5281/zenodo.7639121). +- [hAMRonization](https://github.com/pha4ge/hAMRonization) + + > Maguire, F., Fornika, D., Mendes, I., Phelan, J., Underwood, A., Witney, A., pvanheus, Manuele, A., Lee, T., amos, & imendes. (2023). pha4ge/hAMRonization: Zenodo Release. Zenodo. https://doi.org/10.5281/ZENODO.8131134 + - [HMMER](https://doi.org/10.1371/journal.pcbi.1002195.) > Eddy S. R. (2011). Accelerated Profile HMM Searches. PLoS computational biology, 7(10), e1002195. [DOI: 10.1371/journal.pcbi.1002195](https://doi.org/10.1371/journal.pcbi.1002195) @@ -98,5 +110,8 @@ - [Docker](https://dl.acm.org/doi/10.5555/2600239.2600241) + > Merkel, D. (2014). Docker: lightweight linux containers for consistent development and deployment. Linux Journal, 2014(239), 2. doi: 10.5555/2600239.2600241. + - [Singularity](https://pubmed.ncbi.nlm.nih.gov/28494014/) - > Kurtzer, G. M., Sochat, V., & Bauer, M. W. (2017). Singularity: Scientific containers for mobility of compute. PloS one, 12(5), e0177459. [DOI: 10.1371/journal.pone.0177459](https://doi.org/10.1371/journal.pone.0177459) + + > Kurtzer GM, Sochat V, Bauer MW. Singularity: Scientific containers for mobility of compute. PLoS One. 2017 May 11;12(5):e0177459. doi: 10.1371/journal.pone.0177459. eCollection 2017. PubMed PMID: 28494014; PubMed Central PMCID: PMC5426675. diff --git a/README.md b/README.md index 75eb5ec5..76eecfb7 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,8 @@ # ![nf-core/funscan](docs/images/nf-core-funcscan_logo_flat_light.png#gh-light-mode-only) ![nf-core/funscan](docs/images/nf-core-funcscan_logo_flat_dark.png#gh-dark-mode-only) [![AWS CI](https://img.shields.io/badge/CI%20tests-full%20size-FF9900?labelColor=000000&logo=Amazon%20AWS)](https://nf-co.re/funcscan/results)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.7643099-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.7643099) -[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A522.10.1-23aa62.svg)](https://www.nextflow.io/) +[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](https://www.nextflow.io/) + [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/) [![run with docker](https://img.shields.io/badge/run%20with-docker-0db7ed?labelColor=000000&logo=docker)](https://www.docker.com/) [![run with singularity](https://img.shields.io/badge/run%20with-singularity-1d355c.svg?labelColor=000000)](https://sylabs.io/docs/) @@ -67,11 +68,11 @@ nextflow run nf-core/funcscan \ > provided by the `-c` Nextflow option can be used to provide any configuration _**except for parameters**_; > see [docs](https://nf-co.re/usage/configuration#custom-configuration-files). -For more details, please refer to the [usage documentation](https://nf-co.re/funcscan/usage) and the [parameter documentation](https://nf-co.re/funcscan/parameters). +For more details and further functionality, please refer to the [usage documentation](https://nf-co.re/funcscan/usage) and the [parameter documentation](https://nf-co.re/funcscan/parameters). ## Pipeline output -To see the the results of a test run with a full size dataset refer to the [results](https://nf-co.re/funcscan/results) tab on the nf-core website pipeline page. +To see the results of an example test run with a full size dataset refer to the [results](https://nf-co.re/funcscan/results) tab on the nf-core website pipeline page. For more details about the output files and reports, please refer to the [output documentation](https://nf-co.re/funcscan/output). diff --git a/assets/methods_description_template.yml b/assets/methods_description_template.yml index 450fdf91..2cc2aa50 100644 --- a/assets/methods_description_template.yml +++ b/assets/methods_description_template.yml @@ -3,17 +3,21 @@ description: "Suggested text and references to use when describing pipeline usag section_name: "nf-core/funcscan Methods Description" section_href: "https://github.com/nf-core/funcscan" plot_type: "html" -## TODO nf-core: Update the HTML below to your prefered methods description, e.g. add publication citation for this pipeline +## TODO nf-core: Update the HTML below to your preferred methods description, e.g. add publication citation for this pipeline ## You inject any metadata in the Nextflow '${workflow}' object data: |

Methods

-

Data was processed using nf-core/funcscan v${workflow.manifest.version} ${doi_text} of the nf-core collection of workflows (Ewels et al., 2020).

+

Data was processed using nf-core/funcscan v${workflow.manifest.version} ${doi_text} of the nf-core collection of workflows (Ewels et al., 2020), utilising reproducible software environments from the Bioconda (Grüning et al., 2018) and Biocontainers (da Veiga Leprevost et al., 2017) projects.

The pipeline was executed with Nextflow v${workflow.nextflow.version} (Di Tommaso et al., 2017) with the following command:

${workflow.commandLine}
+

${tool_citations}

References

Notes:
diff --git a/assets/multiqc_config.yml b/assets/multiqc_config.yml index 356df32d..88589ded 100644 --- a/assets/multiqc_config.yml +++ b/assets/multiqc_config.yml @@ -1,7 +1,7 @@ report_comment: > - This report has been generated by the nf-core/funcscan + This report has been generated by the nf-core/funcscan analysis pipeline. For information about how to interpret these results, please see the - documentation. + documentation. report_section_order: "nf-core-funcscan-methods-description": order: -1000 diff --git a/assets/nf-core-funcscan_logo_light.png b/assets/nf-core-funcscan_logo_light.png index 2971be16..f00d53e8 100644 Binary files a/assets/nf-core-funcscan_logo_light.png and b/assets/nf-core-funcscan_logo_light.png differ diff --git a/assets/slackreport.json b/assets/slackreport.json index 043d02f2..501716d6 100644 --- a/assets/slackreport.json +++ b/assets/slackreport.json @@ -3,7 +3,7 @@ { "fallback": "Plain-text summary of the attachment.", "color": "<% if (success) { %>good<% } else { %>danger<%} %>", - "author_name": "sanger-tol/readmapping v${version} - ${runName}", + "author_name": "nf-core/funcscan v${version} - ${runName}", "author_icon": "https://www.nextflow.io/docs/latest/_static/favicon.ico", "text": "<% if (success) { %>Pipeline completed successfully!<% } else { %>Pipeline completed with errors<% } %>", "fields": [ diff --git a/conf/test_full.config b/conf/test_full.config index 9d64e003..e8622529 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -10,8 +10,6 @@ ---------------------------------------------------------------------------------------- */ -cleanup = true - params { config_profile_name = 'Full test profile' config_profile_description = 'Full test dataset to check pipeline function' diff --git a/docs/usage.md b/docs/usage.md index 39822a51..cf9ba24f 100644 --- a/docs/usage.md +++ b/docs/usage.md @@ -249,7 +249,8 @@ If you wish to repeatedly use the same parameters for multiple runs, rather than Pipeline settings can be provided in a `yaml` or `json` file via `-params-file `. > ⚠️ Do not use `-c ` to specify parameters as this will result in errors. Custom config files specified with `-c` must only be used for [tuning process resource specifications](https://nf-co.re/docs/usage/configuration#tuning-workflow-resources), other infrastructural tweaks (such as output directories), or module arguments (args). -> The above pipeline run specified with a params file in yaml format: + +The above pipeline run specified with a params file in yaml format: ```bash nextflow run nf-core/funcscan -profile docker -params-file params.yaml @@ -261,7 +262,6 @@ with `params.yaml` containing: input: './samplesheet.csv' outdir: './results/' genome: 'GRCh37' -input: 'data' <...> ``` diff --git a/lib/NfcoreSchema.groovy b/lib/NfcoreSchema.groovy deleted file mode 100755 index 9b34804d..00000000 --- a/lib/NfcoreSchema.groovy +++ /dev/null @@ -1,530 +0,0 @@ -// -// This file holds several functions used to perform JSON parameter validation, help and summary rendering for the nf-core pipeline template. -// - -import nextflow.Nextflow -import org.everit.json.schema.Schema -import org.everit.json.schema.loader.SchemaLoader -import org.everit.json.schema.ValidationException -import org.json.JSONObject -import org.json.JSONTokener -import org.json.JSONArray -import groovy.json.JsonSlurper -import groovy.json.JsonBuilder - -class NfcoreSchema { - - // - // Resolve Schema path relative to main workflow directory - // - public static String getSchemaPath(workflow, schema_filename='nextflow_schema.json') { - return "${workflow.projectDir}/${schema_filename}" - } - - // - // Function to loop over all parameters defined in schema and check - // whether the given parameters adhere to the specifications - // - /* groovylint-disable-next-line UnusedPrivateMethodParameter */ - public static void validateParameters(workflow, params, log, schema_filename='nextflow_schema.json') { - def has_error = false - //~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~// - // Check for nextflow core params and unexpected params - def json = new File(getSchemaPath(workflow, schema_filename=schema_filename)).text - def Map schemaParams = (Map) new JsonSlurper().parseText(json).get('definitions') - def nf_params = [ - // Options for base `nextflow` command - 'bg', - 'c', - 'C', - 'config', - 'd', - 'D', - 'dockerize', - 'h', - 'log', - 'q', - 'quiet', - 'syslog', - 'v', - - // Options for `nextflow run` command - 'ansi', - 'ansi-log', - 'bg', - 'bucket-dir', - 'c', - 'cache', - 'config', - 'dsl2', - 'dump-channels', - 'dump-hashes', - 'E', - 'entry', - 'latest', - 'lib', - 'main-script', - 'N', - 'name', - 'offline', - 'params-file', - 'pi', - 'plugins', - 'poll-interval', - 'pool-size', - 'profile', - 'ps', - 'qs', - 'queue-size', - 'r', - 'resume', - 'revision', - 'stdin', - 'stub', - 'stub-run', - 'test', - 'w', - 'with-apptainer', - 'with-charliecloud', - 'with-conda', - 'with-dag', - 'with-docker', - 'with-mpi', - 'with-notification', - 'with-podman', - 'with-report', - 'with-singularity', - 'with-timeline', - 'with-tower', - 'with-trace', - 'with-weblog', - 'without-docker', - 'without-podman', - 'work-dir' - ] - def unexpectedParams = [] - - // Collect expected parameters from the schema - def expectedParams = [] - def enums = [:] - for (group in schemaParams) { - for (p in group.value['properties']) { - expectedParams.push(p.key) - if (group.value['properties'][p.key].containsKey('enum')) { - enums[p.key] = group.value['properties'][p.key]['enum'] - } - } - } - - 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}'" - has_error = true - } - // unexpected params - def params_ignore = params.schema_ignore_params.split(',') + 'schema_ignore_params' - def expectedParamsLowerCase = expectedParams.collect{ it.replace("-", "").toLowerCase() } - def specifiedParamLowerCase = specifiedParam.replace("-", "").toLowerCase() - def isCamelCaseBug = (specifiedParam.contains("-") && !expectedParams.contains(specifiedParam) && expectedParamsLowerCase.contains(specifiedParamLowerCase)) - if (!expectedParams.contains(specifiedParam) && !params_ignore.contains(specifiedParam) && !isCamelCaseBug) { - // Temporarily remove camelCase/camel-case params #1035 - def unexpectedParamsLowerCase = unexpectedParams.collect{ it.replace("-", "").toLowerCase()} - if (!unexpectedParamsLowerCase.contains(specifiedParamLowerCase)){ - unexpectedParams.push(specifiedParam) - } - } - } - - //~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~// - // Validate parameters against the schema - InputStream input_stream = new File(getSchemaPath(workflow, schema_filename=schema_filename)).newInputStream() - JSONObject raw_schema = new JSONObject(new JSONTokener(input_stream)) - - // Remove anything that's in params.schema_ignore_params - raw_schema = removeIgnoredParams(raw_schema, params) - - Schema schema = SchemaLoader.load(raw_schema) - - // Clean the parameters - def cleanedParams = cleanParameters(params) - - // Convert to JSONObject - def jsonParams = new JsonBuilder(cleanedParams) - JSONObject params_json = new JSONObject(jsonParams.toString()) - - // Validate - try { - schema.validate(params_json) - } catch (ValidationException e) { - println '' - log.error 'ERROR: Validation of pipeline parameters failed!' - JSONObject exceptionJSON = e.toJSON() - printExceptions(exceptionJSON, params_json, log, enums) - println '' - has_error = true - } - - // Check for unexpected parameters - if (unexpectedParams.size() > 0) { - Map colors = NfcoreTemplate.logColours(params.monochrome_logs) - println '' - def warn_msg = 'Found unexpected parameters:' - for (unexpectedParam in unexpectedParams) { - warn_msg = warn_msg + "\n* --${unexpectedParam}: ${params[unexpectedParam].toString()}" - } - log.warn warn_msg - log.info "- ${colors.dim}Ignore this warning: params.schema_ignore_params = \"${unexpectedParams.join(',')}\" ${colors.reset}" - println '' - } - - if (has_error) { - Nextflow.error('Exiting!') - } - } - - // - // Beautify parameters for --help - // - public static String paramsHelp(workflow, params, command, schema_filename='nextflow_schema.json') { - Map colors = NfcoreTemplate.logColours(params.monochrome_logs) - Integer num_hidden = 0 - String output = '' - output += 'Typical pipeline command:\n\n' - output += " ${colors.cyan}${command}${colors.reset}\n\n" - Map params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename)) - Integer max_chars = paramsMaxChars(params_map) + 1 - Integer desc_indent = max_chars + 14 - Integer dec_linewidth = 160 - desc_indent - for (group in params_map.keySet()) { - Integer num_params = 0 - String group_output = colors.underlined + colors.bold + group + colors.reset + '\n' - def group_params = params_map.get(group) // This gets the parameters of that particular group - for (param in group_params.keySet()) { - if (group_params.get(param).hidden && !params.show_hidden_params) { - num_hidden += 1 - continue; - } - def type = '[' + group_params.get(param).type + ']' - def description = group_params.get(param).description - def defaultValue = group_params.get(param).default != null ? " [default: " + group_params.get(param).default.toString() + "]" : '' - def description_default = description + colors.dim + defaultValue + colors.reset - // Wrap long description texts - // Loosely based on https://dzone.com/articles/groovy-plain-text-word-wrap - if (description_default.length() > dec_linewidth){ - List olines = [] - String oline = "" // " " * indent - description_default.split(" ").each() { wrd -> - if ((oline.size() + wrd.size()) <= dec_linewidth) { - oline += wrd + " " - } else { - olines += oline - oline = wrd + " " - } - } - olines += oline - description_default = olines.join("\n" + " " * desc_indent) - } - group_output += " --" + param.padRight(max_chars) + colors.dim + type.padRight(10) + colors.reset + description_default + '\n' - num_params += 1 - } - group_output += '\n' - if (num_params > 0){ - output += group_output - } - } - if (num_hidden > 0){ - output += colors.dim + "!! Hiding $num_hidden params, use --show_hidden_params to show them !!\n" + colors.reset - } - output += NfcoreTemplate.dashedLine(params.monochrome_logs) - return output - } - - // - // Groovy Map summarising parameters/workflow options used by the pipeline - // - public static LinkedHashMap paramsSummaryMap(workflow, params, schema_filename='nextflow_schema.json') { - // Get a selection of core Nextflow workflow options - def Map workflow_summary = [:] - if (workflow.revision) { - workflow_summary['revision'] = workflow.revision - } - workflow_summary['runName'] = workflow.runName - if (workflow.containerEngine) { - workflow_summary['containerEngine'] = workflow.containerEngine - } - if (workflow.container) { - workflow_summary['container'] = workflow.container - } - workflow_summary['launchDir'] = workflow.launchDir - workflow_summary['workDir'] = workflow.workDir - workflow_summary['projectDir'] = workflow.projectDir - workflow_summary['userName'] = workflow.userName - workflow_summary['profile'] = workflow.profile - workflow_summary['configFiles'] = workflow.configFiles.join(', ') - - // Get pipeline parameters defined in JSON Schema - def Map params_summary = [:] - def params_map = paramsLoad(getSchemaPath(workflow, schema_filename=schema_filename)) - for (group in params_map.keySet()) { - def sub_params = new LinkedHashMap() - def group_params = params_map.get(group) // This gets the parameters of that particular group - for (param in group_params.keySet()) { - if (params.containsKey(param)) { - def params_value = params.get(param) - def schema_value = group_params.get(param).default - def param_type = group_params.get(param).type - if (schema_value != null) { - if (param_type == 'string') { - if (schema_value.contains('$projectDir') || schema_value.contains('${projectDir}')) { - def sub_string = schema_value.replace('\$projectDir', '') - sub_string = sub_string.replace('\${projectDir}', '') - if (params_value.contains(sub_string)) { - schema_value = params_value - } - } - if (schema_value.contains('$params.outdir') || schema_value.contains('${params.outdir}')) { - def sub_string = schema_value.replace('\$params.outdir', '') - sub_string = sub_string.replace('\${params.outdir}', '') - if ("${params.outdir}${sub_string}" == params_value) { - schema_value = params_value - } - } - } - } - - // We have a default in the schema, and this isn't it - if (schema_value != null && params_value != schema_value) { - sub_params.put(param, params_value) - } - // No default in the schema, and this isn't empty - else if (schema_value == null && params_value != "" && params_value != null && params_value != false) { - sub_params.put(param, params_value) - } - } - } - params_summary.put(group, sub_params) - } - return [ 'Core Nextflow options' : workflow_summary ] << params_summary - } - - // - // Beautify parameters for summary and return as string - // - public static String paramsSummaryLog(workflow, params) { - Map colors = NfcoreTemplate.logColours(params.monochrome_logs) - String output = '' - def params_map = paramsSummaryMap(workflow, params) - def max_chars = paramsMaxChars(params_map) - for (group in params_map.keySet()) { - def group_params = params_map.get(group) // This gets the parameters of that particular group - if (group_params) { - output += colors.bold + group + colors.reset + '\n' - for (param in group_params.keySet()) { - output += " " + colors.blue + param.padRight(max_chars) + ": " + colors.green + group_params.get(param) + colors.reset + '\n' - } - output += '\n' - } - } - output += "!! Only displaying parameters that differ from the pipeline defaults !!\n" - output += NfcoreTemplate.dashedLine(params.monochrome_logs) - return output - } - - // - // Loop over nested exceptions and print the causingException - // - private static void printExceptions(ex_json, params_json, log, enums, limit=5) { - def causingExceptions = ex_json['causingExceptions'] - if (causingExceptions.length() == 0) { - def m = ex_json['message'] =~ /required key \[([^\]]+)\] not found/ - // Missing required param - if (m.matches()) { - log.error "* Missing required parameter: --${m[0][1]}" - } - // Other base-level error - else if (ex_json['pointerToViolation'] == '#') { - log.error "* ${ex_json['message']}" - } - // Error with specific param - else { - def param = ex_json['pointerToViolation'] - ~/^#\// - def param_val = params_json[param].toString() - if (enums.containsKey(param)) { - def error_msg = "* --${param}: '${param_val}' is not a valid choice (Available choices" - if (enums[param].size() > limit) { - log.error "${error_msg} (${limit} of ${enums[param].size()}): ${enums[param][0..limit-1].join(', ')}, ... )" - } else { - log.error "${error_msg}: ${enums[param].join(', ')})" - } - } else { - log.error "* --${param}: ${ex_json['message']} (${param_val})" - } - } - } - for (ex in causingExceptions) { - printExceptions(ex, params_json, log, enums) - } - } - - // - // Remove an element from a JSONArray - // - private static JSONArray removeElement(json_array, element) { - def list = [] - int len = json_array.length() - for (int i=0;i - if(raw_schema.keySet().contains('definitions')){ - raw_schema.definitions.each { definition -> - for (key in definition.keySet()){ - if (definition[key].get("properties").keySet().contains(ignore_param)){ - // Remove the param to ignore - definition[key].get("properties").remove(ignore_param) - // If the param was required, change this - if (definition[key].has("required")) { - def cleaned_required = removeElement(definition[key].required, ignore_param) - definition[key].put("required", cleaned_required) - } - } - } - } - } - if(raw_schema.keySet().contains('properties') && raw_schema.get('properties').keySet().contains(ignore_param)) { - raw_schema.get("properties").remove(ignore_param) - } - if(raw_schema.keySet().contains('required') && raw_schema.required.contains(ignore_param)) { - def cleaned_required = removeElement(raw_schema.required, ignore_param) - raw_schema.put("required", cleaned_required) - } - } - return raw_schema - } - - // - // Clean and check parameters relative to Nextflow native classes - // - private static Map cleanParameters(params) { - def new_params = params.getClass().newInstance(params) - for (p in params) { - // remove anything evaluating to false - if (!p['value']) { - new_params.remove(p.key) - } - // Cast MemoryUnit to String - if (p['value'].getClass() == nextflow.util.MemoryUnit) { - new_params.replace(p.key, p['value'].toString()) - } - // Cast Duration to String - if (p['value'].getClass() == nextflow.util.Duration) { - new_params.replace(p.key, p['value'].toString().replaceFirst(/d(?!\S)/, "day")) - } - // Cast LinkedHashMap to String - if (p['value'].getClass() == LinkedHashMap) { - new_params.replace(p.key, p['value'].toString()) - } - } - return new_params - } - - // - // This function tries to read a JSON params file - // - private static LinkedHashMap paramsLoad(String json_schema) { - def params_map = new LinkedHashMap() - try { - params_map = paramsRead(json_schema) - } catch (Exception e) { - println "Could not read parameters settings from JSON. $e" - params_map = new LinkedHashMap() - } - return params_map - } - - // - // Method to actually read in JSON file using Groovy. - // Group (as Key), values are all parameters - // - Parameter1 as Key, Description as Value - // - Parameter2 as Key, Description as Value - // .... - // Group - // - - private static LinkedHashMap paramsRead(String json_schema) throws Exception { - def json = new File(json_schema).text - def Map schema_definitions = (Map) new JsonSlurper().parseText(json).get('definitions') - def Map schema_properties = (Map) new JsonSlurper().parseText(json).get('properties') - /* Tree looks like this in nf-core schema - * definitions <- this is what the first get('definitions') gets us - group 1 - title - description - properties - parameter 1 - type - description - parameter 2 - type - description - group 2 - title - description - properties - parameter 1 - type - description - * properties <- parameters can also be ungrouped, outside of definitions - parameter 1 - type - description - */ - - // Grouped params - def params_map = new LinkedHashMap() - schema_definitions.each { key, val -> - def Map group = schema_definitions."$key".properties // Gets the property object of the group - def title = schema_definitions."$key".title - def sub_params = new LinkedHashMap() - group.each { innerkey, value -> - sub_params.put(innerkey, value) - } - params_map.put(title, sub_params) - } - - // Ungrouped params - def ungrouped_params = new LinkedHashMap() - schema_properties.each { innerkey, value -> - ungrouped_params.put(innerkey, value) - } - params_map.put("Other parameters", ungrouped_params) - - return params_map - } - - // - // Get maximum number of characters across all parameter names - // - private static Integer paramsMaxChars(params_map) { - Integer max_chars = 0 - for (group in params_map.keySet()) { - def group_params = params_map.get(group) // This gets the parameters of that particular group - for (param in group_params.keySet()) { - if (param.size() > max_chars) { - max_chars = param.size() - } - } - } - return max_chars - } -} diff --git a/lib/NfcoreTemplate.groovy b/lib/NfcoreTemplate.groovy index 25a0a74a..408951ae 100755 --- a/lib/NfcoreTemplate.groovy +++ b/lib/NfcoreTemplate.groovy @@ -128,7 +128,7 @@ class NfcoreTemplate { def email_html = html_template.toString() // Render the sendmail template - def max_multiqc_email_size = params.max_multiqc_email_size as nextflow.util.MemoryUnit + def max_multiqc_email_size = (params.containsKey('max_multiqc_email_size') ? params.max_multiqc_email_size : 0) as nextflow.util.MemoryUnit def smail_fields = [ email: email_address, subject: subject, email_txt: email_txt, email_html: email_html, projectDir: "$projectDir", mqcFile: mqc_report, mqcMaxSize: max_multiqc_email_size.toBytes() ] def sf = new File("$projectDir/assets/sendmail_template.txt") def sendmail_template = engine.createTemplate(sf).make(smail_fields) diff --git a/lib/WorkflowFuncscan.groovy b/lib/WorkflowFuncscan.groovy index c70f4940..2a435f05 100755 --- a/lib/WorkflowFuncscan.groovy +++ b/lib/WorkflowFuncscan.groovy @@ -11,6 +11,7 @@ class WorkflowFuncscan { // Check and validate parameters // public static void initialise(params, log) { + genomeExistsError(params, log) //if (!params.fasta) { @@ -45,15 +46,136 @@ class WorkflowFuncscan { return yaml_file_text } - public static String methodsDescriptionText(run_workflow, mqc_methods_yaml) { + // + // Generate methods description for MultiQC + // + + public static String toolCitationText(params) { + + def preprocessing_text = "The pipeline used the following tools: preprocessing included bioawk (Li 2023)." + + def annotation_text = [ + "Annotation was carried out with:", + params.annotation_tool == 'prodigal' ? "Prodigal (Hyatt et al. 2010)." : "", + params.annotation_tool == 'pyrodigal' ? "Pyrodigal (Larralde 2022)." : "", + params.annotation_tool == 'bakta' ? "BAKTA (Schwengers et al. 2021)." : "", + params.annotation_tool == 'prokka' ? "PROKKA (Seemann 2014)." : "", + ].join(' ').trim() + + def amp_text = [ + "The following antimicrobial peptide screening tools were used:", + !params.amp_skip_amplify ? "AMPlify (Li et al. 2022)," : "", + !params.amp_skip_macrel ? "Macrel (Santos-Júnior et al. 2020)," : "", + !params.amp_skip_ampir ? "ampir (Fingerhut et al. 2021)," : "", + !params.amp_skip_hmmsearch ? "HMMER (Eddy 2011)," : "", + ". The output from the antimicrobial peptide screening tools were standardised and summarised with AMPcombi (Ibrahim and Perelo 2023)." + ].join(' ').trim().replaceAll(", \\.", ".") + + def arg_text = [ + "The following antimicrobial resistance gene screening tools were used:", + !params.arg_skip_fargene ? "fARGene (Berglund et al. 2019)," : "", + !params.arg_skip_rgi ? "RGI (Alcock et al. 2020)," : "", + !params.arg_skip_amrfinderplus ? "AMRfinderplus (Feldgarden et al. 2021)," : "", + !params.arg_skip_deeparg ? "deepARG (Arango-Argoty 2018)," : "", + !params.arg_skip_abricate ? "ABRicate (Seemann 2020)," : "", + ". The output from the antimicrobial resistance gene screening tools were standardised and summarised with hAMRonization (Maguire et al. 2023)." + ].join(' ').trim().replaceAll(", +\\.", ".") + + def bgc_text = [ + "The following biosynthetic gene cluster screening tools were used:", + !params.bgc_skip_antismash ? "antiSMASH (Blin et al. 2021)," : "", + !params.bgc_skip_deepbgc ? "deepBGC (Hannigan et al. 2019)," : "", + !params.bgc_skip_gecco ? "GECCO (Carroll et al. 2021)," : "", + !params.bgc_skip_hmmsearch ? "HMMER (Eddy 2011)," : "", + ". The output from the biosynthetic gene cluster screening tools were standardised and summarised with comBGC (Frangenberg et al. 2023)." + ].join(' ').replaceAll(", +\\.", ".").trim() + + def postprocessing_text = "Run statistics were reported using MultiQC (Ewels et al. 2016)." + + def citation_text = [ + preprocessing_text, + annotation_text, + params.run_amp_screening ? amp_text : "", + params.run_arg_screening ? arg_text : "", + params.run_bgc_screening ? bgc_text : "", + postprocessing_text, + ].join(' ').trim() + + return citation_text + } + + public static String toolBibliographyText(params) { + + def preprocessing_text = "
  • Li, H. (2023). bioawk: BWK awk modified for biological data. Github. Retrieved July 12, 2023, from https://github.com/lh3/bioawk
    • " + + + // TODO DUPLCIATED HMMSEARCH + def annotation_text = [ + params.annotation_tool == 'prodigal' ? "
  • Hyatt, D., Chen, G. L., Locascio, P. F., Land, M. L., Larimer, F. W., & Hauser, L. J. (2010). Prodigal: prokaryotic gene recognition and translation initiation site identification. BMC bioinformatics, 11, 119. DOI: 10.1186/1471-2105-11-119" : "", + params.annotation_tool == 'pyrodigal' ? "
  • Larralde, M. (2022). Pyrodigal: Python bindings and interface to Prodigal, an efficient method for gene prediction in prokaryotes. Journal of Open Source Software, 7(72), 4296. DOI: 10.21105/joss.04296
    • " : "", + params.annotation_tool == 'bakta' ? "
  • Schwengers, O., Jelonek, L., Dieckmann, M. A., Beyvers, S., Blom, J., & Goesmann, A. (2021). Bakta: rapid and standardized annotation of bacterial genomes via alignment-free sequence identification. Microbial Genomics, 7(11). DOI: 10.1099/mgen.0.000685
    • " : "", + params.annotation_tool == 'prokka' ? "
  • Seemann, T. (2014). Prokka: rapid prokaryotic genome annotation. Bioinformatics (Oxford, England), 30(14), 2068–2069. DOI: 10.1093/bioinformatics/btu153
    • " : "", + ].join(' ').trim() + + def amp_text = [ + !params.amp_skip_amplify ? "
  • Li, C., Sutherland, D., Hammond, S. A., Yang, C., Taho, F., Bergman, L., Houston, S., Warren, R. L., Wong, T., Hoang, L., Cameron, C. E., Helbing, C. C., & Birol, I. (2022). AMPlify: attentive deep learning model for discovery of novel antimicrobial peptides effective against WHO priority pathogens. BMC genomics, 23(1), 77. DOI: 10.1186/s12864-022-08310-4
    • " : "", + !params.amp_skip_macrel ? "
  • Santos-Júnior, C. D., Pan, S., Zhao, X. M., & Coelho, L. P. (2020). Macrel: antimicrobial peptide screening in genomes and metagenomes. PeerJ, 8, e10555. DOI: 10.7717/peerj.10555
    • " : "", + !params.amp_skip_ampir ? "
  • Fingerhut, L., Miller, D. J., Strugnell, J. M., Daly, N. L., & Cooke, I. R. (2021). ampir: an R package for fast genome-wide prediction of antimicrobial peptides. Bioinformatics (Oxford, England), 36(21), 5262–5263. DOI: 10.1093/bioinformatics/btaa653
    • " : "", + "
  • Ibrahim, A. & Perelo, L. (2023). Darcy220606/AMPcombi. DOI: 10.5281/zenodo.7639121
    • " + ].join(' ').trim().replaceAll(", \\.", ".") + + def arg_text = [ + !params.arg_skip_fargene ? "
  • Berglund, F., Österlund, T., Boulund, F., Marathe, N. P., Larsson, D., & Kristiansson, E. (2019). Identification and reconstruction of novel antibiotic resistance genes from metagenomes. Microbiome, 7(1), 52. DOI: 10.1186/s40168-019-0670-1
    • " : "", + !params.arg_skip_rgi ? "
  • Alcock, B. P., Raphenya, A. R., Lau, T., Tsang, K. K., Bouchard, M., Edalatmand, A., Huynh, W., Nguyen, A. V., Cheng, A. A., Liu, S., Min, S. Y., Miroshnichenko, A., Tran, H. K., Werfalli, R. E., Nasir, J. A., Oloni, M., Speicher, D. J., Florescu, A., Singh, B., Faltyn, M., … McArthur, A. G. (2020). CARD 2020: antibiotic resistome surveillance with the comprehensive antibiotic resistance database. Nucleic acids research, 48(D1), D517–D525. DOI: 10.1093/nar/gkz935
    • " : "", + !params.arg_skip_amrfinderplus ? "
  • Feldgarden, M., Brover, V., Gonzalez-Escalona, N., Frye, J. G., Haendiges, J., Haft, D. H., Hoffmann, M., Pettengill, J. B., Prasad, A. B., Tillman, G. E., Tyson, G. H., & Klimke, W. (2021). AMRFinderPlus and the Reference Gene Catalog facilitate examination of the genomic links among antimicrobial resistance, stress response, and virulence. Scientific reports, 11(1), 12728. DOI: 10.1038/s41598-021-91456-0
    • " : "", + !params.arg_skip_deeparg ? "
  • Arango-Argoty, G., Garner, E., Pruden, A., Heath, L. S., Vikesland, P., & Zhang, L. (2018). DeepARG: a deep learning approach for predicting antibiotic resistance genes from metagenomic data. Microbiome, 6(1), 23. DOI: 10.1186/s40168-018-0401-z" : "", + !params.arg_skip_abricate ? "
  • Seemann, T. (2020). ABRicate. Github https://github.com/tseemann/abricate.
    • " : "", + "
  • Public Health Alliance for Genomic Epidemiology (pha4ge). (2022). Parse multiple Antimicrobial Resistance Analysis Reports into a common data structure. Github. Retrieved October 5, 2022, from https://github.com/pha4ge/hAMRonization
    • " + ].join(' ').trim().replaceAll(", +\\.", ".") + + def bgc_text = [ + !params.bgc_skip_antismash ? "
  • Blin, K., Shaw, S., Kloosterman, A. M., Charlop-Powers, Z., van Wezel, G. P., Medema, M. H., & Weber, T. (2021). antiSMASH 6.0: improving cluster detection and comparison capabilities. Nucleic acids research, 49(W1), W29–W35. DOI:
    • " : "", + !params.bgc_skip_deepbgc ? "
  • Hannigan, G. D., Prihoda, D., Palicka, A., Soukup, J., Klempir, O., Rampula, L., Durcak, J., Wurst, M., Kotowski, J., Chang, D., Wang, R., Piizzi, G., Temesi, G., Hazuda, D. J., Woelk, C. H., & Bitton, D. A. (2019). A deep learning genome-mining strategy for biosynthetic gene cluster prediction. Nucleic acids research, 47(18), e110. DOI: 10.1093/nar/gkz654
    • " : "", + !params.bgc_skip_gecco ? "
  • Carroll, L. M. , Larralde, M., Fleck, J. S., Ponnudurai, R., Milanese, A., Cappio Barazzone, E. & Zeller, G. (2021). Accurate de novo identification of biosynthetic gene clusters with GECCO. bioRxiv DOI: 0.1101/2021.05.03.442509
    • " : "", + "
  • Frangenberg, J. Fellows Yates, J. A., Ibrahim, A., Perelo, L., & Beber, M. E. (2023). nf-core/funcscan: 1.0.0 - German Rollmops - 2023-02-15. https://doi.org/10.5281/zenodo.7643100
    • " + ].join(' ').replaceAll(", +\\.", ".").trim() + + def postprocessing_text = "
  • Ewels, P., Magnusson, M., Lundin, S., & Käller, M. (2016). MultiQC: summarize analysis results for multiple tools and samples in a single report. Bioinformatics , 32(19), 3047–3048. https://doi.org/10.1093/bioinformatics/btw354
    • " + + // Special as reused in multiple subworkflows, and we don't want to cause duplicates + def hmmsearch_text = ( params.run_amp_screening && !params.amp_skip_hmmsearch ) || (params.run_bgc_screening && !params.bgc_skip_hmmsearch) ? "
  • Eddy S. R. (2011). Accelerated Profile HMM Searches. PLoS computational biology, 7(10), e1002195. DOI: 10.1371/journal.pcbi.1002195
    • " : "" + + def reference_text = [ + preprocessing_text, + annotation_text, + params.run_amp_screening ? amp_text : "", + params.run_arg_screening ? arg_text : "", + params.run_bgc_screening ? bgc_text : "", + hmmsearch_text, + postprocessing_text, + ].join(' ').trim() + + return reference_text + + } + + public static String methodsDescriptionText(run_workflow, mqc_methods_yaml, params) { // Convert to a named map so can be used as with familar NXF ${workflow} variable syntax in the MultiQC YML file def meta = [:] meta.workflow = run_workflow.toMap() meta["manifest_map"] = run_workflow.manifest.toMap() + // Pipeline DOI meta["doi_text"] = meta.manifest_map.doi ? "(doi: ${meta.manifest_map.doi})" : "" meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " + // Tool references + meta["tool_citations"] = "" + meta["tool_bibliography"] = "" + + meta["tool_citations"] = toolCitationText(params).replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".") + meta["tool_bibliography"] = toolBibliographyText(params) + def methods_text = mqc_methods_yaml.text def engine = new SimpleTemplateEngine() diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy index 8966df00..d4548417 100755 --- a/lib/WorkflowMain.groovy +++ b/lib/WorkflowMain.groovy @@ -19,40 +19,11 @@ class WorkflowMain { " https://github.com/${workflow.manifest.name}/blob/master/CITATIONS.md" } - // - // Generate help string - // - public static String help(workflow, params) { - def command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --genome GRCh37 -profile docker" - def help_string = '' - help_string += NfcoreTemplate.logo(workflow, params.monochrome_logs) - help_string += NfcoreSchema.paramsHelp(workflow, params, command) - help_string += '\n' + citation(workflow) + '\n' - help_string += NfcoreTemplate.dashedLine(params.monochrome_logs) - return help_string - } - - // - // Generate parameter summary log string - // - public static String paramsSummaryLog(workflow, params) { - def summary_log = '' - summary_log += NfcoreTemplate.logo(workflow, params.monochrome_logs) - summary_log += NfcoreSchema.paramsSummaryLog(workflow, params) - summary_log += '\n' + citation(workflow) + '\n' - summary_log += NfcoreTemplate.dashedLine(params.monochrome_logs) - return summary_log - } // // Validate parameters and print summary to screen // public static void initialise(workflow, params, log) { - // Print help to screen if required - if (params.help) { - log.info help(workflow, params) - System.exit(0) - } // Print workflow version and exit on --version if (params.version) { @@ -61,14 +32,6 @@ class WorkflowMain { System.exit(0) } - // Print parameter summary log to screen - log.info paramsSummaryLog(workflow, params) - - // Validate workflow parameters via the JSON schema - if (params.validate_params) { - NfcoreSchema.validateParameters(workflow, params, log) - } - // Check that a -profile or Nextflow config has been provided to run the pipeline NfcoreTemplate.checkConfigProvided(workflow, log) diff --git a/main.nf b/main.nf index 5251114f..5d87fca2 100644 --- a/main.nf +++ b/main.nf @@ -25,6 +25,22 @@ params.fasta = WorkflowMain.getGenomeAttribute(params, 'fasta') ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ +include { validateParameters; paramsHelp } from 'plugin/nf-validation' + +// Print help message if needed +if (params.help) { + def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs) + def citation = '\n' + WorkflowMain.citation(workflow) + '\n' + def String command = "nextflow run ${workflow.manifest.name} --input samplesheet.csv --genome GRCh37 -profile docker" + log.info logo + paramsHelp(command) + citation + NfcoreTemplate.dashedLine(params.monochrome_logs) + System.exit(0) +} + +// Validate input parameters +if (params.validate_params) { + validateParameters() +} + WorkflowMain.initialise(workflow, params, log) /* diff --git a/nextflow.config b/nextflow.config index a9e49e85..b6fca04e 100644 --- a/nextflow.config +++ b/nextflow.config @@ -12,10 +12,11 @@ params { // Input options input = null - // References NOT USED IN FUNCSCAN, KEPT FOR TEMPLATE MERGE PURPOSES + // References - Not used in funcscan, left for template purposes genome = null igenomes_base = 's3://ngi-igenomes/igenomes' - igenomes_ignore = true + igenomes_ignore = false + // Annotation options annotation_tool = 'pyrodigal' @@ -184,7 +185,6 @@ params { // Boilerplate options outdir = null - tracedir = "${params.outdir}/pipeline_info" publish_dir_mode = 'copy' email = null email_on_fail = null @@ -193,17 +193,14 @@ params { hook_url = null help = false version = false - validate_params = true - show_hidden_params = false - schema_ignore_params = 'genomes,fasta,igenomes_base' // Config options + config_profile_name = null + config_profile_description = null custom_config_version = 'master' custom_config_base = "https://raw.githubusercontent.com/nf-core/configs/${params.custom_config_version}" - config_profile_description = null config_profile_contact = null config_profile_url = null - config_profile_name = null // Max resource options // Defaults only, expecting to be overwritten @@ -211,6 +208,13 @@ params { max_cpus = 16 max_time = '240.h' + // Schema validation default options + validationFailUnrecognisedParams = false + validationLenientMode = false + validationSchemaIgnoreParams = 'genomes' + validationShowHiddenParams = false + validate_params = true + } // Load base.config by default for all pipelines @@ -235,7 +239,7 @@ profiles { debug { dumpHashes = true process.beforeScript = 'echo $HOSTNAME' - cleanup = false + cleanup = false } conda { conda.enabled = true @@ -327,6 +331,19 @@ profiles { test_deeparg { includeConfig 'conf/test_deeparg.config' } } +// Set default registry for Apptainer, Docker, Podman and Singularity independent of -profile +// Will not be used unless Apptainer / Docker / Podman / Singularity are enabled +// Set to your registry if you have a mirror of containers +apptainer.registry = 'quay.io' +docker.registry = 'quay.io' +podman.registry = 'quay.io' +singularity.registry = 'quay.io' + +// Nextflow plugins +plugins { + id 'nf-validation' // Validation of pipeline parameters and creation of an input channel from a sample sheet +} + // Load igenomes.config if required if (!params.igenomes_ignore) { includeConfig 'conf/igenomes.config' @@ -348,28 +365,22 @@ env { // Capture exit codes from upstream processes when piping process.shell = ['/bin/bash', '-euo', 'pipefail'] -// Set default registry for Docker and Podman independent of -profile -// Will not be used unless Docker / Podman are enabled -// Set to your registry if you have a mirror of containers -docker.registry = 'quay.io' -podman.registry = 'quay.io' - def trace_timestamp = new java.util.Date().format( 'yyyy-MM-dd_HH-mm-ss') timeline { enabled = true - file = "${params.tracedir}/execution_timeline_${trace_timestamp}.html" + file = "${params.outdir}/pipeline_info/execution_timeline_${trace_timestamp}.html" } report { enabled = true - file = "${params.tracedir}/execution_report_${trace_timestamp}.html" + file = "${params.outdir}/pipeline_info/execution_report_${trace_timestamp}.html" } trace { enabled = true - file = "${params.tracedir}/execution_trace_${trace_timestamp}.txt" + file = "${params.outdir}/pipeline_info/execution_trace_${trace_timestamp}.txt" } dag { enabled = true - file = "${params.tracedir}/pipeline_dag_${trace_timestamp}.html" + file = "${params.outdir}/pipeline_info/pipeline_dag_${trace_timestamp}.html" } manifest { @@ -378,8 +389,8 @@ manifest { homePage = 'https://github.com/nf-core/funcscan' description = """Pipeline for screening for functional components of assembled contigs""" mainScript = 'main.nf' - nextflowVersion = '!>=22.10.1' - version = '1.1.2' + nextflowVersion = '!>=23.04.0' + version = '1.1.3dev' doi = '10.5281/zenodo.7643099' } diff --git a/nextflow_schema.json b/nextflow_schema.json index 81591e6f..40a9c275 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -15,9 +15,9 @@ "input": { "type": "string", "format": "file-path", + "exists": true, "mimetype": "text/csv", "pattern": "^\\S+\\.csv$", - "schema": "assets/schema_input.json", "description": "Path to comma-separated file containing information sample names and paths to corresponding FASTA files.", "help_text": "Before running the pipeline, you will need to create a design file with information about the samples to be scanned by nf-core/funcscan, containing `sample name` and `path/to/your/contigs.fasta`. Use this parameter to specify its location. It has to be a comma-separated file with 2 columns, and a header row (`sample, fasta`). See [usage docs](https://nf-co.re/funcscan/usage#samplesheet-input).", "fa_icon": "fas fa-file-csv" @@ -1130,6 +1130,7 @@ "fasta": { "type": "string", "format": "file-path", + "exists": false, "mimetype": "text/plain", "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$", "description": "Path to FASTA genome file.", @@ -1231,7 +1232,7 @@ "description": "Maximum amount of time that can be requested for any single job.", "default": "240.h", "fa_icon": "far fa-clock", - "pattern": "^(\\d+\\.?\\s*(s|m|h|day)\\s*)+$", + "pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$", "hidden": true, "help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`" } @@ -1248,12 +1249,14 @@ "type": "boolean", "description": "Display help text.", "fa_icon": "fas fa-question-circle", + "default": false, "hidden": true }, "version": { "type": "boolean", "description": "Display version and exit.", "fa_icon": "fas fa-question-circle", + "default": false, "hidden": true }, "publish_dir_mode": { @@ -1277,6 +1280,7 @@ "type": "boolean", "description": "Send plain-text email instead of HTML.", "fa_icon": "fas fa-remove-format", + "default": false, "hidden": true }, "max_multiqc_email_size": { @@ -1291,6 +1295,7 @@ "type": "boolean", "description": "Do not use coloured log outputs.", "fa_icon": "fas fa-palette", + "default": false, "hidden": true }, "hook_url": { @@ -1302,6 +1307,7 @@ }, "multiqc_config": { "type": "string", + "format": "file-path", "description": "Custom config file to supply to MultiQC.", "fa_icon": "fas fa-cog", "hidden": true @@ -1317,13 +1323,6 @@ "description": "Custom MultiQC yaml file containing HTML including a methods description.", "fa_icon": "fas fa-cog" }, - "tracedir": { - "type": "string", - "description": "Directory to keep pipeline Nextflow logs and reports.", - "default": "${params.outdir}/pipeline_info", - "fa_icon": "fas fa-cogs", - "hidden": true - }, "validate_params": { "type": "boolean", "description": "Boolean whether to validate parameters against the schema at runtime", @@ -1331,12 +1330,29 @@ "fa_icon": "fas fa-check-square", "hidden": true }, - "show_hidden_params": { + "validationShowHiddenParams": { "type": "boolean", "fa_icon": "far fa-eye-slash", "description": "Show all params when using `--help`", + "default": false, "hidden": true, "help_text": "By 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." + }, + "validationFailUnrecognisedParams": { + "type": "boolean", + "fa_icon": "far fa-check-circle", + "description": "Validation of parameters fails when an unrecognised parameter is found.", + "default": false, + "hidden": true, + "help_text": "By default, when an unrecognised parameter is found, it returns a warinig." + }, + "validationLenientMode": { + "type": "boolean", + "fa_icon": "far fa-check-circle", + "description": "Validation of parameters in lenient more.", + "default": false, + "hidden": true, + "help_text": "Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode)." } } } diff --git a/workflows/funcscan.nf b/workflows/funcscan.nf index 27168b24..ad317a20 100644 --- a/workflows/funcscan.nf +++ b/workflows/funcscan.nf @@ -1,12 +1,18 @@ /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - VALIDATE INPUTS + PRINT PARAMS SUMMARY ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -def summary_params = NfcoreSchema.paramsSummaryMap(workflow, params) +include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation' + +def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs) +def citation = '\n' + WorkflowMain.citation(workflow) + '\n' +def summary_params = paramsSummaryMap(workflow) + +// Print parameter summary log to screen +log.info logo + paramsSummaryLog(workflow) + citation -// Validate input parameters WorkflowFuncscan.initialise(params, log) // Check input path parameters to see if they exist @@ -121,9 +127,12 @@ workflow FUNCSCAN { // SUBWORKFLOW: Read in samplesheet, validate and stage input files // INPUT_CHECK ( - ch_input + file(params.input) ) ch_versions = ch_versions.mix(INPUT_CHECK.out.versions) + // TODO: OPTIONAL, you can use nf-validation plugin to create an input channel from the samplesheet with Channel.fromSamplesheet("input") + // See the documentation https://nextflow-io.github.io/nf-validation/samplesheets/fromSamplesheet/ + // ! There is currently no tooling to help you write a sample sheet schema // Some tools require uncompressed input fasta_prep = INPUT_CHECK.out.contigs @@ -266,7 +275,7 @@ workflow FUNCSCAN { workflow_summary = WorkflowFuncscan.paramsSummaryMultiqc(workflow, summary_params) ch_workflow_summary = Channel.value(workflow_summary) - methods_description = WorkflowFuncscan.methodsDescriptionText(workflow, ch_multiqc_custom_methods_description) + methods_description = WorkflowFuncscan.methodsDescriptionText(workflow, ch_multiqc_custom_methods_description, params) ch_methods_description = Channel.value(methods_description) ch_multiqc_files = Channel.empty()