From 8198830da1249750cf9e2d0208cad8937d5eb338 Mon Sep 17 00:00:00 2001 From: Usman Rashid Date: Tue, 20 Feb 2024 14:00:07 +1300 Subject: [PATCH] A basic workflow now running successfully --- .github/ISSUE_TEMPLATE/bug_report.yml | 100 ++-- .github/workflows/ci.yml | 2 +- .github/workflows/download_pipeline.yml | 2 +- .nf-core.yml | 30 +- .pre-commit-config.yaml | 2 +- README.md | 2 +- assets/assemblysheet.csv | 2 + assets/samplesheet.csv | 3 - assets/schema_input.json | 59 ++- bin/check_samplesheet.py | 259 ----------- cleanNXF.sh | 11 + conf/igenomes.config | 440 ------------------ conf/modules.config | 27 -- conf/test.config | 8 +- conf/test_full.config | 8 +- lib/WorkflowAssemblyqc.groovy | 110 +---- lib/WorkflowMain.groovy | 10 +- main.nf | 17 +- modules.json | 10 +- modules/local/samplesheet_check.nf | 31 -- .../dumpsoftwareversions/environment.yml | 2 +- .../custom/dumpsoftwareversions/main.nf | 4 +- .../templates/dumpsoftwareversions.py | 3 +- .../dumpsoftwareversions/tests/main.nf.test | 7 +- .../tests/main.nf.test.snap | 50 +- .../nf-core/fastavalidator/environment.yml | 9 + modules/nf-core/fastavalidator/main.nf | 62 +++ modules/nf-core/fastavalidator/meta.yml | 53 +++ .../nf-core/fastavalidator/tests/main.nf.test | 60 +++ .../fastavalidator/tests/main.nf.test.snap | 76 +++ modules/nf-core/fastavalidator/tests/tags.yml | 2 + modules/nf-core/fastqc/main.nf | 55 --- modules/nf-core/fastqc/meta.yml | 57 --- modules/nf-core/fastqc/tests/main.nf.test | 109 ----- .../nf-core/fastqc/tests/main.nf.test.snap | 10 - modules/nf-core/fastqc/tests/tags.yml | 2 - .../{fastqc => gunzip}/environment.yml | 4 +- modules/nf-core/gunzip/main.nf | 48 ++ modules/nf-core/gunzip/meta.yml | 39 ++ modules/nf-core/gunzip/tests/main.nf.test | 36 ++ .../nf-core/gunzip/tests/main.nf.test.snap | 31 ++ modules/nf-core/gunzip/tests/tags.yml | 2 + modules/nf-core/multiqc/environment.yml | 7 - modules/nf-core/multiqc/main.nf | 55 --- modules/nf-core/multiqc/meta.yml | 59 --- modules/nf-core/multiqc/tests/main.nf.test | 63 --- modules/nf-core/multiqc/tests/tags.yml | 2 - nextflow.config | 119 +++-- nextflow_schema.json | 365 +++++++++++---- subworkflows/local/input_check.nf | 44 -- workflows/assemblyqc.nf | 115 ++--- 51 files changed, 1007 insertions(+), 1676 deletions(-) create mode 100644 assets/assemblysheet.csv delete mode 100644 assets/samplesheet.csv delete mode 100755 bin/check_samplesheet.py create mode 100755 cleanNXF.sh delete mode 100644 conf/igenomes.config mode change 100644 => 100755 main.nf delete mode 100644 modules/local/samplesheet_check.nf create mode 100644 modules/nf-core/fastavalidator/environment.yml create mode 100644 modules/nf-core/fastavalidator/main.nf create mode 100644 modules/nf-core/fastavalidator/meta.yml create mode 100644 modules/nf-core/fastavalidator/tests/main.nf.test create mode 100644 modules/nf-core/fastavalidator/tests/main.nf.test.snap create mode 100644 modules/nf-core/fastavalidator/tests/tags.yml delete mode 100644 modules/nf-core/fastqc/main.nf delete mode 100644 modules/nf-core/fastqc/meta.yml delete mode 100644 modules/nf-core/fastqc/tests/main.nf.test delete mode 100644 modules/nf-core/fastqc/tests/main.nf.test.snap delete mode 100644 modules/nf-core/fastqc/tests/tags.yml rename modules/nf-core/{fastqc => gunzip}/environment.yml (61%) create mode 100644 modules/nf-core/gunzip/main.nf create mode 100644 modules/nf-core/gunzip/meta.yml create mode 100644 modules/nf-core/gunzip/tests/main.nf.test create mode 100644 modules/nf-core/gunzip/tests/main.nf.test.snap create mode 100644 modules/nf-core/gunzip/tests/tags.yml delete mode 100644 modules/nf-core/multiqc/environment.yml delete mode 100644 modules/nf-core/multiqc/main.nf delete mode 100644 modules/nf-core/multiqc/meta.yml delete mode 100644 modules/nf-core/multiqc/tests/main.nf.test delete mode 100644 modules/nf-core/multiqc/tests/tags.yml delete mode 100644 subworkflows/local/input_check.nf diff --git a/.github/ISSUE_TEMPLATE/bug_report.yml b/.github/ISSUE_TEMPLATE/bug_report.yml index c22d7e64..af436aa6 100644 --- a/.github/ISSUE_TEMPLATE/bug_report.yml +++ b/.github/ISSUE_TEMPLATE/bug_report.yml @@ -2,53 +2,53 @@ name: Bug report description: Report something that is broken or incorrect labels: bug body: -- type: textarea - id: description - attributes: - label: Description of the bug - description: A clear and concise description of what the bug is. - validations: - required: true -- type: textarea - id: command_used - attributes: - label: Command used and terminal output - description: Steps to reproduce the behaviour. Please paste the command you used - to launch the pipeline and the output from your terminal. - render: console - placeholder: '$ nextflow run ... - - - Some output where something broke - - ' -- type: textarea - id: files - attributes: - label: Relevant files - description: 'Please drag and drop the relevant files here. Create a `.zip` archive - if the extension is not allowed. - - Your verbose log file `.nextflow.log` is often useful _(this is a hidden file - in the directory where you launched the pipeline)_ as well as custom Nextflow - configuration files. - - ' -- type: textarea - id: system - attributes: - label: System information - description: '* 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)_ - - * OS _(eg. CentOS Linux, macOS, Linux Mint)_ - - * Version of plant-food-research-open/assemblyqc _(eg. 1.1, 1.5, 1.8.2)_ - - ' + - type: textarea + id: description + attributes: + label: Description of the bug + description: A clear and concise description of what the bug is. + validations: + required: true + - type: textarea + id: command_used + attributes: + label: Command used and terminal output + description: Steps to reproduce the behaviour. Please paste the command you used + to launch the pipeline and the output from your terminal. + render: console + placeholder: "$ nextflow run ... + + + Some output where something broke + + " + - type: textarea + id: files + attributes: + label: Relevant files + description: "Please drag and drop the relevant files here. Create a `.zip` archive + if the extension is not allowed. + + Your verbose log file `.nextflow.log` is often useful _(this is a hidden file + in the directory where you launched the pipeline)_ as well as custom Nextflow + configuration files. + + " + - type: textarea + id: system + attributes: + label: System information + description: "* 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)_ + + * OS _(eg. CentOS Linux, macOS, Linux Mint)_ + + * Version of plant-food-research-open/assemblyqc _(eg. 1.1, 1.5, 1.8.2)_ + + " diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml index 9e9668cc..1e763b3d 100644 --- a/.github/workflows/ci.yml +++ b/.github/workflows/ci.yml @@ -24,7 +24,7 @@ jobs: strategy: matrix: NXF_VER: - - "23.04.0" + - "22.04.3" - "latest-everything" steps: - name: Check out pipeline code diff --git a/.github/workflows/download_pipeline.yml b/.github/workflows/download_pipeline.yml index 47168689..69574376 100644 --- a/.github/workflows/download_pipeline.yml +++ b/.github/workflows/download_pipeline.yml @@ -64,4 +64,4 @@ jobs: env: NXF_SINGULARITY_CACHEDIR: ./ NXF_SINGULARITY_HOME_MOUNT: true - run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results + run: nextflow run ./${{ env.REPOTITLE_LOWERCASE }}/$( sed 's/\W/_/g' <<< ${{ env.REPO_BRANCH }}) -stub -profile test,singularity --outdir ./results diff --git a/.nf-core.yml b/.nf-core.yml index 98319d1b..61d19b4d 100644 --- a/.nf-core.yml +++ b/.nf-core.yml @@ -1,23 +1,23 @@ lint: files_exist: - - CODE_OF_CONDUCT.md - - assets/nf-core-assemblyqc_logo_light.png - - docs/images/nf-core-assemblyqc_logo_light.png - - docs/images/nf-core-assemblyqc_logo_dark.png - - .github/ISSUE_TEMPLATE/config.yml - - .github/workflows/awstest.yml - - .github/workflows/awsfulltest.yml + - CODE_OF_CONDUCT.md + - assets/nf-core-assemblyqc_logo_light.png + - docs/images/nf-core-assemblyqc_logo_light.png + - docs/images/nf-core-assemblyqc_logo_dark.png + - .github/ISSUE_TEMPLATE/config.yml + - .github/workflows/awstest.yml + - .github/workflows/awsfulltest.yml files_unchanged: - - CODE_OF_CONDUCT.md - - assets/nf-core-assemblyqc_logo_light.png - - docs/images/nf-core-assemblyqc_logo_light.png - - docs/images/nf-core-assemblyqc_logo_dark.png - - .github/ISSUE_TEMPLATE/bug_report.yml + - CODE_OF_CONDUCT.md + - assets/nf-core-assemblyqc_logo_light.png + - docs/images/nf-core-assemblyqc_logo_light.png + - docs/images/nf-core-assemblyqc_logo_dark.png + - .github/ISSUE_TEMPLATE/bug_report.yml multiqc_config: - - report_comment + - report_comment nextflow_config: - - manifest.name - - manifest.homePage + - manifest.name + - manifest.homePage repository_type: pipeline template: prefix: plant-food-research-open diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 984321ff..af57081f 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,6 +1,6 @@ repos: - repo: https://github.com/pre-commit/mirrors-prettier - rev: "v3.1.1" + rev: "v3.1.0" hooks: - id: prettier - repo: https://github.com/editorconfig-checker/editorconfig-checker.python diff --git a/README.md b/README.md index 92b64574..85f09fe3 100644 --- a/README.md +++ b/README.md @@ -1,7 +1,7 @@ [![GitHub Actions CI Status](https://github.com/plant-food-research-open/assemblyqc/workflows/nf-core%20CI/badge.svg)](https://github.com/plant-food-research-open/assemblyqc/actions?query=workflow%3A%22nf-core+CI%22) [![GitHub Actions Linting Status](https://github.com/plant-food-research-open/assemblyqc/workflows/nf-core%20linting/badge.svg)](https://github.com/plant-food-research-open/assemblyqc/actions?query=workflow%3A%22nf-core+linting%22)[![Cite with Zenodo](http://img.shields.io/badge/DOI-10.5281/zenodo.XXXXXXX-1073c8?labelColor=000000)](https://doi.org/10.5281/zenodo.XXXXXXX) -[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A523.04.0-23aa62.svg)](https://www.nextflow.io/) +[![Nextflow](https://img.shields.io/badge/nextflow%20DSL2-%E2%89%A522.04.3-23aa62.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/) diff --git a/assets/assemblysheet.csv b/assets/assemblysheet.csv new file mode 100644 index 00000000..9b200ff9 --- /dev/null +++ b/assets/assemblysheet.csv @@ -0,0 +1,2 @@ +tag,fasta,gff3,monoploid_ids,hic_reads,synteny_labels +FI1,https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/003/814/445/GCA_003814445.1_ASM381444v1/GCA_003814445.1_ASM381444v1_genomic.fna.gz,,,, diff --git a/assets/samplesheet.csv b/assets/samplesheet.csv deleted file mode 100644 index 5f653ab7..00000000 --- a/assets/samplesheet.csv +++ /dev/null @@ -1,3 +0,0 @@ -sample,fastq_1,fastq_2 -SAMPLE_PAIRED_END,/path/to/fastq/files/AEG588A1_S1_L002_R1_001.fastq.gz,/path/to/fastq/files/AEG588A1_S1_L002_R2_001.fastq.gz -SAMPLE_SINGLE_END,/path/to/fastq/files/AEG588A4_S4_L003_R1_001.fastq.gz, diff --git a/assets/schema_input.json b/assets/schema_input.json index cff17406..6aff8b19 100644 --- a/assets/schema_input.json +++ b/assets/schema_input.json @@ -7,22 +7,61 @@ "items": { "type": "object", "properties": { - "sample": { + "tag": { "type": "string", - "pattern": "^\\S+$", - "errorMessage": "Sample name must be provided and cannot contain spaces" + "pattern": "^\\w+$", + "errorMessage": "Assembly tags must be provided and can only contain alphanumeric characters including '_'" }, - "fastq_1": { + "fasta": { "type": "string", - "pattern": "^\\S+\\.f(ast)?q\\.gz$", - "errorMessage": "FastQ file for reads 1 must be provided, cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'" + "pattern": "^\\S+\\.f(ast|as|sa|na)?\\.gz$", + "errorMessage": "FASTA file path cannot contain spaces and must have extension '.f(ast|as|sa|na)' or '.f(ast|as|sa|na).gz'" }, - "fastq_2": { - "errorMessage": "FastQ file for reads 2 cannot contain spaces and must have extension '.fq.gz' or '.fastq.gz'", + "gff3": { + "type": "string", + "pattern": "^\\S+\\.gff(3)?\\.gz$", + "errorMessage": "GFF3 file path cannot contain spaces and must have extension '.gff.gz' or '.gff3.gz'" + }, + "monoploid_ids": { + "errorMessage": "Monoploid IDs txt file path cannot contain spaces and must have extension '.txt'", + "anyOf": [ + { + "type": "string", + "pattern": "^\\S+\\.txt$" + }, + { + "type": "string", + "maxLength": 0 + } + ] + }, + "hic_reads": { + "errorMessage": "HiC reads should either be provided as a SRA ID or as a path to paired reads with pattern '*_R{1,2}.(fastq|fq).gz'", + "anyOf": [ + { + "type": "string", + "pattern": "^SR\\w+$" + }, + { + "type": "string", + "pattern": "^\\S+_R\\{1,2\\}\\.f(ast)?q\\.gz$" + }, + { + "type": "string", + "maxLength": 0 + } + ] + }, + "synteny_labels": { + "errorMessage": "Synteny labels tsv path cannot contain spaces and must have extension '.tsv'", "anyOf": [ { "type": "string", - "pattern": "^\\S+\\.f(ast)?q\\.gz$" + "pattern": "^SR\\w+$" + }, + { + "type": "string", + "pattern": "^\\S+_R\\{1,2\\}\\.f(ast)?q\\.gz$" }, { "type": "string", @@ -31,6 +70,6 @@ ] } }, - "required": ["sample", "fastq_1"] + "required": ["tag", "fasta"] } } diff --git a/bin/check_samplesheet.py b/bin/check_samplesheet.py deleted file mode 100755 index 4a758fe0..00000000 --- a/bin/check_samplesheet.py +++ /dev/null @@ -1,259 +0,0 @@ -#!/usr/bin/env python - - -"""Provide a command line tool to validate and transform tabular samplesheets.""" - - -import argparse -import csv -import logging -import sys -from collections import Counter -from pathlib import Path - -logger = logging.getLogger() - - -class RowChecker: - """ - Define a service that can validate and transform each given row. - - Attributes: - modified (list): A list of dicts, where each dict corresponds to a previously - validated and transformed row. The order of rows is maintained. - - """ - - VALID_FORMATS = ( - ".fq.gz", - ".fastq.gz", - ) - - def __init__( - self, - sample_col="sample", - first_col="fastq_1", - second_col="fastq_2", - single_col="single_end", - **kwargs, - ): - """ - Initialize the row checker with the expected column names. - - Args: - sample_col (str): The name of the column that contains the sample name - (default "sample"). - first_col (str): The name of the column that contains the first (or only) - FASTQ file path (default "fastq_1"). - second_col (str): The name of the column that contains the second (if any) - FASTQ file path (default "fastq_2"). - single_col (str): The name of the new column that will be inserted and - records whether the sample contains single- or paired-end sequencing - reads (default "single_end"). - - """ - super().__init__(**kwargs) - self._sample_col = sample_col - self._first_col = first_col - self._second_col = second_col - self._single_col = single_col - self._seen = set() - self.modified = [] - - def validate_and_transform(self, row): - """ - Perform all validations on the given row and insert the read pairing status. - - Args: - row (dict): A mapping from column headers (keys) to elements of that row - (values). - - """ - self._validate_sample(row) - self._validate_first(row) - self._validate_second(row) - self._validate_pair(row) - self._seen.add((row[self._sample_col], row[self._first_col])) - self.modified.append(row) - - def _validate_sample(self, row): - """Assert that the sample name exists and convert spaces to underscores.""" - if len(row[self._sample_col]) <= 0: - raise AssertionError("Sample input is required.") - # Sanitize samples slightly. - row[self._sample_col] = row[self._sample_col].replace(" ", "_") - - def _validate_first(self, row): - """Assert that the first FASTQ entry is non-empty and has the right format.""" - if len(row[self._first_col]) <= 0: - raise AssertionError("At least the first FASTQ file is required.") - self._validate_fastq_format(row[self._first_col]) - - def _validate_second(self, row): - """Assert that the second FASTQ entry has the right format if it exists.""" - if len(row[self._second_col]) > 0: - self._validate_fastq_format(row[self._second_col]) - - def _validate_pair(self, row): - """Assert that read pairs have the same file extension. Report pair status.""" - if row[self._first_col] and row[self._second_col]: - row[self._single_col] = False - first_col_suffix = Path(row[self._first_col]).suffixes[-2:] - second_col_suffix = Path(row[self._second_col]).suffixes[-2:] - if first_col_suffix != second_col_suffix: - raise AssertionError("FASTQ pairs must have the same file extensions.") - else: - row[self._single_col] = True - - def _validate_fastq_format(self, filename): - """Assert that a given filename has one of the expected FASTQ extensions.""" - if not any(filename.endswith(extension) for extension in self.VALID_FORMATS): - raise AssertionError( - f"The FASTQ file has an unrecognized extension: {filename}\n" - f"It should be one of: {', '.join(self.VALID_FORMATS)}" - ) - - def validate_unique_samples(self): - """ - Assert that the combination of sample name and FASTQ filename is unique. - - In addition to the validation, also rename all samples to have a suffix of _T{n}, where n is the - number of times the same sample exist, but with different FASTQ files, e.g., multiple runs per experiment. - - """ - if len(self._seen) != len(self.modified): - raise AssertionError("The pair of sample name and FASTQ must be unique.") - seen = Counter() - for row in self.modified: - sample = row[self._sample_col] - seen[sample] += 1 - row[self._sample_col] = f"{sample}_T{seen[sample]}" - - -def read_head(handle, num_lines=10): - """Read the specified number of lines from the current position in the file.""" - lines = [] - for idx, line in enumerate(handle): - if idx == num_lines: - break - lines.append(line) - return "".join(lines) - - -def sniff_format(handle): - """ - Detect the tabular format. - - Args: - handle (text file): A handle to a `text file`_ object. The read position is - expected to be at the beginning (index 0). - - Returns: - csv.Dialect: The detected tabular format. - - .. _text file: - https://docs.python.org/3/glossary.html#term-text-file - - """ - peek = read_head(handle) - handle.seek(0) - sniffer = csv.Sniffer() - dialect = sniffer.sniff(peek) - return dialect - - -def check_samplesheet(file_in, file_out): - """ - Check that the tabular samplesheet has the structure expected by nf-core pipelines. - - Validate the general shape of the table, expected columns, and each row. Also add - an additional column which records whether one or two FASTQ reads were found. - - Args: - file_in (pathlib.Path): The given tabular samplesheet. The format can be either - CSV, TSV, or any other format automatically recognized by ``csv.Sniffer``. - file_out (pathlib.Path): Where the validated and transformed samplesheet should - be created; always in CSV format. - - Example: - This function checks that the samplesheet follows the following structure, - see also the `viral recon samplesheet`_:: - - sample,fastq_1,fastq_2 - SAMPLE_PE,SAMPLE_PE_RUN1_1.fastq.gz,SAMPLE_PE_RUN1_2.fastq.gz - SAMPLE_PE,SAMPLE_PE_RUN2_1.fastq.gz,SAMPLE_PE_RUN2_2.fastq.gz - SAMPLE_SE,SAMPLE_SE_RUN1_1.fastq.gz, - - .. _viral recon samplesheet: - https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv - - """ - required_columns = {"sample", "fastq_1", "fastq_2"} - # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`. - with file_in.open(newline="") as in_handle: - reader = csv.DictReader(in_handle, dialect=sniff_format(in_handle)) - # Validate the existence of the expected header columns. - if not required_columns.issubset(reader.fieldnames): - req_cols = ", ".join(required_columns) - logger.critical(f"The sample sheet **must** contain these column headers: {req_cols}.") - sys.exit(1) - # Validate each row. - checker = RowChecker() - for i, row in enumerate(reader): - try: - checker.validate_and_transform(row) - except AssertionError as error: - logger.critical(f"{str(error)} On line {i + 2}.") - sys.exit(1) - checker.validate_unique_samples() - header = list(reader.fieldnames) - header.insert(1, "single_end") - # See https://docs.python.org/3.9/library/csv.html#id3 to read up on `newline=""`. - with file_out.open(mode="w", newline="") as out_handle: - writer = csv.DictWriter(out_handle, header, delimiter=",") - writer.writeheader() - for row in checker.modified: - writer.writerow(row) - - -def parse_args(argv=None): - """Define and immediately parse command line arguments.""" - parser = argparse.ArgumentParser( - description="Validate and transform a tabular samplesheet.", - epilog="Example: python check_samplesheet.py samplesheet.csv samplesheet.valid.csv", - ) - parser.add_argument( - "file_in", - metavar="FILE_IN", - type=Path, - help="Tabular input samplesheet in CSV or TSV format.", - ) - parser.add_argument( - "file_out", - metavar="FILE_OUT", - type=Path, - help="Transformed output samplesheet in CSV format.", - ) - parser.add_argument( - "-l", - "--log-level", - help="The desired log level (default WARNING).", - choices=("CRITICAL", "ERROR", "WARNING", "INFO", "DEBUG"), - default="WARNING", - ) - return parser.parse_args(argv) - - -def main(argv=None): - """Coordinate argument parsing and program execution.""" - args = parse_args(argv) - logging.basicConfig(level=args.log_level, format="[%(levelname)s] %(message)s") - if not args.file_in.is_file(): - logger.error(f"The given input file {args.file_in} was not found!") - sys.exit(2) - args.file_out.parent.mkdir(parents=True, exist_ok=True) - check_samplesheet(args.file_in, args.file_out) - - -if __name__ == "__main__": - sys.exit(main()) diff --git a/cleanNXF.sh b/cleanNXF.sh new file mode 100755 index 00000000..8c64a3e0 --- /dev/null +++ b/cleanNXF.sh @@ -0,0 +1,11 @@ +#!/usr/bin/env bash + +rm -rf .nextflow* +echo "Cleaned .nextflow..." +rm -rf .nextflow.pid +echo "Cleaned .nextflow.pid..." +for i in $(ls work | grep -v "conda"); +do + rm -rf "work/$i" +done +echo "Cleaned work..." diff --git a/conf/igenomes.config b/conf/igenomes.config deleted file mode 100644 index 3f114377..00000000 --- a/conf/igenomes.config +++ /dev/null @@ -1,440 +0,0 @@ -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - Nextflow config file for iGenomes paths -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - Defines reference genomes using iGenome paths. - Can be used by any config that customises the base path using: - $params.igenomes_base / --igenomes_base ----------------------------------------------------------------------------------------- -*/ - -params { - // illumina iGenomes reference file paths - genomes { - 'GRCh37' { - fasta = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Homo_sapiens/Ensembl/GRCh37/Annotation/README.txt" - mito_name = "MT" - macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/GRCh37-blacklist.bed" - } - 'GRCh38' { - fasta = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/NCBI/GRCh38/Annotation/Genes/genes.bed" - mito_name = "chrM" - macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" - } - 'CHM13' { - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAIndex/" - bwamem2 = "${params.igenomes_base}/Homo_sapiens/UCSC/CHM13/Sequence/BWAmem2Index/" - gtf = "${params.igenomes_base}/Homo_sapiens/NCBI/CHM13/Annotation/Genes/genes.gtf" - gff = "ftp://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/009/914/755/GCF_009914755.1_T2T-CHM13v2.0/GCF_009914755.1_T2T-CHM13v2.0_genomic.gff.gz" - mito_name = "chrM" - } - 'GRCm38' { - fasta = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Mus_musculus/Ensembl/GRCm38/Annotation/README.txt" - mito_name = "MT" - macs_gsize = "1.87e9" - blacklist = "${projectDir}/assets/blacklists/GRCm38-blacklist.bed" - } - 'TAIR10' { - fasta = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Arabidopsis_thaliana/Ensembl/TAIR10/Annotation/README.txt" - mito_name = "Mt" - } - 'EB2' { - fasta = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Bacillus_subtilis_168/Ensembl/EB2/Annotation/README.txt" - } - 'UMD3.1' { - fasta = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Bos_taurus/Ensembl/UMD3.1/Annotation/README.txt" - mito_name = "MT" - } - 'WBcel235' { - fasta = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/Ensembl/WBcel235/Annotation/Genes/genes.bed" - mito_name = "MtDNA" - macs_gsize = "9e7" - } - 'CanFam3.1' { - fasta = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Canis_familiaris/Ensembl/CanFam3.1/Annotation/README.txt" - mito_name = "MT" - } - 'GRCz10' { - fasta = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Danio_rerio/Ensembl/GRCz10/Annotation/Genes/genes.bed" - mito_name = "MT" - } - 'BDGP6' { - fasta = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Drosophila_melanogaster/Ensembl/BDGP6/Annotation/Genes/genes.bed" - mito_name = "M" - macs_gsize = "1.2e8" - } - 'EquCab2' { - fasta = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Equus_caballus/Ensembl/EquCab2/Annotation/README.txt" - mito_name = "MT" - } - 'EB1' { - fasta = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Escherichia_coli_K_12_DH10B/Ensembl/EB1/Annotation/README.txt" - } - 'Galgal4' { - fasta = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Gallus_gallus/Ensembl/Galgal4/Annotation/Genes/genes.bed" - mito_name = "MT" - } - 'Gm01' { - fasta = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Glycine_max/Ensembl/Gm01/Annotation/README.txt" - } - 'Mmul_1' { - fasta = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Macaca_mulatta/Ensembl/Mmul_1/Annotation/README.txt" - mito_name = "MT" - } - 'IRGSP-1.0' { - fasta = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Oryza_sativa_japonica/Ensembl/IRGSP-1.0/Annotation/Genes/genes.bed" - mito_name = "Mt" - } - 'CHIMP2.1.4' { - fasta = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Pan_troglodytes/Ensembl/CHIMP2.1.4/Annotation/README.txt" - mito_name = "MT" - } - 'Rnor_5.0' { - fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_5.0/Annotation/Genes/genes.bed" - mito_name = "MT" - } - 'Rnor_6.0' { - fasta = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Rattus_norvegicus/Ensembl/Rnor_6.0/Annotation/Genes/genes.bed" - mito_name = "MT" - } - 'R64-1-1' { - fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Saccharomyces_cerevisiae/Ensembl/R64-1-1/Annotation/Genes/genes.bed" - mito_name = "MT" - macs_gsize = "1.2e7" - } - 'EF2' { - fasta = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Schizosaccharomyces_pombe/Ensembl/EF2/Annotation/README.txt" - mito_name = "MT" - macs_gsize = "1.21e7" - } - 'Sbi1' { - fasta = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Sorghum_bicolor/Ensembl/Sbi1/Annotation/README.txt" - } - 'Sscrofa10.2' { - fasta = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Sus_scrofa/Ensembl/Sscrofa10.2/Annotation/README.txt" - mito_name = "MT" - } - 'AGPv3' { - fasta = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Zea_mays/Ensembl/AGPv3/Annotation/Genes/genes.bed" - mito_name = "Mt" - } - 'hg38' { - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg38/Annotation/Genes/genes.bed" - mito_name = "chrM" - macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg38-blacklist.bed" - } - 'hg19' { - fasta = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Homo_sapiens/UCSC/hg19/Annotation/README.txt" - mito_name = "chrM" - macs_gsize = "2.7e9" - blacklist = "${projectDir}/assets/blacklists/hg19-blacklist.bed" - } - 'mm10' { - fasta = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Mus_musculus/UCSC/mm10/Annotation/README.txt" - mito_name = "chrM" - macs_gsize = "1.87e9" - blacklist = "${projectDir}/assets/blacklists/mm10-blacklist.bed" - } - 'bosTau8' { - fasta = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Bos_taurus/UCSC/bosTau8/Annotation/Genes/genes.bed" - mito_name = "chrM" - } - 'ce10' { - fasta = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Caenorhabditis_elegans/UCSC/ce10/Annotation/README.txt" - mito_name = "chrM" - macs_gsize = "9e7" - } - 'canFam3' { - fasta = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Canis_familiaris/UCSC/canFam3/Annotation/README.txt" - mito_name = "chrM" - } - 'danRer10' { - fasta = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Danio_rerio/UCSC/danRer10/Annotation/Genes/genes.bed" - mito_name = "chrM" - macs_gsize = "1.37e9" - } - 'dm6' { - fasta = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Drosophila_melanogaster/UCSC/dm6/Annotation/Genes/genes.bed" - mito_name = "chrM" - macs_gsize = "1.2e8" - } - 'equCab2' { - fasta = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Equus_caballus/UCSC/equCab2/Annotation/README.txt" - mito_name = "chrM" - } - 'galGal4' { - fasta = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Gallus_gallus/UCSC/galGal4/Annotation/README.txt" - mito_name = "chrM" - } - 'panTro4' { - fasta = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Pan_troglodytes/UCSC/panTro4/Annotation/README.txt" - mito_name = "chrM" - } - 'rn6' { - fasta = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Rattus_norvegicus/UCSC/rn6/Annotation/Genes/genes.bed" - mito_name = "chrM" - } - 'sacCer3' { - fasta = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Sequence/BismarkIndex/" - readme = "${params.igenomes_base}/Saccharomyces_cerevisiae/UCSC/sacCer3/Annotation/README.txt" - mito_name = "chrM" - macs_gsize = "1.2e7" - } - 'susScr3' { - fasta = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/WholeGenomeFasta/genome.fa" - bwa = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BWAIndex/version0.6.0/" - bowtie2 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/Bowtie2Index/" - star = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/STARIndex/" - bismark = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Sequence/BismarkIndex/" - gtf = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.gtf" - bed12 = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/Genes/genes.bed" - readme = "${params.igenomes_base}/Sus_scrofa/UCSC/susScr3/Annotation/README.txt" - mito_name = "chrM" - } - } -} diff --git a/conf/modules.config b/conf/modules.config index d91c6aba..bb1fc48d 100644 --- a/conf/modules.config +++ b/conf/modules.config @@ -12,24 +12,6 @@ process { - publishDir = [ - path: { "${params.outdir}/${task.process.tokenize(':')[-1].tokenize('_')[0].toLowerCase()}" }, - mode: params.publish_dir_mode, - saveAs: { filename -> filename.equals('versions.yml') ? null : filename } - ] - - withName: SAMPLESHEET_CHECK { - publishDir = [ - path: { "${params.outdir}/pipeline_info" }, - mode: params.publish_dir_mode, - saveAs: { filename -> filename.equals('versions.yml') ? null : filename } - ] - } - - withName: FASTQC { - ext.args = '--quiet' - } - withName: CUSTOM_DUMPSOFTWAREVERSIONS { publishDir = [ path: { "${params.outdir}/pipeline_info" }, @@ -38,13 +20,4 @@ process { ] } - withName: 'MULTIQC' { - ext.args = { params.multiqc_title ? "--title \"$params.multiqc_title\"" : '' } - publishDir = [ - path: { "${params.outdir}/multiqc" }, - mode: params.publish_dir_mode, - saveAs: { filename -> filename.equals('versions.yml') ? null : filename } - ] - } - } diff --git a/conf/test.config b/conf/test.config index 2bc1ad8e..4e55a764 100644 --- a/conf/test.config +++ b/conf/test.config @@ -19,11 +19,5 @@ params { max_memory = '6.GB' max_time = '6.h' - // Input data - // TODO nf-core: Specify the paths to your test data on nf-core/test-datasets - // TODO nf-core: Give any required params for the test so that command line flags are not needed - input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_test_illumina_amplicon.csv' - - // Genome references - genome = 'R64-1-1' + input = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/assemblysheet.csv' } diff --git a/conf/test_full.config b/conf/test_full.config index 63d2687c..1232442e 100644 --- a/conf/test_full.config +++ b/conf/test_full.config @@ -14,11 +14,5 @@ params { config_profile_name = 'Full test profile' config_profile_description = 'Full test dataset to check pipeline function' - // Input data for full size test - // TODO nf-core: Specify the paths to your full test data ( on nf-core/test-datasets or directly in repositories, e.g. SRA) - // TODO nf-core: Give any required params for the test so that command line flags are not needed - input = 'https://raw.githubusercontent.com/nf-core/test-datasets/viralrecon/samplesheet/samplesheet_full_illumina_amplicon.csv' - - // Genome references - genome = 'R64-1-1' + input = 'https://raw.githubusercontent.com/plant-food-research-open/assemblyqc/dev/assets/assemblysheet.csv' } diff --git a/lib/WorkflowAssemblyqc.groovy b/lib/WorkflowAssemblyqc.groovy index 8be44f94..2c45d1e2 100755 --- a/lib/WorkflowAssemblyqc.groovy +++ b/lib/WorkflowAssemblyqc.groovy @@ -10,113 +10,5 @@ class WorkflowAssemblyqc { // // Check and validate parameters // - public static void initialise(params, log) { - - genomeExistsError(params, log) - - - if (!params.fasta) { - Nextflow.error "Genome fasta file not specified with e.g. '--fasta genome.fa' or via a detectable config file." - } - } - - // - // Get workflow summary for MultiQC - // - public static String paramsSummaryMultiqc(workflow, summary) { - String summary_section = '' - for (group in summary.keySet()) { - def group_params = summary.get(group) // This gets the parameters of that particular group - if (group_params) { - summary_section += "

$group

\n" - summary_section += "
\n" - for (param in group_params.keySet()) { - summary_section += "
$param
${group_params.get(param) ?: 'N/A'}
\n" - } - summary_section += "
\n" - } - } - - String yaml_file_text = "id: '${workflow.manifest.name.replace('/','-')}-summary'\n" - yaml_file_text += "description: ' - this information is collected when the pipeline is started.'\n" - yaml_file_text += "section_name: '${workflow.manifest.name} Workflow Summary'\n" - yaml_file_text += "section_href: 'https://github.com/${workflow.manifest.name}'\n" - yaml_file_text += "plot_type: 'html'\n" - yaml_file_text += "data: |\n" - yaml_file_text += "${summary_section}" - return yaml_file_text - } - - // - // Generate methods description for MultiQC - // - - public static String toolCitationText(params) { - - // TODO nf-core: Optionally add in-text citation tools to this list. - // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "Tool (Foo et al. 2023)" : "", - // Uncomment function in methodsDescriptionText to render in MultiQC report - def citation_text = [ - "Tools used in the workflow included:", - "FastQC (Andrews 2010),", - "MultiQC (Ewels et al. 2016)", - "." - ].join(' ').trim() - - return citation_text - } - - public static String toolBibliographyText(params) { - - // TODO Optionally add bibliographic entries to this list. - // Can use ternary operators to dynamically construct based conditions, e.g. params["run_xyz"] ? "
  • Author (2023) Pub name, Journal, DOI
    • " : "", - // Uncomment function in methodsDescriptionText to render in MultiQC report - def reference_text = [ - "
  • Andrews S, (2010) FastQC, URL: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/).
    • ", - "
  • 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. doi: /10.1093/bioinformatics/btw354
    • " - ].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: ${meta.manifest_map.doi})" : "" - meta["nodoi_text"] = meta.manifest_map.doi ? "": "
  • If available, make sure to update the text to include the Zenodo DOI of version of the pipeline used.
    • " - - // Tool references - meta["tool_citations"] = "" - meta["tool_bibliography"] = "" - - // TODO Only uncomment below if logic in toolCitationText/toolBibliographyText has been filled! - //meta["tool_citations"] = toolCitationText(params).replaceAll(", \\.", ".").replaceAll("\\. \\.", ".").replaceAll(", \\.", ".") - //meta["tool_bibliography"] = toolBibliographyText(params) - - - def methods_text = mqc_methods_yaml.text - - def engine = new SimpleTemplateEngine() - def description_html = engine.createTemplate(methods_text).make(meta) - - return description_html - } - - // - // Exit pipeline if incorrect --genome key provided - // - private static void genomeExistsError(params, log) { - if (params.genomes && params.genome && !params.genomes.containsKey(params.genome)) { - def error_string = "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\n" + - " Genome '${params.genome}' not found in any config files provided to the pipeline.\n" + - " Currently, the available genome keys are:\n" + - " ${params.genomes.keySet().join(", ")}\n" + - "~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~" - Nextflow.error(error_string) - } - } + public static void initialise(params, log) { } } diff --git a/lib/WorkflowMain.groovy b/lib/WorkflowMain.groovy index b7f82557..abfc7acf 100755 --- a/lib/WorkflowMain.groovy +++ b/lib/WorkflowMain.groovy @@ -11,9 +11,8 @@ class WorkflowMain { // public static String citation(workflow) { return "If you use ${workflow.manifest.name} for your analysis please cite:\n\n" + - // TODO nf-core: Add Zenodo DOI for pipeline after first release - //"* The pipeline\n" + - //" https://doi.org/10.5281/zenodo.XXXXXXX\n\n" + + "* The pipeline\n" + + " https://doi.org/10.5281/zenodo.10647870\n\n" + "* The nf-core framework\n" + " https://doi.org/10.1038/s41587-020-0439-x\n\n" + "* Software dependencies\n" + @@ -43,11 +42,6 @@ class WorkflowMain { // Check AWS batch settings NfcoreTemplate.awsBatch(workflow, params) - - // Check input has been provided - if (!params.input) { - Nextflow.error("Please provide an input samplesheet to the pipeline e.g. '--input samplesheet.csv'") - } } // // Get attribute from genome config file e.g. fasta diff --git a/main.nf b/main.nf old mode 100644 new mode 100755 index 42a3a13f..34f2ebb3 --- a/main.nf +++ b/main.nf @@ -9,17 +9,6 @@ nextflow.enable.dsl = 2 -/* -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ - GENOME PARAMETER VALUES -~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -*/ - -// TODO nf-core: Remove this line if you don't need a FASTA file -// This is an example of how to use getGenomeAttribute() to fetch parameters -// from igenomes.config using `--genome` -params.fasta = WorkflowMain.getGenomeAttribute(params, 'fasta') - /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ VALIDATE & PRINT PARAMETER SUMMARY @@ -32,18 +21,18 @@ include { validateParameters; paramsHelp } from 'plugin/nf-validation' 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" + def String command = "nextflow run ${workflow.manifest.name} --input assemblysheet.csv --outdir ./results -profile docker" log.info logo + paramsHelp(command) + citation + NfcoreTemplate.dashedLine(params.monochrome_logs) System.exit(0) } +WorkflowMain.initialise(workflow, params, log) + // Validate input parameters if (params.validate_params) { validateParameters() } -WorkflowMain.initialise(workflow, params, log) - /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ NAMED WORKFLOW FOR PIPELINE diff --git a/modules.json b/modules.json index f3c7519d..f01155f8 100644 --- a/modules.json +++ b/modules.json @@ -7,17 +7,17 @@ "nf-core": { "custom/dumpsoftwareversions": { "branch": "master", - "git_sha": "bba7e362e4afead70653f84d8700588ea28d0f9e", + "git_sha": "de45447d060b8c8b98575bc637a4a575fd0638e1", "installed_by": ["modules"] }, - "fastqc": { + "fastavalidator": { "branch": "master", - "git_sha": "65ad3e0b9a4099592e1102e92e10455dc661cf53", + "git_sha": "89ff95427f695086369d7927a3c17cea2a37a382", "installed_by": ["modules"] }, - "multiqc": { + "gunzip": { "branch": "master", - "git_sha": "4ab13872435962dadc239979554d13709e20bf29", + "git_sha": "3a5fef109d113b4997c9822198664ca5f2716208", "installed_by": ["modules"] } } diff --git a/modules/local/samplesheet_check.nf b/modules/local/samplesheet_check.nf deleted file mode 100644 index 7a776dbd..00000000 --- a/modules/local/samplesheet_check.nf +++ /dev/null @@ -1,31 +0,0 @@ -process SAMPLESHEET_CHECK { - tag "$samplesheet" - label 'process_single' - - conda "conda-forge::python=3.8.3" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/python:3.8.3' : - 'biocontainers/python:3.8.3' }" - - input: - path samplesheet - - output: - path '*.csv' , emit: csv - path "versions.yml", emit: versions - - when: - task.ext.when == null || task.ext.when - - script: // This script is bundled with the pipeline, in plant-food-research-open/assemblyqc/bin/ - """ - check_samplesheet.py \\ - $samplesheet \\ - samplesheet.valid.csv - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - python: \$(python --version | sed 's/Python //g') - END_VERSIONS - """ -} diff --git a/modules/nf-core/custom/dumpsoftwareversions/environment.yml b/modules/nf-core/custom/dumpsoftwareversions/environment.yml index f0c63f69..b48ced26 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/environment.yml +++ b/modules/nf-core/custom/dumpsoftwareversions/environment.yml @@ -4,4 +4,4 @@ channels: - bioconda - defaults dependencies: - - bioconda::multiqc=1.17 + - bioconda::multiqc=1.20 diff --git a/modules/nf-core/custom/dumpsoftwareversions/main.nf b/modules/nf-core/custom/dumpsoftwareversions/main.nf index 7685b33c..105f9265 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/main.nf +++ b/modules/nf-core/custom/dumpsoftwareversions/main.nf @@ -4,8 +4,8 @@ process CUSTOM_DUMPSOFTWAREVERSIONS { // Requires `pyyaml` which does not have a dedicated container but is in the MultiQC container conda "${moduleDir}/environment.yml" container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.17--pyhdfd78af_0' : - 'biocontainers/multiqc:1.17--pyhdfd78af_0' }" + 'https://depot.galaxyproject.org/singularity/multiqc:1.20--pyhdfd78af_0' : + 'biocontainers/multiqc:1.20--pyhdfd78af_0' }" input: path versions diff --git a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py b/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py index e55b8d43..da033408 100755 --- a/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py +++ b/modules/nf-core/custom/dumpsoftwareversions/templates/dumpsoftwareversions.py @@ -4,11 +4,10 @@ """Provide functions to merge multiple versions.yml files.""" +import yaml import platform from textwrap import dedent -import yaml - def _make_versions_html(versions): """Generate a tabular HTML output of all versions for MultiQC.""" diff --git a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test b/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test index eec1db10..b1e1630b 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test +++ b/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test @@ -31,7 +31,12 @@ nextflow_process { then { assertAll( { assert process.success }, - { assert snapshot(process.out).match() } + { assert snapshot( + process.out.versions, + file(process.out.mqc_yml[0]).readLines()[0..10], + file(process.out.yml[0]).readLines()[0..7] + ).match() + } ) } } diff --git a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap b/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap index 4274ed57..5f59a936 100644 --- a/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap +++ b/modules/nf-core/custom/dumpsoftwareversions/tests/main.nf.test.snap @@ -1,27 +1,33 @@ { "Should run without failures": { "content": [ - { - "0": [ - "software_versions.yml:md5,1c851188476409cda5752ce971b20b58" - ], - "1": [ - "software_versions_mqc.yml:md5,2570f4ba271ad08357b0d3d32a9cf84d" - ], - "2": [ - "versions.yml:md5,3843ac526e762117eedf8825b40683df" - ], - "mqc_yml": [ - "software_versions_mqc.yml:md5,2570f4ba271ad08357b0d3d32a9cf84d" - ], - "versions": [ - "versions.yml:md5,3843ac526e762117eedf8825b40683df" - ], - "yml": [ - "software_versions.yml:md5,1c851188476409cda5752ce971b20b58" - ] - } + [ + "versions.yml:md5,76d454d92244589d32455833f7c1ba6d" + ], + [ + "data: \"\\n\\n \\n \\n \\n \\n \\n \\n \\n\\", + " \\n\\n\\n \\n \\n\\", + " \\ \\n\\n\\n\\n \\n \\", + " \\ \\n \\n\\n\\n\\n\\", + " \\n\\n \\n \\n\\", + " \\ \\n\\n\\n\\n\\n\\n \\n\\", + " \\ \\n \\n\\n\\n\\n\\", + " \\n\\n \\n \\n\\" + ], + [ + "CUSTOM_DUMPSOFTWAREVERSIONS:", + " python: 3.11.7", + " yaml: 5.4.1", + "TOOL1:", + " tool1: 0.11.9", + "TOOL2:", + " tool2: '1.9'", + "Workflow:" + ] ], - "timestamp": "2023-11-03T14:43:22.157011" + "timestamp": "2024-01-09T23:01:18.710682" } -} +} \ No newline at end of file diff --git a/modules/nf-core/fastavalidator/environment.yml b/modules/nf-core/fastavalidator/environment.yml new file mode 100644 index 00000000..70f346ef --- /dev/null +++ b/modules/nf-core/fastavalidator/environment.yml @@ -0,0 +1,9 @@ +--- +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/environment-schema.json +name: "fastavalidator" +channels: + - conda-forge + - bioconda + - defaults +dependencies: + - "bioconda::py_fasta_validator=0.6" diff --git a/modules/nf-core/fastavalidator/main.nf b/modules/nf-core/fastavalidator/main.nf new file mode 100644 index 00000000..ac5470fb --- /dev/null +++ b/modules/nf-core/fastavalidator/main.nf @@ -0,0 +1,62 @@ +process FASTAVALIDATOR { + tag "$meta.id" + label 'process_single' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/py_fasta_validator:0.6--py37h595c7a6_0': + 'biocontainers/py_fasta_validator:0.6--py37h595c7a6_0' }" + + input: + tuple val(meta), path(fasta) + + output: + tuple val(meta), path('*.success.log') , emit: success_log , optional: true + tuple val(meta), path('*.error.log') , emit: error_log , optional: true + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def prefix = task.ext.prefix ?: "${meta.id}" + """ + py_fasta_validator \\ + -f $fasta \\ + 2> "${prefix}.error.log" \\ + || echo "Errors from fasta_validate printed to ${prefix}.error.log" + + if [ \$(cat "${prefix}.error.log" | wc -l) -gt 0 ]; then + echo "Validation failed..." + + cat \\ + "${prefix}.error.log" + else + echo "Validation successful..." + + mv \\ + "${prefix}.error.log" \\ + fasta_validate.stderr + + echo "Validation successful..." \\ + > "${prefix}.success.log" + fi + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + py_fasta_validator: \$(py_fasta_validator -v | sed 's/.* version //') + END_VERSIONS + """ + + stub: + def prefix = task.ext.prefix ?: "${meta.id}" + """ + echo "Validation successful..." \\ + > "${prefix}.success.log" + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + py_fasta_validator: \$(py_fasta_validator -v | sed 's/.* version //') + END_VERSIONS + """ +} diff --git a/modules/nf-core/fastavalidator/meta.yml b/modules/nf-core/fastavalidator/meta.yml new file mode 100644 index 00000000..c5c4371c --- /dev/null +++ b/modules/nf-core/fastavalidator/meta.yml @@ -0,0 +1,53 @@ +--- +# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json +name: "fastavalidator" +description: | + "Python C-extension for a simple validator for fasta files. The module emits the validated file or an + error log upon validation failure." +keywords: + - fasta + - validation + - genome +tools: + - fasta_validate: + description: | + "Python C-extension for a simple C code to validate a fasta file. It only checks a few things, + and by default only sets its response via the return code, + so you will need to check that!" + homepage: "https://github.com/linsalrob/py_fasta_validator" + documentation: "https://github.com/linsalrob/py_fasta_validator" + tool_dev_url: "https://github.com/linsalrob/py_fasta_validator" + doi: "10.5281/zenodo.5002710" + licence: ["MIT"] +input: + - meta: + type: map + description: | + Groovy Map containing file information + e.g. [ id:'test' ] + - fasta: + type: file + description: Input fasta file + pattern: "*.fasta" +output: + - meta: + type: map + description: | + Groovy Map containing file information + e.g. [ id:'test' ] + - success_log: + type: file + description: Log file for successful validation + pattern: "*.success.log" + - error_log: + type: file + description: Log file for failed validation + pattern: "*.error.log" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@gallvp" +maintainers: + - "@gallvp" diff --git a/modules/nf-core/fastavalidator/tests/main.nf.test b/modules/nf-core/fastavalidator/tests/main.nf.test new file mode 100644 index 00000000..bb8c22cf --- /dev/null +++ b/modules/nf-core/fastavalidator/tests/main.nf.test @@ -0,0 +1,60 @@ +nextflow_process { + + name "Test Process FASTAVALIDATOR" + script "../main.nf" + process "FASTAVALIDATOR" + + tag "modules" + tag "modules_nfcore" + tag "fastavalidator" + + test("sarscov2-fasta-valid") { + + when { + process { + """ + input[0] = [ + [ id:'test', single_end:false ], // meta map + file(params.test_data['sarscov2']['genome']['genome_fasta'], checkIfExists: true) + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() }, + { assert process.out.success_log != null }, + { assert process.out.error_log == [] }, + { assert path(process.out.success_log.get(0).get(1)).getText().contains("Validation successful...") } + ) + } + + } + + test("sarscov2-gff3-invalid") { + + when { + process { + """ + input[0] = [ + [ id:'test', single_end:false ], // meta map + file(params.test_data['sarscov2']['genome']['genome_gff3'], checkIfExists: true) + ] + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() }, + { assert process.out.success_log == [] }, + { assert process.out.error_log != null }, + { assert path(process.out.error_log.get(0).get(1)).getText().contains("genome.gff3 does not start with a >") } + ) + } + + } +} diff --git a/modules/nf-core/fastavalidator/tests/main.nf.test.snap b/modules/nf-core/fastavalidator/tests/main.nf.test.snap new file mode 100644 index 00000000..382dee72 --- /dev/null +++ b/modules/nf-core/fastavalidator/tests/main.nf.test.snap @@ -0,0 +1,76 @@ +{ + "sarscov2-fasta-valid": { + "content": [ + { + "0": [ + [ + { + "id": "test", + "single_end": false + }, + "test.success.log:md5,b0b859eda1db5cd43915846e00ebc22c" + ] + ], + "1": [ + + ], + "2": [ + "versions.yml:md5,05aa059840b3b4dd6d88bc1e4bf976d7" + ], + "error_log": [ + + ], + "success_log": [ + [ + { + "id": "test", + "single_end": false + }, + "test.success.log:md5,b0b859eda1db5cd43915846e00ebc22c" + ] + ], + "versions": [ + "versions.yml:md5,05aa059840b3b4dd6d88bc1e4bf976d7" + ] + } + ], + "timestamp": "2023-11-28T11:23:25.106872" + }, + "sarscov2-gff3-invalid": { + "content": [ + { + "0": [ + + ], + "1": [ + [ + { + "id": "test", + "single_end": false + }, + "test.error.log:md5,531d520c0e7767176f743f197f1f87b3" + ] + ], + "2": [ + "versions.yml:md5,05aa059840b3b4dd6d88bc1e4bf976d7" + ], + "error_log": [ + [ + { + "id": "test", + "single_end": false + }, + "test.error.log:md5,531d520c0e7767176f743f197f1f87b3" + ] + ], + "success_log": [ + + ], + "versions": [ + "versions.yml:md5,05aa059840b3b4dd6d88bc1e4bf976d7" + ] + } + ], + "timestamp": "2023-11-28T11:23:29.40324" + } +} \ No newline at end of file diff --git a/modules/nf-core/fastavalidator/tests/tags.yml b/modules/nf-core/fastavalidator/tests/tags.yml new file mode 100644 index 00000000..c3c77576 --- /dev/null +++ b/modules/nf-core/fastavalidator/tests/tags.yml @@ -0,0 +1,2 @@ +fastavalidator: + - "modules/nf-core/fastavalidator/**" diff --git a/modules/nf-core/fastqc/main.nf b/modules/nf-core/fastqc/main.nf deleted file mode 100644 index 9e19a74c..00000000 --- a/modules/nf-core/fastqc/main.nf +++ /dev/null @@ -1,55 +0,0 @@ -process FASTQC { - tag "$meta.id" - label 'process_medium' - - conda "${moduleDir}/environment.yml" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/fastqc:0.12.1--hdfd78af_0' : - 'biocontainers/fastqc:0.12.1--hdfd78af_0' }" - - input: - tuple val(meta), path(reads) - - output: - tuple val(meta), path("*.html"), emit: html - tuple val(meta), path("*.zip") , emit: zip - path "versions.yml" , emit: versions - - when: - task.ext.when == null || task.ext.when - - script: - def args = task.ext.args ?: '' - def prefix = task.ext.prefix ?: "${meta.id}" - // Make list of old name and new name pairs to use for renaming in the bash while loop - def old_new_pairs = reads instanceof Path || reads.size() == 1 ? [[ reads, "${prefix}.${reads.extension}" ]] : reads.withIndex().collect { entry, index -> [ entry, "${prefix}_${index + 1}.${entry.extension}" ] } - def rename_to = old_new_pairs*.join(' ').join(' ') - def renamed_files = old_new_pairs.collect{ old_name, new_name -> new_name }.join(' ') - """ - printf "%s %s\\n" $rename_to | while read old_name new_name; do - [ -f "\${new_name}" ] || ln -s \$old_name \$new_name - done - - fastqc \\ - $args \\ - --threads $task.cpus \\ - $renamed_files - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - fastqc: \$( fastqc --version | sed '/FastQC v/!d; s/.*v//' ) - END_VERSIONS - """ - - stub: - def prefix = task.ext.prefix ?: "${meta.id}" - """ - touch ${prefix}.html - touch ${prefix}.zip - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - fastqc: \$( fastqc --version | sed '/FastQC v/!d; s/.*v//' ) - END_VERSIONS - """ -} diff --git a/modules/nf-core/fastqc/meta.yml b/modules/nf-core/fastqc/meta.yml deleted file mode 100644 index ee5507e0..00000000 --- a/modules/nf-core/fastqc/meta.yml +++ /dev/null @@ -1,57 +0,0 @@ -name: fastqc -description: Run FastQC on sequenced reads -keywords: - - quality control - - qc - - adapters - - fastq -tools: - - fastqc: - description: | - FastQC gives general quality metrics about your reads. - It provides information about the quality score distribution - across your reads, the per base sequence content (%A/C/G/T). - You get information about adapter contamination and other - overrepresented sequences. - homepage: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ - documentation: https://www.bioinformatics.babraham.ac.uk/projects/fastqc/Help/ - licence: ["GPL-2.0-only"] -input: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - reads: - type: file - description: | - List of input FastQ files of size 1 and 2 for single-end and paired-end data, - respectively. -output: - - meta: - type: map - description: | - Groovy Map containing sample information - e.g. [ id:'test', single_end:false ] - - html: - type: file - description: FastQC report - pattern: "*_{fastqc.html}" - - zip: - type: file - description: FastQC report archive - pattern: "*_{fastqc.zip}" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" -authors: - - "@drpatelh" - - "@grst" - - "@ewels" - - "@FelixKrueger" -maintainers: - - "@drpatelh" - - "@grst" - - "@ewels" - - "@FelixKrueger" diff --git a/modules/nf-core/fastqc/tests/main.nf.test b/modules/nf-core/fastqc/tests/main.nf.test deleted file mode 100644 index b9e8f926..00000000 --- a/modules/nf-core/fastqc/tests/main.nf.test +++ /dev/null @@ -1,109 +0,0 @@ -nextflow_process { - - name "Test Process FASTQC" - script "../main.nf" - process "FASTQC" - tag "modules" - tag "modules_nfcore" - tag "fastqc" - - test("Single-Read") { - - when { - params { - outdir = "$outputDir" - } - process { - """ - input[0] = [ - [ id: 'test', single_end:true ], - [ - file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) - ] - ] - """ - } - } - - then { - assertAll ( - { assert process.success }, - // NOTE The report contains the date inside it, which means that the md5sum is stable per day, but not longer than that. So you can't md5sum it. - // looks like this:
    Mon 2 Oct 2023
    test.gz
    - // https://github.com/nf-core/modules/pull/3903#issuecomment-1743620039 - { assert process.out.html.get(0).get(1) ==~ ".*/test_fastqc.html" }, - { assert path(process.out.html.get(0).get(1)).getText().contains("") }, - { assert snapshot(process.out.versions).match("versions") }, - { assert process.out.zip.get(0).get(1) ==~ ".*/test_fastqc.zip" } - ) - } - } -// TODO -// // -// // Test with paired-end data -// // -// workflow test_fastqc_paired_end { -// input = [ -// [id: 'test', single_end: false], // meta map -// [ -// file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true), -// file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true) -// ] -// ] - -// FASTQC ( input ) -// } - -// // -// // Test with interleaved data -// // -// workflow test_fastqc_interleaved { -// input = [ -// [id: 'test', single_end: false], // meta map -// file(params.test_data['sarscov2']['illumina']['test_interleaved_fastq_gz'], checkIfExists: true) -// ] - -// FASTQC ( input ) -// } - -// // -// // Test with bam data -// // -// workflow test_fastqc_bam { -// input = [ -// [id: 'test', single_end: false], // meta map -// file(params.test_data['sarscov2']['illumina']['test_paired_end_sorted_bam'], checkIfExists: true) -// ] - -// FASTQC ( input ) -// } - -// // -// // Test with multiple samples -// // -// workflow test_fastqc_multiple { -// input = [ -// [id: 'test', single_end: false], // meta map -// [ -// file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true), -// file(params.test_data['sarscov2']['illumina']['test_2_fastq_gz'], checkIfExists: true), -// file(params.test_data['sarscov2']['illumina']['test2_1_fastq_gz'], checkIfExists: true), -// file(params.test_data['sarscov2']['illumina']['test2_2_fastq_gz'], checkIfExists: true) -// ] -// ] - -// FASTQC ( input ) -// } - -// // -// // Test with custom prefix -// // -// workflow test_fastqc_custom_prefix { -// input = [ -// [ id:'mysample', single_end:true ], // meta map -// file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz'], checkIfExists: true) -// ] - -// FASTQC ( input ) -// } -} diff --git a/modules/nf-core/fastqc/tests/main.nf.test.snap b/modules/nf-core/fastqc/tests/main.nf.test.snap deleted file mode 100644 index 636a32ce..00000000 --- a/modules/nf-core/fastqc/tests/main.nf.test.snap +++ /dev/null @@ -1,10 +0,0 @@ -{ - "versions": { - "content": [ - [ - "versions.yml:md5,e1cc25ca8af856014824abd842e93978" - ] - ], - "timestamp": "2023-10-09T23:40:54+0000" - } -} \ No newline at end of file diff --git a/modules/nf-core/fastqc/tests/tags.yml b/modules/nf-core/fastqc/tests/tags.yml deleted file mode 100644 index 7834294b..00000000 --- a/modules/nf-core/fastqc/tests/tags.yml +++ /dev/null @@ -1,2 +0,0 @@ -fastqc: - - modules/nf-core/fastqc/** diff --git a/modules/nf-core/fastqc/environment.yml b/modules/nf-core/gunzip/environment.yml similarity index 61% rename from modules/nf-core/fastqc/environment.yml rename to modules/nf-core/gunzip/environment.yml index 1787b38a..25910b34 100644 --- a/modules/nf-core/fastqc/environment.yml +++ b/modules/nf-core/gunzip/environment.yml @@ -1,7 +1,7 @@ -name: fastqc +name: gunzip channels: - conda-forge - bioconda - defaults dependencies: - - bioconda::fastqc=0.12.1 + - conda-forge::sed=4.7 diff --git a/modules/nf-core/gunzip/main.nf b/modules/nf-core/gunzip/main.nf new file mode 100644 index 00000000..468a6f28 --- /dev/null +++ b/modules/nf-core/gunzip/main.nf @@ -0,0 +1,48 @@ +process GUNZIP { + tag "$archive" + label 'process_single' + + conda "${moduleDir}/environment.yml" + container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? + 'https://depot.galaxyproject.org/singularity/ubuntu:20.04' : + 'nf-core/ubuntu:20.04' }" + + input: + tuple val(meta), path(archive) + + output: + tuple val(meta), path("$gunzip"), emit: gunzip + path "versions.yml" , emit: versions + + when: + task.ext.when == null || task.ext.when + + script: + def args = task.ext.args ?: '' + gunzip = archive.toString() - '.gz' + """ + # Not calling gunzip itself because it creates files + # with the original group ownership rather than the + # default one for that user / the work directory + gzip \\ + -cd \\ + $args \\ + $archive \\ + > $gunzip + + cat <<-END_VERSIONS > versions.yml + "${task.process}": + gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//') + END_VERSIONS + """ + + stub: + gunzip = archive.toString() - '.gz' + """ + touch $gunzip + cat <<-END_VERSIONS > versions.yml + "${task.process}": + gunzip: \$(echo \$(gunzip --version 2>&1) | sed 's/^.*(gzip) //; s/ Copyright.*\$//') + END_VERSIONS + """ +} diff --git a/modules/nf-core/gunzip/meta.yml b/modules/nf-core/gunzip/meta.yml new file mode 100644 index 00000000..231034f2 --- /dev/null +++ b/modules/nf-core/gunzip/meta.yml @@ -0,0 +1,39 @@ +name: gunzip +description: Compresses and decompresses files. +keywords: + - gunzip + - compression + - decompression +tools: + - gunzip: + description: | + gzip is a file format and a software application used for file compression and decompression. + documentation: https://www.gnu.org/software/gzip/manual/gzip.html + licence: ["GPL-3.0-or-later"] +input: + - meta: + type: map + description: | + Optional groovy Map containing meta information + e.g. [ id:'test', single_end:false ] + - archive: + type: file + description: File to be compressed/uncompressed + pattern: "*.*" +output: + - gunzip: + type: file + description: Compressed/uncompressed file + pattern: "*.*" + - versions: + type: file + description: File containing software versions + pattern: "versions.yml" +authors: + - "@joseespinosa" + - "@drpatelh" + - "@jfy133" +maintainers: + - "@joseespinosa" + - "@drpatelh" + - "@jfy133" diff --git a/modules/nf-core/gunzip/tests/main.nf.test b/modules/nf-core/gunzip/tests/main.nf.test new file mode 100644 index 00000000..6406008e --- /dev/null +++ b/modules/nf-core/gunzip/tests/main.nf.test @@ -0,0 +1,36 @@ +nextflow_process { + + name "Test Process GUNZIP" + script "../main.nf" + process "GUNZIP" + tag "gunzip" + tag "modules_nfcore" + tag "modules" + + test("Should run without failures") { + + when { + params { + outdir = "$outputDir" + } + process { + """ + input[0] = Channel.of([ + [], + file(params.modules_testdata_base_path + 'genomics/sarscov2/illumina/fastq/test_1.fastq.gz', checkIfExists: true) + ] + ) + """ + } + } + + then { + assertAll( + { assert process.success }, + { assert snapshot(process.out).match() } + ) + } + + } + +} diff --git a/modules/nf-core/gunzip/tests/main.nf.test.snap b/modules/nf-core/gunzip/tests/main.nf.test.snap new file mode 100644 index 00000000..720fd9ff --- /dev/null +++ b/modules/nf-core/gunzip/tests/main.nf.test.snap @@ -0,0 +1,31 @@ +{ + "Should run without failures": { + "content": [ + { + "0": [ + [ + [ + + ], + "test_1.fastq:md5,4161df271f9bfcd25d5845a1e220dbec" + ] + ], + "1": [ + "versions.yml:md5,54376d32aca20e937a4ec26dac228e84" + ], + "gunzip": [ + [ + [ + + ], + "test_1.fastq:md5,4161df271f9bfcd25d5845a1e220dbec" + ] + ], + "versions": [ + "versions.yml:md5,54376d32aca20e937a4ec26dac228e84" + ] + } + ], + "timestamp": "2023-10-17T15:35:37.690477896" + } +} \ No newline at end of file diff --git a/modules/nf-core/gunzip/tests/tags.yml b/modules/nf-core/gunzip/tests/tags.yml new file mode 100644 index 00000000..fd3f6915 --- /dev/null +++ b/modules/nf-core/gunzip/tests/tags.yml @@ -0,0 +1,2 @@ +gunzip: + - modules/nf-core/gunzip/** diff --git a/modules/nf-core/multiqc/environment.yml b/modules/nf-core/multiqc/environment.yml deleted file mode 100644 index bc0bdb5b..00000000 --- a/modules/nf-core/multiqc/environment.yml +++ /dev/null @@ -1,7 +0,0 @@ -name: multiqc -channels: - - conda-forge - - bioconda - - defaults -dependencies: - - bioconda::multiqc=1.18 diff --git a/modules/nf-core/multiqc/main.nf b/modules/nf-core/multiqc/main.nf deleted file mode 100644 index 00cc48d2..00000000 --- a/modules/nf-core/multiqc/main.nf +++ /dev/null @@ -1,55 +0,0 @@ -process MULTIQC { - label 'process_single' - - conda "${moduleDir}/environment.yml" - container "${ workflow.containerEngine == 'singularity' && !task.ext.singularity_pull_docker_container ? - 'https://depot.galaxyproject.org/singularity/multiqc:1.18--pyhdfd78af_0' : - 'biocontainers/multiqc:1.18--pyhdfd78af_0' }" - - input: - path multiqc_files, stageAs: "?/*" - path(multiqc_config) - path(extra_multiqc_config) - path(multiqc_logo) - - output: - path "*multiqc_report.html", emit: report - path "*_data" , emit: data - path "*_plots" , optional:true, emit: plots - path "versions.yml" , emit: versions - - when: - task.ext.when == null || task.ext.when - - script: - def args = task.ext.args ?: '' - def config = multiqc_config ? "--config $multiqc_config" : '' - def extra_config = extra_multiqc_config ? "--config $extra_multiqc_config" : '' - def logo = multiqc_logo ? /--cl-config 'custom_logo: "${multiqc_logo}"'/ : '' - """ - multiqc \\ - --force \\ - $args \\ - $config \\ - $extra_config \\ - $logo \\ - . - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - multiqc: \$( multiqc --version | sed -e "s/multiqc, version //g" ) - END_VERSIONS - """ - - stub: - """ - touch multiqc_data - touch multiqc_plots - touch multiqc_report.html - - cat <<-END_VERSIONS > versions.yml - "${task.process}": - multiqc: \$( multiqc --version | sed -e "s/multiqc, version //g" ) - END_VERSIONS - """ -} diff --git a/modules/nf-core/multiqc/meta.yml b/modules/nf-core/multiqc/meta.yml deleted file mode 100644 index f1aa660e..00000000 --- a/modules/nf-core/multiqc/meta.yml +++ /dev/null @@ -1,59 +0,0 @@ -# yaml-language-server: $schema=https://raw.githubusercontent.com/nf-core/modules/master/modules/meta-schema.json -name: multiqc -description: Aggregate results from bioinformatics analyses across many samples into a single report -keywords: - - QC - - bioinformatics tools - - Beautiful stand-alone HTML report -tools: - - multiqc: - description: | - MultiQC searches a given directory for analysis logs and compiles a HTML report. - It's a general use tool, perfect for summarising the output from numerous bioinformatics tools. - homepage: https://multiqc.info/ - documentation: https://multiqc.info/docs/ - licence: ["GPL-3.0-or-later"] -input: - - multiqc_files: - type: file - description: | - List of reports / files recognised by MultiQC, for example the html and zip output of FastQC - - multiqc_config: - type: file - description: Optional config yml for MultiQC - pattern: "*.{yml,yaml}" - - extra_multiqc_config: - type: file - description: Second optional config yml for MultiQC. Will override common sections in multiqc_config. - pattern: "*.{yml,yaml}" - - multiqc_logo: - type: file - description: Optional logo file for MultiQC - pattern: "*.{png}" -output: - - report: - type: file - description: MultiQC report file - pattern: "multiqc_report.html" - - data: - type: directory - description: MultiQC data dir - pattern: "multiqc_data" - - plots: - type: file - description: Plots created by MultiQC - pattern: "*_data" - - versions: - type: file - description: File containing software versions - pattern: "versions.yml" -authors: - - "@abhi18av" - - "@bunop" - - "@drpatelh" - - "@jfy133" -maintainers: - - "@abhi18av" - - "@bunop" - - "@drpatelh" - - "@jfy133" diff --git a/modules/nf-core/multiqc/tests/main.nf.test b/modules/nf-core/multiqc/tests/main.nf.test deleted file mode 100644 index c2dad217..00000000 --- a/modules/nf-core/multiqc/tests/main.nf.test +++ /dev/null @@ -1,63 +0,0 @@ -nextflow_process { - - name "Test Process MULTIQC" - script "../main.nf" - process "MULTIQC" - tag "modules" - tag "modules_nfcore" - tag "multiqc" - - test("MULTIQC: FASTQC") { - - when { - params { - outdir = "$outputDir" - } - process { - """ - input[0] = Channel.of([file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz_fastqc_zip'], checkIfExists: true)]) - input[1] = [] - input[2] = [] - input[3] = [] - """ - } - } - - then { - assertAll( - { assert process.success }, - { assert path(process.out.report.get(0)).exists() }, - { assert path(process.out.data.get(0)).exists() }, - { assert path(process.out.versions.get(0)).getText().contains("multiqc") } - ) - } - - } - - test("MULTIQC: FASTQC and a config file") { - - when { - params { - outdir = "$outputDir" - } - process { - """ - input[0] = Channel.of([file(params.test_data['sarscov2']['illumina']['test_1_fastq_gz_fastqc_zip'], checkIfExists: true)]) - input[1] = Channel.of(file("https://github.com/nf-core/tools/raw/dev/nf_core/pipeline-template/assets/multiqc_config.yml", checkIfExists: true)) - input[2] = [] - input[3] = [] - """ - } - } - - then { - assertAll( - { assert process.success }, - { assert path(process.out.report.get(0)).exists() }, - { assert path(process.out.data.get(0)).exists() }, - { assert path(process.out.versions.get(0)).getText().contains("multiqc") } - ) - } - - } -} diff --git a/modules/nf-core/multiqc/tests/tags.yml b/modules/nf-core/multiqc/tests/tags.yml deleted file mode 100644 index bea6c0d3..00000000 --- a/modules/nf-core/multiqc/tests/tags.yml +++ /dev/null @@ -1,2 +0,0 @@ -multiqc: - - modules/nf-core/multiqc/** diff --git a/nextflow.config b/nextflow.config index 3db97ece..92020099 100644 --- a/nextflow.config +++ b/nextflow.config @@ -9,54 +9,87 @@ // Global default params, used in configs params { - // TODO nf-core: Specify your pipeline's command line flags // Input options - input = null - // References - genome = null - igenomes_base = 's3://ngi-igenomes/igenomes/' - igenomes_ignore = false + input = null + // Assemblathon stats options + assemblathon_stats_n_limit = 100 - // MultiQC options - multiqc_config = null - multiqc_title = null - multiqc_logo = null - max_multiqc_email_size = '25.MB' - multiqc_methods_description = null + // NCBI FCS options + ncbi_fcs_adaptor_skip = true + ncbi_fcs_adaptor_empire = 'euk' - // Boilerplate options - outdir = null - publish_dir_mode = 'copy' - email = null - email_on_fail = null - plaintext_email = false - monochrome_logs = false - hook_url = null - help = false - version = false + ncbi_fcs_gx_skip = true + ncbi_fcs_gx_tax_id = null + ncbi_fcs_gx_db_path = null - // 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_contact = null - config_profile_url = null + // BUSCO options + busco_skip = true + busco_mode = 'geno' + busco_lineage_datasets = null + busco_download_path = null + + // TIDK options + tidk_skip = true + tidk_repeat_seq = 'TTAGGG' + tidk_filter_by_size = false + tidk_filter_size_bp = 1000000 + + // LAI options + lai_skip = true + + // kraken2 options + kraken2_skip = true + kraken2_db_path = null + + // HiC options + hic_skip = true + hic_skip_fastp = false + hic_skip_fastqc = false + hic_fastp_ext_args = '--qualified_quality_phred 20 --length_required 50' + // Synteny options + synteny_skip = true + synteny_between_input_assemblies = true + synteny_xref_assemblies = null + synteny_many_to_many_align = false + synteny_max_gap = 1000000 + synteny_min_bundle_size = 1000 + synteny_plot_1_vs_all = true + synteny_color_by_contig = true + + // Output options + outdir = './results' + email = null // Max resource options - // Defaults only, expecting to be overwritten - max_memory = '128.GB' - max_cpus = 16 - max_time = '240.h' + max_memory = '512.GB' + max_cpus = 16 + max_time = '7.day' + + // Boilerplate options + publish_dir_mode = 'copy' + email_on_fail = null + plaintext_email = false + monochrome_logs = false + hook_url = null + help = false + version = false + + // 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_contact = null + config_profile_url = null // Schema validation default options - validationFailUnrecognisedParams = false - validationLenientMode = false - validationSchemaIgnoreParams = 'genomes,igenomes_base' - validationShowHiddenParams = false - validate_params = true + validationFailUnrecognisedParams = false + validationLenientMode = false + validationSchemaIgnoreParams = '' + validationShowHiddenParams = false + validate_params = true } @@ -186,12 +219,6 @@ plugins { id 'nf-validation@1.1.3' // 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' -} else { - params.genomes = [:] -} // Export these variables to prevent local Python/R libraries from conflicting with those in the container // The JULIA depot path has been adjusted to a fixed path `/usr/local/share/julia` that needs to be used for packages in the container. // See https://apeltzer.github.io/post/03-julia-lang-nextflow/ for details on that. Once we have a common agreement on where to keep Julia packages, this is adjustable. @@ -233,9 +260,9 @@ manifest { homePage = 'https://github.com/plant-food-research-open/assemblyqc' description = """AssemblyQC is a NextFlow pipeline which evaluates assembly quality with well-established tools and presents the results in a unified html report.""" mainScript = 'main.nf' - nextflowVersion = '!>=23.04.0' + nextflowVersion = '!>=22.04.3' version = '1.4dev' - doi = '' + doi = '10.5281/zenodo.10647870' } // Load modules.config for DSL2 module specific options diff --git a/nextflow_schema.json b/nextflow_schema.json index 1a13c92b..fd27902b 100644 --- a/nextflow_schema.json +++ b/nextflow_schema.json @@ -8,25 +8,24 @@ "input_output_options": { "title": "Input/output options", "type": "object", - "fa_icon": "fas fa-terminal", - "description": "Define where the pipeline should find input data and save output data.", - "required": ["input", "outdir"], + "description": "", + "default": "", "properties": { "input": { "type": "string", "format": "file-path", - "exists": true, - "mimetype": "text/csv", - "pattern": "^\\S+\\.csv$", - "description": "Path to comma-separated file containing information about the samples in the experiment.", - "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row.", + "mimetype": "csv", + "schema": "assets/schema_input.json", + "help_text": "FASTA and other associated files for input assemblies provided as a formatted CSV file", + "description": "Input assembly sheet in CSV format", "fa_icon": "fas fa-file-csv" }, "outdir": { "type": "string", "format": "directory-path", "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.", - "fa_icon": "fas fa-folder-open" + "fa_icon": "fas fa-folder-open", + "default": "./results" }, "email": { "type": "string", @@ -34,42 +33,258 @@ "fa_icon": "fas fa-envelope", "help_text": "Set 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.", "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$" + } + }, + "required": ["input", "outdir"] + }, + "general_stats_options": { + "title": "General stats options", + "type": "object", + "description": "", + "default": "", + "properties": { + "assemblathon_stats_n_limit": { + "type": "integer", + "default": 100, + "help_text": "This 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.", + "description": "The number of 'N's for the unknown gap size" + } + } + }, + "ncbi_fcs_options": { + "title": "NCBI FCS options", + "type": "object", + "description": "", + "default": "", + "properties": { + "ncbi_fcs_adaptor_skip": { + "type": "boolean", + "description": "Skip NCBI FCS Adaptor checking", + "default": true }, - "multiqc_title": { + "ncbi_fcs_adaptor_empire": { "type": "string", - "description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.", - "fa_icon": "fas fa-file-signature" + "default": "euk", + "enum": ["euk", "prok"], + "description": "Empire for NCBI FCS Adaptor checking" + }, + "ncbi_fcs_gx_skip": { + "type": "boolean", + "description": "Skip NCBI FCS external organism contamination checking", + "default": true + }, + "ncbi_fcs_gx_tax_id": { + "type": "number", + "help_text": "Get correct tax ID from https://www.ncbi.nlm.nih.gov/taxonomy", + "description": "Tax ID for NCBI FCS GX" + }, + "ncbi_fcs_gx_db_path": { + "type": "string", + "format": "directory-path", + "help_text": "NCBI FCS GX DB path\n\nDue 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", + "description": "Path to NCBI FCS GX database" } } }, - "reference_genome_options": { - "title": "Reference genome options", + "busco_options": { + "title": "BUSCO options", "type": "object", - "fa_icon": "fas fa-dna", - "description": "Reference genome related files and options required for the workflow.", + "description": "", + "default": "", "properties": { - "genome": { + "busco_skip": { + "type": "boolean", + "description": "Skip BUSCO", + "default": true + }, + "busco_mode": { + "type": "string", + "default": "geno", + "enum": ["geno", "tran", "prot", "genome", "transcriptome", "proteins"], + "help_text": "'geno' or 'genome' for genome assemblies (DNA), 'tran' or 'transcriptome' for transcriptome assemblies (DNA), 'prot' or 'proteins' for annotated gene sets (protein)", + "description": "BUSCO mode" + }, + "busco_lineage_datasets": { "type": "string", - "description": "Name of iGenomes reference.", - "fa_icon": "fas fa-book", - "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details." + "help_text": "Each input assembly is assessed against each lineage. It should be provided as a space-separated list of lineages: 'fungi_odb10 microsporidia_odb10' ", + "pattern": "^(\\w+_odb10\\s)+\\w+_odb10$", + "description": "BUSCO lineages" }, - "fasta": { + "busco_download_path": { "type": "string", + "help_text": "BUSCO DB download path\n\nThe pipeline automatically downloads the required DB if needed", + "description": "Download path for BUSCO", + "format": "directory-path" + } + } + }, + "tidk_options": { + "title": "TIDK options", + "type": "object", + "description": "", + "default": "", + "properties": { + "tidk_skip": { + "type": "boolean", + "description": "Skip telomere identification", + "default": true + }, + "tidk_repeat_seq": { + "type": "string", + "default": "TTAGGG", + "description": "Telomere repeat sequence", + "pattern": "^[ACGT]+$" + }, + "tidk_filter_by_size": { + "type": "boolean", + "description": "Filter size in base-pairs" + }, + "tidk_filter_size_bp": { + "type": "integer", + "default": 1000000, + "description": "Filter size in base-pairs" + } + } + }, + "lai_options": { + "title": "LAI options", + "type": "object", + "description": "", + "default": "", + "properties": { + "lai_skip": { + "type": "boolean", + "default": true, + "description": "Skip LAI estimation" + } + } + }, + "kraken2_options": { + "title": "Kraken2 options", + "type": "object", + "description": "", + "default": "", + "properties": { + "kraken2_skip": { + "type": "boolean", + "default": true, + "description": "Skip Kraken2" + }, + "kraken2_db_path": { + "type": "string", + "description": "Kraken2 database path", + "format": "path" + } + } + }, + "hic_options": { + "title": "HiC options", + "type": "object", + "description": "", + "default": "", + "properties": { + "hic_skip": { + "type": "boolean", + "default": true, + "description": "Skip HiC contact map construction" + }, + "hic_skip_fastp": { + "type": "boolean", + "description": "Skip HiC read trimming" + }, + "hic_skip_fastqc": { + "type": "boolean", + "description": "Skip HiC read QC" + }, + "hic_fastp_ext_args": { + "type": "string", + "default": "--qualified_quality_phred 20 --length_required 50", + "description": "Additional parameters for fastp trimming" + } + } + }, + "synteny_options": { + "title": "Synteny options", + "type": "object", + "description": "", + "default": "", + "properties": { + "synteny_skip": { + "type": "boolean", + "default": true, + "description": "Skip synteny analysis" + }, + "synteny_between_input_assemblies": { + "type": "boolean", + "description": "Create syntenic plots between each pair of input assemblies", + "default": true + }, + "synteny_xref_assemblies": { + "type": "string", + "description": "Reference assemblies for synteny analysis", + "help_text": "FASTA and synteny label tsv files should be provided in a formatted CSV file ", "format": "file-path", - "exists": true, - "mimetype": "text/plain", - "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$", - "description": "Path to FASTA genome file.", - "help_text": "This parameter is *mandatory* if `--genome` is not specified. If you don't have a BWA index available this will be generated for you automatically. Combine with `--save_reference` to save BWA index for future runs.", - "fa_icon": "far fa-file-code" - }, - "igenomes_ignore": { + "mimetype": "csv", + "schema": "assets/schema_xref_assemblies.json" + }, + "synteny_many_to_many_align": { + "type": "boolean", + "description": "Include alignment blocks with many-to-many mappings (dnadiff .mcoords file)" + }, + "synteny_max_gap": { + "type": "integer", + "default": 1000000, + "description": "Alignments within this distance are bundled together" + }, + "synteny_min_bundle_size": { + "type": "integer", + "default": 1000, + "description": "After bundling, any bundle smaller than this size is filtered out" + }, + "synteny_plot_1_vs_all": { + "type": "boolean", + "default": true, + "description": "Create a separate synteny plot for each contig of the target assembly versus all contigs of the reference assembly" + }, + "synteny_color_by_contig": { "type": "boolean", - "description": "Do not load the iGenomes reference config.", - "fa_icon": "fas fa-ban", + "default": true, + "description": "Synteny plot is colored by contig" + } + } + }, + "max_job_request_options": { + "title": "Max job request options", + "type": "object", + "fa_icon": "fab fa-acquisitions-incorporated", + "description": "Set the top limit for requested resources for any single job.", + "help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.", + "properties": { + "max_cpus": { + "type": "integer", + "description": "Maximum number of CPUs that can be requested for any single job.", + "default": 16, + "fa_icon": "fas fa-microchip", "hidden": true, - "help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`." + "help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`" + }, + "max_memory": { + "type": "string", + "description": "Maximum amount of memory that can be requested for any single job.", + "default": "512.GB", + "fa_icon": "fas fa-memory", + "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$", + "hidden": true, + "help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`" + }, + "max_time": { + "type": "string", + "description": "Maximum amount of time that can be requested for any single job.", + "default": "7.day", + "fa_icon": "far fa-clock", + "pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$", + "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'`" } } }, @@ -121,41 +336,6 @@ } } }, - "max_job_request_options": { - "title": "Max job request options", - "type": "object", - "fa_icon": "fab fa-acquisitions-incorporated", - "description": "Set the top limit for requested resources for any single job.", - "help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.", - "properties": { - "max_cpus": { - "type": "integer", - "description": "Maximum number of CPUs that can be requested for any single job.", - "default": 16, - "fa_icon": "fas fa-microchip", - "hidden": true, - "help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`" - }, - "max_memory": { - "type": "string", - "description": "Maximum amount of memory that can be requested for any single job.", - "default": "128.GB", - "fa_icon": "fas fa-memory", - "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$", - "hidden": true, - "help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`" - }, - "max_time": { - "type": "string", - "description": "Maximum amount of time that can be requested for any single job.", - "default": "240.h", - "fa_icon": "far fa-clock", - "pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$", - "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'`" - } - } - }, "generic_options": { "title": "Generic options", "type": "object", @@ -198,14 +378,6 @@ "fa_icon": "fas fa-remove-format", "hidden": true }, - "max_multiqc_email_size": { - "type": "string", - "description": "File size limit when attaching MultiQC reports to summary emails.", - "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$", - "default": "25.MB", - "fa_icon": "fas fa-file-upload", - "hidden": true - }, "monochrome_logs": { "type": "boolean", "description": "Do not use coloured log outputs.", @@ -219,24 +391,6 @@ "help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.", "hidden": true }, - "multiqc_config": { - "type": "string", - "format": "file-path", - "description": "Custom config file to supply to MultiQC.", - "fa_icon": "fas fa-cog", - "hidden": true - }, - "multiqc_logo": { - "type": "string", - "description": "Custom logo file to supply to MultiQC. File name must also be set in the MultiQC config file", - "fa_icon": "fas fa-image", - "hidden": true - }, - "multiqc_methods_description": { - "type": "string", - "description": "Custom MultiQC yaml file containing HTML including a methods description.", - "fa_icon": "fas fa-cog" - }, "validate_params": { "type": "boolean", "description": "Boolean whether to validate parameters against the schema at runtime", @@ -273,14 +427,35 @@ "$ref": "#/definitions/input_output_options" }, { - "$ref": "#/definitions/reference_genome_options" + "$ref": "#/definitions/general_stats_options" }, { - "$ref": "#/definitions/institutional_config_options" + "$ref": "#/definitions/ncbi_fcs_options" + }, + { + "$ref": "#/definitions/busco_options" + }, + { + "$ref": "#/definitions/tidk_options" + }, + { + "$ref": "#/definitions/lai_options" + }, + { + "$ref": "#/definitions/kraken2_options" + }, + { + "$ref": "#/definitions/hic_options" + }, + { + "$ref": "#/definitions/synteny_options" }, { "$ref": "#/definitions/max_job_request_options" }, + { + "$ref": "#/definitions/institutional_config_options" + }, { "$ref": "#/definitions/generic_options" } diff --git a/subworkflows/local/input_check.nf b/subworkflows/local/input_check.nf deleted file mode 100644 index 0aecf87f..00000000 --- a/subworkflows/local/input_check.nf +++ /dev/null @@ -1,44 +0,0 @@ -// -// Check input samplesheet and get read channels -// - -include { SAMPLESHEET_CHECK } from '../../modules/local/samplesheet_check' - -workflow INPUT_CHECK { - take: - samplesheet // file: /path/to/samplesheet.csv - - main: - SAMPLESHEET_CHECK ( samplesheet ) - .csv - .splitCsv ( header:true, sep:',' ) - .map { create_fastq_channel(it) } - .set { reads } - - emit: - reads // channel: [ val(meta), [ reads ] ] - versions = SAMPLESHEET_CHECK.out.versions // channel: [ versions.yml ] -} - -// Function to get list of [ meta, [ fastq_1, fastq_2 ] ] -def create_fastq_channel(LinkedHashMap row) { - // create meta map - def meta = [:] - meta.id = row.sample - meta.single_end = row.single_end.toBoolean() - - // add path(s) of the fastq file(s) to the meta map - def fastq_meta = [] - if (!file(row.fastq_1).exists()) { - exit 1, "ERROR: Please check input samplesheet -> Read 1 FastQ file does not exist!\n${row.fastq_1}" - } - if (meta.single_end) { - fastq_meta = [ meta, [ file(row.fastq_1) ] ] - } else { - if (!file(row.fastq_2).exists()) { - exit 1, "ERROR: Please check input samplesheet -> Read 2 FastQ file does not exist!\n${row.fastq_2}" - } - fastq_meta = [ meta, [ file(row.fastq_1), file(row.fastq_2) ] ] - } - return fastq_meta -} diff --git a/workflows/assemblyqc.nf b/workflows/assemblyqc.nf index db0a1dd5..56f21437 100644 --- a/workflows/assemblyqc.nf +++ b/workflows/assemblyqc.nf @@ -4,7 +4,7 @@ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -include { paramsSummaryLog; paramsSummaryMap } from 'plugin/nf-validation' +include { paramsSummaryLog; paramsSummaryMap; fromSamplesheet } from 'plugin/nf-validation' def logo = NfcoreTemplate.logo(workflow, params.monochrome_logs) def citation = '\n' + WorkflowMain.citation(workflow) + '\n' @@ -21,10 +21,7 @@ WorkflowAssemblyqc.initialise(params, log) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ */ -ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true) -ch_multiqc_custom_config = params.multiqc_config ? Channel.fromPath( params.multiqc_config, checkIfExists: true ) : Channel.empty() -ch_multiqc_logo = params.multiqc_logo ? Channel.fromPath( params.multiqc_logo, checkIfExists: true ) : Channel.empty() -ch_multiqc_custom_methods_description = params.multiqc_methods_description ? file(params.multiqc_methods_description, checkIfExists: true) : file("$projectDir/assets/methods_description_template.yml", checkIfExists: true) +// ch_multiqc_config = Channel.fromPath("$projectDir/assets/multiqc_config.yml", checkIfExists: true) /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -35,7 +32,7 @@ ch_multiqc_custom_methods_description = params.multiqc_methods_description ? fil // // SUBWORKFLOW: Consisting of a mix of local and nf-core/modules // -include { INPUT_CHECK } from '../subworkflows/local/input_check' +// include { INPUT_CHECK } from '../subworkflows/local/input_check' /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -46,9 +43,13 @@ include { INPUT_CHECK } from '../subworkflows/local/input_check' // // MODULE: Installed directly from nf-core/modules // -include { FASTQC } from '../modules/nf-core/fastqc/main' -include { MULTIQC } from '../modules/nf-core/multiqc/main' -include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main' + +include { GUNZIP as GUNZIP_FASTA } from '../modules/nf-core/gunzip/main' +include { GUNZIP as GUNZIP_GFF3 } from '../modules/nf-core/gunzip/main' +include { FASTAVALIDATOR } from '../modules/nf-core/fastavalidator/main' + +include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoftwareversions/main' + /* ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ @@ -57,57 +58,65 @@ include { CUSTOM_DUMPSOFTWAREVERSIONS } from '../modules/nf-core/custom/dumpsoft */ // Info required for completion email and summary -def multiqc_report = [] +def assemblyqc_report = [] workflow ASSEMBLYQC { - ch_versions = Channel.empty() + ch_versions = Channel.empty() + ch_input = Channel.fromSamplesheet('input') + + ch_target_assemby_branch = ch_input + | map { tag, fasta, gff, ids, reads, labels -> + [ [ id: tag ], file(fasta, checkIfExists: true) ] + } + | branch { meta, fasta -> + gz: "$fasta".endsWith(".gz") + rest: !"$fasta".endsWith(".gz") + } + + ch_assemby_gff3_branch = ch_input + | map { tag, fasta, gff, ids, reads, labels -> + gff + ? [ [ id: tag ], file(gff, checkIfExists: true) ] + : null + } + | branch { meta, gff -> + gz: "$gff".endsWith(".gz") + rest: !"$gff".endsWith(".gz") + } + + // MODULE: GUNZIP as GUNZIP_FASTA + GUNZIP_FASTA ( ch_target_assemby_branch.gz ) + + ch_target_assembly = GUNZIP_FASTA.out.gunzip.mix(ch_target_assemby_branch.rest) + ch_versions = ch_versions.mix(GUNZIP_FASTA.out.versions.first()) - // - // SUBWORKFLOW: Read in samplesheet, validate and stage input files - // - INPUT_CHECK ( - 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 - - // - // MODULE: Run FastQC - // - FASTQC ( - INPUT_CHECK.out.reads - ) - ch_versions = ch_versions.mix(FASTQC.out.versions.first()) + // MODULE: GUNZIP as GUNZIP_GFF3 + GUNZIP_GFF3 ( ch_assemby_gff3_branch.gz ) + + ch_assembly_gff3 = GUNZIP_GFF3.out.gunzip.mix(ch_assemby_gff3_branch.rest) + ch_versions = ch_versions.mix(GUNZIP_GFF3.out.versions.first()) + + // MODULE: FASTAVALIDATOR + FASTAVALIDATOR ( ch_target_assembly ) + + ch_valid_target_assembly = ch_target_assembly.join(FASTAVALIDATOR.out.success_log) + | map { meta, fasta, log -> [ meta, fasta ] } + + ch_invalid_assembly_log = FASTAVALIDATOR.out.error_log + | map { meta, error_log -> + log.warn("FASTA validation failed for ${meta.id}\n${error_log.text}") + + [ meta, error_log ] + } + + ch_versions = ch_versions.mix(FASTAVALIDATOR.out.versions.first()) + + // MODULE: CUSTOM_DUMPSOFTWAREVERSIONS CUSTOM_DUMPSOFTWAREVERSIONS ( ch_versions.unique().collectFile(name: 'collated_versions.yml') ) - - // - // MODULE: MultiQC - // - workflow_summary = WorkflowAssemblyqc.paramsSummaryMultiqc(workflow, summary_params) - ch_workflow_summary = Channel.value(workflow_summary) - - methods_description = WorkflowAssemblyqc.methodsDescriptionText(workflow, ch_multiqc_custom_methods_description, params) - ch_methods_description = Channel.value(methods_description) - - ch_multiqc_files = Channel.empty() - ch_multiqc_files = ch_multiqc_files.mix(ch_workflow_summary.collectFile(name: 'workflow_summary_mqc.yaml')) - ch_multiqc_files = ch_multiqc_files.mix(ch_methods_description.collectFile(name: 'methods_description_mqc.yaml')) - ch_multiqc_files = ch_multiqc_files.mix(CUSTOM_DUMPSOFTWAREVERSIONS.out.mqc_yml.collect()) - ch_multiqc_files = ch_multiqc_files.mix(FASTQC.out.zip.collect{it[1]}.ifEmpty([])) - - MULTIQC ( - ch_multiqc_files.collect(), - ch_multiqc_config.toList(), - ch_multiqc_custom_config.toList(), - ch_multiqc_logo.toList() - ) - multiqc_report = MULTIQC.out.report.toList() } /* @@ -118,7 +127,7 @@ workflow ASSEMBLYQC { workflow.onComplete { if (params.email || params.email_on_fail) { - NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, multiqc_report) + NfcoreTemplate.email(workflow, params, summary_params, projectDir, log, assemblyqc_report) } NfcoreTemplate.dump_parameters(workflow, params) NfcoreTemplate.summary(workflow, params, log)
    Process Name \\", + " \\ Software Version
    CUSTOM_DUMPSOFTWAREVERSIONSpython3.11.7
    yaml5.4.1
    TOOL1tool10.11.9
    TOOL2tool21.9
    WorkflowNextflow
    File typeConventional base calls