nextflow_schema.json

{
    "$schema": "http://json-schema.org/draft-07/schema",
    "$id": "https://raw.githubusercontent.com/nf-core/detaxizer/master/nextflow_schema.json",
    "title": "nf-core/detaxizer pipeline parameters",
    "description": "A pipeline to identify (and remove) certain sequences from raw genomic data. Default taxa to identify (and remove) are Homo and Homo sapiens. Removal is optional.",
    "type": "object",
    "definitions": {
        "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"],
            "properties": {
                "input": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "schema": "assets/schema_input.json",
                    "mimetype": "text/csv",
                    "pattern": "^\\S+\\.csv$",
                    "description": "Path to comma-separated file containing information about the samples in the experiment.",
                    "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row. See [usage docs](https://nf-co.re/detaxizer/usage#samplesheet-input).",
                    "fa_icon": "fas fa-file-csv"
                },
                "outdir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
                    "fa_icon": "fas fa-folder-open",
                    "default": "results"
                },
                "email": {
                    "type": "string",
                    "description": "Email address for completion summary.",
                    "fa_icon": "fas fa-envelope",
                    "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
                },
                "multiqc_title": {
                    "type": "string",
                    "description": "MultiQC report title. Printed as page header, used for filename if not otherwise specified.",
                    "fa_icon": "fas fa-file-signature"
                }
            }
        },
        "general_workflow_parameters": {
            "title": "General workflow parameters",
            "type": "object",
            "description": "Parameters which enable/disable certain steps used in the workflow.",
            "default": "",
            "properties": {
                "enable_filter": {
                    "type": "boolean",
                    "description": "If the filtering step should be carried out.",
                    "help_text": "If set to `True` the filter is used. Otherwise only assessing is performed."
                },
                "filter_trimmed": {
                    "type": "boolean",
                    "description": "If the pre-processed reads should be used by the filter.",
                    "help_text": "If set to `True` the the pre-proccesed reads are used for filtering. Else the raw reads are used."
                },
                "filter_with_kraken2": {
                    "type": "boolean",
                    "help_text": "If this is set to True the kraken2 output is used for filtering.",
                    "description": "If the output of kraken2 should be used for filtering."
                },
                "skip_blastn": {
                    "type": "boolean",
                    "help_text": "Defines if blastn should be used or not. By default blastn is used in the workflow. If also the filter is enabled the reads are filtered using the output from blastn.",
                    "description": "If blastn should be skipped."
                },
                "save_intermediates": {
                    "type": "boolean",
                    "description": "Save intermediates to the results folder.",
                    "help_text": "Set this parameter to `True` if you want to publish the intermediate files to the results folder."
                }
            },
            "fa_icon": "fas fa-angle-double-right"
        },
        "kraken2": {
            "title": "kraken2",
            "type": "object",
            "description": "Parameters used by kraken2 to classify all reads provided. Fine-tuning of the isolation step can be done via the `cutoff_*` parameters.",
            "default": "",
            "properties": {
                "kraken2db": {
                    "type": "string",
                    "default": "https://genome-idx.s3.amazonaws.com/kraken/k2_standard_08gb_20231009.tar.gz",
                    "help_text": "For input how to use this parameter to fine-tune the step see the kraken2 section in the [usage documentation](https://nf-co.re/detaxizer/docs/usage#kraken2)",
                    "description": "The database which is used in the classification step."
                },
                "save_output_fastqs": {
                    "type": "boolean",
                    "description": "Save unclassified reads and classified reads (those assigned to any taxon, not specifically assessed or filtered) to separate files.",
                    "hidden": true
                },
                "kraken2confidence": {
                    "type": "number",
                    "default": 0.05,
                    "description": "Confidence in the classification of a read as a certain taxon.",
                    "help_text": "Refer to https://github.com/DerrickWood/kraken2/blob/master/docs/MANUAL.markdown#confidence-scoring for details."
                },
                "cutoff_tax2filter": {
                    "type": "integer",
                    "default": 2,
                    "description": "If a read has less k-mers assigned to the taxon/taxa to be assessed/to be filtered the read is ignored by the pipeline."
                },
                "cutoff_tax2keep": {
                    "type": "number",
                    "default": 0.5,
                    "minimum": 0,
                    "maximum": 1,
                    "description": "Ratio per read of assigned to tax2filter k-mers to k-mers assigned to any other taxon (except unclassified).",
                    "help_text": "If the ratio of the sum of k-mers mapped to the taxon/taxa to be assessed/to be filtered to (sum(to keep)+sum(to filter/assess)) is below this threshold the read is ignored by the pipeline. Can take values between 0.0 and 1.0."
                },
                "cutoff_unclassified": {
                    "type": "number",
                    "default": 0,
                    "description": "Ratio per read of assigned to tax2filter k-mers to unclassified k-mers.",
                    "minimum": 0,
                    "maximum": 1,
                    "help_text": "If the ratio of the sum of k-mers mapped to the taxon/taxa to be assessed/to be filtered to (unclassified+sum(to filter/assess)) is below this threshold the read is ignored by the pipeline. Can take values between 0.0 and 1.0."
                },
                "tax2filter": {
                    "type": "string",
                    "default": "Homo",
                    "description": "The taxon or taxonomic group to be assessed or filtered by the pipeline.",
                    "help_text": "If a whole taxonomic group should be assessed/filtered use the highest taxonomic name in the hierarchy. E.g. if you want to assess for/filter out the whole taxonomic subtree from Mammalia onward provide this parameter with the string 'Mammalia'."
                }
            },
            "fa_icon": "fas fa-search-location"
        },
        "blastn": {
            "title": "blastn",
            "type": "object",
            "description": "Parameters to fine-tune the output of blastn.",
            "default": "",
            "properties": {
                "blast_coverage": {
                    "type": "number",
                    "default": 40,
                    "description": "Coverage is the percentage of the query sequence which can be found in the alignments of the sequence match. It can be used to fine-tune the validation step."
                },
                "blast_evalue": {
                    "type": "number",
                    "default": 0.01,
                    "description": "The expected(e)-value contains information on how many hits of the same score can be found in a database of the size used in the query by chance. The parameter can be used to fine-tune the validation step."
                },
                "blast_identity": {
                    "type": "number",
                    "default": 40,
                    "description": "Identity is the percentage of the exact matches in the query and the sequence found in the database. The parameter can be used to fine-tune the validation step."
                }
            },
            "fa_icon": "fas fa-search-location"
        },
        "fastp_options": {
            "title": "fastp options",
            "type": "object",
            "description": "Options to control the behavior of fastp",
            "default": "",
            "properties": {
                "reads_minlength": {
                    "type": "integer",
                    "default": 0,
                    "description": "fastp option defining the minimum readlength of a read"
                },
                "fastp_save_trimmed_fail": {
                    "type": "boolean",
                    "description": "fastp option defining if the reads which failed to be trimmed should be saved"
                },
                "fastp_qualified_quality": {
                    "type": "integer",
                    "default": 0,
                    "description": "fastp option to define the threshold of quality of an individual base"
                },
                "fastp_cut_mean_quality": {
                    "type": "integer",
                    "default": 15,
                    "description": "fastp option to define the mean quality for trimming"
                },
                "save_clipped_reads": {
                    "type": "boolean",
                    "description": "fastp option to define if the clipped reads should be saved"
                }
            },
            "fa_icon": "fas fa-cut"
        },
        "reference_genome_options": {
            "title": "Reference genome options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Reference genome related files and options required for the workflow.",
            "properties": {
                "genome": {
                    "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.",
                    "default": "GRCh38"
                },
                "fasta": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "mimetype": "text/plain",
                    "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": {
                    "type": "boolean",
                    "description": "Do not load the iGenomes reference config.",
                    "fa_icon": "fas fa-ban",
                    "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`."
                },
                "saveReference": {
                    "type": "boolean",
                    "default": true
                },
                "igenomes_base": {
                    "type": "string",
                    "description": "Directory / URL base for iGenomes references.",
                    "default": "s3://ngi-igenomes/igenomes/",
                    "format": "directory-path",
                    "fa_icon": "fas fa-cloud-download-alt"
                }
            }
        },
        "institutional_config_options": {
            "title": "Institutional config options",
            "type": "object",
            "fa_icon": "fas fa-university",
            "description": "Parameters used to describe centralised config profiles. These should not be edited.",
            "help_text": "The centralised nf-core configuration profiles use a handful of pipeline parameters to describe themselves. This information is then printed to the Nextflow log when you run a pipeline. You should not need to change these values when you run a pipeline.",
            "properties": {
                "custom_config_version": {
                    "type": "string",
                    "description": "Git commit id for Institutional configs.",
                    "default": "master",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "custom_config_base": {
                    "type": "string",
                    "description": "Base directory for Institutional configs.",
                    "default": "https://raw.githubusercontent.com/nf-core/configs/master",
                    "hidden": true,
                    "help_text": "If you're running offline, Nextflow will not be able to fetch the institutional config files from the internet. If you don't need them, then this is not a problem. If you do need them, you should download the files from the repo and tell Nextflow where to find them with this parameter.",
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_name": {
                    "type": "string",
                    "description": "Institutional config name.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_description": {
                    "type": "string",
                    "description": "Institutional config description.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_contact": {
                    "type": "string",
                    "description": "Institutional config contact information.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                },
                "config_profile_url": {
                    "type": "string",
                    "description": "Institutional config URL link.",
                    "hidden": true,
                    "fa_icon": "fas fa-users-cog"
                }
            }
        },
        "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",
            "fa_icon": "fas fa-file-import",
            "description": "Less common options for the pipeline, typically set in a config file.",
            "help_text": "These options are common to all nf-core pipelines and allow you to customise some of the core preferences for how the pipeline runs.\n\nTypically these options would be set in a Nextflow config file loaded for all pipeline runs, such as `~/.nextflow/config`.",
            "properties": {
                "help": {
                    "type": "boolean",
                    "description": "Display help text.",
                    "fa_icon": "fas fa-question-circle",
                    "hidden": true
                },
                "version": {
                    "type": "boolean",
                    "description": "Display version and exit.",
                    "fa_icon": "fas fa-question-circle",
                    "hidden": true
                },
                "publish_dir_mode": {
                    "type": "string",
                    "default": "copy",
                    "description": "Method used to save pipeline results to output directory.",
                    "help_text": "The Nextflow `publishDir` option specifies which intermediate files should be saved to the output directory. This option tells the pipeline what method should be used to move these files. See [Nextflow docs](https://www.nextflow.io/docs/latest/process.html#publishdir) for details.",
                    "fa_icon": "fas fa-copy",
                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
                    "hidden": true
                },
                "email_on_fail": {
                    "type": "string",
                    "description": "Email address for completion summary, only when pipeline fails.",
                    "fa_icon": "fas fa-exclamation-triangle",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
                    "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
                    "hidden": true
                },
                "plaintext_email": {
                    "type": "boolean",
                    "description": "Send plain-text email instead of HTML.",
                    "fa_icon": "fas fa-remove-format",
                    "hidden": true
                },
                "max_multiqc_email_size": {
                    "type": "string",
                    "description": "File size limit when attaching MultiQC reports to summary emails.",
                    "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
                    "default": "25.MB",
                    "fa_icon": "fas fa-file-upload",
                    "hidden": true
                },
                "monochrome_logs": {
                    "type": "boolean",
                    "description": "Do not use coloured log outputs.",
                    "fa_icon": "fas fa-palette",
                    "hidden": true
                },
                "hook_url": {
                    "type": "string",
                    "description": "Incoming hook URL for messaging service",
                    "fa_icon": "fas fa-people-group",
                    "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",
                    "default": true,
                    "fa_icon": "fas fa-check-square",
                    "hidden": true
                },
                "validationShowHiddenParams": {
                    "type": "boolean",
                    "fa_icon": "far fa-eye-slash",
                    "description": "Show all params when using `--help`",
                    "hidden": true,
                    "help_text": "By default, parameters set as _hidden_ in the schema are not shown on the command line when a user runs with `--help`. Specifying this option will tell the pipeline to show all parameters."
                },
                "validationFailUnrecognisedParams": {
                    "type": "boolean",
                    "fa_icon": "far fa-check-circle",
                    "description": "Validation of parameters fails when an unrecognised parameter is found.",
                    "hidden": true,
                    "help_text": "By default, when an unrecognised parameter is found, it returns a warinig."
                },
                "validationLenientMode": {
                    "type": "boolean",
                    "fa_icon": "far fa-check-circle",
                    "description": "Validation of parameters in lenient more.",
                    "hidden": true,
                    "help_text": "Allows string values that are parseable as numbers or booleans. For further information see [JSONSchema docs](https://github.com/everit-org/json-schema#lenient-mode)."
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/definitions/input_output_options"
        },
        {
            "$ref": "#/definitions/general_workflow_parameters"
        },
        {
            "$ref": "#/definitions/kraken2"
        },
        {
            "$ref": "#/definitions/blastn"
        },
        {
            "$ref": "#/definitions/fastp_options"
        },
        {
            "$ref": "#/definitions/reference_genome_options"
        },
        {
            "$ref": "#/definitions/institutional_config_options"
        },
        {
            "$ref": "#/definitions/max_job_request_options"
        },
        {
            "$ref": "#/definitions/generic_options"
        }
    ]
}