nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/nf-core/createpanelrefs/master/nextflow_schema.json",
    "title": "nf-core/createpanelrefs pipeline parameters",
    "description": "Generate Panel of Normals, models or other similar references from lots of samples",
    "type": "object",
    "$defs": {
        "germlinecnvcaller_options": {
            "title": "Germlinecnvcaller options",
            "type": "object",
            "description": "Options used by the germlinecnvcaller subworkflow",
            "default": "",
            "properties": {
                "gcnv_analysis_type": {
                    "type": "string",
                    "default": "wgs",
                    "description": "Specifies which analysis type for the pipeline- either 'wgs' or 'wes'.",
                    "fa_icon": "fas fa-align-center",
                    "enum": ["wgs", "wes"]
                },
                "gcnv_bin_length": {
                    "type": "number",
                    "default": 1000,
                    "description": "Length (in bp) of the bins. If zero, no binning will be performed.",
                    "fa_icon": "fas fa-sort-numeric-down",
                    "help_text": "Used by GATK's PreprocessIntervals. GATK recommends a bin length of 1000 for WGS analysis, and 0 for WES analysis. "
                },
                "gcnv_exclude_bed": {
                    "type": "string",
                    "exists": true,
                    "format": "path",
                    "fa_icon": "fas fa-file",
                    "pattern": "^\\S+\\.bed$",
                    "description": "Path to directory for a bed file containing regions to be exluded from the analysis.",
                    "help_text": "If the regions you would like to exclude are in bed format, use this option. If you have an interval_list file, use `exclude_interval_list` parameter instead."
                },
                "gcnv_exclude_interval_list": {
                    "type": "string",
                    "exists": true,
                    "format": "path",
                    "fa_icon": "fas fa-file",
                    "pattern": "^\\S+\\._interval_list$",
                    "description": "Path to directory for exclude_interval_list file.",
                    "help_text": "If the regions you would like to exclude are in interval_list format, use this option. If you have a bed file, use `exclude` parameter instead."
                },
                "gcnv_mappable_regions": {
                    "type": "string",
                    "exists": true,
                    "description": "Path to Umap single-read mappability track in .bed or .bed.gz format. Overlapping intervals must be merged.",
                    "format": "file-path",
                    "fa_icon": "fas fa-file",
                    "help_text": "Used by GATK's AnnotateIntervals."
                },
                "gcnv_padding": {
                    "type": "number",
                    "description": "Length (in bp) of the padding regions on each side of the intervals.",
                    "default": 0,
                    "fa_icon": "fas fa-sort-numeric-down",
                    "help_text": "Used by GATK's PreprocessIntervals. GATK recommends a padding of 0 for WGS analysis, and 250 for WES analysis."
                },
                "gcnv_model_name": {
                    "type": "string",
                    "description": "Name for panel of normals.",
                    "default": "germlinecnvcaller"
                },
                "gcnv_ploidy_priors": {
                    "type": "string",
                    "exists": true,
                    "format": "file-path",
                    "mimetype": "text/plain",
                    "description": "Path to a file containing ploidy priors table.",
                    "fa_icon": "fas fa-file",
                    "help_text": "Used by GATK's DeterminGermlineContigPloidy."
                },
                "gcnv_readcount_format": {
                    "type": "string",
                    "description": "Output file format for count data",
                    "default": "HDF5",
                    "fa_icon": "fas fa-align-left",
                    "enum": ["HDF5", "TSV"]
                },
                "gcnv_scatter_content": {
                    "type": "number",
                    "description": "When scattering with this argument, each of the resultant files will (ideally) have this amount of interval-counts.",
                    "default": 5000,
                    "fa_icon": "fas fa-sort-numeric-down",
                    "help_text": "Used by GATK's IntervalListTools."
                },
                "gcnv_segmental_duplications": {
                    "type": "string",
                    "exists": true,
                    "description": "Path to segmental-duplication track in .bed or .bed.gz format. Overlapping intervals must be merged.",
                    "format": "file-path",
                    "fa_icon": "fas fa-file",
                    "help_text": "Used by GATK's AnnotateIntervals."
                },
                "gcnv_target_bed": {
                    "type": "string",
                    "exists": true,
                    "format": "path",
                    "fa_icon": "fas fa-file",
                    "pattern": "^\\S+\\.bed$",
                    "description": "Path to directory for target bed file.",
                    "help_text": "If the regions you would like to analyse are in bed format, use this option. If you have an interval_list file, use `target_interval_list` parameter instead."
                },
                "gcnv_target_interval_list": {
                    "type": "string",
                    "exists": true,
                    "format": "path",
                    "fa_icon": "fas fa-file",
                    "pattern": "^\\S+\\._interval_list$",
                    "description": "Path to directory for target interval_list file.",
                    "help_text": "If the regions you would like to analyse are in interval_list format, use this option. If you have a bed file, use `target_bed` parameter instead."
                }
            }
        },
        "gens_options": {
            "title": "GENS options",
            "type": "object",
            "description": "Options used by the gens subworkflow",
            "default": "",
            "properties": {
                "gens_bin_length": {
                    "type": "number",
                    "default": 100,
                    "description": "Length (in bp) of the bins. If zero, no binning will be performed.",
                    "fa_icon": "fas fa-sort-numeric-down",
                    "help_text": "Used by GATK's PreprocessIntervals. We recommend a bin length of 100."
                },
                "gens_maximum_chunk_size": {
                    "type": "number",
                    "default": 167772150,
                    "description": "Maximum chunk size when writing the HDF5 file"
                },
                "gens_min_interval_median_percentile": {
                    "type": "number",
                    "default": 5,
                    "description": "Minimum interval median percentile for gatk CreateReadCountPanelOfNormals",
                    "help_text": "Genomic intervals with a median (across samples) of fractional coverage (optionally corrected for GC bias) less than or equal to this percentile are filtered out. (This is the first filter applied.)"
                },
                "gens_pon_name": {
                    "type": "string",
                    "description": "Name for panel of normals.",
                    "default": "gens"
                },
                "gens_readcount_format": {
                    "type": "string",
                    "description": "Output file format for count data",
                    "default": "HDF5",
                    "fa_icon": "fas fa-align-left",
                    "enum": ["HDF5", "TSV"]
                }
            }
        },
        "cnvkit_options": {
            "title": "CNVkit options",
            "type": "object",
            "description": "Options used by the cnvkit subworkflow",
            "default": "",
            "properties": {
                "cnvkit_targets": {
                    "type": "string"
                }
            }
        },
        "mutect2_options": {
            "title": "Mutect2 options",
            "type": "object",
            "description": "Options used by the mutect2 subworkflow",
            "default": "",
            "properties": {
                "mutect2_pon_name": {
                    "type": "string"
                },
                "mutect2_target_bed": {
                    "type": "string",
                    "description": "Path to target bed file",
                    "pattern": "^\\S+\\.bed$",
                    "format": "file-path",
                    "fa_icon": "fas fa-file",
                    "exists": true,
                    "mimetype": "text/plain"
                }
            }
        },
        "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": {
                    "description": "Path to comma-separated file containing information about the samples in the experiment.",
                    "help_text": "A design file with information about the samples in your experiment. Use this parameter to specify the location of the input files. It has to be a comma-separated file with a header row. See [usage docs](https://nf-co.re/sarek/usage#input).\n\nIf no input file is specified, sarek will attempt to locate one in the `{outdir}` directory.",
                    "fa_icon": "fas fa-file-csv",
                    "schema": "assets/schema_input.json",
                    "anyOf": [
                        {
                            "type": "string",
                            "format": "file-path",
                            "exists": true,
                            "mimetype": "text/csv",
                            "pattern": "^\\S+\\.csv$"
                        },
                        {
                            "type": "string",
                            "maxLength": 0
                        }
                    ]
                },
                "outdir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
                    "fa_icon": "fas fa-folder-open"
                },
                "email": {
                    "type": "string",
                    "description": "Email address for completion summary.",
                    "fa_icon": "fas fa-envelope",
                    "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
                },
                "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"
                }
            }
        },
        "main_options": {
            "title": "Main options",
            "type": "object",
            "description": "Most common options used for the pipeline",
            "required": ["tools"],
            "default": "",
            "properties": {
                "tools": {
                    "type": "string",
                    "fa_icon": "fas fa-toolbox",
                    "description": "Tools to use for building Panel of Normals or models.",
                    "help_text": "Multiple tools separated with commas.\n\nTools available: CNVKIT,germlinecnvcaller,gens,mutect2",
                    "pattern": "^((cnvkit|germlinecnvcaller|gens|mutect2)?,?)*(?<!,)$"
                }
            },
            "fa_icon": "fas fa-user-cog"
        },
        "reference_genome_options": {
            "title": "Reference genome options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Reference genome related files and options required for the workflow.",
            "properties": {
                "genome": {
                    "type": "string",
                    "description": "Name of iGenomes reference.",
                    "fa_icon": "fas fa-book",
                    "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details."
                },
                "fasta": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "mimetype": "text/plain",
                    "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
                    "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": {
                    "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`."
                },
                "igenomes_base": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "The base path to the igenomes reference files",
                    "fa_icon": "fas fa-ban",
                    "hidden": true,
                    "default": "s3://ngi-igenomes/igenomes/"
                },
                "dict": {
                    "type": "string",
                    "description": "Path to sequence dictionary file",
                    "pattern": "^\\S+\\.dict$",
                    "format": "file-path",
                    "fa_icon": "fas fa-file",
                    "exists": true,
                    "mimetype": "text/plain"
                },
                "fai": {
                    "type": "string",
                    "description": "Path to fasta index file",
                    "pattern": "^\\S+\\.fn?a(sta)?\\.fai$",
                    "format": "file-path",
                    "fa_icon": "fas fa-file",
                    "exists": true,
                    "mimetype": "text/plain"
                }
            }
        },
        "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"
                }
            }
        },
        "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": {
                "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
                },
                "pipelines_testdata_base_path": {
                    "type": "string",
                    "fa_icon": "far fa-check-circle",
                    "description": "Base URL or local path to location of pipeline test dataset files",
                    "default": "https://raw.githubusercontent.com/nf-core/test-datasets/",
                    "hidden": true
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/germlinecnvcaller_options"
        },
        {
            "$ref": "#/$defs/gens_options"
        },
        {
            "$ref": "#/$defs/cnvkit_options"
        },
        {
            "$ref": "#/$defs/mutect2_options"
        },
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/main_options"
        },
        {
            "$ref": "#/$defs/reference_genome_options"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ]
}