nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/doh-jdj0303/vaper/master/nextflow_schema.json",
    "title": "doh-jdj0303/vaper pipeline parameters",
    "description": "VAPER is a viral (meta)-genome assembly pipeline.",
    "type": "object",
    "$defs": {
        "input_output_options": {
            "title": "Input/output options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define where the pipeline should find input data and save output data.",
            "required": [
                "input",
                "outdir"
            ],
            "properties": {
                "input": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "schema": "assets/schema_input.json",
                    "mimetype": "text/csv",
                    "pattern": "^\\S+\\.csv$",
                    "description": "Path to comma-separated file containing sample information (sample name, FASTQ files, reference genomes, etc.,)",
                    "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.",
                    "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"
                },
                "max_reads": {
                    "type": "integer",
                    "default": 2000000,
                    "description": "The maximum number of reads to include in the analysis.",
                    "fa_icon": "fas fa-tachometer-alt"
                },
                "scrub_reads": {
                    "type": "boolean",
                    "description": "Option to use the SRA Human Read Scrubber tool prior to read processing.",
                    "fa_icon": "fas fa-user-alt-slash"
                },
                "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})$",
                    "hidden": true
                },
                "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",
                    "hidden": true
                }
            }
        },
        "metagenomic_analysis": {
            "title": "Metagenomic Analysis",
            "type": "object",
            "description": "Parameters related to the metagenomic analysis using Sourmash",
            "default": "",
            "properties": {
                "metagenome": {
                    "type": "boolean",
                    "default": true,
                    "description": "Perform metagenomic analysis.",
                    "fa_icon": "fas fa-braille"
                },
                "sm_db": {
                    "type": "string",
                    "default": "https://github.com/DOH-JDJ0303/vaper/raw/refs/heads/dev_v2.0/assets/databases/ncbi-viruses-2025.01.dna.k=21.sig.zip",
                    "description": "Path to Sourmash database to use for metagenomic classification",
                    "fa_icon": "fas fa-database"
                },
                "sm_taxa": {
                    "type": "string",
                    "default": "https://github.com/DOH-JDJ0303/vaper/raw/refs/heads/dev_v2.0/assets/databases/ncbi-viruses.2025.01.lineages.csv.gz",
                    "description": "Path to taxonomic information for the Sourmash database supplied via `--sm_db`.",
                    "fa_icon": "fas fa-project-diagram"
                }
            }
        },
        "reference_selection": {
            "title": "Reference Selection",
            "type": "object",
            "description": "Parameters controlling reference selection.",
            "default": "",
            "properties": {
                "ref_set": {
                    "type": "string",
                    "default": "${projectDir}/assets/reference_sets/*.jsonl.gz",
                    "description": "Path to a compressed reference set in JSON lines format or CSV format.",
                    "fa_icon": "fas fa-database"
                },
                "ref_file": {
                    "type": "string",
                    "description": "Path(s) to reference files in FASTA format. References supplied this way will be used to create assemblies for **all** samples.",
                    "fa_icon": "fas fa-copy"
                },
                "ref_mode": {
                    "type": "string",
                    "default": "standard",
                    "description": "Reference selection mode ('standard', 'sensitive', 'kitchen-sink', or null",
                    "fa_icon": "fab fa-buffer"
                },
                "ref_genfrac": {
                    "type": "number",
                    "default": 0.5,
                    "description": "Minimum genome fraction used for reference selection.",
                    "fa_icon": "fas fa-chart-pie"
                },
                "ref_dist": {
                    "type": "number",
                    "default": 0.2,
                    "description": "Average nucleotide difference used to cluster references during reference selection (`1 - ( % ANI / 100 )`).",
                    "fa_icon": "fas fa-chart-pie"
                },
                "ref_denovo_assembler": {
                    "type": "string",
                    "default": "megahit",
                    "description": "De novo assembler to use for accurate reference selection ('spades', 'megahit', 'velvet', 'skesa')",
                    "fa_icon": "fas fa-toolbox"
                },
                "ref_denovo_contigcov": {
                    "type": "integer",
                    "default": 10,
                    "description": "Minimum depth of coverage for a contig to be retained in the de novo assembly.",
                    "fa_icon": "fas fa-chart-pie"
                },
                "ref_denovo_contiglen": {
                    "type": "integer",
                    "default": 300,
                    "description": "Minimum length for a contig to be retained in the de novo assembly.",
                    "fa_icon": "fas fa-chart-pie"
                },
                "ref_denovo_gsize": {
                    "type": "string",
                    "default": "1.0M",
                    "description": "Genome size estimate used by Shovill",
                    "fa_icon": "fas fa-chart-pie"
                },
                "ref_denovo_depth": {
                    "type": "integer",
                    "default": 30,
                    "description": "Target assembly depth used by Shovill",
                    "fa_icon": "fas fa-chart-pie"
                },
                "ref_taxon": {
                    "type": "string",
                    "description": "A semi-colon separated list of taxon in the reference set that should be considered during reference selection",
                    "fa_icon": "fas fa-filter"
                },
                "ref_species": {
                    "type": "string",
                    "description": "A semi-colon separated list of species in the reference set that should be considered during reference selection",
                    "fa_icon": "fas fa-filter"
                },
                "ref_name": {
                    "type": "string",
                    "description": "A semi-colon separated list of references in the reference set that should be used for genome assembly",
                    "fa_icon": "fas fa-filter"
                },
                "ref_include": {
                    "type": "string",
                    "description": "A semi-colon separated list of inclusion patterns to be applied to the reference set",
                    "fa_icon": "fas fa-filter"
                },
                "ref_exclude": {
                    "type": "string",
                    "description": "A semi-colon separated list of exclusion patterns to be applied to the reference set",
                    "fa_icon": "fas fa-filter"
                }
            }
        },
        "assembly_options": {
            "title": "Assembly Options",
            "type": "object",
            "description": "Parameters controlling genome assembly",
            "default": "",
            "properties": {
                "cons_mode": {
                    "type": "string",
                    "default": "standard",
                    "description": "Method used for creating the reference-based assembly ('standard' or 'mixed')",
                    "fa_icon": "fab fa-buffer"
                },
                "cons_allele_qual": {
                    "type": "integer",
                    "default": 20,
                    "description": "Minimum allele quality when making the reference-based assembly.",
                    "fa_icon": "fas fa-chart-pie"
                },
                "cons_allele_ratio": {
                    "type": "number",
                    "default": 0.6,
                    "description": "Minimum allele support when making the reference-based assembly.",
                    "fa_icon": "fas fa-chart-pie"
                },
                "cons_allele_depth": {
                    "type": "integer",
                    "default": 10,
                    "description": "Minimum allele depth when making the reference-based assembly.",
                    "fa_icon": "fas fa-chart-pie"
                },
                "cons_max_depth": {
                    "type": "integer",
                    "default": 100,
                    "description": "Maximum read depth per assembly.",
                    "fa_icon": "fas fa-chart-pie"
                },
                "cons_condist": {
                    "type": "number",
                    "default": 0.1,
                    "description": "Average nucleotide difference used to condense duplicate assemblies (`1 - ( % ANI / 100 )`).",
                    "fa_icon": "fas fa-chart-pie"
                },
                "cons_prune_termini": {
                    "type": "boolean",
                    "fa_icon": "fas fa-cut",
                    "description": "Remove N characters from the ends of each assembly."
                },
                "cons_no_mixed_sites": {
                    "type": "boolean",
                    "description": "Replace all non-ATCGN sites with N",
                    "fa_icon": "fas fa-blender"
                }
            }
        },
        "quality_control": {
            "title": "Quality Control",
            "type": "object",
            "description": "Parameters controlling final assessment of assembly QC",
            "default": "",
            "properties": {
                "qc_genfrac": {
                    "type": "number",
                    "default": 0.8,
                    "description": "Minimum genome fraction used for quality assessment of reference-based assemblies.",
                    "fa_icon": "fas fa-chart-pie"
                },
                "qc_depth": {
                    "type": "integer",
                    "default": 30,
                    "description": "Minimum average depth of coverage used for quality assessment of reference-based assemblies.",
                    "fa_icon": "fas fa-chart-pie"
                }
            }
        },
        "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",
                    "hidden": true
                },
                "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
                },
                "trace_report_suffix": {
                    "type": "string",
                    "fa_icon": "far calendar",
                    "description": "Suffix to add to the trace report filename. Default is the date and time in the format yyyy-MM-dd_HH-mm-ss.",
                    "hidden": true
                },
                "help": {
                    "type": [
                        "boolean",
                        "string"
                    ],
                    "description": "Display the help message.",
                    "hidden": true
                },
                "help_full": {
                    "type": "boolean",
                    "description": "Display the full detailed help message.",
                    "hidden": true
                },
                "show_hidden": {
                    "type": "boolean",
                    "description": "Display hidden parameters in the help message (only works when --help or --help_full are provided).",
                    "hidden": true
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/metagenomic_analysis"
        },
        {
            "$ref": "#/$defs/reference_selection"
        },
        {
            "$ref": "#/$defs/assembly_options"
        },
        {
            "$ref": "#/$defs/quality_control"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ]
}