nextflow_schema.json

{
  "$schema": "http://json-schema.org/draft-07/schema",
  "$id": "https://raw.githubusercontent.com/./master/nextflow_schema.json",
  "title": ". pipeline parameters",
  "description": "",
  "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": ["project", "samplesheet", "outdir"],
      "properties": {
        "project": {
          "type": "string",
          "description": "The MAGs project name, used to create an isolated workdir",
          "fa_icon": "fas fa-ad"
        },
        "metagenome": {
          "type": "string",
          "description": "Metagenome from ENA list for upload",
          "fa_icon": "fas fa-ad"
        },
        "biomes": {
          "type": "string",
          "description": "Biome in format: environment_biome,environment_feature,environment_material",
          "fa_icon": "fas fa-ad",
          "pattern": "^[a-z\\s]+,[a-z\\s]+,[a-z\\s-]+$"
        },
        "samplesheet": {
          "type": "string",
          "format": "file-path",
          "exists": true,
          "mimetype": "text/csv",
          "pattern": "^\\S+\\.csv$",
          "schema": "assets/schema_input.json",
          "description": "Path to comma-separated file containing information about the assemblies, raw reads with the prefix to be used.",
          "help_text": "You will need to create a design file with information about the assemblies, raw reads running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 5 columns, and a header row.",
          "fa_icon": "fas fa-file-csv"
        },
        "assembly_software_file": {
          "type": "string",
          "format": "file-path",
          "exists": true,
          "mimetype": "text/tsv",
          "pattern": "^\\S+\\.tsv$",
          "description": "Path to tab-separated file containing run_accession and assembly software that was used for assembly.",
          "help_text": "The easiest way to create that file is to take run_accession, assembly_accession and assembler info (Assembler_vVERSION from backlog DB.",
          "fa_icon": "fas fa-file-tsv"
        },
        "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"
        }
      }
    },
    "quality_control": {
      "title": "Quality Control",
      "type": "object",
      "description": "QC related parameters",
      "default": "",
      "properties": {
        "merge_pairs": {
          "type": "boolean",
          "description": "Merge the paired reads after QC",
          "default": true
        },
        "min_contig_size": {
          "type": "integer",
          "default": 1500,
          "description": "Minimum contig size in bp. Contigs smaller that this will be discarded"
        }
      }
    },
    "prokaryotes_mags_generation": {
      "title": "Prokaryotes MAGs generation",
      "type": "object",
      "description": "Options for Prokaryotes MAGs generation subworkflow",
      "default": "",
      "properties": {
        "skip_prok": {
          "type": "boolean",
          "description": "Skip the prokaryotes MAGs generation subworkflow"
        },
        "skip_maxbin2": {
          "type": "boolean",
          "description": "Skip Max Bin 2 binning"
        },
        "skip_metabat2": {
          "type": "boolean",
          "description": "Skip MetaBAT 2 binning"
        },
        "skip_concoct": {
          "type": "boolean",
          "description": "Skip CONCOCT binning"
        },
        "metabat2_rng_seed": {
          "type": "integer",
          "default": 1,
          "description": "RNG seed for MetaBAT2",
          "help_text": "MetaBAT2 is run by default with a fixed seed within this pipeline, thus producing reproducible results. You can set it also to any other positive integer to ensure reproducibility. Set the parameter to 0 to use a random seed."
        },
        "cat_db_folder": {
          "type": "string",
          "description": "CAT diamond reference DB folder path",
          "format": "directory-path"
        },
        "cat_diamond_db": {
          "type": "string",
          "description": "CAT diamond reference DB file",
          "format": "file-path"
        },
        "cat_taxonomy_db": {
          "type": "string",
          "description": "CAT taxonomy reference DB folder path",
          "format": "directory-path"
        },
        "gunc_db": {
          "type": "string",
          "description": "GUNC reference db",
          "format": "file-path",
          "pattern": "^\\S+\\.dmnd$"
        },
        "checkm2_db": {
          "type": "string",
          "description": "CheckM 2 referece DB file path",
          "format": "file-path",
          "pattern": "^\\S+\\.dmnd$"
        },
        "rfam_rrna_models": {
          "type": "string",
          "description": "RFam RNA models",
          "format": "directory-path"
        },
        "gtdbtk_db": {
          "type": "string",
          "description": "GTDBTk reference database",
          "format": "directory-path"
        }
      }
    },
    "eukaryotes_mags_generation": {
      "title": "Eukaryotes MAGs generation",
      "type": "object",
      "description": "Options for Eukaryotes MAGs generation subworkflow",
      "default": "",
      "properties": {
        "skip_euk": {
          "type": "boolean"
        },
        "eukcc_db": {
          "type": "string",
          "description": "EukCC reference database. Setup instructions: https://eukcc.readthedocs.io/en/latest/quickstart.html#database-setup",
          "format": "directory-path",
          "help_text": "EukCC reference database. \n"
        },
        "busco_db": {
          "type": "string",
          "description": "Filepath for the BUSCO dataset downloads",
          "format": "directory-path"
        }
      }
    },
    "reference_genome": {
      "title": "Reference genome",
      "type": "object",
      "description": "Reference genome related files and options required for the decontamination subworkflow.",
      "default": "",
      "fa_icon": "fas fa-file",
      "properties": {
        "ref_genome": {
          "type": "string",
          "description": "Reference genome .fasta file",
          "format": "path"
        }
      }
    },
    "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
        },
        "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)."
        },
        "multiqc_title": {
          "type": "string",
          "description": "Custom title for the MultiQC report.",
          "fa_icon": "fas fa-cog"
        },
        "multiqc_config": {
          "type": "string",
          "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"
        }
      }
    }
  },
  "allOf": [
    {
      "$ref": "#/definitions/input_output_options"
    },
    {
      "$ref": "#/definitions/quality_control"
    },
    {
      "$ref": "#/definitions/prokaryotes_mags_generation"
    },
    {
      "$ref": "#/definitions/eukaryotes_mags_generation"
    },
    {
      "$ref": "#/definitions/reference_genome"
    },
    {
      "$ref": "#/definitions/max_job_request_options"
    },
    {
      "$ref": "#/definitions/generic_options"
    }
  ]
}