nextflow_schema.json

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/comparete/comparete/master/nextflow_schema.json",
  "title": "comparete pipeline parameters",
  "description": "TE comparative analysis",
  "type": "object",
  "$defs": {
    "input_output_options": {
      "title": "Input/output options",
      "type": "object",
      "fa_icon": "fas fa-terminal",
      "description": "Define where the pipeline should find input data and save output data.",
      "required": ["input", "outdir"],
      "properties": {
        "input": {
          "type": "string",
          "format": "file-path",
          "exists": true,
          "mimetype": "text/csv",
          "pattern": "^\\S+\\.csv$",
          "description": "Path to comma-separated file describing the genomes to analyse.",
          "help_text": "A headerless CSV with one row per genome. Each row is either two columns (`name,ncbi_accession` or `name,fasta`) or three columns (`name,fasta,gff`). See `assets/schema_input.json` and the `data/` directory for examples.",
          "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.",
          "default": "results",
          "fa_icon": "fas fa-folder-open"
        },
        "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
        }
      }
    },
    "reference_and_download_options": {
      "title": "Reference and download options",
      "type": "object",
      "fa_icon": "fas fa-dna",
      "description": "Options controlling how reference genomes and annotation are obtained.",
      "properties": {
        "ensembl_biomart": {
          "type": "string",
          "description": "Ensembl BioMart identifier used to download GO annotation.",
          "fa_icon": "fas fa-database"
        },
        "ensembl_dataset": {
          "type": "string",
          "description": "Ensembl BioMart dataset (species) used to download GO annotation.",
          "fa_icon": "fas fa-database"
        },
        "predownloaded_fasta": {
          "type": "string",
          "format": "path",
          "description": "Path to a pre-downloaded FASTA file, bypassing the download step.",
          "fa_icon": "fas fa-file"
        },
        "predownloaded_gofiles": {
          "type": "string",
          "format": "path",
          "description": "Path to pre-downloaded GO annotation files, bypassing the download step.",
          "fa_icon": "fas fa-file"
        },
        "famdb": {
          "type": "string",
          "format": "directory-path",
          "description": "Optional Dfam famdb directory to override the one bundled in the Earl Grey container.",
          "help_text": "The Earl Grey container already ships a configured Dfam 3.7 database, so this is not required. To use a newer Dfam release, point this at a directory containing the famdb partitions (e.g. `dfam39_full.N.h5` files); it is bind-mounted into the container at `/opt/conda/share/RepeatMasker/Libraries/famdb`. Note that overriding only the famdb can cause version mismatches with the container's prebuilt RepeatMasker library.",
          "fa_icon": "fas fa-database"
        }
      }
    },
    "analysis_options": {
      "title": "Analysis options",
      "type": "object",
      "fa_icon": "fas fa-cogs",
      "description": "Toggle which downstream analyses are run.",
      "properties": {
        "orthofinder": {
          "type": "boolean",
          "description": "Run OrthoFinder to infer orthogroups across the input genomes.",
          "fa_icon": "fas fa-project-diagram"
        },
        "earlgrey": {
          "type": "boolean",
          "description": "Run Earl Grey for transposable element annotation.",
          "fa_icon": "fas fa-bug"
        },
        "hite": {
          "type": "boolean",
          "description": "Run HiTE for transposable element detection.",
          "fa_icon": "fas fa-bug"
        },
        "repeatmasker": {
          "type": "boolean",
          "description": "Run the RepeatMasker/RepeatModeler subworkflow for transposable element annotation.",
          "help_text": "Uses the Dfam library from --famdb (via famdb.py) to mask each genome with RepeatMasker. Optionally builds a de novo library first with --run_repeatmodeler.",
          "fa_icon": "fas fa-bug"
        },
        "run_repeatmodeler": {
          "type": "boolean",
          "description": "Within --repeatmasker, also build a de novo repeat library with RepeatModeler (slow, adds substantial runtime per genome).",
          "fa_icon": "fas fa-cogs"
        },
        "te_clusterer": {
          "type": "string",
          "default": "linclust",
          "enum": ["linclust", "mmseqs", "cdhit"],
          "description": "Clustering tool used to reduce redundancy in the RepeatMasker library.",
          "fa_icon": "fas fa-layer-group"
        },
        "repeatmasker_speed": {
          "type": "string",
          "default": "qq",
          "enum": ["default", "q", "qq"],
          "description": "RepeatMasker sensitivity/speed: 'default' (most sensitive), 'q' (quick), 'qq' (fastest).",
          "fa_icon": "fas fa-tachometer-alt"
        },
        "famdb_lineage": {
          "type": "string",
          "description": "Lineage to extract from the famdb for RepeatMasker (e.g. 'hymenoptera'). Defaults to 'root' when unset.",
          "fa_icon": "fas fa-sitemap"
        }
      }
    },
    "execution_options": {
      "title": "Execution options",
      "type": "object",
      "fa_icon": "fas fa-running",
      "description": "Options controlling how the pipeline executes.",
      "properties": {
        "forks": {
          "type": "integer",
          "description": "Maximum number of concurrent tasks (process.maxForks). Leave unset for no limit.",
          "fa_icon": "fas fa-code-branch"
        },
        "clean": {
          "type": "boolean",
          "description": "Remove work directories when the pipeline completes successfully.",
          "fa_icon": "fas fa-broom"
        },
        "architecture": {
          "type": "string",
          "default": "amd",
          "enum": ["amd", "arm"],
          "description": "CPU architecture of the platform the pipeline is running on.",
          "fa_icon": "fas fa-microchip"
        },
        "custom_config": {
          "type": "string",
          "format": "file-path",
          "description": "Path to an additional Nextflow config file to include.",
          "fa_icon": "fas fa-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 would need your own configuration file.",
      "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",
          "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",
          "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
          "fa_icon": "fas fa-memory",
          "help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
        },
        "max_time": {
          "type": "string",
          "description": "Maximum amount of time that can be requested for any single job.",
          "default": "48.h",
          "pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$",
          "fa_icon": "far fa-clock",
          "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.",
      "properties": {
        "help": {
          "type": "boolean",
          "description": "Display help text.",
          "fa_icon": "fas fa-question-circle",
          "hidden": true
        },
        "trace_report_suffix": {
          "type": "string",
          "description": "Suffix to add to the trace report filename. Default is the date and time in yyyy-MM-dd_HH-mm-ss format.",
          "fa_icon": "fas fa-clock",
          "hidden": true
        },
        "config_profile_description": {
          "type": "string",
          "description": "Description of the institutional config profile.",
          "fa_icon": "fas fa-users-cog",
          "hidden": true
        },
        "config_profile_contact": {
          "type": "string",
          "description": "Contact person for the institutional config profile.",
          "fa_icon": "fas fa-users-cog",
          "hidden": true
        },
        "config_profile_url": {
          "type": "string",
          "description": "URL with documentation for the institutional config profile.",
          "fa_icon": "fas fa-users-cog",
          "hidden": true
        }
      }
    }
  },
  "allOf": [
    { "$ref": "#/$defs/input_output_options" },
    { "$ref": "#/$defs/reference_and_download_options" },
    { "$ref": "#/$defs/analysis_options" },
    { "$ref": "#/$defs/execution_options" },
    { "$ref": "#/$defs/max_job_request_options" },
    { "$ref": "#/$defs/generic_options" }
  ]
}