nextflow_schema.json

{
    "$schema": "http://json-schema.org/draft-07/schema",
    "$id": "https://raw.githubusercontent.com/Arcadia-Science/noveltree/main/nextflow_schema.json",
    "title": "Arcadia-Science/noveltree pipeline parameters",
    "description": "Phylogenomic inference from whole-proteome data: orthology, gene-family and species trees, reconciliation, and physicochemical distance analysis",
    "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",
                "mcl_inflation",
                "outdir",
                "min_num_spp_per_og",
                "min_prop_spp_for_spptree",
                "max_copy_num_spp_tree"
            ],
            "properties": {
                "input": {
                    "type": "string",
                    "format": "file-path",
                    "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.",
                    "fa_icon": "fas fa-file-csv"
                },
                "mcl_inflation": {
                    "type": "string",
                    "description": "Array of MCL inflation values, expressed as a comma-separated string (ie 1.5,3.0,4.5), or a single numerical value (ie 1.5).",
                    "fa_icon": "fas fa-file-signature"
                },
                "outdir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "The output directory where the results will be saved. Use absolute paths when specifying S3 URIs. No trailing / please.",
                    "fa_icon": "fas fa-folder-open"
                },
                "busco_lineages_path": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Optional path to where BUSCO lineage datasets are stored remotely (e.g. on S3).",
                    "fa_icon": "fas fa-file-csv"
                },
                "min_num_seq_per_og": {
                    "type": "integer",
                    "default": 4,
                    "description": "The minimum number of sequences within a gene family required for retention of that family for phylogenetic inference."
                },
                "min_num_spp_per_og": {
                    "type": "integer",
                    "default": 2,
                    "description": "Minimum number of species included in orthogroup required for inference of MSA, gene family tree, and inclusion in species tree inference."
                },
                "min_prop_spp_for_spptree": {
                    "type": "number",
                    "default": 0.50,
                    "description": "Minimum proportion of all species in orthogroup for inclusion in species tree inference."
                },
                "max_copy_num_spp_tree": {
                    "type": "integer",
                    "default": 10,
                    "description": "Maximum mean per-species orthogroup gene copy allowed for species tree inference."
                },
                "aligner": {
                    "type": "string",
                    "default": "adaptive",
                    "description": "Alignment method. 'adaptive' (default) uses three-tier routing: MAFFT_TIER1 for ≤200 seqs → WITCH_TIER2 for ≤3000 → FAMSA_TIER3 for larger, with automatic fallback. 'mafft', 'witch', and 'famsa' use a single aligner for all families.",
                    "enum": ["adaptive", "mafft", "witch", "famsa"]
                },
                "msa_trimmer": {
                    "type": "string",
                    "default": "clipkit",
                    "description": "Option specifying the method used to trim/clean multiple sequence alignments prior to phylogenetic inference. Either CIAlign ('cialign') or ClipKIT ('clipkit'). Additional params for either method should be provided in modules.config."
                },
                "min_ungapped_length": {
                    "type": "integer",
                    "default": 50,
                    "description": "Option specifying the minimum ungapped length of cleaned/trimmed multiple sequence alignments. Prevents ClipKIT from removing all non-gap characters. Specify as null (no quotes) if you do not want to remove short sequences with CIAlign."
                },
                "tree_method": {
                    "type": "string",
                    "default": "iqtree",
                    "description": "Method used to infer phylogenies from trimmed and cleaned MSAs. Default is iqtree, alternative is fasttree."
                },
                "tree_model": {
                    "type": "string",
                    "default": "LG+F+G4",
                    "description": "AA substitution model used by IQ-TREE for gene family tree inference. Default model is generally applicable, but may be specified by the user. Not used if running FastTree."
                },
                "outgroups": {
                    "type": "string",
                    "default": "none",
                    "description": "If provided, these taxa will be used to manually root the species tree inferred using Asteroid. This tree (with branch lengths inferred using SpeciesRax) will be used in GeneRax analyses. This should be a comma-separated string of sample/species IDs corresponding to the samplesheet. Example: \"Genus_species1,Genus_species2\""
                },
                "iqtree_fasttree_fallback": {
                    "type": "boolean",
                    "default": true,
                    "description": "When using IQ-TREE, fall back to FastTree for gene families that fail or time out.",
                    "fa_icon": "fas fa-redo"
                },
                "busco": {
                    "type": "boolean",
                    "default": false,
                    "description": "Run BUSCO completeness assessment on input proteomes.",
                    "fa_icon": "fas fa-check-circle"
                },
                "ref_species": {
                    "type": "string",
                    "default": "Homo-sapiens",
                    "description": "Reference species for distance comparisons. Set to 'none' for centroid-only analysis.",
                    "help_text": "When set to a species name, both centroid-based and reference-based analyses are produced. When set to 'none', only universal centroid-based analyses are produced for all gene families. Must match a species name from the input samplesheet (format: Genus-species). Underscores and spaces are auto-converted to hyphens.",
                    "fa_icon": "fas fa-bullseye"
                },
                "preprocess": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable optional proteome preprocessing (TransDecoder, isoform filtering, quality cleanup).",
                    "help_text": "When enabled, NovelTree runs preprocessing steps before the main pipeline. Per-species flags in the samplesheet (transdecoder, isoform, reference columns) control which steps run for each species.",
                    "fa_icon": "fas fa-filter"
                },
                "min_protein_length": {
                    "type": "integer",
                    "default": 50,
                    "description": "Minimum protein sequence length (aa) to retain during preprocessing.",
                    "help_text": "Proteins shorter than this length are removed during the preprocessing step. Only applies when --preprocess is enabled.",
                    "fa_icon": "fas fa-ruler"
                },
                "mafft_mode": {
                    "type": "string",
                    "default": "einsi",
                    "description": "MAFFT algorithm for tier-1 alignment. E-INS-i for sequences with conserved motifs, L-INS-i for globally alignable sequences.",
                    "enum": ["einsi", "linsi"]
                },
                "align_tier1_max": {
                    "type": "integer",
                    "default": 200,
                    "description": "Maximum sequences for tier-1 MAFFT alignment. Families above this use WITCH."
                },
                "align_tier2_max": {
                    "type": "integer",
                    "default": 3000,
                    "description": "Maximum sequences for tier-2 WITCH alignment. Families above this use FAMSA."
                },
                "test_run": {
                    "type": "boolean",
                    "default": false,
                    "description": "Restrict to gene families containing ALL species (fast smoke test)."
                },
                "test_run_mcl": {
                    "type": "boolean",
                    "default": false,
                    "description": "Test multiple MCL inflation values on species with UniProt accessions."
                },
                "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})$"
                }
            }
        },
        "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": 192,
                    "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$",
                    "hidden": true,
                    "help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
                },
                "max_time": {
                    "type": "string",
                    "description": "Maximum amount of time that can be requested for any single job.",
                    "default": "240.h",
                    "fa_icon": "far fa-clock",
                    "pattern": "^(\\d+\\.?\\s*(s|m|h|day)\\s*)+$",
                    "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'`"
                }
            },
            "required": [
                "max_cpus",
                "max_memory"
            ]
        },
        "aws_batch_options": {
            "title": "AWS Batch options",
            "type": "object",
            "fa_icon": "fab fa-aws",
            "description": "Parameters required for running on AWS Batch.",
            "help_text": "These parameters are required when using the 'awsbatch' profile. The pipeline must be run with work directory and output directory on S3.",
            "properties": {
                "awsqueue": {
                    "type": "string",
                    "description": "The AWS Batch job queue to submit jobs to.",
                    "fa_icon": "fas fa-list",
                    "help_text": "Specify the name of your AWS Batch job queue. Required when using -profile awsbatch."
                },
                "awsregion": {
                    "type": "string",
                    "description": "The AWS region where your Batch compute environment is located.",
                    "fa_icon": "fas fa-globe",
                    "help_text": "Specify your AWS region (e.g., 'us-east-1', 'us-west-2'). Required when using -profile awsbatch."
                }
            }
        },
        "zoogle_options": {
            "title": "Zoogle analysis options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Options for the Zoogle physicochemical protein distance analysis mode.",
            "properties": {
                "zoogle": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable Zoogle physicochemical protein distance analysis.",
                    "fa_icon": "fas fa-flask"
                },
                "simplified": {
                    "type": "boolean",
                    "default": true,
                    "description": "Run in simplified mode (skip BUSCO, use single MCL inflation value).",
                    "fa_icon": "fas fa-compress"
                },
                "generax_per_family": {
                    "type": "boolean",
                    "default": false,
                    "description": "Run GeneRax per gene family instead of globally.",
                    "fa_icon": "fas fa-sitemap"
                },
                "reference_time_tree": {
                    "type": "string",
                    "default": "none",
                    "description": "Path to a pre-existing time-calibrated reference tree. If 'none', one will be built from TimeTree.org divergence times.",
                    "fa_icon": "fas fa-tree"
                },
                "ncbi_email": {
                    "type": "string",
                    "default": "none",
                    "description": "Email address for NCBI Entrez API queries (used when building reference chronogram from TimeTree.org).",
                    "fa_icon": "fas fa-at"
                },
                "time_calibration_method": {
                    "type": "string",
                    "default": "treePL",
                    "description": "Method for time-calibrating the species tree. Options: treePL (penalized likelihood) or PATHd8. Gene family trees always use treePL with fixed smoothing.",
                    "enum": ["treePL", "PATHd8"]
                },
                "age_bracket": {
                    "type": "number",
                    "default": 0.20,
                    "description": "Proportional bracket applied to calibration ages for both species tree and gene family tree dating (e.g., 0.20 = +/- 20%).",
                    "fa_icon": "fas fa-arrows-alt-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
                },
                "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})$",
                    "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
                    "hidden": true
                },
                "plaintext_email": {
                    "type": "boolean",
                    "description": "Send plain-text email instead of HTML.",
                    "fa_icon": "fas fa-remove-format",
                    "hidden": true
                },
                "monochrome_logs": {
                    "type": "boolean",
                    "description": "Do not use coloured log outputs.",
                    "fa_icon": "fas fa-palette",
                    "hidden": true
                },
                "hook_url": {
                    "type": "string",
                    "description": "Incoming hook URL for messaging service",
                    "fa_icon": "fas fa-people-group",
                    "help_text": "Incoming hook URL for messaging service. Currently, only MS Teams is supported.",
                    "hidden": true
                },
                "tracedir": {
                    "type": "string",
                    "description": "Directory to keep pipeline Nextflow logs and reports.",
                    "default": "${params.outdir}/pipeline_info",
                    "fa_icon": "fas fa-cogs",
                    "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
                },
                "show_hidden_params": {
                    "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."
                },
                "enable_conda": {
                    "type": "boolean",
                    "description": "Run this workflow with Conda. You can also use '-profile conda' instead of providing this parameter.",
                    "hidden": true,
                    "fa_icon": "fas fa-bacon"
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/definitions/input_output_options"
        },
        {
            "$ref": "#/definitions/max_job_request_options"
        },
        {
            "$ref": "#/definitions/aws_batch_options"
        },
        {
            "$ref": "#/definitions/zoogle_options"
        },
        {
            "$ref": "#/definitions/generic_options"
        }
    ],
    "properties": {
        "custom_config_version": {
            "type": "string",
            "default": "master"
        },
        "custom_config_base": {
            "type": "string",
            "default": "https://raw.githubusercontent.com/nf-core/configs/master"
        },
        "config_profile_description": {
            "type": "string",
            "default": "None"
        },
        "config_profile_contact": {
            "type": "string",
            "default": "None"
        },
        "config_profile_url": {
            "type": "string",
            "default": "None"
        },
        "config_profile_name": {
            "type": "string",
            "default": "None"
        }
    }
}