nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/nf-core/multiplesequencealign/master/nextflow_schema.json",
    "title": "nf-core/multiplesequencealign pipeline parameters",
    "description": "Pipeline to run and benchmark multiple sequence alignment tools.",
    "type": "object",
    "$defs": {
        "input_output_options": {
            "title": "Basic Input/output options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define where the pipeline should find input data and save output data.",
            "required": ["outdir"],
            "properties": {
                "input": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "schema": "assets/schema_input.json",
                    "pattern": "^\\S+\\.(csv|tsv|yaml|yml|json)$",
                    "description": "Path to the samplesheet file containing information about datasets to be aligned and evaluated (samplesheet).",
                    "help_text": "You will need to create a file with information about the datasets before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with maximum 5 columns, and a header row. See [usage docs](https://nf-co.re/multiplesequencealign/usage#samplesheet-input).",
                    "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"
                },
                "seqs": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "pattern": "\\S+\\.f(n|ast)?a$",
                    "description": "Path to the input fasta file.",
                    "help_text": "Path to the input fasta file, it can be used in alternative to using the input samplesheet if you only have one dataset.",
                    "fa_icon": "fas fa-folder-open"
                },
                "pdbs_dir": {
                    "type": "string",
                    "format": "path",
                    "exists": true,
                    "description": "Path to a folder containing all the optional data files to be used (e.g. structures).",
                    "help_text": "This is a folder with all the optional data files to be used in the pipeline. It can be used in alternative to the samplesheet if you only have one dataset.",
                    "fa_icon": "fas fa-folder-open"
                },
                "templates_suffix": {
                    "type": "string",
                    "default": ".pdb",
                    "description": "Suffix of the files given in the optional_data directory.",
                    "help_text": "To provide additional data (e.g. protein structures), you must provide the path of a directory where thay are stored. Here, you can provide the suffix of the files in the given directory (e.g. pdb for pdb files).",
                    "fa_icon": "fas fa-file-signature"
                },
                "email": {
                    "type": "string",
                    "description": "Email address for completion summary.",
                    "fa_icon": "fas fa-envelope",
                    "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
                },
                "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"
                }
            }
        },
        "input_tools_options": {
            "title": "Tools input options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define which tools the pipeline should deploy.",
            "oneOf": [{ "required": ["tools"] }, { "required": ["aligner"] }],
            "properties": {
                "tools": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "schema": "assets/schema_tools.json",
                    "pattern": "^\\S+\\.(csv|tsv|yaml|yml|json)$",
                    "description": "Path to the file containing information about the tools to be deployed (toolsheet).",
                    "help_text": "You will need to create a file with information about the tools to be used before running the pipeline. Use this parameter to specify its location. It has to be a file with 4 columns, and a header row. See [usage docs](https://nf-co.re/msa/usage#samplesheet-input).",
                    "fa_icon": "fas fa-file-csv"
                },
                "tree": {
                    "type": "string",
                    "description": "Tool to use for tree building.",
                    "enum": ["FAMSA", "CLUSTALO", "MAFFT"],
                    "fa_icon": "fas fa-terminal",
                    "help_text": "The tool to be used for tree building. If not set, the tree will not be built. This parameter is meant to be used in alternative to the toolsheet, in case you want to deploy only one tool."
                },
                "args_tree": {
                    "type": "string",
                    "description": "Extra arguments for the tree building tool.",
                    "fa_icon": "fas fa-terminal",
                    "help_text": "Extra arguments to be passed to the tree building tool. This parameter is meant to be used in alternative to the toolsheet, in case you want to deploy only one tool."
                },
                "aligner": {
                    "type": "string",
                    "description": "The aligner to be used.",
                    "enum": [
                        "CLUSTALO",
                        "FAMSA",
                        "KALIGN",
                        "LEARNMSA",
                        "MAFFT",
                        "MAGUS",
                        "MUSCLE5",
                        "TCOFFEE",
                        "REGRESSIVE",
                        "UPP",
                        "3DCOFFEE",
                        "MTMALIGN",
                        "FOLDMASON"
                    ],
                    "fa_icon": "fas fa-terminal",
                    "help_text": "The aligner to be used. This parameter is meant to be used in alternative to the toolsheet, in case you want to deploy only one tool."
                },
                "args_aligner": {
                    "type": "string",
                    "description": "Extra arguments for the aligner tool.",
                    "fa_icon": "fas fa-terminal",
                    "help_text": "Extra arguments to be passed to the aligner tool. This parameter is meant to be used in alternative to the toolsheet, in case you want to deploy only one tool."
                }
            }
        },
        "global_options": {
            "title": "Global options",
            "type": "object",
            "description": "Define wether and how to run compression",
            "default": "",
            "properties": {
                "use_gpu": {
                    "type": "boolean",
                    "description": "Run on CPUs (default) or GPUs",
                    "fa_icon": "fas fa-microchip"
                },
                "skip_compression": {
                    "type": "boolean",
                    "description": "Produce uncompressed alignment files"
                },
                "skip_preprocessing": {
                    "type": "boolean",
                    "description": "Skip the preprocessing step for the input files.",
                    "fa_icon": "fas fa-fast-forward",
                    "help_text": "Skip the preprocessing step and use the files directly. Currently the preprocessing only features the structures where the header is cleaned."
                },
                "skip_validation": {
                    "type": "boolean",
                    "description": "Skip the validation of the input files.",
                    "fa_icon": "fas fa-fast-forward",
                    "help_text": "Skip the validation of the input files. This is not recommended, as it can lead to errors in the pipeline."
                },
                "skip_pdbconversion": {
                    "type": "boolean",
                    "description": "Skip the conversion of pdb files to fasta.",
                    "fa_icon": "fas fa-fast-forward",
                    "help_text": "Skip the conversion of pdb files to fasta. PDBs are converted if they are the only input file (no fasta) and are wished to be used either to run sequence-based aligners or sequence-based stats of the input files."
                }
            }
        },
        "align_options": {
            "title": "Align options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define extra alignment options.",
            "properties": {
                "build_consensus": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Build consensus alignment with M-COFFEE."
                }
            }
        },
        "stats_options": {
            "title": "Stats options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define wether to run stats.",
            "properties": {
                "skip_stats": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Skip all of the statistics computation on the fasta file."
                },
                "calc_sim": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Calculate the percentage similarity across the sequences in the input files."
                },
                "calc_seq_stats": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Calculate general statistics on input files."
                },
                "extract_plddt": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Extract plddt from structure files. Only works if the files have been generated by AF2."
                }
            }
        },
        "eval_options": {
            "title": "Eval options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define wether to run stats.",
            "properties": {
                "skip_eval": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Skip all of the evaluations computation on the msa."
                },
                "calc_sp": {
                    "type": "boolean",
                    "default": "true",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Calculate the Sum of Pairs of alignment."
                },
                "calc_tc": {
                    "type": "boolean",
                    "default": true,
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Calculate the Total Column Score of alignment."
                },
                "calc_irmsd": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Calculate the iRMSD of alignment."
                },
                "calc_tcs": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Calculate the Transitive Consistency Score (TCS) of alignment."
                },
                "calc_gaps": {
                    "type": "boolean",
                    "default": true,
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Extract total number of gaps and average number of gaps of the alignment."
                }
            }
        },
        "reports_options": {
            "title": "Reports options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define wether to run stats.",
            "properties": {
                "skip_multiqc": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Skip the multiqc report generation."
                },
                "skip_shiny": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Skip the shiny report generation."
                },
                "shiny_app": {
                    "type": "string",
                    "format": "directory-path",
                    "exists": true,
                    "fa_icon": "fas fa-folder-open",
                    "description": "Folder containing the main shiny app."
                },
                "skip_visualisation": {
                    "type": "boolean",
                    "fa_icon": "fas fa-fast-forward",
                    "description": "Skip the visualization generation."
                }
            }
        },
        "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
                },
                "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
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/input_tools_options"
        },
        {
            "$ref": "#/$defs/global_options"
        },
        {
            "$ref": "#/$defs/align_options"
        },
        {
            "$ref": "#/$defs/stats_options"
        },
        {
            "$ref": "#/$defs/eval_options"
        },
        {
            "$ref": "#/$defs/reports_options"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ]
}