nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/IntGenomicsLab/lrsomatic/main/nextflow_schema.json",
    "title": "IntGenomicsLab/lrsomatic pipeline parameters",
    "description": "Workflow for somatic variant calling of long read data",
    "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 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 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"
                },
                "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"
                }
            }
        },
        "pon_options": {
            "title": "Panel of Normals (PON) options",
            "type": "object",
            "description": "Options for panel of normals filtering",
            "default": "",
            "properties": {
                "clairsto_pon_vcfs": {
                    "type": "string",
                    "description": "Path to panel of normals VCF file(s) for ClairS-TO somatic variant filtering"
                },
                "clairsto_pon_flags": {
                    "type": "string",
                    "description": "Population allele matching flags for ClairS-TO PON VCFs (one per VCF, comma-separated)"
                },
                "deepsomatic_pon_vcfs": {
                    "type": "string",
                    "description": "Path to panel of normals VCF file(s) for DeepSomatic --population_vcfs. If not set, uses container-bundled defaults in tumor-only mode, or no PON in paired mode"
                }
            }
        },
        "small_variant_calling_options": {
            "title": "options for small variant calling",
            "type": "object",
            "properties": {
                "germline_var_keep": {
                    "type": "string",
                    "description": "Comma-separated list of germline variant callers to use. Valid values: deepvariant, clair. Example: 'deepvariant,clair'",
                    "default": "clair"
                },
                "somatic_var_keep": {
                    "type": "string",
                    "description": "Comma-separated list of somatic variant callers to use. Valid values: deepsomatic, clair. Example: 'deepsomatic,clair'",
                    "default": "clair"
                },
                "germline_var_combine": {
                    "type": "string",
                    "description": "When two germline callers are used, specifies how to combine them. 'consensus' keeps only variants called by both callers; 'all' keeps all variants from both callers.",
                    "default": "all",
                    "enum": ["consensus", "all"]
                },
                "somatic_var_combine": {
                    "type": "string",
                    "description": "When two somatic callers are used, specifies how to combine them. 'consensus' keeps only variants called by both callers; 'all' keeps all variants from both callers.",
                    "default": "all",
                    "enum": ["consensus", "all"]
                },
                "prioritize_caller_germline": {
                    "type": "string",
                    "description": "When both germline callers are used, specifies which caller's format to use for variants called by both. Must be [deepvariant, clair].",
                    "default": "clair",
                    "enum": ["deepvariant", "clair"]
                },
                "prioritize_caller_somatic": {
                    "type": "string",
                    "description": "When both somatic callers are used, specifies which caller's format to use for variants called by both. Must be [deepsomatic, clair].",
                    "default": "clair",
                    "enum": ["deepsomatic", "clair"]
                },
                "generate_gvcf": {
                    "type": "boolean"
                }
            }
        },
        "longphase_options": {
            "title": "Longphase options",
            "type": "object",
            "description": "Options for Longphase phasing of small variants",
            "properties": {
                "longphase_tag_supplementary": {
                    "type": "boolean",
                    "description": "Whether to include supplementary alignments in Longphase haplotype tagging.",
                    "default": false
                }
            }
        },
        "reference_genome_options": {
            "title": "Reference genome options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Reference genome related files and options required for the workflow.",
            "properties": {
                "genome": {
                    "type": "string",
                    "description": "Name of iGenomes reference.",
                    "fa_icon": "fas fa-book",
                    "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details.",
                    "enum": ["GRCh38", "CHM13"]
                },
                "igenomes_ignore": {
                    "type": "boolean",
                    "description": "Do not load the iGenomes reference config.",
                    "fa_icon": "fas fa-ban",
                    "hidden": true,
                    "help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
                },
                "igenomes_base": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "The base path to the igenomes reference files",
                    "fa_icon": "fas fa-ban",
                    "hidden": true,
                    "default": "s3://ngi-igenomes/igenomes/"
                }
            }
        },
        "minimap2_options": {
            "title": "minimap2 options",
            "type": "object",
            "description": "",
            "default": "",
            "properties": {
                "minimap2_ont_model": {
                    "type": "string",
                    "description": "Minimap ont model to use"
                },
                "minimap2_pb_model": {
                    "type": "string",
                    "description": "Minimap Pacbio model to use"
                },
                "save_secondary_alignment": {
                    "type": "boolean",
                    "default": true,
                    "description": "Whether to save secondary alignments"
                }
            }
        },
        "fibertools_options": {
            "title": "Fibertools options",
            "type": "object",
            "description": "",
            "default": "",
            "properties": {
                "autocorrelation": {
                    "type": "string"
                }
            }
        },
        "vep_options": {
            "title": "VEP options",
            "type": "object",
            "description": "",
            "default": "",
            "properties": {
                "vep_cache": {
                    "type": "string",
                    "description": "Path to VEP cache directory.",
                    "fa_icon": "fas fa-database",
                    "help_text": "Path to the directory containing the VEP cache. If you are using an iGenomes reference, this will be set automatically. Otherwise, you will need to provide this path yourself.",
                    "default": "s3://annotation-cache/vep_cache/"
                },
                "vep_args": {
                    "type": "string",
                    "description": "Additional command line arguments to pass to VEP.",
                    "fa_icon": "fas fa-terminal",
                    "default": "--everything --filter_common --per_gene --total_length --offline --format vcf"
                },
                "vep_cache_version": {
                    "type": "integer",
                    "description": "Version of the VEP cache to use.",
                    "fa_icon": "fas fa-hashtag",
                    "help_text": "The version of the VEP cache to use. This should match the version of VEP being used.",
                    "default": 113
                },
                "download_vep_cache": {
                    "type": "boolean",
                    "description": "Download the VEP cache if not already present"
                },
                "vep_custom": {
                    "type": "string"
                },
                "vep_custom_tbi": {
                    "type": "string"
                }
            }
        },
        "severus_options": {
            "title": "Severus options",
            "type": "object",
            "description": "",
            "default": "",
            "properties": {
                "severus_minsupport": {
                    "type": "integer",
                    "default": 3
                }
            }
        },
        "ascat_parameters": {
            "title": "ASCAT parameters",
            "type": "object",
            "description": "ASCAT specific parameters",
            "default": "",
            "properties": {
                "ascat_ploidy": {
                    "type": "string",
                    "description": "Enforce a ploidy"
                },
                "ascat_purity": {
                    "type": "string",
                    "description": "Enforce a purity"
                },
                "ascat_penalty": {
                    "type": "integer",
                    "default": 150,
                    "description": "Penalty value"
                },
                "ascat_min_base_qual": {
                    "type": "integer",
                    "default": 20,
                    "description": "Minimum base quality for allelecounter"
                },
                "ascat_min_counts": {
                    "type": "integer",
                    "default": 10,
                    "description": "Minimum counts for allelecounter"
                },
                "ascat_min_map_qual": {
                    "type": "integer",
                    "default": 10,
                    "description": "Minimum mapping quality for allelecounter"
                },
                "ascat_longread_bins": {
                    "type": "integer",
                    "default": 2000,
                    "description": "Binsize for long-read"
                },
                "ascat_allelecounter_flags": {
                    "type": "string",
                    "default": "-f 0",
                    "description": "Additional allelecounter flags to use"
                },
                "ascat_chroms": {
                    "type": "string",
                    "description": "Chromosomes to process (automatically inferred, only use if you want to run on a subset)"
                },
                "ascat_gc_files": {
                    "type": "string",
                    "description": "Path to (zip) of GC files"
                },
                "ascat_rt_files": {
                    "type": "string",
                    "description": "path to (zip) of RT files"
                },
                "ascat_pdf_plots": {
                    "type": "boolean",
                    "description": "Boolean for ASCAT production of pdf plots (entered as string)"
                }
            }
        },
        "wakhan_options": {
            "title": "Wakhan options",
            "type": "object",
            "description": "",
            "default": "",
            "properties": {
                "wakhan_chroms": {
                    "type": "string"
                }
            }
        },
        "skip_options": {
            "title": "Skip options",
            "type": "object",
            "description": "Define whether to skip certain steps",
            "default": "",
            "properties": {
                "skip_qc": {
                    "type": "boolean",
                    "description": "Skips all QC steps"
                },
                "skip_cramino": {
                    "type": "boolean",
                    "description": "Skips Cramino"
                },
                "skip_mosdepth": {
                    "type": "boolean",
                    "description": "Skips Mosdepth"
                },
                "skip_bamstats": {
                    "type": "boolean",
                    "description": "Skips samtools flagstat, stats, and idxstats"
                },
                "skip_wakhan": {
                    "type": "boolean",
                    "description": "Skips wakhan"
                },
                "skip_fiber": {
                    "type": "boolean",
                    "description": "Skip Fibertools steps"
                },
                "skip_ascat": {
                    "type": "boolean",
                    "description": "Skip ASCAT"
                },
                "skip_m6a": {
                    "type": "boolean",
                    "description": "Skip m6a calling by Fibertools"
                },
                "skip_vep": {
                    "type": "boolean",
                    "description": "Skip VEP annotation"
                },
                "skip_normalfiber": {
                    "type": "boolean",
                    "description": "Skip Fibertools steps for the normal sample"
                },
                "skip_nanoplot": {
                    "type": "boolean",
                    "description": "Skip Nanoplot"
                },
                "skip_whatshapstats": {
                    "type": "boolean",
                    "description": "Skip WhatsHap stats"
                },
                "skip_modcall": {
                    "type": "boolean",
                    "description": "Skip modification calling"
                },
                "use_gpu": {
                    "type": "boolean",
                    "description": "Use GPU for supported tools (e.g. DeepVariant, DeepSomatic, Clair3)"
                }
            }
        },
        "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
                },
                "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
                },
                "help": {
                    "type": "boolean",
                    "description": "Display the help message."
                },
                "help_full": {
                    "type": "boolean",
                    "description": "Display the full detailed help message."
                },
                "show_hidden": {
                    "type": "boolean",
                    "description": "Display hidden parameters in the help message (only works when --help or --help_full are provided)."
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/pon_options"
        },
        {
            "$ref": "#/$defs/small_variant_calling_options"
        },
        {
            "$ref": "#/$defs/longphase_options"
        },
        {
            "$ref": "#/$defs/reference_genome_options"
        },
        {
            "$ref": "#/$defs/minimap2_options"
        },
        {
            "$ref": "#/$defs/fibertools_options"
        },
        {
            "$ref": "#/$defs/vep_options"
        },
        {
            "$ref": "#/$defs/severus_options"
        },
        {
            "$ref": "#/$defs/ascat_parameters"
        },
        {
            "$ref": "#/$defs/wakhan_options"
        },
        {
            "$ref": "#/$defs/skip_options"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ],
    "properties": {
        "skip_modkit": {
            "type": "boolean"
        }
    }
}