nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/dhslab/dragenflow/master/nextflow_schema.json",
    "title": "dhslab/dragenflow pipeline parameters",
    "description": "Nextflow pipeline for running DRAGEN alignment and variant calling workflows (germline, somatic, RNA-seq, methylation).",
    "type": "object",
    "allOf": [
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/workflow_options"
        },
        {
            "$ref": "#/$defs/dragen_alignment_options"
        },
        {
            "$ref": "#/$defs/dragen_variant_calling_options"
        },
        {
            "$ref": "#/$defs/dragen_umi_options"
        },
        {
            "$ref": "#/$defs/dragen_rna_options"
        },
        {
            "$ref": "#/$defs/annotation_options"
        },
        {
            "$ref": "#/$defs/compute_options"
        },
        {
            "$ref": "#/$defs/reference_genome_options"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/max_job_request_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ],
    "$defs": {
        "input_output_options": {
            "title": "Input/output options",
            "type": "object",
            "fa_icon": "fas fa-terminal",
            "description": "Define where the pipeline should find input data and save output data.",
            "required": ["outdir"],
            "properties": {
                "input": {
                    "type": "string",
                    "format": "file-path",
                    "mimetype": "text/csv",
                    "description": "Path to samplesheet CSV file. Supports reads (read1/read2), BAM/CRAM, fastq_list, demux_path, or samplemap columns. See README for format details.",
                    "fa_icon": "fas fa-file-csv"
                },
                "outdir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Output directory where results will be saved. Use absolute paths for cloud infrastructure.",
                    "fa_icon": "fas fa-folder-open"
                },
                "demux_outdir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Directory containing demultiplexed FASTQ output (with Reports/fastq_list.csv). Used when providing pre-demuxed data.",
                    "fa_icon": "fas fa-folder"
                },
                "tracedir": {
                    "type": "string",
                    "description": "Directory for pipeline execution trace files.",
                    "default": "${params.outdir}/pipeline_info",
                    "hidden": true,
                    "fa_icon": "fas fa-cogs"
                },
                "email": {
                    "type": "string",
                    "description": "Email address for pipeline completion summary.",
                    "fa_icon": "fas fa-envelope",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
                },
                "multiqc_title": {
                    "type": "string",
                    "description": "MultiQC report title. Used as page header and filename prefix.",
                    "fa_icon": "fas fa-file-signature"
                }
            }
        },
        "workflow_options": {
            "title": "Workflow options",
            "type": "object",
            "fa_icon": "fas fa-project-diagram",
            "description": "Select the analysis mode and control core pipeline behavior.",
            "required": ["workflow"],
            "properties": {
                "workflow": {
                    "type": "string",
                    "description": "Analysis workflow mode. Typically set by the analysis profile rather than on the command line.",
                    "enum": ["align", "germline", "somatic", "tumor", "rna", "bsseq","download_nirvana", "build_hash"],
                    "fa_icon": "fas fa-sitemap"
                },
                "run_dragen": {
                    "type": "boolean",
                    "default": true,
                    "description": "Execute the DRAGEN alignment step. Set to false to skip DRAGEN (e.g., for testing samplesheet parsing).",
                    "fa_icon": "fas fa-play"
                },
                "extra_dragen_args": {
                    "type": "string",
                    "description": "Additional raw arguments appended to the DRAGEN command line. Useful for one-off flags not covered by parameters.",
                    "fa_icon": "fas fa-terminal"
                }
            }
        },
        "dragen_alignment_options": {
            "title": "DRAGEN alignment options",
            "type": "object",
            "fa_icon": "fas fa-align-left",
            "description": "Options controlling DRAGEN alignment behavior and reference files.",
            "properties": {
                "refdir": {
                    "type": "string",
                    "format": "directory-path",
                    "default": "/storage2/fs1/dspencer/Active/shared/refdata/hg38/dragen_hg38v4.3.6",
                    "description": "Path to the DRAGEN hash-table reference directory.",
                    "fa_icon": "fas fa-database"
                },
                "methylation_refdir": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Path to the DRAGEN bisulfite/methylation hash-table reference directory. Set automatically by the bsseq profile.",
                    "fa_icon": "fas fa-database"
                },
                "fasta": {
                    "type": "string",
                    "format": "file-path",
                    "default": "/storage2/fs1/dspencer/Active/shared/refdata/hg38/sequence/hg38_mgi_patch.fa",
                    "description": "Path to the genome FASTA reference. Used for CRAM decoding and downstream annotation.",
                    "fa_icon": "fas fa-file"
                },
                "cram_reference": {
                    "type": "string",
                    "format": "file-path",
                    "default": "/storage2/fs1/dspencer/Active/shared/refdata/hg38/sequence/hg38_mgi_patch.fa",
                    "description": "FASTA reference used when reading input CRAM files.",
                    "fa_icon": "fas fa-file"
                },
                "dbsnp": {
                    "type": "string",
                    "format": "file-path",
                    "default": "/storage2/fs1/dspencer/Active/shared/refdata/hg38/dragenfiles/dbsnp.vcf.gz",
                    "description": "dbSNP VCF for variant annotation. Used when Nirvana annotation is disabled.",
                    "fa_icon": "fas fa-file-alt"
                },
                "intermediate_dir": {
                    "type": "string",
                    "default": "/staging/intermediate-results-dir",
                    "description": "DRAGEN intermediate results directory. Paths beginning with /staging are treated as on-DRAGEN-hardware paths.",
                    "fa_icon": "fas fa-folder"
                },
                "adapter1": {
                    "type": "string",
                    "format": "file-path",
                    "description": "FASTA file of adapter sequences for read 1. Defaults to bundled DRAGEN adapter sequences.",
                    "fa_icon": "fas fa-file"
                },
                "adapter2": {
                    "type": "string",
                    "format": "file-path",
                    "description": "FASTA file of adapter sequences for read 2. Defaults to bundled DRAGEN adapter sequences.",
                    "fa_icon": "fas fa-file"
                },
                "alignment_file_format": {
                    "type": "string",
                    "default": "CRAM",
                    "description": "Output alignment file format.",
                    "enum": ["CRAM", "BAM"],
                    "fa_icon": "fas fa-file-archive"
                },
                "mark_duplicates": {
                    "type": "boolean",
                    "default": true,
                    "description": "Enable DRAGEN duplicate marking. Set to false when using UMI-based deduplication.",
                    "fa_icon": "fas fa-clone"
                },
                "pangenome_reference": {
                    "type": "boolean",
                    "default": false,
                    "description": "Validate pangenome reference. Enable when using a pangenome DRAGEN reference.",
                    "fa_icon": "fas fa-dna",
                    "hidden": true
                },
                "target_bedfile": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Target BED file for exome or panel sequencing. Enables exome-mode SV and CNV calling and restricts variant calling to targeted regions.",
                    "fa_icon": "fas fa-crosshairs"
                }
            }
        },
        "dragen_variant_calling_options": {
            "title": "DRAGEN variant calling options",
            "type": "object",
            "fa_icon": "fas fa-search",
            "description": "Options for SNV, SV, and CNV variant calling.",
            "properties": {
                "variant_caller": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable DRAGEN small variant (SNV/indel) caller.",
                    "fa_icon": "fas fa-dna"
                },
                "sv_caller": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable DRAGEN structural variant (SV) caller.",
                    "fa_icon": "fas fa-exchange-alt"
                },
                "cnv_caller": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable DRAGEN copy number variant (CNV) caller.",
                    "fa_icon": "fas fa-chart-bar"
                },
                "hotspot_vcf": {
                    "type": "string",
                    "format": "file-path",
                    "description": "VCF of somatic hotspot positions passed to --vc-somatic-hotspots.",
                    "fa_icon": "fas fa-fire"
                },
                "hotspot_bed": {
                    "type": "string",
                    "format": "file-path",
                    "description": "BED file used to generate a hotspot VCF on the fly (alternative to --hotspot_vcf).",
                    "fa_icon": "fas fa-fire"
                },
                "snv_noisefile": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Systematic noise BED file for SNV filtering (--vc-systematic-noise).",
                    "fa_icon": "fas fa-filter"
                },
                "sv_noisefile": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Systematic noise BEDPE file for SV filtering (--sv-systematic-noise).",
                    "fa_icon": "fas fa-filter"
                },
                "cnv_population_vcf": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Population B-allele frequency VCF for CNV calling (--cnv-population-b-allele-vcf). Required for tumor-only CNV calling.",
                    "fa_icon": "fas fa-file-alt"
                },
                "dragen_tandem_dup_hotspots": {
                    "type": "string",
                    "format": "file-path",
                    "description": "BED file of somatic insertion/tandem duplication hotspot regions (--sv-somatic-ins-tandup-hotspot-regions-bed).",
                    "fa_icon": "fas fa-fire"
                },
                "dragen_cnv_filter_length": {
                    "type": "integer",
                    "description": "Minimum CNV length (bp) to report (--cnv-filter-length). Recommended: 500000 for tumor-only WGS.",
                    "fa_icon": "fas fa-ruler"
                },
                "dragen_cnv_merge_distance": {
                    "type": "integer",
                    "description": "Maximum distance (bp) between adjacent CNV segments to merge (--cnv-merge-distance). Recommended: 2000000 for tumor-only WGS.",
                    "fa_icon": "fas fa-compress-arrows-alt"
                },
                "sv_annotation_distance": {
                    "type": "integer",
                    "description": "Maximum distance (bp) for SV breakend annotation matching. Used in downstream SV annotation.",
                    "fa_icon": "fas fa-ruler"
                },
                "max_filter_sv_length": {
                    "type": "integer",
                    "description": "Maximum SV length (bp) to retain in downstream annotation. SVs larger than this are filtered.",
                    "fa_icon": "fas fa-ruler"
                },
                "dux4caller": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable DRAGEN DUX4 rearrangement caller (--enable-dux4-caller). For hematologic malignancies with potential DUX4-IGH fusions.",
                    "fa_icon": "fas fa-search-plus"
                },
                "solid_tumor": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable solid tumor UMI variant calling mode (--vc-enable-umi-solid).",
                    "fa_icon": "fas fa-circle"
                },
                "liquid_tumor": {
                    "type": "boolean",
                    "default": false,
                    "description": "Enable liquid tumor UMI variant calling mode (--vc-enable-umi-liquid). For hematologic malignancies.",
                    "fa_icon": "fas fa-tint"
                }
            }
        },
        "dragen_umi_options": {
            "title": "DRAGEN UMI options",
            "type": "object",
            "fa_icon": "fas fa-barcode",
            "description": "Options for UMI-based library processing and deduplication.",
            "properties": {
                "umi": {
                    "type": ["boolean", "string"],
                    "default": false,
                    "description": "UMI library type passed to --umi-library-type. Set to 'random-simplex' for IDT UDI-UMI libraries (or use the idtumi profile). When set, duplicate marking is typically disabled and adapters are trimmed with fastp before DRAGEN. Leave as false to disable.",
                    "fa_icon": "fas fa-barcode"
                },
                "illumina_conversion": {
                    "type": "boolean",
                    "description": "Treat reads as Illumina 5-base (methylation-aware) UMI data, enabling the same DRAGEN UMI arguments as --umi without requiring a library type string. Set automatically by the fivebase profile.",
                    "fa_icon": "fas fa-barcode"
                },
                "readfamilysize": {
                    "type": "integer",
                    "default": 3,
                    "description": "Minimum number of reads in a UMI family to support a variant (--umi-min-supporting-reads).",
                    "fa_icon": "fas fa-layer-group"
                }
            }
        },
        "dragen_rna_options": {
            "title": "DRAGEN RNA-seq options",
            "type": "object",
            "fa_icon": "fas fa-stream",
            "description": "Options specific to the RNA-seq workflow (workflow=rna).",
            "properties": {
                "annotation_gtf": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Gene annotation GTF file for RNA-seq alignment and quantification (-a). Must be gzip-compressed and sorted.",
                    "fa_icon": "fas fa-file-alt"
                },
                "transcript_table": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Transcript-to-gene mapping table used to annotate DRAGEN quantification output with gene names.",
                    "fa_icon": "fas fa-table"
                },
                "downsample_rna": {
                    "type": "integer",
                    "description": "Downsample RNA-seq reads to this many reads (--enable-down-sampler / --down-sampler-reads). Useful for large samples.",
                    "fa_icon": "fas fa-compress"
                }
            }
        },
        "annotation_options": {
            "title": "Variant annotation options",
            "type": "object",
            "fa_icon": "fas fa-tags",
            "description": "Options for VEP and Nirvana variant annotation.",
            "properties": {
                "vepcache": {
                    "type": "string",
                    "format": "directory-path",
                    "default": "/storage2/fs1/dspencer/Active/shared/refdata/hg38/VEP113_cache",
                    "description": "Path to the VEP cache directory used for SNV, SV, and CNV annotation.",
                    "fa_icon": "fas fa-database"
                },
                "cytobands": {
                    "type": "string",
                    "format": "file-path",
                    "description": "Cytogenetic band BED file (gzip-compressed) for SV and CNV annotation. Defaults to bundled hg38 cytobands.",
                    "fa_icon": "fas fa-file"
                },
                "use_nirvana": {
                    "type": "boolean",
                    "default": true,
                    "description": "Use Nirvana for in-DRAGEN variant annotation instead of dbSNP-only annotation. Requires --nirvana_path.",
                    "fa_icon": "fas fa-tags"
                },
                "nirvana_path": {
                    "type": "string",
                    "format": "directory-path",
                    "default": "/storage2/fs1/dspencer/Active/shared/refdata/hg38/dragenfiles/nirvana_annotation_data_323",
                    "description": "Path to the Nirvana annotation data directory (--variant-annotation-data).",
                    "fa_icon": "fas fa-database"
                },
                "nirvana_assembly": {
                    "type": "string",
                    "default": "GRCh38",
                    "description": "Genome assembly name for Nirvana (--variant-annotation-assembly).",
                    "fa_icon": "fas fa-dna",
                    "hidden": true
                }
            }
        },
        "compute_options": {
            "title": "Compute cluster options",
            "type": "object",
            "fa_icon": "fas fa-server",
            "description": "Options for WashU RIS compute cluster job submission.",
            "properties": {
                "user_group": {
                    "type": "string",
                    "default": "compute-dspencer",
                    "description": "LSF user group for compute1 job submission (-G flag).",
                    "fa_icon": "fas fa-users"
                },
                "queue": {
                    "type": "string",
                    "default": "general",
                    "description": "LSF queue name for compute1 job submission (-q flag).",
                    "fa_icon": "fas fa-list"
                },
                "job_group_name": {
                    "type": "string",
                    "description": "LSF job group name for compute1 job scheduling (-g flag). e.g. /dspencer/nextflow",
                    "fa_icon": "fas fa-layer-group"
                },
                "slurm_partition": {
                    "type": "string",
                    "default": "condo-dspencer",
                    "description": "SLURM partition for compute2 job submission.",
                    "fa_icon": "fas fa-server"
                },
                "slurm_account": {
                    "type": "string",
                    "default": "compute2-dspencer",
                    "description": "SLURM account for compute2 job submission.",
                    "fa_icon": "fas fa-server"
                },
                "apptainer_cache": {
                    "type": "string",
                    "format": "directory-path",
                    "description": "Directory for caching Singularity images on compute2.",
                    "fa_icon": "fas fa-box"
                },
                "local_dragen_container": {
                    "type": "string",
                    "default": "apldx/oracle8-dragen-4.3.6",
                    "description": "Docker image name for on-premise DRAGEN jobs.",
                    "fa_icon": "fab fa-docker"
                }
            }
        },
        "reference_genome_options": {
            "title": "Reference genome options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "iGenomes reference options (not used by default).",
            "properties": {
                "genome": {
                    "type": "string",
                    "description": "iGenomes reference name. Not used by this pipeline (igenomes_ignore=true by default).",
                    "fa_icon": "fas fa-book",
                    "hidden": true
                },
                "igenomes_base": {
                    "type": "string",
                    "default": "s3://ngi-igenomes/igenomes",
                    "description": "Base URL for iGenomes reference files.",
                    "fa_icon": "fas fa-cloud-download-alt",
                    "hidden": true
                },
                "igenomes_ignore": {
                    "type": "boolean",
                    "default": true,
                    "description": "Do not load iGenomes reference config.",
                    "fa_icon": "fas fa-ban",
                    "hidden": true
                }
            }
        },
        "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,
                    "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"
                }
            }
        },
        "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.",
            "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
                },
                "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
                },
                "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*)+$",
                    "hidden": true
                }
            }
        },
        "generic_options": {
            "title": "Generic options",
            "type": "object",
            "fa_icon": "fas fa-file-import",
            "description": "Less common options for the pipeline, typically set in a config file.",
            "properties": {
                "help": {
                    "type": "boolean",
                    "description": "Display help text.",
                    "fa_icon": "fas fa-question-circle",
                    "hidden": true
                },
                "version": {
                    "type": "boolean",
                    "description": "Display version and exit.",
                    "fa_icon": "fas fa-question-circle",
                    "hidden": true
                },
                "publish_dir_mode": {
                    "type": "string",
                    "default": "copy",
                    "description": "Method used to save pipeline results to output directory.",
                    "fa_icon": "fas fa-copy",
                    "enum": ["symlink", "rellink", "link", "copy", "copyNoFollow", "move"],
                    "hidden": true
                },
                "email_on_fail": {
                    "type": "string",
                    "description": "Email address for completion summary, only when pipeline fails.",
                    "fa_icon": "fas fa-exclamation-triangle",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$",
                    "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 MS Teams or Slack notifications.",
                    "fa_icon": "fas fa-people-group",
                    "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 methods description.",
                    "fa_icon": "fas fa-cog",
                    "hidden": true
                },
                "validate_params": {
                    "type": "boolean",
                    "description": "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, including hidden parameters.",
                    "hidden": true
                },
                "validationFailUnrecognisedParams": {
                    "type": "boolean",
                    "fa_icon": "far fa-check-circle",
                    "description": "Fail validation if an unrecognised parameter is found.",
                    "hidden": true
                },
                "validationLenientMode": {
                    "type": "boolean",
                    "fa_icon": "far fa-check-circle",
                    "description": "Allow string values parseable as numbers or booleans during validation.",
                    "hidden": true
                },
                "validationSchemaIgnoreParams": {
                    "type": "string",
                    "description": "Comma-separated list of parameter names to ignore during schema validation.",
                    "default": "genomes,igenomes_base",
                    "hidden": true
                }
            }
        }
    }
}