nextflow_schema.json

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/TRON/qualibam/master/nextflow_schema.json",
  "title": "TRON/qualibam pipeline parameters",
  "description": "A Nextflow pipeline built in nf-core style for comprehensive BAM file quality control, supporting both DNA and RNA sequencing input. Integrates RustQC, RNA-SeQC, Qualimap BAM QC, somalier, and alfred to provide multi-dimensional QC metrics covering read quality, alignment statistics, RNA-seq-specific measures, and sample identity verification.",
  "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"
        },
        "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"
        }
      }
    },
    "reference_genome_options": {
      "title": "Reference options",
      "type": "object",
      "fa_icon": "fas fa-dna",
      "description": "Reference annotation files required for the workflow.",
      "properties": {
        "gtf": {
          "type": "string",
          "format": "file-path",
          "exists": true,
          "mimetype": "text/plain",
          "pattern": "^\\S+\\.gtf(\\.gz)?$",
          "description": "Path to GTF annotation file.",
          "help_text": "This parameter is *mandatory* for RNA-seq QC with RustQC. It provides the gene annotation used for biotype quantification, featureCounts and RSeQC metrics.",
          "fa_icon": "fas fa-file-code"
        },
        "rnaseqc_gtf": {
          "type": "string",
          "format": "file-path",
          "description": "Pre-built collapsed GTF for RNA-SeQC (one transcript per gene). If omitted, the pipeline generates it automatically from --gtf using the GTEx collapse_annotation script.",
          "help_text": "RNA-SeQC requires a collapsed gene model where each gene is represented by a single transcript. The pipeline auto-generates this from --gtf via the GTEx `collapse_annotation.py` script (Francois Aguet, Broad Institute). Provide this parameter to skip that step and use a pre-built file instead — useful when you already ran the collapse step or need a specific gene model variant (e.g. stranded, or with a transcript blacklist).",
          "fa_icon": "fas fa-dna",
          "pattern": ".+\\.gtf(\\.gz)?$"
        }
      }
    },
    "pipeline_steps": {
      "title": "Pipeline steps",
      "type": "object",
      "fa_icon": "fas fa-tasks",
      "description": "Options to skip or modify pipeline processing steps.",
      "properties": {
        "skip_markduplicates": {
          "type": "boolean",
          "default": false,
          "description": "Skip the Picard MarkDuplicates step.",
          "help_text": "Set to true if your input BAM files already have duplicates marked (e.g. they were produced by a workflow that runs MarkDuplicates during alignment). When true, the pipeline passes the input BAM directly to downstream QC tools without re-running Picard MarkDuplicates.",
          "fa_icon": "fas fa-forward"
        },
        "skip_rustqc": {
          "type": "boolean",
          "default": false,
          "description": "Skip the RustQC RNA-seq QC step.",
          "fa_icon": "fas fa-forward"
        },
        "skip_music": {
          "type": "boolean",
          "default": false,
          "description": "Skip the MuSiC RNA deconvolution step.",
          "fa_icon": "fas fa-forward"
        },
        "skip_qualimap": {
          "type": "boolean",
          "description": "Skip Qualimap BAM QC.",
          "default": false,
          "fa_icon": "fas fa-fast-forward"
        },
        "skip_somalier": {
          "type": "boolean",
          "description": "Skip Somalier sample-swap and relatedness checks. When not skipped, --fasta and --somalier_sites are required.",
          "default": false,
          "fa_icon": "fas fa-fast-forward"
        },
        "skip_rnaseqc": {
          "type": "boolean",
          "description": "Skip RNA-SeQC (RNA samples only).",
          "default": false,
          "fa_icon": "fas fa-fast-forward"
        }
      }
    },
    "music_options": {
      "title": "MuSiC deconvolution options",
      "type": "object",
      "fa_icon": "fas fa-dna",
      "description": "Options for MuSiC RNA deconvolution.",
      "properties": {
        "sc_reference": {
          "type": "string",
          "format": "file-path",
          "exists": true,
          "description": "Path to the single-cell reference RDS file (SingleCellExperiment) used by MuSiC.",
          "help_text": "A SingleCellExperiment object saved as an RDS file. Must contain a 'counts' assay and 'tissue' and 'sample_id' colData columns. Defaults to the bundled Tabula Sapiens V2 reference in assets/.",
          "fa_icon": "fas fa-database"
        },
        "music_normalize": {
          "type": "boolean",
          "default": true,
          "description": "Apply library-size normalisation in MuSiC.",
          "fa_icon": "fas fa-balance-scale"
        },
        "music_center": {
          "type": "boolean",
          "default": false,
          "description": "Apply gene-expression centering in MuSiC.",
          "fa_icon": "fas fa-align-center"
        }
      }
    },
    "strandedness_options": {
      "title": "Strandedness options",
      "type": "object",
      "fa_icon": "fas fa-arrows-alt-h",
      "description": "Options to control RNA-seq library strandedness used by RustQC.",
      "properties": {
        "strandedness": {
          "type": "string",
          "default": "unstranded",
          "enum": ["unstranded", "forward", "reverse"],
          "description": "Library strandedness applied to all RNA samples.",
          "help_text": "Sets the RNA-seq library strandedness used by RustQC for strand-aware read counting. Use 'unstranded' for non-strand-specific libraries, 'forward' when read 1 maps to the transcript strand, and 'reverse' when read 2 maps to the transcript strand. This value is overridden on a per-sample basis when '--strandedness_table' is provided.",
          "fa_icon": "fas fa-arrows-alt-h"
        },
        "strandedness_table": {
          "type": "string",
          "format": "file-path",
          "exists": true,
          "mimetype": "text/csv",
          "pattern": "^\\S+\\.csv$",
          "description": "Path to a CSV with 'sample' and 'strandedness' columns to set strandedness per sample.",
          "help_text": "Optional comma-separated file with a header row and two columns: 'sample' (matching the sample IDs in '--input') and 'strandedness' (one of 'unstranded', 'forward', 'reverse'). When provided, the per-sample values override the global '--strandedness' parameter. Samples not listed in the table fall back to '--strandedness'.",
          "fa_icon": "fas fa-file-csv"
        }
      }
    },
    "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
        },
        "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", "string"],
          "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)."
        }
      }
    },
    "somalier_options": {
      "title": "Somalier options",
      "type": "object",
      "description": "Options for Somalier sample-swap and relatedness checking.",
      "default": {},
      "fa_icon": "fas fa-users",
      "properties": {
        "fasta": {
          "type": "string",
          "format": "file-path",
          "description": "Reference genome FASTA file. Required when --skip_somalier is not set.",
          "fa_icon": "fas fa-font",
          "pattern": ".+\\.fn?a(sta)?(\\.gz)?$"
        },
        "somalier_sites": {
          "type": "string",
          "format": "file-path",
          "description": "Sites VCF for Somalier extract (genome-build specific). Required when --skip_somalier is not set.",
          "fa_icon": "fas fa-file-alt",
          "pattern": ".+\\.vcf(\\.gz)?$"
        },
        "somalier_ped": {
          "type": "string",
          "format": "file-path",
          "description": "Optional PED file for Somalier relate to check expected family relationships.",
          "fa_icon": "fas fa-file-alt"
        }
      }
    }
  },
  "allOf": [
    {
      "$ref": "#/$defs/input_output_options"
    },
    {
      "$ref": "#/$defs/reference_genome_options"
    },
    {
      "$ref": "#/$defs/pipeline_steps"
    },
    {
      "$ref": "#/$defs/strandedness_options"
    },
    {
      "$ref": "#/$defs/music_options"
    },
    {
      "$ref": "#/$defs/institutional_config_options"
    },
    {
      "$ref": "#/$defs/generic_options"
    },
    {
      "$ref": "#/$defs/somalier_options"
    }
  ]
}