{
  "$schema": "http://json-schema.org/draft-07/schema",
  "$id": "https://raw.githubusercontent.com/epi2me-labs/wf-transcriptomes/master/nextflow_schema.json",
  "title": "epi2me-labs/wf-transcriptomes",
  "workflow_title": "Transcriptomes",
  "description": "Long-read transcriptome analysis using bambu with optional SQANTI3 QC, DESeq2, and DEXSeq.",
  "demo_url": "https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-transcriptomes/wf-transcriptomes-demo.tar.gz",
  "aws_demo_url": "https://ont-exd-int-s3-euwst1-epi2me-labs.s3.amazonaws.com/wf-transcriptomes/wf-transcriptomes-demo/aws.nextflow.config",
  "url": "https://github.com/epi2me-labs/wf-transcriptomes",
  "type": "object",
  "definitions": {
    "main_options": {
      "title": "Main Options",
      "type": "object",
      "description": "Parameters for read ingestion, and setting reference and transcriptome construction mode.",
      "properties": {
        "fastq": {
          "type": "string",
          "format": "path",
          "title": "FASTQ",
          "description": "FASTQ reads to analyse.",
          "help_text": "You can provide a single FASTQ, a folder of FASTQs, or a multiplexed folder containing one sub-folder per sample or barcode."
        },
        "bam": {
          "type": "string",
          "format": "path",
          "description": "BAM or uBAM reads to analyse.",
          "help_text": "You can provide a single BAM or uBAM, a folder of BAMs, or a multiplexed folder containing one sub-folder per sample or barcode."
        },
        "ref_genome": {
          "type": "string",
          "format": "file-path",
          "title": "Reference genome",
          "description": "Reference genome FASTA.",
          "help_text": "Required in both discover and fixed_annotation modes."
        },
        "ref_annotation": {
          "type": "string",
          "format": "file-path",
          "title": "Reference annotation",
          "description": "Reference transcript annotation in GTF or GFF format.",
          "help_text": "Required in both discover and fixed_annotation modes."
        },
        "transcriptome_mode": {
          "type": "string",
          "default": "discover",
          "enum": [
            "discover",
            "fixed_annotation"
          ],
          "description": "How bambu should prepare the transcriptome model.",
          "help_text": "Use discover for reference-guided transcript discovery and quantification, or fixed_annotation for quantification only against the supplied annotation."
        },
        "direct_rna": {
          "type": "boolean",
          "default": false,
          "description": "Set this for direct RNA sequencing libraries."
        }
      },
      "required": [
        "ref_genome",
        "ref_annotation",
        "transcriptome_mode"
      ],
      "allOf": [
        {
          "oneOf": [
            {
              "required": [
                "fastq"
              ]
            },
            {
              "required": [
                "bam"
              ]
            }
          ]
        }
      ]
    },
    "filter_options": {
      "title": "Read Filtering Options",
      "type": "object",
      "description": "Options for filtering input reads.",
      "properties": {
        "analyse_unclassified": {
          "type": "boolean",
          "default": false,
          "description": "Include unclassified reads from multiplexed input directories."
        },
        "analyse_fail": {
          "type": "boolean",
          "default": false,
          "description": "Include fail reads from bam_fail and fastq_fail folders found in sample folders on the input path."
        }
      }
    },
    "sample_options": {
      "title": "Sample Options",
      "type": "object",
      "description": "Parameters that control sample naming and experimental design.",
      "properties": {
        "sample_sheet": {
          "type": "string",
          "format": "file-path",
          "title": "Sample sheet",
          "description": "CSV file describing barcodes, aliases, and optional experimental design columns.",
          "help_text": "For multiplexed runs, the sample sheet should contain both barcode and alias. For differential analysis it must also contain alias, the condition column, and any extra columns named in `--covariates`."
        },
        "sample": {
          "type": "string",
          "description": "Single sample name for singleplexed input or to restrict multiplexed analysis to one sample."
        }
      }
    },
    "de_analysis_options": {
      "title": "Differential Expression Analysis Options",
      "type": "object",
      "description": "Parameters controlling DGE and DTU analyses.",
      "properties": {
        "de_analysis": {
          "type": "boolean",
          "default": false,
          "description": "Run differential gene expression and differential transcript usage analyses."
        },
        "condition_column": {
          "type": "string",
          "default": "condition",
          "description": "Main comparison column in the sample sheet."
        },
        "covariates": {
          "type": "string",
          "description": "Comma-separated extra sample-sheet columns to adjust for, for example batch.",
          "help_text": "Each listed name must exist as a column in the sample sheet."
        },
        "reference_level": {
          "type": "string",
          "description": "Baseline group for the main comparison column.",
          "help_text": "If omitted, the workflow will use control when that level exists."
        }
      },
      "dependencies": {
        "de_analysis": [
            "sample_sheet"
        ]
    }
    },
    "output_options": {
      "title": "Output Options",
      "type": "object",
      "description": "Parameters controlling workflow outputs.",
      "properties": {
        "out_dir": {
          "type": "string",
          "format": "directory-path",
          "default": "output",
          "description": "Directory for user-facing workflow outputs."
        },
        "igv": {
          "type": "boolean",
          "default": false,
          "description": "Generate an IGV configuration file for the aligned BAM outputs."
        }
      }
    },
    "advanced_options": {
      "title": "Advanced Options",
      "type": "object",
      "description": "Performance tuning and tool-specific advanced parameters.",
      "properties": {
        "threads": {
          "type": "integer",
          "default": 4,
          "description": "Thread count to use for the core workflow processes."
        },
        "mod_codes": {
          "type": "string",
          "description": "Comma-separated modified base codes to pass to modkit pileup.",
          "help_text": "Provide values accepted by `modkit pileup --modified-bases`, for example `A:a,C:m`. If omitted, the workflow infers `primary_base:mod_code` pairs from the BAM with `modkit modbam check-tags`."
        },
        "force_alignment" : {
          "type": "boolean",
          "default": false,
          "description": "Force re-alignment of input BAM files.",
          "help_text": "Read alignment is skipped if the existing sequence names in the aligned BAM match the provided reference. Enable this if the existing alignments used incorrect minimap2 presets (e.g. missing --splice or direct RNA settings)."
        },
        "ndr": {
          "type": "number",
          "description": "Optional bambu novel discovery rate override."
        },
        "sqanti_skip_orf": {
          "type": "boolean",
          "default": true,
          "description": "Skip ORF prediction during SQANTI3 QC."
        }
      }
    },
    "misc": {
      "title": "Miscellaneous Options",
      "type": "object",
      "description": "Everything else.",
      "default": "",
      "properties": {
        "disable_ping": {
          "type": "boolean",
          "default": false,
          "description": "Enable to prevent sending a workflow ping.",
          "overrides": {
            "epi2mecloud": {
              "hidden": true
            }
          }
        },
        "help": {
          "type": "boolean",
          "description": "Display help text.",
          "fa_icon": "fas fa-question-circle",
          "default": false,
          "hidden": true
        },
        "version": {
          "type": "boolean",
          "description": "Display version and exit.",
          "fa_icon": "fas fa-question-circle",
          "default": false,
          "hidden": true
        }
      }
    }
  },
  "allOf": [
    {
      "$ref": "#/definitions/main_options"
    },
    {
      "$ref": "#/definitions/filter_options"
    },
    {
      "$ref": "#/definitions/sample_options"
    },
    {
      "$ref": "#/definitions/de_analysis_options"
    },
    {
      "$ref": "#/definitions/output_options"
    },
    {
      "$ref": "#/definitions/advanced_options"
    },
    {
      "$ref": "#/definitions/misc"
    }
  ],
  "properties": {
    "aws_image_prefix": {
      "type": "string",
      "hidden": true
    },
    "aws_queue": {
      "type": "string",
      "hidden": true
    },
    "monochrome_logs": {
      "type": "boolean"
    },
    "validate_params": {
      "type": "boolean",
      "default": true
    },
    "show_hidden_params": {
      "type": "boolean"
    }
  },
  "resources": {
    "recommended": {
      "cpus": 32,
      "memory": "96GB"
    },
    "minimum": {
      "cpus": 12,
      "memory": "64GB"
    },
    "run_time": "Varies with read depth and sample count; expect a small single-sample run to finish in under 30 minutes with the recommended resources.",
    "arm_support": false
  }
}