nextflow_schema.json

{
  "$schema": "http://json-schema.org/draft-07/schema",
  "$id": "https://raw.githubusercontent.com/RNABioInfo/seq_lm/master/nextflow_schema.json",
  "title": "RNABioInfo/seq_lm",
  "description": "Live quality-control and differential-expression analysis of Oxford Nanopore BAM data.",
  "url": "https://github.com/RNABioInfo/seq_lm",
  "type": "object",
  "definitions": {
    "input_options": {
      "title": "Input Options",
      "type": "object",
      "fa_icon": "fas fa-arrow-right",
      "description": "Input samples and controls for live or one-shot BAM ingestion.",
      "properties": {
        "sample_sheet": {
          "type": "string",
          "format": "path",
          "fa_icon": "fas fa-file-csv",
          "description": "CSV sample sheet describing the BAM directories to analyze.",
          "help_text": "The sheet must contain alias, group, and bam_dir columns. Optional is_live and order columns control live watching and timeline order. is_live accepts true or false case-insensitively; missing or blank values default to true. Samples that are not effectively live must contain at least one BAM at startup."
        },
        "live_analysis": {
          "type": "boolean",
          "default": true,
          "fa_icon": "fas fa-eye",
          "description": "Watch eligible sample directories for new BAM files.",
          "help_text": "A sample is watched only when this option and the sample sheet row's is_live value are both true. Disable this option to process every sample once from the BAM files present at startup."
        },
        "timeline_analysis": {
          "type": "boolean",
          "default": false,
          "fa_icon": "fas fa-stream",
          "description": "Process samples according to the order values in the sample sheet.",
          "help_text": "When enabled, every sample-sheet row must provide an order value."
        },
        "differential_expression": {
          "type": "boolean",
          "default": true,
          "fa_icon": "fas fa-chart-line",
          "description": "Quantify transcripts and run differential-expression analysis.",
          "help_text": "Disable this option to run quality control only. Reference genome and annotation inputs are required only when this option is enabled."
        },
        "gene_set_enrichment": {
          "type": "boolean",
          "default": true,
          "fa_icon": "fas fa-project-diagram",
          "description": "Run fry and GSVA gene-set enrichment after differential expression.",
          "help_text": "This option requires differential_expression. The gene_sets input is required only when this option is enabled."
        }
      },
      "required": [
        "sample_sheet"
      ]
    },
    "reference_options": {
      "title": "Reference and Gene Set Options",
      "type": "object",
      "fa_icon": "fas fa-dna",
      "description": "Reference files used for transcript quantification and gene-set analysis.",
      "properties": {
        "reference_genome": {
          "type": "string",
          "format": "path",
          "fa_icon": "fas fa-dna",
          "description": "Reference genome FASTA used by Oarfish for soft-clip rescue."
        },
        "reference_annotation": {
          "type": "string",
          "format": "path",
          "fa_icon": "fas fa-file-alt",
          "description": "Reference transcript annotation in GTF or GFF format used by Oarfish."
        },
        "gene_sets": {
          "type": "string",
          "format": "path",
          "fa_icon": "fas fa-project-diagram",
          "description": "Gene Matrix Transposed (GMT) file used for edgeR fry and GSVA gene-set analysis.",
          "help_text": "GMT members may match count-table feature identifiers directly or identifiers in the supplied GTF/GFF annotation."
        }
      }
    },
    "differential_analysis_options": {
      "title": "Differential Analysis Options",
      "type": "object",
      "fa_icon": "fas fa-chart-line",
      "description": "Significance thresholds used by edgeR and the differential-analysis report.",
      "properties": {
        "de_lfc_cutoff": {
          "type": "number",
          "minimum": 0,
          "default": 1.0,
          "description": "Minimum absolute log2 fold change used by edgeR glmTreat and the report's significance coloring."
        },
        "de_padj_cutoff": {
          "type": "number",
          "exclusiveMinimum": 0,
          "maximum": 1,
          "default": 0.05,
          "description": "Maximum edgeR false-discovery rate used to classify significant results."
        },
        "min_read_count": {
          "type": "integer",
          "minimum": 0,
          "default": 10000,
          "description": "Minimum total assigned reads required for a sample to count toward DEA readiness."
        },
        "min_replicate_sample_count": {
          "type": "integer",
          "minimum": 1,
          "default": 2,
          "description": "Minimum number of samples per group that must satisfy the DEA read-count threshold."
        }
      }
    },
    "output_options": {
      "title": "Output Options",
      "type": "object",
      "fa_icon": "fas fa-folder-open",
      "description": "Names and locations used for workflow outputs.",
      "properties": {
        "ex_name": {
          "type": "string",
          "minLength": 1,
          "default": "seq_lm",
          "fa_icon": "fas fa-flask",
          "description": "Name used to identify the experiment in workflow metadata and reports."
        },
        "out_dir": {
          "type": "string",
          "format": "path",
          "default": "output",
          "fa_icon": "fas fa-folder-open",
          "description": "Directory in which workflow results and execution reports are published."
        }
      }
    },
    "resource_options": {
      "title": "Resource Options",
      "type": "object",
      "fa_icon": "fas fa-microchip",
      "description": "Global analysis limits retained for processes that consume them.",
      "properties": {
        "min_mapq": {
          "type": "integer",
          "minimum": 0,
          "default": 10,
          "description": "Minimum read mapping quality available to analysis steps that apply a mapping-quality filter."
        }
      }
    },
    "advanced_options": {
      "title": "Advanced Options",
      "type": "object",
      "fa_icon": "fas fa-cogs",
      "description": "Telemetry, cloud, validation, and internal workflow settings.",
      "properties": {
        "disable_ping": {
          "type": "boolean",
          "default": false,
          "description": "Prevent the workflow from sending start and completion telemetry pings."
        },
        "monochrome_logs": {
          "type": "boolean",
          "default": false,
          "description": "Disable ANSI colors in workflow log messages."
        },
        "validate_params": {
          "type": "boolean",
          "default": true,
          "description": "Validate workflow parameters against this schema before analysis starts."
        },
        "show_hidden_params": {
          "type": "boolean",
          "default": false,
          "description": "Include internal parameters in command-line help output."
        },
        "aws_image_prefix": {
          "type": "string",
          "description": "Prefix applied to container image names when running on AWS.",
          "hidden": true
        },
        "aws_queue": {
          "type": "string",
          "description": "AWS Batch queue used by an AWS execution profile.",
          "hidden": true
        },
        "ex_mk_cert": {
          "type": "string",
          "format": "path",
          "description": "Reserved path to a MinKNOW client certificate for sequencing-control integration.",
          "hidden": true
        },
        "ex_mk_key": {
          "type": "string",
          "format": "path",
          "description": "Reserved path to a MinKNOW client private key for sequencing-control integration.",
          "hidden": true
        },
        "process_label": {
          "type": "string",
          "default": "seq_lm",
          "description": "Default Nextflow process label used by workflow processes.",
          "hidden": true
        },
        "schema_ignore_params": {
          "type": "string",
          "default": "show_hidden_params,validate_params,monochrome_logs,aws_queue,aws_image_prefix,wf,live_analysis",
          "description": "Comma-separated parameters excluded from schema validation.",
          "hidden": true
        },
        "help": {
          "type": "boolean",
          "default": false,
          "fa_icon": "fas fa-question-circle",
          "description": "Display workflow help and exit.",
          "hidden": true
        },
        "version": {
          "type": "boolean",
          "default": false,
          "fa_icon": "fas fa-info-circle",
          "description": "Display the workflow version and exit.",
          "hidden": true
        }
      }
    }
  },
  "allOf": [
    {
      "$ref": "#/definitions/input_options"
    },
    {
      "$ref": "#/definitions/reference_options"
    },
    {
      "$ref": "#/definitions/differential_analysis_options"
    },
    {
      "$ref": "#/definitions/output_options"
    },
    {
      "$ref": "#/definitions/resource_options"
    },
    {
      "$ref": "#/definitions/advanced_options"
    },
    {
      "if": {
        "properties": {
          "differential_expression": {
            "const": true
          }
        },
        "required": [
          "differential_expression"
        ]
      },
      "then": {
        "required": [
          "reference_genome",
          "reference_annotation"
        ]
      }
    },
    {
      "if": {
        "properties": {
          "gene_set_enrichment": {
            "const": true
          }
        },
        "required": [
          "gene_set_enrichment"
        ]
      },
      "then": {
        "required": [
          "gene_sets"
        ],
        "properties": {
          "differential_expression": {
            "const": true
          }
        }
      }
    }
  ],
  "docs": {
    "intro": "## Introduction\n\nseq_lm performs live or one-shot quality control, transcript quantification, differential-expression analysis, and gene-set enrichment for Oxford Nanopore BAM data.\n\n",
    "links": "## Useful links\n\n* [Nextflow](https://www.nextflow.io/)\n* [Workflow repository](https://github.com/RNABioInfo/seq_lm)\n* [Docker](https://www.docker.com/products/docker-desktop)\n* [Singularity](https://docs.sylabs.io/guides/latest/user-guide/)\n"
  }
}