nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/ScaleRna/nextflow_schema.json",
    "title": "ScaleRna pipeline parameters",
    "description": "ScaleBio Seq Suite: RNA workflow",
    "type": "object",
    "$defs": {
        "input_options": {
            "title": "Input options",
            "type": "object",
            "description": "Input to the workflow",
            "default": "",
            "properties": {
                "genome": {
                    "type": "string",
                    "description": "Reference genome related files and options required for the workflow",
                    "fa_icon": "fas fa-keyboard",
                    "pattern": "^\\S+\\.json$",
                    "format": "file-path",
                    "mimetype": "text/json"
                },
                "samples": {
                    "type": "string",
                    "description": "Csv file describing all samples in the analysis run (required!)",
                    "fa_icon": "fas fa-keyboard",
                    "pattern": "^\\S+\\.csv$",
                    "format": "file-path",
                    "mimetype": "text/csv"
                },
                "runFolder": {
                    "type": "string",
                    "description": "Top-level sequencer run directory (or null when using fastq input)",
                    "fa_icon": "fas fa-keyboard",
                    "format": "directory-path"
                },
                "fastqDir": {
                    "type": "string",
                    "description": "Directory containing pre-generated FASTQs files (or null when using runFolder input)",
                    "fa_icon": "fas fa-keyboard",
                    "format": "directory-path"
                },
                "fastqSamplesheet": {
                    "type": "string",
                    "description": "Optional samplesheet for bcl-convert, replacing the auto-generated one",
                    "fa_icon": "fas fa-keyboard",
                    "pattern": "^\\S+\\.csv$",
                    "format": "file-path",
                    "mimetype": "text/csv"
                },
                "resultDir": {
                    "type": "string",
                    "description": "For reporting runs; output directory for previous pipeline run (to combine multiple runs, specify in samples.csv)",
                    "fa_icon": "fas fa-keyboard",
                    "format": "directory-path"
                }
            },
            "required": [
                "genome",
                "samples"
            ],
            "fa_icon": "fas fa-keyboard"
        },
        "analysis_options": {
            "title": "Analysis options",
            "type": "object",
            "description": "Configure behavior of the workflow",
            "default": "",
            "properties": {
                "libStructure": {
                    "type": "string",
                    "description": "Library structure (barcode locations and sequences). Can be absolute paths or relative to ${projectDir}/references/",
                    "help_text": "RNA kit v1.0: \"libV1.json\"\nRNA kit v1.1: \"libV1.1.json\"\nQuantum kit: \"libQuantumV1.0.json\"",
                    "fa_icon": "fas fa-filter",
                    "pattern": "^\\S+\\.json$",
                    "format": "file-path",
                    "mimetype": "text/json",
                    "default": "libQuantumV1.0.json"
                },
                "scalePlexLibStructure": {
                    "type": "string",
                    "default": "scaleplexlibQuantumV1.0.json",
                    "description": "Library structure json to use for a ScalePlex run",
                    "fa_icon": "fas fa-filter",
                    "pattern": "^\\S+\\.json$",
                    "format": "file-path",
                    "mimetype": "text/json"
                },
                "scalePlex": {
                    "type": "boolean",
                    "description": "Analyze a ScalePlex dataset",
                    "fa_icon": "fas fa-filter"
                },
                "reporting": {
                    "type": "boolean",
                    "description": "Run only cell-filtering and reporting steps, with optional sample merging",
                    "fa_icon": "fas fa-filter"
                },
                "cellFinder": {
                    "type": "boolean",
                    "description": "Compare cell-barcode expression profiles to background to call more cells",
                    "fa_icon": "fas fa-filter",
                    "default": true
                },
                "merge": {
                    "type": "boolean",
                    "default": true,
                    "description": "Merge samples across libraries / plates (based on 'sample' or 'group' column in samples.csv)",
                    "fa_icon": "fas fa-filter"
                },
                "bclConvertParams": {
                    "type": "string",
                    "description": "Additional bcl-convert arguments",
                    "fa_icon": "fas fa-filter",
                    "hidden": true
                },
                "fastqc": {
                    "type": "boolean",
                    "default": true,
                    "description": "Run fastqc on input fastqs",
                    "fa_icon": "fas fa-filter",
                    "hidden": true
                },
                "splitFastq": {
                    "type": "boolean",
                    "description": "Parallel analysis of subsets of reads",
                    "fa_icon": "fas fa-filter",
                    "hidden": true,
                    "default": true
                }
            },
            "required": [
                "libStructure"
            ],
            "fa_icon": "fas fa-filter"
        },
        "output_options": {
            "title": "Output options",
            "type": "object",
            "description": "Configure output options for a pipeline run",
            "default": "",
            "properties": {
                "outDir": {
                    "type": "string",
                    "default": "ScaleRna.out",
                    "description": "Name of the output directory for workflow results",
                    "fa_icon": "fas fa-edit",
                    "format": "directory-path"
                },
                "bamOut": {
                    "type": "boolean",
                    "description": "Set to false to skip BAM output from STAR",
                    "fa_icon": "fas fa-edit"
                },
                "bcParserBamOut": {
                    "type": "boolean",
                    "description": "Set to true to publish unaligned BAMs from bcParser",
                    "fa_icon": "fas fa-edit"
                },
                "fastqOut": {
                    "type": "boolean",
                    "description": "Set to true to publish bcl converted fastq files to outDir",
                    "fa_icon": "fas fa-edit"
                }
            },
            "required": [
                "outDir"
            ],
            "fa_icon": "fas fa-edit"
        },
        "downstream_workflow": {
            "title": "Downstream Workflow",
            "type": "object",
            "description": "Configure options for downstream workflow",
            "default": "",
            "properties": {
                "azimuthRef": {
                    "type": "string",
                    "default": "pbmcref",
                    "description": "Azimuth reference to use",
                    "fa_icon": "fas fa-chart-pie"
                },
                "azimuth": {
                    "type": "boolean",
                    "description": "Enable azimuth cell-type classification",
                    "fa_icon": "fas fa-chart-pie"
                },
                "seurat": {
                    "type": "boolean",
                    "description": "Enable preliminary seurat clustering",
                    "fa_icon": "fas fa-chart-pie"
                },
                "annData": {
                    "type": "boolean",
                    "description": "Enables output of UMI count matrices in annData format",
                    "fa_icon": "fas fa-chart-pie"
                },
                "compSamples": {
                    "type": "boolean",
                    "description": "Enable co-analysis of multiple samples",
                    "fa_icon": "fas fa-chart-pie"
                }
            },
            "fa_icon": "fas fa-chart-pie"
        },
        "internal_options": {
            "title": "Internal options",
            "type": "object",
            "description": "Configure options for internal ScaleBio run",
            "default": "",
            "fa_icon": "fas fa-lock",
            "properties": {
                "internalReport": {
                    "type": "boolean",
                    "fa_icon": "fas fa-lock",
                    "description": "Add extra metrics and plots to QC report",
                    "hidden": true
                },
                "computeOutDir": {
                    "type": "boolean",
                    "fa_icon": "fas fa-lock",
                    "description": "Construct unique output directory based on params.outDir and workflow run name",
                    "hidden": true
                },
                "index2MinFileSize": {
                    "type": "integer",
                    "default": 1048576,
                    "description": "Index2 fastq files below this size get filtered out",
                    "hidden": true,
                    "fa_icon": "fas fa-lock"
                },
                "minPassingSampleReads": {
                    "type": "integer",
                    "default": 100000,
                    "description": "Minimum reads a sample must have post bcParser to make it to alignment",
                    "hidden": true,
                    "fa_icon": "fas fa-lock"
                }
            }
        },
        "resource_usage": {
            "title": "Resource usage",
            "type": "object",
            "description": "Configure options that control resource usage and parallelization",
            "default": "",
            "properties": {
                "bcParserJobsPerLibName": {
                    "type": "integer",
                    "default": 16,
                    "description": "Number of bcParser jobs",
                    "fa_icon": "fas fa-server",
                    "hidden": true
                },
                "rtBarcodesPerStarJob": {
                    "type": "integer",
                    "default": 4,
                    "description": "uBAM files from this number of RT barcodes make it into one STAR job when using splitFastq",
                    "hidden": true,
                    "fa_icon": "fas fa-server"
                },
                "totalFastqcJobs": {
                    "type": "integer",
                    "default": 100,
                    "description": "Number of total fastqc jobs",
                    "hidden": true,
                    "fa_icon": "fas fa-server"
                },
                "filesPerLibDetection": {
                    "type": "integer",
                    "default": 32,
                    "fa_icon": "fas fa-server",
                    "description": "Number of files (input index2 fastq / input ucram) batched into a single LibraryDetection process"
                },
                "taskMaxMemory": {
                    "type": "string",
                    "default": "256 GB",
                    "description": "Maximum memory that can be requested by a process",
                    "fa_icon": "fas fa-server",
                    "hidden": true
                },
                "taskMaxCpus": {
                    "type": "integer",
                    "default": 16,
                    "description": "Maximum number of CPUs that can be requested by a process",
                    "fa_icon": "fas fa-server",
                    "hidden": true
                },
                "taskMaxTime": {
                    "type": "string",
                    "default": "2d",
                    "description": "Maximum allowed running time of a single process",
                    "fa_icon": "fas fa-server",
                    "hidden": true
                }
            },
            "fa_icon": "fas fa-server"
        },
        "star_alignment": {
            "title": "Alignment (STAR)",
            "type": "object",
            "description": "Configure analysis options for alignment",
            "default": "",
            "help_text": "",
            "properties": {
                "starFeature": {
                    "type": "string",
                    "default": "GeneFull_Ex50pAS",
                    "description": "What read to transcript overlaps STAR counts (--soloFeatures)",
                    "fa_icon": "fas fa-indent",
                    "hidden": true
                },
                "starMulti": {
                    "type": "string",
                    "default": "PropUnique",
                    "description": "How to handle reads matching multiple genes (--soloMultiMappers)",
                    "fa_icon": "fas fa-indent",
                    "hidden": true
                },
                "starMultiBarnyard": {
                    "type": "string",
                    "default": "Unique",
                    "description": "How to handle reads matching multiple genes for barnyard datasets (--soloMultiMappers)",
                    "fa_icon": "fas fa-indent",
                    "hidden": true
                },
                "starStrand": {
                    "type": "string",
                    "default": "Forward",
                    "description": "Strandedness of RNA reads relative to annotated genes",
                    "fa_icon": "fas fa-indent",
                    "hidden": true
                },
                "starTrimming": {
                    "type": "string",
                    "description": "Trimming in STAR (in addition to cutadapt)",
                    "fa_icon": "fas fa-indent",
                    "hidden": true
                },
                "starMaxLoci": {
                    "type": "integer",
                    "default": 6,
                    "description": "Maximum number of Loci multimapping reads can map (--outFilterMultimapNmax)",
                    "fa_icon": "fas fa-indent",
                    "hidden": true
                },
                "roundCounts": {
                    "type": "boolean",
                    "description": "Round UMI counts to nearest integer",
                    "fa_icon": "fas fa-indent",
                    "hidden": true
                }
            },
            "fa_icon": "fas fa-indent"
        },
        "scaleplex": {
            "title": "ScalePlex",
            "type": "object",
            "description": "Configure analysis options for a ScalePlex run",
            "default": "",
            "properties": {
                "scalePlexToRnaMapping": {
                    "type": "string",
                    "description": "ScalePlex PCR to RNA PCR mapping for merging ScalePlex library with RNA library",
                    "fa_icon": "fas fa-viruses",
                    "hidden": true
                },
                "scalePlexFCThreshold": {
                    "type": "integer",
                    "default": 2,
                    "description": "If using fold-change assignment algorithm set fc ratio for valid assignment of second / third detected ScalePlex oligo",
                    "fa_icon": "fas fa-viruses",
                    "hidden": true
                },
                "scalePlexPercentFromTopTwo": {
                    "type": "integer",
                    "default": 0,
                    "description": "Threshold percent of ScalePlex UMIs from top two unique to pass assignment, e.g. 50",
                    "fa_icon": "fas fa-viruses",
                    "hidden": true
                },
                "scalePlexAssignmentMethod": {
                    "type": "string",
                    "default": "bg",
                    "description": "Use background ('bg') or fold-change ('fc') algorithm for ScalePlex assignment",
                    "fa_icon": "fas fa-viruses",
                    "hidden": true,
                    "enum": [
                        "bg",
                        "fc"
                    ]
                },
                "scalePlexMinReadUmi": {
                    "type": "integer",
                    "default": 1,
                    "description": "Minimum read count per UMI for inclusion in matrix",
                    "hidden": true,
                    "fa_icon": "fas fa-viruses"
                },
                "scalePlexMinCellCountBG": {
                    "type": "number",
                    "default": 0.01,
                    "description": "Minimum fraction of cells that an ScalePlex oligo needs background UMI counts in to be considered as valid",
                    "hidden": true,
                    "fa_icon": "fas fa-viruses"
                },
                "scalePlexMinBGVal": {
                    "type": "number",
                    "default": 1.0,
                    "description": "Minimum value of ScalePlex oligo counts set in background estimation if a ScalePlex oligo does not meet scalePlexMinCellCountBG check",
                    "hidden": true,
                    "fa_icon": "fas fa-viruses"
                }
            },
            "fa_icon": "fas fa-viruses"
        },
        "cell_calling_filtering_cells": {
            "title": "Cell Calling/Filtering Cells",
            "type": "object",
            "description": "Set cell calling parameters and configure CellFinder behavior",
            "default": "",
            "properties": {
                "expectedCells": {
                    "type": "integer",
                    "default": 0,
                    "description": "Optional input for TopCells or FixedCells; Typically set per sample in samples.csv",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "useSTARthreshold": {
                    "type": "boolean",
                    "description": "Use STARSolo built-in default cell threshold",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "minCellRatio": {
                    "type": "integer",
                    "default": 10,
                    "description": "Ratio between transcript counts of top cells and the lower cell threshold",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "topCellPercent": {
                    "type": "integer",
                    "default": 99,
                    "fa_icon": "fas fa-fingerprint",
                    "description": "Percentage of cells over minUTC to use as 'robust max'",
                    "hidden": true
                },
                "madsReads": {
                    "type": "integer",
                    "default": 5,
                    "description": "If set, flag cells with log(total_reads) outside +/- x MADs",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "madsPassingReads": {
                    "type": "integer",
                    "default": 8,
                    "description": "Low passing read fraction: (passingReads/Reads) < x MADs",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "madsMito": {
                    "type": "integer",
                    "default": 5,
                    "description": "# High mito. reads: (mitoReads/reads) > x MADs",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "filterOutliers": {
                    "type": "boolean",
                    "description": "Filter flagged cells from passing cell matrix",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "minBeadDivergence": {
                    "type": "number",
                    "default": 0.2,
                    "description": "Classify beads as ambient with KL divergence below this threshold",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "fixedCells": {
                    "type": "boolean",
                    "description": "Call the top \"expectedCells\" many barcodes per sample as cells (set in samples.csv)",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "UTC": {
                    "type": "integer",
                    "default": 0,
                    "description": "Set a fixed threshold above which all barcodes are called (minUTC < X < UTC go to CellFinder if enabled)",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "minUTC": {
                    "type": "integer",
                    "default": 100,
                    "description": "Minimum transcript count to consider a barcode as a potential cell",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "filterAmbientBeads": {
                    "type": "boolean",
                    "description": "Flag used to filter cells from UMI count matrix which were captured on ambient beads",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "cellFinderFdr": {
                    "type": "number",
                    "default": 0.001,
                    "description": "False Discovery Rate Threshold to call a cell-barcode above background",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                },
                "medianFraction": {
                    "type": "number",
                    "default": 0.05,
                    "description": "Lower count threshold for barcodes to be tested relative to 'top cells'; 0 to disable",
                    "fa_icon": "fas fa-fingerprint",
                    "hidden": true
                }
            },
            "fa_icon": "fas fa-fingerprint"
        },
        "ultima": {
            "title": "Ultima",
            "type": "object",
            "description": "Configure options when analyzing ultima sequenced data",
            "default": "",
            "fa_icon": "fas fa-guitar",
            "properties": {
                "ultimaCramDir": {
                    "type": "string",
                    "fa_icon": "fas fa-guitar",
                    "description": "Path to directory containing ultima unaligned cram files",
                    "hidden": true,
                    "format": "directory-path"
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/input_options"
        },
        {
            "$ref": "#/$defs/analysis_options"
        },
        {
            "$ref": "#/$defs/output_options"
        },
        {
            "$ref": "#/$defs/downstream_workflow"
        },
        {
            "$ref": "#/$defs/internal_options"
        },
        {
            "$ref": "#/$defs/resource_usage"
        },
        {
            "$ref": "#/$defs/star_alignment"
        },
        {
            "$ref": "#/$defs/scaleplex"
        },
        {
            "$ref": "#/$defs/cell_calling_filtering_cells"
        },
        {
            "$ref": "#/$defs/ultima"
        }
    ]
}