nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/nfdata-omics/spatialomics/master/nextflow_schema.json",
    "title": "nfdata-omics/spatialomics pipeline parameters",
    "description": "Analysis of spatial omics dataset",
    "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"
                },
                "email": {
                    "type": "string",
                    "description": "Email address for completion summary.",
                    "fa_icon": "fas fa-envelope",
                    "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
                    "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
                },
                "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"
                }
            }
        },
        "bin_level_matrix_analysis_options": {
            "title": "Bin-level matrix analysis options",
            "type": "object",
            "fa_icon": "fas fa-sliders-h",
            "description": "Parameters controlling bin-level matrix analysis and quality control.",
            "properties": {
                "bin_analysis_bin_size": {
                    "type": "string",
                    "default": "square_016um",
                    "description": "Space Ranger binned output label used for bin-level matrix analysis.",
                    "help_text": "For Visium HD data this is typically one of square_002um, square_008um, or square_016um.",
                    "fa_icon": "fas fa-border-all"
                },
                "bin_analysis_min_counts": {
                    "type": "integer",
                    "default": 100,
                    "minimum": 0,
                    "description": "Minimum total counts threshold for bin-level quality control.",
                    "fa_icon": "fas fa-filter"
                },
                "bin_analysis_min_genes": {
                    "type": "integer",
                    "default": 50,
                    "minimum": 0,
                    "description": "Minimum detected genes threshold for bin-level quality control.",
                    "fa_icon": "fas fa-filter"
                },
                "bin_analysis_max_mt": {
                    "type": "integer",
                    "default": 20,
                    "minimum": 0,
                    "maximum": 100,
                    "description": "Maximum mitochondrial counts percentage threshold for bin-level quality control.",
                    "fa_icon": "fas fa-filter"
                }
            }
        },
        "cell_segmentation_options": {
            "title": "Cell segmentation options",
            "type": "object",
            "fa_icon": "fas fa-draw-polygon",
            "description": "Parameters controlling cell segmentation and microscopy coordinate handling.",
            "properties": {
                "skip_segmentation": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip microscopy image conversion, Cellpose segmentation, and segmentation visualization outputs.",
                    "help_text": "Use this option when microscopy images are present in the samplesheet but cell segmentation and the related MultiQC plots/statistics should not be generated.",
                    "fa_icon": "fas fa-ban"
                },
                "zarr_downsample_factor": {
                    "type": "number",
                    "default": 1,
                    "exclusiveMinimum": 0,
                    "description": "Downsampling factor between full-resolution TIFF image coordinates and the SpatialData zarr coordinate system.",
                    "help_text": "Use this parameter when the coordinates stored in the SpatialData zarr are downsampled relative to the full-resolution microscopy and segmentation TIFF images.",
                    "fa_icon": "fas fa-compress-arrows-alt"
                }
            }
        },
        "bin_to_cell_mapping_options": {
            "title": "Bin-to-cell mapping options",
            "type": "object",
            "fa_icon": "fas fa-project-diagram",
            "description": "Parameters controlling Bin2Cell aggregation of spatial bins into cell-level data.",
            "properties": {
                "skip_bin2cell": {
                    "type": "boolean",
                    "default": false,
                    "description": "Skip Bin2Cell aggregation of Visium HD bins into cell-level AnnData.",
                    "help_text": "Use this option when segmentation should be run but cell-level Bin2Cell aggregation should be skipped.",
                    "fa_icon": "fas fa-ban"
                },
                "bin2cell_bin_size": {
                    "type": "string",
                    "default": "square_002um",
                    "description": "Space Ranger binned output label used by Bin2Cell in bin aggregation.",
                    "help_text": "For Visium HD data this is typically one of square_002um, square_008um, or square_016um.",
                    "fa_icon": "fas fa-border-all"
                },
                "bin2cell_volume_ratio": {
                    "type": "number",
                    "default": 4,
                    "exclusiveMinimum": 0,
                    "description": "Volume ratio used by Bin2Cell label expansion.",
                    "help_text": "Passed to bin2cell.expand_labels to expand nuclear segmentation labels before bin-to-cell aggregation.",
                    "fa_icon": "fas fa-expand-arrows-alt"
                }
            }
        },
        "reference_genome_options": {
            "title": "Reference genome options",
            "type": "object",
            "fa_icon": "fas fa-dna",
            "description": "Reference genome related files and options required for the workflow.",
            "properties": {
                "genome": {
                    "type": "string",
                    "description": "Name of iGenomes reference.",
                    "fa_icon": "fas fa-book",
                    "help_text": "If using a reference genome configured in the pipeline using iGenomes, use this parameter to give the ID for the reference. This is then used to build the full paths for all required reference genome files e.g. `--genome GRCh38`. \n\nSee the [nf-core website docs](https://nf-co.re/usage/reference_genomes) for more details."
                },
                "fasta": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "mimetype": "text/plain",
                    "pattern": "^\\S+\\.fn?a(sta)?(\\.gz)?$",
                    "description": "Path to FASTA genome file.",
                    "help_text": "This parameter is *mandatory* if `--genome` or `--spaceranger_index` are not specified. If you don't have a Space Ranger index available this will be generated for you automatically.",
                    "fa_icon": "far fa-file-code"
                },
                "gtf": {
                    "type": "string",
                    "format": "file-path",
                    "exists": true,
                    "mimetype": "text/plain",
                    "pattern": "^\\S+\\.gtf(\\.gz)?$",
                    "description": "Path to GTF annotation file.",
                    "help_text": "This parameter is mandatory if `--genome` or `--spaceranger_index` are not specified. If you don't have a Space Ranger index available this will be generated for you automatically.",
                    "errorMessage": "The GTF file must have a .gtf or .gtf.gz extension, must not contain spaces, and must exist.",
                    "fa_icon": "fas fa-code-branch"
                },
                "spaceranger_index": {
                    "type": "string",
                    "format": "path",
                    "description": "Path to a Space Ranger reference folder. Can alternatively be provided as `tar.gz` archive.",
                    "help_text": "Please see the [10x website](https://support.10xgenomics.com/spatial-gene-expression/software/downloads/latest) to download either of the supported human or mouse references.",
                    "fa_icon": "fas fa-folder-open",
                    "exists": true
                },
                "reference_name": {
                    "type": "string",
                    "fa_icon": "fas fa-book",
                    "description": "Genome assembly label that will be used to name a new index built from fasta and gft files with spaceranger mkref."
                },
                "probeset": {
                    "type": "string",
                    "format": "file-path",
                    "mimetype": "text/csv",
                    "pattern": "^\\S+\\.csv$",
                    "description": "Location of Space Ranger probeset file.",
                    "fa_icon": "fas fa-file-csv",
                    "exists": true
                },
                "igenomes_ignore": {
                    "type": "boolean",
                    "description": "Do not load the iGenomes reference config.",
                    "fa_icon": "fas fa-ban",
                    "hidden": true,
                    "help_text": "Do not load `igenomes.config` when running the pipeline. You may choose this option if you observe clashes between custom parameters and those supplied in `igenomes.config`."
                },
                "igenomes_base": {
                    "type": "string",
                    "description": "The base path to the igenomes reference files",
                    "fa_icon": "fas fa-ban",
                    "hidden": true,
                    "default": "s3://ngi-igenomes/igenomes/"
                }
            }
        },
        "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
                },
                "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})$",
                    "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
                    "hidden": true
                },
                "plaintext_email": {
                    "type": "boolean",
                    "description": "Send plain-text email instead of HTML.",
                    "fa_icon": "fas fa-remove-format",
                    "hidden": true
                },
                "max_multiqc_email_size": {
                    "type": "string",
                    "description": "File size limit when attaching MultiQC reports to summary emails.",
                    "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
                    "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
                },
                "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)."
                }
            }
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/bin_level_matrix_analysis_options"
        },
        {
            "$ref": "#/$defs/cell_segmentation_options"
        },
        {
            "$ref": "#/$defs/bin_to_cell_mapping_options"
        },
        {
            "$ref": "#/$defs/reference_genome_options"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ]
}