nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/nf-core/spatialvi/master/nextflow_schema.json",
    "title": "nf-core/spatialvi pipeline parameters",
    "description": "10X Visium Spatial Transcriptomics",
    "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 2 or 5 columns, plus a header row. See [usage docs](https://nf-co.re/spatialvi/usage#samplesheet-input).",
                    "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"
                }
            }
        },

        "spaceranger_options": {
            "title": "Space Ranger options",
            "type": "object",
            "fa_icon": "fas fa-rocket",
            "description": "Options related to Space Ranger execution and raw spatial data processing",
            "properties": {
                "spaceranger_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
                },
                "spaceranger_reference": {
                    "type": "string",
                    "format": "path",
                    "description": "Location of Space Ranger reference directory. May be packed as `tar.gz` file.",
                    "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. If not specified the GRCh38 human reference is automatically downloaded and used.",
                    "fa_icon": "fas fa-folder-open",
                    "default": "https://cf.10xgenomics.com/supp/spatial-exp/refdata-gex-GRCh38-2020-A.tar.gz",
                    "exists": true
                }
            }
        },

        "visium_hd_options": {
            "title": "Visium HD options",
            "type": "object",
            "fa_icon": "fas fa-table-cells",
            "description": "Options specific to the analysis of Visium HD data.",
            "properties": {
                "hd_bin_size": {
                    "type": "integer",
                    "default": 8,
                    "enum": [2, 8, 16],
                    "description": "Bin size for Visium HD data. Allowed values: 2, 8, 16.",
                    "fa_icon": "fas fa-expand"
                }
            }
        },

        "filtering_options": {
            "title": "Filtering options",
            "type": "object",
            "fa_icon": "fas fa-filter",
            "description": "Filtering settings and thresholds used by the pipeline",
            "properties": {
                "qc_min_counts": {
                    "type": "integer",
                    "default": 500,
                    "description": "The minimum number of UMIs needed in a spot for that spot to pass the filtering.",
                    "fa_icon": "fas fa-hashtag"
                },
                "qc_min_genes": {
                    "type": "integer",
                    "default": 250,
                    "description": "The minimum number of expressed genes in a spot needed for that spot to pass the filtering.",
                    "fa_icon": "fas fa-hashtag"
                },
                "qc_min_spots": {
                    "type": "integer",
                    "default": 1,
                    "description": "The minimum number of spots in which a gene is expressed for that gene to pass the filtering.",
                    "fa_icon": "fas fa-hashtag"
                },
                "qc_mito_threshold": {
                    "type": "number",
                    "default": 20,
                    "description": "The maximum proportion of mitochondrial content that a spot is allowed to have to pass the filtering.",
                    "help_text": "If you do not wish to filter based on mitochondrial content, set this parameter to `100`.",
                    "fa_icon": "fas fa-hashtag"
                },
                "qc_ribo_threshold": {
                    "type": "number",
                    "default": 0,
                    "description": "The minimum percentage of ribosomal content that a spot needs to have to pass the filtering (no filtering is done by default).",
                    "fa_icon": "fas fa-hashtag"
                },
                "qc_hb_threshold": {
                    "type": "number",
                    "default": 100,
                    "description": "The maximum proportion of haemoglobin content that a spot is allowed to have to pass the filtering (no filtering is done by default).",
                    "fa_icon": "fas fa-hashtag"
                }
            }
        },

        "normalization_options": {
            "title": "Normalization options",
            "type": "object",
            "fa_icon": "fas fa-filter",
            "description": "Normalization options used by the pipeline.",
            "properties": {
                "normalize_target_sum": {
                    "type": "integer",
                    "default": 0,
                    "description": "Target sum for normalization of counts per cell.",
                    "help_text": "By default (with value 0), normalizes so that each cell has a total count equal to the median cell total before normalization. By specifying `1000000` the normalization become CPM normalization; `10000` is another common option for scRNA-seq data.",
                    "fa_icon": "fas fa-crosshairs"
                }
            }
        },

        "hvg_options": {
            "title": "Highly variable genes options",
            "type": "object",
            "fa_icon": "fas fa-arrow-trend-up",
            "description": "Options for calculating highly variable genes.",
            "properties": {
                "n_highly_variable_genes": {
                    "type": "integer",
                    "default": 2000,
                    "description": "The number of top highly variable genes to use for the analyses.",
                    "fa_icon": "fas fa-hashtag"
                },
                "hvg_flavor": {
                    "type": "string",
                    "default": "seurat",
                    "enum": ["seurat", "cell_ranger"],
                    "description": "The method for identifying highly variable genes",
                    "fa_icon": "fas fa-cookie-bite"
                }
            }
        },

        "pca_options": {
            "title": "Principal component analysis options",
            "type": "object",
            "fa_icon": "fas fa-uncharted",
            "description": "Options for principal component analyses used in the pipeline.",
            "properties": {
                "n_principal_components": {
                    "type": "integer",
                    "default": 50,
                    "description": "The number of principal components to use for downstream analyses.",
                    "fa_icon": "fas fa-hashtag"
                },
                "pca_use_highly_variable": {
                    "type": "boolean",
                    "description": "Whether to use highly variable genes only for principal component analyses.",
                    "fa_icon": "fas fa-arrow-trend-up"
                }
            }
        },

        "nearest_neighbors_options": {
            "title": "Nearest neighbors options",
            "type": "object",
            "fa_icon": "fas fa-square-share-nodes",
            "description": "Options for nearest neighbors calculations.",
            "properties": {
                "n_neighbors": {
                    "type": "integer",
                    "default": 15,
                    "description": "The number of nearest neighbors to use for the neighborhood graph calculation.",
                    "fa_icon": "fas fa-hashtag"
                },
                "neighbors_n_pcs": {
                    "type": "integer",
                    "default": 50,
                    "description": "The number of principal components to use for the nearest neighbors calculation.",
                    "fa_icon": "fas fa-hashtag"
                }
            }
        },

        "dimensionality_reduction_options": {
            "title": "Dimensionality reduction options",
            "type": "object",
            "fa_icon": "fas fa-down-left-and-up-right-to-center",
            "description": "Options for the dimensionality reductions performed by the pipeline.",
            "properties": {
                "umap_min_dist": {
                    "type": "number",
                    "default": 0.5,
                    "description": "Minimium distance between points in the UMAP embedding, where lower values produces tigher clusters.",
                    "fa_icon": "fas fa-hashtag"
                },
                "umap_spread": {
                    "type": "number",
                    "default": 1.0,
                    "description": "Scale of the UMAP embedding, where larger values spread points further away from each other.",
                    "fa_icon": "fas fa-hashtag"
                }
            }
        },

        "clustering_options": {
            "title": "Clustering options",
            "type": "object",
            "fa_icon": "fas fa-circle-nodes",
            "description": "Options for the clustering performed by the pipeline.",
            "properties": {
                "cluster_resolution": {
                    "type": "number",
                    "default": 1,
                    "description": "The resolution for the clustering of the spots.",
                    "help_text": "The resolution controls the coarseness of the clustering, where a higher resolution leads to more clusters.",
                    "fa_icon": "fas fa-hashtag"
                }
            }
        },

        "rank_genes_groups_options": {
            "title": "Rank genes groups options",
            "type": "object",
            "fa_icon": "fas fa-chart-gantt",
            "description": "Options for determinig spatially variable genes.",
            "properties": {
                "rank_genes_method": {
                    "type": "string",
                    "default": "wilcoxon",
                    "description": "Statistical method to use for differential expression testing.",
                    "enum": ["logreg", "t-test", "t-test_overestim_var", "wilcoxon"],
                    "fa_icon": "fas fa-tag"
                }
            }
        },

        "spatial_analysis_options": {
            "title": "Spatial analysis options",
            "type": "object",
            "fa_icon": "fas fa-circle-nodes",
            "description": "Options for the various spatial analyses performed by the pipeline.",
            "properties": {
                "spatial_coord_type": {
                    "type": "string",
                    "default": "grid",
                    "enum": ["generic", "grid"],
                    "description": "The coordinate type to use for spatial neighborhood enrichment.",
                    "fa_icon": "fas fa-tag"
                },
                "spatial_n_neighbors": {
                    "type": "integer",
                    "default": 6,
                    "description": "Number of neighborhoods to use for spatial neighborhood enrichment.",
                    "fa_icon": "fas fa-hashtag"
                },
                "svg_autocorr_method": {
                    "type": "string",
                    "default": "moran",
                    "enum": ["moran", "geary"],
                    "description": "The method to use for spatially variable gene autocorrelation.",
                    "fa_icon": "fas fa-tag"
                },
                "n_top_svgs": {
                    "type": "integer",
                    "default": 15,
                    "description": "The number of top spatially variable genes to plot.",
                    "fa_icon": "fas fa-hashtag"
                }
            }
        },

        "integration_options": {
            "title": "Integration options",
            "type": "object",
            "fa_icon": "fas fa-rocket",
            "description": "Options related to aggregation of final data objects",
            "properties": {
                "skip_integration": {
                    "type": "boolean",
                    "description": "Skip integration of per-sample objects into one and the associated report.",
                    "fa_icon": "fas fa-arrows-to-dot"
                },
                "integration_method": {
                    "type": "string",
                    "default": "harmony",
                    "enum": ["harmony", "scanorama"],
                    "description": "The integration method to use",
                    "fa_icon": "fas fa-tag"
                },
                "integration_cluster_resolution": {
                    "type": "number",
                    "default": 1,
                    "description": "The resolution for the clustering of the spots after integration of samples.",
                    "help_text": "The resolution controls the coarseness of the clustering, where a higher resolution leads to more clusters.",
                    "fa_icon": "fas fa-circle-nodes"
                }
            }
        },

        "optional_outputs": {
            "title": "Optional outputs",
            "type": "object",
            "fa_icon": "fas fa-floppy-disk",
            "description": "Additional intermediate output files that can be optionally saved.",
            "properties": {
                "spaceranger_save_reference": {
                    "type": "boolean",
                    "description": "Save the extracted tar archive of the Space Ranger reference.",
                    "help_text": "By default, extracted versions of archived Space Ranger reference data will not be saved to the results directory. Specify this flag (or set to true in your config file) to copy these files to the results directory when complete.",
                    "fa_icon": "fas fa-floppy-disk"
                },
                "save_untar_output": {
                    "type": "boolean",
                    "description": "Save extracted tar archives of input data.",
                    "help_text": "By default, extracted versions of archived input data will not be saved to the results directory. Specify this flag (or set to true in your config file) to copy these files to the results directory when complete.",
                    "fa_icon": "fas fa-floppy-disk"
                },
                "skip_downstream": {
                    "type": "boolean",
                    "description": "Skip downstream analyses.",
                    "help_text": "This option will only give Space Ranger outputs, a MultiQC report and a merged SpatialData object.",
                    "fa_icon": "fas fa-ban"
                }
            }
        },

        "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 colored log outputs.",
                    "fa_icon": "fas fa-palette",
                    "hidden": true
                },
                "hook_url": {
                    "type": "string",
                    "description": "Incoming hook URL for messaging service",
                    "fa_icon": "fas fa-people-group",
                    "help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
                    "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/spaceranger_options"
        },
        {
            "$ref": "#/$defs/visium_hd_options"
        },
        {
            "$ref": "#/$defs/filtering_options"
        },
        {
            "$ref": "#/$defs/normalization_options"
        },
        {
            "$ref": "#/$defs/hvg_options"
        },
        {
            "$ref": "#/$defs/pca_options"
        },
        {
            "$ref": "#/$defs/nearest_neighbors_options"
        },
        {
            "$ref": "#/$defs/dimensionality_reduction_options"
        },
        {
            "$ref": "#/$defs/clustering_options"
        },
        {
            "$ref": "#/$defs/rank_genes_groups_options"
        },
        {
            "$ref": "#/$defs/spatial_analysis_options"
        },
        {
            "$ref": "#/$defs/integration_options"
        },
        {
            "$ref": "#/$defs/optional_outputs"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        }
    ]
}