nextflow_schema.json

{
    "$schema": "https://json-schema.org/draft/2020-12/schema",
    "$id": "https://raw.githubusercontent.com/nf-core/sopa/master/nextflow_schema.json",
    "title": "nf-core/sopa pipeline parameters",
    "description": "Technology-invariant pipeline for spatial omics analysis that scales to millions of cells",
    "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. See [usage docs](https://nf-co.re/sopa/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})$"
                }
            }
        },
        "spaceranger_options": {
            "title": "Space Ranger options",
            "type": "object",
            "fa_icon": "fas fa-rocket",
            "description": "Options related to Space Ranger execution and raw spatial data processing",
            "properties": {
                "spaceranger_probeset": {
                    "type": "string",
                    "format": "file-path",
                    "mimetype": "text/csv",
                    "pattern": "^\\S+\\.csv$",
                    "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 downladed 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
                }
            }
        },
        "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
                },
                "monochrome_logs": {
                    "type": "boolean",
                    "description": "Do not use coloured 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
                },
                "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)."
                }
            }
        },
        "reader": {
            "title": "Reader",
            "type": "object",
            "description": "Parameters related to the SpatialData reader",
            "default": "",
            "properties": {
                "technology": {
                    "type": "string",
                    "description": "Technology used for the spatial data, e.g., 'xenium', 'merscope', ...",
                    "enum": [
                        "xenium",
                        "merscope",
                        "cosmx",
                        "visium_hd",
                        "molecular_cartography",
                        "macsima",
                        "phenocycler",
                        "hyperion",
                        "ome_tif",
                        "toy_dataset"
                    ],
                    "default": "xenium"
                },
                "visium_hd_imread_page": {
                    "type": "number",
                    "description": "Optional page for the imageio reader"
                }
            },
            "required": ["technology"],
            "fa_icon": "fas fa-arrows-alt-h"
        },
        "patches": {
            "title": "Patches",
            "type": "object",
            "description": "Creation of the image and transcript patches before segmentation",
            "default": "",
            "properties": {
                "patch_width_pixel": {
                    "type": "number",
                    "description": "Width (and height) of each patch in pixels"
                },
                "patch_overlap_pixel": {
                    "type": "number",
                    "description": "Number of overlapping pixels between the patches. We advise to choose approximately twice the diameter of a cell"
                },
                "patch_width_microns": {
                    "type": "number",
                    "description": "Width (and height) of each patch in microns"
                },
                "patch_overlap_microns": {
                    "type": "number",
                    "description": "Number of overlapping microns between the patches. We advise to choose approximately twice the diameter of a cell"
                },
                "prior_shapes_key": {
                    "type": "string",
                    "description": "Optional name of the boundaries element to use as a segmentation prior. Either a column name for the transcript dataframe, or a key of `sdata` containing the shapes names. If combining cellpose with proseg/baysor/comseg, it will be set automatically to `'cellpose_boundaries'`."
                },
                "unassigned_value": {
                    "type": "string",
                    "description": "If `prior_shapes_key` is provided, this is the value given to transcripts that are not inside any cell (if it's already 0, don't provide this argument)"
                }
            },
            "fa_icon": "far fa-square"
        },
        "tissue_segmentation": {
            "title": "Tissue segmentation",
            "type": "object",
            "description": "Parameters related to the tissue segmentation",
            "default": "",
            "properties": {
                "use_tissue_segmentation": {
                    "type": "boolean",
                    "description": "Whether to run tissue segmentation"
                },
                "level": {
                    "type": "number",
                    "description": "Level of the image pyramid to use for tissue segmentation"
                },
                "mode": {
                    "type": "string",
                    "description": "Mode for the tissue segmentation: 'staining' or 'saturation' (for H&E images).",
                    "enum": ["staining", "saturation"]
                },
                "tissue_segmentation_kwargs": {
                    "type": "string",
                    "description": "Additional tissue segmentation parameters as a python dict string"
                }
            },
            "fa_icon": "fab fa-bitbucket"
        },
        "filtering": {
            "title": "Cell filtering",
            "type": "object",
            "description": "Filtering low-quality cells during and after segmentation",
            "default": "",
            "properties": {
                "min_area_pixels2": {
                    "type": "number",
                    "description": "Cells with an area less than this value will be filtered. The unit is in pixels^2, and used by Stardist/Cellpose.",
                    "default": 0.0
                },
                "min_area_microns2": {
                    "type": "number",
                    "description": "Cells with an area less than this value will be filtered. The unit is in microns^2, and used by Baysor/Comseg. Not used by Proseg.",
                    "default": 0.0
                },
                "min_transcripts": {
                    "type": "number",
                    "description": "Cells with less transcripts than this value will be filtered."
                },
                "min_intensity_ratio": {
                    "type": "number",
                    "description": "Cells whose mean channel intensity is less than `min_intensity_ratio * quantile_90` will be filtered."
                }
            },
            "fa_icon": "fas fa-filter"
        },
        "aggregation": {
            "title": "Aggregation",
            "type": "object",
            "description": "Aggregation of genes and channels inside each cell",
            "default": "",
            "properties": {
                "aggregate_genes": {
                    "type": "boolean",
                    "description": "Whether to aggregate the genes (counts) inside each cell"
                },
                "aggregate_channels": {
                    "type": "boolean",
                    "description": "Whether to aggregate the channels (intensity) inside each cell"
                },
                "expand_radius_ratio": {
                    "type": "string",
                    "description": "Cells polygons will be expanded by `expand_radius_ratio * mean_radius` for channels averaging **only**. This help better aggregate boundary stainings"
                }
            },
            "fa_icon": "fas fa-calculator"
        },
        "scanpy_preprocessing": {
            "title": "Scanpy preprocessing",
            "type": "object",
            "description": "Optional scanpy table preprocessing (log1p, UMAP, leiden clustering) after aggregation/annotation.",
            "default": "",
            "properties": {
                "use_scanpy_preprocessing": {
                    "type": "boolean",
                    "description": "Whether to run scanpy preprocessing"
                },
                "resolution": {
                    "type": "number",
                    "description": "Resolution parameter for the leiden clustering"
                },
                "check_counts": {
                    "type": "boolean",
                    "description": "Whether to check that adata.X contains counts"
                },
                "hvg": {
                    "type": "boolean",
                    "description": "Whether to compute highly variable genes before computing the UMAP and clustering"
                }
            },
            "fa_icon": "fas fa-tools"
        },
        "explorer": {
            "title": "Explorer",
            "type": "object",
            "description": "Parameters related to the Xenium Explorer visualization tool",
            "default": "",
            "properties": {
                "pixel_size": {
                    "type": "number",
                    "default": 0.2125,
                    "description": "Number of microns in a pixel. Invalid value can lead to inconsistent scales in the Explorer."
                },
                "lazy": {
                    "type": "boolean",
                    "default": true,
                    "description": "If `True`, will not load the full images in memory (except if the image memory is below `ram_threshold_gb`)"
                },
                "ram_threshold_gb": {
                    "type": "number",
                    "description": "Threshold (in gygabytes) from which image can be loaded in memory.",
                    "default": 4.0
                }
            },
            "fa_icon": "fas fa-tools"
        },
        "image_preprocessing": {
            "title": "Image preprocessing",
            "type": "object",
            "description": "Image preprocessing applied before channel-based segmentation methods (cellpose, stardist)",
            "default": "",
            "properties": {
                "gaussian_sigma": {
                    "type": "number",
                    "description": "Parameter for scipy gaussian_filter (applied before running the segmentation method)"
                },
                "clip_limit": {
                    "type": "number",
                    "description": "Parameter for skimage.exposure.equalize_adapthist (applied before running the segmentation method)"
                },
                "clahe_kernel_size": {
                    "type": "number",
                    "description": "Parameter for skimage.exposure.equalize_adapthist (applied before running the segmentation method)"
                }
            },
            "fa_icon": "fas fa-file-image"
        },
        "proseg": {
            "title": "Proseg",
            "type": "object",
            "description": "Parameters related to the proseg segmentation method",
            "default": "",
            "properties": {
                "use_proseg": {
                    "type": "boolean",
                    "description": "Whether to run proseg segmentation"
                },
                "command_line_suffix": {
                    "type": "string",
                    "description": "String suffix to add to the proseg command line. This can be used to add extra parameters to the proseg command line."
                },
                "infer_presets": {
                    "type": "boolean",
                    "description": "Whether to infer the proseg presets based on the columns of the transcripts dataframe."
                },
                "visium_hd_prior_shapes_key": {
                    "type": "string",
                    "description": "**Only for Visium HD data.** Key of `sdata` containing the prior cell boundaries. If `'auto'`, use the latest performed segmentation (e.g., stardist or the 10X Genomics segmentation). If combining stardist with proseg, it will be set automatically to `'stardist_boundaries'`."
                }
            },
            "fa_icon": "fas fa-tools"
        },
        "comseg": {
            "title": "Comseg",
            "type": "object",
            "description": "Parameters related to the comseg segmentation method",
            "default": "",
            "properties": {
                "use_comseg": {
                    "type": "boolean",
                    "description": "Whether to run comseg segmentation"
                },
                "mean_cell_diameter": {
                    "type": "number",
                    "description": "Comseg `mean_cell_diameter` parameter",
                    "default": 10.0
                },
                "max_cell_radius": {
                    "type": "number",
                    "description": "Comseg `max_cell_radius` parameter",
                    "default": 15.0
                },
                "alpha": {
                    "type": "number",
                    "description": "Comseg `alpha` parameter",
                    "default": 0.5
                },
                "min_rna_per_cell": {
                    "type": "number",
                    "description": "Comseg `min_rna_per_cell` parameter",
                    "default": 1.0
                },
                "allow_disconnected_polygon": {
                    "type": "boolean",
                    "description": "Comseg `allow_disconnected_polygon` parameter"
                },
                "norm_vector": {
                    "type": "boolean",
                    "description": "Comseg `norm_vector` parameter"
                }
            },
            "fa_icon": "fas fa-tools"
        },
        "baysor": {
            "title": "Baysor",
            "type": "object",
            "description": "Parameters related to the baysor segmentation method",
            "default": "",
            "properties": {
                "use_baysor": {
                    "type": "boolean",
                    "description": "Whether to run baysor segmentation"
                },
                "baysor_scale": {
                    "type": "number",
                    "description": "Baysor `scale` parameter",
                    "default": -1.0
                },
                "baysor_scale_std": {
                    "type": "string",
                    "description": "Baysor `scale_std` parameter",
                    "default": "25%"
                },
                "prior_segmentation_confidence": {
                    "type": "number",
                    "description": "Baysor `prior_segmentation_confidence` parameter",
                    "default": 0.2
                },
                "min_molecules_per_cell": {
                    "type": "number",
                    "description": "Baysor `min_molecules_per_cell` parameter",
                    "default": 20.0
                },
                "min_molecules_per_gene": {
                    "type": "number",
                    "description": "Baysor `min_molecules_per_gene` parameter",
                    "default": 10.0
                },
                "min_molecules_per_segment": {
                    "type": "number",
                    "description": "Baysor `min_molecules_per_segment` parameter"
                },
                "confidence_nn_id": {
                    "type": "number",
                    "description": "Baysor `confidence_nn_id` parameter"
                },
                "force_2d": {
                    "type": "boolean",
                    "description": "Baysor `force_2d` parameter",
                    "default": true
                }
            },
            "fa_icon": "fas fa-tools"
        },
        "cellpose": {
            "title": "Cellpose",
            "type": "object",
            "description": "Parameters related to the cellpose segmentation method",
            "default": "",
            "properties": {
                "use_cellpose": {
                    "type": "boolean",
                    "description": "Whether to run cellpose segmentation"
                },
                "cellpose_diameter": {
                    "type": "number",
                    "description": "Cellpose `diameter` parameter"
                },
                "cellpose_channels": {
                    "type": "string",
                    "description": "Channel name(s) to use for cellpose segmentation. If multiple, separate by space, comma or pipe characters."
                },
                "flow_threshold": {
                    "type": "number",
                    "description": "Cellpose `flow_threshold` parameter"
                },
                "cellprob_threshold": {
                    "type": "number",
                    "description": "Cellpose `cellprob_threshold` parameter"
                },
                "cellpose_model_type": {
                    "type": "string",
                    "description": "Cellpose model type to use"
                },
                "pretrained_model": {
                    "type": "string",
                    "description": "Cellpose `pretrained_model` parameter"
                },
                "cellpose_use_gpu": {
                    "type": "boolean",
                    "description": "Whether to use GPU for Cellpose segmentation"
                },
                "cellpose_kwargs": {
                    "type": "string",
                    "description": "Additional cellpose parameters as a python dict string"
                }
            },
            "fa_icon": "fas fa-tools"
        },
        "stardist": {
            "title": "Stardist",
            "type": "object",
            "description": "Parameters related to the stardist segmentation method",
            "default": "",
            "properties": {
                "use_stardist": {
                    "type": "boolean",
                    "description": "Whether to run stardist segmentation"
                },
                "stardist_model_type": {
                    "type": "string",
                    "description": "Name of stardist model to use"
                },
                "prob_thresh": {
                    "type": "number",
                    "description": "Stardist `prob_thresh` parameter"
                },
                "nms_thresh": {
                    "type": "number",
                    "description": "Stardist `nms_thresh` parameter"
                },
                "stardist_channels": {
                    "type": "string",
                    "description": "Optional channel name(s) to use for stardist segmentation. If multiple, separate by space, comma or pipe characters."
                },
                "stardist_kwargs": {
                    "type": "string",
                    "description": "Additional stardist parameters as a python dict string"
                }
            },
            "fa_icon": "fas fa-tools"
        },
        "tangram": {
            "title": "Tangram",
            "type": "object",
            "description": "Parameters related to the tangram cell-type annotation method",
            "default": "",
            "properties": {
                "use_tangram": {
                    "type": "boolean",
                    "description": "Whether to run tangram cell-type annotation"
                },
                "sc_reference_path": {
                    "type": "string",
                    "description": "Path to the scRNAseq annotated reference, as a `.h5ad` file"
                },
                "tangram_cell_type_key": {
                    "type": "string",
                    "description": "Key of `adata_ref.obs` containing the cell-types"
                },
                "reference_preprocessing": {
                    "type": "string",
                    "description": "Preprocessing method applied to the reference. Either None (raw counts), or `normalized` (sc.pp.normalize_total) or `log1p` (sc.pp.normalize_total and sc.pp.log1p)"
                },
                "bag_size": {
                    "type": "number",
                    "description": "Number of cells in each bag of the spatial table. Low values will decrease the memory usage"
                },
                "max_obs_reference": {
                    "type": "number",
                    "description": "Maximum samples to be considered in the reference for tangram. Low values will decrease the memory usage"
                }
            },
            "fa_icon": "fas fa-scroll"
        },
        "fluorescence_annotation": {
            "title": "Fluorescence annotation",
            "type": "object",
            "description": "Parameters related to the fluorescence-based cell-type annotation method",
            "default": "",
            "properties": {
                "use_fluorescence_annotation": {
                    "type": "boolean",
                    "description": "Whether to run cell-type annotation based on a marker-to-cell dictionary"
                },
                "fluorescence_cell_type_key": {
                    "type": "string",
                    "description": "Key of `sdata.obs` containing the cell-types"
                },
                "marker_cell_dict": {
                    "type": "string",
                    "description": "Dictionary mapping whose keys are marker channel names and values are the cell types associated to each marker. Should be provided as a string representation of a python dictionary."
                }
            },
            "fa_icon": "fas fa-scroll"
        }
    },
    "allOf": [
        {
            "$ref": "#/$defs/input_output_options"
        },
        {
            "$ref": "#/$defs/spaceranger_options"
        },
        {
            "$ref": "#/$defs/institutional_config_options"
        },
        {
            "$ref": "#/$defs/generic_options"
        },
        {
            "$ref": "#/$defs/reader"
        },
        {
            "$ref": "#/$defs/patches"
        },
        {
            "$ref": "#/$defs/tissue_segmentation"
        },
        {
            "$ref": "#/$defs/filtering"
        },
        {
            "$ref": "#/$defs/aggregation"
        },
        {
            "$ref": "#/$defs/scanpy_preprocessing"
        },
        {
            "$ref": "#/$defs/explorer"
        },
        {
            "$ref": "#/$defs/image_preprocessing"
        },
        {
            "$ref": "#/$defs/proseg"
        },
        {
            "$ref": "#/$defs/comseg"
        },
        {
            "$ref": "#/$defs/baysor"
        },
        {
            "$ref": "#/$defs/cellpose"
        },
        {
            "$ref": "#/$defs/stardist"
        },
        {
            "$ref": "#/$defs/tangram"
        },
        {
            "$ref": "#/$defs/fluorescence_annotation"
        }
    ]
}