nextflow_schema.json

{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/openscpca-nf/main/nextflow_schema.json",
  "title": "openscpca-nf pipeline parameters",
  "description": "A workflow to run modules from the OpenScPCA project.",
  "type": "object",
  "$defs": {
    "input_and_output_locations": {
      "title": "Input and Output Locations",
      "type": "object",
      "description": "",
      "default": "",
      "properties": {
        "workflow": {
          "type": "string",
          "default": "default",
          "options": ["default", "test", "simulate"],
          "description": "Workflow to run, either 'default' for the standard workflow, 'test' for a workflow with parameters set for testing, or 'simulate' to run the workflow on simulated data. Default is 'default'."
        },
        "release_bucket": {
          "type": "string",
          "default": "s3://openscpca-data-release",
          "format": "directory-path",
          "description": "Base URI for input data from OpenScPCA",
          "help_text": "Standard configurations will use an S3 bucket, but local paths can also be used."
        },
        "release_prefix": {
          "type": "string",
          "default": "2025-06-30",
          "format": "directory-path",
          "description": "Prefix for the specific release used as input"
        },
        "results_bucket": {
          "type": "string",
          "default": "s3://openscpca-nf-workflow-results-staging",
          "description": "Base URI for results output",
          "help_text": "Standard configurations will use an S3 bucket, but local paths can also be used."
        },
        "sim_bucket": {
          "type": "string",
          "default": "s3://openscpca-test-data-release-staging",
          "description": "Base URI for simulated data output",
          "help_text": "Standard configurations will use an S3 bucket, but local paths can also be used."
        },
        "annotations_bucket": {
          "type": "string",
          "default": "s3://openscpca-celltype-annotations-public-access",
          "description": "Base URI for saving cell type annotations output",
          "help_text": "Standard configurations will use an S3 bucket, but local paths can also be used."
        },
        "project": {
          "type": "string",
          "default": "all",
          "description": "Projects that will be used in the workflow run",
          "help_text": "Default is to run all projects. To run a single project or specified projects, include them as a list of SCPCP ids, separated by commas, semicolons, or spaces.",
          "pattern": "^[aA][lL][lL]$|^(SCPCP\\d{6}([,; ]+|$))+$"
        },
        "gtf_file": {
          "type": "string",
          "default": "s3://scpca-nf-references/homo_sapiens/ensembl-104/annotation/Homo_sapiens.GRCh38.104.gtf.gz",
          "description": "Path or URI to GTF file corresponding to reference genome build used with scpca-nf"
        },
        "cytoband_file": {
          "type": "string",
          "default": "ftp://hgdownload.cse.ucsc.edu/goldenPath/hg38/database/cytoBand.txt.gz",
          "description": "Path or URI to cytoband file corresponding to reference genome build used with scpca-nf"
        }
      }
    },
    "containers": {
      "title": "Containers",
      "type": "object",
      "description": "Locations for Docker images used by workflow processes",
      "default": "",
      "properties": {
        "pullthrough_registry": {
          "type": "string",
          "description": "address of docker pull-through registry, if using",
          "help_text": "If using a pull-through registry, this is the address that will be used as prefix, i.e., '<account_id>.dkr.ecr.<region>.amazonaws.com'."
        },
        "python_container": {
          "type": "string",
          "default": "docker.io/library/python:3.11"
        },
        "scpcatools_slim_container": {
          "type": "string",
          "default": "ghcr.io/alexslemonade/scpcatools-slim:v0.4.3"
        },
        "scpcatools_reports_container": {
          "type": "string",
          "default": "ghcr.io/alexslemonade/scpcatools-reports:v0.4.3"
        },
        "scpcatools_anndata_container": {
          "type": "string",
          "default": "ghcr.io/alexslemonade/scpcatools-anndata:v0.4.3"
        },
        "simulate_sce_container": {
          "type": "string",
          "default": "public.ecr.aws/openscpca/simulate-sce:v0.2.4"
        },
        "doublet_detection_container": {
          "type": "string",
          "default": "public.ecr.aws/openscpca/doublet-detection:v0.2.4",
          "description": "Docker container for the doublet-detection module to run in"
        },
        "seurat_conversion_container": {
          "type": "string",
          "default": "public.ecr.aws/openscpca/seurat-conversion:v0.2.4",
          "description": "Docker container for the seurat-conversion module to run in"
        },
        "consensus_cell_type_container": {
          "type": "string",
          "default": "public.ecr.aws/openscpca/cell-type-consensus:v0.2.4",
          "description": "Docker container for the cell-type-consensus module to run in"
        },
        "cell_type_ewing_container": {
          "type": "string",
          "default": "public.ecr.aws/openscpca/cell-type-ewings:v0.2.4",
          "description": "Docker container for the cell-type-ewings module to run in"
        },
        "cell_type_nb_04_container": {
          "type": "string",
          "default": "public.ecr.aws/openscpca/cell-type-neuroblastoma-04:v0.2.4"
        },
        "cell_type_scimilarity_container": {
          "type": "string",
          "default": "public.ecr.aws/openscpca/cell-type-scimilarity:v0.2.4"
        }
      }
    },
    "module_specific_parameters": {
      "title": "Module-specific parameters",
      "type": "object",
      "description": "Parameters used by individual modules",
      "default": "",
      "properties": {
        "merge_reuse": {
          "type": "boolean",
          "description": "Whether to reuse previous merge data output"
        },
        "merge_max_libraries": {
          "type": "integer",
          "default": 75,
          "description": "Maximum number of libraries to merge into a single object"
        },
        "merge_hvg": {
          "type": "integer",
          "default": 2000,
          "description": "Number of highly variable genes to use when performing dimensionality reduction on merged objects"
        },
        "cell_type_blueprint_ref_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-consensus/references/blueprint-mapped-ontologies.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "BlueprintEncodeData cell type reference file"
        },
        "cell_type_panglao_ref_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-consensus/references/panglao-cell-type-ontologies.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "PanglaoDB cell type reference file"
        },
        "cell_type_consensus_ref_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-consensus/references/consensus-cell-type-reference.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "Consensus cell types reference file"
        },
        "cell_type_consensus_validation_marker_genes_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-consensus/references/validation-markers.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "Table of marker genes for validation groups used to validate consensus cell types"
        },
        "cell_type_consensus_all_marker_genes_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-consensus/references/consensus-markers.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "Table of marker genes for all consensus cell types"
        },
        "cell_type_ewings_auc_max_rank": {
          "type": "integer",
          "default": 425,
          "description": "Number of detected genes to use as the threshold for the max AUC rank when running AUCell"
        },
        "cell_type_ewings_msigdb_list": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-ewings/references/msigdb-gene-sets.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "Table of MSigDB gene sets"
        },
        "cell_type_ewings_ews_high_list": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-ewings/references/gene_signatures/aynaud-ews-targets.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "Table with custom gene set expressed in EWS-FLI1 high tumor cells"
        },
        "cell_type_ewings_ews_low_list": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-ewings/references/gene_signatures/wrenn-nt5e-genes.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "Table with custom gene set expressed in EWS-FLI1 low tumor cells"
        },
        "cell_type_ewings_marker_gene_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-ewings/references/tumor-cell-state-markers.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "Table with custom gene sets specific to Ewing sarcoma tumor cells"
        },
        "cell_type_ewings_auc_thresholds_file": {
          "type": "string",
          "default": "${projectDir}/modules/cell-type-ewings/resources/auc-thresholds.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "Table with AUC thresholds to use for each gene set to define cell states"
        },
        "cell_type_scimilarity_model": {
          "type": "string",
          "default": "s3://scpca-references/celltype/scimilarity_references/model_v1.1",
          "format": "directory-path",
          "description": "URI to SCimilarity model"
        },
        "cell_type_scimilarity_ontology_ref_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-scimilarity/references/scimilarity-mapped-ontologies.tsv",
          "pattern": "\\.tsv$",
          "format": "file-path",
          "mimetype": "text/tab-separated-values",
          "description": "TSV file with SCimilarity annotation labels and associated cell ontology identifiers"
        },
        "cell_type_nb_04_scanvi_pp_threshold": {
          "type": "number",
          "default": 0.75,
          "description": "Posterior probability threshold for annotating cells with scANVI/scArches"
        },
        "cell_type_nb_04_label_map_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-neuroblastoma-04/references/nbatlas-label-map.tsv",
          "description": "Path or URL to TSV mapping NBAtlas labels across levels of organization"
        },
        "cell_type_nb_04_validation_group_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-consensus/references/consensus-validation-groups.tsv",
          "description": "Path or URL to TSV mapping consensus cell types to broad validation groups"
        },
        "cell_type_nb_04_ontology_map_file": {
          "type": "string",
          "default": "https://raw.githubusercontent.com/AlexsLemonade/OpenScPCA-analysis/refs/tags/v0.2.4/analyses/cell-type-neuroblastoma-04/references/nbatlas-ontology-ids.tsv",
          "description": "Path or URL to TSV mapping NBAtlas labels to ontology ids"
        },
        "cell_type_nb_04_nbatlas_url": {
          "type": "string",
          "default": "https://data.mendeley.com/public-files/datasets/yhcf6787yp/files/f5969395-5f6e-4c5d-a61a-5894773d0fee/file_downloaded",
          "description": "Path or URL to the released NBAtlas object"
        }
      }
    }
  },
  "allOf": [
    {
      "$ref": "#/$defs/input_and_output_locations"
    },
    {
      "$ref": "#/$defs/containers"
    },
    {
      "$ref": "#/$defs/module_specific_parameters"
    }
  ]
}