nextflow_schema.json

{
  "$schema": "http://json-schema.org/draft-07/schema",
  "$id": "https://raw.githubusercontent.com/pgscatalog/pgsc_calc/master/nextflow_schema.json",
  "title": "pgscatalog/pgsc_calc pipeline parameters",
  "description": "The Polygenic Score Catalog Calculator is a nextflow pipeline for polygenic score calculation",
  "type": "object",
  "definitions": {
    "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,
          "pattern": "^\\S+\\.(csv|json)$",
          "description": "Path to comma-separated file containing information about the samples in the experiment.",
          "help_text": "You will need to create a design file with information about the samples in your experiment before running the pipeline. Use this parameter to specify its location. It has to be a comma-separated file with 3 columns, and a header row.",
          "fa_icon": "fas fa-file-csv"
        },
        "outdir": {
          "type": "string",
          "format": "directory-path",
          "description": "The output directory where the results will be saved. You have to use absolute paths to storage on Cloud infrastructure.",
          "fa_icon": "fas fa-folder-open",
          "default": "results"
        },
        "email": {
          "type": "string",
          "description": "Email address for completion summary.",
          "fa_icon": "fas fa-envelope",
          "help_text": "Set this parameter to your e-mail address to get a summary e-mail with details of the run sent to you when the workflow exits. If set in your user config file (`~/.nextflow/config`) then you don't need to specify this on the command line for every run.",
          "pattern": "^([a-zA-Z0-9_\\-\\.]+)@([a-zA-Z0-9_\\-\\.]+)\\.([a-zA-Z]{2,5})$"
        },
        "format": {
          "type": "string",
          "default": "csv",
          "enum": ["csv", "json"],
          "description": "What format is the samplesheet in? (csv/json)"
        },
        "scorefile": {
          "type": "string",
          "description": "Path to a scoring file in PGS Catalog format. Multiple scorefiles can be specified using wildcards (e.g., ``--scorefile \\\"path/to/scores/*.txt\\\"``)"
        },
        "pgs_id": {
          "type": "string",
          "description": "A comma separated list of PGS score IDs, e.g. PGS000802",
          "pattern": "PGS[0-9]{6}"
        },
        "pgp_id": {
          "type": "string",
          "description": "A comma separated list of PGS Catalog publications, e.g. PGP000001",
          "pattern": "PGP[0-9]{6}"
        },
        "efo_id": {
          "type": "string",
          "description": "A comma separated list of PGS Catalog EFO traits, e.g. EFO_0004214"
        },
        "trait_efo": {
          "type": "string",
          "description": "DEPRECATED: A comma separated list of PGS Catalog EFO traits, e.g. EFO_0004214"
        },
        "efo_direct": {
          "type": "boolean",
          "description": "Return only PGS tagged with exact EFO term (e.g. no PGS for child/descendant terms in the ontology)"
        },
        "copy_genomes": {
          "type": "boolean",
          "description": "Copy harmonised genomes (plink2 pgen/pvar/psam files) to outdir"
        },
        "genotypes_cache": {
          "type": "string",
          "description": "Path to a directory that can store relabelled genotypes (and the reference panel intersections and PCA with --run_ancestry) to speed up new PGS calculations on previously harmonized samples",
          "format": "directory-path"
        }
      }
    },
    "compatibility_options": {
      "title": "Compatibility options",
      "type": "object",
      "description": "Define parameters that control how scoring files and target genomes are made compatible with each other",
      "default": "",
      "properties": {
        "target_build": {
          "type": "string",
          "description": "Genome build of target genomes",
          "enum": ["GRCh37", "GRCh38"]
        },
        "liftover": {
          "type": "boolean",
          "description": "Lift scoring files to match your target genomes. Requires build information in the header of the scoring files."
        },
        "min_lift": {
          "type": "number",
          "default": 0.95,
          "description": "Minimum proportion of variants required to successfully remap a scoring file to a different genome build.",
          "minimum": 0,
          "maximum": 1
        }
      },
      "required": ["target_build"]
    },
    "matching_options": {
      "title": "Matching options",
      "type": "object",
      "description": "Define how variants are matched across scoring files and target genomes.",
      "default": "",
      "properties": {
        "keep_multiallelic": {
          "type": "boolean",
          "description": "Allow matches of scoring file variants to multiallelic variants in the target dataset"
        },
        "keep_ambiguous": {
          "type": "boolean",
          "description": "Keep matches of scoring file variants to strand ambiguous variants (e.g. A/T and C/G SNPs) in the target dataset. This assumes the scoring file and target dataset report variants on the same strand."
        },
        "min_overlap": {
          "type": "number",
          "default": 0.75,
          "minimum": 0,
          "maximum": 1,
          "description": "Minimum proportion of variants present in both the score file and input target genomic data"
        }
      }
    },
    "genetic_ancestry_options": {
      "title": "Genetic ancestry options",
      "type": "object",
      "description": "Parameters used to control genetic ancestry similarity analysis on TARGET samples and variants included in PCA",
      "default": "",
      "properties": {
        "projection_method": {
          "type": "string",
          "default": "oadp",
          "description": "The method for PCA prediction. oadp: most accurate. adp: accurate but slow. sp: fast but inaccurate.",
          "enum": ["oadp", "sp", "adp"]
        },
        "ancestry_method": {
          "type": "string",
          "default": "RandomForest",
          "description": "Method used for population/ancestry assignment",
          "enum": ["Mahalanobis", "RandomForest"]
        },
        "ref_label": {
          "type": "string",
          "default": "SuperPop",
          "description": "Population labels in reference psam to use for assignment"
        },
        "n_popcomp": {
          "type": "integer",
          "default": 5,
          "description": "Number of PCs used for population assignment"
        },
        "normalization_method": {
          "type": "string",
          "default": "empirical mean mean+var",
          "enum": ["empirical", "mean", "mean+var", "empirical mean mean+var"],
          "description": "Method used for normalisation of genetic ancestry"
        },
        "n_normalization": {
          "type": "integer",
          "default": 4,
          "description": "Number of PCs used for population normalisation"
        },
        "load_afreq": {
          "type": "boolean",
          "default": true,
          "description": "Load allelic frequencies from reference panel when scoring target genomes"
        },
        "pca_maf_target": {
          "type": "number",
          "default": 0,
          "description": "Minimum MAF threshold in TARGET samples for variants to be included in the PCA.",
          "minimum": 0,
          "maximum": 1
        },
        "pca_geno_miss_target": {
          "type": "number",
          "default": 0.1,
          "description": "Maximum genotype missingness threshold in TARGET samples for variants to be included in the PCA.",
          "minimum": 0,
          "maximum": 1
        }
      },
      "required": [
        "projection_method",
        "ancestry_method",
        "ref_label",
        "n_popcomp",
        "normalization_method",
        "n_normalization",
        "load_afreq",
        "pca_maf_target",
        "pca_geno_miss_target"
      ]
    },
    "reference_options": {
      "title": "Reference options",
      "type": "object",
      "description": "Define how genomes and variants in REFERENCE panel are defined and processed for PCA",
      "default": "",
      "properties": {
        "run_ancestry": {
          "type": "string",
          "description": "Path to reference database. Must be set if --ref_samplesheet is not set.",
          "format": "file-path"
        },
        "ref_samplesheet": {
          "type": "string",
          "description": "Path to a samplesheet that describes the structure of reference data. Must be set if --ref isn't set.",
          "format": "file-path"
        },
        "hg19_chain": {
          "type": "string",
          "description": "Path to a UCSC chain file for converting from hg19 to hg38.  Needed if lifting over a custom scoring file.",
          "pattern": ".*chain.gz$",
          "format": "file-path",
          "mimetype": "application/gzip"
        },
        "hg38_chain": {
          "type": "string",
          "description": "Path to a UCSC chain file for converting from hg38 to hg19.  Needed if lifting over a custom scoring file.",
          "pattern": ".*chain.gz$",
          "format": "file-path",
          "mimetype": "application/gzip"
        },
        "geno_ref": {
          "type": "number",
          "default": 0.1,
          "description": "Exclude VARIANTS with percentage of missing genotype calls greater than a threshold (in reference genomes)",
          "minimum": 0,
          "maximum": 1
        },
        "mind_ref": {
          "type": "number",
          "default": 0.1,
          "minimum": 0,
          "maximum": 1,
          "description": "Exclude SAMPLES with percentage of missing genotype calls greater than a threshold (in reference genomes)"
        },
        "maf_ref": {
          "type": "number",
          "default": 0.05,
          "minimum": 0,
          "maximum": 1,
          "description": "Exclude variants with minor allele frequency (MAF) lower than a threshold (in reference genomes)"
        },
        "hwe_ref": {
          "type": "number",
          "default": 0.0001,
          "description": "Exclude variants with Hardy-Weinberg equilibrium exact test p-values below  a threshold (in reference genomes)",
          "minimum": 0,
          "maximum": 1
        },
        "indep_pairwise_ref": {
          "type": "string",
          "default": "1000 50 0.05",
          "description": "Used to generate a list of variants in approximate linkage equilibrium in reference genomes. Window size - step size - unphased hardcall r^2 threshold."
        },
        "ld_grch37": {
          "type": "string",
          "default": "/Users/bwingfield/Documents/projects/pgsc_calc/assets/ancestry/high-LD-regions-hg19-GRCh37.txt",
          "description": "Path to a file that contains areas of high linkage disequilibrium in the reference data (build GRCh37).",
          "format": "file-path",
          "mimetype": "text/plain"
        },
        "ld_grch38": {
          "type": "string",
          "default": "/Users/bwingfield/Documents/projects/pgsc_calc/assets/ancestry/high-LD-regions-hg38-GRCh38.txt",
          "description": "Path to a file that contains areas of high linkage disequilibrium in the reference data (build GRCh38).",
          "format": "file-path",
          "mimetype": "text/plain"
        },
        "ref_format_version": {
          "type": "string",
          "default": "v0.1",
          "description": "Version of the default reference database"
        },
        "ancestry_checksums": {
          "type": "string",
          "description": "Used to validate files in the reference database when built"
        }
      }
    },
    "developer_options": {
      "title": "Developer options",
      "type": "object",
      "description": "Control subworkflow execution, useful for debugging",
      "default": "",
      "properties": {
        "only_bootstrap": {
          "type": "boolean",
          "hidden": true
        },
        "only_input": {
          "type": "boolean",
          "hidden": true
        },
        "only_compatible": {
          "type": "boolean",
          "hidden": true
        },
        "only_match": {
          "type": "boolean",
          "hidden": true
        },
        "only_projection": {
          "type": "boolean",
          "hidden": true
        },
        "only_score": {
          "type": "boolean",
          "hidden": true
        },
        "skip_ancestry": {
          "type": "boolean",
          "default": true,
          "hidden": 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"
        }
      }
    },
    "max_job_request_options": {
      "title": "Max job request options",
      "type": "object",
      "fa_icon": "fab fa-acquisitions-incorporated",
      "description": "Set the top limit for requested resources for any single job.",
      "help_text": "If you are running on a smaller system, a pipeline step requesting more resources than are available may cause the Nextflow to stop the run with an error. These options allow you to cap the maximum resources requested by any single job so that the pipeline will run on your system.\n\nNote that you can not _increase_ the resources requested by any job using these options. For that you will need your own configuration file. See [the nf-core website](https://nf-co.re/usage/configuration) for details.",
      "properties": {
        "max_cpus": {
          "type": "integer",
          "description": "Maximum number of CPUs that can be requested for any single job.",
          "default": 16,
          "fa_icon": "fas fa-microchip",
          "hidden": true,
          "help_text": "Use to set an upper-limit for the CPU requirement for each process. Should be an integer e.g. `--max_cpus 1`"
        },
        "max_memory": {
          "type": "string",
          "description": "Maximum amount of memory that can be requested for any single job.",
          "default": "128.GB",
          "fa_icon": "fas fa-memory",
          "pattern": "^\\d+(\\.\\d+)?\\.?\\s*(K|M|G|T)?B$",
          "hidden": true,
          "help_text": "Use to set an upper-limit for the memory requirement for each process. Should be a string in the format integer-unit e.g. `--max_memory '8.GB'`"
        },
        "max_time": {
          "type": "string",
          "description": "Maximum amount of time that can be requested for any single job.",
          "default": "240.h",
          "fa_icon": "far fa-clock",
          "pattern": "^(\\d+\\.?\\s*(s|m|h|d|day)\\s*)+$",
          "hidden": true,
          "help_text": "Use to set an upper-limit for the time requirement for each process. Should be a string in the format integer-unit e.g. `--max_time '2.h'`"
        }
      }
    },
    "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": {
        "help": {
          "type": "boolean",
          "description": "Display help text.",
          "fa_icon": "fas fa-question-circle",
          "hidden": true
        },
        "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})$",
          "help_text": "An email address to send a summary email to when the pipeline is completed - ONLY sent if the pipeline does not exit successfully.",
          "hidden": true
        },
        "plaintext_email": {
          "type": "boolean",
          "description": "Send plain-text email instead of HTML.",
          "fa_icon": "fas fa-remove-format",
          "hidden": true
        },
        "monochrome_logs": {
          "type": "boolean",
          "description": "Do not use coloured log outputs.",
          "fa_icon": "fas fa-palette",
          "hidden": true
        },
        "hook_url": {
          "type": "string",
          "description": "Incoming hook URL for messaging service",
          "fa_icon": "fas fa-people-group",
          "help_text": "Incoming hook URL for messaging service. Currently, MS Teams and Slack are supported.",
          "hidden": true
        }
      }
    }
  },
  "allOf": [
    {
      "$ref": "#/definitions/input_output_options"
    },
    {
      "$ref": "#/definitions/compatibility_options"
    },
    {
      "$ref": "#/definitions/matching_options"
    },
    {
      "$ref": "#/definitions/genetic_ancestry_options"
    },
    {
      "$ref": "#/definitions/reference_options"
    },
    {
      "$ref": "#/definitions/developer_options"
    },
    {
      "$ref": "#/definitions/institutional_config_options"
    },
    {
      "$ref": "#/definitions/max_job_request_options"
    },
    {
      "$ref": "#/definitions/generic_options"
    }
  ]
}