digital-patients/params.json

{
  "params": {
    "n_pat": {
      "type": "integer",
      "description": "Number of patients to generate (must be >= 2)",
      "default": 2,
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.n_pat",
      "examples": [2, 10, 100],
      "pattern": "^[0-9]+$",
      "validation": { "min": 2 },
      "notes": "Minimum of 2 patients required (one male, one female)"
    },
    "percent_male": {
      "type": "number",
      "description": "Percentage of male patients (between 0-1)",
      "default": 0.5,
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.percent_male",
      "examples": [0.0, 0.5, 1.0],
      "validation": { "min": 0.0, "max": 1.0 },
      "notes": "Value must be between 0 and 1 inclusive"
    },
    "disease": {
      "type": "string",
      "description": "Disease or condition to simulate",
      "default": "schizophrenia",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.disease",
      "examples": ["schizophrenia", "healthy", "leukaemia"],
      "enum": ["schizophrenia", "healthy", "leukaemia", "Purpura and other haemorrhagic conditions"],
      "notes": "Use 'healthy' for healthy individuals or specify a disease condition"
    },
    "project_name": {
      "type": "string",
      "description": "Project identifier",
      "default": "test",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.project_name",
      "examples": ["test", "production", "schizophrenia_study"]
    },
    "imputed_store": {
      "type": "folder",
      "description": "Path to imputed UKBB data directory",
      "default": "/omic/eureka/digital-patients/imputed",
      "required": true,
      "pipeline_io": "input",
      "var_name": "params.imputed_store",
      "examples": ["/omic/eureka/digital-patients/imputed"],
      "notes": "Directory containing imputed UKBB GWAS .bgz files"
    },
    "pheno_store": {
      "type": "file",
      "description": "Path to phenotype data file",
      "default": "/omic/eureka/digital-patients/ukbb_phenotypes_filtered.csv",
      "required": true,
      "pipeline_io": "input",
      "var_name": "params.pheno_store",
      "examples": ["/omic/eureka/digital-patients/ukbb_phenotypes_filtered.csv"],
      "pattern": ".*\\.csv$",
      "notes": "CSV file containing filtered UKBB phenotype data"
    },
    "healthy_dir": {
      "type": "folder",
      "description": "Path to healthy patient data directory (gnomad files)",
      "default": "/omic/eureka/digital-patients/healthy",
      "required": true,
      "pipeline_io": "input",
      "var_name": "params.healthy_dir",
      "examples": ["/omic/eureka/digital-patients/healthy"],
      "notes": "Directory containing gnomad.genomes.v4.1.sites.{male,female}.txt"
    },
    "synthea_support_dir": {
      "type": "folder",
      "description": "Path to Synthea supporting data (VCF templates, liftover, genome)",
      "default": "/omic/eureka/digital-patients/supporting-data",
      "required": true,
      "pipeline_io": "input",
      "var_name": "params.synthea_support_dir",
      "examples": ["/omic/eureka/digital-patients/supporting-data"],
      "notes": "Must contain vcf/vcf_template.vcf, ucsc-liftover/hg19ToHg38.over.chain.gz, genome/hg38.fa"
    },
    "mane": {
      "type": "file",
      "description": "Path to MANE reference file",
      "default": "/omic/eureka/digital-patients/MANE.GRCh38.v1.3.update.tsv",
      "required": true,
      "pipeline_io": "input",
      "var_name": "params.mane",
      "examples": ["/omic/eureka/digital-patients/MANE.GRCh38.v1.3.update.tsv"],
      "pattern": ".*\\.tsv$",
      "notes": "MANE transcripts reference file in TSV format"
    },
    "regulon": {
      "type": "file",
      "description": "Path to regulon RDA file",
      "default": "/omic/eureka/digital-patients/regulon.rda",
      "required": true,
      "pipeline_io": "input",
      "var_name": "params.regulon",
      "examples": ["/omic/eureka/digital-patients/regulon.rda"],
      "pattern": ".*\\.rda$",
      "notes": "Regulon data file in RDA format for CORTO module"
    },
    "signature_matrix": {
      "type": "file",
      "description": "Path to signature matrix file for CIBERSORTx",
      "default": "/omic/eureka/digital-patients/LM22_sourceGEP_ensg.txt",
      "required": true,
      "pipeline_io": "input",
      "var_name": "params.signature_matrix",
      "examples": ["/omic/eureka/digital-patients/LM22_sourceGEP_ensg.txt"],
      "pattern": ".*\\.txt$",
      "notes": "Signature matrix file for CIBERSORTx analysis"
    },
    "outdir": {
      "type": "folder",
      "description": "Output directory for results",
      "default": "/omic/eureka/digital-patients/output",
      "required": true,
      "pipeline_io": "output",
      "var_name": "params.outdir",
      "examples": ["/omic/eureka/digital-patients/output"],
      "notes": "Directory where all pipeline results will be stored"
    },
    "cibersortx_username": {
      "type": "string",
      "description": "CIBERSORTx username for authentication",
      "default": "gabriel.richman.2009@anderson.ucla.edu",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.cibersortx_username",
      "notes": "Username (email) for CIBERSORTx authentication"
    },
    "cibersortx_token": {
      "type": "string",
      "description": "CIBERSORTx authentication token",
      "default": "b5b39e563fb947df4cfd4843d40fdb99",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.cibersortx_token",
      "notes": "Authentication token for CIBERSORTx API access"
    },
    "container_borzoi": {
      "type": "string",
      "description": "Borzoi container image",
      "default": "harbor.cluster.omic.ai/omic/digital-patients/borzoi:latest",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.container_borzoi"
    },
    "container_vcf2prot": {
      "type": "string",
      "description": "VCF2PROT container image",
      "default": "harbor.cluster.omic.ai/omic/digital-patients/vcf2prot:latest",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.container_vcf2prot"
    },
    "container_rna2protexpression": {
      "type": "string",
      "description": "RNA2PROTEINEXPRESSION container image",
      "default": "harbor.cluster.omic.ai/omic/digital-patients/rna2protexpression:latest",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.container_rna2protexpression"
    },
    "container_corto": {
      "type": "string",
      "description": "CORTO container image",
      "default": "harbor.cluster.omic.ai/omic/digital-patients/corto:latest",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.container_corto"
    },
    "container_ecotyper": {
      "type": "string",
      "description": "ECOTyper/CIBERSORTx container image",
      "default": "harbor.cluster.omic.ai/omic/digital-patients/ecotyper:latest",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.container_ecotyper"
    },
    "container_synthea": {
      "type": "string",
      "description": "Synthea container image",
      "default": "harbor.cluster.omic.ai/omic/digital-patients/synthea:cudf",
      "required": true,
      "pipeline_io": "parameter",
      "var_name": "params.container_synthea"
    }
  }
}