omic/digital-patients
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Initial commit: digital-patients pipeline (clean, no large files)

Browse Source 
Large reference/model files excluded from repo - to be staged to S3 or baked into Docker images.
This commit is contained in:
Olamide Isreal
2026-03-26 15:15:23 +01:00
commit 9e6a16c19b
45 changed files with 7207 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

325
params.json Normal file
View File

@@ -0,0 +1,325 @@
{
"params": {
"// SYNTHEA PARAMETERS": {},
"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]+$",
"validation": {
"min": 2
},
"notes": "Minimum of 2 patients required (one male, one female)"
},
"percent_male": {
"type": "number",
"description": "Percentage of male patients (between 0-1)",
"default": 0.5,
"required": true,
"pipeline_io": "parameter",
"var_name": "params.percent_male",
"examples": [0.0, 0.5, 1.0],
"pattern": "^0(\\.\\d+)?|1(\\.0)?$",
"validation": {
"min": 0.0,
"max": 1.0
},
"notes": "Value must be between 0 and 1 inclusive"
},
"imputed_store": {
"type": "folder",
"description": "Path to imputed UKBB data",
"default": "/mnt/Avatar/imputed/ukbb/imputed",
"required": true,
"pipeline_io": "input",
"var_name": "params.imputed_store",
"examples": [
"/mnt/Avatar/imputed/ukbb/imputed",
"/rosalind/ukbb/imputed"
],
"pattern": ".*",
"validation": {},
"notes": "Directory containing imputed UKBB data"
},
"pheno_store": {
"type": "file",
"description": "Path to phenotype data file",
"default": "/mnt/Avatar/dd/synthea/metadata/ukbb_phenotypes_filtered.csv",
"required": true,
"pipeline_io": "input",
"var_name": "params.pheno_store",
"examples": [
"/mnt/Avatar/dd/synthea/metadata/ukbb_phenotypes_filtered.csv"
],
"pattern": ".*\\.csv$",
"validation": {},
"notes": "CSV file containing filtered UKBB phenotype data"
},
"disease": {
"type": "string",
"description": "Disease or condition to simulate",
"default": "schizophrenia",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.disease",
"examples": [
"schizophrenia",
"healthy",
"leukaemia",
"Purpura and other haemorrhagic conditions"
],
"pattern": ".*",
"enum": [
"schizophrenia",
"healthy",
"leukaemia",
"Purpura and other haemorrhagic conditions"
],
"validation": {},
"notes": "Use 'healthy' for healthy individuals or specify a disease condition"
},
"healthy_dir": {
"type": "folder",
"description": "Path to healthy patient data directory",
"default": "/Workspace/next/registry/pipelines/digital_patient",
"required": true,
"pipeline_io": "input",
"var_name": "params.healthy_dir",
"examples": [
"/Workspace/next/registry/pipelines/digital_patient",
"/mnt/Avatar/digital_patient"
],
"pattern": ".*",
"validation": {},
"notes": "Directory containing data for healthy patient generation"
},
"outdir": {
"type": "folder",
"description": "Output directory for results",
"default": "/mnt/omic-next-apis/wes/digital_patients",
"required": true,
"pipeline_io": "output",
"var_name": "params.outdir",
"examples": [
"/mnt/OmicNAS/dd/digital_patient",
"/path/to/custom/output"
],
"pattern": ".*",
"validation": {},
"notes": "Directory where all pipeline results will be stored"
},
"// BORZOI PARAMETERS": {},
"container_borzoi": {
"type": "string",
"description": "Borzoi container image",
"default": "borzoi:latest",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.container_borzoi",
"examples": [
"borzoi:latest",
"borzoi:v1.0"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container image for Borzoi module"
},
"containerOptions": {
"type": "string",
"description": "Container runtime options",
"default": "--gpus all --rm -v /mnt:/mnt",
"required": false,
"pipeline_io": "parameter",
"var_name": "params.containerOptions",
"examples": [
"--gpus all --rm -v /mnt:/mnt",
"--rm -v /data:/data"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container runtime options for GPU usage and volume mounts"
},
"project_name": {
"type": "string",
"description": "Project identifier",
"default": "test",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.project_name",
"examples": [
"test",
"production",
"schizophrenia_study"
],
"pattern": ".*",
"validation": {},
"notes": "Identifier for the digital patient project"
},
"mane": {
"type": "file",
"description": "Path to MANE reference file",
"default": "/Workspace/next/registry/pipelines/digital_patient/MANE.GRCh38.v1.3.update.tsv",
"required": true,
"pipeline_io": "input",
"var_name": "params.mane",
"examples": [
"/Workspace/next/registry/pipelines/digital_patient/MANE.GRCh38.v1.3.update.tsv"
],
"pattern": ".*\\.tsv$",
"validation": {},
"notes": "MANE transcripts reference file in TSV format"
},
"// VCF2PROT PARAMETERS": {},
"container_vcf2prot": {
"type": "string",
"description": "VCF2PROT container image",
"default": "vcf2prot:latest",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.container_vcf2prot",
"examples": [
"vcf2prot:latest",
"vcf2prot:v1.0"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container image for VCF2PROT module"
},
"// RNA2PROTEINEXPRESSION PARAMETERS": {},
"container_rna2protexpression": {
"type": "string",
"description": "RNA2PROTEINEXPRESSION container image",
"default": "rna2protexpression:latest",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.container_rna2protexpression",
"examples": [
"rna2protexpression:latest",
"rna2protexpression:v1.0"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container image for RNA2PROTEINEXPRESSION module"
},
"containerOptions_rna2protexpression": {
"type": "string",
"description": "Container options for RNA2PROTEINEXPRESSION",
"default": "--gpus all --rm -v /mnt:/mnt -v /dbs:/dbs",
"required": false,
"pipeline_io": "parameter",
"var_name": "params.containerOptions_rna2protexpression",
"examples": [
"--gpus all --rm -v /mnt:/mnt -v /dbs:/dbs"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container runtime options for RNA2PROTEINEXPRESSION with GPU and database volume mounts"
},
"// CORTO PARAMETERS": {},
"container_corto": {
"type": "string",
"description": "CORTO container image",
"default": "corto:latest",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.container_corto",
"examples": [
"corto:latest",
"corto:v1.0"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container image for CORTO module"
},
"regulon": {
"type": "file",
"description": "Path to regulon RDA file",
"default": "/Workspace/next/registry/pipelines/digital_patient/regulon.rda",
"required": true,
"pipeline_io": "input",
"var_name": "params.regulon",
"examples": [
"/Workspace/next/registry/pipelines/digital_patient/regulon.rda"
],
"pattern": ".*\\.rda$",
"validation": {},
"notes": "Regulon data file in RDA format for CORTO module"
},
"// CIBERSORT PARAMETERS": {},
"cibersortx_username": {
"type": "string",
"description": "CIBERSORTx username for authentication",
"default": "gabriel.richman.2009@anderson.ucla.edu",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.cibersortx_username",
"examples": [
"gabriel.richman.2009@anderson.ucla.edu"
],
"pattern": "^[a-zA-Z0-9._%+-]+@[a-zA-Z0-9.-]+\\.[a-zA-Z]{2,}$",
"validation": {},
"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",
"examples": [
"b5b39e563fb947df4cfd4843d40fdb99"
],
"pattern": "^[a-f0-9]{32}$",
"validation": {},
"notes": "Authentication token for CIBERSORTx API access"
},
"container_ecotyper": {
"type": "string",
"description": "ECOTyper container image",
"default": "ecotyper:latest",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.container_ecotyper",
"examples": [
"ecotyper:latest",
"ecotyper:v1.0"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container image for ECOTyper module"
},
"signature_matrix": {
"type": "file",
"description": "Path to signature matrix file",
"default": "/Workspace/next/registry/pipelines/digital_patient/LM22_sourceGEP_ensg.txt",
"required": true,
"pipeline_io": "input",
"var_name": "params.signature_matrix",
"examples": [
"/Workspace/next/registry/pipelines/digital_patient/LM22_sourceGEP_ensg.txt"
],
"pattern": ".*\\.txt$",
"validation": {},
"notes": "Signature matrix file for CIBERSORTx analysis"
},
"ecotyper_outdir": {
"type": "folder",
"description": "Output directory for ECOTyper results",
"default": "/mnt/omic-next-apis/wes/digital-patients/ecotyper",
"required": true,
"pipeline_io": "output",
"var_name": "params.ecotyper_outdir",
"examples": [
"/mnt/OmicNAS/olamide/ecotyper/results/ecotyper"
],
"pattern": ".*",
"validation": {},
"notes": "Directory where ECOTyper results will be stored"
}
}
}