Digital Trials pipeline configured for WES

Source-only snapshot of the cluster branch for WES execution. Large
reference files (HPA/MANE/ensemble FASTA, model weights, ~597 MB) are
omitted: they are baked into the container images at build time and
mounted from the dreamdock-data PVC at runtime, and exceed the Gitea
request size limit.

Pipeline entry point is main.nf, which orchestrates the biotransformer,
conplex and tissue modules as a single workflow. Ligand inputs are read
from the eureka workspace; protein_zarr and chembl_db come from the
dreamdock-data PVC.
This commit is contained in:
Olamide Isreal
2026-07-27 21:59:52 +01:00
commit 9e75f44f1a
86 changed files with 10142 additions and 0 deletions

192
params.json Normal file
View File

@@ -0,0 +1,192 @@
{
"params": {
"// GENERAL PARAMETERS": {},
"outdir": {
"type": "folder",
"description": "Output directory for results",
"default": "/mnt/OmicNAS/private/old/gabe/digital_trials",
"required": true,
"pipeline_io": "output",
"var_name": "params.outdir",
"examples": [
"/mnt/OmicNAS/private/old/gabe/digital_trials",
"/path/to/custom/output"
],
"pattern": ".*",
"validation": {},
"notes": "Directory where all pipeline results will be stored"
},
"project_name": {
"type": "string",
"description": "Project identifier",
"default": "test",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.project_name",
"examples": [
"test",
"production",
"drug_metabolism_study"
],
"pattern": ".*",
"validation": {},
"notes": "Identifier for the digital trials project"
},
"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"
},
"// BIOTRANSFORMER PARAMETERS": {},
"container_biotransformer": {
"type": "string",
"description": "BioTransformer container image",
"default": "biotransformer:latest",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.container_biotransformer",
"examples": [
"biotransformer:latest",
"biotransformer:v1.0"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container image for BioTransformer module"
},
"ligands": {
"type": "folder",
"description": "Path to input ligands directory",
"default": "/Workspace/next/registry/pipelines/digital_trials/input",
"required": true,
"pipeline_io": "input",
"var_name": "params.ligands",
"examples": [
"/Workspace/next/registry/pipelines/digital_trials/input",
"/path/to/ligands"
],
"pattern": ".*",
"validation": {},
"notes": "Directory containing CSV files with ligand data for metabolic transformation"
},
"mode": {
"type": "string",
"description": "BioTransformer operation mode",
"default": "HUMAN",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.mode",
"examples": [
"HUMAN",
"SUPER",
"MASS",
"ORDERED"
],
"pattern": "^(HUMAN|SUPER|MASS|ORDERED)$",
"enum": [
"HUMAN",
"SUPER",
"MASS",
"ORDERED"
],
"validation": {},
"notes": "IMPORTANT: Use HUMAN mode as it's the only fully implemented option that returns expected metabolism to the last step"
},
"// CONPLEX PARAMETERS": {},
"container_conplex": {
"type": "string",
"description": "CONPLEX container image",
"default": "conplex_dig_pat:latest",
"required": true,
"pipeline_io": "parameter",
"var_name": "params.container_conplex",
"examples": [
"conplex_dig_pat:latest",
"conplex_dig_pat:v1.0"
],
"pattern": ".*",
"validation": {},
"notes": "Docker container image for CONPLEX module"
},
"mutated_protein_fasta": {
"type": "folder",
"description": "Path to mutated protein FASTA files directory",
"default": "/Workspace/next/registry/pipelines/digital_trials/input",
"required": true,
"pipeline_io": "input",
"var_name": "params.mutated_protein_fasta",
"examples": [
"/Workspace/next/registry/pipelines/digital_trials/input",
"/path/to/protein/fasta/files"
],
"pattern": ".*",
"validation": {},
"notes": "Directory containing FASTA files with mutated protein sequences"
},
"threshold": {
"type": "number",
"description": "Binding affinity threshold for interactions",
"default": 0.7,
"required": false,
"pipeline_io": "parameter",
"var_name": "params.threshold",
"examples": [
0.5,
0.7,
0.9
],
"pattern": "^\\d+(\\.\\d+)?$",
"validation": {
"min": 0.0,
"max": 1.0
},
"notes": "Threshold value for determining significant binding interactions"
},
"screening_batch_size": {
"type": "integer",
"description": "Batch size for virtual screening",
"default": 100000,
"required": false,
"pipeline_io": "parameter",
"var_name": "params.screening_batch_size",
"examples": [
10000,
100000,
1000000
],
"pattern": "^\\d+$",
"validation": {
"min": 1
},
"notes": "Batch size for virtual screening (100k is ideal to optimize performance)"
},
"protein_network_threshold": {
"type": "number",
"description": "Threshold for protein network analysis",
"default": 0.95,
"required": false,
"pipeline_io": "parameter",
"var_name": "params.protein_network_threshold",
"examples": [
0.9,
0.95,
0.99
],
"pattern": "^\\d+(\\.\\d+)?$",
"validation": {
"min": 0.0,
"max": 1.0
},
"notes": "Threshold value for protein-protein interaction network construction"
}
}
}