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

View File

@@ -0,0 +1,24 @@
#!/usr/bin/env nextflow
process METABOLITE_SCREEN {
memory '10 GB'
container "harbor.cluster.omic.ai/omic/metabolite-screen:adaptive"
// containerOptions "--rm --gpus all"
// errorStrategy 'ignore'
input:
path input_tsv // TSV file with the smiles
path input_zarr // ZARR DB holding all the protein vectors and their names
output:
path "*_result.tsv"
script:
"""
set -e
python /app/screen.py -i ${input_tsv} -z ${input_zarr}
"""
}