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.
25 lines
515 B
Plaintext
25 lines
515 B
Plaintext
#!/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}
|
|
"""
|
|
}
|