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.
18 lines
579 B
Plaintext
18 lines
579 B
Plaintext
#!/usr/bin/env nextflow
|
|
|
|
// params.input_tsv = '../sample/in-molecule/test_known_drugs.tsv' //metabolites.tsv'
|
|
params.input_tsv = '../sample/in-molecule/metabolites-rev.tsv' //metabolites.tsv'
|
|
params.input_zarr = '../data/protein_seq.zarr' //mane_all.zarr'
|
|
|
|
// Include the buildFaissIndex workflow from main.nf
|
|
include { METABOLITE_SCREEN } from './main.nf'
|
|
|
|
workflow {
|
|
|
|
input_tsv = file(params.input_tsv)
|
|
input_zarr = file(params.input_zarr)
|
|
|
|
// Call the combined workflow with both inputs
|
|
protein_scores = METABOLITE_SCREEN(input_tsv, input_zarr)
|
|
}
|