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.
28 lines
1.0 KiB
Plaintext
28 lines
1.0 KiB
Plaintext
nextflow.enable.dsl=2
|
|
|
|
// STRING-only re-run workflow
|
|
// Feeds existing ConPLex significant_interactions files into NETWORK_ENRICHMENT
|
|
//
|
|
// Required params:
|
|
// interactions - directory containing *_significant_interactions.tsv files
|
|
// interaction_ids - comma-separated InChIKey prefixes to select (e.g. "PWKSKIMOESPYIA_SCSAIBSYSA_N,ZETLRLRYANUSAI_SCSAIBSYSA_N")
|
|
// if empty/not set, all files in the directory are used
|
|
|
|
params.protein_network_threshold = 0.65
|
|
|
|
include { NETWORK_ENRICHMENT } from './main_conplex.nf'
|
|
|
|
workflow {
|
|
if (params.interaction_ids) {
|
|
// Build a channel from the explicit list of IDs
|
|
ids = params.interaction_ids.tokenize(',')
|
|
interactions_ch = Channel
|
|
.fromList(ids)
|
|
.map { id -> file("${params.interactions}/${id}_patient_0_significant_interactions.tsv") }
|
|
} else {
|
|
interactions_ch = Channel.fromPath("${params.interactions}/*_significant_interactions.tsv")
|
|
}
|
|
|
|
NETWORK_ENRICHMENT(interactions_ch)
|
|
}
|