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.
2026-07-27 21:59:52 +01:00
commit 9e75f44f1a
86 changed files with 10142 additions and 0 deletions
--- a/nf_metabol_screen_adaptive/nextflow.config
+++ b/nf_metabol_screen_adaptive/nextflow.config
@@ -0,0 +1,113 @@
+// Nextflow configuration file
+
+// Execution report
+report {
+    enabled = true
+    file = "execution_report.html"
+    overwrite = true}
+
+
+// Resource usage tracking
+trace {
+    enabled = true
+    file = "execution_trace.txt"
+    overwrite = true
+}
+
+// Error reporting
+timeline {
+    enabled = true
+    file = "execution_timeline.html"
+    overwrite = true
+}
+
+// // Max resources
+// executor {
+//     $local {
+//         memory = '80 GB'
+//         cpus = 2
+//     }
+// }
+
+// Default parameters (overridden by test.nf)
+params {
+    // Set defaults here
+    // input = '/mnt/ZINC-22/conplex/total.zarr'
+    nshards = 12
+    outdir = "$launchDir"
+}
+
+profiles {
+  k8s {
+    process.executor = 'k8s'
+    process.namespace = 'bioinformatics'  
+    process.debug = true
+
+    workDir = "/workdir/work"
+
+    k8s {
+      serviceAccount = 'nextflow-sa'
+      namespace = 'bioinformatics'
+      storageClaimName = 'conplex-data'
+      storageMountPath = '/workdir'
+      
+      pullPolicy = 'IfNotPresent'
+      cleanup = true                    // delete pods after Ctrl+C or finished?
+      
+
+      // RUN AS DIFFERENT USERS
+      // securityContext = [fsGroup: 1000]
+      // securityContext = [
+      //   runAsUser: 1000,
+      //   fsGroup: 1000,
+      //   runAsNonRoot: true
+      // ]
+    }
+    
+    // Use container image
+    // process.container = 'harbor.cluster.omic.ai/omic/faiss-indexer:latest'
+
+    // Pod-level customization
+    process.pod = [
+      [env: 'NXF_DEBUG', value: '0'],
+      [label: 'omic-app', value: 'conplex'],
+      [imagePullSecret: 'gitlab-registry-secret'],
+      [volumeClaim: 'fingerprint-data', mountPath: '/fingerprint-data']
+      //[nodeSelector: [gpu: 'yes', 'kubernetes.io/hostname': 'k8s-node25']],
+      // [privileged: true],
+    ]
+
+    // process {
+    //   withName: 'trainIndex' {
+    //     container = 'harbor.cluster.omic.ai/omic/conplex-faiss-train:latest'
+    //     accelerator = 1
+    //     memory = '75 GB'
+    //     cpus = 1
+        
+    //     // GPU-specific pod settings
+    //     pod = [
+    //       [nodeSelector: [gpu: 'yes']]
+    //     ]
+    //   }
+      
+    //   // Specific settings for addToIndex process (CPU only)
+    //   withName: 'addToIndex' {
+    //     container = 'harbor.cluster.omic.ai/omic/conplex-faiss-add:latest'
+    //     memory = '75 GB'
+    //     cpus = 1
+        
+    //     // Explicitly ensure no GPU requirements
+    //     // No accelerator property set, and no GPU nodeSelector
+    //   }
+    // }
+  }
+
+  docker {
+    // Docker/Singularity configuration
+    docker {
+      enabled = true
+      runOptions = '--rm'
+    }
+  }
+}
+