Initial commit: digital-patients pipeline (clean, no large files)

Large reference/model files excluded from repo - to be staged to S3 or baked into Docker images.

k8s/job-copy-node-to-pvc.yaml

@@ -0,0 +1,54 @@
+apiVersion: batch/v1
+kind: Job
+metadata:
+  name: job-data-copy-digital-patient-node-to-pvc
+  namespace: bioinformatics
+spec:
+  backoffLimit: 6
+  completionMode: NonIndexed
+  completions: 1
+  manualSelector: false
+  parallelism: 1
+  suspend: false
+  template:
+    spec:
+      containers:
+      - args:
+        - |
+          apk add --no-cache rsync
+          mkdir -p /target
+          rsync -av --exclude .git/ --exclude .git-old/ --exclude work/ /source/ /target/digital-patient-data
+        command:
+        - /bin/sh
+        - -c
+        image: alpine
+        imagePullPolicy: Always
+        name: data-copy
+        resources: {}
+        terminationMessagePath: /dev/termination-log
+        terminationMessagePolicy: File
+        volumeMounts:
+        - mountPath: /source
+          name: k8s-node
+        - mountPath: /target
+          name: pvc-volume
+      dnsPolicy: ClusterFirst
+      nodeSelector:
+        kubernetes.io/hostname: k8s-node23
+      restartPolicy: Never
+      schedulerName: default-scheduler
+      securityContext: {}
+      terminationGracePeriodSeconds: 30
+      tolerations:
+      - effect: NoExecute
+        key: omic-app
+        operator: Equal
+        value: similarity-search
+      volumes:
+      - name: pvc-volume
+        persistentVolumeClaim:
+          claimName: dreamdock-data
+      - hostPath:
+          path: /data/bugra/digital_patient  ## CHANGE ME
+          type: ""
+        name: k8s-node