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.

nf_metabol_screen_adaptive/Dockerfile

@@ -0,0 +1,20 @@
+FROM mambaorg/micromamba:2.1.1
+
+USER root
+
+COPY ./app /app
+
+ARG MAMBA_DOCKERFILE_ACTIVATE=1 
+
+RUN micromamba install -n base -y -c conda-forge --channel-priority flexible \
+        python=3.12 \
+        numpy \
+        "pandas<3" \
+        scikit-learn \
+        parallelbar \
+        zarr=3.0.7 \
+        onnxruntime \
+        procps-ng && \
+    pip install \
+        /app/bitexpand-0.1.0-cp38-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl \
+        /app/mol_fingerprint-0.1.0-cp312-cp312-manylinux_2_34_x86_64.whl