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.

Dockerfile_biotransformer

@@ -0,0 +1,71 @@
+FROM debian:bullseye-slim
+
+USER root
+
+SHELL ["/bin/bash", "-c"]
+WORKDIR /home
+RUN mkdir -p /home/omic
+WORKDIR /home/omic
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt update -y && apt-get install -y --no-install-recommends \
+    build-essential \
+    cmake \
+    curl \
+    git \
+    wget \
+    ca-certificates \
+    default-jre \
+    unzip \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
+
+RUN wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh \
+    && bash miniconda.sh -b -p /opt/conda \
+    && rm miniconda.sh \
+    && ln -s /opt/conda/etc/profile.d/conda.sh /etc/profile.d/conda.sh \
+    && echo ". /opt/conda/etc/profile.d/conda.sh" >> ~/.bashrc \
+    && echo "conda activate base" >> ~/.bashrc \
+    && find /opt/conda/ -follow -type f -name '*.a' -delete \
+    && find /opt/conda/ -follow -type f -name '*.js.map' -delete \
+    && /opt/conda/bin/conda clean -afy
+
+ENV PATH /opt/conda/bin:$PATH
+
+# main conda env (biotransformer)
+RUN conda create -n biotransformer
+ENV PATH="$PATH:/opt/conda/envs/biotransformer/bin"
+RUN echo "source activate biotransformer" >> ~/.bashrc
+RUN conda clean --all -f -y
+
+# Install RDKit
+RUN conda install -y -n biotransformer -c conda-forge rdkit
+
+WORKDIR /home/omic
+# RUN wget https://bitbucket.org/wishartlab/biotransformer3.0jar/get/6432cf887ed7.zip && \
+#     unzip 6432cf887ed7.zip && \
+#     rm 6432cf887ed7.zip && \
+#     mv wishartlab-biotransformer3.0jar-6432cf887ed7 biotransformer
+
+# RUN git clone https://github.com/Wishartlab-openscience/Biotransformer.git && \
+# mv Biotransformer biotransformer
+RUN git clone https://bitbucket.org/wishartlab/biotransformer3.0jar biotransformer && mv biotransformer/BioTransformer3.0_20230525.jar biotransformer/biotransformer
+WORKDIR /home/omic/biotransformer
+# RUN wget https://bitbucket.org/wishartlab/biotransformer3.0jar/raw/6432cf887ed70c7c943c2dfeb60298ccdc788d7d/BioTransformer3.0_20230525.jar && \
+#     mv BioTransformer3.0_20230525.jar biotransformer && \
+#     chmod +x biotransformer
+ENV PATH="$PATH:/home/omic/biotransformer"
+
+# Create a symlink from /home/omic/biotransformer/database to /home/omic/biotransformer/btkb
+RUN ln -s /home/omic/biotransformer/database /home/omic/biotransformer/btkb
+
+## Test
+# RUN java -jar biotransformer -multiThread "2 example.csv 36000 3 1 true"
+
+#Download The Human Metabolome Database smiles
+RUN wget https://hmdb.ca/system/downloads/current/structures.zip
+RUN unzip structures.zip
+
+
+#install pandas and requests
+RUN conda install -y -n biotransformer -c conda-forge pandas requests