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.

Dockerfile_corto

@@ -0,0 +1,49 @@
+FROM r-base:latest
+
+WORKDIR /usr/src/app
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    git \
+    libcurl4-gnutls-dev \
+    libssl-dev \
+    libxml2-dev \
+    procps  # Adding procps for the 'ps' command
+
+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:$PATH
+RUN conda update -y -n base -c defaults conda
+
+# main conda env (rpy2)
+RUN conda create -n rpy2 python=3.9
+ENV PATH "$PATH:/opt/conda/envs/rpy2/bin"
+RUN echo "source activate rpy2" >> ~/.bashrc
+RUN conda clean --all -f -y
+
+RUN conda install -y -n rpy2 -c anaconda pandas
+RUN conda install -y -n rpy2 -c anaconda numpy
+
+# Install R packages
+RUN Rscript -e "install.packages('remotes', dependencies=TRUE)" \
+    && Rscript -e "remotes::install_github('federicogiorgi/corto')" \
+    && Rscript -e "install.packages('data.table', dependencies=TRUE)" \
+    && Rscript -e "install.packages('BiocManager')" \
+    && Rscript -e "BiocManager::install('DESeq2')"
+
+# Test commands to validate installation
+RUN Rscript -e "library(corto)"
+
+# Clone the corto repository (optional, based on your needs)
+RUN git clone https://github.com/federicogiorgi/corto.git
+
+CMD ["/bin/bash"]
+