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.
2026-03-26 15:15:23 +01:00
commit 9e6a16c19b
45 changed files with 7207 additions and 0 deletions
--- a/126
+++ b/126
@@ -0,0 +1,126 @@
+# Start with Ubuntu base
+FROM ubuntu:22.04
+
+USER root
+SHELL ["/bin/bash", "-c"]
+
+# Set environment variables
+ENV DEBIAN_FRONTEND=noninteractive \
+    TZ=Etc/UTC \
+    PATH="/opt/conda/bin:/opt/conda/condabin:/opt/conda/envs/ecotyper/bin:$PATH" \
+    R_LIBS="/opt/conda/envs/ecotyper/lib/R/library:/ecotyper/R/library" \
+    ECOTYPER_HOME="/ecotyper"
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    wget \
+    ca-certificates \
+    git \
+    libcurl4-openssl-dev \
+    libssl-dev \
+    libxml2-dev \
+    build-essential \
+    r-base \
+    r-base-dev \
+    libcairo2-dev \
+    libxt-dev \
+    libgraphicsmagick1-dev \
+    default-jdk \
+    xvfb \
+    xauth \
+    xfonts-base \
+    && rm -rf /var/lib/apt/lists/*
+
+# Set up R environment
+RUN echo "options(repos = c(CRAN = 'https://cloud.r-project.org'))" > /root/.Rprofile
+
+# Install Conda
+RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh && \
+    mkdir -p /opt && \
+    bash miniconda.sh -b -p /opt/conda && \
+    rm miniconda.sh && \
+    ln -s /opt/conda/etc/profile.d/conda.sh /etc/profile.d/conda.sh && \
+    echo ". /opt/conda/etc/profile.d/conda.sh" >> ~/.bashrc && \
+    echo "conda activate base" >> ~/.bashrc && \
+    find /opt/conda/ -follow -type f -name '*.a' -delete && \
+    find /opt/conda/ -follow -type f -name '*.js.map' -delete && \
+    /opt/conda/bin/conda clean -afy
+
+ENV PATH=/opt/conda/bin:$PATH
+
+# Update conda and create environment
+RUN conda update -y -n base -c defaults conda && \
+    conda create -n ecotyper -c conda-forge -c bioconda \
+    python=3.8 \
+    r-base=4.1.3 \
+    r-matrix \
+    r-mass \
+    r-nmf \
+    r-rcpp \
+    r-data.table \
+    r-reshape2 \
+    r-plyr \
+    r-stringr \
+    r-ggplot2 \
+    r-rcolorbrewer \
+    r-circlize \
+    r-cowplot \
+    r-viridis \
+    r-gridextra \
+    r-ggpubr \
+    r-cluster \
+    r-matrixtests \
+    r-doparallel \
+    r-foreach \
+    r-optparse \
+    r-argparse \
+    r-config \
+    r-colorspace \
+    r-rjson \
+    bioconductor-biobase \
+    bioconductor-complexheatmap \
+    bioconductor-genomicranges \
+    -y && \
+    conda clean -afy
+
+# Clone EcoTyper and setup directory structure
+RUN git clone --depth 1 https://github.com/digitalcytometry/ecotyper.git /ecotyper && \
+    cd /ecotyper && \
+    mkdir -p EcoTyper/Carcinoma/Carcinoma_Fractions/Analysis/rank_selection && \
+    mkdir -p EcoTyper/Lymphoma/Lymphoma_Fractions/Analysis/rank_selection && \
+    mkdir -p EcoTyper/Carcinoma/Carcinoma_Fractions/Cell_States/recovery && \
+    mkdir -p EcoTyper/Carcinoma/Carcinoma_Fractions/Ecotypes/recovery && \
+    mkdir -p EcoTyper/Lymphoma/Lymphoma_Fractions/Cell_States/recovery && \
+    mkdir -p EcoTyper/Lymphoma/Lymphoma_Fractions/Ecotypes/recovery && \
+    chmod -R +x pipeline/*.R && \
+    chmod -R +x *.R
+
+# Setup EcoTyper permissions
+RUN cd /ecotyper && \
+    ln -sf /ecotyper/pipeline pipeline && \
+    chmod -R 755 /ecotyper/EcoTyper && \
+    chmod -R 755 /ecotyper/pipeline
+
+# Setup CIBERSORTx
+RUN mkdir -p /src
+WORKDIR /src
+
+# Copy CIBERSORTx files
+COPY ./CIBERSORTx-fractionshires/ /src/
+
+# Install R dependencies for CIBERSORTx
+RUN R -e "if (!require('BiocManager', quietly=TRUE)) install.packages('BiocManager', repos='https://cloud.r-project.org/')" && \
+    Rscript /src/install_R_dependencies.R
+
+# Add src to PATH
+ENV PATH="/src:${PATH}"
+
+# Setup final environment
+RUN echo ". /opt/conda/etc/profile.d/conda.sh" >> ~/.bashrc && \
+    echo "conda activate ecotyper" >> ~/.bashrc
+
+#Add pandas 
+RUN conda install -n ecotyper anaconda::pandas
+
+# Set default command
+CMD ["/bin/bash"]