Container for Speedseq

docker/Dockerfile

-# Recommended build process
-
-#get CUDA - getting an older version for compatibility, recommend changing to newer
-FROM nvidia/cuda:12.6.0-devel-ubuntu22.04
-
-# get packages 
-WORKDIR /root
-ARG DEBIAN_FRONTEND="noninteractive"
-RUN apt-get update -y
-RUN apt-get install build-essential -y wget -y libboost-all-dev -y libeigen3-dev -y libgoogle-glog-dev -y libprotobuf-dev -y protobuf-compiler -y libhdf5-dev -y libatlas-base-dev -y python3-dev -y librdkit-dev -y python3-numpy -y python3-pip -y python3-pytest -y swig -y
-RUN apt update ; apt upgrade -y ; apt-get -y install build-essential git wget libboost-all-dev libeigen3-dev libgoogle-glog-dev libprotobuf-dev protobuf-compiler libhdf5-dev libatlas-base-dev python3-dev librdkit-dev python3-numpy python3-pip python3-pytest libjsoncpp-dev
-RUN apt-get update -y && apt-get install git-all -y curl && apt-get update -y
-RUN rm -rf /var/lib/apt/lists/*
-RUN pip3 install cmake scikit-image pyquaternion google-api-python-client six
-RUN pip3 install torch torchvision torchaudio
-
-RUN git clone https://github.com/openbabel/openbabel.git && cd openbabel &&  git checkout openbabel-3-1-1 && mkdir build && cd build && cmake -DWITH_MAEPARSER=OFF -DWITH_COORDGEN=OFF -DPYTHON_BINDINGS=ON -DRUN_SWIG=ON .. && make -j4 && make install
-
-ADD "https://github.com/gnina/gnina/commits?per_page=1" latest_commit
-
-RUN git clone https://github.com/gnina/gnina.git; \
-    cd gnina; mkdir build; cd build; \
-    cmake .. ;\
-    make -j4 ; make install 
+FROM ubuntu:18.04
+
+LABEL maintainer="Your Name <your.email@example.com>"
+
+ENV DEBIAN_FRONTEND=noninteractive
+
+# ----------- Install Core System Dependencies -----------
+RUN apt-get update && apt-get install -y \
+    git build-essential cmake g++ \
+    zlib1g-dev libncurses5-dev libbz2-dev liblzma-dev \
+    libcurl4-openssl-dev libssl-dev \
+    python2.7 python-pip python-numpy python-scipy \
+    libboost-all-dev curl unzip wget parallel \
+    libtbb-dev samtools locales \
+    perl curl \
+    unzip \
+    x11-utils xorg-dev libx11-dev \
+    libxpm-dev libxft-dev libxext-dev && \
+    apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# Set Python 2 as default
+RUN update-alternatives --install /usr/bin/python python /usr/bin/python2.7 1
+
+# Install Python modules
\ No newline at end of file
+RUN pip install pysam==0.8.4
+
+# Set UTF-8 locale
+RUN locale-gen en_US.UTF-8
+ENV LANG en_US.UTF-8
+ENV LANGUAGE en_US:en
+ENV LC_ALL=en_US.UTF-8
+
+# ----------- Clone and Build SpeedSeq -----------
+WORKDIR /opt
+RUN git clone --recursive https://github.com/hall-lab/speedseq.git
+WORKDIR /opt/speedseq
+RUN make
+
+ENV SPEEDSEQ_DIR=/opt/speedseq
+ENV PATH="$SPEEDSEQ_DIR/bin:$PATH"
+
+# ----------- OPTIONAL: Install CNVnator and ROOT -----------
+# Toggle these installs with --build-arg flags
+ARG INSTALL_CNVNATOR=true
+
+RUN if [ "$INSTALL_CNVNATOR" = "true" ]; then \
+    curl -OL ftp://root.cern.ch/root/root_v5.34.20.source.tar.gz && \
+    tar -zxvf root_v5.34.20.source.tar.gz && \
+    cd root && \
+    ./configure --prefix=/opt/root && \
+    make -j4 && \
+    echo "source /opt/root/bin/thisroot.sh" >> /etc/bash.bashrc && \
+    cd $SPEEDSEQ_DIR && \
+    source /opt/root/bin/thisroot.sh && \
+    make cnvnator; \
+    fi
+
+ENV ROOTSYS=/opt/root
+ENV PATH="$ROOTSYS/bin:$PATH"
+ENV LD_LIBRARY_PATH="$ROOTSYS/lib:$LD_LIBRARY_PATH"
+ENV DYLD_LIBRARY_PATH="$ROOTSYS/lib:$DYLD_LIBRARY_PATH"
+
+# ----------- OPTIONAL: Install VEP -----------
+ARG INSTALL_VEP=true
+
+RUN if [ "$INSTALL_VEP" = "true" ]; then \
+    mkdir -p $SPEEDSEQ_DIR/annotations/vep_cache && \
+    curl -OL https://github.com/Ensembl/ensembl-tools/archive/release/76.zip && \
+    unzip 76.zip && \
+    perl ensembl-tools-release-76/scripts/variant_effect_predictor/INSTALL.pl \
+        -c $SPEEDSEQ_DIR/annotations/vep_cache \
+        -a ac -s homo_sapiens -y GRCh37 && \
+    cp ensembl-tools-release-76/scripts/variant_effect_predictor/variant_effect_predictor.pl $SPEEDSEQ_DIR/bin && \
+    cp -r ensembl-tools-release-76/scripts/variant_effect_predictor/Bio $SPEEDSEQ_DIR/bin; \
+    fi
+
+# ----------- Final Touches -----------
+WORKDIR /data
+ENTRYPOINT ["speedseq"]
\ No newline at end of file