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_synthea

@@ -0,0 +1,64 @@
+FROM ubuntu:latest
+
+ARG DEBIAN_FRONTEND=noninteractive
+USER root
+
+# Install gradle and JDK
+RUN apt -y update && apt-get -y update
+RUN apt install -y build-essential openjdk-8-jdk wget git python3 python3-pip tabix
+
+# install conda
+RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh && \
+    mkdir -p /opt && \
+    sh 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:$PATH
+
+# main conda env (synthea)
+RUN conda create -n synthea
+ENV PATH "$PATH:/opt/conda/envs/synthea/bin"
+RUN echo "source activate synthea" >> ~/.bashrc
+
+# Install pandas and numpy
+RUN python3 -m pip install --upgrade pip
+RUN python3 -m pip install pandas numpy fuzzywuzzy python-Levenshtein requests
+
+# Install synthea from latest release
+RUN wget https://github.com/synthetichealth/synthea/archive/refs/tags/master-branch-latest.tar.gz
+RUN tar xzf master-branch-latest.tar.gz && mv synthea-master-branch-latest synthea
+WORKDIR /synthea
+
+ARG PATH $PATH:/synthea
+ENV PATH $PATH:/synthea
+
+RUN conda config --add channels bioconda
+RUN conda config --add channels conda-forge
+
+# Install samtools
+RUN conda install -n synthea -c bioconda samtools
+
+# Install UCSC Liftover
+RUN conda install -n synthea -c bioconda ucsc-liftover
+RUN conda install -n synthea -c bioconda gatk4
+RUN conda install -n synthea -c bioconda bedtools
+RUN apt-get -y install vcftools
+
+# DNA to Protein Sequence code
+WORKDIR /synthea
+RUN git clone https://github.com/prestevez/dna2proteins.git
+RUN mv dna2proteins/dna2proteins.py .
+RUN rm -r dna2proteins
+RUN apt install -y 2to3
+RUN 2to3 -w dna2proteins.py
+
+#Test
+# RUN ./gradlew build check test
+RUN ./run_synthea -p 10 --exporter.csv.export true
+# use -a for age range e.g. 30-40 and -g for gender M/F