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_vcf2prot

@@ -0,0 +1,96 @@
+#FROM nvidia/cuda:12.2.2-cudnn8-runtime-ubuntu22.04
+FROM rust:1.61
+
+USER root
+
+SHELL ["/bin/bash", "-c"]
+#SHELL [ "/bin/sh", "-s", ".", "$HOME/.cargo/env" ]
+WORKDIR /home
+RUN mkdir -p /home/omic
+WORKDIR /home/omic
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update -y && apt-get install -y software-properties-common --no-install-recommends \
+    build-essential \
+    cmake \
+    curl \
+    git \
+    wget \
+    ca-certificates \
+    libopenblas-dev \
+    libgsl-dev \
+  && apt-get clean \
+  && rm -rf /var/lib/apt/lists/*
+
+# Get Rust
+#RUN curl https://sh.rustup.rs -sSf | bash -s -- --default-toolchain nightly -y 
+#RUN source $HOME/.cargo/env
+#RUN echo 'source $HOME/.cargo/env' >> $HOME/.bashrc 
+
+# Install vcf2prot
+RUN git clone https://github.com/ikmb/vcf2prot.git
+WORKDIR /home/omic/vcf2prot
+
+RUN cargo build --release 
+ 
+WORKDIR /home/omic/vcf2prot/target/release
+
+RUN export DEBUG_CPU_EXEC=TRUE
+RUN export INSPECT_TXP=TRUE
+RUN export INSPECT_INS_GEN=TRUE
+
+#Test
+RUN ./vcf2prot -h
+
+WORKDIR /home/omic/vcf2prot
+RUN gunzip examples/reference_sequences.fasta.gz
+
+COPY reference.fasta .
+
+#install bcftools
+WORKDIR /home/omic/
+
+# install conda
+RUN wget --quiet https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh && \
+  mkdir -p /opt && \     
+  bash miniconda.sh -b -p /opt/conda && \      
+  rm miniconda.sh && \
+  ln -s /opt/conda/etc/profile.d/conda.sh /etc/profile.d/conda.sh && \
+  echo ". /opt/conda/etc/profile.d/conda.sh" >> ~/.bashrc && \
+  echo "conda activate base" >> ~/.bashrc && \
+  find /opt/conda/ -follow -type f -name '*.a' -delete && \
+  find /opt/conda/ -follow -type f -name '*.js.map' -delete && \
+  /opt/conda/bin/conda clean -afy
+
+ENV PATH /opt/conda/bin:$PATH
+
+## update conda
+RUN conda update -y -n base -c defaults conda
+
+# main conda env (vcf2prot)
+RUN conda create -n vcf2prot python=3.9
+ENV PATH "$PATH:/opt/conda/envs/vcf2prot/bin"
+RUN echo "source activate vcf2prot" >> ~/.bashrc
+
+RUN conda install -y -n vcf2prot -c bioconda openssl
+RUN conda install -y -n vcf2prot -c conda-forge libgcc-ng
+RUN conda install -y -n vcf2prot -c bioconda bcftools==1.20
+
+#Install beagle
+#RUN wget https://faculty.washington.edu/browning/beagle/beagle.28Jun21.220.jar
+
+#Get data
+RUN wget https://ftp.ensembl.org/pub/release-112/gff3/homo_sapiens/Homo_sapiens.GRCh38.112.gff3.gz
+RUN gunzip Homo_sapiens.GRCh38.112.gff3.gz
+#RUN wget http://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz
+#RUN gunzip hg38.fa.gz
+RUN wget https://ftp.ensembl.org/pub/release-112/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna.toplevel.fa.gz
+RUN gunzip Homo_sapiens.GRCh38.dna.toplevel.fa.gz
+
+WORKDIR /home/omic/vcf2prot
+
+
+RUN conda install -y -n vcf2prot numpy pandas
+
+
+COPY MANE_transcipts_reference.fasta .