Docker image with all genomes cached via pyensembl in it

Dockerfile.pyensembl

# This Docker image is meant to serve commonly used Ensembl Genomes
#  already cached via PyEnsembl. Any application that depends on
#  the pyensembl library can use this image to speed things up
#  as caching these genomes is a huge bottleneck for most applications

FROM ubuntu:latest
MAINTAINER B. Arman Aksoy <[email protected]>

## We will be needing a few utilities to get this going

# So, let's start with updating the package list
RUN apt-get update
# wget, to be able to download Conda script
RUN apt-get install -y wget
# bzip2, so that Conda can unbundle stuff
RUN apt-get install -y bzip2
# because http://stackoverflow.com/a/25423366
RUN rm /bin/sh && ln -s /bin/bash /bin/sh

## Let's set up our playground and cache 

RUN mkdir -p $HOME/miniconda
RUN cd $HOME && \
    wget -q https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh && \
    bash miniconda.sh -b -f -p $HOME/miniconda && \
    export PATH="$HOME/miniconda/bin:$PATH" && \
    hash -r && \

    # Create our Conda environment and activate it
    conda create -y -n pyensembl-cache python=3 && \
    echo "$PATH" && ls $HOME/miniconda/bin && \
    . activate pyensembl-cache && \

    # Install some packages up-front
    conda install numpy scipy nose pandas matplotlib biopython && \

    # and install pyensembl
    pip install pyensembl && \

    # Cache all the genomes!
    pyensembl install --release 54 --species human && \
    pyensembl install --release 75 --species human && \
    pyensembl install --release 77 --species human && \
    pyensembl install --release 83 --species human && \
    pyensembl install --release 84 --species human && \
    pyensembl install --release 67 --species mouse && \
    pyensembl install --release 84 --species mouse

## Remove 
RUN echo "All done!"
## All done!