Merge pull request #121 from RabadanLab/buendia/ref_patch

Dockerfile and CI/CD to use conda environment

.github/workflows/docker-build-test.yml

@@ -18,4 +18,4 @@ jobs:
     - name: Build docker image
       run: docker build -t test-arcas-hla -f Docker/Dockerfile .
     - name: Test with pytest
-      run: docker run --rm -v $GITHUB_WORKSPACE:/home test-arcas-hla pytest
+      run: docker run --rm -v $GITHUB_WORKSPACE:/app test-arcas-hla pytest

Docker/Dockerfile

@@ -1,80 +1,14 @@
-# work from latest LTS ubuntu release
-FROM ubuntu:18.04
+FROM continuumio/miniconda3:latest
 
-# set the environment variables
-ENV kallisto_version 0.44.0
-ENV samtools_version 1.9
-ENV bedtools_version 2.29.2
-ENV biopython_version 1.77
-ENV LANG C.UTF-8
-ENV LC_ALL C.UTF-8
+WORKDIR /app
 
-# run update and install necessary tools from package manager
-RUN apt-get update -y && apt-get install -y \
-    build-essential \
-    cmake \
-    zlib1g-dev \
-    libhdf5-dev \
-    libnss-sss \
-    curl \
-    autoconf \
-    bzip2 \
-    python3-dev \
-    python3-pip \
-    python \
-    pigz \
-    git \
-    libncurses5-dev \
-    libncursesw5-dev \
-    libbz2-dev \
-    liblzma-dev \
-    bzip2 \
-    unzip
-
-# install python libraries
-RUN pip3 install numpy
-RUN pip3 install scipy
-RUN pip3 install pandas
-RUN pip3 install biopython==${biopython_version}
-RUN pip3 install pytest
-
-# install kallisto
-RUN mkdir -p /usr/bin/kallisto \
-    && curl -SL https://github.com/pachterlab/kallisto/archive/v${kallisto_version}.tar.gz \
-    | tar -zxvC /usr/bin/kallisto
-
-RUN mkdir -p /usr/bin/kallisto/kallisto-${kallisto_version}/build
-RUN cd /usr/bin/kallisto/kallisto-${kallisto_version}/build && cmake ..
-RUN cd /usr/bin/kallisto/kallisto-${kallisto_version}/ext/htslib && autoreconf
-RUN cd /usr/bin/kallisto/kallisto-${kallisto_version}/build && make
-RUN cd /usr/bin/kallisto/kallisto-${kallisto_version}/build && make install
-
-# install samtools
-WORKDIR /usr/bin/
-RUN curl -SL https://github.com/samtools/samtools/releases/download/${samtools_version}/samtools-${samtools_version}.tar.bz2 \
-    > samtools-${samtools_version}.tar.bz2
-RUN tar -xjvf samtools-${samtools_version}.tar.bz2
-WORKDIR /usr/bin/samtools-${samtools_version}
-RUN ./configure
-RUN make
-RUN make install
-
-# install bedtools
-WORKDIR /usr/bin
-RUN curl -SL https://github.com/arq5x/bedtools2/releases/download/v${bedtools_version}/bedtools-${bedtools_version}.tar.gz \
-    > bedtools-${bedtools_version}.tar.gz
-RUN tar -xzvf bedtools-${bedtools_version}.tar.gz
-WORKDIR /usr/bin/bedtools2
-RUN make
-RUN ln -s /usr/bin/bedtools2/bin/bedtools /usr/bin/bedtools
-
-# git lfs
+# Install Git LFS
+RUN apt-get update && \
+    apt-get install -y git curl pigz
 RUN curl -s https://packagecloud.io/install/repositories/github/git-lfs/script.deb.sh | bash
 RUN apt-get install -y git-lfs
-RUN git lfs install --system --skip-repo
-
-# install arcasHLA
-WORKDIR /home/
-RUN git clone https://github.com/RabadanLab/arcasHLA.git arcasHLA-master
 
-ENV PATH="${PATH}:/home/arcasHLA-master/"
+RUN git clone -b buendia/ref_patch https://github.com/RabadanLab/arcasHLA.git
+RUN conda env create -f /app/arcasHLA/environment.yml
+RUN echo "source activate arcas-hla" > ~/.bashrc
+ENV PATH /opt/conda/envs/arcas-hla/bin:$PATH

Docker/README.md

@@ -1,20 +1,6 @@
 # Container for arcasHLA #
 
-Installs up-to-date versions of arcasHLA and all dependencies:
-
-- arcasHLA
-- [Git Large File Storage](https://github.com/git-lfs/git-lfs/wiki/Installation)
-- coreutils
-- [Samtools v1.19](http://www.htslib.org/)
-- [bedtools v2.29.1](http://bedtools.readthedocs.io/)
-- [pigz v2.3.1](https://zlib.net/pigz/)
-- [Kallisto v0.44.0](https://pachterlab.github.io/kallisto/)
-- python 3.6
-- [Biopython v1.77](https://biopython.org/wiki/Download)
-- numpy
-- scipy
-- pandas
-- pytest
+Installs up-to-date versions of arcasHLA and all dependencies from `environment.yml`.
 
 ### Build ###
 In order to use this arcasHLA container, install Docker and build in this directory:
@@ -33,5 +19,4 @@ docker run \
 	<image_name> \
 	arcasHLA extract --o docker/path/to/files/out_dir \
 	[other options] docker/path/to/files/sample.bam & 
-
 ```

README.md

@@ -19,7 +19,7 @@ conda activate arcas-hla
 
 ```
 docker build -t <image-name> -f Docker/Dockerfile .
-docker run --rm -v /path/to/repo:/home <image-name> pytest
+docker run --rm -v /path/to/repo:/app <image-name> pytest
 ```
 -----
 

environment.yml

@@ -1,14 +1,16 @@
 name: arcas-hla
 channels:
 - bioconda
-- defaults
 dependencies:
 - bedtools==2.26.0
 - kallisto==0.44.0
 - pip==23.3.1
-- python==3.11.5
-- samtools==1.5
+- python==3.10.0
+- samtools==1.11
 - pip:
   - biopython==1.83
   - numpy==1.26.3
+  - pandas==2.2.0
+  - pyarrow==15.0.0
+  - pytest==8.0.0
   - scipy==1.12.0