CADD 1.6.post1 container (#547)

* CADD scripts with bundled required environments

* Fix maintainer, biotools, software name

* Fix issue with license and cleanup conda storage

* Add usage documentation

* Use gh release instead of conda, move to version 1.6post1

cadd-scripts-with-envs/1.6.post1/Dockerfile

@@ -0,0 +1,48 @@
+FROM mambaorg/micromamba:1.5.3
+
+ARG CADD_VERSION=1.6.post1
+ARG CADD_CONFIG_VERSION=1.6
+
+MAINTAINER "Marius Bjoernstad" <[email protected]>
+LABEL software="cadd-scripts-with-envs" \
+    software.version="$CADD_VERSION" \
+    version="1" \
+    about.summary="CADD is a tool for scoring the deleteriousness of single nucleotide variants as well as insertion/deletions variants in the human genome" \
+    about.home="https://cadd.gs.washington.edu/" \
+    about.documentation="https://github.com/BioContainers/containers/blob/master/cadd-scripts-with-envs/$CADD_VERSION/README.md" \
+    about.license="Custom License" \
+    about.license_file="https://github.com/kircherlab/CADD-scripts/blob/v$CADD_VERSION/LICENSE" \
+    extra.binaries="/opt/conda/bin/cadd.sh" \
+    about.tags="Genomics, Human geneitcs" \
+    base_image="mambaorg/micromamba:1.5.3"
+
+# Need to be root to install apt packages
+USER root
+
+# Install ps command required by some tools
+RUN apt-get update && \
+        apt-get install -y procps curl && \
+        apt-get clean && \
+        apt-get purge && \
+        rm -rf /var/lib/apt/lists/* /tmp/*
+
+# Install snakemake and mamba. mamba is required by snakemake (as it provides the conda command).
+# bgzip (tabix package) is required by the pipeline.
+RUN micromamba install -y -c conda-forge -c bioconda -n base snakemake mamba tabix && \
+        micromamba clean --all --yes
+
+# Download and untar CADD from github. Create a symlink with lowercase cadd.sh for
+# compatibility with conda package.
+RUN cd /opt && \
+    curl -L https://github.com/kircherlab/CADD-scripts/archive/refs/tags/v${CADD_VERSION}.tar.gz | tar xz && \
+    cd CADD-scripts-${CADD_VERSION} && \
+    ln -s CADD.sh cadd.sh
+
+# Add CADD.sh and conda to the path
+ENV PATH=/opt/CADD-scripts-${CADD_VERSION}:/opt/conda/bin:/opt/conda/condabin:$PATH
+
+# Run snakemake to include the necessary conda environments inside the container
+RUN cd /opt/CADD-scripts-${CADD_VERSION} && \
+	snakemake -j 1 test/input.tsv.gz --use-conda --conda-create-envs-only --conda-prefix envs \
+        	--configfile config/config_GRCh38_v${CADD_CONFIG_VERSION}.yml --snakefile Snakefile
+

cadd-scripts-with-envs/1.6.post1/README.md

@@ -0,0 +1,26 @@
+# Container image for CADD-scripts
+
+This container image lets you use the CADD scripts snakemake pipeline to annotate variants.
+Documentation for CADD-scripts is here:
+
+https://github.com/kircherlab/CADD-scripts
+
+
+To use this container image you also need to mount the reference data. Assume you have
+downloaded the reference data to a directory `$REFPATH`, such that it looks something
+like this:
+
+    $ ls $REFPATH
+    GRCh37_v1.6
+
+Then use the following options
+
+Singularity/Apptainer:
+
+    -B $REFPATH:/opt/conda/share/cadd-scripts-1.6-1/data/annotations
+
+Docker:
+
+    -v $REFPATH:/opt/conda/share/cadd-scripts-1.6-1/data/annotations
+
+