StaPH-B · erinyoung · Sep 24, 2024 · Sep 25, 2024 · Sep 25, 2024
diff --git a/README.md b/README.md
@@ -203,7 +203,7 @@ To learn more about the docker pull rate limits and the open source software pro
 | [Mash](https://hub.docker.com/r/staphb/mash/) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/mash)](https://hub.docker.com/r/staphb/mash)  | <ul><li>2.1</li><li>2.2</li><li>2.3</li></ul> | https://github.com/marbl/Mash |
 | [mashtree](https://hub.docker.com/r/staphb/mashtree) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/mashtree)](https://hub.docker.com/r/staphb/mashtree) | <ul><li>[0.52.0](./mashtree/0.52.0/)</li><li>[0.57.0](./mashtree/0.57.0/)</li><li>[1.0.4](./mashtree/1.0.4/)</li><li>[1.2.0](./mashtree/1.2.0/)</li><li>[1.4.6](./mashtree/1.4.6/)</li></ul> | https://github.com/lskatz/mashtree |
 | [MaSuRCA](https://hub.docker.com/r/staphb/masurca) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/masurca)](https://hub.docker.com/r/staphb/masurca) | <ul><li>4.0.8</li><li>4.0.9</li><li>4.1.0</li></ul> | https://github.com/alekseyzimin/masurca |
-| [medaka](https://hub.docker.com/r/staphb/medaka) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/medaka)](https://hub.docker.com/r/staphb/medaka) | <ul><li>0.8.1</li><li>1.0.1</li><li>1.2.0</li></ul> | https://github.com/nanoporetech/medaka |
+| [medaka](https://hub.docker.com/r/staphb/medaka) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/medaka)](https://hub.docker.com/r/staphb/medaka) | <ul><li>[0.8.1](./medaka/0.8.1/)</li><li>[1.0.1](./medaka/1.0.1/)</li><li>[1.2.0](./medaka/1.2.0/)</li><li>[2.0.0](./medaka/2.0.0/)</li></ul> | https://github.com/nanoporetech/medaka |
 | [metaphlan](https://hub.docker.com/r/staphb/metaphlan) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/metaphlan)](https://hub.docker.com/r/staphb/metaphlan) | <ul><li>[3.0.3-no-db (no database)](./metaphlan/3.0.3-no-db/)</li><li> [3.0.3 (~3GB db)](./metaphlan/3.0.3/)</li><li>[4.1.0](./metaphlan/4.1.0/) (no database)</li><li>[4.1.1](./metaphlan/4.1.1/) (no database)</li></ul> | https://github.com/biobakery/MetaPhlAn |
 | [MIDAS](https://hub.docker.com/r/staphb/midas) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/midas)](https://hub.docker.com/r/staphb/midas) | <ul><li>1.3.2 (no database)</li> | https://github.com/snayfach/MIDAS |
 | [minimap2](https://hub.docker.com/r/staphb/minimap2) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/minimap2)](https://hub.docker.com/r/staphb/minimap2) | <ul><li>2.17</li><li>2.18</li><li>2.21</li><li>2.22</li><li>2.23</li><li>2.24</li><li>2.25</li><li>[2.26](./minimap2/2.26)</li><li>[2.27](./minimap2/2.27/)</li>li>[2.28](./minimap2/2.28/)</li></ul> | https://github.com/lh3/minimap2 |

diff --git a/medaka/2.0.0/Dockerfile b/medaka/2.0.0/Dockerfile
@@ -0,0 +1,156 @@
+ARG MEDAKA_VER="2.0.0"
+ARG SAMTOOLS_VER="1.21"
+ARG BCFTOOLS_VER=${SAMTOOLS_VER}
+ARG HTSLIB_VER=${SAMTOOLS_VER}
+ARG MINIMAP2_VER="2.28"
+
+FROM ubuntu:jammy as builder
+
+ARG SAMTOOLS_VER
+ARG BCFTOOLS_VER
+ARG HTSLIB_VER
+ARG MINIMAP2_VER
+
+# install dependencies required for compiling samtools
+ARG DEBIAN_FRONTEND=noninteractive
+
+RUN apt-get update && apt-get install --no-install-recommends -y \
+    libncurses5-dev \
+    libbz2-dev \
+    liblzma-dev \
+    libcurl4-gnutls-dev \
+    zlib1g-dev \
+    libssl-dev \
+    gcc \
+    wget \
+    make \
+    perl \
+    bzip2 \
+    gnuplot \
+    ca-certificates \
+    curl \
+    perl \
+    bzip2 \
+    autoconf \
+    automake \
+    make \
+    gcc \
+    libdeflate-dev \
+    zlib1g-dev \
+    libbz2-dev \
+    liblzma-dev \
+    libcurl4-gnutls-dev \
+    libssl-dev \
+    libperl-dev \
+    libgsl0-dev \
+    libdeflate-dev \
+    procps && \
+    rm -rf /var/lib/apt/lists/* && apt-get autoclean
+
+# download, compile, and install bcftools
+RUN wget -q https://github.com/samtools/bcftools/releases/download/${BCFTOOLS_VER}/bcftools-${BCFTOOLS_VER}.tar.bz2 && \
+    tar -xjf bcftools-${BCFTOOLS_VER}.tar.bz2 && \
+    rm -v bcftools-${BCFTOOLS_VER}.tar.bz2 && \
+    cd bcftools-${BCFTOOLS_VER} && \
+    ./configure --enable-libgsl --enable-perl-filters &&\
+    make && \
+    make install
+
+# download, compile, and install samtools
+RUN wget -q https://github.com/samtools/samtools/releases/download/${SAMTOOLS_VER}/samtools-${SAMTOOLS_VER}.tar.bz2 && \
+    tar -xjf samtools-${SAMTOOLS_VER}.tar.bz2 && \
+    cd samtools-${SAMTOOLS_VER} && \
+    ./configure && \
+    make && \
+    make install 
+
+RUN wget -q https://github.com/samtools/htslib/releases/download/${HTSLIB_VER}/htslib-${HTSLIB_VER}.tar.bz2 && \
+    tar -vxjf htslib-${HTSLIB_VER}.tar.bz2 && \
+    rm -v htslib-${HTSLIB_VER}.tar.bz2 && \
+    cd htslib-${HTSLIB_VER} && \
+    ./configure && \
+    make && \
+    make install 
+
+RUN curl -L https://github.com/lh3/minimap2/releases/download/v${MINIMAP2_VER}/minimap2-${MINIMAP2_VER}_x64-linux.tar.bz2 | tar -jxvf - --no-same-owner && \
+    ls && \
+    mv minimap2-${MINIMAP2_VER}_x64-linux/minimap2 /usr/local/bin
+
+### start of app stage ###
+FROM ubuntu:jammy as app
+
+ARG MEDAKA_VER
+
+LABEL base.image="ubuntu:jammy"
+LABEL dockerfile.version=1
+LABEL container.version="1"
+LABEL software="Medaka"
+LABEL software.version="${MEDAKA_VER}"
+LABEL description="Consensus sequence correction provided by ONT Research"
+LABEL website="https://github.com/nanoporetech/medaka"
+LABEL license="https://github.com/nanoporetech/medaka/blob/master/LICENSE.md"
+LABEL maintainer="Curtis Kapsak"
+LABEL maintainer.email="[email protected]"
+LABEL maintainer1="Erin Young"
+LABEL maintainer1.email="[email protected]"
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+# install dependencies required for running samtools
+RUN apt-get update && apt-get install --no-install-recommends -y \
+    perl \
+    zlib1g \
+    libncurses5 \
+    bzip2 \
+    libdeflate-dev \
+    liblzma-dev \
+    libcurl4-gnutls-dev \
+    python3 \
+    python3-pip \
+    python-is-python3 \
+    python3-dev \
+    build-essential \
+    libssl-dev \
+    libffi-dev \
+    libxml2-dev \
+    libxslt1-dev \
+    zlib1g-dev \
+    libgsl-dev \
+    && apt-get autoclean && rm -rf /var/lib/apt/lists/*
+
+# copy in samtools, htslib, and minimap2 executables from builder stage
+COPY --from=builder /usr/local/bin/* /usr/local/bin/
+
+# install medaka via pip
+RUN pip install medaka-cpu --extra-index-url https://download.pytorch.org/whl/cpu -vv --no-cache-dir && \
+    pip install pyabpoa -vv --no-cache-dir
+
+ENV LC_ALL=C
+
+# final working directory is /data
+WORKDIR /data
+
+# default command is to pull up help options
+CMD medaka --help
+
+### start of test stage ###
+FROM app as test
+
+RUN apt-get update && apt-get install --no-install-recommends -y wget
+
+# making sure dependencies are in path
+RUN samtools --help && minimap2 --help && tabix --help && bgzip --help
+
+RUN medaka --help && \
+    medaka --version
+
+# set working directory so that all test inputs & outputs are kept in /test
+WORKDIR /test
+
+# using on real data (CRPA isolate)
+RUN wget -q https://www.ebi.ac.uk/ena/browser/api/fasta/GCA_021601745.3 -O GCA_021601745.3.fasta && \
+    wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR234/068/SRR23473168/SRR23473168_1.fastq.gz && \
+    medaka_consensus -i SRR23473168_1.fastq.gz -d GCA_021601745.3.fasta -o testing -t 4
+
+# listing available models
+RUN medaka tools list\_models
diff --git a/medaka/2.0.0/README.md b/medaka/2.0.0/README.md
@@ -0,0 +1,34 @@
+# medaka container
+
+Main tool : [medaka](https://github.com/nanoporetech/medaka)
+
+Additional tools:
+- bcftools version 1.21
+- samtools version 1.21
+- htslib version 1.21
+- minimap2 version 2.28
+
+Full documentation: [https://github.com/nanoporetech/medaka](https://github.com/nanoporetech/medaka)
+
+> medaka is a tool to create consensus sequences and variant calls from nanopore sequencing data. This task is performed using neural networks applied a pileup of individual sequencing reads against a draft assembly. It provides state-of-the-art results outperforming sequence-graph based methods and signal-based methods, whilst also being faster.
+
+## Example Usage
+
+```bash
+
+# listing models
+medaka tools list\_models
+
+# polishing
+medaka_consensus -i sample.fastq.gz -d sample.fasta -o medaka/sample -t 4
+
+```
+
+## Medaka models
+
+Medaka updates frequently. These are the medaka models in this image:
+```
+Available: r103_fast_g507, r103_fast_snp_g507, r103_fast_variant_g507, r103_hac_g507, r103_hac_snp_g507, r103_hac_variant_g507, r103_sup_g507, r103_sup_snp_g507, r103_sup_variant_g507, r1041_e82_260bps_fast_g632, r1041_e82_260bps_fast_variant_g632, r1041_e82_260bps_hac_g632, r1041_e82_260bps_hac_v4.0.0, r1041_e82_260bps_hac_v4.1.0, r1041_e82_260bps_hac_variant_g632, r1041_e82_260bps_hac_variant_v4.1.0, r1041_e82_260bps_joint_apk_ulk_v5.0.0, r1041_e82_260bps_sup_g632, r1041_e82_260bps_sup_v4.0.0, r1041_e82_260bps_sup_v4.1.0, r1041_e82_260bps_sup_variant_g632, r1041_e82_260bps_sup_variant_v4.1.0, r1041_e82_400bps_bacterial_methylation, r1041_e82_400bps_fast_g615, r1041_e82_400bps_fast_g632, r1041_e82_400bps_fast_variant_g615, r1041_e82_400bps_fast_variant_g632, r1041_e82_400bps_hac_g615, r1041_e82_400bps_hac_g632, r1041_e82_400bps_hac_v4.0.0, r1041_e82_400bps_hac_v4.1.0, r1041_e82_400bps_hac_v4.2.0, r1041_e82_400bps_hac_v4.3.0, r1041_e82_400bps_hac_v5.0.0, r1041_e82_400bps_hac_variant_g615, r1041_e82_400bps_hac_variant_g632, r1041_e82_400bps_hac_variant_v4.1.0, r1041_e82_400bps_hac_variant_v4.2.0, r1041_e82_400bps_hac_variant_v4.3.0, r1041_e82_400bps_hac_variant_v5.0.0, r1041_e82_400bps_sup_g615, r1041_e82_400bps_sup_v4.0.0, r1041_e82_400bps_sup_v4.1.0, r1041_e82_400bps_sup_v4.2.0, r1041_e82_400bps_sup_v4.3.0, r1041_e82_400bps_sup_v5.0.0, r1041_e82_400bps_sup_variant_g615, r1041_e82_400bps_sup_variant_v4.1.0, r1041_e82_400bps_sup_variant_v4.2.0, r1041_e82_400bps_sup_variant_v4.3.0, r1041_e82_400bps_sup_variant_v5.0.0, r104_e81_fast_g5015, r104_e81_fast_variant_g5015, r104_e81_hac_g5015, r104_e81_hac_variant_g5015, r104_e81_sup_g5015, r104_e81_sup_g610, r104_e81_sup_variant_g610, r941_e81_fast_g514, r941_e81_fast_variant_g514, r941_e81_hac_g514, r941_e81_hac_variant_g514, r941_e81_sup_g514, r941_e81_sup_variant_g514, r941_min_fast_g507, r941_min_fast_snp_g507, r941_min_fast_variant_g507, r941_min_hac_g507, r941_min_hac_snp_g507, r941_min_hac_variant_g507, r941_min_sup_g507, r941_min_sup_snp_g507, r941_min_sup_variant_g507, r941_prom_fast_g507, r941_prom_fast_snp_g507, r941_prom_fast_variant_g507, r941_prom_hac_g507, r941_prom_hac_snp_g507, r941_prom_hac_variant_g507, r941_prom_sup_g507, r941_prom_sup_snp_g507, r941_prom_sup_variant_g507, r941_sup_plant_g610, r941_sup_plant_variant_g610
+Default consensus:  r1041_e82_400bps_sup_v5.0.0
+Default variant:  r1041_e82_400bps_sup_variant_v5.0.0
+```