From 115c0302198b59ffefdb995ff56c1da669819767 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Thu, 26 Oct 2023 16:10:29 +0000 Subject: [PATCH 1/4] adds checkm --- Program_Licenses.md | 1 + README.md | 1 + checkm/1.2.2/Dockerfile | 50 +++++++++++++++++++++++++++++++++++++++++ checkm/1.2.2/README.md | 36 +++++++++++++++++++++++++++++ 4 files changed, 88 insertions(+) create mode 100644 checkm/1.2.2/Dockerfile create mode 100644 checkm/1.2.2/README.md diff --git a/Program_Licenses.md b/Program_Licenses.md index bcd0c34d2..614ee735d 100644 --- a/Program_Licenses.md +++ b/Program_Licenses.md @@ -23,6 +23,7 @@ The licenses of the open-source software that is contained in these Docker image | centroid | GitHub No License | https://github.com/https://github.com/stjacqrm/centroid | | CDC-SPN | GitHub No License | https://github.com/BenJamesMetcalf/Spn_Scripts_Reference | | cfsan-snp-pipeline | non-standard license see --> | https://github.com/CFSAN-Biostatistics/snp-pipeline/blob/master/LICENSE.txt | +| CheckM | GNU GPLv3 | https://github.com/Ecogenomics/CheckM/blob/master/LICENSE | | Circlator | GNU GPLv3 | https://github.com/sanger-pathogens/circlator/blob/master/LICENSE | | colorid | MIT | https://github.com/hcdenbakker/colorid/blob/master/LICENSE | | datasets-sars-cov-2 | Apache 2.0 | https://github.com/CDCgov/datasets-sars-cov-2/blob/master/LICENSE | diff --git a/README.md b/README.md index 316a18592..ae280ff73 100644 --- a/README.md +++ b/README.md @@ -126,6 +126,7 @@ To learn more about the docker pull rate limits and the open source software pro | [centroid](https://hub.docker.com/r/staphb/centroid/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/centroid)](https://hub.docker.com/r/staphb/centroid) | | https://github.com/stjacqrm/centroid | | [CDC-SPN](https://hub.docker.com/r/staphb/cdc-spn/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/cdc-spn)](https://hub.docker.com/r/staphb/cdc-spn) | | https://github.com/BenJamesMetcalf/Spn_Scripts_Reference | | [cfsan-snp-pipeline](https://hub.docker.com/r/staphb/cfsan-snp-pipeline)
[![docker pulls](https://badgen.net/docker/pulls/staphb/cfsan-snp-pipeline)](https://hub.docker.com/r/staphb/cfsan-snp-pipeline) | | https://github.com/CFSAN-Biostatistics/snp-pipeline | +| [CheckM](https://hub.docker.com/r/staphb/checkm)
[![docker pulls](https://badgen.net/docker/pulls/staphb/checkm)](https://hub.docker.com/r/staphb/checkm) | | https://github.com/Ecogenomics/CheckM | | [Circlator](https://hub.docker.com/r/staphb/circlator)
[![docker pulls](https://badgen.net/docker/pulls/staphb/circlator)](https://hub.docker.com/r/staphb/circlator) | | https://github.com/sanger-pathogens/circlator | | [Clustalo](https://hub.docker.com/r/staphb/clustalo)
[![docker pulls](https://badgen.net/docker/pulls/staphb/clustalo)](https://hub.docker.com/r/staphb/clustalo) | | http://www.clustal.org/omega/ | | [colorid](https://hub.docker.com/r/staphb/colorid)
[![docker pulls](https://badgen.net/docker/pulls/staphb/colorid)](https://hub.docker.com/r/staphb/colorid) | | https://github.com/hcdenbakker/colorid | diff --git a/checkm/1.2.2/Dockerfile b/checkm/1.2.2/Dockerfile new file mode 100644 index 000000000..b1866923d --- /dev/null +++ b/checkm/1.2.2/Dockerfile @@ -0,0 +1,50 @@ +FROM ubuntu:jammy as app + +ARG CHECKM_VER="1.2.2" +ARG PPLACER_VER="v1.1.alpha19" + +LABEL base.image="ubuntu:jammy" +LABEL dockerfile.version="1" +LABEL software="CheckM" +LABEL software.version="${CHECKM_VER}" +LABEL description="CheckM provides a set of tools for assessing the quality of genomes recovered from isolates, single cells, or metagenomes." +LABEL website="dockerfile-template/Dockerfile dockerfile-template/README.md" +LABEL license="https://github.com/Ecogenomics/CheckM/blob/master/LICENSE" +LABEL maintainer="Kutluhan Incekara" +LABEL maintainer.email="kutluhan.incekara@ct.gov" + +# install system requirements +RUN apt-get update && apt-get install -y --no-install-recommends \ + wget \ + unzip \ + python3-pip \ + hmmer \ + prodigal &&\ + apt-get autoclean && rm -rf /var/lib/apt/lists/* + +# install checkm and its dependencies +RUN pip install --no-cache-dir numpy matplotlib pysam checkm-genome &&\ + wget https://github.com/matsen/pplacer/releases/download/${PPLACER_VER}/pplacer-linux-${PPLACER_VER}.zip && \ + unzip pplacer-linux-${PPLACER_VER}.zip && rm pplacer-linux-${PPLACER_VER}.zip + +ENV PATH=$PATH:/pplacer-Linux-${PPLACER_VER} \ + LC_ALL=C + +# 'CMD' instructions set a default command when the container is run. +CMD [ "checkm", "-h" ] + +# 'WORKDIR' sets working directory +WORKDIR /data + +## Test ## +FROM app as test + +# download database and inform CheckM of where the files have been placed +RUN wget https://data.ace.uq.edu.au/public/CheckM_databases/checkm_data_2015_01_16.tar.gz &&\ + mkdir checkm_db && tar -C checkm_db -xvf checkm_data_2015_01_16.tar.gz &&\ + checkm data setRoot checkm_db + +# run an internal test +RUN checkm test ./checkm_test_results &&\ + tail -n2 ./checkm_test_results/checkm.log &&\ + head ./checkm_test_results/results/qa_test.tsv diff --git a/checkm/1.2.2/README.md b/checkm/1.2.2/README.md new file mode 100644 index 000000000..b471ab42a --- /dev/null +++ b/checkm/1.2.2/README.md @@ -0,0 +1,36 @@ +# CheckM container + +Main tool: [CheckM](https://github.com/Ecogenomics/CheckM) + +Code repository: https://github.com/Ecogenomics/CheckM + +Additional tools: +- HHMER: 3.3.2 +- prodigal: 2.6.3 +- pplacer: 1.1.alpha19-0-g807f6f3 + +Basic information on how to use this tool: +- executable: checkm +- help: <-h> +- version: <-h> +- description: CheckM provides a set of tools for assessing the quality of genomes recovered from isolates, single cells, or metagenomes. + +Additional information: + +This container does not include precalculated data files that CheckM relies on
+Those files can be downloaded from either: +- https://data.ace.uq.edu.au/public/CheckM_databases +- https://zenodo.org/record/7401545#.Y44ymHbMJD8 + +The reference data must be decompress into a directory. Inform CheckM of where the files have been placed with the following command: +``` +checkm data setRoot +``` + +Full documentation: https://github.com/Ecogenomics/CheckM/wiki + +## Example Usage + +```bash +checkm lineage_wf -t 8 -x fasta input_folder output_folder +``` From c96f22f7a5ca9fa6385a129f6f0241025fb1139b Mon Sep 17 00:00:00 2001 From: Kincekara Date: Thu, 26 Oct 2023 21:30:03 +0000 Subject: [PATCH 2/4] fix test --- checkm/1.2.2/Dockerfile | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/checkm/1.2.2/Dockerfile b/checkm/1.2.2/Dockerfile index b1866923d..571add7de 100644 --- a/checkm/1.2.2/Dockerfile +++ b/checkm/1.2.2/Dockerfile @@ -44,7 +44,6 @@ RUN wget https://data.ace.uq.edu.au/public/CheckM_databases/checkm_data_2015_01_ mkdir checkm_db && tar -C checkm_db -xvf checkm_data_2015_01_16.tar.gz &&\ checkm data setRoot checkm_db -# run an internal test -RUN checkm test ./checkm_test_results &&\ - tail -n2 ./checkm_test_results/checkm.log &&\ - head ./checkm_test_results/results/qa_test.tsv +# run test with internal test data +RUN checkm lineage_wf -r ./checkm_db/test_data/ ./checkm_test_results + From 7b34e98214b043bd52c6ffadff359842e0f59dc2 Mon Sep 17 00:00:00 2001 From: Kincekara Date: Tue, 31 Oct 2023 13:00:30 +0000 Subject: [PATCH 3/4] change test workflow --- checkm/1.2.2/Dockerfile | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/checkm/1.2.2/Dockerfile b/checkm/1.2.2/Dockerfile index 571add7de..3564e602e 100644 --- a/checkm/1.2.2/Dockerfile +++ b/checkm/1.2.2/Dockerfile @@ -45,5 +45,5 @@ RUN wget https://data.ace.uq.edu.au/public/CheckM_databases/checkm_data_2015_01_ checkm data setRoot checkm_db # run test with internal test data -RUN checkm lineage_wf -r ./checkm_db/test_data/ ./checkm_test_results +RUN checkm taxonomy_wf species "Escherichia coli" ./checkm_db/test_data/ ./checkm_test_results From 3f78628b9db9c00201396b53794c810bcee949e5 Mon Sep 17 00:00:00 2001 From: Young Date: Tue, 31 Oct 2023 11:57:58 -0600 Subject: [PATCH 4/4] Added hyperlink --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index ae280ff73..be7b5eae5 100644 --- a/README.md +++ b/README.md @@ -126,7 +126,7 @@ To learn more about the docker pull rate limits and the open source software pro | [centroid](https://hub.docker.com/r/staphb/centroid/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/centroid)](https://hub.docker.com/r/staphb/centroid) |
  • 1.0.0
| https://github.com/stjacqrm/centroid | | [CDC-SPN](https://hub.docker.com/r/staphb/cdc-spn/)
[![docker pulls](https://badgen.net/docker/pulls/staphb/cdc-spn)](https://hub.docker.com/r/staphb/cdc-spn) |
  • 0.1 (no version)
| https://github.com/BenJamesMetcalf/Spn_Scripts_Reference | | [cfsan-snp-pipeline](https://hub.docker.com/r/staphb/cfsan-snp-pipeline)
[![docker pulls](https://badgen.net/docker/pulls/staphb/cfsan-snp-pipeline)](https://hub.docker.com/r/staphb/cfsan-snp-pipeline) |
  • 2.0.2
  • 2.2.1
| https://github.com/CFSAN-Biostatistics/snp-pipeline | -| [CheckM](https://hub.docker.com/r/staphb/checkm)
[![docker pulls](https://badgen.net/docker/pulls/staphb/checkm)](https://hub.docker.com/r/staphb/checkm) |
  • 1.2.2
| https://github.com/Ecogenomics/CheckM | +| [CheckM](https://hub.docker.com/r/staphb/checkm)
[![docker pulls](https://badgen.net/docker/pulls/staphb/checkm)](https://hub.docker.com/r/staphb/checkm) |
  • [1.2.2](./checkm/1.2.2)
| https://github.com/Ecogenomics/CheckM | | [Circlator](https://hub.docker.com/r/staphb/circlator)
[![docker pulls](https://badgen.net/docker/pulls/staphb/circlator)](https://hub.docker.com/r/staphb/circlator) |
  • 1.5.6
  • 1.5.5
| https://github.com/sanger-pathogens/circlator | | [Clustalo](https://hub.docker.com/r/staphb/clustalo)
[![docker pulls](https://badgen.net/docker/pulls/staphb/clustalo)](https://hub.docker.com/r/staphb/clustalo) |
  • 1.2.4
| http://www.clustal.org/omega/ | | [colorid](https://hub.docker.com/r/staphb/colorid)
[![docker pulls](https://badgen.net/docker/pulls/staphb/colorid)](https://hub.docker.com/r/staphb/colorid) |
  • 0.1.4.3
| https://github.com/hcdenbakker/colorid |