-
Notifications
You must be signed in to change notification settings - Fork 126
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
adding kaptive version 3.0.0b6 (#1091)
* adding kaptive version 3.0.0b6 * updated usage * added help and version * minor changes to kaptive dockerfile and readme --------- Co-authored-by: Curtis Kapsak <[email protected]>
- Loading branch information
Showing
3 changed files
with
182 additions
and
1 deletion.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,120 @@ | ||
| FROM ubuntu:jammy AS app | ||
|
|
||
| # for easy upgrade later. ARG variables only persist during image build time | ||
| ARG MINIMAP2_VER="2.28" | ||
| ARG MASH_VER="2.3" | ||
| ARG KAPTIVE_VER="3.0.0b6" | ||
| ARG VP_GENOMOSEROTYPING_VER="1.0" | ||
|
|
||
| LABEL base.image="ubuntu:jammy" | ||
| LABEL dockerfile.version="1" | ||
| LABEL software="Kaptive" | ||
| LABEL software.version="${KAPTIVE_VER}" | ||
| LABEL description="Report information about surface polysaccharide loci for Klebsiella pneumoniae species complex and Acinetobacter baumannii genome assemblies" | ||
| LABEL website="https://github.com/klebgenomics/Kaptive/" | ||
| LABEL license="https://github.com/klebgenomics/Kaptive/blob/master/LICENSE" | ||
| LABEL website.VPdatabase="https://github.com/aldertzomer/vibrio_parahaemolyticus_genomoserotyping" | ||
| LABEL license.VPdatabase="https://github.com/aldertzomer/vibrio_parahaemolyticus_genomoserotyping/blob/main/LICENSE" | ||
| LABEL maintainer="Tamas Stirling" | ||
| LABEL maintainer.email="[email protected]" | ||
| LABEL maintainer2="Curtis Kapsak" | ||
| LABEL maintainer2.email="[email protected]" | ||
| LABEL maintainer3="Erin Young" | ||
| LABEL maintainer3.email="[email protected]" | ||
|
|
||
| # install prerequisites. Cleanup apt garbage | ||
| RUN apt-get update && apt-get install -y --no-install-recommends \ | ||
| python3 \ | ||
| python3-pip \ | ||
| wget \ | ||
| ca-certificates \ | ||
| bzip2 \ | ||
| procps \ | ||
| curl && \ | ||
| rm -rf /var/lib/apt/lists/* && apt-get autoclean | ||
|
|
||
| # mash; update UID and GID of mash files; make /data | ||
| # UID and GID changes because the original owner is UID: 1081147385 and GID: 1360859114 which does NOT play well with systems that limits GIDs and UIDs | ||
| RUN wget -q https://github.com/marbl/Mash/releases/download/v${MASH_VER}/mash-Linux64-v${MASH_VER}.tar && \ | ||
| tar -xvf mash-Linux64-v${MASH_VER}.tar --no-same-owner && \ | ||
| rm -rf mash-Linux64-v${MASH_VER}.tar && \ | ||
| chown root:root /mash-Linux64-v${MASH_VER}/* | ||
|
|
||
| # install minimap2 binary; make /data | ||
| 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 | ||
|
|
||
| # install kaptive | ||
| RUN pip install --no-cache-dir kaptive==${KAPTIVE_VER} | ||
|
|
||
| # move databases | ||
| RUN wget -q https://github.com/klebgenomics/Kaptive/releases/download/v${KAPTIVE_VER}/kaptive-${KAPTIVE_VER}.tar.gz && \ | ||
| tar -vxf kaptive-${KAPTIVE_VER}.tar.gz --no-same-owner && \ | ||
| mkdir -p /data /kaptive/ && \ | ||
| mv /kaptive-${KAPTIVE_VER}/reference_database /kaptive/reference_database && \ | ||
| rm -rf kaptive-${KAPTIVE_VER}.tar.gz kaptive-${KAPTIVE_VER} | ||
|
|
||
| # download Vibrio parahemolyticus database; mv gbk files to where the other references are | ||
| RUN wget -q https://github.com/aldertzomer/vibrio_parahaemolyticus_genomoserotyping/archive/refs/tags/${VP_GENOMOSEROTYPING_VER}.tar.gz && \ | ||
| tar -xzf ${VP_GENOMOSEROTYPING_VER}.tar.gz && \ | ||
| rm -v ${VP_GENOMOSEROTYPING_VER}.tar.gz && \ | ||
| mv -v vibrio_parahaemolyticus_genomoserotyping-${VP_GENOMOSEROTYPING_VER}/*gbk /kaptive/reference_database/. && \ | ||
| rm -rf vibrio_parahaemolyticus_genomoserotyping-${VP_GENOMOSEROTYPING_VER} | ||
|
|
||
| # set PATH | ||
| ENV PATH="/mash-Linux64-v${MASH_VER}:/minimap2-${MINIMAP2_VER}_x64-linux:${PATH}" | ||
|
|
||
| # set working directory | ||
| WORKDIR /data | ||
|
|
||
| # default command is to print help options | ||
| CMD [ "kaptive", "--help" ] | ||
|
|
||
| # test layer | ||
| FROM app AS test | ||
|
|
||
| RUN kaptive --help && kaptive --version | ||
|
|
||
| WORKDIR /test1 | ||
|
|
||
| # test with A. baumannii; testing both k and o locus | ||
| RUN echo "downloading an A. baumannii genome & testing Kaptive..." && \ | ||
| wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/016/486/705/GCA_016486705.1_PDT000751301.1/GCA_016486705.1_PDT000751301.1_genomic.fna.gz && \ | ||
| gzip -d GCA_016486705.1_PDT000751301.1_genomic.fna.gz && \ | ||
| kaptive assembly /kaptive/reference_database/Acinetobacter_baumannii_k_locus_primary_reference.gbk GCA_016486705.1_PDT000751301.1_genomic.fna -o abau_k.txt && head abau_k.txt && \ | ||
| kaptive assembly /kaptive/reference_database/Acinetobacter_baumannii_OC_locus_primary_reference.gbk GCA_016486705.1_PDT000751301.1_genomic.fna -o abau_oc.txt && head abau_oc.txt | ||
|
|
||
| WORKDIR /test2 | ||
| # test with K. pneumoniae; testing both k and o locus | ||
| RUN echo "downloading an K. pneumoniae genome & testing Kaptive..." && \ | ||
| wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/022/268/055/GCA_022268055.1_PDT000434809.1/GCA_022268055.1_PDT000434809.1_genomic.fna.gz && \ | ||
| gzip -d GCA_022268055.1_PDT000434809.1_genomic.fna.gz && \ | ||
| kaptive assembly /kaptive/reference_database/Klebsiella_k_locus_primary_reference.gbk GCA_022268055.1_PDT000434809.1_genomic.fna -o kpneu_k.txt && \ | ||
| kaptive assembly /kaptive/reference_database/Klebsiella_o_locus_primary_reference.gbk GCA_022268055.1_PDT000434809.1_genomic.fna -o kpneu_o.txt && \ | ||
| head kpneu_k.txt kpneu_o.txt | ||
|
|
||
| WORKDIR /test3 | ||
| # test with recommended usage in documentatation | ||
| RUN echo "downloading an K. pneumoniae genome & testing Kaptive..." && \ | ||
| wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCA/022/268/055/GCA_022268055.1_PDT000434809.1/GCA_022268055.1_PDT000434809.1_genomic.fna.gz && \ | ||
| gzip -d GCA_022268055.1_PDT000434809.1_genomic.fna.gz && \ | ||
| kaptive assembly kpsc_k assemblies/*.fna -o kaptive_results.tsv && \ | ||
| head kaptive_results.tsv | ||
|
|
||
| WORKDIR /test4 | ||
|
|
||
| ### test with at 2 Vibrio parahaemolyticus genomes with a known serotype. These 2 are pulled from the publication describing custom database ## | ||
| # GCA_001558495.2 - expect OL1 and KL1 | ||
| # GCA_001728135.1 - expect OL4 KL53 | ||
| # more info on test genome here: https://www.ncbi.nlm.nih.gov/data-hub/genome/GCF_001558495.2/ | ||
| # strain: ATCC17802 | ||
| # more info on 2nd test genome here: https://www.ncbi.nlm.nih.gov/data-hub/genome/GCF_001728135.1/ | ||
| # strain: CDC_K5009W | ||
| RUN echo "downloading an 2 V. parahaemolyticus genomes & testing Kaptive..." && \ | ||
| wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/558/495/GCF_001558495.2_ASM155849v2/GCF_001558495.2_ASM155849v2_genomic.fna.gz && \ | ||
| wget -q https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/001/728/135/GCF_001728135.1_ASM172813v1/GCF_001728135.1_ASM172813v1_genomic.fna.gz && \ | ||
| gzip -d GCF_001558495.2_ASM155849v2_genomic.fna.gz && \ | ||
| gzip -d GCF_001728135.1_ASM172813v1_genomic.fna.gz && \ | ||
| kaptive assembly /kaptive/reference_database/VibrioPara_Kaptivedb_K.gbk *.fna -o Vparahaemolyticus_K.txt && \ | ||
| kaptive assembly /kaptive/reference_database/VibrioPara_Kaptivedb_O.gbk *.fna -o Vparahaemolyticus_O.txt && \ | ||
| head Vparahaemolyticus_K.txt Vparahaemolyticus_O.txt |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,61 @@ | ||
| # Kaptive Container | ||
|
|
||
| Main tool: [Kaptive](https://github.com/klebgenomics/Kaptive) | ||
|
|
||
| Additional tools: | ||
|
|
||
| - minimap2 2.28 | ||
| - python 3.10.12 | ||
| - biopython 1.84 | ||
| - matplotlib 3.9.2 | ||
| - dna-features-viewer 3.1.3 | ||
| - numpy 2.1.3 | ||
|
|
||
| ## Kaptive databases | ||
|
|
||
| There are few databases included in this docker image: | ||
|
|
||
| - Klebsiella pneumoniae species complex | ||
| - included w/ Kaptive | ||
| - Acinetobacter baumannii | ||
| - included w/ Kaptive | ||
| - Vibrio parahaemolyticus | ||
| - Located in separate GitHub repo: https://github.com/aldertzomer/vibrio_parahaemolyticus_genomoserotyping | ||
| - Publication: https://www.microbiologyresearch.org/content/journal/mgen/10.1099/mgen.0.001007 | ||
|
|
||
| The databases (Genbank/GBK files) are located as follows in the container filesystem: | ||
|
|
||
| ```bash | ||
| # Klebsiella pneumoniae species complex | ||
| /kaptive/reference_database/Klebsiella_k_locus_primary_reference.gbk | ||
| /kaptive/reference_database/Klebsiella_o_locus_primary_reference.gbk | ||
|
|
||
| # Acinetobacter baumannii | ||
| /kaptive/reference_database/Acinetobacter_baumannii_k_locus_primary_reference.gbk | ||
| /kaptive/reference_database/Acinetobacter_baumannii_OC_locus_primary_reference.gbk | ||
|
|
||
| # Vibrio parahaeolyticus | ||
| /kaptive/reference_database/VibrioPara_Kaptivedb_K.gbk | ||
| /kaptive/reference_database/VibrioPara_Kaptivedb_O.gbk | ||
| ``` | ||
|
|
||
| Example commands for each of these databases can be found below. | ||
|
|
||
| ## Example Usage | ||
|
|
||
| ```bash | ||
| # K locus, A. baumannii | ||
| kaptive.py assembly /kaptive/reference_database/Acinetobacter_baumannii_k_locus_primary_reference.gbk assembly.fasta -o outfile.txt | ||
| # O locus, A. baumannii | ||
| kaptive.py assembly /kaptive/reference_database/Acinetobacter_baumannii_OC_locus_primary_reference.gbk assembly.fasta -o outfile.txt | ||
|
|
||
| # K locus, K. pneumoniae | ||
| kaptive.py assembly /kaptive/reference_database/Klebsiella_k_locus_primary_reference.gbk assembly.fasta -o outfile.txt | ||
| # O locus, K. pneumoniae | ||
| kaptive.py assembly /kaptive/reference_database/Klebsiella_o_locus_primary_reference.gbk assembly.fasta -o outfile.txt | ||
|
|
||
| # K locus, V. parahaemolyticus | ||
| kaptive.py assembly /kaptive/reference_database/VibrioPara_Kaptivedb_K.gbk assembly.fasta -o outfile.txt | ||
| # O locus, V. parahaemolyticus | ||
| kaptive.py assembly /kaptive/reference_database/VibrioPara_Kaptivedb_O.gbk assembly.fasta -o outfile.txt | ||
| ``` |