Merge pull request #803 from HarryHung/poppunk-2.6.2

Add v2.6.2 to PopPUNK

README.md

@@ -210,7 +210,7 @@ To learn more about the docker pull rate limits and the open source software pro
 | [PlasmidSeeker](https://hub.docker.com/r/staphb/plasmidseeker) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/plasmidseeker)](https://hub.docker.com/r/staphb/plasmidseeker) | <ul><li>1.0</li><li>1.3</li></ul> | https://github.com/bioinfo-ut/PlasmidSeeker |
 | [pmga](https://hub.docker.com/r/staphb/pmga/) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/pmga)](https://hub.docker.com/r/staphb/pmga) | <ul><li>3.0.2</li></ul> | https://github.com/rpetit3/pmga |
 | [polypolish](https://hub.docker.com/r/staphb/polypolish/) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/polypolish)](https://hub.docker.com/r/staphb/polypolish) | <ul><li>0.5.0</li></ul> | https://github.com/rrwick/Polypolish |
-| [PopPUNK](https://hub.docker.com/r/staphb/poppunk/) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/poppunk)](https://hub.docker.com/r/staphb/poppunk) | <ul><li>2.4.0</li><li>2.5.0</li><li>2.6.0</li></ul> | https://github.com/bacpop/PopPUNK |
+| [PopPUNK](https://hub.docker.com/r/staphb/poppunk/) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/poppunk)](https://hub.docker.com/r/staphb/poppunk) | <ul><li>[2.4.0](./poppunk/2.4.0/)</li><li>[2.5.0](./poppunk/2.5.0/)</li><li>[2.6.0](./poppunk/2.6.0/)</li><li>[2.6.2](./poppunk/2.6.2/)</li></ul> | https://github.com/bacpop/PopPUNK |
 | [Porechop](https://hub.docker.com/r/staphb/porechop/) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/porechop)](https://hub.docker.com/r/staphb/porechop) | <ul><li>0.2.4</li></ul> | https://github.com/rrwick/Porechop |
 | [Prokka](https://hub.docker.com/r/staphb/prokka/) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/prokka)](https://hub.docker.com/r/staphb/prokka) | <ul><li>1.13.4</li><li>1.14.0</li><li>1.14.5</li><li>1.14.6</li></ul> | https://github.com/tseemann/prokka |
 | [pyCirclize](https://hub.docker.com/r/staphb/pycirclize/) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/pycirclize)](https://hub.docker.com/r/staphb/pycirclize) | <ul><li>[1.0.0](pycirclize/1.0.0/)</li></ul> | https://github.com/moshi4/pyCirclize |

poppunk/2.6.2/Dockerfile

@@ -0,0 +1,65 @@
+FROM mambaorg/micromamba:1.5.3 as app
+
+# Version arguments
+# ARG variables only persist during build time
+ARG POPPUNK_VERSION="2.6.2"
+
+# build and run as root users since micromamba image has 'mambauser' set as the $USER
+USER root
+# set workdir to default for building; set to /data at the end
+WORKDIR /
+
+LABEL base.image="mambaorg/micromamba:1.5.3"
+LABEL dockerfile.version="2"
+LABEL software="PopPUNK"
+LABEL software.version=${POPPUNK_VERSION}
+LABEL description="POPulation Partitioning Using Nucleotide Kmers"
+LABEL website="https://github.com/bacpop/PopPUNK"
+LABEL license="https://github.com/bacpop/PopPUNK/blob/master/LICENSE"
+LABEL maintainer="Curtis Kapsak"
+LABEL maintainer.email="[email protected]"
+LABEL maintainer2="Harry Hung"
+LABEL maintainer2.email="[email protected]"
+
+# install dependencies; cleanup apt garbage
+RUN apt-get update && apt-get install -y --no-install-recommends \
+ wget \
+ ca-certificates \
+ procps && \
+ apt-get autoclean && rm -rf /var/lib/apt/lists/*
+
+# Create PopPUNK conda environment called poppunk-env from bioconda recipe
+# clean up conda garbage
+RUN micromamba create -n poppunk-env -c conda-forge -c bioconda -c defaults poppunk=${POPPUNK_VERSION} && \
+ micromamba clean -a -y
+
+# set the environment, put new conda env in PATH by default; set locales to UTF-8
+ENV PATH="/opt/conda/envs/poppunk-env/bin:${PATH}" \
+ LC_ALL=C.UTF-8
+
+# set working directory to /data
+WORKDIR /data
+
+# new base for testing
+FROM app as test
+
+# so that mamba/conda env is active when running below commands
+ENV ENV_NAME="poppunk-env"
+ARG MAMBA_DOCKERFILE_ACTIVATE=1
+
+# print out various help options and version
+RUN poppunk --help && \
+ poppunk_assign --help && \
+ poppunk_visualise --help && \
+ poppunk_mst --help && \
+ poppunk_references --help && \
+ poppunk_info --help && \
+ poppunk_mandrake --help && \
+ poppunk --version
+
+# Download 100 S. Pneumo assemblies from GPS Public Data on ENA
+# Build PopPUNK database from the assemblies
+# Assign clusters on the same assemblies using the built database
+# Compare the database clusters and assigned clusters of the assemblies
+COPY test.sh ftps.txt /data/
+RUN bash test.sh

poppunk/2.6.2/README.md

@@ -0,0 +1,56 @@
+# PopPUNK container
+
+Main tool : 
+- [PopPUNK](https://github.com/bacpop/PopPUNK)
+
+Additional tools:
+- biopython 1.81
+- pp-sketchlib 2.1.1
+- python 3.10.13
+- rapidnj 2.3.2
+- treeswift 1.1.38
+
+Full documentation: [https://poppunk.readthedocs.io/en/latest/](https://poppunk.readthedocs.io/en/latest/)
+
+PopPUNK is also available as a webtool: [https://www.poppunk.net/](https://www.poppunk.net/)
+
+PopPUNK is a tool for clustering genomes.
+
+*NOTE: This docker image is intended for the CLI usage of the PopPUNK tool. It has not been built with the full web-interface functionality in mind.*
+
+## Example Usage
+
+This example is for usage of PopPUNK for Streptococcus pneumoniae clustering using a database & reference files provided by the [Global Pneumococcal Sequencing Project](https://www.pneumogen.net/gps/training_command_line.html). An example S. pneumoniae genome can be obtained from [here](https://github.com/rpetit3/pbptyper/blob/main/test/SRR2912551.fna.gz)
+
+```bash
+# poppunk requires an input File Of File Names (FOFN). headerless TSV with a sample name (first column), followed by path to input FASTA
+$ echo -e "SRR2912551\t/data/SRR2912551.fna.gz" > poppunk_input.tsv
+
+# showing reference files, FASTA input, and poppunk_input.tsv
+$ ls
+GPS_v6/  GPS_v6_external_clusters.csv  SRR2912551.fna.gz  poppunk_input.tsv
+
+# run the docker container interactively
+# followed by poppunk command run inside the container
+$ docker run --rm -ti -v ${PWD}:/data -u $(id -u):$(id -g) staphb/poppunk:2.6.2
+$ poppunk_assign --db GPS_v6 --distances GPS_v6/GPS_v6.dists --query /data/poppunk_input.tsv --output docker_test --external-clustering GPS_v6_external_clusters.csv
+PopPUNK: assign
+        (with backend: sketchlib v2.0.0
+         sketchlib: /opt/conda/envs/poppunk-env/lib/python3.10/site-packages/pp_sketchlib.cpython-310-x86_64-linux-gnu.so)
+
+Graph-tools OpenMP parallelisation enabled: with 1 threads
+Mode: Assigning clusters of query sequences
+
+Loading previously refined model
+Completed model loading
+Sketching 1 genomes using 1 thread(s)
+Progress (CPU): 1 / 1
+Writing sketches to file
+WARNING: versions of input databases sketches are different, results may not be compatible
+Calculating distances using 1 thread(s)
+Progress (CPU): 100.0%
+Selected type isolate for distance QC is 10050_2#1
+Network loaded: 42163 samples
+
+Done
+```

poppunk/2.6.2/ftps.txt

@@ -0,0 +1,100 @@
+ftp.sra.ebi.ac.uk/vol1/ERZ322/ERZ3224520/SAMEA3171250.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3198719/SAMEA2554210.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ322/ERZ3225470/SAMEA3175912.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3213352/SAMEA2696388.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3198630/SAMEA2554162.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3217126/SAMEA2783707.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ342/ERZ3423083/SAMEA3447953.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3218603/SAMEA2797493.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ304/ERZ3040777/SAMEA104035490.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ304/ERZ3041170/SAMEA104035895.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3206617/SAMEA2658361.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3218818/SAMEA2814082.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ937/ERZ9377441/SAMEA4763391.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3206566/SAMEA2658309.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3195033/SAMEA2467770.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3079299/SAMEA104154757.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3193270/SAMEA2434815.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3079844/SAMEA104155118.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ289/ERZ2890096/SAMEA102263668.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3079332/SAMEA104154777.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3218215/SAMEA2797058.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ322/ERZ3225910/SAMEA3176187.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3197406/SAMEA2521772.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ316/ERZ3164266/SAMEA2204200.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3192969/SAMEA2434607.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ930/ERZ9307577/SAMEA3232684.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ313/ERZ3136035/SAMEA2051001.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3218069/SAMEA2796905.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ304/ERZ3041120/SAMEA104035851.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3078938/SAMEA104154484.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3207298/SAMEA2659051.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3197214/SAMEA2521572.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3078796/SAMEA104154345.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3217801/SAMEA2796638.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ325/ERZ3251997/SAMEA3309548.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ314/ERZ3148576/SAMEA2066281.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3192932/SAMEA2434566.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3206876/SAMEA2658626.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ342/ERZ3425910/SAMEA3486806.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3219036/SAMEA2814305.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ342/ERZ3423073/SAMEA3447941.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ315/ERZ3157278/SAMEA2160059.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ347/ERZ3470667/SAMEA3504771.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3206664/SAMEA2658409.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3219281/SAMEA2814555.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3217894/SAMEA2796732.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3198788/SAMEA2554243.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3078812/SAMEA104154360.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ937/ERZ9377474/SAMEA4763408.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3079689/SAMEA104155019.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3217835/SAMEA2796676.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3198813/SAMEA2554255.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ355/ERZ3557099/SAMEA4732546.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ304/ERZ3041014/SAMEA104035733.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3193000/SAMEA2434629.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3079342/SAMEA104154791.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ318/ERZ3180205/SAMEA2298232.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3204423/SAMEA2627391.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ347/ERZ3470928/SAMEA3504807.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ325/ERZ3255898/SAMEA3354185.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ937/ERZ9378367/SAMEA4763819.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ313/ERZ3137747/SAMEA2057315.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ318/ERZ3180296/SAMEA2298295.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3206874/SAMEA2658623.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ349/ERZ3499256/SAMEA3714360.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ304/ERZ3040602/SAMEA104035309.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3218412/SAMEA2797262.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ318/ERZ3181632/SAMEA2335756.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ325/ERZ3255160/SAMEA3353584.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3204680/SAMEA2627527.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ322/ERZ3225180/SAMEA3175678.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ930/ERZ9308145/SAMEA3233336.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ342/ERZ3421572/SAMEA3431627.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ325/ERZ3256127/SAMEA3354364.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3204642/SAMEA2627509.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3218686/SAMEA2813951.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3198971/SAMEA2554336.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ355/ERZ3557464/SAMEA4732913.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ326/ERZ3260947/SAMEA3389675.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3213543/SAMEA2696586.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3204451/SAMEA2627406.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ325/ERZ3258030/SAMEA3373712.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3079114/SAMEA104154622.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ318/ERZ3180293/SAMEA2298296.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ930/ERZ9303942/SAMEA3209083.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ930/ERZ9308103/SAMEA3233306.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ288/ERZ2889920/SAMEA102184918.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ930/ERZ9302272/SAMEA3206695.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ930/ERZ9303776/SAMEA3208988.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3192979/SAMEA2434614.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ320/ERZ3206542/SAMEA2658288.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3198331/SAMEA2553822.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ316/ERZ3164201/SAMEA2204129.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ325/ERZ3254708/SAMEA3353251.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ304/ERZ3041104/SAMEA104035825.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ307/ERZ3079033/SAMEA104154554.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ321/ERZ3213369/SAMEA2696405.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ319/ERZ3194930/SAMEA2467335.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ937/ERZ9379100/SAMEA4764119.contigs.fa.gz
+ftp.sra.ebi.ac.uk/vol1/ERZ304/ERZ3040936/SAMEA104035654.contigs.fa.gz

poppunk/2.6.2/test.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+set -euxo pipefail
+
+# Download 100 S. Pneumo assemblies from GPS Public Data on ENA
+mkdir assemblies
+while read link; do
+  wget -q -P assemblies $link;
+done < ftps.txt
+
+# Generate r-file for creating PopPUNK database
+for FILE in assemblies/*; do
+    printf $(basename -s .contigs.fa.gz $FILE)'\t'$FILE'\n' >> rfile.txt;
+done
+
+# Build PopPUNK database from the assemblies
+poppunk --create-db --output database --r-files rfile.txt --threads $(nproc)
+poppunk --fit-model bgmm --ref-db database
+
+# Assign clusters on the same assemblies using the built database
+# the sample names are modified as PopPUNK reject samples with names that are already in the database
+sed 's/^/prefix_/' rfile.txt > qfile.txt
+poppunk_assign --db database --query qfile.txt --output output --threads $(nproc)
+
+# Compare the database clusters and assigned clusters of the assemblies
+sed 's/^prefix_//' output/output_clusters.csv | awk 'NR == 1; NR > 1 { print $0 | "sort" }' > assigned.csv
+awk 'NR == 1; NR > 1 { print $0 | "sort" }' database/database_clusters.csv > database.csv
+cmp assigned.csv database.csv