Merge branch 'master' into master

Program_Licenses.md

@@ -7,6 +7,7 @@ The licenses of the open-source software that is contained in these Docker image
 | Software | License | Link to license |
 | :--------: | :-------: | -------- |
 | ABRicate | GNU GPLv2 | https://github.com/tseemann/abricate/blob/master/LICENSE |
+| artic | MIT | https://github.com/artic-network/fieldbioinformatics/blob/master/LICENSE |
 | artic-ncov2019-epi2me | MPL 2.0 | https://github.com/epi2me-labs/wf-artic/blob/master/LICENSE |
 | any2fasta | GNU GPLv3 | https://github.com/tseemann/any2fasta/blob/master/LICENSE |
 | ARIBA | GNU GPLv3 | https://github.com/sanger-pathogens/ariba/blob/master/LICENSE |
@@ -17,12 +18,14 @@ The licenses of the open-source software that is contained in these Docker image
 | bedtools | MIT | https://github.com/arq5x/bedtools2/blob/master/LICENSE |
 | blast+ | Public Domain | https://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/lxr/source/scripts/projects/blast/LICENSE |
 | bowtie2 | GNU GPLv3 | https://github.com/BenLangmead/bowtie2/blob/master/LICENSE |
+| Bracken | GNU GPLv3 | https://github.com/jenniferlu717/Bracken/blob/master/LICENSE |
 | BUSCO | MIT | https://gitlab.com/ezlab/busco/-/raw/master/LICENSE |
 | BWA | GNU GPLv3 | https://github.com/lh3/bwa/blob/master/COPYING |
 | Canu <br/> Racon <br/> Minimap2 | GNU GPLv3 (Canu), <br/> MIT (Racon), <br/> MIT (Minimap2) | https://github.com/marbl/canu/blob/master/README.license.GPL https://github.com/isovic/racon/blob/master/LICENSE https://github.com/lh3/minimap2/blob/master/LICENSE.txt |
 | 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 |
@@ -63,6 +66,7 @@ The licenses of the open-source software that is contained in these Docker image
 | kSNP4 | BSD | available in zipped kSNP archive on sourceforge or in docker image under `/opt/kSNP4 Linux package/Documentation/THE BSD OPENSOURCE LICENSE.pdf` |
 | legsta | GNU GPLv3 | https://github.com/tseemann/legsta/blob/master/LICENSE |
 | liftoff | GNU GPLv3 | https://github.com/agshumate/Liftoff/blob/master/LICENSE.md |
+| longshot | MIT | https://github.com/pjedge/longshot/blob/master/LICENSE |
 | Lyve-SET  | MIT | https://github.com/lskatz/lyve-SET/blob/master/LICENSE |
 | Mafft  | BSD | https://mafft.cbrc.jp/alignment/software/license.txt |
 | Mash | non-standard license (see link) | https://github.com/marbl/Mash/blob/master/LICENSE.txt |
@@ -88,6 +92,7 @@ The licenses of the open-source software that is contained in these Docker image
 | Panaroo | MIT | https://github.com/gtonkinhill/panaroo/blob/master/LICENSE |
 | Pangolin | GNU GPLv3 | https://github.com/cov-lineages/pangolin/blob/master/LICENSE.txt |
 | pasty | Apache 2.0 | https://github.com/rpetit3/pasty/blob/main/LICENSE |
+| Pavian | GNU GPLv3 | https://github.com/fbreitwieser/pavian/blob/master/DESCRIPTION |
 | pbptyper | MIT | https://github.com/rpetit3/pbptyper/blob/main/LICENSE |
 | Phyml | GNU GPLv3 | https://github.com/stephaneguindon/phyml/blob/master/COPYING |
 | Piggy | GNU GPLv3 | https://github.com/harry-thorpe/piggy/blob/master/LICENSE |

artic/1.2.4-1.11.1/Dockerfile

@@ -0,0 +1,101 @@
+ARG ARTIC_VER=1.2.4
+
+FROM mambaorg/micromamba:1.4.9 as app
+
+ARG ARTIC_VER
+ARG MEDAKA_VER=1.11.1
+
+LABEL base.image="ubuntu:jammy"
+LABEL dockerfile.version="1"
+LABEL software="artic"
+LABEL software.version="${ARTIC_VER}"
+LABEL software1="medaka"
+LABEL software1.version="${MEDAKA_VER}"
+LABEL description="A bioinformatics pipeline for working with virus sequencing data sequenced with nanopore"
+LABEL website="https://github.com/artic-network/fieldbioinformatics"
+LABEL license="https://github.com/artic-network/fieldbioinformatics/blob/master/LICENSE"
+LABEL sop="https://artic.network/ncov-2019/ncov2019-bioinformatics-sop.html"
+LABEL maintainer="Erin Young"
+LABEL maintainer.email="[email protected]"
+
+USER root
+WORKDIR /
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+    wget \
+    ca-certificates \
+    procps \
+    gcc \
+    make \
+    pkg-config \
+    zlib1g-dev \
+    libbz2-dev \
+    liblzma-dev \
+    libcurl4-gnutls-dev \
+    libssl-dev \
+    python3-dev \
+    python3-pip \
+    python-is-python3 && \
+    apt-get autoclean && rm -rf /var/lib/apt/lists/*
+
+RUN wget -q https://github.com/artic-network/fieldbioinformatics/archive/refs/tags/v${ARTIC_VER}.tar.gz && \
+    tar -xzf v${ARTIC_VER}.tar.gz && \
+    micromamba env create -y -f /fieldbioinformatics-${ARTIC_VER}/environment.yml && \
+    rm v${ARTIC_VER}.tar.gz && \
+    cd fieldbioinformatics-${ARTIC_VER} && \
+    python setup.py install && \
+    artic -v && \
+    mkdir /data
+
+ENV ENV_NAME="artic"
+ARG MAMBA_DOCKERFILE_ACTIVATE=1
+
+RUN /opt/conda/envs/artic/bin/pip install setuptools wheel cython medaka==${MEDAKA_VER} && \
+    medaka --version && \
+    /opt/conda/envs/artic/bin/pip install pyabpoa==1.2.4
+
+ENV PATH="${PATH}:/opt/conda/envs/artic/bin/" \
+    LC_ALL=C.UTF-8
+
+CMD artic --help
+
+WORKDIR /data
+
+##### ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- #####
+##### Step 2. Set up the testing stage.                                 #####
+##### The docker image is built to the 'test' stage before merging, but #####
+##### the test stage (or any stage after 'app') will be lost.           #####
+##### ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- ----- #####
+
+# A second FROM insruction creates a new stage
+# new base for testing
+FROM app as test
+ARG ARTIC_VER
+
+# print help and version info; check dependencies (not all software has these options available)
+# Mostly this ensures the tool of choice is in path and is executable
+RUN artic --help && \
+    artic --version
+
+# listing available models
+RUN medaka tools list\_models
+
+# set working directory so that all test inputs & outputs are kept in /test
+WORKDIR /fieldbioinformatics-${ARTIC_VER}
+
+# test that came with artic
+RUN bash ./test-runner.sh medaka && bash ./test-runner.sh nanopolish
+
+WORKDIR /test
+
+# using on "real" data (sample files were not sequenced with version 5.3.2 primers)
+RUN wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR224/050/SRR22452250/SRR22452250_1.fastq.gz && \
+    artic guppyplex --min-length 400 --max-length 700  --directory . --prefix SRR22452250_1.fastq.gz --output SRR22452250_1_filtered.fastq.gz && \ 
+    mkdir -p dir/name/V5 && \
+    wget -q https://raw.githubusercontent.com/artic-network/primer-schemes/master/nCoV-2019/V5.3.2/SARS-CoV-2.primer.bed      -O dir/name/V5/name.primer.bed && \
+    wget -q https://raw.githubusercontent.com/artic-network/primer-schemes/master/nCoV-2019/V5.3.2/SARS-CoV-2.reference.fasta -O dir/name/V5/name.reference.fasta  && \
+    wget -q https://raw.githubusercontent.com/artic-network/primer-schemes/master/nCoV-2019/V5.3.2/SARS-CoV-2.scheme.bed      -O dir/name/V5/name.scheme.bed && \
+    samtools faidx dir/name/V5/name.reference.fasta && \
+    artic minion --normalise 200 --skip-nanopolish --medaka --medaka-model r941_min_high_g360 --threads 4 --read-file SRR22452250_1_filtered.fastq.gz --scheme-directory ./dir --scheme-version 5 name final && \
+    ls final*
+

artic/1.2.4-1.11.1/README.md

@@ -0,0 +1,66 @@
+# artic fieldbioinformatics container
+
+Main tool : [artic](https://github.com/artic-network/fieldbioinformatics)
+
+Additional tools:
+
+- medaka=1.11.1
+
+Full documentation: [https://github.com/artic-network/fieldbioinformatics](https://github.com/artic-network/fieldbioinformatics)
+
+There is also a very useful SOP: [https://artic.network/ncov-2019/ncov2019-bioinformatics-sop.html](https://artic.network/ncov-2019/ncov2019-bioinformatics-sop.html)
+And additional documentation: [https://artic.readthedocs.io/en/latest/](https://artic.readthedocs.io/en/latest/)
+
+> A bioinformatics pipeline for working with virus sequencing data sequenced with nanopore.
+
+WARNING : This container does not contain the primer schemes found at [https://github.com/artic-network/primer-schemes](https://github.com/artic-network/primer-schemes). Those will have to be downloaded and mounted separately.
+
+## Example Usage with the artic primers
+
+```bash
+# get primers
+git clone https://github.com/artic-network/primer-schemes
+
+# download reads for example
+wget -q ftp://ftp.sra.ebi.ac.uk/vol1/fastq/SRR224/050/SRR22452250/SRR22452250_1.fastq.gz
+
+# read filtering
+docker run -v $(pwd):/data staphb/artic:latest artic guppyplex --min-length 400 --max-length 700  --directory . --prefix SRR22452250_1.fastq.gz --output SRR22452250_1_filtered.fastq.gz
+
+# running the artic minion workflow with medaka
+docker run -v $(pwd):/data staphb/artic:latest artic minion --normalise 200 --skip-nanopolish --medaka --medaka-model r941_min_high_g360 --threads 4 --read-file SRR22452250_1_filtered.fastq.gz --scheme-directory primer-schemes --scheme-version 5.3.2 nCoV-2019 test
+
+# the result files will all start with test*
+```
+
+In general, any primer scheme can be used as long as it meeds [artic's requirments](https://github.com/artic-network/primer-schemes).
+
+This is the recommended directory structure with corresponding files:
+
+```bash
+${diretory}/${name}/V${version}/${name}.primer.bed
+${diretory}/${name}/V${version}/${name}.scheme.bed
+${diretory}/${name}/V${version}/${name}.reference.fasta
+${diretory}/${name}/V${version}/${name}.reference.fasta.fai
+```
+
+The command to use this primer scheme would be
+
+```bash
+artic minion --normalise 200 --skip-nanopolish --medaka --medaka-model r941_min_high_g360 --threads 4 --read-file input.fastq.gz --scheme-directory ${directory} --scheme-version ${version} ${name} outputprefix
+```
+
+Different primer schemes can be validated via artic-tools (already in PATH) via
+
+```bash
+artic-tools validate_scheme ${basename}.primer.bed --outputInserts ${basename}.insert.bed
+```
+
+## Medaka models
+
+Medaka updates frequently, and artic can throw errors when corresponding ONT models are not found.
+
+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_min_high_g345, r103_min_high_g360, r103_prom_high_g360, r103_prom_snp_g3210, r103_prom_variant_g3210, 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_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_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_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_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_variant_g615, r1041_e82_400bps_sup_variant_v4.1.0, r1041_e82_400bps_sup_variant_v4.2.0, 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, r10_min_high_g303, r10_min_high_g340, 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_g303, 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_high_g303, r941_min_high_g330, r941_min_high_g340_rle, r941_min_high_g344, r941_min_high_g351, r941_min_high_g360, r941_min_sup_g507, r941_min_sup_snp_g507, r941_min_sup_variant_g507, r941_prom_fast_g303, 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_high_g303, r941_prom_high_g330, r941_prom_high_g344, r941_prom_high_g360, r941_prom_high_g4011, r941_prom_snp_g303, r941_prom_snp_g322, r941_prom_snp_g360, r941_prom_sup_g507, r941_prom_sup_snp_g507, r941_prom_sup_variant_g507, r941_prom_variant_g303, r941_prom_variant_g322, r941_prom_variant_g360, r941_sup_plant_g610, r941_sup_plant_variant_g610
+```

blast/2.14.1/Dockerfile

@@ -0,0 +1,63 @@
+FROM ubuntu:focal as app
+
+ARG BLAST_VER="2.14.1"
+
+# LABEL instructions tag the image with metadata that might be important to the user
+LABEL base.image="ubuntu:focal"
+LABEL dockerfile.version="1"
+LABEL software="blast+"
+LABEL software.version=$BLAST_VER
+LABEL description="Finds matches in sequencing reads"
+LABEL website="https://blast.ncbi.nlm.nih.gov/Blast.cgi?PAGE_TYPE=BlastDocs&DOC_TYPE=Download"
+LABEL license="https://www.ncbi.nlm.nih.gov/IEB/ToolBox/CPP_DOC/lxr/source/scripts/projects/blast/LICENSE"
+LABEL maintainer="Erin Young"
+LABEL maintainer.email="[email protected]"
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+  wget \
+  ca-certificates \
+  libgomp1 && \
+  apt-get autoclean && rm -rf /var/lib/apt/lists/*
+
+# Install and/or setup more things. Make /data for use as a working dir
+RUN wget https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/${BLAST_VER}/ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz && \
+  tar -xzf ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz && \
+  rm ncbi-blast-${BLAST_VER}+-x64-linux.tar.gz && \
+  mkdir /data
+
+# ENV instructions set environment variables that persist from the build into the resulting image
+# Use for e.g. $PATH and locale settings for compatibility with Singularity
+ENV PATH="/ncbi-blast-${BLAST_VER}+/bin:$PATH" \
+  LC_ALL=C
+
+# WORKDIR sets working directory
+WORKDIR /data
+
+# default command is to pull up help options for virulencefinder
+# yes, there are more tools than blastn, but it's likely the most common one used
+CMD [ "blastn", "-help" ]
+
+
+
+# A second FROM insruction creates a new stage
+# We use `test` for the test image
+FROM app as test
+
+# getting all the exectubles in bin
+RUN ls /ncbi-blast-*/bin/
+
+# getting a genome
+RUN mkdir db && \
+  wget https://ftp.ncbi.nlm.nih.gov/genomes/all/GCF/000/005/845/GCF_000005845.2_ASM584v2/GCF_000005845.2_ASM584v2_genomic.fna.gz -P db && \
+  gunzip db/GCF_000005845.2_ASM584v2_genomic.fna.gz && \
+  makeblastdb -dbtype nucl -in db/GCF_000005845.2_ASM584v2_genomic.fna
+
+# getting a list of genes
+RUN wget https://raw.githubusercontent.com/rrwick/Unicycler/main/unicycler/gene_data/dnaA.fasta
+
+# getting some blast results
+RUN tblastn -query dnaA.fasta \
+  -db db/GCF_000005845.2_ASM584v2_genomic.fna \
+  -outfmt '6' \
+  -out blast_hits.txt && \
+  head blast_hits.txt

blast/2.14.1/README.md

@@ -0,0 +1,60 @@
+# blast+ container
+
+Main tools:
+
+- [blast+](https://blast.ncbi.nlm.nih.gov/Blast.cgi?PAGE_TYPE=BlastDocs&DOC_TYPE=Download)
+
+This is meant to assist in local blast searches. No blast databases will be maintained in this container. Be sure to mount your relevant Volumes with `--volumes` or `-v` when using the command line.
+
+blast+ is actually a suite of tools. blast+ v.2.14.1 includes:
+
+```bash
+$ ls /ncbi-blast-2.14.1+/bin
+blast_formatter
+blast_formatter_vdb
+blast_vdb_cmd
+blastdb_aliastool
+blastdbcheck
+blastdbcmd
+blastn
+blastn_vdb
+blastp
+blastx
+cleanup-blastdb-volumes.py
+convert2blastmask
+deltablast
+dustmasker
+get_species_taxids.sh
+legacy_blast.pl
+makeblastdb
+makembindex
+makeprofiledb
+psiblast
+rpsblast
+rpstblastn
+segmasker
+tblastn
+tblastn_vdb
+tblastx
+update_blastdb.pl
+windowmasker 
+```
+
+Currently not supported, but could be:
+
+```bash
+get_species_taxids.sh # requires E-direct
+update_blastdb.pl     # requires perl
+```
+
+## Example Usage
+
+```bash
+# making a blast database
+makeblastdb -dbtype nucl -in fasta.fa
+
+# query
+tblastn -query query.fasta -db fasta.fa -outfmt '6' -out blast_hits.txt
+```
+
+More documentation can be found at [https://www.ncbi.nlm.nih.gov/books/NBK569856/](https://www.ncbi.nlm.nih.gov/books/NBK569856/) and [https://www.ncbi.nlm.nih.gov/books/NBK279690/](https://www.ncbi.nlm.nih.gov/books/NBK279690/)