Merge pull request #752 from Kincekara/ki-fastani-1.34

updated FastANI to 1.34

README.md

@@ -65,7 +65,7 @@ To learn more about the docker pull rate limits and the open source software pro
 | [emmtyper](https://hub.docker.com/r/staphb/emmtyper) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/emmtyper)](https://hub.docker.com/r/staphb/emmtyper) | <ul><li>0.2.0</li></ul> | https://github.com/MDU-PHL/emmtyper |
 | [emm-typing-tool](https://hub.docker.com/r/staphb/emm-typing-tool) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/emm-typing-tool)](https://hub.docker.com/r/staphb/emm-typing-tool) | <ul><li>0.0.1 (no version)</li></ul> | https://github.com/phe-bioinformatics/emm-typing-tool |
 | [EToKi](https://hub.docker.com/r/staphb/etoki) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/etoki)](https://hub.docker.com/r/staphb/etoki) | <ul><li>1.2.1</li></ul> | https://github.com/zheminzhou/EToKi |
-| [FastANI](https://hub.docker.com/r/staphb/fastani) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/fastani)](https://hub.docker.com/r/staphb/fastani) | <ul><li>1.1</li><li>1.32</li><li>1.33</li><li>1.33 + RGDv2</li></ul> | https://github.com/ParBLiSS/FastANI |
+| [FastANI](https://hub.docker.com/r/staphb/fastani) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/fastani)](https://hub.docker.com/r/staphb/fastani) | <ul><li>1.1</li><li>1.32</li><li>1.33</li><li>1.33 + RGDv2</li><li>[1.34](fastani/1.34)</li><li>[1.34 + RGDv2](fastani/1.34-RGDV2/)</li></ul> | https://github.com/ParBLiSS/FastANI |
 | [Fastp](https://hub.docker.com/r/staphb/fastp) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/fastp)](https://hub.docker.com/r/staphb/fastp) | <ul><li>0.23.2</li><li>[0.23.4](fastp/0.23.4/)</li></ul> | http://opengene.org/fastp/ <br/> https://github.com/OpenGene/fastp |
 | [FastTree](https://hub.docker.com/r/staphb/fasttree) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/fasttree)](https://hub.docker.com/r/staphb/fasttree) | <ul><li>2.1.11</li></ul> | http://www.microbesonline.org/fasttree/ |
 | [FastQC](https://hub.docker.com/r/staphb/fastqc) <br/> [![docker pulls](https://badgen.net/docker/pulls/staphb/fastqc)](https://hub.docker.com/r/staphb/fastqc) | <ul><li>0.11.8</li><li>0.11.9</li><li>0.12.1</li></ul> | https://www.bioinformatics.babraham.ac.uk/projects/fastqc/ <br/> https://github.com/s-andrews/FastQC |

fastani/1.34-RGDV2/Dockerfile

@@ -0,0 +1,77 @@
+## build RGDv2 ##
+FROM staphb/ncbi-datasets:15.11.0 as stage
+
+# copy in list of NCBI accessions and species list
+COPY RGDv2-NCBI-assembly-accessions.txt /RGDv2/RGDv2-NCBI-assembly-accessions.txt
+COPY RGDv2-NCBI-assembly-accessions-and-species.txt /RGDv2/RGDv2-NCBI-assembly-accessions-and-species.txt
+
+# download RGD genomes using NCBI datasets tools; cleanup unneccessary files; 
+# move and re-name assemblies to include Species in the filename
+# make fasta files readable to all users; create File Of FileNames for all 43 assemblies (to be used with fastANI)
+RUN for ID in $(cat /RGDv2/RGDv2-NCBI-assembly-accessions.txt); do \
+ SPECIES=$(grep "${ID}" /RGDv2/RGDv2-NCBI-assembly-accessions-and-species.txt | cut -f 1) && \
+ echo "downloading $ID, species "${SPECIES}", from NCBI..."; \
+ datasets download genome accession ${ID} --filename ${ID}.zip; \
+ unzip ${ID}.zip; \
+ rm ${ID}.zip; \
+ mv -v ncbi_dataset/data/${ID}/${ID}*.fna /RGDv2/${ID}.${SPECIES}.fasta; \
+ rm -rfv ncbi_dataset/; \
+ rm -v README.md; \
+done && \
+ls /RGDv2/*.fasta >/RGDv2/FOFN-RGDv2.txt &&\
+chmod 664 /RGDv2/*
+
+## App ##
+FROM ubuntu:jammy as app
+
+# for easy upgrade later. ARG variables only persist at build time
+ARG FASTANI_VER="v1.34"
+
+LABEL base.image="ubuntu:jammy"
+LABEL dockerfile.version="1"
+LABEL software="FastANI"
+LABEL software.version=${FASTANI_VER}
+LABEL description="Fast alignment-free computation of whole-genome Average Nucleotide Identity"
+LABEL website="https://github.com/ParBLiSS/FastANI"
+LABEL license="https://github.com/ParBLiSS/FastANI/blob/master/LICENSE"
+LABEL maintainer="Kelsey Florek"
+LABEL maintainer.email="kelsey.florek@slh.wisc.edu"
+LABEL maintainer2="Curtis Kapsak"
+LABEL maintainer2.email="kapsakcj@gmail.com"
+LABEL maintainer3="Kutluhan Incekara"
+LABEL maintainer3.email="kutluhan.incekara@ct.gov"
+
+# install dependencies; cleanup apt garbage
+RUN apt-get update && apt-get install --no-install-recommends -y \
+ wget \
+ unzip \
+ libgomp1 && \
+ apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# download pre-compiled binary; unzip; put binary in /usr/local/bin
+# apt dependencies: libgomp1 unzip wget
+RUN wget --no-check-certificate https://github.com/ParBLiSS/FastANI/releases/download/${FASTANI_VER}/fastANI-Linux64-${FASTANI_VER}.zip && \
+ unzip fastANI-Linux64-${FASTANI_VER}.zip -d /usr/local/bin && \
+ rm fastANI-Linux64-${FASTANI_VER}.zip
+
+# copy RGDv2 from stage
+COPY --from=stage /RGDv2/ /RGDv2/
+
+# default run command
+CMD fastANI -h
+
+# singularity compatibility
+ENV LC_ALL=C
+
+# set working directory
+WORKDIR /data
+
+## Test ##
+FROM app as test
+
+# test against RGDv2
+RUN wget --no-check-certificate -P /data https://github.com/ParBLiSS/FastANI/raw/master/tests/data/Escherichia_coli_str_K12_MG1655.fna && \
+ fastANI -t 8 -q /data/Escherichia_coli_str_K12_MG1655.fna --rl /RGDv2/FOFN-RGDv2.txt -o fastANI.RGDv2.out.tsv &&\
+ echo "output TSV from fastANI test:" && \
+ cat fastANI.RGDv2.out.tsv 
+

fastani/1.34-RGDV2/README.md

@@ -0,0 +1,21 @@
+# fastANI container
+
+Main tool : [fastANI](https://github.com/ParBLiSS/FastANI)
+
+Full documentation: https://github.com/ParBLiSS/FastANI
+
+FastANI was developed for fast alignment-free computation of whole-genome Average Nucleotide Identity (ANI). ANI is defined as mean nucleotide identity of orthologous gene pairs shared between two microbial genomes.
+
+This docker image contains the Reference Genome Database version 2 (RGDv2) from the Enteric Diseases Laboratory Branch at the CDC. It contains the genomes of 43 enteric bacterial isolates that are used to for species identification of bacterial isolate WGS data. This database is NOT meant to be comprehensive - it contains the genomes of enteric pathogens commonly sequenced by EDLB and some closely related species.
+
+The FASTA files for RGDv2 can be found within `/RGDv2/` inside the docker image.
+
+## Example Usage
+
+```bash
+# query one genome against another genome
+fastANI -t 8 -q bacterial-genome1.fasta -r bacterial-genome2.fasta -o fastANI.out.tsv
+
+# query one genome against the 43 genomes in RGDv2 (requires a File Of FileNames as input)
+fastANI -t 8 -q bacterial-genome.fasta --rl /RGDv2/FOFN-RGDv2.txt -o fastANI.RGDv2.out.tsv
+```

fastani/1.34-RGDV2/RGDv2-NCBI-assembly-accessions-and-species.txt

@@ -0,0 +1,43 @@
+Campylobacter_coli	GCA_008011635.1
+Campylobacter_fetus	GCA_000015085.1
+Campylobacter_fetus	GCA_000495505.1
+Campylobacter_fetus	GCA_000759515.1
+Campylobacter_hyointestinalis	GCA_001643955.1
+Campylobacter_jejuni	GCA_000017485.1
+Campylobacter_jejuni	GCA_008011525.1
+Campylobacter_lari	GCA_000019205.1
+Campylobacter_lari	GCA_000816225.1
+Campylobacter_upsaliensis	GCA_008011615.1
+Escherichia_albertii	GCA_000512125.1
+Escherichia_coli	GCA_002741475.1
+Escherichia_fergusonii	GCA_000026225.1
+Grimontia_hollisae	GCA_009665295.1
+Listeria_innocua	GCA_017363615.1
+Listeria_innocua	GCA_017363655.1
+Listeria_ivanovii	GCA_000252975.1
+Listeria_marthii	GCA_017363645.1
+Listeria_monocytogenes	GCA_001466295.1
+Listeria_monocytogenes	GCA_013625895.1
+Listeria_monocytogenes	GCA_013625995.1
+Listeria_monocytogenes	GCA_013626145.1
+Listeria_monocytogenes	GCA_014526935.1
+Listeria_seeligeri	GCA_017363605.1
+Listeria_welshimeri	GCA_002489005.1
+Photobacterium_damselae	GCA_009665375.1
+Salmonella_bongori	GCA_013588055.1
+Salmonella_enterica	GCA_011388235.1
+Vibrio_alginolyticus	GCA_009665435.1
+Vibrio_cholerae	GCA_009665515.2
+Vibrio_cidicii	GCA_009665415.1
+Vibrio_cincinnatiensis	GCA_009665395.1
+Vibrio_fluvialis	GCA_009665355.1
+Vibrio_furnissii	GCA_009665335.1
+Vibrio_harveyi	GCA_009665315.1
+Vibrio_metoecus	GCA_009665255.1
+Vibrio_metoecus	GCA_009665275.1
+Vibrio_metschnikovii	GCA_009665235.1
+Vibrio_mimicus	GCA_009665195.1
+Vibrio_navarrensis	GCA_009665215.1
+Vibrio_parahaemolyticus	GCA_009665495.1
+Vibrio_vulnificus	GCA_009665455.1
+Vibrio_vulnificus	GCA_009665475.1

fastani/1.34-RGDV2/RGDv2-NCBI-assembly-accessions.txt

@@ -0,0 +1,43 @@
+GCA_008011635.1
+GCA_000015085.1
+GCA_000495505.1
+GCA_000759515.1
+GCA_001643955.1
+GCA_000017485.1
+GCA_008011525.1
+GCA_000816225.1
+GCA_000019205.1
+GCA_008011615.1
+GCA_000512125.1
+GCA_002741475.1
+GCA_000026225.1
+GCA_009665295.1
+GCA_017363655.1
+GCA_017363615.1
+GCA_000252975.1
+GCA_017363645.1
+GCA_001466295.1
+GCA_014526935.1
+GCA_013626145.1
+GCA_013625995.1
+GCA_013625895.1
+GCA_017363605.1
+GCA_002489005.1
+GCA_009665375.1
+GCA_013588055.1
+GCA_011388235.1
+GCA_009665435.1
+GCA_009665515.2
+GCA_009665415.1
+GCA_009665395.1
+GCA_009665355.1
+GCA_009665335.1
+GCA_009665315.1
+GCA_009665275.1
+GCA_009665255.1
+GCA_009665235.1
+GCA_009665195.1
+GCA_009665215.1
+GCA_009665495.1
+GCA_009665475.1
+GCA_009665455.1

fastani/1.34-RGDV2/RGDv2-metadata.tsv

@@ -0,0 +1,44 @@
+Species	BioSample	NCBI Assembly	Strain ID	
+Campylobacter coli	SAMN12323645	GCA_008011635.1	2013D-9606	
+Campylobacter fetus	SAMN02604050	GCA_000015085.1	82-40	
+Campylobacter fetus	SAMN02604287	GCA_000495505.1	03-427	
+Campylobacter fetus	SAMN02870596	GCA_000759515.1	97-608	
+Campylobacter hyointestinalis	SAMN03737973	GCA_001643955.1	LMG 9260	
+Campylobacter jejuni	SAMN02604056	GCA_000017485.1	NC_009707	
+Campylobacter jejuni	SAMN12323651	GCA_008011525.1	D0133	
+Campylobacter lari	SAMN02604025	GCA_000019205.1	RM2100	
+Campylobacter lari	SAMN03248542	GCA_000816225.1	LMG 11760	
+Campylobacter upsaliensis	SAMN12323647	GCA_008011615.1	D1914	
+Escherichia albertii	SAMN02641387	GCA_000512125.1	KF1	
+Escherichia coli	SAMN07731009	GCA_002741475.1	B4103-1	
+Escherichia fergusonii	SAMEA3138228	GCA_000026225.1	ATCC_35469	
+Grimontia hollisae	SAMN10812938	GCA_009665295.1	2013V-1029	
+Listeria innocua	SAMN10869157	GCA_017363615.1	2010L-2059	
+Listeria innocua	SAMN10869156	GCA_017363655.1	H0996 L	
+Listeria ivanovii	SAMEA3138408	GCA_000252975.1	PAM55	
+Listeria marthii	SAMN10869158	GCA_017363645.1	FSL S4-696	
+Listeria monocytogenes	SAMN02944835	GCA_001466295.1	G4599	
+Listeria monocytogenes	SAMN02847829	GCA_013625895.1	2014L-6256	
+Listeria monocytogenes	SAMN03067768	GCA_013625995.1	J0099	
+Listeria monocytogenes	SAMN02950479	GCA_013626145.1	2014L-6393	
+Listeria monocytogenes	SAMN03761815	GCA_014526935.1	2011L-2626	
+Listeria seeligeri	SAMN10869159	GCA_017363605.1	F5761	
+Listeria welshimeri	SAMN03462185	GCA_002489005.1	SLCC5334	
+Photobacterium damselae	SAMN10702680	GCA_009665375.1	2012V-1072	
+Salmonella bongori	SAMN13207407	GCA_013588055.1	04-0440	
+Salmonella enterica	SAMN08167480	GCA_011388235.1	2010K-2370	
+Vibrio alginolyticus	SAMN10702675	GCA_009665435.1	2013V-1302	
+Vibrio cholerae	SAMN10863496	GCA_009665515.2	2010EL-1786	
+Vibrio cidicii	SAMN10863497	GCA_009665415.1	2423-01	
+Vibrio cincinnatiensis	SAMN10812936	GCA_009665395.1	2409-02	
+Vibrio fluvialis	SAMN10812937	GCA_009665355.1	2013V-1049	
+Vibrio furnissii	SAMN10702681	GCA_009665335.1	2419-04	
+Vibrio harveyi	SAMN10702676	GCA_009665315.1	2011V-1164	
+Vibrio metoecus	SAMN10702677	GCA_009665255.1	2011V-1169	
+Vibrio metoecus	SAMN10863498	GCA_009665275.1	08-2459	
+Vibrio metschnikovii	SAMN10702671	GCA_009665235.1	2012V-1020	
+Vibrio mimicus	SAMN10812939	GCA_009665195.1	2011V-1073	
+Vibrio navarrensis	SAMN10863499	GCA_009665215.1	08-2462	
+Vibrio parahaemolyticus	SAMN10702672	GCA_009665495.1	2012AW-0154	
+Vibrio vulnificus	SAMN10702674	GCA_009665455.1	2009V-1035	
+Vibrio vulnificus	SAMN10702673	GCA_009665475.1	2142-77	

fastani/1.34/Dockerfile

@@ -0,0 +1,51 @@
+FROM ubuntu:jammy as app
+
+# for easy upgrade later. ARG variables only persist at build time
+ARG FASTANI_VER="v1.34"
+
+LABEL base.image="ubuntu:jammy"
+LABEL dockerfile.version="1"
+LABEL software="FastANI"
+LABEL software.version=${FASTANI_VER}
+LABEL description="Fast alignment-free computation of whole-genome Average Nucleotide Identity"
+LABEL website="https://github.com/ParBLiSS/FastANI"
+LABEL license="https://github.com/ParBLiSS/FastANI/blob/master/LICENSE"
+LABEL maintainer="Kelsey Florek"
+LABEL maintainer.email="kelsey.florek@slh.wisc.edu"
+LABEL maintainer2="Curtis Kapsak"
+LABEL maintainer2.email="kapsakcj@gmail.com"
+LABEL maintainer3="Kutluhan Incekara"
+LABEL maintainer3.email="kutluhan.incekara@ct.gov"
+
+# install dependencies; cleanup apt garbage
+RUN apt-get update && apt-get install --no-install-recommends -y \
+ wget \
+ unzip \
+ libgomp1 && \
+ apt-get clean && rm -rf /var/lib/apt/lists/*
+
+# download pre-compiled binary; unzip; put binary in /usr/local/bin
+# apt dependencies: libgomp1 unzip wget
+RUN wget --no-check-certificate https://github.com/ParBLiSS/FastANI/releases/download/${FASTANI_VER}/fastANI-Linux64-${FASTANI_VER}.zip && \
+ unzip fastANI-Linux64-${FASTANI_VER}.zip -d /usr/local/bin && \
+ rm fastANI-Linux64-${FASTANI_VER}.zip
+
+# default run command
+CMD fastANI -h
+
+# singularity compatibility
+ENV LC_ALL=C
+
+# set working directory
+WORKDIR /data
+
+## Test ##
+FROM app as test
+
+# download 2 genomes from fastANI GitHub; compare the 2; cat the output file
+RUN wget --no-check-certificate -P /data https://github.com/ParBLiSS/FastANI/raw/master/tests/data/Escherichia_coli_str_K12_MG1655.fna && \
+ wget --no-check-certificate -P /data https://github.com/ParBLiSS/FastANI/raw/master/tests/data/Shigella_flexneri_2a_01.fna && \
+ fastANI -q /data/Shigella_flexneri_2a_01.fna -r /data/Escherichia_coli_str_K12_MG1655.fna -o /data/fastANI-test-ShiglellaFlexneri-EcoliK12.tsv && \
+ echo "output TSV from fastANI test:" && \
+ cat fastANI-test-ShiglellaFlexneri-EcoliK12.tsv
+

fastani/1.34/README.md

@@ -0,0 +1,19 @@
+# fastANI container
+
+Main tool : [fastANI](https://github.com/ParBLiSS/FastANI)
+
+Full documentation: https://github.com/ParBLiSS/FastANI
+
+FastANI was developed for fast alignment-free computation of whole-genome Average Nucleotide Identity (ANI). ANI is defined as mean nucleotide identity of orthologous gene pairs shared between two microbial genomes.
+
+This docker image contains no references.
+
+## Example Usage
+
+```bash
+# query one genome against another genome
+fastANI -t 8 -q bacterial-genome1.fasta -r bacterial-genome2.fasta -o fastANI.out.tsv
+
+# query one genome against the 43 genomes in RGDv2 (requires a File Of FileNames as input)
+fastANI -t 8 -q bacterial-genome.fasta --rl /RGDv2/FOFN-RGDv2.txt -o fastANI.RGDv2.out.tsv
+```