Mercurial > repos > thanhlv > metamlst
changeset 0:d1df295495a9 draft
"planemo upload for repository https://github.com/quadram-institute-bioscience/galaxy-tools/tree/master/tools/metamlst commit 041ede79a8b699b00b1106cc82a5efe3c90c9876-dirty"
| author | thanhlv |
|---|---|
| date | Wed, 23 Feb 2022 10:17:46 +0000 |
| parents | |
| children | 4d3e54bace61 |
| files | metamlst.xml tool-data/metamlstdb.loc tool-data/metamlstdb.loc.sample tool_data_table_conf.xml.sample |
| diffstat | 4 files changed, 389 insertions(+), 0 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/metamlst.xml Wed Feb 23 10:17:46 2022 +0000 @@ -0,0 +1,379 @@ +<tool id="metamlst" name="metamlst" version="@VERSION@"> + <description> performs an in-silico Multi Locus Sequence Typing (MLST) Analysis on metagenomic samples</description> + <macros> + <token name="@VERSION@">1.2.2</token> + </macros> + <requirements> + <requirement type="package" version="@VERSION@">metamlst</requirement> + </requirements> + <version_command>metamlst.py --version | head -n 1 | cut -f 2</version_command> + <command detect_errors="exit_code"><![CDATA[ + #import re + ## Link in the input files, so bowtie2 can tell their type + #set compressed="False" + #set reads_are_fastq = True + #if str($library.type) == 'paired': + #set name_1 = re.sub('[^\w\-\s]', '_', str($library.input_1.element_identifier)) + #set name_2 = re.sub('[^\w\-\s]', '_', str($library.input_2.element_identifier)) + #if $library.input_1.is_of_type("fastq.gz", "fastqsanger.gz"): + #set read1 = $name_1 + '.fastq.gz' + #set compressed = "GZ" + #else if $library.input_1.is_of_type("fastq.bz2", "fastqsanger.bz2"): + #set read1 = $name_1 + '.fastq.bz2' + #set compressed = "BZ2" + #else if $library.input_1.is_of_type('fasta'): + #set reads_are_fastq = False + #set read1 = $name_1 + '.fasta' + #else: + #set read1 = $name_1 + '.fastq' + #end if + ln -f -s '${library.input_1}' ${read1} && + + #if $library.input_2.is_of_type("fastq.gz", "fastqsanger.gz"): + #set read2 = $name_2 + '.fastq.gz' + #set compressed = "GZ" + #else if $library.input_2.is_of_type("fastq.bz2", "fastqsanger.bz2"): + #set read2 = $name_1 + '.fastq.bz2' + #set compressed = "BZ2" + #else if $library.input_2.is_of_type('fasta'): + #set read2 = $name_1 + '.fasta' + #else: + #set read2 = $name_1 + '.fastq' + #end if + ln -f -s '${library.input_2}' ${read2} && + #else if str($library.type) == 'paired_collection': + #set pe_input_1 = $library.input_1.forward + #set pe_input_2 = $library.input_1.reverse + #set name_1 = re.sub('[^\w\-\s]', '_', str($library.pe_input_1.name)) + "_1" + #set name_2 = re.sub('[^\w\-\s]', '_', str($library.pe_input_2.name)) + "_2" + #if $library.input_1.forward.is_of_type("fastq.gz", "fastqsanger.gz"): + #set read1 = $name_1 + '.fastq.gz' + #set compressed = "GZ" + #else if $library.input_1.forward.is_of_type("fastq.bz2", "fastqsanger.bz2"): + #set read1 = $name_1 + '.fastq.bz2' + #set compressed = "BZ2" + #else if $library.input_1.forward.is_of_type('fasta'): + #set reads_are_fastq = False + #set read1 = $name_1 + '.fasta' + #else: + #set read1 = $name_1 + '.fastq' + #end if + ln -s '${library.input_1.forward}' ${read1} && + + #if $library.input_1.reverse.is_of_type("fastq.gz", "fastqsanger.gz"): + #set read2 = $name_2 + '.fastq.gz' + #set compressed = "GZ" + #else if $library.input_1.reverse.is_of_type("fastq.bz2", "fastqsanger.bz2"): + #set read2 = $name_2 + '.fastq.bz2' + #set compressed = "BZ2" + #else if $library.input_1.reverse.is_of_type("fasta"): + #set read2 = $name_2 + '.fasta' + #else: + #set read2 = $name_2 + '.fastq' + #end if + ln -s '${library.input_1.reverse}' ${read2} && + + #else if str($library.type) == 'paired_interleaved': + #set name_1 = re.sub('[^\w\-\s]', '_', str($library.input_1.element_identifier)) + #if $library.input_1.is_of_type("fastq.gz", "fastqsanger.gz"): + #set read1 = $name_1 + '.fastq.gz' + #set compressed = "GZ" + #else if $library.input_1.is_of_type("fastq.bz2", "fastqsanger.bz2"): + #set read1 = $name_1 + '.fastq.bz2' + #set compressed = "BZ2" + #else if $library.input_1.is_of_type("fasta"): + #set reads_are_fastq = False + #set read1 = $name_1 + '.fasta' + #else: + #set read1 = $name_1 + '.fastq' + #end if + ln -s '${library.input_1}' ${read1} && + #else: + #set name_1 = re.sub('[^\w\-\s]', '_', str($library.input_1.element_identifier)) + #if $library.input_1.is_of_type("fastq.gz", "fastqsanger.gz"): + #set read1 = $name_1.fastq.gz + #set compressed = "GZ" + #else if $library.input_1.is_of_type("fastq.bz2", "fastqsanger.bz2"): + #set read1 = $name_1.fastq.bz2 + #set compressed = "BZ2" + #else if $library.input_1.is_of_type("fasta"): + #set reads_are_fastq = False + #set read1 = $name_1 + '.fasta' + #else: + #set read1 = $name_1 + '.fastq' + #end if + ln -s '${library.input_1}' ${read1} && + #end if + + metamlst-index.py + -i bowtie_MmetaMLST + -d '$metamlstdb.fields.path' && + + bowtie2 + --very-sensitive-local + -a + --no-unal + + ## number of threads + -p \${GALAXY_SLOTS:-4} + + ## index file path + -x bowtie_MmetaMLST + + ## Input reads + #if str( $library.type ) == "single": + -U '${read1}' + #elif str( $library.type ) == "paired_interleaved": + --interleaved '${read1}' + #else: + -1 '${read1}' + -2 '${read2}' + #end if + | samtools view -bS -F 4 - > ${read1}.bam && + metamlst.py + #if $filter_species.filter=='yes' + #set species_list = ",".join([$species for $species in $filter_species.species]) + --filter $species_list + #end if + --penalty $penalty + --minscore $minscore + --max_xM $max_xm + --min_read_len $min_read_len + --min_accuracy $min_accuracy + --nloci $nloci + $log + $write_sequences + ${read1}.bam + -o ./out + -d '$metamlstdb.fields.path' && + metamlst-merge.py ./out -d '$metamlstdb.fields.path' && + #if $log + cat ./out/*.out > log.txt && + #end if + #if $write_sequences + cat ./out/*.nfo > sequences.txt + #end if + ]]> </command> + + <inputs> + <conditional name="library"> + <param name="type" type="select" label="Is this single or paired library"> + <option value="single">Single-end</option> + <option value="paired">Paired-end</option> + <option value="paired_collection">Paired-end Dataset Collection</option> + <option value="paired_interleaved">Paired-end data from single interleaved dataset</option> + </param> + + <when value="single"> + <param name="input_1" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data" label="FASTA/Q file" help="Must be of datatype "fastqsanger" or "fasta"" /> + </when> + <when value="paired"> + <param name="input_1" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data" label="FASTA/Q file #1" help="Must be of datatype "fastqsanger"or "fasta"" /> + <param name="input_2" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data" label="FASTA/Q file #2" help="Must be of datatype "fastqsanger"or "fasta"" /> + </when> + <when value="paired_collection"> + <param name="input_1" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data_collection" collection_type="paired" label="FASTQ Paired Dataset" help="Must be of datatype "fastqsanger" or "fasta"" /> + </when> + <when value="paired_interleaved"> + <param name="input_1" format="fastqsanger,fastqsanger.gz,fastqsanger.bz2" type="data" label="Interleaved FASTQ file" help="Must be of datatype "fastqsanger" or "fasta". --interleaved"/> + </when> + </conditional> + <param name="metamlstdb" label="Select a database" type="select"> + <options from_data_table="metamlstdb"> + <validator message="No database is available" type="no_options" /> + </options> + </param> + <conditional name="filter_species"> + <param name="filter" type="select" label="Filtering species"> + <option value="yes">Yes</option> + <option value="no" selected="true">No</option> + </param> + <when value="yes"> + <param name="species" type="select" multiple="true" label="Filter species"> + <option value="achromobacter">Achromobacter spp.</option> + <option value="abaumannii1">Acinetobacter baumannii#1</option> + <option value="abaumannii2">Acinetobacter baumannii#2</option> + <option value="aeromonas">Aeromonas spp.</option> + <option value="aactinomycetemcomitans">Aggregatibacter actinomycetemcomitans</option> + <option value="aphagocytophilum">Anaplasma phagocytophilum</option> + <option value="arcobacter">Arcobacter spp.</option> + <option value="afumigatus">Aspergillus fumigatus</option> + <option value="bcereus">Bacillus cereus</option> + <option value="blicheniformis">Bacillus licheniformis</option> + <option value="bsubtilis">Bacillus subtilis</option> + <option value="bbacilliformis">Bartonella bacilliformis</option> + <option value="bhenselae">Bartonella henselae</option> + <option value="bwashoensis">Bartonella washoensis</option> + <option value="bordetella">Bordetella spp.</option> + <option value="borrelia">Borrelia spp.</option> + <option value="bhampsonii">Brachyspira hampsonii</option> + <option value="bhyodysenteriae">Brachyspira hyodysenteriae</option> + <option value="bintermedia">Brachyspira intermedia</option> + <option value="bpilosicoli">Brachyspira pilosicoli</option> + <option value="brachyspira">Brachyspira spp.</option> + <option value="brucella">Brucella spp.</option> + <option value="bcepacia">Burkholderia cepacia complex</option> + <option value="bpseudomallei">Burkholderia pseudomallei</option> + <option value="cconcisus-curvus">Campylobacter concisus/curvus</option> + <option value="cfetus">Campylobacter fetus</option> + <option value="chelveticus">Campylobacter helveticus</option> + <option value="chyointestinalis">Campylobacter hyointestinalis</option> + <option value="cinsulaenigrae">Campylobacter insulaenigrae</option> + <option value="cjejuni">Campylobacter jejuni</option> + <option value="clanienae">Campylobacter lanienae</option> + <option value="clari">Campylobacter lari</option> + <option value="csputorum">Campylobacter sputorum</option> + <option value="cupsaliensis">Campylobacter upsaliensis</option> + <option value="calbicans">Candida albicans</option> + <option value="cglabrata">Candida glabrata</option> + <option value="ckrusei">Candida krusei</option> + <option value="ctropicalis">Candida tropicalis</option> + <option value="cliberibacter">Candidatus Liberibacter solanacearum</option> + <option value="cmaltaromaticum">Carnobacterium maltaromaticum</option> + <option value="chlamydiales">Chlamydiales spp.</option> + <option value="cfreundii">Citrobacter freundii</option> + <option value="csinensis">Clonorchis sinensis</option> + <option value="cdifficile">Clostridioides difficile</option> + <option value="cbotulinum">Clostridium botulinum</option> + <option value="cperfringens">Clostridium perfringens</option> + <option value="csepticum">Clostridium septicum</option> + <option value="cdiphtheriae">Corynebacterium diphtheriae</option> + <option value="cronobacter">Cronobacter spp.</option> + <option value="dnodosus">Dichelobacter nodosus</option> + <option value="edwardsiella">Edwardsiella spp.</option> + <option value="ecloacae">Enterobacter cloacae</option> + <option value="efaecalis">Enterococcus faecalis</option> + <option value="efaecium">Enterococcus faecium</option> + <option value="ecoli1">Escherichia coli#1</option> + <option value="ecoli2">Escherichia coli#2</option> + <option value="fpsychrophilum">Flavobacterium psychrophilum</option> + <option value="ganatis">Gallibacterium anatis</option> + <option value="geotrichum">Geotrichum spp.</option> + <option value="gparasuis">Glaesserella parasuis</option> + <option value="hinfluenzae">Haemophilus influenzae</option> + <option value="hcinaedi">Helicobacter cinaedi</option> + <option value="hpylori">Helicobacter pylori</option> + <option value="hsuis">Helicobacter suis</option> + <option value="kkingae">Kingella kingae</option> + <option value="kaerogenes">Klebsiella aerogenes</option> + <option value="koxytoca">Klebsiella oxytoca</option> + <option value="kpneumoniae">Klebsiella pneumoniae</option> + <option value="kseptempunctata">Kudoa septempunctata</option> + <option value="lsalivarius">Lactobacillus salivarius</option> + <option value="leptospira">Leptospira spp.</option> + <option value="leptospira2">Leptospira spp.#2</option> + <option value="leptospira3">Leptospira spp.#3</option> + <option value="lmonocytogenes">Listeria monocytogenes</option> + <option value="mcanis">Macrococcus canis</option> + <option value="mcaseolyticus">Macrococcus caseolyticus</option> + <option value="mhaemolytica">Mannheimia haemolytica</option> + <option value="mplutonius">Melissococcus plutonius</option> + <option value="mcatarrhalis">Moraxella catarrhalis</option> + <option value="mycobacteria">Mycobacteria spp.</option> + <option value="mabscessus">Mycobacterium abscessus</option> + <option value="mmassiliense">Mycobacterium massiliense</option> + <option value="magalactiae">Mycoplasma agalactiae</option> + <option value="mbovis">Mycoplasma bovis (legacy)</option> + <option value="mflocculare">Mycoplasma flocculare</option> + <option value="mgallisepticum1">Mycoplasma gallisepticum#1</option> + <option value="mgallisepticum2">Mycoplasma gallisepticum#2</option> + <option value="mhominis">Mycoplasma hominis</option> + <option value="mhyopneumoniae">Mycoplasma hyopneumoniae</option> + <option value="mhyorhinis">Mycoplasma hyorhinis</option> + <option value="miowae">Mycoplasma iowae</option> + <option value="mpneumoniae">Mycoplasma pneumoniae</option> + <option value="msynoviae">Mycoplasma synoviae</option> + <option value="neisseria">Neisseria spp.</option> + <option value="otsutsugamushi">Orientia tsutsugamushi</option> + <option value="orhinotracheale">Ornithobacterium rhinotracheale</option> + <option value="plarvae">Paenibacillus larvae</option> + <option value="pmultocida1">Pasteurella multocida#1</option> + <option value="pmultocida2">Pasteurella multocida#2</option> + <option value="ppentosaceus">Pediococcus pentosaceus</option> + <option value="pdamselae">Photobacterium damselae</option> + <option value="psalmonis">Piscirickettsia salmonis</option> + <option value="pgingivalis">Porphyromonas gingivalis</option> + <option value="pacnes">Propionibacterium acnes</option> + <option value="paeruginosa">Pseudomonas aeruginosa</option> + <option value="pfluorescens">Pseudomonas fluorescens</option> + <option value="pputida">Pseudomonas putida</option> + <option value="rhodococcus">Rhodococcus spp.</option> + <option value="ranatipestifer">Riemerella anatipestifer</option> + <option value="senterica">Salmonella enterica</option> + <option value="sparasitica">Saprolegnia parasitica</option> + <option value="shewanella">Shewanella spp.</option> + <option value="sinorhizobium">Sinorhizobium spp.</option> + <option value="saureus">Staphylococcus aureus</option> + <option value="schromogenes">Staphylococcus chromogenes</option> + <option value="sepidermidis">Staphylococcus epidermidis</option> + <option value="shaemolyticus">Staphylococcus haemolyticus</option> + <option value="shominis">Staphylococcus hominis</option> + <option value="slugdunensis">Staphylococcus lugdunensis</option> + <option value="spseudintermedius">Staphylococcus pseudintermedius</option> + <option value="smaltophilia">Stenotrophomonas maltophilia</option> + <option value="sagalactiae">Streptococcus agalactiae</option> + <option value="sbovis-equinus">Streptococcus bovis/equinus complex (SBSEC)</option> + <option value="scanis">Streptococcus canis</option> + <option value="sdysgalactiae">Streptococcus dysgalactiae equisimilis</option> + <option value="sgallolyticus">Streptococcus gallolyticus</option> + <option value="soralis">Streptococcus oralis</option> + <option value="spneumoniae">Streptococcus pneumoniae</option> + <option value="spyogenes">Streptococcus pyogenes</option> + <option value="ssuis">Streptococcus suis</option> + <option value="sthermophilus">Streptococcus thermophilus</option> + <option value="sthermophilus2">Streptococcus thermophilus#2</option> + <option value="suberis">Streptococcus uberis</option> + <option value="szooepidemicus">Streptococcus zooepidemicus</option> + <option value="streptomyces">Streptomyces spp</option> + <option value="taylorella">Taylorella spp.</option> + <option value="tenacibaculum">Tenacibaculum spp.</option> + <option value="tpallidum">Treponema pallidum</option> + <option value="tvaginalis">Trichomonas vaginalis</option> + <option value="ureaplasma">Ureaplasma spp.</option> + <option value="vcholerae">Vibrio cholerae</option> + <option value="vcholerae2">Vibrio cholerae#2</option> + <option value="vparahaemolyticus">Vibrio parahaemolyticus</option> + <option value="vibrio">Vibrio spp.</option> + <option value="vtapetis">Vibrio tapetis</option> + <option value="vvulnificus">Vibrio vulnificus</option> + <option value="wolbachia">Wolbachia </option> + <option value="xfastidiosa">Xylella fastidiosa</option> + <option value="ypseudotuberculosis">Yersinia pseudotuberculosis</option> + <option value="yruckeri">Yersinia ruckeri</option> + </param> + </when> + </conditional> + <param argument="--penalty" type="integer" min="0" value="100" label="MetaMLST penaty for under-represented alleles" /> + <param argument="--minscore" type="integer" min="0" value="80" label="Minimum alignment score for each alignment to be considered valid" /> + <param argument="--max_xm" type="integer" min="0" value="5" label="Maximum SNPs rate for each alignment to be considered valid" /> + <param argument="--min_read_len" type="integer" min="0" value="50" label="Minimum BowTie2 alignment length" /> + <param argument="--min_accuracy" type="float" min="0" max="1" value="0.9" label="Minimum threshold on Confidence score to pass the reconstruction step" /> + <param argument="--nloci" type="integer" min="0" value="100" label="Do not discard samples where at least NLOCI are detected" /> + <param argument="--log" type="boolean" truevalue="--log" falsevalue="" checked="true" label="Generate log file" /> + <param name="write_sequences" type="boolean" truevalue="-a" falsevalue="" checked="false" label="Write known sequences" /> + </inputs> + + <outputs> + <collection name="report" type="list" label="${tool.name} on ${on_string} Report"> + <discover_datasets pattern="(?P<designation>[a-zA-Z0-9\-\_]+)_report\.txt$" format="tabular" directory="./out/merged" visible="false"/> + </collection> + <collection name="st" type="list" label="${tool.name} on ${on_string} ST"> + <discover_datasets pattern="(?P<designation>[a-zA-Z0-9\-\_]+)_ST\.txt$" format="tabular" directory="./out/merged" visible="false"/> + </collection> + <data name="log_file" format="txt" from_work_dir="log.txt" label="${tool.name} on ${on_string} Log"> + <filter>log == True</filter> + </data> + <data name="sequence" format="txt" from_work_dir="sequences.txt" label="${tool.name} on ${on_string} Sequences"> + <filter>write_sequences == True</filter> + </data> + </outputs> + <!-- <tests> + <test> + </test> + </tests> --> + <help><![CDATA[ + ]]> </help> + <citations> + <citation type="doi">10.1093/nar/gkw837</citation> + </citations> +</tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/metamlstdb.loc Wed Feb 23 10:17:46 2022 +0000 @@ -0,0 +1,1 @@ +metamlstDB_2021 metamlstDB_2021 /home/ubuntu/galaxy-tools/tools/metamlst/metamlstDB_2021.db \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/metamlstdb.loc.sample Wed Feb 23 10:17:46 2022 +0000 @@ -0,0 +1,2 @@ +# bowtie2_indices.loc.sample +#<unique_build_id> <dbkey> <display_name> <file_base_path> \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Wed Feb 23 10:17:46 2022 +0000 @@ -0,0 +1,7 @@ +<tables> + <!-- Locations of ariba database in the required format --> + <table name="metamlstdb" comment_char="#" allow_duplicate_entries="False"> + <columns>value, name, path</columns> + <file path="tool-data/metamlstdb.loc"/> + </table> +</tables> \ No newline at end of file