Mercurial > repos > iuc > mykrobe_predict
changeset 4:a2e3ad69ee23 draft default tip
"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/mykrobe commit 3df97df276e6d3c2800d6f41161b3d7cd8fcbf2a"
| author | iuc |
|---|---|
| date | Thu, 26 Aug 2021 20:38:36 +0000 |
| parents | e8405163fb4e |
| children | |
| files | macro.xml mykrobe_predict.xml |
| diffstat | 2 files changed, 224 insertions(+), 232 deletions(-) [+] |
line wrap: on
line diff
--- a/macro.xml Tue Aug 10 11:29:58 2021 +0000 +++ b/macro.xml Thu Aug 26 20:38:36 2021 +0000 @@ -1,121 +1,102 @@ -<?xml version="1.1"?> <macros> - <token name="@TOOL_VERSION@">0.10.0</token> - <xml name="requirements"> - <requirements> - <requirement type="package" version="@TOOL_VERSION@">mykrobe</requirement> - </requirements> - </xml> - <token name="@select_inputs@"> - <![CDATA[ - #set $name='sample' - ]]> - </token> - - <token name="@shared_options@"> - <![CDATA[ - #if $kmer: - --kmer '${kmer}' - #end if - #if $expected_depth: - --expected_depth '${expected_depth}' - #end if - - $ont - - $report_all_calls + <token name="@TOOL_VERSION@">0.10.0</token> + <token name="@PROFILE@">20.09</token> + <xml name="requirements"> + <requirements> + <requirement type="package" version="@TOOL_VERSION@">mykrobe</requirement> + </requirements> + </xml> - #if $expected_error_rate: - --expected_error_rate '${expected_error_rate}' - #end if - - #if $min_variant_conf: - --min_variant_conf '${min_variant_conf}' - #end if - - #if $min_gene_conf: - --min_gene_conf '${min_gene_conf}' - #end if - - #if $min_proportion_expected_depth: - --min_proportion_expected_depth '${min_proportion_expected_depth}' - #end if - - #if $min_gene_percent_covg_threshold: - --min_gene_percent_covg_threshold '${min_gene_percent_covg_threshold}' - #end if - - $guess_sequence_method - - $ignore_minor_calls - - #if $ignore_filtered: - --ignore_filtered '${ignore_filtered}' - #end if - - #if $model: - --model '${model}' - #end if + <token name="@shared_options@"> + <![CDATA[ + #if $kmer: + --kmer ${kmer} + #end if + #if $expected_depth: + --expected_depth ${expected_depth} + #end if + $ont + $report_all_calls + #if $expected_error_rate: + --expected_error_rate ${expected_error_rate} + #end if + #if $min_variant_conf: + --min_variant_conf ${min_variant_conf} + #end if + #if $min_gene_conf: + --min_gene_conf ${min_gene_conf} + #end if + #if $min_proportion_expected_depth: + --min_proportion_expected_depth ${min_proportion_expected_depth} + #end if + #if $min_gene_percent_covg_threshold: + --min_gene_percent_covg_threshold ${min_gene_percent_covg_threshold} + #end if + $guess_sequence_method + $ignore_minor_calls + #if $ignore_filtered: + --ignore_filtered '${ignore_filtered}' + #end if + #if $model: + --model '${model}' + #end if + #if $ploidy: + --ploidy '${ploidy}' + #end if + ]]> + </token> - #if $ploidy: - --ploidy '${ploidy}' - #end if - ]]> - </token> - - <xml name="inputs"> - <conditional name="data_type"> - <param name="type" type="select" label="Specify the read type."> - <option value="single">Single-end Data</option> - <option value="paired">Paired-end Data</option> - <option value="collection">Collection Paired-end Data</option> - </param> - <when value="single"> - <param name="seq1" type="data" format="fastqsanger,fastqsanger.gz,fastq,fastq.gz,fasta,fasta.gz,bam" label="Single end read file(s)"/> - </when> - <when value="paired"> - <param name="seq1" type="data" format="fastqsanger,fastqsanger.gz,fastq,fastq.gz" label="Forward paired-end read file"/> - <param name="seq2" type="data" format="fastqsanger,fastqsanger.gz,fastq,fastq.gz" label="Reverse paired-end read file"/> - </when> - <when value="collection"> - <param name="collection1" type="data_collection" label="Paired-end reads collection" optional="false" format="fastqsanger,fastqsanger.gz,fastq,fastq.gz" collection_type="paired" /> - </when> - </conditional> - </xml> + <xml name="inputs"> + <conditional name="data_type"> + <param name="type" type="select" label="Specify the read type."> + <option value="single">Single-end Data</option> + <option value="paired">Paired-end Data</option> + <option value="collection">Collection Paired-end Data</option> + </param> + <when value="single"> + <param name="seq1" type="data" format="fastqsanger,fastqsanger.gz,fastq,fastq.gz,fasta,fasta.gz,bam" label="Single end read file(s)"/> + </when> + <when value="paired"> + <param name="seq1" type="data" format="fastqsanger,fastqsanger.gz,fastq,fastq.gz" label="Forward paired-end read file"/> + <param name="seq2" type="data" format="fastqsanger,fastqsanger.gz,fastq,fastq.gz" label="Reverse paired-end read file"/> + </when> + <when value="collection"> + <param name="collection1" type="data_collection" label="Paired-end reads collection" optional="false" format="fastqsanger,fastqsanger.gz,fastq,fastq.gz" collection_type="paired" /> + </when> + </conditional> + </xml> - <xml name="options"> - <param argument="--kmer" optional="True" type="integer" min="0" label="Kmer length" value="21" help="default = 21"/> - <param argument="--expected_error_rate" optional="True" type="float" label="Expected error rate" help="Expected sequencing error rate. Set to 0.15 for ONT genotyping"/> - <param argument="--expected_depth" optional="True" type="integer" min="0" label="Expected depth" help=""/> - <param argument="--ont" type="boolean" truevalue="--ont" falsevalue="" label="Set default for ONT data" help=""/> - <param argument="--min_variant_conf" optional="True" type="integer" min="0" label="Minimum genotype confidence for variant genotyping" help=""/> - <param argument="--min_gene_conf" optional="True" type="integer" min="0" label="Minimum genotype confidence for gene genotyping" help=""/> - <param argument="--min_gene_percent_covg_threshold" optional="True" type="integer" min="0" label="Minimum gene predict coverage" help="all genes alleles found above this percent coverage will be reported (default 100 (only best alleles reported))"/> - <param argument="--min_proportion_expected_depth" optional="True" type="float" label="Minimum depth required on the sum of both alleles" help="Default 0.3 (30%)"/> - <param argument="--model" optional="True" type="data" format="txt" label="Genotype model used" help="default kmer_count. Options kmer_count, median_depth"/> - <param argument="--ploidy" optional="True" type="select" label="Diploid or Haploid" help="Use a diploid (includes 0/1 calls) or haploid genotyping model"> - <option value="diploid">diploid</option> - <option value="haploid">haploid</option> - </param> - <param argument="--report_all_calls" type="boolean" truevalue="--report_all_calls" falsevalue="" label="Report all calls" help=""/> - <param argument="--ignore_minor_calls" type="boolean" truevalue="--ignore_minor_calls" falsevalue="" label="Ignore minor calls" help="Ignore minor calls when running resistance prediction"/> - <param argument="--ignore_filtered" type="data" format="txt" label="Ignore filtered" optional="True" help="Don't include filtered genotypes"/> - <param argument="--guess_sequence_method" type="boolean" truevalue="--guess_sequence_method" falsevalue="" label="Guess sequence method" help="Guess if ONT or Illumia based on error rate. If error rate is > 10%, ploidy is set to haploid and a confidence threshold is used"/> - </xml> + <xml name="options"> + <param argument="--kmer" optional="True" type="integer" min="0" label="Kmer length" value="21" help="default = 21"/> + <param argument="--expected_error_rate" optional="True" type="float" label="Expected error rate" help="Expected sequencing error rate. Set to 0.15 for ONT genotyping"/> + <param argument="--expected_depth" optional="True" type="integer" min="0" label="Expected depth" help=""/> + <param argument="--ont" type="boolean" truevalue="--ont" falsevalue="" label="Set default for ONT data" help=""/> + <param argument="--min_variant_conf" optional="True" type="integer" min="0" label="Minimum genotype confidence for variant genotyping" help=""/> + <param argument="--min_gene_conf" optional="True" type="integer" min="0" label="Minimum genotype confidence for gene genotyping" help=""/> + <param argument="--min_gene_percent_covg_threshold" optional="True" type="integer" min="0" label="Minimum gene predict coverage" help="all genes alleles found above this percent coverage will be reported (default 100 (only best alleles reported))"/> + <param argument="--min_proportion_expected_depth" optional="True" type="float" label="Minimum depth required on the sum of both alleles" help="Default 0.3 (30%)"/> + <param argument="--model" optional="True" type="data" format="txt" label="Genotype model used" help="default kmer_count. Options kmer_count, median_depth"/> + <param argument="--ploidy" optional="True" type="select" label="Diploid or Haploid" help="Use a diploid (includes 0/1 calls) or haploid genotyping model"> + <option value="diploid">diploid</option> + <option value="haploid">haploid</option> + </param> + <param argument="--report_all_calls" type="boolean" truevalue="--report_all_calls" falsevalue="" label="Report all calls" help=""/> + <param argument="--ignore_minor_calls" type="boolean" truevalue="--ignore_minor_calls" falsevalue="" label="Ignore minor calls" help="Ignore minor calls when running resistance prediction"/> + <param argument="--ignore_filtered" type="data" format="txt" label="Ignore filtered" optional="True" help="Don't include filtered genotypes"/> + <param argument="--guess_sequence_method" type="boolean" truevalue="--guess_sequence_method" falsevalue="" label="Guess sequence method" help="Guess if ONT or Illumia based on error rate. If error rate is > 10%, ploidy is set to haploid and a confidence threshold is used"/> + </xml> - <token name="@ATTRIBUTION@"> - <![CDATA[ - - **MyKrobe predict - Antibiotic resistance predictions** - - Rapid antibiotic-resistance predictions from genome sequence data for Staphylococcus aureus and Mycobacterium tuberculosis - using Bruijn graph. - ]]> - </token> + <token name="@ATTRIBUTION@"> + <![CDATA[ + **MyKrobe predict - Antibiotic resistance predictions** + Rapid antibiotic-resistance predictions from genome sequence data for Staphylococcus aureus and Mycobacterium tuberculosis + using Bruijn graph. + ]]> + </token> - <xml name="citation"> - <citations> - <citation type="doi">10.1038/ncomms10063</citation> - </citations> - </xml> + <xml name="citation"> + <citations> + <citation type="doi">10.1038/ncomms10063</citation> + </citations> + </xml> </macros>
--- a/mykrobe_predict.xml Tue Aug 10 11:29:58 2021 +0000 +++ b/mykrobe_predict.xml Thu Aug 26 20:38:36 2021 +0000 @@ -1,129 +1,140 @@ -<tool id="mykrobe_predict" name="mkyrobe predict" version="@TOOL_VERSION@"> - <description>Antibiotic resistance predictions</description> - <macros> - <import>macro.xml</import> - </macros> - <expand macro="requirements"/> - <command detect_errors="exit_code"> -<![CDATA[ - @select_inputs@ +<tool id="mykrobe_predict" name="mkyrobe predict" version="@TOOL_VERSION@.1+galaxy0" profile="@PROFILE@"> + <description>Antibiotic resistance predictions</description> + <macros> + <import>macro.xml</import> + </macros> + <expand macro="requirements"/> + <command detect_errors="exit_code"><![CDATA[ +#import difflib +#import re - mykrobe predict - --sample '${name}' - --species ${select_species.species} - --panel '${select_species.panel}' +mykrobe predict +--species '${select_species.species}' +--panel '${select_species.panel}' - #if $conf_percent_cutoff: - --conf_percent_cutoff '${conf_percent_cutoff}' - #end if +#if $conf_percent_cutoff: + --conf_percent_cutoff '${conf_percent_cutoff}' +#end if - #if $min_depth: - --min_depth '${min_depth}' - #end if +#if $min_depth: + --min_depth ${min_depth} +#end if - @shared_options@ +@shared_options@ - -q - -t "\${GALAXY_SLOTS:-1}" +-q +-t "\${GALAXY_SLOTS:-1}" - --seq - #if $data_type.type == "single": - $data_type.seq1 - #elif $data_type.type == "paired": - $data_type.seq1 $data_type.seq2 - #elif $data_type.type == "collection": - $data_type.collection1.forward $data_type.collection1.reverse - #end if +#if $data_type.type in ["single", "paired"]: + #set read1 = $data_type.seq1 + #set read1_identifier = re.sub('[^\s\w\-]', '_', str($read1.element_identifier)) + #if $data_type.type == "single": + --sample '${read1_identifier}' + --seq '${read1}' + #else: + #set read2 = $data_type.seq2 + #set read2_identifier = re.sub('[^\s\w\-]', '_', str($read2.element_identifier)) + #set matches = difflib.SequenceMatcher(None, read1_identifier, read2_identifier).get_matching_blocks() + #set match = $matches[0] + #set identifier = re.sub('[^\s\w\-]', '_', str($read1_identifier[match.a:match.a + match.size])) + --sample '${identifier}' + --seq '${read1}' '${read2}' + #end if +#elif $data_type.type == "collection": + #set identifier = re.sub('[^\s\w\-]', '_', str($data_type.collection1.element_identifier)) + --sample '${identifier}' + --seq '${data_type.collection1.forward}' '${data_type.collection1.reverse}' +#end if - --format '${format}' +--format '${format}' - > '$output' -]]> - </command> - <inputs> - <expand macro="inputs"/> - <conditional name="select_species"> - <param name="species" type="select" label="Specify Species for AMR"> - <option value="tb">Mycobacterium tuberculosis (tb)</option> - <option value="staph">Staphylococcus aureus (staph)</option> - <option value="sonnei">Shigella sonnei (sonnei)</option> - </param> - <when value="staph"> - <param name="panel" type="select" label="Select panel for Staph only"> - <option value="20170217">20170217</option> - </param> - </when> - <when value="tb"> - <param name="panel" type="select" label="Select panel for TB only"> - <option value="202010">202010</option> - <option value="201901">201901</option> - <option value="bradley-2015">Bradely 2015</option> +> '$output']]> + </command> + <inputs> + <expand macro="inputs"/> + <conditional name="select_species"> + <param name="species" type="select" label="Specify Species for AMR"> + <option value="tb">Mycobacterium tuberculosis (tb)</option> + <option value="staph">Staphylococcus aureus (staph)</option> + <option value="sonnei">Shigella sonnei (sonnei)</option> + </param> + <when value="staph"> + <param name="panel" type="select" label="Select panel for Staph only"> + <option value="20170217">20170217</option> + </param> + </when> + <when value="tb"> + <param name="panel" type="select" label="Select panel for TB only"> + <option value="202010">202010</option> + <option value="201901">201901</option> + <option value="bradley-2015">Bradely 2015</option> + </param> + </when> + <when value="sonnei"> + <param name="panel" type="select" label="Select panel for sonnei only"> + <option value="20210201">20210201</option> + <option value="20201012">20201012</option> + </param> + </when> + </conditional> + <param argument="--min_depth" optional="True" type="integer" min="0" label="Minimum depth" help=""/> + <param argument="--conf_percent_cutoff" optional="True" type="integer" label="Confidence percent cutoff" help="Number between 0 and 100. Determines --min_variant_conf, by simulating variants and choosing the cutoff that would keep x% of the variants. Default is 90 if --ont, otherwise --min_variant_conf is used as the cutoff"> + <validator type="in_range" min="0" max="100" message="Confidence percent cutoff should be between 0 and 100" /> </param> - </when> - <when value="sonnei"> - <param name="panel" type="select" label="Select panel for sonnei only"> - <option value="20210201">20210201</option> - <option value="20201012">20201012</option> + <expand macro="options"/> + <param argument="--format" type="select" label="Select the prefered output format"> + <option value="csv" >csv</option> + <option value="json">json</option> </param> - </when> - </conditional> - <param argument="--min_depth" optional="True" type="integer" min="0" label="Minimum depth" help=""/> - <param argument="--conf_percent_cutoff" optional="True" type="integer" label="Confidence percent cutoff" help="Number between 0 and 100. Determines --min_variant_conf, by simulating variants and choosing the cutoff that would keep x% of the variants. Default is 90 if --ont, otherwise --min_variant_conf is used as the cutoff"> - <validator type="in_range" min="0" max="100" message="Confidence percent cutoff should be between 0 and 100" /> - </param> - <expand macro="options"/> - <param argument="--format" type="select" label="Select the prefered output format"> - <option value="csv" >csv</option> - <option value="json">json</option> - </param> - </inputs> - <outputs> - <data name="output" format="csv" label="prediction"> - <change_format> - <when input="format" value="json" format="json"/> - </change_format> - </data> - </outputs> - <tests> - <test> - <param name="type" value="single"/> - <param name="seq1" ftype="fastq" value="reads.fastq"/> - <param name="species" value="tb"/> - <param name="panel" value="bradley-2015"/> - <param name="format" value="json"/> - <output name="output"> - <assert_contents> - <has_text_matching expression="susceptibility"/> - </assert_contents> - </output> - </test> - <test> - <param name="type" value="single"/> - <param name="seq1" ftype="fastq" value="reads.fastq"/> - <param name="species" value="sonnei"/> - <param name="panel" value="20201012"/> - <param name="format" value="json"/> - <output name="output"> - <assert_contents> - <has_text_matching expression="susceptibility"/> - </assert_contents> - </output> - </test> - <test> - <param name="type" value="single"/> - <param name="seq1" ftype="fastq.gz" value="reads.fastq.gz"/> - <param name="species" value="sonnei"/> - <param name="panel" value="20201012"/> - <param name="format" value="json"/> - <output name="output"> - <assert_contents> - <has_text_matching expression="susceptibility"/> - </assert_contents> - </output> - </test> - </tests> - <help> - @ATTRIBUTION@ - </help> - <expand macro="citation" /> + </inputs> + <outputs> + <data name="output" format="csv" label="prediction"> + <change_format> + <when input="format" value="json" format="json"/> + </change_format> + </data> + </outputs> + <tests> + <test> + <param name="type" value="single"/> + <param name="seq1" ftype="fastq" value="reads.fastq"/> + <param name="species" value="tb"/> + <param name="panel" value="bradley-2015"/> + <param name="format" value="json"/> + <output name="output"> + <assert_contents> + <has_text_matching expression="susceptibility"/> + </assert_contents> + </output> + </test> + <test> + <param name="type" value="single"/> + <param name="seq1" ftype="fastq" value="reads.fastq"/> + <param name="species" value="sonnei"/> + <param name="panel" value="20201012"/> + <param name="format" value="json"/> + <output name="output"> + <assert_contents> + <has_text_matching expression="susceptibility"/> + </assert_contents> + </output> + </test> + <test> + <param name="type" value="single"/> + <param name="seq1" ftype="fastq.gz" value="reads.fastq.gz"/> + <param name="species" value="sonnei"/> + <param name="panel" value="20201012"/> + <param name="format" value="json"/> + <output name="output"> + <assert_contents> + <has_text_matching expression="susceptibility"/> + </assert_contents> + </output> + </test> + </tests> + <help> + @ATTRIBUTION@ + </help> + <expand macro="citation" /> </tool> +