annotate srst2.xml @ 3:f995ba9f1caa draft default tip

planemo upload for repository https://github.com/katholt/srst2 commit 90275e51aa271edacdd9d277c441e38e99502c53

<tool id="srst2" name="SRST2" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>Short Read Sequence Typing for Bacterial Pathogens</description>
    <macros>
        <import>macros.xml</import>
        <token name="@FAST_A_Q_FORMATS@">fasta,fasta.gz,fastq,fastq.gz,fastqsanger,fastqsanger.gz</token>
    </macros>
    <expand macro="xrefs"/>
    <expand macro="requirements"/>
    <version_command>srst2 --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
#if $input.selector == "single"
#set ext=$input.single_input.datatype.file_ext
    ln -s $input.single_input './input_read1.$ext' &&
#else if $input.selector == "paired"
#set ext_1=$input.paired_input1.datatype.file_ext
#set ext_2=$input.paired_input2.datatype.file_ext
    ln -s $input.paired_input1 './input_read1.$ext_1' &&
    ln -s $input.paired_input2 './input_read2.$ext_2' &&
#end if
#for $i, $s in enumerate($prev_output)
    #if $s
        ln -s $s './$i-prev_output.txt' &&
    #end if
#end for
#if $use_gene_db.selector == "yes" 
    #for $i, $s in enumerate($use_gene_db.gene_db)
        #if $s
            ln -s $s './$i-gene_db.fasta' &&
        #end if
    #end for
#end if
#if $use_mlst_db.selector == "yes"
#set ext_3=$use_mlst_db.mlst_definitions.datatype.file_ext
    ln -s $use_mlst_db.mlst_db './mlst_db.fasta' &&
    ln -s $use_mlst_db.mlst_definitions './mlst_definitions.$ext_3' &&
#end if
srst2
#if $input.selector == "single"
    --input_se './input_read1.$ext'
    --read_type ${input.read_type}
#else if $input.selector == "paired"
    --input_pe './input_read1.$ext_1' './input_read2.$ext_2'
    $input.merge_paired
    --forward _read1
    --reverse _read2
    --read_type ${input.read_type}
#end if
#if $use_mlst_db.selector == "yes"    
    --mlst_db './mlst_db.fasta'
    --mlst_definitions './mlst_definitions.$ext_3'
    --mlst_delimiter '$use_mlst_db.mlst_delimiter'
    --mlst_max_mismatch $use_mlst_db.mlst_max_mismatch
    --min_depth $use_mlst_db.min_depth
    --min_edge_depth $use_mlst_db.min_edge_depth    
#end if
#if $use_gene_db.selector == "yes" 
    --gene_db
    #for $i, $s in enumerate($use_gene_db.gene_db)
        #if $s
            '$i-gene_db.fasta'
        #end if
    #end for
    $use_gene_db.no_gene_details
    --gene_max_mismatch $use_gene_db.gene_max_mismatch
    --min_coverage $use_gene_db.min_coverage
    --max_divergence $use_gene_db.max_divergence
#end if
    --prob_err $prob_err
#if $truncation_score_tolerance     
    --truncation_score_tolerance $truncation_score_tolerance
#end if
#if $stop_after    
    --stop_after $stop_after
#end if
    --max_unaligned_overlap $max_unaligned_overlap
    --mapq $mapq
    --baseq $baseq
    --output 'output'
#if $prev_output
    --prev_output 
    #for $i, $s in enumerate($prev_output)
        #if $s
            '$i-prev_output.txt'
        #end if
    #end for  
#end if 
#if 'log' in str($output_files_selector)
    --log
#end if
#if 'save_scores' in str($output_files_selector)
    --save_scores
#end if
#if 'report_new_consensus' in str($output_files_selector)
    --report_new_consensus
#end if
#if 'report_all_consensus' in str($output_files_selector)
    --report_all_consensus
#end if
#if 'keep_interim_alignment' in str($output_files_selector)
    --keep_interim_alignment
#end if
## |true here is added in order not to search for a file that is not produced at all, such that if the user provided no gene/MLST databases or there are no outputs found, the tool will run successfully and only notify the user that no outputs are found
#if 'report_new_consensus' in str($output_files_selector) and $use_gene_db.selector == "yes" and $use_mlst_db.selector == "yes"
&& mkdir -p allelesOutput/ && cp *.output__input.*.pileup allelesOutput | true
#end if

#if $use_gene_db.selector == "yes" and  $use_gene_db.no_gene_details
&& mkdir -p geneTypingOutput/ geneTypingOutputFull/ && cp output__genes__*__results.txt geneTypingOutput | true && cp output__fullgenes__*__results.txt geneTypingOutputFull | true
#end if

#if 'save_scores' in str($output_files_selector)
    && mkdir -p scoresOutput/ && cp *.scores scoresOutput | true
#end if
#if $input.selector == "single" or $input.selector == "paired"
&& mkdir -p bowtie2Alignments/ && cp *.sorted.bam bowtie2Alignments | true
&& mkdir -p samtoolsPileup/ && cp output__input.*.pileup samtoolsPileup | true
#end if
    ]]></command>
    <inputs>
        <conditional name="input">
            <param name="selector" type="select" label="Reads files type for anaylsis">
                <option value="single">Single-end</option>
                <option value="paired">Paired-end</option>
                <option value="only_compiling_previous_results">Only Compiling Previous SRST2 Results</option>
            </param>
            <when value="single">
                <param name="single_input" type="data" format="@FAST_A_Q_FORMATS@" label="Single end read file(s) for analysing (may be gzipped)"/>
                <expand macro="read_type_options" />  
            </when>
            <when value="paired">
                <param name="paired_input1" type="data" format="@FAST_A_Q_FORMATS@" label="Paired end read files for analysing (may be gzipped)"/>
                <param name="paired_input2" type="data" format="@FAST_A_Q_FORMATS@" label="Paired end read files for analysing (may be gzipped)"/>                
                <param argument="--merge_paired" type="boolean" truevalue="--merge_paired" falsevalue="" checked="false" label="Do you want to merge the data to get a single result" help="Important only if all the input read sets belong to a single sample"/> 
                <expand macro="read_type_options" />
            </when>
            <when value="only_compiling_previous_results">
            </when>    
        </conditional>
        <conditional name="use_mlst_db">
            <param name="selector" type="select" label="Do you want to provide an MLST database of all allele sequences for the MLST scheme?">
                <option value="yes">Yes</option>
                <option value="no">No</option>
            </param>
            <when value="yes">
                <param argument="--mlst_db" type="data" format="fasta" label="Fasta file of MLST alleles"/>
                <param argument="--mlst_definitions" type="data" format="tabular" label="ST definitions for MLST scheme" help="This is the file that tells you the ST number that is assigned to known combinations of alleles. Column 1 is the ST, and subsequent columns are the loci that make up the scheme."/>
                <param argument="--mlst_delimiter" type="text" value="-" label="Character(s) separating gene name from allele number in MLST database" help="E.g.'-', as in arcc-1">           
                    <sanitizer invalid_char="">
                        <valid initial="string.letters,string.digits">
                            <add value="\" />
                            <add value="-" />
                            <add value="/" />
                            <add value="+" />
                            <add value="=" />
                            <add value=" " />
                            <add value="_" />    
                        </valid>
                    </sanitizer>
                    <validator type="regex">[A-Za-z0-9 =_/+-]+</validator>
                </param>
                <param argument="--mlst_max_mismatch" type="integer" value="10" label="Maximum number of mismatches per read for MLST allele calling"/>
                <param argument="--min_depth" type="integer" value="5" label="Minimum mean depth to flag as dubious allele call"/>
                <param argument="--min_edge_depth" type="integer" value="2" label="Minimum edge depth to flag as dubious allele call"/>            
            </when>
            <when value="no">
            </when>
        </conditional>
        <conditional name="use_gene_db">
            <param name="selector" type="select" label="Do you want to use a Gene database(s)?">
                <option value="yes">Yes</option>
                <option value="no">No</option>
            </param>
            <when value="yes">
                <param argument="--gene_db" type="data" optional="true" multiple="true" format="fasta" label="Gene database(s)" help="Fasta file/s for gene databases"/>
                <param argument="--no_gene_details" type="boolean" truevalue="" falsevalue="--no_gene_details" checked="false" label="Do you want reporting of gene typing?"/>
                <param argument="--gene_max_mismatch" type="integer" value="10" label="Maximum number of mismatches per read for gene detection and allele calling"/>
                <param argument="--min_coverage" type="integer" value="90" label="Minimum %coverage cutoff for gene reporting"/>
                <param argument="--max_divergence" type="integer" value="10" label="Maximum %divergence cutoff for gene reporting"/>            
            </when>
            <when value="no">
            </when>
        </conditional>
        <param name="output_files_selector" type="select" label="Select all outputs you need" multiple="true">
            <option value="log">Save the log</option>
            <option value="save_scores">Report scores</option>
            <option value="report_new_consensus">Report the consensus allele if a matching alleles is not found</option>
            <option value="report_all_consensus">Report the consensus allele for the most likely allele</option>
            <option value="keep_interim_alignment">Keep interim files (sam and unsorted bam)</option>
        </param>
        <param argument="--prob_err" type="float" min="0" max="1" value="0.01" label="Probability of sequencing error"/>
        <param argument="--truncation_score_tolerance" optional="true" type="float" label="% increase in score allowed to choose non-truncated allele"/>
        <param argument="--stop_after" type="integer" optional="true" label="Stop mapping after this number of reads have been mapped" help="Leave empty to map all"/>       
        <param argument="--max_unaligned_overlap" type="integer" value="10" label="Read discarded from alignment" help="if either of its ends has unaligned overlap with the reference that is longer than this value"/>
        <param argument="--mapq" type="integer" value="1" label="Samtools -q parameter (Minimum mapping quality)"/>
        <param argument="--baseq" type="integer" value="20" label="Samtools -Q parameter (Minimum base quality)"/>
        <param argument="--prev_output" type="data" format="tabular" multiple="true" optional="true" label="SRST2 results files to compile" help="Any new results from this run will also be incorporated"/>
    </inputs>
    <outputs> 
        <data name="mlst_results" format="tabular" from_work_dir="output__mlst__mlst_db__results.txt" label="${tool.name} on ${on_string}: MLST Results">
            <filter>use_mlst_db['selector'] == "yes"</filter>
        </data>  
        <collection name="gene_typing" type="list" label="${tool.name} on ${on_string}: Gene typing results files" >
            <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="geneTypingOutput" format="tabular"/>
            <filter>use_gene_db['selector'] == "yes" and use_gene_db['no_gene_details'] is True</filter>
        </collection>         
        <collection name="gene_typing_full" type="list" label="${tool.name} on ${on_string}: Full Gene typing results files" >
            <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="geneTypingOutputFull" format="tabular"/>
            <filter>use_gene_db['selector'] == "yes" and use_gene_db['no_gene_details'] is True</filter>
        </collection>         
        <data name="Compiled_gene_and_mlst_output" format="tabular" from_work_dir="output__compiledResults.txt" label="${tool.name} on ${on_string}: Compiled MLST and Gene databases Results">
        </data>
        <data name="all_consensus" format="fasta" from_work_dir="output.all_consensus_alleles.fasta" label="${tool.name} on ${on_string}: All consensus Results">
            <filter>"report_all_consensus" in output_files_selector</filter>
        </data>              
        <collection name="new_consensus" type="list" label="${tool.name} on ${on_string}: New consensus Results" >
            <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="allelesOutput" format="pileup"/>
            <filter>"report_new_consensus" in output_files_selector</filter>
        </collection>
        <collection name="scores_ofEachAllele" type="list" label="${tool.name} on ${on_string}: Scores for each allele in the database(s)" >
            <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="scoresOutput" format="tabular"/>
            <filter>"save_scores" in output_files_selector</filter>
        </collection>
        <collection name="bowtie2_alignment_output" type="list" label="${tool.name} on ${on_string}: Bowtie2 alignment of reads to each input database" >
            <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="bowtie2Alignments" format="bam"/>
            <filter>input['selector'] == "single" or input['selector'] == "paired"</filter>        
        </collection>
        <collection name="samtools_pileup_alignment" type="list" label="${tool.name} on ${on_string}: Samtools pileup of the alignment to each input database" >
            <discover_datasets pattern="(?P&lt;designation&gt;.+)" directory="samtoolsPileup" format="pileup"/>
            <filter>input['selector'] == "single" or input['selector'] == "paired"</filter>        
        </collection>               
        <data name="log_output" format="tabular" from_work_dir="output.log" label="${tool.name} on ${on_string}: Log file">
            <filter>"log" in output_files_selector</filter>
        </data>             
    </outputs>
    <tests>
    <test expect_num_outputs="10">
        <param name="prob_err" value="0.01"/>
        <param name="max_unaligned_overlap" value="10"/>
        <param name="mapq" value="1"/>
        <param name="baseq" value="20"/>
        <param name="output_files_selector" value="log,save_scores,report_new_consensus,report_all_consensus"/>
        <conditional name="input">
            <param name="selector" value="paired"/>
            <param name="paired_input1" value="ERR024070_1_reduced_forward_reads.fastqsanger.gz"/>
            <param name="paired_input2" value="ERR024070_2_reduced_reverse_reads.fastqsanger.gz"/>
            <param name="merge_paired" value="false"/>
            <param name="read_type" value="q"/>
        </conditional>
        <conditional name="use_mlst_db">
            <param name="selector" value="yes"/>
            <param name="mlst_db" value="Escherichia_coli1R.fasta"/>
            <param name="mlst_definitions" value="profiles_csv"/>
            <param name="mlst_delimiter" value="_"/>
            <param name="mlst_max_mismatch" value="10"/>
            <param name="min_depth" value="5"/>
            <param name="min_edge_depth" value="2"/>
        </conditional>
        <conditional name="use_gene_db">
            <param name="selector" value="yes"/>
            <param name="gene_db" value="ARGannotR.fasta"/>
            <param name="no_gene_details" value="true"/>
            <param name="gene_max_mismatch" value="10"/>
            <param name="min_coverage" value="90"/>
            <param name="max_divergence" value="10"/>
        </conditional>
        <output name="mlst_results">
            <assert_contents>
                <has_text text="fumC"/>
                <has_n_lines n="2"/>
            </assert_contents>
        </output>
        <output_collection name="gene_typing" type="list">
            <element name="output__genes__0-gene_db__results.txt">
                <assert_contents>
                    <has_text text="AmpC1_Ecoli_Bla"/>
                    <has_n_lines n="2"/>
                </assert_contents>
            </element>
        </output_collection>
        <output_collection name="gene_typing_full" type="list">
            <element name="output__fullgenes__0-gene_db__results.txt">
                <assert_contents>
                    <has_text text="AmpC1_Ecoli_Bla"/>
                    <has_n_lines n="2"/>
                </assert_contents>
            </element>
        </output_collection>
        <output name="Compiled_gene_and_mlst_output">
            <assert_contents>
                <has_text text="fumC"/>
                <has_n_lines n="2"/>
            </assert_contents>
        </output>
        <output name="all_consensus">
            <assert_contents>
                <has_text text="49__AmpC1_Ecoli_Bla__AmpC1__1670"/>
                <has_n_lines n="2"/>
            </assert_contents>
        </output>
        <output_collection name="new_consensus" type="list" count="1">
            <element name="49__AmpC1_Ecoli_Bla__AmpC1__1670.output__input.0-gene_db.pileup">
                <assert_contents>
                    <has_text text="49__AmpC1_Ecoli_Bla__AmpC1__1670"/>
                    <has_n_lines n="1196"/>
                </assert_contents>
            </element>
        </output_collection>
        <output_collection name="samtools_pileup_alignment" type="list" count="1">
            <element name="output__input.0-gene_db.pileup">
                <assert_contents>
                    <has_text text="49__AmpC1_Ecoli_Bla__AmpC1__1670"/>
                    <has_n_lines n="1196"/>
                </assert_contents>
            </element>
        </output_collection>
        <output_collection name="bowtie2_alignment_output" type="list" count="1">
            <element name="output__input.0-gene_db.sorted.bam">
                <assert_contents>
                    <has_size value="18500" delta="1000"/>
                </assert_contents>
            </element>
        </output_collection>
        <output name="log_output">
            <assert_contents>
                <has_text text="Building"/>
                <has_n_lines n="52"/>
            </assert_contents>
        </output>
    </test>
    <test expect_num_outputs="7">
        <param name="prob_err" value="0.01"/>
        <param name="max_unaligned_overlap" value="10"/>
        <param name="mapq" value="1"/>
        <param name="baseq" value="20"/>
        <param name="output_files_selector" value="log,save_scores,report_new_consensus,report_all_consensus"/>
        <conditional name="input">
            <param name="selector" value="paired"/>
            <param name="paired_input1" value="ERR024070_1_reduced_forward_reads.fastqsanger.gz"/>
            <param name="paired_input2" value="ERR024070_2_reduced_reverse_reads.fastqsanger.gz"/>
            <param name="merge_paired" value="false"/>
            <param name="read_type" value="q"/>
        </conditional>
        <conditional name="use_mlst_db">
            <param name="selector" value="no"/>
        </conditional>
        <conditional name="use_gene_db">
            <param name="selector" value="no"/>
        </conditional>
        <output name="Compiled_gene_and_mlst_output">
            <assert_contents>
                <has_n_lines n="0"/>
            </assert_contents>
        </output>
        <output name="all_consensus">
            <assert_contents>
                <has_size value="0" delta="0"/>
            </assert_contents>
        </output>
        <output_collection name="new_consensus" type="list" count="0"/>
        <output_collection name="samtools_pileup_alignment" type="list" count="0"/>
        <output_collection name="bowtie2_alignment_output" type="list" count="0"/>
        <output_collection name="scores_ofEachAllele" type="list" count="0"/>
        <output name="log_output">
            <assert_contents>
                <has_text text="Total paired readsets found:1"/>
                <has_n_lines n="4"/>
            </assert_contents>
        </output>
    </test>
    </tests>
    <help><![CDATA[
SRST2
=====
Short Read Sequence Typing for Bacterial Pathogens

This program is designed to take Illumina sequence data, a MLST (Multi Locus Sequence Types) database and/or a database of gene sequences (e.g. resistance genes, virulence genes, etc) and report the presence of STs (Serotypes) and/or reference genes

Read more about the tool: https://holtlab.net/2014/12/27/behind-the-paper-srst2-for-short-read-sequence-typing-of-bacterial-pathogens/

Input
=====
Learn more about all inputs and their formates: https://github.com/katholt/srst2#input-read-formats-and-options

Output
======
Learn more about all outputs: https://github.com/katholt/srst2#output-files
    ]]></help> 
    <citations>
        <citation type="doi">10.1186/s13073-014-0090-6</citation>
    </citations>
 </tool>